diff options
| author | Stephen Rothwell <sfr@canb.auug.org.au> | 2021-09-30 11:40:07 +1000 |
|---|---|---|
| committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2021-09-30 11:40:07 +1000 |
| commit | b9e01d4150dad935c0e387f399e13b03a917a2fe (patch) | |
| tree | 5c710ad02f2ace9f2efb71e56632892776f4d60b | |
| parent | 88bdd2a7e3bbfc4154904eaf7102cbed2cb59b28 (diff) | |
| parent | ef91abfb20c743c0cbe98e4351cd0ce05c81340a (diff) | |
| download | devel-b9e01d4150dad935c0e387f399e13b03a917a2fe.tar.gz | |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
# Conflicts:
# drivers/net/phy/bcm7xxx.c
376 files changed, 14949 insertions, 5977 deletions
diff --git a/Documentation/ABI/testing/sysfs-timecard b/Documentation/ABI/testing/sysfs-timecard new file mode 100644 index 00000000000000..97f6773794a511 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-timecard @@ -0,0 +1,174 @@ +What: /sys/class/timecard/ +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This directory contains files and directories + providing a standardized interface to the ancillary + features of the OpenCompute timecard. + +What: /sys/class/timecard/ocpN/ +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This directory contains the attributes of the Nth timecard + registered. + +What: /sys/class/timecard/ocpN/available_clock_sources +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RO) The list of available time sources that the PHC + uses for clock adjustments. + + ==== ================================================= + NONE no adjustments + PPS adjustments come from the PPS1 selector (default) + TOD adjustments from the GNSS/TOD module + IRIG adjustments from external IRIG-B signal + DCF adjustments from external DCF signal + ==== ================================================= + +What: /sys/class/timecard/ocpN/available_sma_inputs +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RO) Set of available destinations (sinks) for a SMA + input signal. + + ===== ================================================ + 10Mhz signal is used as the 10Mhz reference clock + PPS1 signal is sent to the PPS1 selector + PPS2 signal is sent to the PPS2 selector + TS1 signal is sent to timestamper 1 + TS2 signal is sent to timestamper 2 + IRIG signal is sent to the IRIG-B module + DCF signal is sent to the DCF module + ===== ================================================ + +What: /sys/class/timecard/ocpN/available_sma_outputs +Date: May 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RO) Set of available sources for a SMA output signal. + + ===== ================================================ + 10Mhz output is from the 10Mhz reference clock + PHC output PPS is from the PHC clock + MAC output PPS is from the Miniature Atomic Clock + GNSS output PPS is from the GNSS module + GNSS2 output PPS is from the second GNSS module + IRIG output is from the PHC, in IRIG-B format + DCF output is from the PHC, in DCF format + ===== ================================================ + +What: /sys/class/timecard/ocpN/clock_source +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RW) Contains the current synchronization source used by + the PHC. May be changed by writing one of the listed + values from the available_clock_sources attribute set. + +What: /sys/class/timecard/ocpN/gnss_sync +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RO) Indicates whether a valid GNSS signal is received, + or when the signal was lost. + +What: /sys/class/timecard/ocpN/i2c +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This optional attribute links to the associated i2c device. + +What: /sys/class/timecard/ocpN/irig_b_mode +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RW) An integer from 0-7 indicating the timecode format + of the IRIG-B output signal: B00<n> + +What: /sys/class/timecard/ocpN/pps +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This optional attribute links to the associated PPS device. + +What: /sys/class/timecard/ocpN/ptp +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This attribute links to the associated PTP device. + +What: /sys/class/timecard/ocpN/serialnum +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RO) Provides the serial number of the timecard. + +What: /sys/class/timecard/ocpN/sma1 +What: /sys/class/timecard/ocpN/sma2 +What: /sys/class/timecard/ocpN/sma3 +What: /sys/class/timecard/ocpN/sma4 +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RW) These attributes specify the direction of the signal + on the associated SMA connectors, and also the signal sink + or source. + + The display format of the attribute is a space separated + list of signals, prefixed by the input/output direction. + + The signal direction may be changed (if supported) by + prefixing the signal list with either "in:" or "out:". + If neither prefix is present, then the direction is unchanged. + + The output signal may be changed by writing one of the listed + values from the available_sma_outputs attribute set. + + The input destinations may be changed by writing multiple + values from the available_sma_inputs attribute set, + separated by spaces. If there are duplicated input + destinations between connectors, the lowest numbered SMA + connector is given priority. + + Note that not all input combinations may make sense. + + The 10Mhz reference clock input is currently only valid + on SMA1 and may not be combined with other destination sinks. + +What: /sys/class/timecard/ocpN/ts_window_adjust +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RW) When retrieving the PHC with the PTP SYS_OFFSET_EXTENDED + ioctl, a system timestamp is made before and after the PHC + time is retrieved. The midpoint between the two system + timestamps is usually taken to be the SYS time associated + with the PHC time. This estimate may be wrong, as it depends + on PCI latencies, and when the PHC time was latched + + The attribute value reduces the end timestamp by the given + number of nanoseconds, so the computed midpoint matches the + retrieved PHC time. + + The initial value is set based on measured PCI latency and + the estimated point where the FPGA latches the PHC time. This + value may be changed by writing an unsigned integer. + +What: /sys/class/timecard/ocpN/ttyGNSS +What: /sys/class/timecard/ocpN/ttyGNSS2 +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: These optional attributes link to the TTY serial ports + associated with the GNSS devices. + +What: /sys/class/timecard/ocpN/ttyMAC +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This optional attribute links to the TTY serial port + associated with the Miniature Atomic Clock. + +What: /sys/class/timecard/ocpN/ttyNMEA +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: This optional attribute links to the TTY serial port + which outputs the PHC time in NMEA ZDA format. + +What: /sys/class/timecard/ocpN/utc_tai_offset +Date: September 2021 +Contact: Jonathan Lemon <jonathan.lemon@gmail.com> +Description: (RW) The DCF and IRIG output signals are in UTC, while the + TimeCard operates on TAI. This attribute allows setting the + offset in seconds, which is added to the TAI timebase for + these formats. + + The offset may be changed by writing an unsigned integer. diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 846354cd2d69eb..1bfe4072f5fca7 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -85,6 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id #define BTF_KIND_VAR 14 /* Variable */ #define BTF_KIND_DATASEC 15 /* Section */ #define BTF_KIND_FLOAT 16 /* Floating point */ + #define BTF_KIND_TAG 17 /* Tag */ Note that the type section encodes debug info, not just pure types. ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram. @@ -106,7 +107,7 @@ Each type contains the following common data:: * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC and FUNC_PROTO. + * FUNC, FUNC_PROTO and TAG. * "type" is a type_id referring to another type. */ union { @@ -465,6 +466,32 @@ map definition. No additional type data follow ``btf_type``. +2.2.17 BTF_KIND_TAG +~~~~~~~~~~~~~~~~~~~ + +``struct btf_type`` encoding requirement: + * ``name_off``: offset to a non-empty string + * ``info.kind_flag``: 0 + * ``info.kind``: BTF_KIND_TAG + * ``info.vlen``: 0 + * ``type``: ``struct``, ``union``, ``func`` or ``var`` + +``btf_type`` is followed by ``struct btf_tag``.:: + + struct btf_tag { + __u32 component_idx; + }; + +The ``name_off`` encodes btf_tag attribute string. +The ``type`` should be ``struct``, ``union``, ``func`` or ``var``. +For ``var`` type, ``btf_tag.component_idx`` must be ``-1``. +For the other three types, if the btf_tag attribute is +applied to the ``struct``, ``union`` or ``func`` itself, +``btf_tag.component_idx`` must be ``-1``. Otherwise, +the attribute is applied to a ``struct``/``union`` member or +a ``func`` argument, and ``btf_tag.component_idx`` should be a +valid index (starting from 0) pointing to a member or an argument. + 3. BTF Kernel API ***************** diff --git a/Documentation/devicetree/bindings/net/lantiq,etop-xway.yaml b/Documentation/devicetree/bindings/net/lantiq,etop-xway.yaml new file mode 100644 index 00000000000000..437502c5ca9626 --- /dev/null +++ b/Documentation/devicetree/bindings/net/lantiq,etop-xway.yaml @@ -0,0 +1,69 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/lantiq,etop-xway.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Lantiq Xway ETOP Ethernet driver + +maintainers: + - John Crispin <john@phrozen.org> + +properties: + $nodename: + pattern: "^ethernet@[0-9a-f]+$" + + compatible: + const: lantiq,etop-xway + + reg: + maxItems: 1 + + interrupts: + items: + - description: TX interrupt + - description: RX interrupt + + interrupt-names: + items: + - const: tx + - const: rx + + lantiq,tx-burst-length: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + TX programmable burst length. + enum: [2, 4, 8] + + lantiq,rx-burst-length: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + RX programmable burst length. + enum: [2, 4, 8] + + phy-mode: true + +required: + - compatible + - reg + - interrupt-parent + - interrupts + - interrupt-names + - lantiq,tx-burst-length + - lantiq,rx-burst-length + - phy-mode + +additionalProperties: false + +examples: + - | + ethernet@e180000 { + compatible = "lantiq,etop-xway"; + reg = <0xe180000 0x40000>; + interrupt-parent = <&icu0>; + interrupts = <73>, <78>; + interrupt-names = "tx", "rx"; + lantiq,tx-burst-length = <8>; + lantiq,rx-burst-length = <8>; + phy-mode = "rmii"; + }; diff --git a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt deleted file mode 100644 index 5ff5e68bbbb691..00000000000000 --- a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt +++ /dev/null @@ -1,21 +0,0 @@ -Lantiq xRX200 GSWIP PMAC Ethernet driver -================================== - -Required properties: - -- compatible : "lantiq,xrx200-net" for the PMAC of the embedded - : GSWIP in the xXR200 -- reg : memory range of the PMAC core inside of the GSWIP core -- interrupts : TX and RX DMA interrupts. Use interrupt-names "tx" for - : the TX interrupt and "rx" for the RX interrupt. - -Example: - -ethernet@e10b308 { - #address-cells = <1>; - #size-cells = <0>; - compatible = "lantiq,xrx200-net"; - reg = <0xe10b308 0xcf8>; - interrupts = <73>, <72>; - interrupt-names = "tx", "rx"; -}; diff --git a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml new file mode 100644 index 00000000000000..16d831f22063d5 --- /dev/null +++ b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.yaml @@ -0,0 +1,75 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/lantiq,xrx200-net.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Lantiq xRX200 GSWIP PMAC Ethernet driver + +maintainers: + - Hauke Mehrtens <hauke@hauke-m.de> + +properties: + $nodename: + pattern: "^ethernet@[0-9a-f]+$" + + compatible: + const: lantiq,xrx200-net + + reg: + maxItems: 1 + + interrupts: + items: + - description: TX interrupt + - description: RX interrupt + + interrupt-names: + items: + - const: tx + - const: rx + + lantiq,tx-burst-length: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + TX programmable burst length. + enum: [2, 4, 8] + + lantiq,rx-burst-length: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + RX programmable burst length. + enum: [2, 4, 8] + + '#address-cells': + const: 1 + + '#size-cells': + const: 0 + +required: + - compatible + - reg + - interrupt-parent + - interrupts + - interrupt-names + - lantiq,tx-burst-length + - lantiq,rx-burst-length + - "#address-cells" + - "#size-cells" + +additionalProperties: false + +examples: + - | + ethernet@e10b308 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-net"; + reg = <0xe10b308 0xcf8>; + interrupt-parent = <&icu0>; + interrupts = <73>, <72>; + interrupt-names = "tx", "rx"; + lantiq,tx-burst-length = <8>; + lantiq,rx-burst-length = <8>; + }; diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index 45b5f8b341df1b..19ffd561cf4fd3 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -47,3 +47,4 @@ parameters, info versions, and other features it supports. ti-cpsw-switch am65-nuss-cpsw-switch prestera + iosm diff --git a/Documentation/networking/devlink/iosm.rst b/Documentation/networking/devlink/iosm.rst new file mode 100644 index 00000000000000..dd460c1c15cd6f --- /dev/null +++ b/Documentation/networking/devlink/iosm.rst @@ -0,0 +1,182 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +iosm devlink support +==================== + +This document describes the devlink features implemented by the ``iosm`` +device driver. + +Parameters +========== + +The ``iosm`` driver implements the following driver-specific parameters. + +.. list-table:: Driver-specific parameters implemented + :widths: 5 5 5 85 + + * - Name + - Type + - Mode + - Description + * - ``erase_full_flash`` + - u8 + - runtime + - erase_full_flash parameter is used to check if full erase is required for + the device during firmware flashing. + If set, Full nand erase command will be sent to the device. By default, + only conditional erase support is enabled. + * - ``download_region`` + - u8 + - runtime + - download_region parameter is used to identify if we are flashing the + loadmap/region file during the firmware flashing. + * - ``address`` + - u32 + - runtime + - address parameter is used to send the address information of the + loadmap/region file which is required during the firmware flashing + process. Each region file has be flashed to its respective flash address. + * - ``region_count`` + - u8 + - runtime + - region_count parameter is used to inform the driver on how many total + loadmap/region files are present in modem firmware image that has to be + flashed. + + +Flash Update +============ + +The ``iosm`` driver implements support for flash update using the +``devlink-flash`` interface. + +It supports updating the device flash using a combined flash image which contains +the Bootloader images and other modem software images. + +The driver uses DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT to identify type of +firmware image that need to be flashed as requested by user space application. +Supported firmware image types. + +.. list-table:: Firmware Image types + :widths: 15 85 + + * - Name + - Description + * - ``PSI RAM`` + - Primary Signed Image + * - ``EBL`` + - External Bootloader + * - ``FLS`` + - Modem Software Image + +PSI RAM and EBL are the RAM images which are injected to the device when the +device is in BOOT ROM stage. Once this is successful, the actual modem firmware +image is flashed to the device. The modem software image contains multiple files +each having one secure bin file and at least one Loadmap/Region file. For flashing +these files, appropriate commands are sent to the modem device along with the +data required for flashing. The data like region count and address of each region +has to be passed to the driver using the devlink param command. + +If the device has to be fully erased before firmware flashing, user application +need to set the erase_full_flash parameter using devlink param command. +By default, conditional erase feature is supported. + +Flash Commands: +=============== +1) When modem is in Boot ROM stage, user can use below command to inject PSI RAM +image using devlink flash command. + +$ devlink dev flash pci/0000:02:00.0 file <PSI_RAM_File_name> component PSI + +2) If user want to do a full erase, below command need to be issued to set the +erase full flash param (To be set only if full erase required). + +$ devlink dev param set pci/0000:02:00.0 name erase_full_flash value true cmode runtime + +3) Inject EBL after the modem is in PSI stage. +$ devlink dev flash pci/0000:02:00.0 file <EBL_File_name> component EBL + +4) Once EBL is injected successfully, then the actual firmware flashing takes +place. Below is the sequence of commands used for each of the firmware images. + +a) Flash secure bin file. +$ devlink dev flash pci/0000:02:00.0 file <Secure_bin_file_name> component FLS + +b) Flashing the Loadmap/Region file +$ devlink dev param set pci/0000:02:00.0 name region_count value 1 cmode runtime + +$ devlink dev param set pci/0000:02:00.0 name download_region value true cmode runtime + +$ devlink dev param set pci/0000:02:00.0 name address value <Nand_address> cmode runtime + +$ devlink dev flash pci/0000:02:00.0 file <Load_map_file_name> component FLS + +Regions +======= + +The ``iosm`` driver supports dumping the coredump logs. + +In case a firmware encounters an exception, a snapshot will be taken by the +driver. Following regions are accessed for device internal data. + +.. list-table:: Regions implemented + :widths: 15 85 + + * - Name + - Description + * - ``report.json`` + - The summary of exception details logged as part of this region. + * - ``coredump.fcd`` + - This region contains the details related to the exception occurred in the + device (RAM dump). + * - ``cdd.log`` + - This region contains the logs related to the modem CDD driver. + * - ``eeprom.bin`` + - This region contains the eeprom logs. + * - ``bootcore_trace.bin`` + - This region contains the current instance of bootloader logs. + * - ``bootcore_prev_trace.bin`` + - This region contains the previous instance of bootloader logs. + + +Region commands +=============== + +$ devlink region show + +$ devlink region new pci/0000:02:00.0/report.json + +$ devlink region dump pci/0000:02:00.0/report.json snapshot 0 + +$ devlink region del pci/0000:02:00.0/report.json snapshot 0 + +$ devlink region new pci/0000:02:00.0/coredump.fcd + +$ devlink region dump pci/0000:02:00.0/coredump.fcd snapshot 1 + +$ devlink region del pci/0000:02:00.0/coredump.fcd snapshot 1 + +$ devlink region new pci/0000:02:00.0/cdd.log + +$ devlink region dump pci/0000:02:00.0/cdd.log snapshot 2 + +$ devlink region del pci/0000:02:00.0/cdd.log snapshot 2 + +$ devlink region new pci/0000:02:00.0/eeprom.bin + +$ devlink region dump pci/0000:02:00.0/eeprom.bin snapshot 3 + +$ devlink region del pci/0000:02:00.0/eeprom.bin snapshot 3 + +$ devlink region new pci/0000:02:00.0/bootcore_trace.bin + +$ devlink region dump pci/0000:02:00.0/bootcore_trace.bin snapshot 4 + +$ devlink region del pci/0000:02:00.0/bootcore_trace.bin snapshot 4 + +$ devlink region new pci/0000:02:00.0/bootcore_prev_trace.bin + +$ devlink region dump pci/0000:02:00.0/bootcore_prev_trace.bin snapshot 5 + +$ devlink region del pci/0000:02:00.0/bootcore_prev_trace.bin snapshot 5 diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index d91ab28718d493..16b8bf72feaf42 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -989,14 +989,6 @@ tcp_challenge_ack_limit - INTEGER in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks) Default: 1000 -tcp_rx_skb_cache - BOOLEAN - Controls a per TCP socket cache of one skb, that might help - performance of some workloads. This might be dangerous - on systems with a lot of TCP sockets, since it increases - memory usage. - - Default: 0 (disabled) - UDP variables ============= diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst index 6100cdc220f6b9..2c54b029f99037 100644 --- a/Documentation/networking/mctp.rst +++ b/Documentation/networking/mctp.rst @@ -211,3 +211,62 @@ remote address is already known, or the message does not require a reply. Like the send calls, sockets will only receive responses to requests they have sent (TO=1) and may only respond (TO=0) to requests they have received. + +Kernel internals +================ + +There are a few possible packet flows in the MCTP stack: + +1. local TX to remote endpoint, message <= MTU:: + + sendmsg() + -> mctp_local_output() + : route lookup + -> rt->output() (== mctp_route_output) + -> dev_queue_xmit() + +2. local TX to remote endpoint, message > MTU:: + + sendmsg() + -> mctp_local_output() + -> mctp_do_fragment_route() + : creates packet-sized skbs. For each new skb: + -> rt->output() (== mctp_route_output) + -> dev_queue_xmit() + +3. remote TX to local endpoint, single-packet message:: + + mctp_pkttype_receive() + : route lookup + -> rt->output() (== mctp_route_input) + : sk_key lookup + -> sock_queue_rcv_skb() + +4. remote TX to local endpoint, multiple-packet message:: + + mctp_pkttype_receive() + : route lookup + -> rt->output() (== mctp_route_input) + : sk_key lookup + : stores skb in struct sk_key->reasm_head + + mctp_pkttype_receive() + : route lookup + -> rt->output() (== mctp_route_input) + : sk_key lookup + : finds existing reassembly in sk_key->reasm_head + : appends new fragment + -> sock_queue_rcv_skb() + +Key refcounts +------------- + + * keys are refed by: + + - a skb: during route output, stored in ``skb->cb``. + + - netns and sock lists. + + * keys can be associated with a device, in which case they hold a + reference to the dev (set through ``key->dev``, counted through + ``dev->key_count``). Multiple keys can reference the device. diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h index 8218a1356bd8bf..31ca9151b539d5 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h +++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h @@ -45,6 +45,6 @@ extern void ltq_dma_close(struct ltq_dma_channel *ch); extern void ltq_dma_alloc_tx(struct ltq_dma_channel *ch); extern void ltq_dma_alloc_rx(struct ltq_dma_channel *ch); extern void ltq_dma_free(struct ltq_dma_channel *ch); -extern void ltq_dma_init_port(int p); +extern void ltq_dma_init_port(int p, int tx_burst, int rx_burst); #endif diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 63dccb2ed08b28..f8eedeb15f1829 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -11,6 +11,7 @@ #include <linux/export.h> #include <linux/spinlock.h> #include <linux/clk.h> +#include <linux/delay.h> #include <linux/err.h> #include <linux/of.h> @@ -30,6 +31,7 @@ #define LTQ_DMA_PCTRL 0x44 #define LTQ_DMA_IRNEN 0xf4 +#define DMA_ID_CHNR GENMASK(26, 20) /* channel number */ #define DMA_DESCPT BIT(3) /* descriptor complete irq */ #define DMA_TX BIT(8) /* TX channel direction */ #define DMA_CHAN_ON BIT(0) /* channel on / off bit */ @@ -39,8 +41,11 @@ #define DMA_IRQ_ACK 0x7e /* IRQ status register */ #define DMA_POLL BIT(31) /* turn on channel polling */ #define DMA_CLK_DIV4 BIT(6) /* polling clock divider */ -#define DMA_2W_BURST BIT(1) /* 2 word burst length */ -#define DMA_MAX_CHANNEL 20 /* the soc has 20 channels */ +#define DMA_PCTRL_2W_BURST 0x1 /* 2 word burst length */ +#define DMA_PCTRL_4W_BURST 0x2 /* 4 word burst length */ +#define DMA_PCTRL_8W_BURST 0x3 /* 8 word burst length */ +#define DMA_TX_BURST_SHIFT 4 /* tx burst shift */ +#define DMA_RX_BURST_SHIFT 2 /* rx burst shift */ #define DMA_ETOP_ENDIANNESS (0xf << 8) /* endianness swap etop channels */ #define DMA_WEIGHT (BIT(17) | BIT(16)) /* default channel wheight */ @@ -177,7 +182,7 @@ ltq_dma_free(struct ltq_dma_channel *ch) EXPORT_SYMBOL_GPL(ltq_dma_free); void -ltq_dma_init_port(int p) +ltq_dma_init_port(int p, int tx_burst, int rx_burst) { ltq_dma_w32(p, LTQ_DMA_PS); switch (p) { @@ -186,15 +191,44 @@ ltq_dma_init_port(int p) * Tell the DMA engine to swap the endianness of data frames and * drop packets if the channel arbitration fails. */ - ltq_dma_w32_mask(0, DMA_ETOP_ENDIANNESS | DMA_PDEN, + ltq_dma_w32_mask(0, (DMA_ETOP_ENDIANNESS | DMA_PDEN), LTQ_DMA_PCTRL); break; - case DMA_PORT_DEU: - ltq_dma_w32((DMA_2W_BURST << 4) | (DMA_2W_BURST << 2), + default: + break; + } + + switch (rx_burst) { + case 8: + ltq_dma_w32_mask(0x0c, (DMA_PCTRL_8W_BURST << DMA_RX_BURST_SHIFT), + LTQ_DMA_PCTRL); + break; + case 4: + ltq_dma_w32_mask(0x0c, (DMA_PCTRL_4W_BURST << DMA_RX_BURST_SHIFT), + LTQ_DMA_PCTRL); + break; + case 2: + ltq_dma_w32_mask(0x0c, (DMA_PCTRL_2W_BURST << DMA_RX_BURST_SHIFT), LTQ_DMA_PCTRL); break; + default: + break; + } + switch (tx_burst) { + case 8: + ltq_dma_w32_mask(0x30, (DMA_PCTRL_8W_BURST << DMA_TX_BURST_SHIFT), + LTQ_DMA_PCTRL); + break; + case 4: + ltq_dma_w32_mask(0x30, (DMA_PCTRL_4W_BURST << DMA_TX_BURST_SHIFT), + LTQ_DMA_PCTRL); + break; + case 2: + ltq_dma_w32_mask(0x30, (DMA_PCTRL_2W_BURST << DMA_TX_BURST_SHIFT), + LTQ_DMA_PCTRL); + break; default: break; } @@ -206,7 +240,7 @@ ltq_dma_init(struct platform_device *pdev) { struct clk *clk; struct resource *res; - unsigned id; + unsigned int id, nchannels; int i; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -222,21 +256,24 @@ ltq_dma_init(struct platform_device *pdev) clk_enable(clk); ltq_dma_w32_mask(0, DMA_RESET, LTQ_DMA_CTRL); + usleep_range(1, 10); + /* disable all interrupts */ ltq_dma_w32(0, LTQ_DMA_IRNEN); /* reset/configure each channel */ - for (i = 0; i < DMA_MAX_CHANNEL; i++) { + id = ltq_dma_r32(LTQ_DMA_ID); + nchannels = ((id & DMA_ID_CHNR) >> 20); + for (i = 0; i < nchannels; i++) { ltq_dma_w32(i, LTQ_DMA_CS); ltq_dma_w32(DMA_CHAN_RST, LTQ_DMA_CCTRL); ltq_dma_w32(DMA_POLL | DMA_CLK_DIV4, LTQ_DMA_CPOLL); ltq_dma_w32_mask(DMA_CHAN_ON, 0, LTQ_DMA_CCTRL); } - id = ltq_dma_r32(LTQ_DMA_ID); dev_info(&pdev->dev, "Init done - hw rev: %X, ports: %d, channels: %d\n", - id & 0x1f, (id >> 16) & 0xf, id >> 20); + id & 0x1f, (id >> 16) & 0xf, nchannels); return 0; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d030..1248fc1937f82f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2143,19 +2143,19 @@ static __initconst const u64 knl_hw_cache_extra_regs * However, there are some cases which may change PEBS status, e.g. PMI * throttle. The PEBS_ENABLE should be updated where the status changes. */ -static void __intel_pmu_disable_all(void) +static __always_inline void __intel_pmu_disable_all(bool bts) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); } -static void intel_pmu_disable_all(void) +static __always_inline void intel_pmu_disable_all(void) { - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); intel_pmu_pebs_disable_all(); intel_pmu_lbr_disable_all(); } @@ -2186,6 +2186,49 @@ static void intel_pmu_enable_all(int added) __intel_pmu_enable_all(added, false); } +static noinline int +__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, + unsigned int cnt, unsigned long flags) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + intel_pmu_lbr_read(); + cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr); + + memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt); + intel_pmu_enable_all(0); + local_irq_restore(flags); + return cnt; +} + +static int +intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + +static int +intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_arch_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + /* * Workaround for: * Intel Errata AAK100 (model 26) @@ -2929,7 +2972,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); cpuc->enabled = 0; - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); status = intel_pmu_get_status(); @@ -6283,9 +6326,21 @@ __init int intel_pmu_init(void) x86_pmu.lbr_nr = 0; } - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr) { pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + /* only support branch_stack snapshot for perfmon >= v2 */ + if (x86_pmu.disable_all == intel_pmu_disable_all) { + if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_arch_branch_stack); + } else { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_branch_stack); + } + } + } + intel_pmu_check_extra_regs(x86_pmu.extra_regs); /* Support full width counters using alternative MSR range */ diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8647713276a734..ac5991fea9ee3f 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1301,7 +1301,7 @@ void intel_pmu_pebs_disable_all(void) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + __intel_pmu_pebs_disable_all(); } static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 9e6d6eaeb4cb60..6b72e9b55c69cf 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi) wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN); } -static void __intel_pmu_lbr_disable(void) -{ - u64 debugctl; - - if (static_cpu_has(X86_FEATURE_ARCH_LBR)) { - wrmsrl(MSR_ARCH_LBR_CTL, 0); - return; - } - - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); - debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); -} - void intel_pmu_lbr_reset_32(void) { int i; @@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (cpuc->lbr_users && !vlbr_exclude_host()) + if (cpuc->lbr_users && !vlbr_exclude_host()) { + if (static_cpu_has(X86_FEATURE_ARCH_LBR)) + return __intel_pmu_arch_lbr_disable(); + __intel_pmu_lbr_disable(); + } } void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e59..0e3e596e33cdd3 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1240,6 +1240,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event) return intel_pmu_has_bts_period(event, hwc->sample_period); } +static __always_inline void __intel_pmu_pebs_disable_all(void) +{ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); +} + +static __always_inline void __intel_pmu_arch_lbr_disable(void) +{ + wrmsrl(MSR_ARCH_LBR_CTL, 0); +} + +static __always_inline void __intel_pmu_lbr_disable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9ea57389c554b7..576ef1a6954a6c 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1070,41 +1070,34 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; case BPF_ALU | BPF_MUL | BPF_K: - case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU64 | BPF_MUL | BPF_K: - case BPF_ALU64 | BPF_MUL | BPF_X: - { - bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_2mod(0x48, dst_reg, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); - if (dst_reg != BPF_REG_0) - EMIT1(0x50); /* push rax */ - if (dst_reg != BPF_REG_3) - EMIT1(0x52); /* push rdx */ + if (is_imm8(imm32)) + /* imul dst_reg, dst_reg, imm8 */ + EMIT3(0x6B, add_2reg(0xC0, dst_reg, dst_reg), + imm32); + else + /* imul dst_reg, dst_reg, imm32 */ + EMIT2_off32(0x69, + add_2reg(0xC0, dst_reg, dst_reg), + imm32); + break; - /* mov r11, dst_reg */ - EMIT_mov(AUX_REG, dst_reg); + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_X: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_2mod(0x48, src_reg, dst_reg)); + else if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, src_reg, dst_reg)); - if (BPF_SRC(insn->code) == BPF_X) - emit_mov_reg(&prog, is64, BPF_REG_0, src_reg); - else - emit_mov_imm32(&prog, is64, BPF_REG_0, imm32); - - if (is64) - EMIT1(add_1mod(0x48, AUX_REG)); - else if (is_ereg(AUX_REG)) - EMIT1(add_1mod(0x40, AUX_REG)); - /* mul(q) r11 */ - EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); - - if (dst_reg != BPF_REG_3) - EMIT1(0x5A); /* pop rdx */ - if (dst_reg != BPF_REG_0) { - /* mov dst_reg, rax */ - EMIT_mov(dst_reg, BPF_REG_0); - EMIT1(0x58); /* pop rax */ - } + /* imul dst_reg, src_reg */ + EMIT3(0x0F, 0xAF, add_2reg(0xC0, src_reg, dst_reg)); break; - } + /* Shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 604f541126654f..06279ba64cc8ea 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1222,7 +1222,7 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, return; /* Enable flow control on BCM5301x's CPU port */ - if (is5301x(dev) && port == dev->cpu_port) + if (is5301x(dev) && dsa_is_cpu_port(ds, port)) tx_pause = rx_pause = true; if (phydev->pause) { @@ -1291,12 +1291,6 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, return; } } - } else if (is5301x(dev)) { - if (port != dev->cpu_port) { - b53_force_port_config(dev, dev->cpu_port, 2000, - DUPLEX_FULL, true, true); - b53_force_link(dev, dev->cpu_port, 1); - } } /* Re-negotiate EEE if it was enabled already */ @@ -2302,33 +2296,30 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM5325_DEVICE_ID, .dev_name = "BCM5325", .vlans = 16, - .enabled_ports = 0x1f, + .enabled_ports = 0x3f, .arl_bins = 2, .arl_buckets = 1024, .imp_port = 5, - .cpu_port = B53_CPU_PORT_25, .duplex_reg = B53_DUPLEX_STAT_FE, }, { .chip_id = BCM5365_DEVICE_ID, .dev_name = "BCM5365", .vlans = 256, - .enabled_ports = 0x1f, + .enabled_ports = 0x3f, .arl_bins = 2, .arl_buckets = 1024, .imp_port = 5, - .cpu_port = B53_CPU_PORT_25, .duplex_reg = B53_DUPLEX_STAT_FE, }, { .chip_id = BCM5389_DEVICE_ID, .dev_name = "BCM5389", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x11f, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2338,11 +2329,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM5395_DEVICE_ID, .dev_name = "BCM5395", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x11f, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2352,11 +2342,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM5397_DEVICE_ID, .dev_name = "BCM5397", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x11f, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS_9798, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2366,11 +2355,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM5398_DEVICE_ID, .dev_name = "BCM5398", .vlans = 4096, - .enabled_ports = 0x7f, + .enabled_ports = 0x17f, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS_9798, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2380,12 +2368,11 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM53115_DEVICE_ID, .dev_name = "BCM53115", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x11f, .arl_bins = 4, .arl_buckets = 1024, .vta_regs = B53_VTA_REGS, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, @@ -2394,11 +2381,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM53125_DEVICE_ID, .dev_name = "BCM53125", .vlans = 4096, - .enabled_ports = 0xff, + .enabled_ports = 0x1ff, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2412,7 +2398,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2426,7 +2411,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS_63XX, .duplex_reg = B53_DUPLEX_STAT_63XX, .jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX, @@ -2436,11 +2420,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM53010_DEVICE_ID, .dev_name = "BCM53010", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x1bf, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2454,7 +2437,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2468,7 +2450,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2478,11 +2459,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM53018_DEVICE_ID, .dev_name = "BCM53018", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x1bf, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2492,11 +2472,10 @@ static const struct b53_chip_data b53_switch_chips[] = { .chip_id = BCM53019_DEVICE_ID, .dev_name = "BCM53019", .vlans = 4096, - .enabled_ports = 0x1f, + .enabled_ports = 0x1bf, .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT_25, /* TODO: auto detect */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2510,7 +2489,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2524,7 +2502,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2539,7 +2516,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 256, .imp_port = 8, - .cpu_port = 8, /* TODO: ports 4, 5, 8 */ .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2553,7 +2529,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 1024, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2567,7 +2542,6 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_bins = 4, .arl_buckets = 256, .imp_port = 8, - .cpu_port = B53_CPU_PORT, .vta_regs = B53_VTA_REGS, .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, @@ -2593,7 +2567,6 @@ static int b53_switch_init(struct b53_device *dev) dev->vta_regs[2] = chip->vta_regs[2]; dev->jumbo_pm_reg = chip->jumbo_pm_reg; dev->imp_port = chip->imp_port; - dev->cpu_port = chip->cpu_port; dev->num_vlans = chip->vlans; dev->num_arl_bins = chip->arl_bins; dev->num_arl_buckets = chip->arl_buckets; @@ -2625,16 +2598,8 @@ static int b53_switch_init(struct b53_device *dev) break; #endif } - } else if (dev->chip_id == BCM53115_DEVICE_ID) { - u64 strap_value; - - b53_read48(dev, B53_STAT_PAGE, B53_STRAP_VALUE, &strap_value); - /* use second IMP port if GMII is enabled */ - if (strap_value & SV_GMII_CTRL_115) - dev->cpu_port = 5; } - dev->enabled_ports |= BIT(dev->cpu_port); dev->num_ports = fls(dev->enabled_ports); dev->ds->num_ports = min_t(unsigned int, dev->num_ports, DSA_MAX_PORTS); diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 959a52d41f0a17..544101e74bca18 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -124,7 +124,6 @@ struct b53_device { /* used ports mask */ u16 enabled_ports; unsigned int imp_port; - unsigned int cpu_port; /* connect specific data */ u8 current_page; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 7578a5c38df597..a86ddc4bb897e1 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -667,7 +667,9 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) if (priv->int_phy_mask & BIT(port)) return priv->hw_params.gphy_rev; else - return 0; + return PHY_BRCM_AUTO_PWRDWN_ENABLE | + PHY_BRCM_DIS_TXCRXC_NOENRGY | + PHY_BRCM_IDDQ_SUSPEND; } static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index a3a9636430d6c0..01c01bd0c8549d 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -955,8 +955,10 @@ static int felix_parse_dt(struct felix *felix, phy_interface_t *port_phy_modes) switch_node = dev->of_node; ports_node = of_get_child_by_name(switch_node, "ports"); + if (!ports_node) + ports_node = of_get_child_by_name(switch_node, "ethernet-ports"); if (!ports_node) { - dev_err(dev, "Incorrect bindings: absent \"ports\" node\n"); + dev_err(dev, "Incorrect bindings: absent \"ports\" or \"ethernet-ports\" node\n"); return -ENODEV; } diff --git a/drivers/net/dsa/realtek-smi-core.h b/drivers/net/dsa/realtek-smi-core.h index fcf465f7f92266..214f710d7dd528 100644 --- a/drivers/net/dsa/realtek-smi-core.h +++ b/drivers/net/dsa/realtek-smi-core.h @@ -129,9 +129,6 @@ int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port, int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable); int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable); int rtl8366_reset_vlan(struct realtek_smi *smi); -int rtl8366_init_vlan(struct realtek_smi *smi); -int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, - struct netlink_ext_ack *extack); int rtl8366_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack); diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 75897a3690969f..bdb8d8d348807f 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -292,89 +292,6 @@ int rtl8366_reset_vlan(struct realtek_smi *smi) } EXPORT_SYMBOL_GPL(rtl8366_reset_vlan); -int rtl8366_init_vlan(struct realtek_smi *smi) -{ - int port; - int ret; - - ret = rtl8366_reset_vlan(smi); - if (ret) - return ret; - - /* Loop over the available ports, for each port, associate - * it with the VLAN (port+1) - */ - for (port = 0; port < smi->num_ports; port++) { - u32 mask; - - if (port == smi->cpu_port) - /* For the CPU port, make all ports members of this - * VLAN. - */ - mask = GENMASK((int)smi->num_ports - 1, 0); - else - /* For all other ports, enable itself plus the - * CPU port. - */ - mask = BIT(port) | BIT(smi->cpu_port); - - /* For each port, set the port as member of VLAN (port+1) - * and untagged, except for the CPU port: the CPU port (5) is - * member of VLAN 6 and so are ALL the other ports as well. - * Use filter 0 (no filter). - */ - dev_info(smi->dev, "VLAN%d port mask for port %d, %08x\n", - (port + 1), port, mask); - ret = rtl8366_set_vlan(smi, (port + 1), mask, mask, 0); - if (ret) - return ret; - - dev_info(smi->dev, "VLAN%d port %d, PVID set to %d\n", - (port + 1), port, (port + 1)); - ret = rtl8366_set_pvid(smi, port, (port + 1)); - if (ret) - return ret; - } - - return rtl8366_enable_vlan(smi, true); -} -EXPORT_SYMBOL_GPL(rtl8366_init_vlan); - -int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, - struct netlink_ext_ack *extack) -{ - struct realtek_smi *smi = ds->priv; - struct rtl8366_vlan_4k vlan4k; - int ret; - - /* Use VLAN nr port + 1 since VLAN0 is not valid */ - if (!smi->ops->is_vlan_valid(smi, port + 1)) - return -EINVAL; - - dev_info(smi->dev, "%s filtering on port %d\n", - vlan_filtering ? "enable" : "disable", - port); - - /* TODO: - * The hardware support filter ID (FID) 0..7, I have no clue how to - * support this in the driver when the callback only says on/off. - */ - ret = smi->ops->get_vlan_4k(smi, port + 1, &vlan4k); - if (ret) - return ret; - - /* Just set the filter to FID 1 for now then */ - ret = rtl8366_set_vlan(smi, port + 1, - vlan4k.member, - vlan4k.untag, - 1); - if (ret) - return ret; - - return 0; -} -EXPORT_SYMBOL_GPL(rtl8366_vlan_filtering); - int rtl8366_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) @@ -401,12 +318,9 @@ int rtl8366_vlan_add(struct dsa_switch *ds, int port, return ret; } - dev_info(smi->dev, "add VLAN %d on port %d, %s, %s\n", - vlan->vid, port, untagged ? "untagged" : "tagged", - pvid ? " PVID" : "no PVID"); - - if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port)) - dev_err(smi->dev, "port is DSA or CPU port\n"); + dev_dbg(smi->dev, "add VLAN %d on port %d, %s, %s\n", + vlan->vid, port, untagged ? "untagged" : "tagged", + pvid ? "PVID" : "no PVID"); member |= BIT(port); @@ -439,7 +353,7 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, struct realtek_smi *smi = ds->priv; int ret, i; - dev_info(smi->dev, "del VLAN %04x on port %d\n", vlan->vid, port); + dev_dbg(smi->dev, "del VLAN %d on port %d\n", vlan->vid, port); for (i = 0; i < smi->num_vlan_mc; i++) { struct rtl8366_vlan_mc vlanmc; @@ -457,7 +371,7 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, * anymore then clear the whole member * config so it can be reused. */ - if (!vlanmc.member && vlanmc.untag) { + if (!vlanmc.member) { vlanmc.vid = 0; vlanmc.priority = 0; vlanmc.fid = 0; diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index a89093bc6c6add..6382404814c3dd 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -143,6 +143,21 @@ #define RTL8366RB_PHY_NO_OFFSET 9 #define RTL8366RB_PHY_NO_MASK (0x1f << 9) +/* VLAN Ingress Control Register 1, one bit per port. + * bit 0 .. 5 will make the switch drop ingress frames without + * VID such as untagged or priority-tagged frames for respective + * port. + * bit 6 .. 11 will make the switch drop ingress frames carrying + * a C-tag with VID != 0 for respective port. + */ +#define RTL8366RB_VLAN_INGRESS_CTRL1_REG 0x037E +#define RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port) (BIT((port)) | BIT((port) + 6)) + +/* VLAN Ingress Control Register 2, one bit per port. + * bit0 .. bit5 will make the switch drop all ingress frames with + * a VLAN classification that does not include the port is in its + * member set. + */ #define RTL8366RB_VLAN_INGRESS_CTRL2_REG 0x037f /* LED control registers */ @@ -300,6 +315,13 @@ #define RTL8366RB_INTERRUPT_STATUS_REG 0x0442 #define RTL8366RB_NUM_INTERRUPT 14 /* 0..13 */ +/* Port isolation registers */ +#define RTL8366RB_PORT_ISO_BASE 0x0F08 +#define RTL8366RB_PORT_ISO(pnum) (RTL8366RB_PORT_ISO_BASE + (pnum)) +#define RTL8366RB_PORT_ISO_EN BIT(0) +#define RTL8366RB_PORT_ISO_PORTS_MASK GENMASK(7, 1) +#define RTL8366RB_PORT_ISO_PORTS(pmask) ((pmask) << 1) + /* bits 0..5 enable force when cleared */ #define RTL8366RB_MAC_FORCE_CTRL_REG 0x0F11 @@ -314,9 +336,13 @@ /** * struct rtl8366rb - RTL8366RB-specific data * @max_mtu: per-port max MTU setting + * @pvid_enabled: if PVID is set for respective port + * @vlan_filtering: if VLAN filtering is enabled for respective port */ struct rtl8366rb { unsigned int max_mtu[RTL8366RB_NUM_PORTS]; + bool pvid_enabled[RTL8366RB_NUM_PORTS]; + bool vlan_filtering[RTL8366RB_NUM_PORTS]; }; static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = { @@ -835,6 +861,21 @@ static int rtl8366rb_setup(struct dsa_switch *ds) if (ret) return ret; + /* Isolate all user ports so they can only send packets to itself and the CPU port */ + for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { + ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(i), + RTL8366RB_PORT_ISO_PORTS(BIT(RTL8366RB_PORT_NUM_CPU)) | + RTL8366RB_PORT_ISO_EN); + if (ret) + return ret; + } + /* CPU port can send packets to all ports */ + ret = regmap_write(smi->map, RTL8366RB_PORT_ISO(RTL8366RB_PORT_NUM_CPU), + RTL8366RB_PORT_ISO_PORTS(dsa_user_ports(ds)) | + RTL8366RB_PORT_ISO_EN); + if (ret) + return ret; + /* Set up the "green ethernet" feature */ ret = rtl8366rb_jam_table(rtl8366rb_green_jam, ARRAY_SIZE(rtl8366rb_green_jam), smi, false); @@ -911,11 +952,13 @@ static int rtl8366rb_setup(struct dsa_switch *ds) if (ret) return ret; - /* Discard VLAN tagged packets if the port is not a member of - * the VLAN with which the packets is associated. - */ + /* Accept all packets by default, we enable filtering on-demand */ + ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + 0); + if (ret) + return ret; ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, - RTL8366RB_PORT_ALL); + 0); if (ret) return ret; @@ -963,7 +1006,7 @@ static int rtl8366rb_setup(struct dsa_switch *ds) return ret; } - ret = rtl8366_init_vlan(smi); + ret = rtl8366_reset_vlan(smi); if (ret) return ret; @@ -977,8 +1020,6 @@ static int rtl8366rb_setup(struct dsa_switch *ds) return -ENODEV; } - ds->configure_vlan_while_not_filtering = false; - return 0; } @@ -1127,6 +1168,115 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) rb8366rb_set_port_led(smi, port, false); } +static int +rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *bridge) +{ + struct realtek_smi *smi = ds->priv; + unsigned int port_bitmap = 0; + int ret, i; + + /* Loop over all other ports than the current one */ + for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { + /* Current port handled last */ + if (i == port) + continue; + /* Not on this bridge */ + if (dsa_to_port(ds, i)->bridge_dev != bridge) + continue; + /* Join this port to each other port on the bridge */ + ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + RTL8366RB_PORT_ISO_PORTS(BIT(port)), + RTL8366RB_PORT_ISO_PORTS(BIT(port))); + if (ret) + dev_err(smi->dev, "failed to join port %d\n", port); + + port_bitmap |= BIT(i); + } + + /* Set the bits for the ports we can access */ + return regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + RTL8366RB_PORT_ISO_PORTS(port_bitmap), + RTL8366RB_PORT_ISO_PORTS(port_bitmap)); +} + +static void +rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, + struct net_device *bridge) +{ + struct realtek_smi *smi = ds->priv; + unsigned int port_bitmap = 0; + int ret, i; + + /* Loop over all other ports than this one */ + for (i = 0; i < RTL8366RB_PORT_NUM_CPU; i++) { + /* Current port handled last */ + if (i == port) + continue; + /* Not on this bridge */ + if (dsa_to_port(ds, i)->bridge_dev != bridge) + continue; + /* Remove this port from any other port on the bridge */ + ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), + RTL8366RB_PORT_ISO_PORTS(BIT(port)), 0); + if (ret) + dev_err(smi->dev, "failed to leave port %d\n", port); + + port_bitmap |= BIT(i); + } + + /* Clear the bits for the ports we can not access, leave ourselves */ + regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(port), + RTL8366RB_PORT_ISO_PORTS(port_bitmap), 0); +} + +/** + * rtl8366rb_drop_untagged() - make the switch drop untagged and C-tagged frames + * @smi: SMI state container + * @port: the port to drop untagged and C-tagged frames on + * @drop: whether to drop or pass untagged and C-tagged frames + */ +static int rtl8366rb_drop_untagged(struct realtek_smi *smi, int port, bool drop) +{ + return regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL1_REG, + RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port), + drop ? RTL8366RB_VLAN_INGRESS_CTRL1_DROP(port) : 0); +} + +static int rtl8366rb_vlan_filtering(struct dsa_switch *ds, int port, + bool vlan_filtering, + struct netlink_ext_ack *extack) +{ + struct realtek_smi *smi = ds->priv; + struct rtl8366rb *rb; + int ret; + + rb = smi->chip_data; + + dev_dbg(smi->dev, "port %d: %s VLAN filtering\n", port, + vlan_filtering ? "enable" : "disable"); + + /* If the port is not in the member set, the frame will be dropped */ + ret = regmap_update_bits(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG, + BIT(port), vlan_filtering ? BIT(port) : 0); + if (ret) + return ret; + + /* Keep track if filtering is enabled on each port */ + rb->vlan_filtering[port] = vlan_filtering; + + /* If VLAN filtering is enabled and PVID is also enabled, we must + * not drop any untagged or C-tagged frames. If we turn off VLAN + * filtering on a port, we need ti accept any frames. + */ + if (vlan_filtering) + ret = rtl8366rb_drop_untagged(smi, port, !rb->pvid_enabled[port]); + else + ret = rtl8366rb_drop_untagged(smi, port, false); + + return ret; +} + static int rtl8366rb_change_mtu(struct dsa_switch *ds, int port, int new_mtu) { struct realtek_smi *smi = ds->priv; @@ -1338,24 +1488,44 @@ static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val) static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index) { + struct rtl8366rb *rb; + bool pvid_enabled; + int ret; + + rb = smi->chip_data; + pvid_enabled = !!index; + if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS) return -EINVAL; - return regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), + ret = regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port), RTL8366RB_PORT_VLAN_CTRL_MASK << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port), (index & RTL8366RB_PORT_VLAN_CTRL_MASK) << RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)); + if (ret) + return ret; + + rb->pvid_enabled[port] = pvid_enabled; + + /* If VLAN filtering is enabled and PVID is also enabled, we must + * not drop any untagged or C-tagged frames. Make sure to update the + * filtering setting. + */ + if (rb->vlan_filtering[port]) + ret = rtl8366rb_drop_untagged(smi, port, !pvid_enabled); + + return ret; } static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan) { - unsigned int max = RTL8366RB_NUM_VLANS; + unsigned int max = RTL8366RB_NUM_VLANS - 1; if (smi->vlan4k_enabled) max = RTL8366RB_NUM_VIDS - 1; - if (vlan == 0 || vlan > max) + if (vlan > max) return false; return true; @@ -1510,7 +1680,9 @@ static const struct dsa_switch_ops rtl8366rb_switch_ops = { .get_strings = rtl8366_get_strings, .get_ethtool_stats = rtl8366_get_ethtool_stats, .get_sset_count = rtl8366_get_sset_count, - .port_vlan_filtering = rtl8366_vlan_filtering, + .port_bridge_join = rtl8366rb_port_bridge_join, + .port_bridge_leave = rtl8366rb_port_bridge_leave, + .port_vlan_filtering = rtl8366rb_vlan_filtering, .port_vlan_add = rtl8366_vlan_add, .port_vlan_del = rtl8366_vlan_del, .port_enable = rtl8366rb_port_enable, diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 5e5d24e7c02b2d..618c8d6a8be1e3 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -226,12 +226,10 @@ struct sja1105_private { bool rgmii_tx_delay[SJA1105_MAX_NUM_PORTS]; phy_interface_t phy_mode[SJA1105_MAX_NUM_PORTS]; bool fixed_link[SJA1105_MAX_NUM_PORTS]; - bool vlan_aware; unsigned long ucast_egress_floods; unsigned long bcast_egress_floods; const struct sja1105_info *info; size_t max_xfer_len; - struct gpio_desc *reset_gpio; struct spi_device *spidev; struct dsa_switch *ds; u16 bridge_pvid[SJA1105_MAX_NUM_PORTS]; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 7c0db80eff008f..0f1bba0076a8b1 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -27,15 +27,29 @@ #define SJA1105_UNKNOWN_MULTICAST 0x010000000000ull -static void sja1105_hw_reset(struct gpio_desc *gpio, unsigned int pulse_len, - unsigned int startup_delay) +/* Configure the optional reset pin and bring up switch */ +static int sja1105_hw_reset(struct device *dev, unsigned int pulse_len, + unsigned int startup_delay) { + struct gpio_desc *gpio; + + gpio = gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); + + if (!gpio) + return 0; + gpiod_set_value_cansleep(gpio, 1); /* Wait for minimum reset pulse length */ msleep(pulse_len); gpiod_set_value_cansleep(gpio, 0); /* Wait until chip is ready after reset */ msleep(startup_delay); + + gpiod_put(gpio); + + return 0; } static void @@ -1766,6 +1780,7 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port, static int sja1105_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data) { + struct dsa_port *dp = dsa_to_port(ds, port); struct sja1105_private *priv = ds->priv; struct device *dev = ds->dev; int i; @@ -1802,7 +1817,7 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port, u64_to_ether_addr(l2_lookup.macaddr, macaddr); /* We need to hide the dsa_8021q VLANs from the user. */ - if (!priv->vlan_aware) + if (!dsa_port_is_vlan_filtering(dp)) l2_lookup.vlanid = 0; rc = cb(macaddr, l2_lookup.vlanid, l2_lookup.lockeds, data); if (rc) @@ -2295,11 +2310,6 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, tpid2 = ETH_P_SJA1105; } - if (priv->vlan_aware == enabled) - return 0; - - priv->vlan_aware = enabled; - table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS]; general_params = table->entries; /* EtherType used to identify inner tagged (C-tag) VLAN traffic */ @@ -2332,7 +2342,7 @@ int sja1105_vlan_filtering(struct dsa_switch *ds, int port, bool enabled, */ table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP_PARAMS]; l2_lookup_params = table->entries; - l2_lookup_params->shared_learn = !priv->vlan_aware; + l2_lookup_params->shared_learn = !enabled; for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) @@ -2965,7 +2975,6 @@ static int sja1105_setup_ports(struct sja1105_private *priv) continue; dp->priv = sp; - sp->dp = dp; sp->data = tagger_data; slave = dp->slave; kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit); @@ -3117,7 +3126,7 @@ static void sja1105_teardown(struct dsa_switch *ds) sja1105_static_config_free(&priv->static_config); } -const struct dsa_switch_ops sja1105_switch_ops = { +static const struct dsa_switch_ops sja1105_switch_ops = { .get_tag_protocol = sja1105_get_tag_protocol, .setup = sja1105_setup, .teardown = sja1105_teardown, @@ -3166,7 +3175,6 @@ const struct dsa_switch_ops sja1105_switch_ops = { .port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload, .port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload, }; -EXPORT_SYMBOL_GPL(sja1105_switch_ops); static const struct of_device_id sja1105_dt_ids[]; @@ -3230,17 +3238,14 @@ static int sja1105_probe(struct spi_device *spi) return -EINVAL; } + rc = sja1105_hw_reset(dev, 1, 1); + if (rc) + return rc; + priv = devm_kzalloc(dev, sizeof(struct sja1105_private), GFP_KERNEL); if (!priv) return -ENOMEM; - /* Configure the optional reset pin and bring up switch */ - priv->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); - if (IS_ERR(priv->reset_gpio)) - dev_dbg(dev, "reset-gpios not defined, ignoring\n"); - else - sja1105_hw_reset(priv->reset_gpio, 1, 1); - /* Populate our driver private structure (priv) based on * the device tree node that was probed (spi) */ diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 691f6dd7e66973..54396992a9199c 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -64,6 +64,7 @@ enum sja1105_ptp_clk_mode { static int sja1105_change_rxtstamping(struct sja1105_private *priv, bool on) { + struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_general_params_entry *general_params; struct sja1105_table *table; @@ -79,7 +80,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, priv->tagger_data.stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&ptp_data->skb_txtstamp_queue); + skb_queue_purge(&tagger_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -452,40 +453,6 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return priv->info->rxtstamp(ds, port, skb); } -void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, - enum sja1110_meta_tstamp dir, u64 tstamp) -{ - struct sja1105_private *priv = ds->priv; - struct sja1105_ptp_data *ptp_data = &priv->ptp_data; - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; - struct skb_shared_hwtstamps shwt = {0}; - - /* We don't care about RX timestamps on the CPU port */ - if (dir == SJA1110_META_TSTAMP_RX) - return; - - spin_lock(&ptp_data->skb_txtstamp_queue.lock); - - skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { - if (SJA1105_SKB_CB(skb)->ts_id != ts_id) - continue; - - __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); - skb_match = skb; - - break; - } - - spin_unlock(&ptp_data->skb_txtstamp_queue.lock); - - if (WARN_ON(!skb_match)) - return; - - shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); - skb_complete_tx_timestamp(skb_match, &shwt); -} -EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp); - /* In addition to cloning the skb which is done by the common * sja1105_port_txtstamp, we need to generate a timestamp ID and save the * packet to the TX timestamping queue. @@ -494,7 +461,6 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; - struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_port *sp = &priv->ports[port]; u8 ts_id; @@ -510,7 +476,7 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) spin_unlock(&sp->data->meta_lock); - skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); + skb_queue_tail(&sp->data->skb_txtstamp_queue, clone); } /* Called from dsa_skb_tx_timestamp. This callback is just to clone @@ -953,7 +919,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); /* Only used on SJA1110 */ - skb_queue_head_init(&ptp_data->skb_txtstamp_queue); + skb_queue_head_init(&tagger_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); @@ -971,6 +937,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) void sja1105_ptp_clock_unregister(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; + struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -978,7 +945,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&ptp_data->skb_txtstamp_queue); + skb_queue_purge(&tagger_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 3c874bb4c17b73..3ae6b9fdd492b5 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -8,21 +8,6 @@ #if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) -{ - return ns / SJA1105_TICK_NS; -} - -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - /* Calculate the first base_time in the future that satisfies this * relationship: * @@ -77,10 +62,6 @@ struct sja1105_ptp_data { struct timer_list extts_timer; /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index 6802f4057cc038..d55572994e1f4a 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -494,13 +494,15 @@ int sja1105_vl_redirect(struct sja1105_private *priv, int port, bool append) { struct sja1105_rule *rule = sja1105_rule_find(priv, cookie); + struct dsa_port *dp = dsa_to_port(priv->ds, port); + bool vlan_aware = dsa_port_is_vlan_filtering(dp); int rc; - if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { + if (!vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on DMAC"); return -EOPNOTSUPP; - } else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { + } else if (vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only redirect based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; @@ -568,6 +570,8 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port, u32 num_entries, struct action_gate_entry *entries) { struct sja1105_rule *rule = sja1105_rule_find(priv, cookie); + struct dsa_port *dp = dsa_to_port(priv->ds, port); + bool vlan_aware = dsa_port_is_vlan_filtering(dp); int ipv = -1; int i, rc; s32 rem; @@ -592,11 +596,11 @@ int sja1105_vl_gate(struct sja1105_private *priv, int port, return -ERANGE; } - if (!priv->vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { + if (!vlan_aware && key->type != SJA1105_KEY_VLAN_UNAWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only gate based on DMAC"); return -EOPNOTSUPP; - } else if (priv->vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { + } else if (vlan_aware && key->type != SJA1105_KEY_VLAN_AWARE_VL) { NL_SET_ERR_MSG_MOD(extack, "Can only gate based on {DMAC, VID, PCP}"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 54cdafdd067db3..9acf589b1178bb 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -151,10 +151,9 @@ int arc_mdio_probe(struct arc_emac_priv *priv) data->reset_gpio = devm_gpiod_get_optional(priv->dev, "phy-reset", GPIOD_OUT_LOW); if (IS_ERR(data->reset_gpio)) { - error = PTR_ERR(data->reset_gpio); - dev_err(priv->dev, "Failed to request gpio: %d\n", error); mdiobus_free(bus); - return error; + return dev_err_probe(priv->dev, PTR_ERR(data->reset_gpio), + "Failed to request gpio\n"); } of_property_read_u32(np, "phy-reset-duration", &data->msec); @@ -166,9 +165,9 @@ int arc_mdio_probe(struct arc_emac_priv *priv) error = of_mdiobus_register(bus, priv->dev->of_node); if (error) { - dev_err(priv->dev, "cannot register MDIO bus %s\n", bus->name); mdiobus_free(bus); - return error; + return dev_err_probe(priv->dev, error, + "cannot register MDIO bus %s\n", bus->name); } return 0; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 3b51b172b3172b..1c258e4ddc96c2 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1847,7 +1847,7 @@ static int atl1c_alloc_rx_buffer(struct atl1c_adapter *adapter, u32 queue, buffer_info->skb = NULL; buffer_info->length = 0; ATL1C_SET_BUFFER_STATE(buffer_info, ATL1C_BUFFER_FREE); - netif_warn(adapter, rx_err, adapter->netdev, "RX pci_map_single failed"); + netif_warn(adapter, rx_err, adapter->netdev, "RX dma_map_single failed"); break; } buffer_info->dma = mapping; @@ -2662,10 +2662,8 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* enable device (incl. PCI PM wakeup and hotplug setup) */ err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "cannot enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "cannot enable PCI device\n"); /* * The atl1c chip can DMA to 64-bit addresses, but it uses a single diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 753973ac922e9b..2e22483a9040f6 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -2297,10 +2297,8 @@ static int atl1e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) int err = 0; err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "cannot enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "cannot enable PCI device\n"); /* * The atl1e chip can DMA to 64-bit addresses, but it uses a single diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index fa784953c60188..38b465452902b9 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1200,7 +1200,7 @@ static int b44_alloc_consistent(struct b44 *bp, gfp_t gfp) bp->rx_ring = dma_alloc_coherent(bp->sdev->dma_dev, size, &bp->rx_ring_dma, gfp); if (!bp->rx_ring) { - /* Allocation may have failed due to pci_alloc_consistent + /* Allocation may have failed due to dma_alloc_coherent insisting on use of GFP_DMA, which is more restrictive than necessary... */ struct dma_desc *rx_ring; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 62f84cc91e4d10..0fba01db336cc7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -13370,7 +13370,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } bnxt_inv_fw_health_reg(bp); - bnxt_dl_register(bp); + rc = bnxt_dl_register(bp); + if (rc) + goto init_err_dl; rc = register_netdev(dev); if (rc) @@ -13390,6 +13392,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) init_err_cleanup: bnxt_dl_unregister(bp); +init_err_dl: bnxt_shutdown_tc(bp); bnxt_clear_int_mode(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 9576547df4aba2..951c0c00cc9521 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -134,7 +134,7 @@ void bnxt_dl_fw_reporters_create(struct bnxt *bp) { struct bnxt_fw_health *health = bp->fw_health; - if (!bp->dl || !health) + if (!health) return; if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) || health->fw_reset_reporter) @@ -188,7 +188,7 @@ void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all) { struct bnxt_fw_health *health = bp->fw_health; - if (!bp->dl || !health) + if (!health) return; if ((all || !(bp->fw_cap & BNXT_FW_CAP_HOT_RESET)) && @@ -736,9 +736,6 @@ static const struct devlink_param bnxt_dl_params[] = { NULL), }; -static const struct devlink_param bnxt_dl_port_params[] = { -}; - static int bnxt_dl_params_register(struct bnxt *bp) { int rc; @@ -748,22 +745,10 @@ static int bnxt_dl_params_register(struct bnxt *bp) rc = devlink_params_register(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); - if (rc) { + if (rc) netdev_warn(bp->dev, "devlink_params_register failed. rc=%d\n", rc); - return rc; - } - rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params, - ARRAY_SIZE(bnxt_dl_port_params)); - if (rc) { - netdev_err(bp->dev, "devlink_port_params_register failed\n"); - devlink_params_unregister(bp->dl, bnxt_dl_params, - ARRAY_SIZE(bnxt_dl_params)); - return rc; - } - devlink_params_publish(bp->dl); - - return 0; + return rc; } static void bnxt_dl_params_unregister(struct bnxt *bp) @@ -773,14 +758,13 @@ static void bnxt_dl_params_unregister(struct bnxt *bp) devlink_params_unregister(bp->dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); - devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params, - ARRAY_SIZE(bnxt_dl_port_params)); } int bnxt_dl_register(struct bnxt *bp) { const struct devlink_ops *devlink_ops; struct devlink_port_attrs attrs = {}; + struct bnxt_dl *bp_dl; struct devlink *dl; int rc; @@ -795,21 +779,17 @@ int bnxt_dl_register(struct bnxt *bp) return -ENOMEM; } - bnxt_link_bp_to_dl(bp, dl); + bp->dl = dl; + bp_dl = devlink_priv(dl); + bp_dl->bp = bp; /* Add switchdev eswitch mode setting, if SRIOV supported */ if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV) && bp->hwrm_spec_code > 0x10803) bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY; - rc = devlink_register(dl); - if (rc) { - netdev_warn(bp->dev, "devlink_register failed. rc=%d\n", rc); - goto err_dl_free; - } - if (!BNXT_PF(bp)) - return 0; + goto out; attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; attrs.phys.port_number = bp->pf.port_id; @@ -819,21 +799,20 @@ int bnxt_dl_register(struct bnxt *bp) rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); if (rc) { netdev_err(bp->dev, "devlink_port_register failed\n"); - goto err_dl_unreg; + goto err_dl_free; } rc = bnxt_dl_params_register(bp); if (rc) goto err_dl_port_unreg; +out: + devlink_register(dl); return 0; err_dl_port_unreg: devlink_port_unregister(&bp->dl_port); -err_dl_unreg: - devlink_unregister(dl); err_dl_free: - bnxt_link_bp_to_dl(bp, NULL); devlink_free(dl); return rc; } @@ -842,13 +821,10 @@ void bnxt_dl_unregister(struct bnxt *bp) { struct devlink *dl = bp->dl; - if (!dl) - return; - + devlink_unregister(dl); if (BNXT_PF(bp)) { bnxt_dl_params_unregister(bp); devlink_port_unregister(&bp->dl_port); } - devlink_unregister(dl); devlink_free(dl); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index d889f240da2b2c..406dc655a5fc90 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -20,19 +20,6 @@ static inline struct bnxt *bnxt_get_bp_from_dl(struct devlink *dl) return ((struct bnxt_dl *)devlink_priv(dl))->bp; } -/* To clear devlink pointer from bp, pass NULL dl */ -static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) -{ - bp->dl = dl; - - /* add a back pointer in dl to bp */ - if (dl) { - struct bnxt_dl *bp_dl = devlink_priv(dl); - - bp_dl->bp = bp; - } -} - #define NVM_OFF_MSIX_VEC_PER_PF_MAX 108 #define NVM_OFF_MSIX_VEC_PER_PF_MIN 114 #define NVM_OFF_IGNORE_ARI 164 diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 23c7595d2a1d3f..6a8234bc94283d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -935,6 +935,48 @@ static int bcmgenet_set_coalesce(struct net_device *dev, return 0; } +static void bcmgenet_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *epause) +{ + struct bcmgenet_priv *priv; + u32 umac_cmd; + + priv = netdev_priv(dev); + + epause->autoneg = priv->autoneg_pause; + + if (netif_carrier_ok(dev)) { + /* report active state when link is up */ + umac_cmd = bcmgenet_umac_readl(priv, UMAC_CMD); + epause->tx_pause = !(umac_cmd & CMD_TX_PAUSE_IGNORE); + epause->rx_pause = !(umac_cmd & CMD_RX_PAUSE_IGNORE); + } else { + /* otherwise report stored settings */ + epause->tx_pause = priv->tx_pause; + epause->rx_pause = priv->rx_pause; + } +} + +static int bcmgenet_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *epause) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + if (!dev->phydev) + return -ENODEV; + + if (!phy_validate_pause(dev->phydev, epause)) + return -EINVAL; + + priv->autoneg_pause = !!epause->autoneg; + priv->tx_pause = !!epause->tx_pause; + priv->rx_pause = !!epause->rx_pause; + + bcmgenet_phy_pause_set(dev, priv->rx_pause, priv->tx_pause); + + return 0; +} + /* standard ethtool support functions. */ enum bcmgenet_stat_type { BCMGENET_STAT_NETDEV = -1, @@ -1587,6 +1629,8 @@ static const struct ethtool_ops bcmgenet_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, .get_rxnfc = bcmgenet_get_rxnfc, .set_rxnfc = bcmgenet_set_rxnfc, + .get_pauseparam = bcmgenet_get_pauseparam, + .set_pauseparam = bcmgenet_set_pauseparam, }; /* Power down the unimac, based on mode. */ @@ -3364,6 +3408,8 @@ static int bcmgenet_open(struct net_device *dev) goto err_irq1; } + bcmgenet_phy_pause_set(dev, priv->rx_pause, priv->tx_pause); + bcmgenet_netif_start(dev); netif_tx_start_all_queues(dev); @@ -3408,11 +3454,6 @@ static void bcmgenet_netif_stop(struct net_device *dev) */ cancel_work_sync(&priv->bcmgenet_irq_work); - priv->old_link = -1; - priv->old_speed = -1; - priv->old_duplex = -1; - priv->old_pause = -1; - /* tx reclaim */ bcmgenet_tx_reclaim_all(dev); bcmgenet_fini_dma(priv); @@ -3950,6 +3991,11 @@ static int bcmgenet_probe(struct platform_device *pdev) spin_lock_init(&priv->lock); + /* Set default pause parameters */ + priv->autoneg_pause = 1; + priv->tx_pause = 1; + priv->rx_pause = 1; + SET_NETDEV_DEV(dev, &pdev->dev); dev_set_drvdata(&pdev->dev, dev); dev->watchdog_timeo = 2 * HZ; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 0a6d91b0f0aa23..1cc2838e52c69d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -594,6 +594,9 @@ struct bcmgenet_priv { /* other misc variables */ struct bcmgenet_hw_params *hw_params; + unsigned autoneg_pause:1; + unsigned tx_pause:1; + unsigned rx_pause:1; /* MDIO bus variables */ wait_queue_head_t wq; @@ -606,10 +609,6 @@ struct bcmgenet_priv { bool clk_eee_enabled; /* PHY device variables */ - int old_link; - int old_speed; - int old_duplex; - int old_pause; phy_interface_t phy_interface; int phy_addr; int ext_phy; @@ -690,6 +689,7 @@ int bcmgenet_mii_init(struct net_device *dev); int bcmgenet_mii_config(struct net_device *dev, bool init); int bcmgenet_mii_probe(struct net_device *dev); void bcmgenet_mii_exit(struct net_device *dev); +void bcmgenet_phy_pause_set(struct net_device *dev, bool rx, bool tx); void bcmgenet_phy_power_set(struct net_device *dev, bool enable); void bcmgenet_mii_setup(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 89d16c587bb7dc..ad56f54eda0a3c 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -25,92 +25,80 @@ #include "bcmgenet.h" -/* setup netdev link state when PHY link status change and - * update UMAC and RGMII block when link up - */ -void bcmgenet_mii_setup(struct net_device *dev) +static void bcmgenet_mac_config(struct net_device *dev) { struct bcmgenet_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; u32 reg, cmd_bits = 0; - bool status_changed = false; - if (priv->old_link != phydev->link) { - status_changed = true; - priv->old_link = phydev->link; - } + /* speed */ + if (phydev->speed == SPEED_1000) + cmd_bits = CMD_SPEED_1000; + else if (phydev->speed == SPEED_100) + cmd_bits = CMD_SPEED_100; + else + cmd_bits = CMD_SPEED_10; + cmd_bits <<= CMD_SPEED_SHIFT; - if (phydev->link) { - /* check speed/duplex/pause changes */ - if (priv->old_speed != phydev->speed) { - status_changed = true; - priv->old_speed = phydev->speed; - } + /* duplex */ + if (phydev->duplex != DUPLEX_FULL) { + cmd_bits |= CMD_HD_EN | + CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE; + } else { + /* pause capability defaults to Symmetric */ + if (priv->autoneg_pause) { + bool tx_pause = 0, rx_pause = 0; - if (priv->old_duplex != phydev->duplex) { - status_changed = true; - priv->old_duplex = phydev->duplex; - } + if (phydev->autoneg) + phy_get_pause(phydev, &tx_pause, &rx_pause); - if (priv->old_pause != phydev->pause) { - status_changed = true; - priv->old_pause = phydev->pause; + if (!tx_pause) + cmd_bits |= CMD_TX_PAUSE_IGNORE; + if (!rx_pause) + cmd_bits |= CMD_RX_PAUSE_IGNORE; } - /* done if nothing has changed */ - if (!status_changed) - return; - - /* speed */ - if (phydev->speed == SPEED_1000) - cmd_bits = CMD_SPEED_1000; - else if (phydev->speed == SPEED_100) - cmd_bits = CMD_SPEED_100; - else - cmd_bits = CMD_SPEED_10; - cmd_bits <<= CMD_SPEED_SHIFT; - - /* duplex */ - if (phydev->duplex != DUPLEX_FULL) - cmd_bits |= CMD_HD_EN; - - /* pause capability */ - if (!phydev->pause) - cmd_bits |= CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE; - - /* - * Program UMAC and RGMII block based on established - * link speed, duplex, and pause. The speed set in - * umac->cmd tell RGMII block which clock to use for - * transmit -- 25MHz(100Mbps) or 125MHz(1Gbps). - * Receive clock is provided by the PHY. - */ - reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); - reg &= ~OOB_DISABLE; - reg |= RGMII_LINK; - bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + /* Manual override */ + if (!priv->rx_pause) + cmd_bits |= CMD_RX_PAUSE_IGNORE; + if (!priv->tx_pause) + cmd_bits |= CMD_TX_PAUSE_IGNORE; + } - reg = bcmgenet_umac_readl(priv, UMAC_CMD); - reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | - CMD_HD_EN | - CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE); - reg |= cmd_bits; - if (reg & CMD_SW_RESET) { - reg &= ~CMD_SW_RESET; - bcmgenet_umac_writel(priv, reg, UMAC_CMD); - udelay(2); - reg |= CMD_TX_EN | CMD_RX_EN; - } + /* Program UMAC and RGMII block based on established + * link speed, duplex, and pause. The speed set in + * umac->cmd tell RGMII block which clock to use for + * transmit -- 25MHz(100Mbps) or 125MHz(1Gbps). + * Receive clock is provided by the PHY. + */ + reg = bcmgenet_ext_readl(priv, EXT_RGMII_OOB_CTRL); + reg &= ~OOB_DISABLE; + reg |= RGMII_LINK; + bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL); + + reg = bcmgenet_umac_readl(priv, UMAC_CMD); + reg &= ~((CMD_SPEED_MASK << CMD_SPEED_SHIFT) | + CMD_HD_EN | + CMD_RX_PAUSE_IGNORE | CMD_TX_PAUSE_IGNORE); + reg |= cmd_bits; + if (reg & CMD_SW_RESET) { + reg &= ~CMD_SW_RESET; bcmgenet_umac_writel(priv, reg, UMAC_CMD); - } else { - /* done if nothing has changed */ - if (!status_changed) - return; - - /* needed for MoCA fixed PHY to reflect correct link status */ - netif_carrier_off(dev); + udelay(2); + reg |= CMD_TX_EN | CMD_RX_EN; } + bcmgenet_umac_writel(priv, reg, UMAC_CMD); +} +/* setup netdev link state when PHY link status change and + * update UMAC and RGMII block when link up + */ +void bcmgenet_mii_setup(struct net_device *dev) +{ + struct phy_device *phydev = dev->phydev; + + if (phydev->link) + bcmgenet_mac_config(dev); phy_print_status(phydev); } @@ -130,6 +118,21 @@ static int bcmgenet_fixed_phy_link_update(struct net_device *dev, return 0; } +void bcmgenet_phy_pause_set(struct net_device *dev, bool rx, bool tx) +{ + struct phy_device *phydev = dev->phydev; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->advertising, rx); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising, + rx | tx); + phy_start_aneg(phydev); + + mutex_lock(&phydev->lock); + if (phydev->link) + bcmgenet_mac_config(dev); + mutex_unlock(&phydev->lock); +} + void bcmgenet_phy_power_set(struct net_device *dev, bool enable) { struct bcmgenet_priv *priv = netdev_priv(dev); @@ -286,23 +289,53 @@ int bcmgenet_mii_probe(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; struct device_node *dn = kdev->of_node; + phy_interface_t phy_iface = priv->phy_interface; struct phy_device *phydev; - u32 phy_flags = 0; + u32 phy_flags = PHY_BRCM_AUTO_PWRDWN_ENABLE | + PHY_BRCM_DIS_TXCRXC_NOENRGY | + PHY_BRCM_IDDQ_SUSPEND; int ret; /* Communicate the integrated PHY revision */ if (priv->internal_phy) phy_flags = priv->gphy_rev; - /* Initialize link state variables that bcmgenet_mii_setup() uses */ - priv->old_link = -1; - priv->old_speed = -1; - priv->old_duplex = -1; - priv->old_pause = -1; + /* This is an ugly quirk but we have not been correctly interpreting + * the phy_interface values and we have done that across different + * drivers, so at least we are consistent in our mistakes. + * + * When the Generic PHY driver is in use either the PHY has been + * strapped or programmed correctly by the boot loader so we should + * stick to our incorrect interpretation since we have validated it. + * + * Now when a dedicated PHY driver is in use, we need to reverse the + * meaning of the phy_interface_mode values to something that the PHY + * driver will interpret and act on such that we have two mistakes + * canceling themselves so to speak. We only do this for the two + * modes that GENET driver officially supports on Broadcom STB chips: + * PHY_INTERFACE_MODE_RGMII and PHY_INTERFACE_MODE_RGMII_TXID. Other + * modes are not *officially* supported with the boot loader and the + * scripted environment generating Device Tree blobs for those + * platforms. + * + * Note that internal PHY, MoCA and fixed-link configurations are not + * affected because they use different phy_interface_t values or the + * Generic PHY driver. + */ + switch (priv->phy_interface) { + case PHY_INTERFACE_MODE_RGMII: + phy_iface = PHY_INTERFACE_MODE_RGMII_ID; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + phy_iface = PHY_INTERFACE_MODE_RGMII_RXID; + break; + default: + break; + } if (dn) { phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup, - phy_flags, priv->phy_interface); + phy_flags, phy_iface); if (!phydev) { pr_err("could not attach to PHY\n"); return -ENODEV; @@ -332,7 +365,7 @@ int bcmgenet_mii_probe(struct net_device *dev) phydev->dev_flags = phy_flags; ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup, - priv->phy_interface); + phy_iface); if (ret) { pr_err("could not attach to PHY\n"); return -ENODEV; @@ -350,8 +383,6 @@ int bcmgenet_mii_probe(struct net_device *dev) return ret; } - linkmode_copy(phydev->advertising, phydev->supported); - /* The internal PHY has its link interrupts routed to the * Ethernet MAC ISRs. On GENETv5 there is a hardware issue * that prevents the signaling of link UP interrupts when diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index d8d87213697cde..5620b97b3482b1 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -243,9 +243,11 @@ #define MACB_NCR_TPF_SIZE 1 #define MACB_TZQ_OFFSET 12 /* Transmit zero quantum pause frame */ #define MACB_TZQ_SIZE 1 -#define MACB_SRTSM_OFFSET 15 -#define MACB_OSSMODE_OFFSET 24 /* Enable One Step Synchro Mode */ +#define MACB_SRTSM_OFFSET 15 /* Store Receive Timestamp to Memory */ +#define MACB_OSSMODE_OFFSET 24 /* Enable One Step Synchro Mode */ #define MACB_OSSMODE_SIZE 1 +#define MACB_MIIONRGMII_OFFSET 28 /* MII Usage on RGMII Interface */ +#define MACB_MIIONRGMII_SIZE 1 /* Bitfields in NCFGR */ #define MACB_SPD_OFFSET 0 /* Speed */ @@ -713,6 +715,7 @@ #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 +#define MACB_CAPS_MIIONRGMII 0x00000200 #define MACB_CAPS_CLK_HW_CHG 0x04000000 #define MACB_CAPS_MACB_IS_EMAC 0x08000000 #define MACB_CAPS_FIFO_MODE 0x10000000 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index d13fb1d3182155..e2730b3e1a5778 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -684,6 +684,9 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, } else if (state->interface == PHY_INTERFACE_MODE_10GBASER) { ctrl |= GEM_BIT(PCSSEL); ncr |= GEM_BIT(ENABLE_HS_MAC); + } else if (bp->caps & MACB_CAPS_MIIONRGMII && + bp->phy_interface == PHY_INTERFACE_MODE_MII) { + ncr |= MACB_BIT(MIIONRGMII); } } @@ -4594,7 +4597,8 @@ static const struct macb_config zynq_config = { }; static const struct macb_config sama7g5_gem_config = { - .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG | + MACB_CAPS_MIIONRGMII, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -4602,7 +4606,8 @@ static const struct macb_config sama7g5_gem_config = { }; static const struct macb_config sama7g5_emac_config = { - .caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | MACB_CAPS_USRIO_HAS_CLKEN, + .caps = MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII | + MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_MIIONRGMII, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 2907e13b9df697..dafc79bd34f48e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1279,6 +1279,14 @@ static int liquidio_stop_nic_module(struct octeon_device *oct) struct lio *lio; dev_dbg(&oct->pci_dev->dev, "Stopping network interfaces\n"); + device_lock(&oct->pci_dev->dev); + if (oct->devlink) { + devlink_unregister(oct->devlink); + devlink_free(oct->devlink); + oct->devlink = NULL; + } + device_unlock(&oct->pci_dev->dev); + if (!oct->ifcount) { dev_err(&oct->pci_dev->dev, "Init for Octeon was not completed\n"); return 1; @@ -1300,12 +1308,6 @@ static int liquidio_stop_nic_module(struct octeon_device *oct) for (i = 0; i < oct->ifcount; i++) liquidio_destroy_nic_device(oct, i); - if (oct->devlink) { - devlink_unregister(oct->devlink); - devlink_free(oct->devlink); - oct->devlink = NULL; - } - dev_dbg(&oct->pci_dev->dev, "Network interfaces stopped\n"); return 0; } @@ -3749,10 +3751,12 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) } } + device_lock(&octeon_dev->pci_dev->dev); devlink = devlink_alloc(&liquidio_devlink_ops, sizeof(struct lio_devlink_priv), &octeon_dev->pci_dev->dev); if (!devlink) { + device_unlock(&octeon_dev->pci_dev->dev); dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n"); goto setup_nic_dev_free; } @@ -3760,15 +3764,10 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio_devlink = devlink_priv(devlink); lio_devlink->oct = octeon_dev; - if (devlink_register(devlink)) { - devlink_free(devlink); - dev_err(&octeon_dev->pci_dev->dev, - "devlink registration failed\n"); - goto setup_nic_dev_free; - } - octeon_dev->devlink = devlink; octeon_dev->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY; + devlink_register(devlink); + device_unlock(&octeon_dev->pci_dev->dev); return 0; diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 691e1475d55e4e..b3d7d1afced72d 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -1311,9 +1311,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = pci_enable_device(pdev); if (err) { - dev_err(dev, "Failed to enable PCI device\n"); pci_set_drvdata(pdev, NULL); - return err; + return dev_err_probe(dev, err, "Failed to enable PCI device\n"); } err = pci_request_regions(pdev, DRV_NAME); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index d1667b7595223f..2b87565781a0b2 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2119,10 +2119,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } err = pci_enable_device(pdev); - if (err) { - dev_err(dev, "Failed to enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(dev, err, "Failed to enable PCI device\n"); err = pci_request_regions(pdev, DRV_NAME); if (err) { diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index c36fed9c3d737d..db66d4beb28afb 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1597,9 +1597,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = pcim_enable_device(pdev); if (err) { - dev_err(dev, "Failed to enable PCI device\n"); pci_set_drvdata(pdev, NULL); - return err; + return dev_err_probe(dev, err, "Failed to enable PCI device\n"); } err = pci_request_regions(pdev, DRV_NAME); diff --git a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c index 873c1c7b4ca0f5..a19284bdb80eb5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c +++ b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c @@ -591,7 +591,7 @@ static void port_stats_update(struct cmac *mac) } hw_stats[] = { #define HW_STAT(reg, stat_name) \ - { reg, (&((struct cmac_statistics *)NULL)->stat_name) - (u64 *)NULL } + { reg, offsetof(struct cmac_statistics, stat_name) / sizeof(u64) } /* Rx stats */ HW_STAT(RxUnicast, RxUnicastFramesOK), diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 49b76fd47daa0f..4920a80a046079 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2902,10 +2902,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, * Initialize generic PCI device state. */ err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "cannot enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "cannot enable PCI device\n"); /* * Reserve PCI resources for the device. If we can't get them some diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 12ffc14fbecd8e..6ded4d9fa32a07 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -139,7 +139,7 @@ static void enic_get_drvinfo(struct net_device *netdev, int err; err = enic_dev_fw_info(enic, &fw_info); - /* return only when pci_zalloc_consistent fails in vnic_dev_fw_info + /* return only when dma_alloc_coherent fails in vnic_dev_fw_info * For other failures, like devcmd failure, we return previously * recorded info. */ @@ -270,7 +270,7 @@ static void enic_get_ethtool_stats(struct net_device *netdev, int err; err = enic_dev_stats_dump(enic, &vstats); - /* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump + /* return only when dma_alloc_coherent fails in vnic_dev_stats_dump * For other failures, like devcmd failure, we return previously * recorded stats. */ diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index d0a8f7106958bc..13dbdd5d07b40b 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -882,7 +882,7 @@ static void enic_get_stats(struct net_device *netdev, int err; err = enic_dev_stats_dump(enic, &stats); - /* return only when pci_zalloc_consistent fails in vnic_dev_stats_dump + /* return only when dma_alloc_coherent fails in vnic_dev_stats_dump * For other failures, like devcmd failure, we return previously * recorded stats. */ diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index ed1ed48e748388..0064ebdaf4b483 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -707,20 +707,16 @@ static int ethoc_mdio_probe(struct net_device *dev) else phy = phy_find_first(priv->mdio); - if (!phy) { - dev_err(&dev->dev, "no PHY found\n"); - return -ENXIO; - } + if (!phy) + return dev_err_probe(&dev->dev, -ENXIO, "no PHY found\n"); priv->old_duplex = -1; priv->old_link = -1; err = phy_connect_direct(dev, phy, ethoc_mdio_poll, PHY_INTERFACE_MODE_GMII); - if (err) { - dev_err(&dev->dev, "could not attach to PHY\n"); - return err; - } + if (err) + return dev_err_probe(&dev->dev, err, "could not attach to PHY\n"); phy_set_max_speed(phy, SPEED_100); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c index 605a39f892b949..7fefe1574b6a02 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-devlink.c @@ -189,12 +189,11 @@ static const struct devlink_ops dpaa2_eth_devlink_ops = { .trap_group_action_set = dpaa2_eth_dl_trap_group_action_set, }; -int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv) +int dpaa2_eth_dl_alloc(struct dpaa2_eth_priv *priv) { struct net_device *net_dev = priv->net_dev; struct device *dev = net_dev->dev.parent; struct dpaa2_eth_devlink_priv *dl_priv; - int err; priv->devlink = devlink_alloc(&dpaa2_eth_devlink_ops, sizeof(*dl_priv), dev); @@ -204,25 +203,23 @@ int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv) } dl_priv = devlink_priv(priv->devlink); dl_priv->dpaa2_priv = priv; - - err = devlink_register(priv->devlink); - if (err) { - dev_err(dev, "devlink_register() = %d\n", err); - goto devlink_free; - } - return 0; +} -devlink_free: +void dpaa2_eth_dl_free(struct dpaa2_eth_priv *priv) +{ devlink_free(priv->devlink); +} - return err; + +void dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv) +{ + devlink_register(priv->devlink); } void dpaa2_eth_dl_unregister(struct dpaa2_eth_priv *priv) { devlink_unregister(priv->devlink); - devlink_free(priv->devlink); } int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 7065c71ed7b86e..03c168b1712fca 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4431,7 +4431,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) if (err) goto err_connect_mac; - err = dpaa2_eth_dl_register(priv); + err = dpaa2_eth_dl_alloc(priv); if (err) goto err_dl_register; @@ -4453,6 +4453,7 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) dpaa2_dbg_add(priv); #endif + dpaa2_eth_dl_register(priv); dev_info(dev, "Probed interface %s\n", net_dev->name); return 0; @@ -4461,7 +4462,7 @@ err_netdev_reg: err_dl_port_add: dpaa2_eth_dl_traps_unregister(priv); err_dl_trap_register: - dpaa2_eth_dl_unregister(priv); + dpaa2_eth_dl_free(priv); err_dl_register: dpaa2_eth_disconnect_mac(priv); err_connect_mac: @@ -4508,6 +4509,8 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) net_dev = dev_get_drvdata(dev); priv = netdev_priv(net_dev); + dpaa2_eth_dl_unregister(priv); + #ifdef CONFIG_DEBUG_FS dpaa2_dbg_remove(priv); #endif @@ -4519,7 +4522,7 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev) dpaa2_eth_dl_port_del(priv); dpaa2_eth_dl_traps_unregister(priv); - dpaa2_eth_dl_unregister(priv); + dpaa2_eth_dl_free(priv); if (priv->do_link_poll) kthread_stop(priv->poll_thread); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index cdb623d5f2c1a5..628d2d45f045db 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -725,7 +725,10 @@ void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, extern const struct dcbnl_rtnl_ops dpaa2_eth_dcbnl_ops; -int dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv); +int dpaa2_eth_dl_alloc(struct dpaa2_eth_priv *priv); +void dpaa2_eth_dl_free(struct dpaa2_eth_priv *priv); + +void dpaa2_eth_dl_register(struct dpaa2_eth_priv *priv); void dpaa2_eth_dl_unregister(struct dpaa2_eth_priv *priv); int dpaa2_eth_dl_port_add(struct dpaa2_eth_priv *priv); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index ae6d382d87352a..543c1f20242097 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -140,6 +140,11 @@ static void dpaa2_mac_validate(struct phylink_config *config, case PHY_INTERFACE_MODE_10GBASER: case PHY_INTERFACE_MODE_USXGMII: phylink_set(mask, 10000baseT_Full); + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); if (state->interface == PHY_INTERFACE_MODE_10GBASER) break; phylink_set(mask, 5000baseT_Full); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 042327b9981fad..3cbfa8b4e26536 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2607,10 +2607,8 @@ int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv) pcie_flr(pdev); err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "device enable failed\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "device enable failed\n"); /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 4c977dfc44f0dd..8c6fa134599628 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -803,10 +803,8 @@ static int enetc_mdio_probe(struct enetc_pf *pf, struct device_node *np) snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); err = of_mdiobus_register(bus, np); - if (err) { - dev_err(dev, "cannot register MDIO bus\n"); - return err; - } + if (err) + return dev_err_probe(dev, err, "cannot register MDIO bus\n"); pf->mdio = bus; @@ -1215,10 +1213,8 @@ static int enetc_pf_probe(struct pci_dev *pdev, ERR_PTR(err)); err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf)); - if (err) { - dev_err(&pdev->dev, "PCI probing failed\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); si = pci_get_drvdata(pdev); if (!si->hw.port || !si->hw.global) { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c index bc594892507acb..36b4f51dd297c2 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -39,10 +39,8 @@ static int enetc_ptp_probe(struct pci_dev *pdev, } err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "device enable failed\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "device enable failed\n"); /* set up for high or low dma */ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 1a9d1e8b772ce7..0704f6bf12fde3 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -143,10 +143,8 @@ static int enetc_vf_probe(struct pci_dev *pdev, int err; err = enetc_pci_probe(pdev, KBUILD_MODNAME, 0); - if (err) { - dev_err(&pdev->dev, "PCI probing failed\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "PCI probing failed\n"); si = pci_get_drvdata(pdev); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 1d3188e8e3b3c0..85bf825606e899 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -224,11 +224,6 @@ struct gve_tx_iovec { u32 iov_padding; /* padding associated with this segment */ }; -struct gve_tx_dma_buf { - DEFINE_DMA_UNMAP_ADDR(dma); - DEFINE_DMA_UNMAP_LEN(len); -}; - /* Tracks the memory in the fifo occupied by the skb. Mapped 1:1 to a desc * ring entry but only used for a pkt_desc not a seg_desc */ @@ -236,7 +231,10 @@ struct gve_tx_buffer_state { struct sk_buff *skb; /* skb for this pkt */ union { struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */ - struct gve_tx_dma_buf buf; + struct { + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + }; }; }; @@ -280,7 +278,8 @@ struct gve_tx_pending_packet_dqo { * All others correspond to `skb`'s frags and should be unmapped with * `dma_unmap_page`. */ - struct gve_tx_dma_buf bufs[MAX_SKB_FRAGS + 1]; + DEFINE_DMA_UNMAP_ADDR(dma[MAX_SKB_FRAGS + 1]); + DEFINE_DMA_UNMAP_LEN(len[MAX_SKB_FRAGS + 1]); u16 num_bufs; /* Linked list index to next element in the list, or -1 if none */ diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 099a2bc5ae6704..cd9df68cc01ec3 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -268,7 +268,7 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) int i, j; int err; - priv->msix_vectors = kvzalloc(num_vecs_requested * + priv->msix_vectors = kvcalloc(num_vecs_requested, sizeof(*priv->msix_vectors), GFP_KERNEL); if (!priv->msix_vectors) return -ENOMEM; @@ -628,7 +628,7 @@ static int gve_alloc_rings(struct gve_priv *priv) int err; /* Setup tx rings */ - priv->tx = kvzalloc(priv->tx_cfg.num_queues * sizeof(*priv->tx), + priv->tx = kvcalloc(priv->tx_cfg.num_queues, sizeof(*priv->tx), GFP_KERNEL); if (!priv->tx) return -ENOMEM; @@ -641,7 +641,7 @@ static int gve_alloc_rings(struct gve_priv *priv) goto free_tx; /* Setup rx rings */ - priv->rx = kvzalloc(priv->rx_cfg.num_queues * sizeof(*priv->rx), + priv->rx = kvcalloc(priv->rx_cfg.num_queues, sizeof(*priv->rx), GFP_KERNEL); if (!priv->rx) { err = -ENOMEM; @@ -764,12 +764,11 @@ static int gve_alloc_queue_page_list(struct gve_priv *priv, u32 id, qpl->id = id; qpl->num_entries = 0; - qpl->pages = kvzalloc(pages * sizeof(*qpl->pages), GFP_KERNEL); + qpl->pages = kvcalloc(pages, sizeof(*qpl->pages), GFP_KERNEL); /* caller handles clean up */ if (!qpl->pages) return -ENOMEM; - qpl->page_buses = kvzalloc(pages * sizeof(*qpl->page_buses), - GFP_KERNEL); + qpl->page_buses = kvcalloc(pages, sizeof(*qpl->page_buses), GFP_KERNEL); /* caller handles clean up */ if (!qpl->page_buses) return -ENOMEM; @@ -828,7 +827,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) if (priv->queue_format == GVE_GQI_RDA_FORMAT) return 0; - priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL); + priv->qpls = kvcalloc(num_qpls, sizeof(*priv->qpls), GFP_KERNEL); if (!priv->qpls) return -ENOMEM; @@ -847,7 +846,7 @@ static int gve_alloc_qpls(struct gve_priv *priv) priv->qpl_cfg.qpl_map_size = BITS_TO_LONGS(num_qpls) * sizeof(unsigned long) * BITS_PER_BYTE; - priv->qpl_cfg.qpl_id_map = kvzalloc(BITS_TO_LONGS(num_qpls) * + priv->qpl_cfg.qpl_id_map = kvcalloc(BITS_TO_LONGS(num_qpls), sizeof(unsigned long), GFP_KERNEL); if (!priv->qpl_cfg.qpl_id_map) { err = -ENOMEM; diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 665ac795a1adf8..9922ce46a63510 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -303,15 +303,15 @@ static inline int gve_skb_fifo_bytes_required(struct gve_tx_ring *tx, static void gve_tx_unmap_buf(struct device *dev, struct gve_tx_buffer_state *info) { if (info->skb) { - dma_unmap_single(dev, dma_unmap_addr(&info->buf, dma), - dma_unmap_len(&info->buf, len), + dma_unmap_single(dev, dma_unmap_addr(info, dma), + dma_unmap_len(info, len), DMA_TO_DEVICE); - dma_unmap_len_set(&info->buf, len, 0); + dma_unmap_len_set(info, len, 0); } else { - dma_unmap_page(dev, dma_unmap_addr(&info->buf, dma), - dma_unmap_len(&info->buf, len), + dma_unmap_page(dev, dma_unmap_addr(info, dma), + dma_unmap_len(info, len), DMA_TO_DEVICE); - dma_unmap_len_set(&info->buf, len, 0); + dma_unmap_len_set(info, len, 0); } } @@ -491,7 +491,6 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, struct gve_tx_buffer_state *info; bool is_gso = skb_is_gso(skb); u32 idx = tx->req & tx->mask; - struct gve_tx_dma_buf *buf; u64 addr; u32 len; int i; @@ -515,9 +514,8 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, tx->dma_mapping_error++; goto drop; } - buf = &info->buf; - dma_unmap_len_set(buf, len, len); - dma_unmap_addr_set(buf, dma, addr); + dma_unmap_len_set(info, len, len); + dma_unmap_addr_set(info, dma, addr); payload_nfrags = shinfo->nr_frags; if (hlen < len) { @@ -549,10 +547,9 @@ static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx, tx->dma_mapping_error++; goto unmap_drop; } - buf = &tx->info[idx].buf; tx->info[idx].skb = NULL; - dma_unmap_len_set(buf, len, len); - dma_unmap_addr_set(buf, dma, addr); + dma_unmap_len_set(&tx->info[idx], len, len); + dma_unmap_addr_set(&tx->info[idx], dma, addr); gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr); } diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index 05ddb6a75c38f3..ec394d9916681a 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -85,18 +85,16 @@ static void gve_tx_clean_pending_packets(struct gve_tx_ring *tx) int j; for (j = 0; j < cur_state->num_bufs; j++) { - struct gve_tx_dma_buf *buf = &cur_state->bufs[j]; - if (j == 0) { dma_unmap_single(tx->dev, - dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), - DMA_TO_DEVICE); + dma_unmap_addr(cur_state, dma[j]), + dma_unmap_len(cur_state, len[j]), + DMA_TO_DEVICE); } else { dma_unmap_page(tx->dev, - dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), - DMA_TO_DEVICE); + dma_unmap_addr(cur_state, dma[j]), + dma_unmap_len(cur_state, len[j]), + DMA_TO_DEVICE); } } if (cur_state->skb) { @@ -457,15 +455,15 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, const bool is_gso = skb_is_gso(skb); u32 desc_idx = tx->dqo_tx.tail; - struct gve_tx_pending_packet_dqo *pending_packet; + struct gve_tx_pending_packet_dqo *pkt; struct gve_tx_metadata_dqo metadata; s16 completion_tag; int i; - pending_packet = gve_alloc_pending_packet(tx); - pending_packet->skb = skb; - pending_packet->num_bufs = 0; - completion_tag = pending_packet - tx->dqo.pending_packets; + pkt = gve_alloc_pending_packet(tx); + pkt->skb = skb; + pkt->num_bufs = 0; + completion_tag = pkt - tx->dqo.pending_packets; gve_extract_tx_metadata_dqo(skb, &metadata); if (is_gso) { @@ -493,8 +491,6 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, /* Map the linear portion of skb */ { - struct gve_tx_dma_buf *buf = - &pending_packet->bufs[pending_packet->num_bufs]; u32 len = skb_headlen(skb); dma_addr_t addr; @@ -502,9 +498,9 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, if (unlikely(dma_mapping_error(tx->dev, addr))) goto err; - dma_unmap_len_set(buf, len, len); - dma_unmap_addr_set(buf, dma, addr); - ++pending_packet->num_bufs; + dma_unmap_len_set(pkt, len[pkt->num_bufs], len); + dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr); + ++pkt->num_bufs; gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr, completion_tag, @@ -512,8 +508,6 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, } for (i = 0; i < shinfo->nr_frags; i++) { - struct gve_tx_dma_buf *buf = - &pending_packet->bufs[pending_packet->num_bufs]; const skb_frag_t *frag = &shinfo->frags[i]; bool is_eop = i == (shinfo->nr_frags - 1); u32 len = skb_frag_size(frag); @@ -523,9 +517,9 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, if (unlikely(dma_mapping_error(tx->dev, addr))) goto err; - dma_unmap_len_set(buf, len, len); - dma_unmap_addr_set(buf, dma, addr); - ++pending_packet->num_bufs; + dma_unmap_len_set(pkt, len[pkt->num_bufs], len); + dma_unmap_addr_set(pkt, dma[pkt->num_bufs], addr); + ++pkt->num_bufs; gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, skb, len, addr, completion_tag, is_eop, is_gso); @@ -552,22 +546,23 @@ static int gve_tx_add_skb_no_copy_dqo(struct gve_tx_ring *tx, return 0; err: - for (i = 0; i < pending_packet->num_bufs; i++) { - struct gve_tx_dma_buf *buf = &pending_packet->bufs[i]; - + for (i = 0; i < pkt->num_bufs; i++) { if (i == 0) { - dma_unmap_single(tx->dev, dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), + dma_unmap_single(tx->dev, + dma_unmap_addr(pkt, dma[i]), + dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE); } else { - dma_unmap_page(tx->dev, dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), DMA_TO_DEVICE); + dma_unmap_page(tx->dev, + dma_unmap_addr(pkt, dma[i]), + dma_unmap_len(pkt, len[i]), + DMA_TO_DEVICE); } } - pending_packet->skb = NULL; - pending_packet->num_bufs = 0; - gve_free_pending_packet(tx, pending_packet); + pkt->skb = NULL; + pkt->num_bufs = 0; + gve_free_pending_packet(tx, pkt); return -1; } @@ -725,12 +720,12 @@ static void add_to_list(struct gve_tx_ring *tx, struct gve_index_list *list, static void remove_from_list(struct gve_tx_ring *tx, struct gve_index_list *list, - struct gve_tx_pending_packet_dqo *pending_packet) + struct gve_tx_pending_packet_dqo *pkt) { s16 prev_index, next_index; - prev_index = pending_packet->prev; - next_index = pending_packet->next; + prev_index = pkt->prev; + next_index = pkt->next; if (prev_index == -1) { /* Node is head */ @@ -747,21 +742,18 @@ static void remove_from_list(struct gve_tx_ring *tx, } static void gve_unmap_packet(struct device *dev, - struct gve_tx_pending_packet_dqo *pending_packet) + struct gve_tx_pending_packet_dqo *pkt) { - struct gve_tx_dma_buf *buf; int i; /* SKB linear portion is guaranteed to be mapped */ - buf = &pending_packet->bufs[0]; - dma_unmap_single(dev, dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), DMA_TO_DEVICE); - for (i = 1; i < pending_packet->num_bufs; i++) { - buf = &pending_packet->bufs[i]; - dma_unmap_page(dev, dma_unmap_addr(buf, dma), - dma_unmap_len(buf, len), DMA_TO_DEVICE); + dma_unmap_single(dev, dma_unmap_addr(pkt, dma[0]), + dma_unmap_len(pkt, len[0]), DMA_TO_DEVICE); + for (i = 1; i < pkt->num_bufs; i++) { + dma_unmap_page(dev, dma_unmap_addr(pkt, dma[i]), + dma_unmap_len(pkt, len[i]), DMA_TO_DEVICE); } - pending_packet->num_bufs = 0; + pkt->num_bufs = 0; } /* Completion types and expected behavior: diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 8ba21d6dc220ca..17872c50b63c0e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -95,6 +95,7 @@ enum HNAE3_DEV_CAP_BITS { HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, + HNAE3_DEV_SUPPORT_MC_MAC_MNG_B, }; #define hnae3_dev_fd_supported(hdev) \ @@ -151,6 +152,9 @@ enum HNAE3_DEV_CAP_BITS { #define hnae3_ae_dev_rxd_adv_layout_supported(ae_dev) \ test_bit(HNAE3_DEV_SUPPORT_RXD_ADV_LAYOUT_B, (ae_dev)->caps) +#define hnae3_ae_dev_mc_mac_mng_supported(ae_dev) \ + test_bit(HNAE3_DEV_SUPPORT_MC_MAC_MNG_B, (ae_dev)->caps) + enum HNAE3_PF_CAP_BITS { HNAE3_PF_SUPPORT_VLAN_FLTR_MDF_B = 0, }; @@ -341,6 +345,8 @@ struct hnae3_dev_specs { u8 max_non_tso_bd_num; /* max BD number of one non-TSO packet */ u16 max_frm_size; u16 max_qset_num; + u16 umv_size; + u16 mc_mac_size; }; struct hnae3_client_ops { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 2b66c59f5eafd2..a1555f074e06b7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -924,6 +924,10 @@ hns3_dbg_dev_specs(struct hnae3_handle *h, char *buf, int len, int *pos) dev_specs->max_tm_rate); *pos += scnprintf(buf + *pos, len - *pos, "MAX QSET number: %u\n", dev_specs->max_qset_num); + *pos += scnprintf(buf + *pos, len - *pos, "umv size: %u\n", + dev_specs->umv_size); + *pos += scnprintf(buf + *pos, len - *pos, "mc mac size: %u\n", + dev_specs->mc_mac_size); } static int hns3_dbg_dev_info(struct hnae3_handle *h, char *buf, int len) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 33244472e0d0e7..bfcfefa9d2b574 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -1188,7 +1188,10 @@ struct hclge_dev_specs_1_cmd { __le16 max_frm_size; __le16 max_qset_num; __le16 max_int_gl; - u8 rsv1[18]; + u8 rsv0[2]; + __le16 umv_size; + __le16 mc_mac_size; + u8 rsv1[12]; }; /* mac speed type defined in firmware command */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 32f62cd2dd99f4..f0aa4fbd2200e2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -1992,6 +1992,9 @@ static int hclge_dbg_dump_umv_info(struct hclge_dev *hdev, char *buf, int len) } mutex_unlock(&hdev->vport_lock); + pos += scnprintf(buf + pos, len - pos, "used_mc_mac_num : %u\n", + hdev->used_mc_mac_num); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c index e4aad695abcc18..59b0ae7d59e018 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_devlink.c @@ -109,7 +109,6 @@ int hclge_devlink_init(struct hclge_dev *hdev) struct pci_dev *pdev = hdev->pdev; struct hclge_devlink_priv *priv; struct devlink *devlink; - int ret; devlink = devlink_alloc(&hclge_devlink_ops, sizeof(struct hclge_devlink_priv), &pdev->dev); @@ -120,20 +119,9 @@ int hclge_devlink_init(struct hclge_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; - ret = devlink_register(devlink); - if (ret) { - dev_err(&pdev->dev, "failed to register devlink, ret = %d\n", - ret); - goto out_reg_fail; - } - + devlink_register(devlink); devlink_reload_enable(devlink); - return 0; - -out_reg_fail: - devlink_free(devlink); - return ret; } void hclge_devlink_uninit(struct hclge_dev *hdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index f5b8d1fee0f1ae..cd981b33d4ff43 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -1342,8 +1342,6 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) cfg->umv_space = hnae3_get_field(__le32_to_cpu(req->param[1]), HCLGE_CFG_UMV_TBL_SPACE_M, HCLGE_CFG_UMV_TBL_SPACE_S); - if (!cfg->umv_space) - cfg->umv_space = HCLGE_DEFAULT_UMV_SPACE_PER_PF; cfg->pf_rss_size_max = hnae3_get_field(__le32_to_cpu(req->param[2]), HCLGE_CFG_PF_RSS_SIZE_M, @@ -1419,6 +1417,7 @@ static void hclge_set_default_dev_specs(struct hclge_dev *hdev) ae_dev->dev_specs.max_int_gl = HCLGE_DEF_MAX_INT_GL; ae_dev->dev_specs.max_frm_size = HCLGE_MAC_MAX_FRAME; ae_dev->dev_specs.max_qset_num = HCLGE_MAX_QSET_NUM; + ae_dev->dev_specs.umv_size = HCLGE_DEFAULT_UMV_SPACE_PER_PF; } static void hclge_parse_dev_specs(struct hclge_dev *hdev, @@ -1440,6 +1439,8 @@ static void hclge_parse_dev_specs(struct hclge_dev *hdev, ae_dev->dev_specs.max_qset_num = le16_to_cpu(req1->max_qset_num); ae_dev->dev_specs.max_int_gl = le16_to_cpu(req1->max_int_gl); ae_dev->dev_specs.max_frm_size = le16_to_cpu(req1->max_frm_size); + ae_dev->dev_specs.umv_size = le16_to_cpu(req1->umv_size); + ae_dev->dev_specs.mc_mac_size = le16_to_cpu(req1->mc_mac_size); } static void hclge_check_dev_specs(struct hclge_dev *hdev) @@ -1460,6 +1461,8 @@ static void hclge_check_dev_specs(struct hclge_dev *hdev) dev_specs->max_int_gl = HCLGE_DEF_MAX_INT_GL; if (!dev_specs->max_frm_size) dev_specs->max_frm_size = HCLGE_MAC_MAX_FRAME; + if (!dev_specs->umv_size) + dev_specs->umv_size = HCLGE_DEFAULT_UMV_SPACE_PER_PF; } static int hclge_query_dev_specs(struct hclge_dev *hdev) @@ -1549,7 +1552,10 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->tm_info.num_pg = 1; hdev->tc_max = cfg.tc_num; hdev->tm_info.hw_pfc_map = 0; - hdev->wanted_umv_size = cfg.umv_space; + if (cfg.umv_space) + hdev->wanted_umv_size = cfg.umv_space; + else + hdev->wanted_umv_size = hdev->ae_dev->dev_specs.umv_size; hdev->tx_spare_buf_size = cfg.tx_spare_buf_size; hdev->gro_en = true; if (cfg.vlan_fliter_cap == HCLGE_VLAN_FLTR_CAN_MDF) @@ -8498,6 +8504,9 @@ static int hclge_init_umv_space(struct hclge_dev *hdev) hdev->share_umv_size = hdev->priv_umv_size + hdev->max_umv_size % (hdev->num_alloc_vport + 1); + if (hdev->ae_dev->dev_specs.mc_mac_size) + set_bit(HNAE3_DEV_SUPPORT_MC_MAC_MNG_B, hdev->ae_dev->caps); + return 0; } @@ -8515,6 +8524,8 @@ static void hclge_reset_umv_space(struct hclge_dev *hdev) hdev->share_umv_size = hdev->priv_umv_size + hdev->max_umv_size % (hdev->num_alloc_vport + 1); mutex_unlock(&hdev->vport_lock); + + hdev->used_mc_mac_num = 0; } static bool hclge_is_umv_space_full(struct hclge_vport *vport, bool need_lock) @@ -8769,6 +8780,7 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hclge_mac_vlan_tbl_entry_cmd req; struct hclge_desc desc[3]; + bool is_new_addr = false; int status; /* mac addr check */ @@ -8782,6 +8794,13 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, hclge_prepare_mac_addr(&req, addr, true); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (status) { + if (hnae3_ae_dev_mc_mac_mng_supported(hdev->ae_dev) && + hdev->used_mc_mac_num >= + hdev->ae_dev->dev_specs.mc_mac_size) + goto err_no_space; + + is_new_addr = true; + /* This mac addr do not exist, add new entry for it */ memset(desc[0].data, 0, sizeof(desc[0].data)); memset(desc[1].data, 0, sizeof(desc[0].data)); @@ -8791,12 +8810,18 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, if (status) return status; status = hclge_add_mac_vlan_tbl(vport, &req, desc); - /* if already overflow, not to print each time */ - if (status == -ENOSPC && - !(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE)) - dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); + if (status == -ENOSPC) + goto err_no_space; + else if (!status && is_new_addr) + hdev->used_mc_mac_num++; return status; + +err_no_space: + /* if already overflow, not to print each time */ + if (!(vport->overflow_promisc_flags & HNAE3_OVERFLOW_MPE)) + dev_err(&hdev->pdev->dev, "mc mac vlan table is full\n"); + return -ENOSPC; } static int hclge_rm_mc_addr(struct hnae3_handle *handle, @@ -8833,12 +8858,15 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, if (status) return status; - if (hclge_is_all_function_id_zero(desc)) + if (hclge_is_all_function_id_zero(desc)) { /* All the vfid is zero, so need to delete this entry */ status = hclge_remove_mac_vlan_tbl(vport, &req); - else + if (!status) + hdev->used_mc_mac_num--; + } else { /* Not all the vfid is zero, update the vfid */ status = hclge_add_mac_vlan_tbl(vport, &req, desc); + } } else if (status == -ENOENT) { status = 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index de6afbcbfbac48..ca25e2edf3f0d4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -938,6 +938,8 @@ struct hclge_dev { u16 priv_umv_size; /* unicast mac vlan space shared by PF and its VFs */ u16 share_umv_size; + /* multicast mac address number used by PF and its VFs */ + u16 used_mc_mac_num; DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats, HCLGE_MAC_TNL_LOG_SIZE); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c index f478770299c6cd..d60cc9426f7019 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_devlink.c @@ -110,7 +110,6 @@ int hclgevf_devlink_init(struct hclgevf_dev *hdev) struct pci_dev *pdev = hdev->pdev; struct hclgevf_devlink_priv *priv; struct devlink *devlink; - int ret; devlink = devlink_alloc(&hclgevf_devlink_ops, @@ -122,20 +121,9 @@ int hclgevf_devlink_init(struct hclgevf_dev *hdev) priv->hdev = hdev; hdev->devlink = devlink; - ret = devlink_register(devlink); - if (ret) { - dev_err(&pdev->dev, "failed to register devlink, ret = %d\n", - ret); - goto out_reg_fail; - } - + devlink_register(devlink); devlink_reload_enable(devlink); - return 0; - -out_reg_fail: - devlink_free(devlink); - return ret; } void hclgevf_devlink_uninit(struct hclgevf_dev *hdev) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c index 6e11ee339f12f5..60ae8bfc5f69a7 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c @@ -303,11 +303,11 @@ void hinic_devlink_free(struct devlink *devlink) devlink_free(devlink); } -int hinic_devlink_register(struct hinic_devlink_priv *priv) +void hinic_devlink_register(struct hinic_devlink_priv *priv) { struct devlink *devlink = priv_to_devlink(priv); - return devlink_register(devlink); + devlink_register(devlink); } void hinic_devlink_unregister(struct hinic_devlink_priv *priv) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h index 9e315011015c56..46760d607b9b08 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.h @@ -110,7 +110,7 @@ struct host_image_st { struct devlink *hinic_devlink_alloc(struct device *dev); void hinic_devlink_free(struct devlink *devlink); -int hinic_devlink_register(struct hinic_devlink_priv *priv); +void hinic_devlink_register(struct hinic_devlink_priv *priv); void hinic_devlink_unregister(struct hinic_devlink_priv *priv); int hinic_health_reporters_create(struct hinic_devlink_priv *priv); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c index 56b6b04e209b3e..657a15447bd0e3 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c @@ -754,17 +754,9 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev) return err; } - err = hinic_devlink_register(hwdev->devlink_dev); - if (err) { - dev_err(&hwif->pdev->dev, "Failed to register devlink\n"); - hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); - return err; - } - err = hinic_func_to_func_init(hwdev); if (err) { dev_err(&hwif->pdev->dev, "Failed to init mailbox\n"); - hinic_devlink_unregister(hwdev->devlink_dev); hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); return err; } @@ -787,7 +779,7 @@ static int init_pfhwdev(struct hinic_pfhwdev *pfhwdev) } hinic_set_pf_action(hwif, HINIC_PF_MGMT_ACTIVE); - + hinic_devlink_register(hwdev->devlink_dev); return 0; } @@ -799,6 +791,7 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev) { struct hinic_hwdev *hwdev = &pfhwdev->hwdev; + hinic_devlink_unregister(hwdev->devlink_dev); hinic_set_pf_action(hwdev->hwif, HINIC_PF_MGMT_INIT); if (!HINIC_IS_VF(hwdev->hwif)) { @@ -816,8 +809,6 @@ static void free_pfhwdev(struct hinic_pfhwdev *pfhwdev) hinic_func_to_func_free(hwdev); - hinic_devlink_unregister(hwdev->devlink_dev); - hinic_pf_to_mgmt_free(&pfhwdev->pf_to_mgmt); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index ae707e305684b2..9965e8d5d0a964 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1379,10 +1379,8 @@ static int hinic_probe(struct pci_dev *pdev, { int err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "Failed to enable PCI device\n"); - return err; - } + if (err) + return dev_err_probe(&pdev->dev, err, "Failed to enable PCI device\n"); err = pci_request_regions(pdev, HINIC_DRV_NAME); if (err) { diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 664a91af662df8..523c488c71f65f 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2848,7 +2848,6 @@ static int emac_init_phy(struct emac_instance *dev) static int emac_init_config(struct emac_instance *dev) { struct device_node *np = dev->ofdev->dev.of_node; - const void *p; int err; /* Read config from device-tree */ @@ -2976,13 +2975,12 @@ static int emac_init_config(struct emac_instance *dev) } /* Read MAC-address */ - p = of_get_property(np, "local-mac-address", NULL); - if (p == NULL) { - printk(KERN_ERR "%pOF: Can't find local-mac-address property\n", - np); - return -ENXIO; + err = of_get_mac_address(np, dev->ndev->dev_addr); + if (err) { + if (err != -EPROBE_DEFER) + dev_err(&dev->ofdev->dev, "Can't get valid [local-]mac-address from OF !\n"); + return err; } - memcpy(dev->ndev->dev_addr, p, ETH_ALEN); /* IAHT and GAHT filter parameterization */ if (emac_has_feature(dev, EMAC_FTR_EMAC4SYNC)) { diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 3d9b4f99d357f7..3aedb680adb805 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -605,17 +605,13 @@ static int ibmveth_open(struct net_device *netdev) } rc = -ENOMEM; - adapter->bounce_buffer = - kmalloc(netdev->mtu + IBMVETH_BUFF_OH, GFP_KERNEL); - if (!adapter->bounce_buffer) - goto out_free_irq; - adapter->bounce_buffer_dma = - dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer, - netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) { - netdev_err(netdev, "unable to map bounce buffer\n"); - goto out_free_bounce_buffer; + adapter->bounce_buffer = dma_alloc_coherent(&adapter->vdev->dev, + netdev->mtu + IBMVETH_BUFF_OH, + &adapter->bounce_buffer_dma, GFP_KERNEL); + if (!adapter->bounce_buffer) { + netdev_err(netdev, "unable to alloc bounce buffer\n"); + goto out_free_irq; } netdev_dbg(netdev, "initial replenish cycle\n"); @@ -627,8 +623,6 @@ static int ibmveth_open(struct net_device *netdev) return 0; -out_free_bounce_buffer: - kfree(adapter->bounce_buffer); out_free_irq: free_irq(netdev->irq, netdev); out_free_buffer_pools: @@ -702,10 +696,9 @@ static int ibmveth_close(struct net_device *netdev) ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[i]); - dma_unmap_single(&adapter->vdev->dev, adapter->bounce_buffer_dma, - adapter->netdev->mtu + IBMVETH_BUFF_OH, - DMA_BIDIRECTIONAL); - kfree(adapter->bounce_buffer); + dma_free_coherent(&adapter->vdev->dev, + adapter->netdev->mtu + IBMVETH_BUFF_OH, + adapter->bounce_buffer, adapter->bounce_buffer_dma); netdev_dbg(netdev, "close complete\n"); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 6aa6ff89a76511..21efd76dd4274f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -108,6 +108,8 @@ static int init_crq_queue(struct ibmvnic_adapter *adapter); static int send_query_phys_parms(struct ibmvnic_adapter *adapter); static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, struct ibmvnic_sub_crq_queue *tx_scrq); +static void free_long_term_buff(struct ibmvnic_adapter *adapter, + struct ibmvnic_long_term_buff *ltb); struct ibmvnic_stat { char name[ETH_GSTRING_LEN]; @@ -214,22 +216,77 @@ static int ibmvnic_wait_for_completion(struct ibmvnic_adapter *adapter, return -ETIMEDOUT; } +/** + * reuse_ltb() - Check if a long term buffer can be reused + * @ltb: The long term buffer to be checked + * @size: The size of the long term buffer. + * + * An LTB can be reused unless its size has changed. + * + * Return: Return true if the LTB can be reused, false otherwise. + */ +static bool reuse_ltb(struct ibmvnic_long_term_buff *ltb, int size) +{ + return (ltb->buff && ltb->size == size); +} + +/** + * alloc_long_term_buff() - Allocate a long term buffer (LTB) + * + * @adapter: ibmvnic adapter associated to the LTB + * @ltb: container object for the LTB + * @size: size of the LTB + * + * Allocate an LTB of the specified size and notify VIOS. + * + * If the given @ltb already has the correct size, reuse it. Otherwise if + * its non-NULL, free it. Then allocate a new one of the correct size. + * Notify the VIOS either way since we may now be working with a new VIOS. + * + * Allocating larger chunks of memory during resets, specially LPM or under + * low memory situations can cause resets to fail/timeout and for LPAR to + * lose connectivity. So hold onto the LTB even if we fail to communicate + * with the VIOS and reuse it on next open. Free LTB when adapter is closed. + * + * Return: 0 if we were able to allocate the LTB and notify the VIOS and + * a negative value otherwise. + */ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, struct ibmvnic_long_term_buff *ltb, int size) { struct device *dev = &adapter->vdev->dev; int rc; - ltb->size = size; - ltb->buff = dma_alloc_coherent(dev, ltb->size, <b->addr, - GFP_KERNEL); + if (!reuse_ltb(ltb, size)) { + dev_dbg(dev, + "LTB size changed from 0x%llx to 0x%x, reallocating\n", + ltb->size, size); + free_long_term_buff(adapter, ltb); + } - if (!ltb->buff) { - dev_err(dev, "Couldn't alloc long term buffer\n"); - return -ENOMEM; + if (ltb->buff) { + dev_dbg(dev, "Reusing LTB [map %d, size 0x%llx]\n", + ltb->map_id, ltb->size); + } else { + ltb->buff = dma_alloc_coherent(dev, size, <b->addr, + GFP_KERNEL); + if (!ltb->buff) { + dev_err(dev, "Couldn't alloc long term buffer\n"); + return -ENOMEM; + } + ltb->size = size; + + ltb->map_id = find_first_zero_bit(adapter->map_ids, + MAX_MAP_ID); + bitmap_set(adapter->map_ids, ltb->map_id, 1); + + dev_dbg(dev, + "Allocated new LTB [map %d, size 0x%llx]\n", + ltb->map_id, ltb->size); } - ltb->map_id = adapter->map_id; - adapter->map_id++; + + /* Ensure ltb is zeroed - specially when reusing it. */ + memset(ltb->buff, 0, ltb->size); mutex_lock(&adapter->fw_lock); adapter->fw_done_rc = 0; @@ -243,24 +300,20 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter, rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000); if (rc) { - dev_err(dev, - "Long term map request aborted or timed out,rc = %d\n", + dev_err(dev, "LTB map request aborted or timed out, rc = %d\n", rc); goto out; } if (adapter->fw_done_rc) { - dev_err(dev, "Couldn't map long term buffer,rc = %d\n", + dev_err(dev, "Couldn't map LTB, rc = %d\n", adapter->fw_done_rc); rc = -1; goto out; } rc = 0; out: - if (rc) { - dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); - ltb->buff = NULL; - } + /* don't free LTB on communication error - see function header */ mutex_unlock(&adapter->fw_lock); return rc; } @@ -281,48 +334,15 @@ static void free_long_term_buff(struct ibmvnic_adapter *adapter, adapter->reset_reason != VNIC_RESET_MOBILITY && adapter->reset_reason != VNIC_RESET_TIMEOUT) send_request_unmap(adapter, ltb->map_id); + dma_free_coherent(dev, ltb->size, ltb->buff, ltb->addr); + ltb->buff = NULL; + /* mark this map_id free */ + bitmap_clear(adapter->map_ids, ltb->map_id, 1); ltb->map_id = 0; } -static int reset_long_term_buff(struct ibmvnic_adapter *adapter, - struct ibmvnic_long_term_buff *ltb) -{ - struct device *dev = &adapter->vdev->dev; - int rc; - - memset(ltb->buff, 0, ltb->size); - - mutex_lock(&adapter->fw_lock); - adapter->fw_done_rc = 0; - - reinit_completion(&adapter->fw_done); - rc = send_request_map(adapter, ltb->addr, ltb->size, ltb->map_id); - if (rc) { - mutex_unlock(&adapter->fw_lock); - return rc; - } - - rc = ibmvnic_wait_for_completion(adapter, &adapter->fw_done, 10000); - if (rc) { - dev_info(dev, - "Reset failed, long term map request timed out or aborted\n"); - mutex_unlock(&adapter->fw_lock); - return rc; - } - - if (adapter->fw_done_rc) { - dev_info(dev, - "Reset failed, attempting to free and reallocate buffer\n"); - free_long_term_buff(adapter, ltb); - mutex_unlock(&adapter->fw_lock); - return alloc_long_term_buff(adapter, ltb, ltb->size); - } - mutex_unlock(&adapter->fw_lock); - return 0; -} - static void deactivate_rx_pools(struct ibmvnic_adapter *adapter) { int i; @@ -363,31 +383,41 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, * be 0. */ for (i = ind_bufp->index; i < count; ++i) { - skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); + index = pool->free_map[pool->next_free]; + + /* We maybe reusing the skb from earlier resets. Allocate + * only if necessary. But since the LTB may have changed + * during reset (see init_rx_pools()), update LTB below + * even if reusing skb. + */ + skb = pool->rx_buff[index].skb; if (!skb) { - dev_err(dev, "Couldn't replenish rx buff\n"); - adapter->replenish_no_mem++; - break; + skb = netdev_alloc_skb(adapter->netdev, + pool->buff_size); + if (!skb) { + dev_err(dev, "Couldn't replenish rx buff\n"); + adapter->replenish_no_mem++; + break; + } } - index = pool->free_map[pool->next_free]; - - if (pool->rx_buff[index].skb) - dev_err(dev, "Inconsistent free_map!\n"); + pool->free_map[pool->next_free] = IBMVNIC_INVALID_MAP; + pool->next_free = (pool->next_free + 1) % pool->size; /* Copy the skb to the long term mapped DMA buffer */ offset = index * pool->buff_size; dst = pool->long_term_buff.buff + offset; memset(dst, 0, pool->buff_size); dma_addr = pool->long_term_buff.addr + offset; - pool->rx_buff[index].data = dst; - pool->free_map[pool->next_free] = IBMVNIC_INVALID_MAP; + /* add the skb to an rx_buff in the pool */ + pool->rx_buff[index].data = dst; pool->rx_buff[index].dma = dma_addr; pool->rx_buff[index].skb = skb; pool->rx_buff[index].pool_index = pool->index; pool->rx_buff[index].size = pool->buff_size; + /* queue the rx_buff for the next send_subcrq_indirect */ sub_crq = &ind_bufp->indir_arr[ind_bufp->index++]; memset(sub_crq, 0, sizeof(*sub_crq)); sub_crq->rx_add.first = IBMVNIC_CRQ_CMD; @@ -405,7 +435,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter, shift = 8; #endif sub_crq->rx_add.len = cpu_to_be32(pool->buff_size << shift); - pool->next_free = (pool->next_free + 1) % pool->size; + + /* if send_subcrq_indirect queue is full, flush to VIOS */ if (ind_bufp->index == IBMVNIC_MAX_IND_DESCS || i == count - 1) { lpar_rc = @@ -523,53 +554,12 @@ static int init_stats_token(struct ibmvnic_adapter *adapter) return 0; } -static int reset_rx_pools(struct ibmvnic_adapter *adapter) -{ - struct ibmvnic_rx_pool *rx_pool; - u64 buff_size; - int rx_scrqs; - int i, j, rc; - - if (!adapter->rx_pool) - return -1; - - buff_size = adapter->cur_rx_buf_sz; - rx_scrqs = adapter->num_active_rx_pools; - for (i = 0; i < rx_scrqs; i++) { - rx_pool = &adapter->rx_pool[i]; - - netdev_dbg(adapter->netdev, "Re-setting rx_pool[%d]\n", i); - - if (rx_pool->buff_size != buff_size) { - free_long_term_buff(adapter, &rx_pool->long_term_buff); - rx_pool->buff_size = ALIGN(buff_size, L1_CACHE_BYTES); - rc = alloc_long_term_buff(adapter, - &rx_pool->long_term_buff, - rx_pool->size * - rx_pool->buff_size); - } else { - rc = reset_long_term_buff(adapter, - &rx_pool->long_term_buff); - } - - if (rc) - return rc; - - for (j = 0; j < rx_pool->size; j++) - rx_pool->free_map[j] = j; - - memset(rx_pool->rx_buff, 0, - rx_pool->size * sizeof(struct ibmvnic_rx_buff)); - - atomic_set(&rx_pool->available, 0); - rx_pool->next_alloc = 0; - rx_pool->next_free = 0; - rx_pool->active = 1; - } - - return 0; -} - +/** + * release_rx_pools() - Release any rx pools attached to @adapter. + * @adapter: ibmvnic adapter + * + * Safe to call this multiple times - even if no pools are attached. + */ static void release_rx_pools(struct ibmvnic_adapter *adapter) { struct ibmvnic_rx_pool *rx_pool; @@ -584,6 +574,7 @@ static void release_rx_pools(struct ibmvnic_adapter *adapter) netdev_dbg(adapter->netdev, "Releasing rx_pool[%d]\n", i); kfree(rx_pool->free_map); + free_long_term_buff(adapter, &rx_pool->long_term_buff); if (!rx_pool->rx_buff) @@ -602,21 +593,91 @@ static void release_rx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->rx_pool); adapter->rx_pool = NULL; adapter->num_active_rx_pools = 0; + adapter->prev_rx_pool_size = 0; } +/** + * reuse_rx_pools() - Check if the existing rx pools can be reused. + * @adapter: ibmvnic adapter + * + * Check if the existing rx pools in the adapter can be reused. The + * pools can be reused if the pool parameters (number of pools, + * number of buffers in the pool and size of each buffer) have not + * changed. + * + * NOTE: This assumes that all pools have the same number of buffers + * which is the case currently. If that changes, we must fix this. + * + * Return: true if the rx pools can be reused, false otherwise. + */ +static bool reuse_rx_pools(struct ibmvnic_adapter *adapter) +{ + u64 old_num_pools, new_num_pools; + u64 old_pool_size, new_pool_size; + u64 old_buff_size, new_buff_size; + + if (!adapter->rx_pool) + return false; + + old_num_pools = adapter->num_active_rx_pools; + new_num_pools = adapter->req_rx_queues; + + old_pool_size = adapter->prev_rx_pool_size; + new_pool_size = adapter->req_rx_add_entries_per_subcrq; + + old_buff_size = adapter->prev_rx_buf_sz; + new_buff_size = adapter->cur_rx_buf_sz; + + /* Require buff size to be exactly same for now */ + if (old_buff_size != new_buff_size) + return false; + + if (old_num_pools == new_num_pools && old_pool_size == new_pool_size) + return true; + + if (old_num_pools < adapter->min_rx_queues || + old_num_pools > adapter->max_rx_queues || + old_pool_size < adapter->min_rx_add_entries_per_subcrq || + old_pool_size > adapter->max_rx_add_entries_per_subcrq) + return false; + + return true; +} + +/** + * init_rx_pools(): Initialize the set of receiver pools in the adapter. + * @netdev: net device associated with the vnic interface + * + * Initialize the set of receiver pools in the ibmvnic adapter associated + * with the net_device @netdev. If possible, reuse the existing rx pools. + * Otherwise free any existing pools and allocate a new set of pools + * before initializing them. + * + * Return: 0 on success and negative value on error. + */ static int init_rx_pools(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct device *dev = &adapter->vdev->dev; struct ibmvnic_rx_pool *rx_pool; - int rxadd_subcrqs; + u64 num_pools; + u64 pool_size; /* # of buffers in one pool */ u64 buff_size; int i, j; - rxadd_subcrqs = adapter->num_active_rx_scrqs; + pool_size = adapter->req_rx_add_entries_per_subcrq; + num_pools = adapter->req_rx_queues; buff_size = adapter->cur_rx_buf_sz; - adapter->rx_pool = kcalloc(rxadd_subcrqs, + if (reuse_rx_pools(adapter)) { + dev_dbg(dev, "Reusing rx pools\n"); + goto update_ltb; + } + + /* Allocate/populate the pools. */ + release_rx_pools(adapter); + + adapter->rx_pool = kcalloc(num_pools, sizeof(struct ibmvnic_rx_pool), GFP_KERNEL); if (!adapter->rx_pool) { @@ -624,26 +685,27 @@ static int init_rx_pools(struct net_device *netdev) return -1; } - adapter->num_active_rx_pools = rxadd_subcrqs; + /* Set num_active_rx_pools early. If we fail below after partial + * allocation, release_rx_pools() will know how many to look for. + */ + adapter->num_active_rx_pools = num_pools; - for (i = 0; i < rxadd_subcrqs; i++) { + for (i = 0; i < num_pools; i++) { rx_pool = &adapter->rx_pool[i]; netdev_dbg(adapter->netdev, "Initializing rx_pool[%d], %lld buffs, %lld bytes each\n", - i, adapter->req_rx_add_entries_per_subcrq, - buff_size); + i, pool_size, buff_size); - rx_pool->size = adapter->req_rx_add_entries_per_subcrq; + rx_pool->size = pool_size; rx_pool->index = i; rx_pool->buff_size = ALIGN(buff_size, L1_CACHE_BYTES); - rx_pool->active = 1; rx_pool->free_map = kcalloc(rx_pool->size, sizeof(int), GFP_KERNEL); if (!rx_pool->free_map) { - release_rx_pools(adapter); - return -1; + dev_err(dev, "Couldn't alloc free_map %d\n", i); + goto out_release; } rx_pool->rx_buff = kcalloc(rx_pool->size, @@ -651,69 +713,58 @@ static int init_rx_pools(struct net_device *netdev) GFP_KERNEL); if (!rx_pool->rx_buff) { dev_err(dev, "Couldn't alloc rx buffers\n"); - release_rx_pools(adapter); - return -1; + goto out_release; } - - if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff, - rx_pool->size * rx_pool->buff_size)) { - release_rx_pools(adapter); - return -1; - } - - for (j = 0; j < rx_pool->size; ++j) - rx_pool->free_map[j] = j; - - atomic_set(&rx_pool->available, 0); - rx_pool->next_alloc = 0; - rx_pool->next_free = 0; } - return 0; -} - -static int reset_one_tx_pool(struct ibmvnic_adapter *adapter, - struct ibmvnic_tx_pool *tx_pool) -{ - int rc, i; - - rc = reset_long_term_buff(adapter, &tx_pool->long_term_buff); - if (rc) - return rc; + adapter->prev_rx_pool_size = pool_size; + adapter->prev_rx_buf_sz = adapter->cur_rx_buf_sz; - memset(tx_pool->tx_buff, 0, - tx_pool->num_buffers * - sizeof(struct ibmvnic_tx_buff)); - - for (i = 0; i < tx_pool->num_buffers; i++) - tx_pool->free_map[i] = i; +update_ltb: + for (i = 0; i < num_pools; i++) { + rx_pool = &adapter->rx_pool[i]; + dev_dbg(dev, "Updating LTB for rx pool %d [%d, %d]\n", + i, rx_pool->size, rx_pool->buff_size); - tx_pool->consumer_index = 0; - tx_pool->producer_index = 0; + if (alloc_long_term_buff(adapter, &rx_pool->long_term_buff, + rx_pool->size * rx_pool->buff_size)) + goto out; - return 0; -} + for (j = 0; j < rx_pool->size; ++j) { + struct ibmvnic_rx_buff *rx_buff; -static int reset_tx_pools(struct ibmvnic_adapter *adapter) -{ - int tx_scrqs; - int i, rc; + rx_pool->free_map[j] = j; - if (!adapter->tx_pool) - return -1; + /* NOTE: Don't clear rx_buff->skb here - will leak + * memory! replenish_rx_pool() will reuse skbs or + * allocate as necessary. + */ + rx_buff = &rx_pool->rx_buff[j]; + rx_buff->dma = 0; + rx_buff->data = 0; + rx_buff->size = 0; + rx_buff->pool_index = 0; + } - tx_scrqs = adapter->num_active_tx_pools; - for (i = 0; i < tx_scrqs; i++) { - ibmvnic_tx_scrq_clean_buffer(adapter, adapter->tx_scrq[i]); - rc = reset_one_tx_pool(adapter, &adapter->tso_pool[i]); - if (rc) - return rc; - rc = reset_one_tx_pool(adapter, &adapter->tx_pool[i]); - if (rc) - return rc; + /* Mark pool "empty" so replenish_rx_pools() will + * update the LTB info for each buffer + */ + atomic_set(&rx_pool->available, 0); + rx_pool->next_alloc = 0; + rx_pool->next_free = 0; + /* replenish_rx_pool() may have called deactivate_rx_pools() + * on failover. Ensure pool is active now. + */ + rx_pool->active = 1; } - return 0; +out_release: + release_rx_pools(adapter); +out: + /* We failed to allocate one or more LTBs or map them on the VIOS. + * Hold onto the pools and any LTBs that we did allocate/map. + */ + return -1; } static void release_vpd_data(struct ibmvnic_adapter *adapter) @@ -735,10 +786,19 @@ static void release_one_tx_pool(struct ibmvnic_adapter *adapter, free_long_term_buff(adapter, &tx_pool->long_term_buff); } +/** + * release_tx_pools() - Release any tx pools attached to @adapter. + * @adapter: ibmvnic adapter + * + * Safe to call this multiple times - even if no pools are attached. + */ static void release_tx_pools(struct ibmvnic_adapter *adapter) { int i; + /* init_tx_pools() ensures that ->tx_pool and ->tso_pool are + * both NULL or both non-NULL. So we only need to check one. + */ if (!adapter->tx_pool) return; @@ -752,84 +812,218 @@ static void release_tx_pools(struct ibmvnic_adapter *adapter) kfree(adapter->tso_pool); adapter->tso_pool = NULL; adapter->num_active_tx_pools = 0; + adapter->prev_tx_pool_size = 0; } static int init_one_tx_pool(struct net_device *netdev, struct ibmvnic_tx_pool *tx_pool, - int num_entries, int buf_size) + int pool_size, int buf_size) { - struct ibmvnic_adapter *adapter = netdev_priv(netdev); int i; - tx_pool->tx_buff = kcalloc(num_entries, + tx_pool->tx_buff = kcalloc(pool_size, sizeof(struct ibmvnic_tx_buff), GFP_KERNEL); if (!tx_pool->tx_buff) return -1; - if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff, - num_entries * buf_size)) - return -1; - - tx_pool->free_map = kcalloc(num_entries, sizeof(int), GFP_KERNEL); - if (!tx_pool->free_map) + tx_pool->free_map = kcalloc(pool_size, sizeof(int), GFP_KERNEL); + if (!tx_pool->free_map) { + kfree(tx_pool->tx_buff); + tx_pool->tx_buff = NULL; return -1; + } - for (i = 0; i < num_entries; i++) + for (i = 0; i < pool_size; i++) tx_pool->free_map[i] = i; tx_pool->consumer_index = 0; tx_pool->producer_index = 0; - tx_pool->num_buffers = num_entries; + tx_pool->num_buffers = pool_size; tx_pool->buf_size = buf_size; return 0; } +/** + * reuse_tx_pools() - Check if the existing tx pools can be reused. + * @adapter: ibmvnic adapter + * + * Check if the existing tx pools in the adapter can be reused. The + * pools can be reused if the pool parameters (number of pools, + * number of buffers in the pool and mtu) have not changed. + * + * NOTE: This assumes that all pools have the same number of buffers + * which is the case currently. If that changes, we must fix this. + * + * Return: true if the tx pools can be reused, false otherwise. + */ +static bool reuse_tx_pools(struct ibmvnic_adapter *adapter) +{ + u64 old_num_pools, new_num_pools; + u64 old_pool_size, new_pool_size; + u64 old_mtu, new_mtu; + + if (!adapter->tx_pool) + return false; + + old_num_pools = adapter->num_active_tx_pools; + new_num_pools = adapter->num_active_tx_scrqs; + old_pool_size = adapter->prev_tx_pool_size; + new_pool_size = adapter->req_tx_entries_per_subcrq; + old_mtu = adapter->prev_mtu; + new_mtu = adapter->req_mtu; + + /* Require MTU to be exactly same to reuse pools for now */ + if (old_mtu != new_mtu) + return false; + + if (old_num_pools == new_num_pools && old_pool_size == new_pool_size) + return true; + + if (old_num_pools < adapter->min_tx_queues || + old_num_pools > adapter->max_tx_queues || + old_pool_size < adapter->min_tx_entries_per_subcrq || + old_pool_size > adapter->max_tx_entries_per_subcrq) + return false; + + return true; +} + +/** + * init_tx_pools(): Initialize the set of transmit pools in the adapter. + * @netdev: net device associated with the vnic interface + * + * Initialize the set of transmit pools in the ibmvnic adapter associated + * with the net_device @netdev. If possible, reuse the existing tx pools. + * Otherwise free any existing pools and allocate a new set of pools + * before initializing them. + * + * Return: 0 on success and negative value on error. + */ static int init_tx_pools(struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); - int tx_subcrqs; + struct device *dev = &adapter->vdev->dev; + int num_pools; + u64 pool_size; /* # of buffers in pool */ u64 buff_size; - int i, rc; + int i, j, rc; + + num_pools = adapter->req_tx_queues; - tx_subcrqs = adapter->num_active_tx_scrqs; - adapter->tx_pool = kcalloc(tx_subcrqs, + /* We must notify the VIOS about the LTB on all resets - but we only + * need to alloc/populate pools if either the number of buffers or + * size of each buffer in the pool has changed. + */ + if (reuse_tx_pools(adapter)) { + netdev_dbg(netdev, "Reusing tx pools\n"); + goto update_ltb; + } + + /* Allocate/populate the pools. */ + release_tx_pools(adapter); + + pool_size = adapter->req_tx_entries_per_subcrq; + num_pools = adapter->num_active_tx_scrqs; + + adapter->tx_pool = kcalloc(num_pools, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); if (!adapter->tx_pool) return -1; - adapter->tso_pool = kcalloc(tx_subcrqs, + adapter->tso_pool = kcalloc(num_pools, sizeof(struct ibmvnic_tx_pool), GFP_KERNEL); + /* To simplify release_tx_pools() ensure that ->tx_pool and + * ->tso_pool are either both NULL or both non-NULL. + */ if (!adapter->tso_pool) { kfree(adapter->tx_pool); adapter->tx_pool = NULL; return -1; } - adapter->num_active_tx_pools = tx_subcrqs; + /* Set num_active_tx_pools early. If we fail below after partial + * allocation, release_tx_pools() will know how many to look for. + */ + adapter->num_active_tx_pools = num_pools; + + buff_size = adapter->req_mtu + VLAN_HLEN; + buff_size = ALIGN(buff_size, L1_CACHE_BYTES); + + for (i = 0; i < num_pools; i++) { + dev_dbg(dev, "Init tx pool %d [%llu, %llu]\n", + i, adapter->req_tx_entries_per_subcrq, buff_size); - for (i = 0; i < tx_subcrqs; i++) { - buff_size = adapter->req_mtu + VLAN_HLEN; - buff_size = ALIGN(buff_size, L1_CACHE_BYTES); rc = init_one_tx_pool(netdev, &adapter->tx_pool[i], - adapter->req_tx_entries_per_subcrq, - buff_size); - if (rc) { - release_tx_pools(adapter); - return rc; - } + pool_size, buff_size); + if (rc) + goto out_release; rc = init_one_tx_pool(netdev, &adapter->tso_pool[i], IBMVNIC_TSO_BUFS, IBMVNIC_TSO_BUF_SZ); - if (rc) { - release_tx_pools(adapter); - return rc; - } + if (rc) + goto out_release; + } + + adapter->prev_tx_pool_size = pool_size; + adapter->prev_mtu = adapter->req_mtu; + +update_ltb: + /* NOTE: All tx_pools have the same number of buffers (which is + * same as pool_size). All tso_pools have IBMVNIC_TSO_BUFS + * buffers (see calls init_one_tx_pool() for these). + * For consistency, we use tx_pool->num_buffers and + * tso_pool->num_buffers below. + */ + rc = -1; + for (i = 0; i < num_pools; i++) { + struct ibmvnic_tx_pool *tso_pool; + struct ibmvnic_tx_pool *tx_pool; + u32 ltb_size; + + tx_pool = &adapter->tx_pool[i]; + ltb_size = tx_pool->num_buffers * tx_pool->buf_size; + if (alloc_long_term_buff(adapter, &tx_pool->long_term_buff, + ltb_size)) + goto out; + + dev_dbg(dev, "Updated LTB for tx pool %d [%p, %d, %d]\n", + i, tx_pool->long_term_buff.buff, + tx_pool->num_buffers, tx_pool->buf_size); + + tx_pool->consumer_index = 0; + tx_pool->producer_index = 0; + + for (j = 0; j < tx_pool->num_buffers; j++) + tx_pool->free_map[j] = j; + + tso_pool = &adapter->tso_pool[i]; + ltb_size = tso_pool->num_buffers * tso_pool->buf_size; + if (alloc_long_term_buff(adapter, &tso_pool->long_term_buff, + ltb_size)) + goto out; + + dev_dbg(dev, "Updated LTB for tso pool %d [%p, %d, %d]\n", + i, tso_pool->long_term_buff.buff, + tso_pool->num_buffers, tso_pool->buf_size); + + tso_pool->consumer_index = 0; + tso_pool->producer_index = 0; + + for (j = 0; j < tso_pool->num_buffers; j++) + tso_pool->free_map[j] = j; } return 0; +out_release: + release_tx_pools(adapter); +out: + /* We failed to allocate one or more LTBs or map them on the VIOS. + * Hold onto the pools and any LTBs that we did allocate/map. + */ + return rc; } static void ibmvnic_napi_enable(struct ibmvnic_adapter *adapter) @@ -1020,9 +1214,6 @@ static void release_resources(struct ibmvnic_adapter *adapter) { release_vpd_data(adapter); - release_tx_pools(adapter); - release_rx_pools(adapter); - release_napi(adapter); release_login_buffer(adapter); release_login_rsp_buffer(adapter); @@ -1198,8 +1389,6 @@ static int init_resources(struct ibmvnic_adapter *adapter) return rc; } - adapter->map_id = 1; - rc = init_napi(adapter); if (rc) return rc; @@ -1296,6 +1485,8 @@ static int ibmvnic_open(struct net_device *netdev) if (rc) { netdev_err(netdev, "failed to initialize resources\n"); release_resources(adapter); + release_rx_pools(adapter); + release_tx_pools(adapter); goto out; } } @@ -1424,9 +1615,6 @@ static void ibmvnic_cleanup(struct net_device *netdev) ibmvnic_napi_disable(adapter); ibmvnic_disable_irqs(adapter); - - clean_rx_pools(adapter); - clean_tx_pools(adapter); } static int __ibmvnic_close(struct net_device *netdev) @@ -1460,6 +1648,8 @@ static int ibmvnic_close(struct net_device *netdev) rc = __ibmvnic_close(netdev); ibmvnic_cleanup(netdev); + clean_rx_pools(adapter); + clean_tx_pools(adapter); return rc; } @@ -2036,9 +2226,9 @@ static const char *reset_reason_to_string(enum ibmvnic_reset_reason reason) static int do_reset(struct ibmvnic_adapter *adapter, struct ibmvnic_rwi *rwi, u32 reset_state) { + struct net_device *netdev = adapter->netdev; u64 old_num_rx_queues, old_num_tx_queues; u64 old_num_rx_slots, old_num_tx_slots; - struct net_device *netdev = adapter->netdev; int rc; netdev_dbg(adapter->netdev, @@ -2188,8 +2378,6 @@ static int do_reset(struct ibmvnic_adapter *adapter, !adapter->rx_pool || !adapter->tso_pool || !adapter->tx_pool) { - release_rx_pools(adapter); - release_tx_pools(adapter); release_napi(adapter); release_vpd_data(adapter); @@ -2198,16 +2386,18 @@ static int do_reset(struct ibmvnic_adapter *adapter, goto out; } else { - rc = reset_tx_pools(adapter); + rc = init_tx_pools(netdev); if (rc) { - netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", + netdev_dbg(netdev, + "init tx pools failed (%d)\n", rc); goto out; } - rc = reset_rx_pools(adapter); + rc = init_rx_pools(netdev); if (rc) { - netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", + netdev_dbg(netdev, + "init rx pools failed (%d)\n", rc); goto out; } @@ -4778,9 +4968,10 @@ static void handle_query_map_rsp(union ibmvnic_crq *crq, dev_err(dev, "Error %ld in QUERY_MAP_RSP\n", rc); return; } - netdev_dbg(netdev, "page_size = %d\ntot_pages = %d\nfree_pages = %d\n", - crq->query_map_rsp.page_size, crq->query_map_rsp.tot_pages, - crq->query_map_rsp.free_pages); + netdev_dbg(netdev, "page_size = %d\ntot_pages = %u\nfree_pages = %u\n", + crq->query_map_rsp.page_size, + __be32_to_cpu(crq->query_map_rsp.tot_pages), + __be32_to_cpu(crq->query_map_rsp.free_pages)); } static void handle_query_cap_rsp(union ibmvnic_crq *crq, @@ -5527,6 +5718,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->vdev = dev; adapter->netdev = netdev; adapter->login_pending = false; + memset(&adapter->map_ids, 0, sizeof(adapter->map_ids)); + /* map_ids start at 1, so ensure map_id 0 is always "in-use" */ + bitmap_set(adapter->map_ids, 0, 1); ether_addr_copy(adapter->mac_addr, mac_addr_p); ether_addr_copy(netdev->dev_addr, adapter->mac_addr); @@ -5547,6 +5741,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) init_completion(&adapter->reset_done); init_completion(&adapter->stats_done); clear_bit(0, &adapter->resetting); + adapter->prev_rx_buf_sz = 0; + adapter->prev_mtu = 0; init_success = false; do { @@ -5647,6 +5843,8 @@ static void ibmvnic_remove(struct vio_dev *dev) unregister_netdevice(netdev); release_resources(adapter); + release_rx_pools(adapter); + release_tx_pools(adapter); release_sub_crqs(adapter, 1); release_crq_queue(adapter); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 22df602323bc02..b8e42f67d897e1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -827,7 +827,7 @@ struct ibmvnic_rx_buff { struct ibmvnic_rx_pool { struct ibmvnic_rx_buff *rx_buff; - int size; + int size; /* # of buffers in the pool */ int index; int buff_size; atomic_t available; @@ -967,6 +967,7 @@ struct ibmvnic_adapter { u64 min_mtu; u64 max_mtu; u64 req_mtu; + u64 prev_mtu; u64 max_multicast_filters; u64 vlan_header_insertion; u64 rx_vlan_header_insertion; @@ -979,13 +980,18 @@ struct ibmvnic_adapter { u64 opt_tx_entries_per_subcrq; u64 opt_rxba_entries_per_subcrq; __be64 tx_rx_desc_req; - u8 map_id; +#define MAX_MAP_ID 255 + DECLARE_BITMAP(map_ids, MAX_MAP_ID); u32 num_active_rx_scrqs; u32 num_active_rx_pools; u32 num_active_rx_napi; u32 num_active_tx_scrqs; u32 num_active_tx_pools; + + u32 prev_rx_pool_size; + u32 prev_tx_pool_size; u32 cur_rx_buf_sz; + u32 prev_rx_buf_sz; struct tasklet_struct tasklet; enum vnic_state state; diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 5b2143f4b1f85f..f3424255bd2b01 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -21,6 +21,7 @@ #include <linux/ptp_classify.h> #include <linux/mii.h> #include <linux/mdio.h> +#include <linux/mutex.h> #include <linux/pm_qos.h> #include "hw.h" diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 3c4f08d20414e0..83413772b00c61 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -158,6 +158,11 @@ #define ice_pf_to_dev(pf) (&((pf)->pdev->dev)) +enum ice_feature { + ICE_F_DSCP, + ICE_F_MAX +}; + struct ice_txq_meta { u32 q_teid; /* Tx-scheduler element identifier */ u16 q_id; /* Entry in VSI's txq_map bitmap */ @@ -443,6 +448,7 @@ struct ice_pf { /* used to ratelimit the MDD event logging */ unsigned long last_printed_mdd_jiffies; DECLARE_BITMAP(malvfs, ICE_MAX_VF_COUNT); + DECLARE_BITMAP(features, ICE_F_MAX); DECLARE_BITMAP(state, ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS); unsigned long *avail_txqs; /* bitmap to track PF Tx queue usage */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 21b4c7cd6f0502..d407cf8c829d40 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -671,6 +671,16 @@ struct ice_aqc_sw_rules_elem { } __packed pdata; }; +/* Query PFC Mode (direct 0x0302) + * Set PFC Mode (direct 0x0303) + */ +struct ice_aqc_set_query_pfc_mode { + u8 pfc_mode; +/* For Query Command response, reserved in all other cases */ +#define ICE_AQC_PFC_VLAN_BASED_PFC 1 +#define ICE_AQC_PFC_DSCP_BASED_PFC 2 + u8 rsvd[15]; +}; /* Get Default Topology (indirect 0x0400) */ struct ice_aqc_get_topo { u8 port_num; @@ -1936,6 +1946,7 @@ struct ice_aq_desc { struct ice_aqc_nvm_pkg_data pkg_data; struct ice_aqc_nvm_pass_comp_tbl pass_comp_tbl; struct ice_aqc_pf_vf_msg virt; + struct ice_aqc_set_query_pfc_mode set_query_pfc_mode; struct ice_aqc_lldp_get_mib lldp_get_mib; struct ice_aqc_lldp_set_mib_change lldp_set_event; struct ice_aqc_lldp_stop lldp_stop; @@ -2040,6 +2051,10 @@ enum ice_adminq_opc { ice_aqc_opc_clear_pf_cfg = 0x02A4, + /* DCB commands */ + ice_aqc_opc_query_pfc_mode = 0x0302, + ice_aqc_opc_set_pfc_mode = 0x0303, + /* transmit scheduler commands */ ice_aqc_opc_get_dflt_topo = 0x0400, ice_aqc_opc_add_sched_elems = 0x0401, diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 88d98c9e5f914d..3071b8e7949980 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -513,7 +513,7 @@ void ice_init_arfs(struct ice_vsi *vsi) if (!vsi || vsi->type != ICE_VSI_PF) return; - arfs_fltr_list = kzalloc(sizeof(*arfs_fltr_list) * ICE_MAX_ARFS_LIST, + arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list), GFP_KERNEL); if (!arfs_fltr_list) return; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index 849fcf60547908..241427cd9bc02e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include "ice_common.h" +#include "ice_lib.h" #include "ice_sched.h" #include "ice_dcb.h" @@ -736,6 +737,45 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw, } /** + * ice_aq_set_pfc_mode - Set PFC mode + * @hw: pointer to the HW struct + * @pfc_mode: value of PFC mode to set + * @cd: pointer to command details structure or NULL + * + * This AQ call configures the PFC mode to DSCP-based PFC mode or + * VLAN-based PFC (0x0303) + */ +int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd) +{ + struct ice_aqc_set_query_pfc_mode *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + if (pfc_mode > ICE_AQC_PFC_DSCP_BASED_PFC) + return -EINVAL; + + cmd = &desc.params.set_query_pfc_mode; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_pfc_mode); + + cmd->pfc_mode = pfc_mode; + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (status) + return ice_status_to_errno(status); + + /* FW will write the PFC mode set back into cmd->pfc_mode, but if DCB is + * disabled, FW will write back 0 to cmd->pfc_mode. After the AQ has + * been executed, check if cmd->pfc_mode is what was requested. If not, + * return an error. + */ + if (cmd->pfc_mode != pfc_mode) + return -EOPNOTSUPP; + + return 0; +} + +/** * ice_cee_to_dcb_cfg * @cee_cfg: pointer to CEE configuration struct * @pi: port information structure @@ -1207,7 +1247,140 @@ ice_add_ieee_app_pri_tlv(struct ice_lldp_org_tlv *tlv, } /** - * ice_add_dcb_tlv - Add all IEEE TLVs + * ice_add_dscp_up_tlv - Prepare DSCP to UP TLV + * @tlv: location to build the TLV data + * @dcbcfg: location of data to convert to TLV + */ +static void +ice_add_dscp_up_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) +{ + u8 *buf = tlv->tlvinfo; + u32 ouisubtype; + u16 typelen; + int i; + + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_DSCP_UP_TLV_LEN); + tlv->typelen = htons(typelen); + + ouisubtype = (u32)((ICE_DSCP_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_DSCP_SUBTYPE_DSCP2UP); + tlv->ouisubtype = htonl(ouisubtype); + + /* bytes 0 - 63 - IPv4 DSCP2UP LUT */ + for (i = 0; i < ICE_DSCP_NUM_VAL; i++) { + /* IPv4 mapping */ + buf[i] = dcbcfg->dscp_map[i]; + /* IPv6 mapping */ + buf[i + ICE_DSCP_IPV6_OFFSET] = dcbcfg->dscp_map[i]; + } + + /* byte 64 - IPv4 untagged traffic */ + buf[i] = 0; + + /* byte 144 - IPv6 untagged traffic */ + buf[i + ICE_DSCP_IPV6_OFFSET] = 0; +} + +#define ICE_BYTES_PER_TC 8 +/** + * ice_add_dscp_enf_tlv - Prepare DSCP Enforcement TLV + * @tlv: location to build the TLV data + */ +static void +ice_add_dscp_enf_tlv(struct ice_lldp_org_tlv *tlv) +{ + u8 *buf = tlv->tlvinfo; + u32 ouisubtype; + u16 typelen; + + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_DSCP_ENF_TLV_LEN); + tlv->typelen = htons(typelen); + + ouisubtype = (u32)((ICE_DSCP_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_DSCP_SUBTYPE_ENFORCE); + tlv->ouisubtype = htonl(ouisubtype); + + /* Allow all DSCP values to be valid for all TC's (IPv4 and IPv6) */ + memset(buf, 0, 2 * (ICE_MAX_TRAFFIC_CLASS * ICE_BYTES_PER_TC)); +} + +/** + * ice_add_dscp_tc_bw_tlv - Prepare DSCP BW for TC TLV + * @tlv: location to build the TLV data + * @dcbcfg: location of the data to convert to TLV + */ +static void +ice_add_dscp_tc_bw_tlv(struct ice_lldp_org_tlv *tlv, + struct ice_dcbx_cfg *dcbcfg) +{ + struct ice_dcb_ets_cfg *etscfg; + u8 *buf = tlv->tlvinfo; + u32 ouisubtype; + u8 offset = 0; + u16 typelen; + int i; + + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_DSCP_TC_BW_TLV_LEN); + tlv->typelen = htons(typelen); + + ouisubtype = (u32)((ICE_DSCP_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_DSCP_SUBTYPE_TCBW); + tlv->ouisubtype = htonl(ouisubtype); + + /* First Octect after subtype + * ---------------------------- + * | RSV | CBS | RSV | Max TCs | + * | 1b | 1b | 3b | 3b | + * ---------------------------- + */ + etscfg = &dcbcfg->etscfg; + buf[0] = etscfg->maxtcs & ICE_IEEE_ETS_MAXTC_M; + + /* bytes 1 - 4 reserved */ + offset = 5; + + /* TC BW table + * bytes 0 - 7 for TC 0 - 7 + * + * TSA Assignment table + * bytes 8 - 15 for TC 0 - 7 + */ + for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { + buf[offset] = etscfg->tcbwtable[i]; + buf[offset + ICE_MAX_TRAFFIC_CLASS] = etscfg->tsatable[i]; + offset++; + } +} + +/** + * ice_add_dscp_pfc_tlv - Prepare DSCP PFC TLV + * @tlv: Fill PFC TLV in IEEE format + * @dcbcfg: Local store which holds the PFC CFG data + */ +static void +ice_add_dscp_pfc_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg) +{ + u8 *buf = tlv->tlvinfo; + u32 ouisubtype; + u16 typelen; + + typelen = ((ICE_TLV_TYPE_ORG << ICE_LLDP_TLV_TYPE_S) | + ICE_DSCP_PFC_TLV_LEN); + tlv->typelen = htons(typelen); + + ouisubtype = (u32)((ICE_DSCP_OUI << ICE_LLDP_TLV_OUI_S) | + ICE_DSCP_SUBTYPE_PFC); + tlv->ouisubtype = htonl(ouisubtype); + + buf[0] = dcbcfg->pfc.pfccap & 0xF; + buf[1] = dcbcfg->pfc.pfcena & 0xF; +} + +/** + * ice_add_dcb_tlv - Add all IEEE or DSCP TLVs * @tlv: Fill TLV data in IEEE format * @dcbcfg: Local store which holds the DCB Config * @tlvid: Type of IEEE TLV @@ -1218,21 +1391,41 @@ static void ice_add_dcb_tlv(struct ice_lldp_org_tlv *tlv, struct ice_dcbx_cfg *dcbcfg, u16 tlvid) { - switch (tlvid) { - case ICE_IEEE_TLV_ID_ETS_CFG: - ice_add_ieee_ets_tlv(tlv, dcbcfg); - break; - case ICE_IEEE_TLV_ID_ETS_REC: - ice_add_ieee_etsrec_tlv(tlv, dcbcfg); - break; - case ICE_IEEE_TLV_ID_PFC_CFG: - ice_add_ieee_pfc_tlv(tlv, dcbcfg); - break; - case ICE_IEEE_TLV_ID_APP_PRI: - ice_add_ieee_app_pri_tlv(tlv, dcbcfg); - break; - default: - break; + if (dcbcfg->pfc_mode == ICE_QOS_MODE_VLAN) { + switch (tlvid) { + case ICE_IEEE_TLV_ID_ETS_CFG: + ice_add_ieee_ets_tlv(tlv, dcbcfg); + break; + case ICE_IEEE_TLV_ID_ETS_REC: + ice_add_ieee_etsrec_tlv(tlv, dcbcfg); + break; + case ICE_IEEE_TLV_ID_PFC_CFG: + ice_add_ieee_pfc_tlv(tlv, dcbcfg); + break; + case ICE_IEEE_TLV_ID_APP_PRI: + ice_add_ieee_app_pri_tlv(tlv, dcbcfg); + break; + default: + break; + } + } else { + /* pfc_mode == ICE_QOS_MODE_DSCP */ + switch (tlvid) { + case ICE_TLV_ID_DSCP_UP: + ice_add_dscp_up_tlv(tlv, dcbcfg); + break; + case ICE_TLV_ID_DSCP_ENF: + ice_add_dscp_enf_tlv(tlv); + break; + case ICE_TLV_ID_DSCP_TC_BW: + ice_add_dscp_tc_bw_tlv(tlv, dcbcfg); + break; + case ICE_TLV_ID_DSCP_TO_PFC: + ice_add_dscp_pfc_tlv(tlv, dcbcfg); + break; + default: + break; + } } } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h index d7e5e6178a21c1..9b6f87a889a633 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb.h @@ -22,6 +22,14 @@ #define ICE_CEE_DCBX_OUI 0x001B21 #define ICE_CEE_DCBX_TYPE 2 + +#define ICE_DSCP_OUI 0xFFFFFF +#define ICE_DSCP_SUBTYPE_DSCP2UP 0x41 +#define ICE_DSCP_SUBTYPE_ENFORCE 0x42 +#define ICE_DSCP_SUBTYPE_TCBW 0x43 +#define ICE_DSCP_SUBTYPE_PFC 0x44 +#define ICE_DSCP_IPV6_OFFSET 80 + #define ICE_CEE_SUBTYPE_PG_CFG 2 #define ICE_CEE_SUBTYPE_PFC_CFG 3 #define ICE_CEE_SUBTYPE_APP_PRI 4 @@ -78,11 +86,20 @@ #define ICE_IEEE_TLV_ID_APP_PRI 6 #define ICE_TLV_ID_END_OF_LLDPPDU 7 #define ICE_TLV_ID_START ICE_IEEE_TLV_ID_ETS_CFG +#define ICE_TLV_ID_DSCP_UP 3 +#define ICE_TLV_ID_DSCP_ENF 4 +#define ICE_TLV_ID_DSCP_TC_BW 5 +#define ICE_TLV_ID_DSCP_TO_PFC 6 #define ICE_IEEE_ETS_TLV_LEN 25 #define ICE_IEEE_PFC_TLV_LEN 6 #define ICE_IEEE_APP_TLV_LEN 11 +#define ICE_DSCP_UP_TLV_LEN 148 +#define ICE_DSCP_ENF_TLV_LEN 132 +#define ICE_DSCP_TC_BW_TLV_LEN 25 +#define ICE_DSCP_PFC_TLV_LEN 6 + /* IEEE 802.1AB LLDP Organization specific TLV */ struct ice_lldp_org_tlv { __be16 typelen; @@ -120,6 +137,7 @@ struct ice_cee_app_prio { u8 prio_map; } __packed; +int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd); enum ice_status ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, struct ice_dcbx_cfg *dcbcfg); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 926cf748c5ecd1..26b4d5f579e6bb 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -544,7 +544,7 @@ static int ice_dcb_init_cfg(struct ice_pf *pf, bool locked) * @ets_willing: configure ETS willing * @locked: was this function called with RTNL held */ -static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked) +int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked) { struct ice_aqc_port_ets_elem buf = { 0 }; struct ice_dcbx_cfg *dcbcfg; @@ -726,6 +726,11 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) /* FW LLDP is disabled, activate SW DCBX/LLDP mode */ dev_info(dev, "FW LLDP is disabled, DCBx/LLDP in SW mode.\n"); clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); + err = ice_aq_set_pfc_mode(&pf->hw, ICE_AQC_PFC_VLAN_BASED_PFC, + NULL); + if (err) + dev_info(dev, "Failed to set VLAN PFC mode\n"); + err = ice_dcb_sw_dflt_cfg(pf, true, locked); if (err) { dev_err(dev, "Failed to set local DCB config %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 261b6e2ed7bc24..3dcde1750a5e37 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -15,6 +15,7 @@ #define ICE_DCB_HW_CHG 2 /* DCB configuration changed, no reset */ void ice_dcb_rebuild(struct ice_pf *pf); +int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool ets_willing, bool locked); u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg *dcbcfg); u8 ice_dcb_get_num_tc(struct ice_dcbx_cfg *dcbcfg); void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi); @@ -59,6 +60,12 @@ static inline bool ice_is_dcb_active(struct ice_pf *pf) return (test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags) || test_bit(ICE_FLAG_DCB_ENA, pf->flags)); } + +static inline u8 ice_get_pfc_mode(struct ice_pf *pf) +{ + return pf->hw.port_info->qos_cfg.local_dcbx_cfg.pfc_mode; +} + #else static inline void ice_dcb_rebuild(struct ice_pf *pf) { } @@ -113,6 +120,11 @@ ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf, return false; } +static inline u8 ice_get_pfc_mode(struct ice_pf *pf) +{ + return 0; +} + static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { } static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } static inline void ice_update_dcb_stats(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 4180f1f35fb89c..7fdeb411b6df44 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -64,7 +64,7 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_dcbx_cfg *new_cfg; int bwcfg = 0, bwrec = 0; - int err, i, max_tc = 0; + int err, i; if ((pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) || !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) @@ -80,13 +80,14 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) new_cfg->etscfg.tcbwtable[i] = ets->tc_tx_bw[i]; bwcfg += ets->tc_tx_bw[i]; new_cfg->etscfg.tsatable[i] = ets->tc_tsa[i]; - new_cfg->etscfg.prio_table[i] = ets->prio_tc[i]; - if (ets->prio_tc[i] > max_tc) - max_tc = ets->prio_tc[i]; + if (new_cfg->pfc_mode == ICE_QOS_MODE_VLAN) { + /* in DSCP mode up->tc mapping cannot change */ + new_cfg->etscfg.prio_table[i] = ets->prio_tc[i]; + new_cfg->etsrec.prio_table[i] = ets->reco_prio_tc[i]; + } new_cfg->etsrec.tcbwtable[i] = ets->tc_reco_bw[i]; bwrec += ets->tc_reco_bw[i]; new_cfg->etsrec.tsatable[i] = ets->tc_reco_tsa[i]; - new_cfg->etsrec.prio_table[i] = ets->reco_prio_tc[i]; } if (ice_dcb_bwchk(pf, new_cfg)) { @@ -94,12 +95,7 @@ static int ice_dcbnl_setets(struct net_device *netdev, struct ieee_ets *ets) goto ets_out; } - max_tc = pf->hw.func_caps.common_cap.maxtc; - - new_cfg->etscfg.maxtcs = max_tc; - - if (!bwcfg) - new_cfg->etscfg.tcbwtable[0] = 100; + new_cfg->etscfg.maxtcs = pf->hw.func_caps.common_cap.maxtc; if (!bwrec) new_cfg->etsrec.tcbwtable[0] = 100; @@ -173,10 +169,13 @@ static u8 ice_dcbnl_setdcbx(struct net_device *netdev, u8 mode) pf->dcbx_cap = mode; qos_cfg = &pf->hw.port_info->qos_cfg; - if (mode & DCB_CAP_DCBX_VER_CEE) + if (mode & DCB_CAP_DCBX_VER_CEE) { + if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP) + return ICE_DCB_NO_HW_CHG; qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_CEE; - else + } else { qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_IEEE; + } dev_info(ice_pf_to_dev(pf), "DCBx mode = 0x%x\n", mode); return ICE_DCB_HW_CHG_RST; @@ -683,6 +682,8 @@ ice_dcbnl_find_app(struct ice_dcbx_cfg *cfg, return false; } +#define ICE_BYTES_PER_DSCP_VAL 8 + /** * ice_dcbnl_setapp - set local IEEE App config * @netdev: relevant netdev struct @@ -693,42 +694,117 @@ static int ice_dcbnl_setapp(struct net_device *netdev, struct dcb_app *app) struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_dcb_app_priority_table new_app; struct ice_dcbx_cfg *old_cfg, *new_cfg; + u8 max_tc; int ret; - if ((pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) || - !(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + /* ONLY DSCP APP TLVs have operational significance */ + if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP) return -EINVAL; - mutex_lock(&pf->tc_mutex); + /* only allow APP TLVs in SW Mode */ + if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) { + netdev_err(netdev, "can't do DSCP QoS when FW DCB agent active\n"); + return -EINVAL; + } - new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; + if (!(pf->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; - old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + if (!ice_is_feature_supported(pf, ICE_F_DSCP)) + return -EOPNOTSUPP; - if (old_cfg->numapps == ICE_DCBX_MAX_APPS) { - ret = -EINVAL; - goto setapp_out; + if (app->protocol >= ICE_DSCP_NUM_VAL) { + netdev_err(netdev, "DSCP value 0x%04X out of range\n", + app->protocol); + return -EINVAL; + } + + max_tc = pf->hw.func_caps.common_cap.maxtc; + if (app->priority >= max_tc) { + netdev_err(netdev, "TC %d out of range, max TC %d\n", + app->priority, max_tc); + return -EINVAL; } + /* grab TC mutex */ + mutex_lock(&pf->tc_mutex); + + new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; + old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + ret = dcb_ieee_setapp(netdev, app); if (ret) goto setapp_out; + if (test_and_set_bit(app->protocol, new_cfg->dscp_mapped)) { + netdev_err(netdev, "DSCP value 0x%04X already user mapped\n", + app->protocol); + ret = dcb_ieee_delapp(netdev, app); + if (ret) + netdev_err(netdev, "Failed to delete re-mapping TLV\n"); + ret = -EINVAL; + goto setapp_out; + } + new_app.selector = app->selector; new_app.prot_id = app->protocol; new_app.priority = app->priority; - if (ice_dcbnl_find_app(old_cfg, &new_app)) { - ret = 0; - goto setapp_out; - } + /* If port is not in DSCP mode, need to set */ + if (old_cfg->pfc_mode == ICE_QOS_MODE_VLAN) { + int i, j; + + /* set DSCP mode */ + ret = ice_aq_set_pfc_mode(&pf->hw, ICE_AQC_PFC_DSCP_BASED_PFC, + NULL); + if (ret) { + netdev_err(netdev, "Failed to set DSCP PFC mode %d\n", + ret); + goto setapp_out; + } + netdev_info(netdev, "Switched QoS to L3 DSCP mode\n"); + + new_cfg->pfc_mode = ICE_QOS_MODE_DSCP; + + /* set default DSCP QoS values */ + new_cfg->etscfg.willing = 0; + new_cfg->pfc.pfccap = max_tc; + new_cfg->pfc.willing = 0; + + for (i = 0; i < max_tc; i++) + for (j = 0; j < ICE_BYTES_PER_DSCP_VAL; j++) { + int dscp, offset; + + dscp = (i * max_tc) + j; + offset = max_tc * ICE_BYTES_PER_DSCP_VAL; + + new_cfg->dscp_map[dscp] = i; + /* if less that 8 TCs supported */ + if (max_tc < ICE_MAX_TRAFFIC_CLASS) + new_cfg->dscp_map[dscp + offset] = i; + } + + new_cfg->etscfg.tcbwtable[0] = 100; + new_cfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS; + new_cfg->etscfg.prio_table[0] = 0; + + for (i = 1; i < max_tc; i++) { + new_cfg->etscfg.tcbwtable[i] = 0; + new_cfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS; + new_cfg->etscfg.prio_table[i] = i; + } + } /* end of switching to DSCP mode */ + + /* apply new mapping for this DSCP value */ + new_cfg->dscp_map[app->protocol] = app->priority; new_cfg->app[new_cfg->numapps++] = new_app; + ret = ice_pf_dcb_cfg(pf, new_cfg, true); /* return of zero indicates new cfg applied */ if (ret == ICE_DCB_HW_CHG_RST) ice_dcbnl_devreset(netdev); - if (ret == ICE_DCB_NO_HW_CHG) - ret = ICE_DCB_HW_CHG_RST; + else + ret = ICE_DCB_NO_HW_CHG; setapp_out: mutex_unlock(&pf->tc_mutex); @@ -749,22 +825,21 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) unsigned int i, j; int ret = 0; - if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) + if (pf->dcbx_cap & DCB_CAP_DCBX_LLD_MANAGED) { + netdev_err(netdev, "can't delete DSCP netlink app when FW DCB agent is active\n"); return -EINVAL; + } mutex_lock(&pf->tc_mutex); old_cfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; - if (old_cfg->numapps <= 1) - goto delapp_out; - ret = dcb_ieee_delapp(netdev, app); if (ret) goto delapp_out; new_cfg = &pf->hw.port_info->qos_cfg.desired_dcbx_cfg; - for (i = 1; i < new_cfg->numapps; i++) { + for (i = 0; i < new_cfg->numapps; i++) { if (app->selector == new_cfg->app[i].selector && app->protocol == new_cfg->app[i].prot_id && app->priority == new_cfg->app[i].priority) { @@ -784,17 +859,58 @@ static int ice_dcbnl_delapp(struct net_device *netdev, struct dcb_app *app) new_cfg->numapps--; for (j = i; j < new_cfg->numapps; j++) { - new_cfg->app[i].selector = old_cfg->app[j + 1].selector; - new_cfg->app[i].prot_id = old_cfg->app[j + 1].prot_id; - new_cfg->app[i].priority = old_cfg->app[j + 1].priority; + new_cfg->app[j].selector = old_cfg->app[j + 1].selector; + new_cfg->app[j].prot_id = old_cfg->app[j + 1].prot_id; + new_cfg->app[j].priority = old_cfg->app[j + 1].priority; } - ret = ice_pf_dcb_cfg(pf, new_cfg, true); - /* return of zero indicates new cfg applied */ + /* if not a DSCP APP TLV or DSCP is not supported, we are done */ + if (app->selector != IEEE_8021QAZ_APP_SEL_DSCP || + !ice_is_feature_supported(pf, ICE_F_DSCP)) { + ret = ICE_DCB_HW_CHG; + goto delapp_out; + } + + /* if DSCP TLV, then need to address change in mapping */ + clear_bit(app->protocol, new_cfg->dscp_mapped); + /* remap this DSCP value to default value */ + new_cfg->dscp_map[app->protocol] = app->protocol % + ICE_BYTES_PER_DSCP_VAL; + + /* if the last DSCP mapping just got deleted, need to switch + * to L2 VLAN QoS mode + */ + if (bitmap_empty(new_cfg->dscp_mapped, ICE_DSCP_NUM_VAL) && + new_cfg->pfc_mode == ICE_QOS_MODE_DSCP) { + ret = ice_aq_set_pfc_mode(&pf->hw, + ICE_AQC_PFC_VLAN_BASED_PFC, + NULL); + if (ret) { + netdev_info(netdev, "Failed to set VLAN PFC mode %d\n", + ret); + goto delapp_out; + } + netdev_info(netdev, "Switched QoS to L2 VLAN mode\n"); + + new_cfg->pfc_mode = ICE_QOS_MODE_VLAN; + + ret = ice_dcb_sw_dflt_cfg(pf, true, true); + } else { + ret = ice_pf_dcb_cfg(pf, new_cfg, true); + } + + /* return of ICE_DCB_HW_CHG_RST indicates new cfg applied + * and reset needs to be performed + */ if (ret == ICE_DCB_HW_CHG_RST) ice_dcbnl_devreset(netdev); + + /* if the change was not siginificant enough to actually call + * the reconfiguration flow, we still need to tell caller that + * their request was successfully handled + */ if (ret == ICE_DCB_NO_HW_CHG) - ret = ICE_DCB_HW_CHG_RST; + ret = ICE_DCB_HW_CHG; delapp_out: mutex_unlock(&pf->tc_mutex); diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 14afce82ef6312..cae1cd97a1efad 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -22,7 +22,7 @@ struct ice_info_ctx { * * If a version does not exist, for example when attempting to get the * inactive version of flash when there is no pending update, the function - * should leave the buffer in the ctx structure empty and return 0. + * should leave the buffer in the ctx structure empty. */ static void ice_info_get_dsn(struct ice_pf *pf, struct ice_info_ctx *ctx) @@ -35,7 +35,7 @@ static void ice_info_get_dsn(struct ice_pf *pf, struct ice_info_ctx *ctx) snprintf(ctx->buf, sizeof(ctx->buf), "%8phD", dsn); } -static int ice_info_pba(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_pba(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; enum ice_status status; @@ -45,148 +45,127 @@ static int ice_info_pba(struct ice_pf *pf, struct ice_info_ctx *ctx) /* We failed to locate the PBA, so just skip this entry */ dev_dbg(ice_pf_to_dev(pf), "Failed to read Product Board Assembly string, status %s\n", ice_stat_str(status)); - - return 0; } -static int ice_info_fw_mgmt(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_fw_mgmt(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; - snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", hw->fw_maj_ver, hw->fw_min_ver, - hw->fw_patch); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", + hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch); } -static int ice_info_fw_api(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_fw_api(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; - snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u", hw->api_maj_ver, hw->api_min_ver); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u", + hw->api_maj_ver, hw->api_min_ver); } -static int ice_info_fw_build(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_fw_build(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", hw->fw_build); - - return 0; } -static int ice_info_orom_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_orom_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_orom_info *orom = &pf->hw.flash.orom; - snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", orom->major, orom->build, orom->patch); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", + orom->major, orom->build, orom->patch); } -static int -ice_info_pending_orom_ver(struct ice_pf __always_unused *pf, struct ice_info_ctx *ctx) +static void +ice_info_pending_orom_ver(struct ice_pf __always_unused *pf, + struct ice_info_ctx *ctx) { struct ice_orom_info *orom = &ctx->pending_orom; if (ctx->dev_caps.common_cap.nvm_update_pending_orom) snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", orom->major, orom->build, orom->patch); - - return 0; } -static int ice_info_nvm_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_nvm_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_nvm_info *nvm = &pf->hw.flash.nvm; snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor); - - return 0; } -static int -ice_info_pending_nvm_ver(struct ice_pf __always_unused *pf, struct ice_info_ctx *ctx) +static void +ice_info_pending_nvm_ver(struct ice_pf __always_unused *pf, + struct ice_info_ctx *ctx) { struct ice_nvm_info *nvm = &ctx->pending_nvm; if (ctx->dev_caps.common_cap.nvm_update_pending_nvm) - snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", nvm->major, nvm->minor); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%x.%02x", + nvm->major, nvm->minor); } -static int ice_info_eetrack(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_eetrack(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_nvm_info *nvm = &pf->hw.flash.nvm; snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm->eetrack); - - return 0; } -static int -ice_info_pending_eetrack(struct ice_pf __always_unused *pf, struct ice_info_ctx *ctx) +static void +ice_info_pending_eetrack(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_nvm_info *nvm = &ctx->pending_nvm; if (ctx->dev_caps.common_cap.nvm_update_pending_nvm) snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", nvm->eetrack); - - return 0; } -static int ice_info_ddp_pkg_name(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_ddp_pkg_name(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_hw *hw = &pf->hw; snprintf(ctx->buf, sizeof(ctx->buf), "%s", hw->active_pkg_name); - - return 0; } -static int ice_info_ddp_pkg_version(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void +ice_info_ddp_pkg_version(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_pkg_ver *pkg = &pf->hw.active_pkg_ver; - snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u.%u", pkg->major, pkg->minor, pkg->update, - pkg->draft); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u.%u", + pkg->major, pkg->minor, pkg->update, pkg->draft); } -static int ice_info_ddp_pkg_bundle_id(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void +ice_info_ddp_pkg_bundle_id(struct ice_pf *pf, struct ice_info_ctx *ctx) { snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", pf->hw.active_track_id); - - return 0; } -static int ice_info_netlist_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_netlist_ver(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_netlist_info *netlist = &pf->hw.flash.netlist; /* The netlist version fields are BCD formatted */ - snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x", netlist->major, netlist->minor, - netlist->type >> 16, netlist->type & 0xFFFF, netlist->rev, - netlist->cust_ver); - - return 0; + snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x", + netlist->major, netlist->minor, + netlist->type >> 16, netlist->type & 0xFFFF, + netlist->rev, netlist->cust_ver); } -static int ice_info_netlist_build(struct ice_pf *pf, struct ice_info_ctx *ctx) +static void ice_info_netlist_build(struct ice_pf *pf, struct ice_info_ctx *ctx) { struct ice_netlist_info *netlist = &pf->hw.flash.netlist; snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash); - - return 0; } -static int -ice_info_pending_netlist_ver(struct ice_pf __always_unused *pf, struct ice_info_ctx *ctx) +static void +ice_info_pending_netlist_ver(struct ice_pf __always_unused *pf, + struct ice_info_ctx *ctx) { struct ice_netlist_info *netlist = &ctx->pending_netlist; @@ -194,21 +173,18 @@ ice_info_pending_netlist_ver(struct ice_pf __always_unused *pf, struct ice_info_ if (ctx->dev_caps.common_cap.nvm_update_pending_netlist) snprintf(ctx->buf, sizeof(ctx->buf), "%x.%x.%x-%x.%x.%x", netlist->major, netlist->minor, - netlist->type >> 16, netlist->type & 0xFFFF, netlist->rev, - netlist->cust_ver); - - return 0; + netlist->type >> 16, netlist->type & 0xFFFF, + netlist->rev, netlist->cust_ver); } -static int -ice_info_pending_netlist_build(struct ice_pf __always_unused *pf, struct ice_info_ctx *ctx) +static void +ice_info_pending_netlist_build(struct ice_pf __always_unused *pf, + struct ice_info_ctx *ctx) { struct ice_netlist_info *netlist = &ctx->pending_netlist; if (ctx->dev_caps.common_cap.nvm_update_pending_netlist) snprintf(ctx->buf, sizeof(ctx->buf), "0x%08x", netlist->hash); - - return 0; } #define fixed(key, getter) { ICE_VERSION_FIXED, key, getter, NULL } @@ -238,8 +214,8 @@ enum ice_version_type { static const struct ice_devlink_version { enum ice_version_type type; const char *key; - int (*getter)(struct ice_pf *pf, struct ice_info_ctx *ctx); - int (*fallback)(struct ice_pf *pf, struct ice_info_ctx *ctx); + void (*getter)(struct ice_pf *pf, struct ice_info_ctx *ctx); + void (*fallback)(struct ice_pf *pf, struct ice_info_ctx *ctx); } ice_devlink_versions[] = { fixed(DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, ice_info_pba), running(DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, ice_info_fw_mgmt), @@ -351,24 +327,15 @@ static int ice_devlink_info_get(struct devlink *devlink, memset(ctx->buf, 0, sizeof(ctx->buf)); - err = ice_devlink_versions[i].getter(pf, ctx); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Unable to obtain version info"); - goto out_free_ctx; - } + ice_devlink_versions[i].getter(pf, ctx); /* If the default getter doesn't report a version, use the * fallback function. This is primarily useful in the case of * "stored" versions that want to report the same value as the * running version in the normal case of no pending update. */ - if (ctx->buf[0] == '\0' && ice_devlink_versions[i].fallback) { - err = ice_devlink_versions[i].fallback(pf, ctx); - if (err) { - NL_SET_ERR_MSG_MOD(extack, "Unable to obtain version info"); - goto out_free_ctx; - } - } + if (ctx->buf[0] == '\0' && ice_devlink_versions[i].fallback) + ice_devlink_versions[i].fallback(pf, ctx); /* Do not report missing versions */ if (ctx->buf[0] == '\0') @@ -498,19 +465,11 @@ struct ice_pf *ice_allocate_pf(struct device *dev) * * Return: zero on success or an error code on failure. */ -int ice_devlink_register(struct ice_pf *pf) +void ice_devlink_register(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); - struct device *dev = ice_pf_to_dev(pf); - int err; - - err = devlink_register(devlink); - if (err) { - dev_err(dev, "devlink registration failed: %d\n", err); - return err; - } - return 0; + devlink_register(devlink); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/ice_devlink.h index e07e74426bde85..e721d7b0d627c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/ice_devlink.h @@ -6,7 +6,7 @@ struct ice_pf *ice_allocate_pf(struct device *dev); -int ice_devlink_register(struct ice_pf *pf); +void ice_devlink_register(struct ice_pf *pf); void ice_devlink_unregister(struct ice_pf *pf); int ice_devlink_create_port(struct ice_vsi *vsi); void ice_devlink_destroy_port(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index c451cf401e635b..6f0a29be3ee56e 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1215,6 +1215,13 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) enum ice_status status; bool dcbx_agent_status; + if (ice_get_pfc_mode(pf) == ICE_QOS_MODE_DSCP) { + clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); + dev_err(dev, "QoS in L3 DSCP mode, FW Agent not allowed to start\n"); + ret = -EOPNOTSUPP; + goto ethtool_exit; + } + /* Remove rule to direct LLDP packets to default VSI. * The FW LLDP engine will now be consuming them. */ diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.c b/drivers/net/ethernet/intel/ice/ice_fdir.c index 59ef68f072c0ac..cbd8424631e32a 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_fdir.c @@ -952,7 +952,7 @@ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input, ice_pkt_insert_u8(loc, ICE_IPV4_TTL_OFFSET, input->ip.v4.ttl); ice_pkt_insert_mac_addr(loc, input->ext_data.dst_mac); if (frag) - loc[20] = ICE_FDIR_IPV4_PKT_FLAG_DF; + loc[20] = ICE_FDIR_IPV4_PKT_FLAG_MF; break; case ICE_FLTR_PTYPE_NONF_IPV4_UDP: ice_pkt_insert_u32(loc, ICE_IPV4_DST_ADDR_OFFSET, diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h index d2d40e18ae8aab..da4163856f4c27 100644 --- a/drivers/net/ethernet/intel/ice/ice_fdir.h +++ b/drivers/net/ethernet/intel/ice/ice_fdir.h @@ -48,7 +48,7 @@ * requests that the packet not be fragmented. MF indicates that a packet has * been fragmented. */ -#define ICE_FDIR_IPV4_PKT_FLAG_DF 0x20 +#define ICE_FDIR_IPV4_PKT_FLAG_MF 0x20 enum ice_fltr_prgm_desc_dest { ICE_FLTR_PRGM_DESC_DEST_DROP_PKT, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index dde9802c6c7290..3adbd9a179a7b4 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3573,3 +3573,50 @@ int ice_set_link(struct ice_vsi *vsi, bool ena) return 0; } + +/** + * ice_is_feature_supported + * @pf: pointer to the struct ice_pf instance + * @f: feature enum to be checked + * + * returns true if feature is supported, false otherwise + */ +bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f) +{ + if (f < 0 || f >= ICE_F_MAX) + return false; + + return test_bit(f, pf->features); +} + +/** + * ice_set_feature_support + * @pf: pointer to the struct ice_pf instance + * @f: feature enum to set + */ +static void ice_set_feature_support(struct ice_pf *pf, enum ice_feature f) +{ + if (f < 0 || f >= ICE_F_MAX) + return; + + set_bit(f, pf->features); +} + +/** + * ice_init_feature_support + * @pf: pointer to the struct ice_pf instance + * + * called during init to setup supported feature + */ +void ice_init_feature_support(struct ice_pf *pf) +{ + switch (pf->hw.device_id) { + case ICE_DEV_ID_E810C_BACKPLANE: + case ICE_DEV_ID_E810C_QSFP: + case ICE_DEV_ID_E810C_SFP: + ice_set_feature_support(pf, ICE_F_DSCP); + break; + default: + break; + } +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index d5a28bf0fc2ccc..4512c8513178dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -116,4 +116,6 @@ bool ice_is_vsi_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_set_dflt_vsi(struct ice_sw *sw, struct ice_vsi *vsi); int ice_clear_dflt_vsi(struct ice_sw *sw); +bool ice_is_feature_supported(struct ice_pf *pf, enum ice_feature f); +void ice_init_feature_support(struct ice_pf *pf); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 0d6c143f665327..909e5cd9805480 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -624,7 +624,10 @@ static void ice_print_topo_conflict(struct ice_vsi *vsi) netdev_info(vsi->netdev, "Potential misconfiguration of the Ethernet port detected. If it was not intended, please use the Intel (R) Ethernet Port Configuration Tool to address the issue.\n"); break; case ICE_AQ_LINK_TOPO_UNSUPP_MEDIA: - netdev_info(vsi->netdev, "Rx/Tx is disabled on this device because an unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); + if (test_bit(ICE_FLAG_LINK_LENIENT_MODE_ENA, vsi->back->flags)) + netdev_warn(vsi->netdev, "An unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules\n"); + else + netdev_err(vsi->netdev, "Rx/Tx is disabled on this device because an unsupported module type was detected. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for a list of supported modules.\n"); break; default: break; @@ -1965,7 +1968,8 @@ static int ice_configure_phy(struct ice_vsi *vsi) ice_print_topo_conflict(vsi); - if (phy->link_info.topo_media_conflict == ICE_AQ_LINK_TOPO_UNSUPP_MEDIA) + if (!test_bit(ICE_FLAG_LINK_LENIENT_MODE_ENA, pf->flags) && + phy->link_info.topo_media_conflict == ICE_AQ_LINK_TOPO_UNSUPP_MEDIA) return -EPERM; if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) @@ -4258,12 +4262,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); - err = ice_devlink_register(pf); - if (err) { - dev_err(dev, "ice_devlink_register failed: %d\n", err); - goto err_exit_unroll; - } - #ifndef CONFIG_DYNAMIC_DEBUG if (debug < -1) hw->debug_mask = debug; @@ -4276,6 +4274,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_exit_unroll; } + ice_init_feature_support(pf); + ice_request_fw(pf); /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be @@ -4497,6 +4497,7 @@ probe_done: dev_warn(dev, "RDMA is not supported on this device\n"); } + ice_devlink_register(pf); return 0; err_init_aux_unroll: @@ -4520,7 +4521,6 @@ err_init_pf_unroll: ice_devlink_destroy_regions(pf); ice_deinit_hw(hw); err_exit_unroll: - ice_devlink_unregister(pf); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); return err; @@ -4597,9 +4597,7 @@ static void ice_remove(struct pci_dev *pdev) struct ice_pf *pf = pci_get_drvdata(pdev); int i; - if (!pf) - return; - + ice_devlink_unregister(pf); for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { if (!ice_is_reset_in_progress(pf->state)) break; @@ -4636,7 +4634,6 @@ static void ice_remove(struct pci_dev *pdev) ice_deinit_pf(pf); ice_devlink_destroy_regions(pf); ice_deinit_hw(&pf->hw); - ice_devlink_unregister(pf); /* Issue a PFR as part of the prescribed driver unload flow. Do not * do it via ice_schedule_reset() since there is no need to rebuild @@ -7239,6 +7236,7 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_open = ice_open, .ndo_stop = ice_stop, .ndo_start_xmit = ice_start_xmit, + .ndo_select_queue = ice_select_queue, .ndo_features_check = ice_features_check, .ndo_set_rx_mode = ice_set_rx_mode, .ndo_set_mac_address = ice_set_mac_address, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 6ee8e0032d52cb..13b2bdc25b0d61 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -6,6 +6,7 @@ #include <linux/prefetch.h> #include <linux/mm.h> #include <linux/bpf_trace.h> +#include <net/dsfield.h> #include <net/xdp.h> #include "ice_txrx_lib.h" #include "ice_lib.h" @@ -2296,6 +2297,39 @@ netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev) } /** + * ice_get_dscp_up - return the UP/TC value for a SKB + * @dcbcfg: DCB config that contains DSCP to UP/TC mapping + * @skb: SKB to query for info to determine UP/TC + * + * This function is to only be called when the PF is in L3 DSCP PFC mode + */ +static u8 ice_get_dscp_up(struct ice_dcbx_cfg *dcbcfg, struct sk_buff *skb) +{ + u8 dscp = 0; + + if (skb->protocol == htons(ETH_P_IP)) + dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; + else if (skb->protocol == htons(ETH_P_IPV6)) + dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; + + return dcbcfg->dscp_map[dscp]; +} + +u16 +ice_select_queue(struct net_device *netdev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_dcbx_cfg *dcbcfg; + + dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; + if (dcbcfg->pfc_mode == ICE_QOS_MODE_DSCP) + skb->priority = ice_get_dscp_up(dcbcfg, skb); + + return netdev_pick_tx(netdev, skb, sb_dev); +} + +/** * ice_clean_ctrl_tx_irq - interrupt handler for flow director Tx queue * @tx_ring: tx_ring to clean */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 1e46e80f3d6f89..b0bbbec4e3a3c7 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -378,6 +378,9 @@ union ice_32b_rx_flex_desc; bool ice_alloc_rx_bufs(struct ice_ring *rxr, u16 cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); +u16 +ice_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev); void ice_clean_tx_ring(struct ice_ring *tx_ring); void ice_clean_rx_ring(struct ice_ring *rx_ring); int ice_setup_tx_ring(struct ice_ring *tx_ring); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index d33d1906103c7c..6705f56be020e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -604,7 +604,8 @@ struct ice_dcb_app_priority_table { }; #define ICE_MAX_USER_PRIORITY 8 -#define ICE_DCBX_MAX_APPS 32 +#define ICE_DCBX_MAX_APPS 64 +#define ICE_DSCP_NUM_VAL 64 #define ICE_LLDPDU_SIZE 1500 #define ICE_TLV_STATUS_OPER 0x1 #define ICE_TLV_STATUS_SYNC 0x2 @@ -622,7 +623,14 @@ struct ice_dcbx_cfg { struct ice_dcb_ets_cfg etscfg; struct ice_dcb_ets_cfg etsrec; struct ice_dcb_pfc_cfg pfc; +#define ICE_QOS_MODE_VLAN 0x0 +#define ICE_QOS_MODE_DSCP 0x1 + u8 pfc_mode; struct ice_dcb_app_priority_table app[ICE_DCBX_MAX_APPS]; + /* when DSCP mapping defined by user set its bit to 1 */ + DECLARE_BITMAP(dscp_mapped, ICE_DSCP_NUM_VAL); + /* array holding DSCP -> UP/TC values for DSCP L3 QoS mode */ + u8 dscp_map[ICE_DSCP_NUM_VAL]; u8 dcbx_mode; #define ICE_DCBX_MODE_CEE 0x1 #define ICE_DCBX_MODE_IEEE 0x2 diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 62f8c52121822d..2258e3f1916107 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -96,6 +96,9 @@ struct ltq_etop_priv { struct ltq_etop_chan ch[MAX_DMA_CHAN]; int tx_free[MAX_DMA_CHAN >> 1]; + int tx_burst_len; + int rx_burst_len; + spinlock_t lock; }; @@ -259,7 +262,7 @@ ltq_etop_hw_init(struct net_device *dev) /* enable crc generation */ ltq_etop_w32(PPE32_CGEN, LQ_PPE32_ENET_MAC_CFG); - ltq_dma_init_port(DMA_PORT_ETOP); + ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len); for (i = 0; i < MAX_DMA_CHAN; i++) { int irq = LTQ_DMA_CH0_INT + i; @@ -472,8 +475,8 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - /* dma needs to start on a 16 byte aligned address */ - byte_offset = CPHYSADDR(skb->data) % 16; + /* dma needs to start on a burst length value aligned address */ + byte_offset = CPHYSADDR(skb->data) % (priv->tx_burst_len * 4); ch->skb[ch->dma.desc] = skb; netif_trans_update(dev); @@ -667,6 +670,18 @@ ltq_etop_probe(struct platform_device *pdev) spin_lock_init(&priv->lock); SET_NETDEV_DEV(dev, &pdev->dev); + err = device_property_read_u32(&pdev->dev, "lantiq,tx-burst-length", &priv->tx_burst_len); + if (err < 0) { + dev_err(&pdev->dev, "unable to read tx-burst-length property\n"); + return err; + } + + err = device_property_read_u32(&pdev->dev, "lantiq,rx-burst-length", &priv->rx_burst_len); + if (err < 0) { + dev_err(&pdev->dev, "unable to read rx-burst-length property\n"); + return err; + } + for (i = 0; i < MAX_DMA_CHAN; i++) { if (IS_TX(i)) netif_napi_add(dev, &priv->ch[i].napi, diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index fb78f17d734fe2..9b7307eba97ca3 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -14,13 +14,15 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/if_vlan.h> + #include <linux/of_net.h> #include <linux/of_platform.h> #include <xway_dma.h> /* DMA */ -#define XRX200_DMA_DATA_LEN 0x600 +#define XRX200_DMA_DATA_LEN (SZ_64K - 1) #define XRX200_DMA_RX 0 #define XRX200_DMA_TX 1 @@ -71,6 +73,9 @@ struct xrx200_priv { struct net_device *net_dev; struct device *dev; + int tx_burst_len; + int rx_burst_len; + __iomem void *pmac_reg; }; @@ -106,7 +111,8 @@ static void xrx200_flush_dma(struct xrx200_chan *ch) break; desc->ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | - XRX200_DMA_DATA_LEN; + (ch->priv->net_dev->mtu + VLAN_ETH_HLEN + + ETH_FCS_LEN); ch->dma.desc++; ch->dma.desc %= LTQ_DESC_NUM; } @@ -154,19 +160,20 @@ static int xrx200_close(struct net_device *net_dev) static int xrx200_alloc_skb(struct xrx200_chan *ch) { + int len = ch->priv->net_dev->mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; struct sk_buff *skb = ch->skb[ch->dma.desc]; dma_addr_t mapping; int ret = 0; ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, - XRX200_DMA_DATA_LEN); + len); if (!ch->skb[ch->dma.desc]) { ret = -ENOMEM; goto skip; } mapping = dma_map_single(ch->priv->dev, ch->skb[ch->dma.desc]->data, - XRX200_DMA_DATA_LEN, DMA_FROM_DEVICE); + len, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(ch->priv->dev, mapping))) { dev_kfree_skb_any(ch->skb[ch->dma.desc]); ch->skb[ch->dma.desc] = skb; @@ -179,8 +186,7 @@ static int xrx200_alloc_skb(struct xrx200_chan *ch) wmb(); skip: ch->dma.desc_base[ch->dma.desc].ctl = - LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | - XRX200_DMA_DATA_LEN; + LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | len; return ret; } @@ -316,8 +322,8 @@ static netdev_tx_t xrx200_start_xmit(struct sk_buff *skb, if (unlikely(dma_mapping_error(priv->dev, mapping))) goto err_drop; - /* dma needs to start on a 16 byte aligned address */ - byte_offset = mapping % 16; + /* dma needs to start on a burst length value aligned address */ + byte_offset = mapping % (priv->tx_burst_len * 4); desc->addr = mapping - byte_offset; /* Make sure the address is written before we give it to HW */ @@ -340,10 +346,57 @@ err_drop: return NETDEV_TX_OK; } +static int +xrx200_change_mtu(struct net_device *net_dev, int new_mtu) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + struct xrx200_chan *ch_rx = &priv->chan_rx; + int old_mtu = net_dev->mtu; + bool running = false; + struct sk_buff *skb; + int curr_desc; + int ret = 0; + + net_dev->mtu = new_mtu; + + if (new_mtu <= old_mtu) + return ret; + + running = netif_running(net_dev); + if (running) { + napi_disable(&ch_rx->napi); + ltq_dma_close(&ch_rx->dma); + } + + xrx200_poll_rx(&ch_rx->napi, LTQ_DESC_NUM); + curr_desc = ch_rx->dma.desc; + + for (ch_rx->dma.desc = 0; ch_rx->dma.desc < LTQ_DESC_NUM; + ch_rx->dma.desc++) { + skb = ch_rx->skb[ch_rx->dma.desc]; + ret = xrx200_alloc_skb(ch_rx); + if (ret) { + net_dev->mtu = old_mtu; + break; + } + dev_kfree_skb_any(skb); + } + + ch_rx->dma.desc = curr_desc; + if (running) { + napi_enable(&ch_rx->napi); + ltq_dma_open(&ch_rx->dma); + ltq_dma_enable_irq(&ch_rx->dma); + } + + return ret; +} + static const struct net_device_ops xrx200_netdev_ops = { .ndo_open = xrx200_open, .ndo_stop = xrx200_close, .ndo_start_xmit = xrx200_start_xmit, + .ndo_change_mtu = xrx200_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; @@ -369,7 +422,7 @@ static int xrx200_dma_init(struct xrx200_priv *priv) int ret = 0; int i; - ltq_dma_init_port(DMA_PORT_ETOP); + ltq_dma_init_port(DMA_PORT_ETOP, priv->tx_burst_len, rx_burst_len); ch_rx->dma.nr = XRX200_DMA_RX; ch_rx->dma.dev = priv->dev; @@ -453,7 +506,7 @@ static int xrx200_probe(struct platform_device *pdev) net_dev->netdev_ops = &xrx200_netdev_ops; SET_NETDEV_DEV(net_dev, dev); net_dev->min_mtu = ETH_ZLEN; - net_dev->max_mtu = XRX200_DMA_DATA_LEN; + net_dev->max_mtu = XRX200_DMA_DATA_LEN - VLAN_ETH_HLEN - ETH_FCS_LEN; /* load the memory ranges */ priv->pmac_reg = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); @@ -478,6 +531,18 @@ static int xrx200_probe(struct platform_device *pdev) if (err) eth_hw_addr_random(net_dev); + err = device_property_read_u32(dev, "lantiq,tx-burst-length", &priv->tx_burst_len); + if (err < 0) { + dev_err(dev, "unable to read tx-burst-length property\n"); + return err; + } + + err = device_property_read_u32(dev, "lantiq,rx-burst-length", &priv->rx_burst_len); + if (err < 0) { + dev_err(dev, "unable to read rx-burst-length property\n"); + return err; + } + /* bring up the dma engine and IP core */ err = xrx200_dma_init(priv); if (err) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 34a089b71e5542..d379a35c4618fd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -838,9 +838,6 @@ void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable) if (!cgx) return; - if (is_dev_rpm(cgx)) - return; - if (enable) { /* Enable inbound PTP timestamping */ cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL); @@ -1545,9 +1542,11 @@ static int cgx_lmac_exit(struct cgx *cgx) static void cgx_populate_features(struct cgx *cgx) { if (is_dev_rpm(cgx)) - cgx->hw_features = (RVU_MAC_RPM | RVU_LMAC_FEAT_FC); + cgx->hw_features = (RVU_LMAC_FEAT_DMACF | RVU_MAC_RPM | + RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_PTP); else - cgx->hw_features = (RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_PTP); + cgx->hw_features = (RVU_LMAC_FEAT_FC | RVU_LMAC_FEAT_HIGIG2 | + RVU_LMAC_FEAT_PTP | RVU_LMAC_FEAT_DMACF); } static struct mac_ops cgx_mac_ops = { @@ -1571,6 +1570,7 @@ static struct mac_ops cgx_mac_ops = { .mac_get_pause_frm_status = cgx_lmac_get_pause_frm_status, .mac_enadis_pause_frm = cgx_lmac_enadis_pause_frm, .mac_pause_frm_config = cgx_lmac_pause_frm_config, + .mac_enadis_ptp_config = cgx_lmac_ptp_config, }; static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index d9bea13f15b863..8931864ee110c4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -191,6 +191,7 @@ enum nix_scheduler { #define NIX_CHAN_SDP_CH_START (0x700ull) #define NIX_CHAN_SDP_CHX(a) (NIX_CHAN_SDP_CH_START + (a)) #define NIX_CHAN_SDP_NUM_CHANS 256 +#define NIX_CHAN_CPT_CH_START (0x800ull) /* The mask is to extract lower 10-bits of channel number * which CPT will pass to X2P. diff --git a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h index c38306b3384a70..fc6e7423cbd81d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/lmac_common.h @@ -102,6 +102,11 @@ struct mac_ops { void (*mac_pause_frm_config)(void *cgxd, int lmac_id, bool enable); + + /* Enable/Disable Inbound PTP */ + void (*mac_enadis_ptp_config)(void *cgxd, + int lmac_id, + bool enable); }; struct cgx { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 154877706a0e11..dfe487235007ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -84,7 +84,7 @@ struct mbox_msghdr { #define OTX2_MBOX_REQ_SIG (0xdead) #define OTX2_MBOX_RSP_SIG (0xbeef) u16 sig; /* Signature, for validating corrupted msgs */ -#define OTX2_MBOX_VERSION (0x0009) +#define OTX2_MBOX_VERSION (0x000a) u16 ver; /* Version of msg's structure for this ID */ u16 next_msgoff; /* Offset of next msg within mailbox region */ int rc; /* Msg process'ed response code */ @@ -154,23 +154,23 @@ M(CGX_PTP_RX_ENABLE, 0x20C, cgx_ptp_rx_enable, msg_req, msg_rsp) \ M(CGX_PTP_RX_DISABLE, 0x20D, cgx_ptp_rx_disable, msg_req, msg_rsp) \ M(CGX_CFG_PAUSE_FRM, 0x20E, cgx_cfg_pause_frm, cgx_pause_frm_cfg, \ cgx_pause_frm_cfg) \ -M(CGX_FEC_SET, 0x210, cgx_set_fec_param, fec_mode, fec_mode) \ -M(CGX_FEC_STATS, 0x211, cgx_fec_stats, msg_req, cgx_fec_stats_rsp) \ -M(CGX_GET_PHY_FEC_STATS, 0x212, cgx_get_phy_fec_stats, msg_req, msg_rsp) \ -M(CGX_FW_DATA_GET, 0x213, cgx_get_aux_link_info, msg_req, cgx_fw_data) \ -M(CGX_SET_LINK_MODE, 0x214, cgx_set_link_mode, cgx_set_link_mode_req,\ - cgx_set_link_mode_rsp) \ -M(CGX_FEATURES_GET, 0x215, cgx_features_get, msg_req, \ - cgx_features_info_msg) \ -M(RPM_STATS, 0x216, rpm_stats, msg_req, rpm_stats_rsp) \ -M(CGX_MAC_ADDR_ADD, 0x217, cgx_mac_addr_add, cgx_mac_addr_add_req, \ - cgx_mac_addr_add_rsp) \ -M(CGX_MAC_ADDR_DEL, 0x218, cgx_mac_addr_del, cgx_mac_addr_del_req, \ +M(CGX_FW_DATA_GET, 0x20F, cgx_get_aux_link_info, msg_req, cgx_fw_data) \ +M(CGX_FEC_SET, 0x210, cgx_set_fec_param, fec_mode, fec_mode) \ +M(CGX_MAC_ADDR_ADD, 0x211, cgx_mac_addr_add, cgx_mac_addr_add_req, \ + cgx_mac_addr_add_rsp) \ +M(CGX_MAC_ADDR_DEL, 0x212, cgx_mac_addr_del, cgx_mac_addr_del_req, \ msg_rsp) \ -M(CGX_MAC_MAX_ENTRIES_GET, 0x219, cgx_mac_max_entries_get, msg_req, \ +M(CGX_MAC_MAX_ENTRIES_GET, 0x213, cgx_mac_max_entries_get, msg_req, \ cgx_max_dmac_entries_get_rsp) \ -M(CGX_MAC_ADDR_RESET, 0x21A, cgx_mac_addr_reset, msg_req, msg_rsp) \ -M(CGX_MAC_ADDR_UPDATE, 0x21B, cgx_mac_addr_update, cgx_mac_addr_update_req, \ +M(CGX_FEC_STATS, 0x217, cgx_fec_stats, msg_req, cgx_fec_stats_rsp) \ +M(CGX_SET_LINK_MODE, 0x218, cgx_set_link_mode, cgx_set_link_mode_req,\ + cgx_set_link_mode_rsp) \ +M(CGX_GET_PHY_FEC_STATS, 0x219, cgx_get_phy_fec_stats, msg_req, msg_rsp) \ +M(CGX_FEATURES_GET, 0x21B, cgx_features_get, msg_req, \ + cgx_features_info_msg) \ +M(RPM_STATS, 0x21C, rpm_stats, msg_req, rpm_stats_rsp) \ +M(CGX_MAC_ADDR_RESET, 0x21D, cgx_mac_addr_reset, msg_req, msg_rsp) \ +M(CGX_MAC_ADDR_UPDATE, 0x21E, cgx_mac_addr_update, cgx_mac_addr_update_req, \ msg_rsp) \ /* NPA mbox IDs (range 0x400 - 0x5FF) */ \ M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \ @@ -186,6 +186,8 @@ M(CPT_LF_ALLOC, 0xA00, cpt_lf_alloc, cpt_lf_alloc_req_msg, \ M(CPT_LF_FREE, 0xA01, cpt_lf_free, msg_req, msg_rsp) \ M(CPT_RD_WR_REGISTER, 0xA02, cpt_rd_wr_register, cpt_rd_wr_reg_msg, \ cpt_rd_wr_reg_msg) \ +M(CPT_INLINE_IPSEC_CFG, 0xA04, cpt_inline_ipsec_cfg, \ + cpt_inline_ipsec_cfg_msg, msg_rsp) \ M(CPT_STATS, 0xA05, cpt_sts, cpt_sts_req, cpt_sts_rsp) \ M(CPT_RXC_TIME_CFG, 0xA06, cpt_rxc_time_cfg, cpt_rxc_time_cfg_req, \ msg_rsp) \ @@ -229,6 +231,8 @@ M(NPC_DELETE_FLOW, 0x600e, npc_delete_flow, \ M(NPC_MCAM_READ_ENTRY, 0x600f, npc_mcam_read_entry, \ npc_mcam_read_entry_req, \ npc_mcam_read_entry_rsp) \ +M(NPC_SET_PKIND, 0x6010, npc_set_pkind, \ + npc_set_pkind, msg_rsp) \ M(NPC_MCAM_READ_BASE_RULE, 0x6011, npc_read_base_steer_rule, \ msg_req, npc_mcam_read_base_rule_rsp) \ M(NPC_MCAM_GET_STATS, 0x6012, npc_mcam_entry_stats, \ @@ -270,6 +274,10 @@ M(NIX_BP_ENABLE, 0x8016, nix_bp_enable, nix_bp_cfg_req, \ nix_bp_cfg_rsp) \ M(NIX_BP_DISABLE, 0x8017, nix_bp_disable, nix_bp_cfg_req, msg_rsp) \ M(NIX_GET_MAC_ADDR, 0x8018, nix_get_mac_addr, msg_req, nix_get_mac_addr_rsp) \ +M(NIX_INLINE_IPSEC_CFG, 0x8019, nix_inline_ipsec_cfg, \ + nix_inline_ipsec_cfg, msg_rsp) \ +M(NIX_INLINE_IPSEC_LF_CFG, 0x801a, nix_inline_ipsec_lf_cfg, \ + nix_inline_ipsec_lf_cfg, msg_rsp) \ M(NIX_CN10K_AQ_ENQ, 0x801b, nix_cn10k_aq_enq, nix_cn10k_aq_enq_req, \ nix_cn10k_aq_enq_rsp) \ M(NIX_GET_HW_INFO, 0x801c, nix_get_hw_info, msg_req, nix_hw_info) \ @@ -575,10 +583,13 @@ struct cgx_mac_addr_update_req { }; #define RVU_LMAC_FEAT_FC BIT_ULL(0) /* pause frames */ -#define RVU_LMAC_FEAT_PTP BIT_ULL(1) /* precision time protocol */ -#define RVU_MAC_VERSION BIT_ULL(2) -#define RVU_MAC_CGX BIT_ULL(3) -#define RVU_MAC_RPM BIT_ULL(4) +#define RVU_LMAC_FEAT_HIGIG2 BIT_ULL(1) + /* flow control from physical link higig2 messages */ +#define RVU_LMAC_FEAT_PTP BIT_ULL(2) /* precison time protocol */ +#define RVU_LMAC_FEAT_DMACF BIT_ULL(3) /* DMAC FILTER */ +#define RVU_MAC_VERSION BIT_ULL(4) +#define RVU_MAC_CGX BIT_ULL(5) +#define RVU_MAC_RPM BIT_ULL(6) struct cgx_features_info_msg { struct mbox_msghdr hdr; @@ -593,6 +604,22 @@ struct rpm_stats_rsp { u64 tx_stats[RPM_TX_STATS_COUNT]; }; +struct npc_set_pkind { + struct mbox_msghdr hdr; +#define OTX2_PRIV_FLAGS_DEFAULT BIT_ULL(0) +#define OTX2_PRIV_FLAGS_CUSTOM BIT_ULL(63) + u64 mode; +#define PKIND_TX BIT_ULL(0) +#define PKIND_RX BIT_ULL(1) + u8 dir; + u8 pkind; /* valid only in case custom flag */ + u8 var_len_off; /* Offset of custom header length field. + * Valid only for pkind NPC_RX_CUSTOM_PRE_L2_PKIND + */ + u8 var_len_off_mask; /* Mask for length with in offset */ + u8 shift_dir; /* shift direction to get length of the header at var_len_off */ +}; + /* NPA mbox message formats */ /* NPA mailbox error codes @@ -698,6 +725,8 @@ enum nix_af_status { NIX_AF_ERR_INVALID_BANDPROF = -426, NIX_AF_ERR_IPOLICER_NOTSUPP = -427, NIX_AF_ERR_BANDPROF_INVAL_REQ = -428, + NIX_AF_ERR_CQ_CTX_WRITE_ERR = -429, + NIX_AF_ERR_AQ_CTX_RETRY_WRITE = -430, }; /* For NIX RX vtag action */ @@ -1065,6 +1094,40 @@ struct nix_bp_cfg_rsp { u8 chan_cnt; /* Number of channel for which bpids are assigned */ }; +/* Global NIX inline IPSec configuration */ +struct nix_inline_ipsec_cfg { + struct mbox_msghdr hdr; + u32 cpt_credit; + struct { + u8 egrp; + u8 opcode; + u16 param1; + u16 param2; + } gen_cfg; + struct { + u16 cpt_pf_func; + u8 cpt_slot; + } inst_qsel; + u8 enable; +}; + +/* Per NIX LF inline IPSec configuration */ +struct nix_inline_ipsec_lf_cfg { + struct mbox_msghdr hdr; + u64 sa_base_addr; + struct { + u32 tag_const; + u16 lenm1_max; + u8 sa_pow2_size; + u8 tt; + } ipsec_cfg0; + struct { + u32 sa_idx_max; + u8 sa_idx_w; + } ipsec_cfg1; + u8 enable; +}; + struct nix_hw_info { struct mbox_msghdr hdr; u16 rsvs16; @@ -1357,12 +1420,15 @@ struct npc_mcam_get_stats_rsp { enum ptp_op { PTP_OP_ADJFINE = 0, PTP_OP_GET_CLOCK = 1, + PTP_OP_GET_TSTMP = 2, + PTP_OP_SET_THRESH = 3, }; struct ptp_req { struct mbox_msghdr hdr; u8 op; s64 scaled_ppm; + u64 thresh; }; struct ptp_rsp { @@ -1399,7 +1465,9 @@ enum cpt_af_status { CPT_AF_ERR_LF_INVALID = -903, CPT_AF_ERR_ACCESS_DENIED = -904, CPT_AF_ERR_SSO_PF_FUNC_INVALID = -905, - CPT_AF_ERR_NIX_PF_FUNC_INVALID = -906 + CPT_AF_ERR_NIX_PF_FUNC_INVALID = -906, + CPT_AF_ERR_INLINE_IPSEC_INB_ENA = -907, + CPT_AF_ERR_INLINE_IPSEC_OUT_ENA = -908 }; /* CPT mbox message formats */ @@ -1420,6 +1488,22 @@ struct cpt_lf_alloc_req_msg { int blkaddr; }; +#define CPT_INLINE_INBOUND 0 +#define CPT_INLINE_OUTBOUND 1 + +/* Mailbox message request format for CPT IPsec + * inline inbound and outbound configuration. + */ +struct cpt_inline_ipsec_cfg_msg { + struct mbox_msghdr hdr; + u8 enable; + u8 slot; + u8 dir; + u8 sso_pf_func_ovrd; + u16 sso_pf_func; /* inbound path SSO_PF_FUNC */ + u16 nix_pf_func; /* outbound path NIX_PF_FUNC */ +}; + /* Mailbox message request and response format for CPT stats. */ struct cpt_sts_req { struct mbox_msghdr hdr; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 3a819b24accc66..6e1192f5260891 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -31,9 +31,9 @@ enum npc_kpu_la_ltype { NPC_LT_LA_HIGIG2_ETHER, NPC_LT_LA_IH_NIX_HIGIG2_ETHER, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_LT_LA_CH_LEN_90B_ETHER, NPC_LT_LA_CPT_HDR, NPC_LT_LA_CUSTOM_L2_24B_ETHER, + NPC_LT_LA_CUSTOM_PRE_L2_ETHER, NPC_LT_LA_CUSTOM0 = 0xE, NPC_LT_LA_CUSTOM1 = 0xF, }; @@ -148,10 +148,11 @@ enum npc_kpu_lh_ltype { * Software assigns pkind for each incoming port such as CGX * Ethernet interfaces, LBK interfaces, etc. */ -#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_VLAN_EXDSA_PKIND +#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_CUSTOM_PRE_L2_PKIND enum npc_pkind_type { NPC_RX_LBK_PKIND = 0ULL, + NPC_RX_CUSTOM_PRE_L2_PKIND = 55ULL, NPC_RX_VLAN_EXDSA_PKIND = 56ULL, NPC_RX_CHLEN24B_PKIND = 57ULL, NPC_RX_CPT_HDR_PKIND, @@ -162,6 +163,10 @@ enum npc_pkind_type { NPC_TX_DEF_PKIND, /* NIX-TX PKIND */ }; +enum npc_interface_type { + NPC_INTF_MODE_DEF, +}; + /* list of known and supported fields in packet header and * fields present in key structure. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index 588822a0cf21e7..65280a8c4ac373 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -176,9 +176,8 @@ enum npc_kpu_parser_state { NPC_S_KPU1_EXDSA, NPC_S_KPU1_HIGIG2, NPC_S_KPU1_IH_NIX_HIGIG2, - NPC_S_KPU1_CUSTOM_L2_90B, + NPC_S_KPU1_CUSTOM_PRE_L2, NPC_S_KPU1_CPT_HDR, - NPC_S_KPU1_CUSTOM_L2_24B, NPC_S_KPU1_VLAN_EXDSA, NPC_S_KPU2_CTAG, NPC_S_KPU2_CTAG2, @@ -979,8 +978,8 @@ static struct npc_kpu_profile_action ikpu_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 12, 16, 20, 0, 0, - NPC_S_KPU1_ETHER, 0, 0, - NPC_LID_LA, NPC_LT_NA, + NPC_S_KPU1_CUSTOM_PRE_L2, 0, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_PRE_L2_ETHER, 0, 0, 0, 0, 0, @@ -996,9 +995,9 @@ static struct npc_kpu_profile_action ikpu_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 36, 40, 44, 0, 0, - NPC_S_KPU1_CUSTOM_L2_24B, 0, 0, - NPC_LID_LA, NPC_LT_NA, + 12, 16, 20, 0, 0, + NPC_S_KPU1_CUSTOM_PRE_L2, 24, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, 0, 0, 0, 0, 0, @@ -1014,9 +1013,9 @@ static struct npc_kpu_profile_action ikpu_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 102, 106, 110, 0, 0, - NPC_S_KPU1_CUSTOM_L2_90B, 0, 0, - NPC_LID_LA, NPC_LT_NA, + 12, 16, 20, 0, 0, + NPC_S_KPU1_CUSTOM_PRE_L2, 90, 1, + NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, 0, 0, 0, 0, 0, @@ -1711,7 +1710,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_IP, 0xffff, 0x0000, @@ -1720,7 +1719,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_IP6, 0xffff, 0x0000, @@ -1729,7 +1728,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_ARP, 0xffff, 0x0000, @@ -1738,7 +1737,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_RARP, 0xffff, 0x0000, @@ -1747,7 +1746,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_PTP, 0xffff, 0x0000, @@ -1756,7 +1755,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_FCOE, 0xffff, 0x0000, @@ -1765,7 +1764,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_CTAG, 0xffff, NPC_ETYPE_CTAG, @@ -1774,7 +1773,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_CTAG, 0xffff, 0x0000, @@ -1783,7 +1782,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_SBTAG, 0xffff, 0x0000, @@ -1792,7 +1791,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_QINQ, 0xffff, 0x0000, @@ -1801,7 +1800,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_ETAG, 0xffff, 0x0000, @@ -1810,7 +1809,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_MPLSU, 0xffff, 0x0000, @@ -1819,7 +1818,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_MPLSM, 0xffff, 0x0000, @@ -1828,7 +1827,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, NPC_ETYPE_NSH, 0xffff, 0x0000, @@ -1837,7 +1836,7 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_90B, 0xff, + NPC_S_KPU1_CUSTOM_PRE_L2, 0xff, 0x0000, 0x0000, 0x0000, @@ -1927,141 +1926,6 @@ static struct npc_kpu_profile_cam kpu1_cam_entries[] = { 0x0000, }, { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_IP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_IP6, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_ARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_RARP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_PTP, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_FCOE, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_CTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_SBTAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_QINQ, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_ETAG, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_MPLSU, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_MPLSM, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - NPC_ETYPE_NSH, - 0xffff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU1_CUSTOM_L2_24B, 0xff, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - 0x0000, - }, - { NPC_S_KPU1_VLAN_EXDSA, 0xff, NPC_ETYPE_CTAG, 0xffff, @@ -7496,15 +7360,6 @@ static struct npc_kpu_profile_cam kpu9_cam_entries[] = { NPC_S_KPU9_GTPU, 0xff, 0x0000, 0x0000, - NPC_GTP_PT_GTP | NPC_GTP_VER1 | NPC_GTP_MT_G_PDU, - NPC_GTP_PT_MASK | NPC_GTP_VER_MASK | NPC_GTP_MT_MASK, - 0x0000, - 0x0000, - }, - { - NPC_S_KPU9_GTPU, 0xff, - 0x0000, - 0x0000, NPC_GTP_PT_GTP | NPC_GTP_VER1, NPC_GTP_PT_MASK | NPC_GTP_VER_MASK, 0x0000, @@ -9192,121 +9047,121 @@ static struct npc_kpu_profile_action kpu1_action_entries[] = { { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 0, 6, 3, 0, - NPC_S_KPU5_IP, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_IP, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 6, 0, 0, 3, 0, - NPC_S_KPU5_IP6, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_IP6, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 3, 0, - NPC_S_KPU5_ARP, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_ARP, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 3, 0, - NPC_S_KPU5_RARP, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_RARP, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 3, 0, - NPC_S_KPU5_PTP, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_PTP, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 3, 0, - NPC_S_KPU5_FCOE, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, + NPC_S_KPU5_FCOE, 14, 0, + NPC_LID_LA, NPC_LT_NA, 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 12, 0, 0, 0, - NPC_S_KPU2_CTAG2, 102, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + NPC_S_KPU2_CTAG2, 12, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 4, 8, 0, 0, 0, - NPC_S_KPU2_CTAG, 102, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + NPC_S_KPU2_CTAG, 12, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 4, 8, 22, 0, 0, - NPC_S_KPU2_SBTAG, 102, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + NPC_S_KPU2_SBTAG, 12, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 4, 8, 0, 0, 0, - NPC_S_KPU2_QINQ, 102, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, + NPC_S_KPU2_QINQ, 12, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 8, 12, 26, 0, 0, - NPC_S_KPU2_ETAG, 102, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, + NPC_S_KPU2_ETAG, 12, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, - NPC_S_KPU4_MPLS, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_L_WITH_MPLS, + NPC_S_KPU4_MPLS, 14, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 6, 10, 2, 0, - NPC_S_KPU4_MPLS, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_L_WITH_MPLS, + NPC_S_KPU4_MPLS, 14, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 2, 0, 0, 2, 0, - NPC_S_KPU4_NSH, 104, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_L_WITH_NSH, + NPC_S_KPU4_NSH, 14, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { NPC_ERRLEV_RE, NPC_EC_NOERR, 0, 0, 0, 0, 1, - NPC_S_NA, 0, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_90B_ETHER, - NPC_F_LA_L_UNK_ETYPE, + NPC_S_NA, 0, 0, + NPC_LID_LA, NPC_LT_NA, + 0, 0, 0, 0, 0, }, { @@ -9383,126 +9238,6 @@ static struct npc_kpu_profile_action kpu1_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 3, 0, - NPC_S_KPU5_IP, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 6, 0, 0, 3, 0, - NPC_S_KPU5_IP6, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 3, 0, - NPC_S_KPU5_ARP, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 3, 0, - NPC_S_KPU5_RARP, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 3, 0, - NPC_S_KPU5_PTP, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 3, 0, - NPC_S_KPU5_FCOE, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - 0, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 12, 0, 0, 0, - NPC_S_KPU2_CTAG2, 36, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 4, 8, 0, 0, 0, - NPC_S_KPU2_CTAG, 36, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 4, 8, 22, 0, 0, - NPC_S_KPU2_SBTAG, 36, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 4, 8, 0, 0, 0, - NPC_S_KPU2_QINQ, 36, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_VLAN, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 12, 26, 0, 0, - NPC_S_KPU2_ETAG, 36, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_U_HAS_TAG | NPC_F_LA_L_WITH_ETAG, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 2, 6, 10, 2, 0, - NPC_S_KPU4_MPLS, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_L_WITH_MPLS, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 2, 6, 10, 2, 0, - NPC_S_KPU4_MPLS, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_L_WITH_MPLS, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 2, 0, 0, 2, 0, - NPC_S_KPU4_NSH, 38, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_L_WITH_NSH, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 0, 0, 0, 0, 1, - NPC_S_NA, 0, 1, - NPC_LID_LA, NPC_LT_LA_CUSTOM_L2_24B_ETHER, - NPC_F_LA_L_UNK_ETYPE, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, 12, 0, 0, 1, 0, NPC_S_KPU3_VLAN_EXDSA, 12, 1, NPC_LID_LA, NPC_LT_LA_ETHER, @@ -14335,16 +14070,8 @@ static struct npc_kpu_profile_action kpu9_action_entries[] = { }, { NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU12_TU_IP, 8, 1, - NPC_LID_LE, NPC_LT_LE_GTPU, - NPC_F_LE_L_GTPU_G_PDU, - 0, 0, 0, 0, - }, - { - NPC_ERRLEV_RE, NPC_EC_NOERR, - 8, 0, 6, 2, 0, - NPC_S_KPU12_TU_IP, 8, 1, + 8, 0, 6, 2, 1, + NPC_S_NA, 0, 1, NPC_LID_LE, NPC_LT_LE_GTPU, 0, 0, 0, 0, 0, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c index 9b8e59f4c206d5..d6321de3cc1719 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.c @@ -27,54 +27,29 @@ #define PCI_DEVID_CN10K_PTP 0xA09E #define PCI_PTP_BAR_NO 0 -#define PCI_RST_BAR_NO 0 #define PTP_CLOCK_CFG 0xF00ULL #define PTP_CLOCK_CFG_PTP_EN BIT_ULL(0) +#define PTP_CLOCK_CFG_EXT_CLK_EN BIT_ULL(1) +#define PTP_CLOCK_CFG_EXT_CLK_IN_MASK GENMASK_ULL(7, 2) +#define PTP_CLOCK_CFG_TSTMP_EDGE BIT_ULL(9) +#define PTP_CLOCK_CFG_TSTMP_EN BIT_ULL(8) +#define PTP_CLOCK_CFG_TSTMP_IN_MASK GENMASK_ULL(15, 10) +#define PTP_CLOCK_CFG_PPS_EN BIT_ULL(30) +#define PTP_CLOCK_CFG_PPS_INV BIT_ULL(31) + +#define PTP_PPS_HI_INCR 0xF60ULL +#define PTP_PPS_LO_INCR 0xF68ULL +#define PTP_PPS_THRESH_HI 0xF58ULL + #define PTP_CLOCK_LO 0xF08ULL #define PTP_CLOCK_HI 0xF10ULL #define PTP_CLOCK_COMP 0xF18ULL - -#define RST_BOOT 0x1600ULL -#define RST_MUL_BITS GENMASK_ULL(38, 33) -#define CLOCK_BASE_RATE 50000000ULL +#define PTP_TIMESTAMP 0xF20ULL static struct ptp *first_ptp_block; static const struct pci_device_id ptp_id_table[]; -static u64 get_clock_rate(void) -{ - u64 cfg, ret = CLOCK_BASE_RATE * 16; - struct pci_dev *pdev; - void __iomem *base; - - /* To get the input clock frequency with which PTP co-processor - * block is running the base frequency(50 MHz) needs to be multiplied - * with multiplier bits present in RST_BOOT register of RESET block. - * Hence below code gets the multiplier bits from the RESET PCI - * device present in the system. - */ - pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, - PCI_DEVID_OCTEONTX2_RST, NULL); - if (!pdev) - goto error; - - base = pci_ioremap_bar(pdev, PCI_RST_BAR_NO); - if (!base) - goto error_put_pdev; - - cfg = readq(base + RST_BOOT); - ret = CLOCK_BASE_RATE * FIELD_GET(RST_MUL_BITS, cfg); - - iounmap(base); - -error_put_pdev: - pci_dev_put(pdev); - -error: - return ret; -} - struct ptp *ptp_get(void) { struct ptp *ptp = first_ptp_block; @@ -145,13 +120,74 @@ static int ptp_get_clock(struct ptp *ptp, u64 *clk) return 0; } +void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts) +{ + struct pci_dev *pdev; + u64 clock_comp; + u64 clock_cfg; + + if (!ptp) + return; + + pdev = ptp->pdev; + + if (!sclk) { + dev_err(&pdev->dev, "PTP input clock cannot be zero\n"); + return; + } + + /* sclk is in MHz */ + ptp->clock_rate = sclk * 1000000; + + /* Enable PTP clock */ + clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); + + if (ext_clk_freq) { + ptp->clock_rate = ext_clk_freq; + /* Set GPIO as PTP clock source */ + clock_cfg &= ~PTP_CLOCK_CFG_EXT_CLK_IN_MASK; + clock_cfg |= PTP_CLOCK_CFG_EXT_CLK_EN; + } + + if (extts) { + clock_cfg |= PTP_CLOCK_CFG_TSTMP_EDGE; + /* Set GPIO as timestamping source */ + clock_cfg &= ~PTP_CLOCK_CFG_TSTMP_IN_MASK; + clock_cfg |= PTP_CLOCK_CFG_TSTMP_EN; + } + + clock_cfg |= PTP_CLOCK_CFG_PTP_EN; + clock_cfg |= PTP_CLOCK_CFG_PPS_EN | PTP_CLOCK_CFG_PPS_INV; + writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); + + /* Set 50% duty cycle for 1Hz output */ + writeq(0x1dcd650000000000, ptp->reg_base + PTP_PPS_HI_INCR); + writeq(0x1dcd650000000000, ptp->reg_base + PTP_PPS_LO_INCR); + + clock_comp = ((u64)1000000000ull << 32) / ptp->clock_rate; + /* Initial compensation value to start the nanosecs counter */ + writeq(clock_comp, ptp->reg_base + PTP_CLOCK_COMP); +} + +static int ptp_get_tstmp(struct ptp *ptp, u64 *clk) +{ + *clk = readq(ptp->reg_base + PTP_TIMESTAMP); + + return 0; +} + +static int ptp_set_thresh(struct ptp *ptp, u64 thresh) +{ + writeq(thresh, ptp->reg_base + PTP_PPS_THRESH_HI); + + return 0; +} + static int ptp_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct device *dev = &pdev->dev; struct ptp *ptp; - u64 clock_comp; - u64 clock_cfg; int err; ptp = devm_kzalloc(dev, sizeof(*ptp), GFP_KERNEL); @@ -172,17 +208,6 @@ static int ptp_probe(struct pci_dev *pdev, ptp->reg_base = pcim_iomap_table(pdev)[PCI_PTP_BAR_NO]; - ptp->clock_rate = get_clock_rate(); - - /* Enable PTP clock */ - clock_cfg = readq(ptp->reg_base + PTP_CLOCK_CFG); - clock_cfg |= PTP_CLOCK_CFG_PTP_EN; - writeq(clock_cfg, ptp->reg_base + PTP_CLOCK_CFG); - - clock_comp = ((u64)1000000000ull << 32) / ptp->clock_rate; - /* Initial compensation value to start the nanosecs counter */ - writeq(clock_comp, ptp->reg_base + PTP_CLOCK_COMP); - pci_set_drvdata(pdev, ptp); if (!first_ptp_block) first_ptp_block = ptp; @@ -272,6 +297,12 @@ int rvu_mbox_handler_ptp_op(struct rvu *rvu, struct ptp_req *req, case PTP_OP_GET_CLOCK: err = ptp_get_clock(rvu->ptp, &rsp->clk); break; + case PTP_OP_GET_TSTMP: + err = ptp_get_tstmp(rvu->ptp, &rsp->clk); + break; + case PTP_OP_SET_THRESH: + err = ptp_set_thresh(rvu->ptp, req->thresh); + break; default: err = -EINVAL; break; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h index 76d404b24552e0..1b81a0493cd32b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/ptp.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/ptp.h @@ -20,6 +20,7 @@ struct ptp { struct ptp *ptp_get(void); void ptp_put(struct ptp *ptp); +void ptp_start(struct ptp *ptp, u64 sclk, u32 ext_clk_freq, u32 extts); extern struct pci_driver ptp_driver; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c index 07b0eafccad87c..e695fa0e82a94c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.c @@ -29,6 +29,7 @@ static struct mac_ops rpm_mac_ops = { .mac_get_pause_frm_status = rpm_lmac_get_pause_frm_status, .mac_enadis_pause_frm = rpm_lmac_enadis_pause_frm, .mac_pause_frm_config = rpm_lmac_pause_frm_config, + .mac_enadis_ptp_config = rpm_lmac_ptp_config, }; struct mac_ops *rpm_get_mac_ops(void) @@ -270,3 +271,19 @@ int rpm_lmac_internal_loopback(void *rpmd, int lmac_id, bool enable) return 0; } + +void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable) +{ + rpm_t *rpm = rpmd; + u64 cfg; + + if (!is_lmac_valid(rpm, lmac_id)) + return; + + cfg = rpm_read(rpm, lmac_id, RPMX_CMRX_CFG); + if (enable) + cfg |= RPMX_RX_TS_PREPEND; + else + cfg &= ~RPMX_RX_TS_PREPEND; + rpm_write(rpm, lmac_id, RPMX_CMRX_CFG, cfg); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h index f0b069442dccb9..57c8a687b488a9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rpm.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rpm.h @@ -14,6 +14,8 @@ #define PCI_DEVID_CN10K_RPM 0xA060 /* Registers */ +#define RPMX_CMRX_CFG 0x00 +#define RPMX_RX_TS_PREPEND BIT_ULL(22) #define RPMX_CMRX_SW_INT 0x180 #define RPMX_CMRX_SW_INT_W1S 0x188 #define RPMX_CMRX_SW_INT_ENA_W1S 0x198 @@ -54,4 +56,5 @@ int rpm_lmac_enadis_pause_frm(void *rpmd, int lmac_id, u8 tx_pause, u8 rx_pause); int rpm_get_tx_stats(void *rpmd, int lmac_id, int idx, u64 *tx_stat); int rpm_get_rx_stats(void *rpmd, int lmac_id, int idx, u64 *rx_stat); +void rpm_lmac_ptp_config(void *rpmd, int lmac_id, bool enable); #endif /* RPM_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index 35836903b7fbc3..4cb24e91e648a5 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1287,6 +1287,60 @@ static int rvu_lookup_rsrc(struct rvu *rvu, struct rvu_block *block, return (val & 0xFFF); } +int rvu_get_blkaddr_from_slot(struct rvu *rvu, int blktype, u16 pcifunc, + u16 global_slot, u16 *slot_in_block) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int numlfs, total_lfs = 0, nr_blocks = 0; + int i, num_blkaddr[BLK_COUNT] = { 0 }; + struct rvu_block *block; + int blkaddr; + u16 start_slot; + + if (!is_blktype_attached(pfvf, blktype)) + return -ENODEV; + + /* Get all the block addresses from which LFs are attached to + * the given pcifunc in num_blkaddr[]. + */ + for (blkaddr = BLKADDR_RVUM; blkaddr < BLK_COUNT; blkaddr++) { + block = &rvu->hw->block[blkaddr]; + if (block->type != blktype) + continue; + if (!is_block_implemented(rvu->hw, blkaddr)) + continue; + + numlfs = rvu_get_rsrc_mapcount(pfvf, blkaddr); + if (numlfs) { + total_lfs += numlfs; + num_blkaddr[nr_blocks] = blkaddr; + nr_blocks++; + } + } + + if (global_slot >= total_lfs) + return -ENODEV; + + /* Based on the given global slot number retrieve the + * correct block address out of all attached block + * addresses and slot number in that block. + */ + total_lfs = 0; + blkaddr = -ENODEV; + for (i = 0; i < nr_blocks; i++) { + numlfs = rvu_get_rsrc_mapcount(pfvf, num_blkaddr[i]); + total_lfs += numlfs; + if (global_slot < total_lfs) { + blkaddr = num_blkaddr[i]; + start_slot = total_lfs - numlfs; + *slot_in_block = global_slot - start_slot; + break; + } + } + + return blkaddr; +} + static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -3186,6 +3240,10 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&rvu->rswitch.switch_lock); + if (rvu->fwdata) + ptp_start(rvu->ptp, rvu->fwdata->sclk, rvu->fwdata->ptp_ext_clk_rate, + rvu->fwdata->ptp_ext_tstamp); + return 0; err_dl: rvu_unregister_dl(rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 1d9411232f1dab..58b166698fa5d8 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -220,6 +220,7 @@ struct rvu_pfvf { u16 maxlen; u16 minlen; + bool hw_rx_tstamp_en; /* Is rx_tstamp enabled */ u8 mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */ u8 default_mac[ETH_ALEN]; /* MAC address from FWdata */ @@ -237,6 +238,7 @@ struct rvu_pfvf { bool cgx_in_use; /* this PF/VF using CGX? */ int cgx_users; /* number of cgx users - used only by PFs */ + int intf_mode; u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ @@ -394,7 +396,9 @@ struct rvu_fwdata { u64 mcam_addr; u64 mcam_sz; u64 msixtr_base; -#define FWDATA_RESERVED_MEM 1023 + u32 ptp_ext_clk_rate; + u32 ptp_ext_tstamp; +#define FWDATA_RESERVED_MEM 1022 u64 reserved[FWDATA_RESERVED_MEM]; #define CGX_MAX 5 #define CGX_LMACS_MAX 4 @@ -656,6 +660,8 @@ int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf); int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc); int rvu_poll_reg(struct rvu *rvu, u64 block, u64 offset, u64 mask, bool zero); int rvu_get_num_lbk_chans(void); +int rvu_get_blkaddr_from_slot(struct rvu *rvu, int blktype, u16 pcifunc, + u16 global_slot, u16 *slot_in_block); /* RVU HW reg validation */ enum regmap_block { @@ -794,6 +800,7 @@ void npc_enable_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, int blkaddr, u16 src, struct mcam_entry *entry, u8 *intf, u8 *ena); +bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc); bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); void *rvu_first_cgx_pdata(struct rvu *rvu); @@ -827,4 +834,7 @@ void rvu_switch_enable(struct rvu *rvu); void rvu_switch_disable(struct rvu *rvu); void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc); +int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, + u64 pkind, u8 var_len_off, u8 var_len_off_mask, + u8 shift_dir); #endif /* RVU_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 81e8ea9ee30ea0..c3842e4546579a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -411,7 +411,7 @@ int rvu_cgx_exit(struct rvu *rvu) * VF's of mapped PF and other PFs are not allowed. This fn() checks * whether a PFFUNC is permitted to do the config or not. */ -static bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc) +inline bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc) { if ((pcifunc & RVU_PFVF_FUNC_MASK) || !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) @@ -694,7 +694,9 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req, static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) { + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; u8 cgx_id, lmac_id; void *cgxd; @@ -711,13 +713,16 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); cgxd = rvu_cgx_pdata(cgx_id, rvu); - cgx_lmac_ptp_config(cgxd, lmac_id, enable); + mac_ops = get_mac_ops(cgxd); + mac_ops->mac_enadis_ptp_config(cgxd, lmac_id, true); /* If PTP is enabled then inform NPC that packets to be * parsed by this PF will have their data shifted by 8 bytes * and if PTP is disabled then no shift is required */ if (npc_config_ts_kpuaction(rvu, pf, pcifunc, enable)) return -EINVAL; + /* This flag is required to clean up CGX conf if app gets killed */ + pfvf->hw_rx_tstamp_en = enable; return 0; } @@ -725,6 +730,9 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable) int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { + if (!is_pf_cgxmapped(rvu, rvu_get_pf(req->hdr.pcifunc))) + return -EPERM; + return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c index 46a41cfff5751b..7dbbc115cde426 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c @@ -334,8 +334,8 @@ int rvu_set_channels_base(struct rvu *rvu) /* Out of 4096 channels start CPT from 2048 so * that MSB for CPT channels is always set */ - if (cpt_chan_base <= 0x800) { - hw->cpt_chan_base = 0x800; + if (cpt_chan_base <= NIX_CHAN_CPT_CH_START) { + hw->cpt_chan_base = NIX_CHAN_CPT_CH_START; } else { dev_err(rvu->dev, "CPT channels could not fit in the range 2048-4095\n"); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c index 1f90a7403392d5..267d092b8e9735 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c @@ -197,6 +197,141 @@ int rvu_mbox_handler_cpt_lf_free(struct rvu *rvu, struct msg_req *req, return ret; } +static int cpt_inline_ipsec_cfg_inbound(struct rvu *rvu, int blkaddr, u8 cptlf, + struct cpt_inline_ipsec_cfg_msg *req) +{ + u16 sso_pf_func = req->sso_pf_func; + u8 nix_sel; + u64 val; + + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf)); + if (req->enable && (val & BIT_ULL(16))) { + /* IPSec inline outbound path is already enabled for a given + * CPT LF, HRM states that inline inbound & outbound paths + * must not be enabled at the same time for a given CPT LF + */ + return CPT_AF_ERR_INLINE_IPSEC_INB_ENA; + } + /* Check if requested 'CPTLF <=> SSOLF' mapping is valid */ + if (sso_pf_func && !is_pffunc_map_valid(rvu, sso_pf_func, BLKTYPE_SSO)) + return CPT_AF_ERR_SSO_PF_FUNC_INVALID; + + nix_sel = (blkaddr == BLKADDR_CPT1) ? 1 : 0; + /* Enable CPT LF for IPsec inline inbound operations */ + if (req->enable) + val |= BIT_ULL(9); + else + val &= ~BIT_ULL(9); + + val |= (u64)nix_sel << 8; + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); + + if (sso_pf_func) { + /* Set SSO_PF_FUNC */ + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + val |= (u64)sso_pf_func << 32; + val |= (u64)req->nix_pf_func << 48; + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val); + } + if (req->sso_pf_func_ovrd) + /* Set SSO_PF_FUNC_OVRD for inline IPSec */ + rvu_write64(rvu, blkaddr, CPT_AF_ECO, 0x1); + + /* Configure the X2P Link register with the cpt base channel number and + * range of channels it should propagate to X2P + */ + if (!is_rvu_otx2(rvu)) { + val = (ilog2(NIX_CHAN_CPT_X2P_MASK + 1) << 16); + val |= rvu->hw->cpt_chan_base; + + rvu_write64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(0), val); + rvu_write64(rvu, blkaddr, CPT_AF_X2PX_LINK_CFG(1), val); + } + + return 0; +} + +static int cpt_inline_ipsec_cfg_outbound(struct rvu *rvu, int blkaddr, u8 cptlf, + struct cpt_inline_ipsec_cfg_msg *req) +{ + u16 nix_pf_func = req->nix_pf_func; + int nix_blkaddr; + u8 nix_sel; + u64 val; + + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf)); + if (req->enable && (val & BIT_ULL(9))) { + /* IPSec inline inbound path is already enabled for a given + * CPT LF, HRM states that inline inbound & outbound paths + * must not be enabled at the same time for a given CPT LF + */ + return CPT_AF_ERR_INLINE_IPSEC_OUT_ENA; + } + + /* Check if requested 'CPTLF <=> NIXLF' mapping is valid */ + if (nix_pf_func && !is_pffunc_map_valid(rvu, nix_pf_func, BLKTYPE_NIX)) + return CPT_AF_ERR_NIX_PF_FUNC_INVALID; + + /* Enable CPT LF for IPsec inline outbound operations */ + if (req->enable) + val |= BIT_ULL(16); + else + val &= ~BIT_ULL(16); + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); + + if (nix_pf_func) { + /* Set NIX_PF_FUNC */ + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf)); + val |= (u64)nix_pf_func << 48; + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL2(cptlf), val); + + nix_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, nix_pf_func); + nix_sel = (nix_blkaddr == BLKADDR_NIX0) ? 0 : 1; + + val = rvu_read64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf)); + val |= (u64)nix_sel << 8; + rvu_write64(rvu, blkaddr, CPT_AF_LFX_CTL(cptlf), val); + } + + return 0; +} + +int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu, + struct cpt_inline_ipsec_cfg_msg *req, + struct msg_rsp *rsp) +{ + u16 pcifunc = req->hdr.pcifunc; + struct rvu_block *block; + int cptlf, blkaddr, ret; + u16 actual_slot; + + blkaddr = rvu_get_blkaddr_from_slot(rvu, BLKTYPE_CPT, pcifunc, + req->slot, &actual_slot); + if (blkaddr < 0) + return CPT_AF_ERR_LF_INVALID; + + block = &rvu->hw->block[blkaddr]; + + cptlf = rvu_get_lf(rvu, block, pcifunc, actual_slot); + if (cptlf < 0) + return CPT_AF_ERR_LF_INVALID; + + switch (req->dir) { + case CPT_INLINE_INBOUND: + ret = cpt_inline_ipsec_cfg_inbound(rvu, blkaddr, cptlf, req); + break; + + case CPT_INLINE_OUTBOUND: + ret = cpt_inline_ipsec_cfg_outbound(rvu, blkaddr, cptlf, req); + break; + + default: + return CPT_AF_ERR_PARAM; + } + + return ret; +} + static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req) { u64 offset = req->reg_offset; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 274d3abe30eb43..70bacd38a6d9d0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1510,13 +1510,6 @@ int rvu_register_dl(struct rvu *rvu) return -ENOMEM; } - err = devlink_register(dl); - if (err) { - dev_err(rvu->dev, "devlink register failed with error %d\n", err); - devlink_free(dl); - return err; - } - rvu_dl = devlink_priv(dl); rvu_dl->dl = dl; rvu_dl->rvu = rvu; @@ -1537,13 +1530,11 @@ int rvu_register_dl(struct rvu *rvu) goto err_dl_health; } - devlink_params_publish(dl); - + devlink_register(dl); return 0; err_dl_health: rvu_health_reporters_destroy(rvu); - devlink_unregister(dl); devlink_free(dl); return err; } @@ -1553,12 +1544,9 @@ void rvu_unregister_dl(struct rvu *rvu) struct rvu_devlink *rvu_dl = rvu->rvu_dl; struct devlink *dl = rvu_dl->dl; - if (!dl) - return; - + devlink_unregister(dl); devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); rvu_health_reporters_destroy(rvu); - devlink_unregister(dl); devlink_free(dl); } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 9ef4e942e31e0a..67feb26792e4b6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -28,6 +28,7 @@ static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req, static int nix_free_all_bandprof(struct rvu *rvu, u16 pcifunc); static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw, u32 leaf_prof); +static const char *nix_get_ctx_name(int ctype); enum mc_tbl_sz { MC_TBL_SZ_256, @@ -1061,10 +1062,68 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, return 0; } +static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw, + struct nix_aq_enq_req *req, u8 ctype) +{ + struct nix_cn10k_aq_enq_req aq_req; + struct nix_cn10k_aq_enq_rsp aq_rsp; + int rc, word; + + if (req->ctype != NIX_AQ_CTYPE_CQ) + return 0; + + rc = nix_aq_context_read(rvu, nix_hw, &aq_req, &aq_rsp, + req->hdr.pcifunc, ctype, req->qidx); + if (rc) { + dev_err(rvu->dev, + "%s: Failed to fetch %s%d context of PFFUNC 0x%x\n", + __func__, nix_get_ctx_name(ctype), req->qidx, + req->hdr.pcifunc); + return rc; + } + + /* Make copy of original context & mask which are required + * for resubmission + */ + memcpy(&aq_req.cq_mask, &req->cq_mask, sizeof(struct nix_cq_ctx_s)); + memcpy(&aq_req.cq, &req->cq, sizeof(struct nix_cq_ctx_s)); + + /* exclude fields which HW can update */ + aq_req.cq_mask.cq_err = 0; + aq_req.cq_mask.wrptr = 0; + aq_req.cq_mask.tail = 0; + aq_req.cq_mask.head = 0; + aq_req.cq_mask.avg_level = 0; + aq_req.cq_mask.update_time = 0; + aq_req.cq_mask.substream = 0; + + /* Context mask (cq_mask) holds mask value of fields which + * are changed in AQ WRITE operation. + * for example cq.drop = 0xa; + * cq_mask.drop = 0xff; + * Below logic performs '&' between cq and cq_mask so that non + * updated fields are masked out for request and response + * comparison + */ + for (word = 0; word < sizeof(struct nix_cq_ctx_s) / sizeof(u64); + word++) { + *(u64 *)((u8 *)&aq_rsp.cq + word * 8) &= + (*(u64 *)((u8 *)&aq_req.cq_mask + word * 8)); + *(u64 *)((u8 *)&aq_req.cq + word * 8) &= + (*(u64 *)((u8 *)&aq_req.cq_mask + word * 8)); + } + + if (memcmp(&aq_req.cq, &aq_rsp.cq, sizeof(struct nix_cq_ctx_s))) + return NIX_AF_ERR_AQ_CTX_RETRY_WRITE; + + return 0; +} + static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, struct nix_aq_enq_rsp *rsp) { struct nix_hw *nix_hw; + int err, retries = 5; int blkaddr; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, req->hdr.pcifunc); @@ -1075,7 +1134,24 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, if (!nix_hw) return NIX_AF_ERR_INVALID_NIXBLK; - return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, req, rsp); +retry: + err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, req, rsp); + + /* HW errata 'AQ Modification to CQ could be discarded on heavy traffic' + * As a work around perfrom CQ context read after each AQ write. If AQ + * read shows AQ write is not updated perform AQ write again. + */ + if (!err && req->op == NIX_AQ_INSTOP_WRITE) { + err = rvu_nix_verify_aq_ctx(rvu, nix_hw, req, NIX_AQ_CTYPE_CQ); + if (err == NIX_AF_ERR_AQ_CTX_RETRY_WRITE) { + if (retries--) + goto retry; + else + return NIX_AF_ERR_CQ_CTX_WRITE_ERR; + } + } + + return err; } static const char *nix_get_ctx_name(int ctype) @@ -4440,6 +4516,10 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct hwctx_disable_req ctx_req; + int pf = rvu_get_pf(pcifunc); + struct mac_ops *mac_ops; + u8 cgx_id, lmac_id; + void *cgxd; int err; ctx_req.hdr.pcifunc = pcifunc; @@ -4476,6 +4556,22 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) dev_err(rvu->dev, "CQ ctx disable failed\n"); } + /* reset HW config done for Switch headers */ + rvu_npc_set_parse_mode(rvu, pcifunc, OTX2_PRIV_FLAGS_DEFAULT, + (PKIND_TX | PKIND_RX), 0, 0, 0, 0); + + /* Disabling CGX and NPC config done for PTP */ + if (pfvf->hw_rx_tstamp_en) { + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + cgxd = rvu_cgx_pdata(cgx_id, rvu); + mac_ops = get_mac_ops(cgxd); + mac_ops->mac_enadis_ptp_config(cgxd, lmac_id, false); + /* Undo NPC config done for PTP */ + if (npc_config_ts_kpuaction(rvu, pf, pcifunc, false)) + dev_err(rvu->dev, "NPC config for PTP failed\n"); + pfvf->hw_rx_tstamp_en = false; + } + nix_ctx_free(rvu, pfvf); nix_free_all_bandprof(rvu, pcifunc); @@ -4579,6 +4675,119 @@ int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu, return 0; } +#define IPSEC_GEN_CFG_EGRP GENMASK_ULL(50, 48) +#define IPSEC_GEN_CFG_OPCODE GENMASK_ULL(47, 32) +#define IPSEC_GEN_CFG_PARAM1 GENMASK_ULL(31, 16) +#define IPSEC_GEN_CFG_PARAM2 GENMASK_ULL(15, 0) + +#define CPT_INST_QSEL_BLOCK GENMASK_ULL(28, 24) +#define CPT_INST_QSEL_PF_FUNC GENMASK_ULL(23, 8) +#define CPT_INST_QSEL_SLOT GENMASK_ULL(7, 0) + +static void nix_inline_ipsec_cfg(struct rvu *rvu, struct nix_inline_ipsec_cfg *req, + int blkaddr) +{ + u8 cpt_idx, cpt_blkaddr; + u64 val; + + cpt_idx = (blkaddr == BLKADDR_NIX0) ? 0 : 1; + if (req->enable) { + val = 0; + /* Enable context prefetching */ + if (!is_rvu_otx2(rvu)) + val |= BIT_ULL(51); + + /* Set OPCODE and EGRP */ + val |= FIELD_PREP(IPSEC_GEN_CFG_EGRP, req->gen_cfg.egrp); + val |= FIELD_PREP(IPSEC_GEN_CFG_OPCODE, req->gen_cfg.opcode); + val |= FIELD_PREP(IPSEC_GEN_CFG_PARAM1, req->gen_cfg.param1); + val |= FIELD_PREP(IPSEC_GEN_CFG_PARAM2, req->gen_cfg.param2); + + rvu_write64(rvu, blkaddr, NIX_AF_RX_IPSEC_GEN_CFG, val); + + /* Set CPT queue for inline IPSec */ + val = FIELD_PREP(CPT_INST_QSEL_SLOT, req->inst_qsel.cpt_slot); + val |= FIELD_PREP(CPT_INST_QSEL_PF_FUNC, + req->inst_qsel.cpt_pf_func); + + if (!is_rvu_otx2(rvu)) { + cpt_blkaddr = (cpt_idx == 0) ? BLKADDR_CPT0 : + BLKADDR_CPT1; + val |= FIELD_PREP(CPT_INST_QSEL_BLOCK, cpt_blkaddr); + } + + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_INST_QSEL(cpt_idx), + val); + + /* Set CPT credit */ + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + req->cpt_credit); + } else { + rvu_write64(rvu, blkaddr, NIX_AF_RX_IPSEC_GEN_CFG, 0x0); + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_INST_QSEL(cpt_idx), + 0x0); + rvu_write64(rvu, blkaddr, NIX_AF_RX_CPTX_CREDIT(cpt_idx), + 0x3FFFFF); + } +} + +int rvu_mbox_handler_nix_inline_ipsec_cfg(struct rvu *rvu, + struct nix_inline_ipsec_cfg *req, + struct msg_rsp *rsp) +{ + if (!is_block_implemented(rvu->hw, BLKADDR_CPT0)) + return 0; + + nix_inline_ipsec_cfg(rvu, req, BLKADDR_NIX0); + if (is_block_implemented(rvu->hw, BLKADDR_CPT1)) + nix_inline_ipsec_cfg(rvu, req, BLKADDR_NIX1); + + return 0; +} + +int rvu_mbox_handler_nix_inline_ipsec_lf_cfg(struct rvu *rvu, + struct nix_inline_ipsec_lf_cfg *req, + struct msg_rsp *rsp) +{ + int lf, blkaddr, err; + u64 val; + + if (!is_block_implemented(rvu->hw, BLKADDR_CPT0)) + return 0; + + err = nix_get_nixlf(rvu, req->hdr.pcifunc, &lf, &blkaddr); + if (err) + return err; + + if (req->enable) { + /* Set TT, TAG_CONST, SA_POW2_SIZE and LENM1_MAX */ + val = (u64)req->ipsec_cfg0.tt << 44 | + (u64)req->ipsec_cfg0.tag_const << 20 | + (u64)req->ipsec_cfg0.sa_pow2_size << 16 | + req->ipsec_cfg0.lenm1_max; + + if (blkaddr == BLKADDR_NIX1) + val |= BIT_ULL(46); + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_CFG0(lf), val); + + /* Set SA_IDX_W and SA_IDX_MAX */ + val = (u64)req->ipsec_cfg1.sa_idx_w << 32 | + req->ipsec_cfg1.sa_idx_max; + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_CFG1(lf), val); + + /* Set SA base address */ + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_SA_BASE(lf), + req->sa_base_addr); + } else { + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_CFG0(lf), 0x0); + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_CFG1(lf), 0x0); + rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_IPSEC_SA_BASE(lf), + 0x0); + } + + return 0; +} void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc) { bool from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 5efb4174e82dff..2881ccc56b289f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -3167,6 +3167,102 @@ int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req, return 0; } +int +npc_set_var_len_offset_pkind(struct rvu *rvu, u16 pcifunc, u64 pkind, + u8 var_len_off, u8 var_len_off_mask, u8 shift_dir) +{ + struct npc_kpu_action0 *act0; + u8 shift_count = 0; + int blkaddr; + u64 val; + + if (!var_len_off_mask) + return -EINVAL; + + if (var_len_off_mask != 0xff) { + if (shift_dir) + shift_count = __ffs(var_len_off_mask); + else + shift_count = (8 - __fls(var_len_off_mask)); + } + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, pcifunc); + if (blkaddr < 0) { + dev_err(rvu->dev, "%s: NPC block not implemented\n", __func__); + return -EINVAL; + } + val = rvu_read64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind)); + act0 = (struct npc_kpu_action0 *)&val; + act0->var_len_shift = shift_count; + act0->var_len_right = shift_dir; + act0->var_len_mask = var_len_off_mask; + act0->var_len_offset = var_len_off; + rvu_write64(rvu, blkaddr, NPC_AF_PKINDX_ACTION0(pkind), val); + return 0; +} + +int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir, + u64 pkind, u8 var_len_off, u8 var_len_off_mask, + u8 shift_dir) + +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int blkaddr, nixlf, rc, intf_mode; + int pf = rvu_get_pf(pcifunc); + u64 rxpkind, txpkind; + u8 cgx_id, lmac_id; + + /* use default pkind to disable edsa/higig */ + rxpkind = rvu_npc_get_pkind(rvu, pf); + txpkind = NPC_TX_DEF_PKIND; + intf_mode = NPC_INTF_MODE_DEF; + + if (mode & OTX2_PRIV_FLAGS_CUSTOM) { + if (pkind == NPC_RX_CUSTOM_PRE_L2_PKIND) { + rc = npc_set_var_len_offset_pkind(rvu, pcifunc, pkind, + var_len_off, + var_len_off_mask, + shift_dir); + if (rc) + return rc; + } + rxpkind = pkind; + txpkind = pkind; + } + + if (dir & PKIND_RX) { + /* rx pkind set req valid only for cgx mapped PFs */ + if (!is_cgx_config_permitted(rvu, pcifunc)) + return 0; + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + + rc = cgx_set_pkind(rvu_cgx_pdata(cgx_id, rvu), lmac_id, + rxpkind); + if (rc) + return rc; + } + + if (dir & PKIND_TX) { + /* Tx pkind set request valid if PCIFUNC has NIXLF attached */ + rc = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + if (rc) + return rc; + + rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_PARSE_CFG(nixlf), + txpkind); + } + + pfvf->intf_mode = intf_mode; + return 0; +} + +int rvu_mbox_handler_npc_set_pkind(struct rvu *rvu, struct npc_set_pkind *req, + struct msg_rsp *rsp) +{ + return rvu_npc_set_parse_mode(rvu, req->hdr.pcifunc, req->mode, + req->dir, req->pkind, req->var_len_off, + req->var_len_off_mask, req->shift_dir); +} + int rvu_mbox_handler_npc_read_base_steer_rule(struct rvu *rvu, struct msg_req *req, struct npc_mcam_read_base_rule_rsp *rsp) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 21f1ed4e222f75..dbaeb10de7c28d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -236,6 +236,8 @@ #define NIX_AF_RX_DEF_OIP6_DSCP (0x02F8) #define NIX_AF_RX_IPSEC_GEN_CFG (0x0300) #define NIX_AF_RX_CPTX_INST_ADDR (0x0310) +#define NIX_AF_RX_CPTX_INST_QSEL(a) (0x0320ull | (uint64_t)(a) << 3) +#define NIX_AF_RX_CPTX_CREDIT(a) (0x0360ull | (uint64_t)(a) << 3) #define NIX_AF_NDC_TX_SYNC (0x03F0) #define NIX_AF_AQ_CFG (0x0400) #define NIX_AF_AQ_BASE (0x0410) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile index b92c267628b872..aaf9accc40edcc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile @@ -9,6 +9,6 @@ obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \ otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \ otx2_devlink.o -rvu_nicvf-y := otx2_vf.o otx2_devlink.o +rvu_nicvf-y := otx2_vf.o otx2_devlink.o otx2_ptp.o ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 78df173e6df240..4c3dbade8cfb56 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1006,6 +1006,9 @@ int otx2_config_nix_queues(struct otx2_nic *pfvf) return err; } + pfvf->cq_op_addr = (__force u64 *)otx2_get_regaddr(pfvf, + NIX_LF_CQ_OP_STATUS); + /* Initialize work queue for receive buffer refill */ pfvf->refill_wrk = devm_kcalloc(pfvf->dev, pfvf->qset.cq_cnt, sizeof(struct refill_work), GFP_KERNEL); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index a51ecd771d0755..bf86a5572a3da9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -223,6 +223,7 @@ struct otx2_hw { #define HW_TSO 0 #define CN10K_MBOX 1 #define CN10K_LMTST 2 +#define CN10K_RPM 3 unsigned long cap_flag; #define LMT_LINE_SIZE 128 @@ -263,6 +264,12 @@ struct otx2_ptp { struct cyclecounter cycle_counter; struct timecounter time_counter; + + struct delayed_work extts_work; + u64 last_extts; + u64 thresh; + + struct ptp_pin_desc extts_config; }; #define OTX2_HW_TIMESTAMP_LEN 8 @@ -336,6 +343,7 @@ struct otx2_nic { #define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13) #define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14) u64 flags; + u64 *cq_op_addr; struct otx2_qset qset; struct otx2_hw hw; @@ -452,6 +460,7 @@ static inline void otx2_setup_dev_hw_settings(struct otx2_nic *pfvf) if (!is_dev_otx2(pfvf->pdev)) { __set_bit(CN10K_MBOX, &hw->cap_flag); __set_bit(CN10K_LMTST, &hw->cap_flag); + __set_bit(CN10K_RPM, &hw->cap_flag); } } @@ -825,6 +834,9 @@ int otx2_open(struct net_device *netdev); int otx2_stop(struct net_device *netdev); int otx2_set_real_num_queues(struct net_device *netdev, int tx_queues, int rx_queues); +int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd); +int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr); + /* MCAM filter related APIs */ int otx2_mcam_flow_init(struct otx2_nic *pf); int otx2vf_mcam_flow_init(struct otx2_nic *pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c index 7ac3ef2fa06a26..777a27047c8e8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_devlink.c @@ -108,13 +108,6 @@ int otx2_register_dl(struct otx2_nic *pfvf) return -ENOMEM; } - err = devlink_register(dl); - if (err) { - dev_err(pfvf->dev, "devlink register failed with error %d\n", err); - devlink_free(dl); - return err; - } - otx2_dl = devlink_priv(dl); otx2_dl->dl = dl; otx2_dl->pfvf = pfvf; @@ -128,12 +121,10 @@ int otx2_register_dl(struct otx2_nic *pfvf) goto err_dl; } - devlink_params_publish(dl); - + devlink_register(dl); return 0; err_dl: - devlink_unregister(dl); devlink_free(dl); return err; } @@ -141,16 +132,10 @@ err_dl: void otx2_unregister_dl(struct otx2_nic *pfvf) { struct otx2_devlink *otx2_dl = pfvf->dl; - struct devlink *dl; - - if (!otx2_dl || !otx2_dl->dl) - return; - - dl = otx2_dl->dl; + struct devlink *dl = otx2_dl->dl; + devlink_unregister(dl); devlink_params_unregister(dl, otx2_dl_params, ARRAY_SIZE(otx2_dl_params)); - - devlink_unregister(dl); devlink_free(dl); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index dbfa3bc39e34e6..b0f57bda7e27ab 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -121,14 +121,16 @@ static void otx2_get_strings(struct net_device *netdev, u32 sset, u8 *data) otx2_get_qset_strings(pfvf, &data, 0); - for (stats = 0; stats < CGX_RX_STATS_COUNT; stats++) { - sprintf(data, "cgx_rxstat%d: ", stats); - data += ETH_GSTRING_LEN; - } + if (!test_bit(CN10K_RPM, &pfvf->hw.cap_flag)) { + for (stats = 0; stats < CGX_RX_STATS_COUNT; stats++) { + sprintf(data, "cgx_rxstat%d: ", stats); + data += ETH_GSTRING_LEN; + } - for (stats = 0; stats < CGX_TX_STATS_COUNT; stats++) { - sprintf(data, "cgx_txstat%d: ", stats); - data += ETH_GSTRING_LEN; + for (stats = 0; stats < CGX_TX_STATS_COUNT; stats++) { + sprintf(data, "cgx_txstat%d: ", stats); + data += ETH_GSTRING_LEN; + } } strcpy(data, "reset_count"); @@ -205,11 +207,15 @@ static void otx2_get_ethtool_stats(struct net_device *netdev, [otx2_drv_stats[stat].index]); otx2_get_qset_stats(pfvf, stats, &data); - otx2_update_lmac_stats(pfvf); - for (stat = 0; stat < CGX_RX_STATS_COUNT; stat++) - *(data++) = pfvf->hw.cgx_rx_stats[stat]; - for (stat = 0; stat < CGX_TX_STATS_COUNT; stat++) - *(data++) = pfvf->hw.cgx_tx_stats[stat]; + + if (!test_bit(CN10K_RPM, &pfvf->hw.cap_flag)) { + otx2_update_lmac_stats(pfvf); + for (stat = 0; stat < CGX_RX_STATS_COUNT; stat++) + *(data++) = pfvf->hw.cgx_rx_stats[stat]; + for (stat = 0; stat < CGX_TX_STATS_COUNT; stat++) + *(data++) = pfvf->hw.cgx_tx_stats[stat]; + } + *(data++) = pfvf->reset_count; fec_corr_blks = pfvf->hw.cgx_fec_corr_blks; @@ -242,18 +248,19 @@ static void otx2_get_ethtool_stats(struct net_device *netdev, static int otx2_get_sset_count(struct net_device *netdev, int sset) { struct otx2_nic *pfvf = netdev_priv(netdev); - int qstats_count; + int qstats_count, mac_stats = 0; if (sset != ETH_SS_STATS) return -EINVAL; qstats_count = otx2_n_queue_stats * (pfvf->hw.rx_queues + pfvf->hw.tx_queues); + if (!test_bit(CN10K_RPM, &pfvf->hw.cap_flag)) + mac_stats = CGX_RX_STATS_COUNT + CGX_TX_STATS_COUNT; otx2_update_lmac_fec_stats(pfvf); return otx2_n_dev_stats + otx2_n_drv_stats + qstats_count + - CGX_RX_STATS_COUNT + CGX_TX_STATS_COUNT + OTX2_FEC_STATS_CNT - + 1; + mac_stats + OTX2_FEC_STATS_CNT + 1; } /* Get no of queues device supports and current queue count */ @@ -1340,6 +1347,7 @@ static const struct ethtool_ops otx2vf_ethtool_ops = { .get_pauseparam = otx2_get_pauseparam, .set_pauseparam = otx2_set_pauseparam, .get_link_ksettings = otx2vf_get_link_ksettings, + .get_ts_info = otx2_get_ts_info, }; void otx2vf_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 53df7fff92c403..ab07964dbf0a99 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1493,6 +1493,44 @@ static void otx2_free_hw_resources(struct otx2_nic *pf) mutex_unlock(&mbox->lock); } +static void otx2_do_set_rx_mode(struct otx2_nic *pf) +{ + struct net_device *netdev = pf->netdev; + struct nix_rx_mode *req; + bool promisc = false; + + if (!(netdev->flags & IFF_UP)) + return; + + if ((netdev->flags & IFF_PROMISC) || + (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) { + promisc = true; + } + + /* Write unicast address to mcam entries or del from mcam */ + if (!promisc && netdev->priv_flags & IFF_UNICAST_FLT) + __dev_uc_sync(netdev, otx2_add_macfilter, otx2_del_macfilter); + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_nix_set_rx_mode(&pf->mbox); + if (!req) { + mutex_unlock(&pf->mbox.lock); + return; + } + + req->mode = NIX_RX_MODE_UCAST; + + if (promisc) + req->mode |= NIX_RX_MODE_PROMISC; + if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) + req->mode |= NIX_RX_MODE_ALLMULTI; + + req->mode |= NIX_RX_MODE_USE_MCE; + + otx2_sync_mbox_msg(&pf->mbox); + mutex_unlock(&pf->mbox.lock); +} + int otx2_open(struct net_device *netdev) { struct otx2_nic *pf = netdev_priv(netdev); @@ -1646,6 +1684,8 @@ int otx2_open(struct net_device *netdev) if (err) goto err_tx_stop_queues; + otx2_do_set_rx_mode(pf); + return 0; err_tx_stop_queues: @@ -1791,43 +1831,11 @@ static void otx2_set_rx_mode(struct net_device *netdev) queue_work(pf->otx2_wq, &pf->rx_mode_work); } -static void otx2_do_set_rx_mode(struct work_struct *work) +static void otx2_rx_mode_wrk_handler(struct work_struct *work) { struct otx2_nic *pf = container_of(work, struct otx2_nic, rx_mode_work); - struct net_device *netdev = pf->netdev; - struct nix_rx_mode *req; - bool promisc = false; - - if (!(netdev->flags & IFF_UP)) - return; - - if ((netdev->flags & IFF_PROMISC) || - (netdev_uc_count(netdev) > OTX2_MAX_UNICAST_FLOWS)) { - promisc = true; - } - /* Write unicast address to mcam entries or del from mcam */ - if (!promisc && netdev->priv_flags & IFF_UNICAST_FLT) - __dev_uc_sync(netdev, otx2_add_macfilter, otx2_del_macfilter); - - mutex_lock(&pf->mbox.lock); - req = otx2_mbox_alloc_msg_nix_set_rx_mode(&pf->mbox); - if (!req) { - mutex_unlock(&pf->mbox.lock); - return; - } - - req->mode = NIX_RX_MODE_UCAST; - - if (promisc) - req->mode |= NIX_RX_MODE_PROMISC; - if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) - req->mode |= NIX_RX_MODE_ALLMULTI; - - req->mode |= NIX_RX_MODE_USE_MCE; - - otx2_sync_mbox_msg(&pf->mbox); - mutex_unlock(&pf->mbox.lock); + otx2_do_set_rx_mode(pf); } static int otx2_set_features(struct net_device *netdev, @@ -1967,7 +1975,7 @@ static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable) return 0; } -static int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) +int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) { struct otx2_nic *pfvf = netdev_priv(netdev); struct hwtstamp_config config; @@ -2023,8 +2031,9 @@ static int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; } +EXPORT_SYMBOL(otx2_config_hwtstamp); -static int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) +int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) { struct otx2_nic *pfvf = netdev_priv(netdev); struct hwtstamp_config *cfg = &pfvf->tstamp; @@ -2039,6 +2048,7 @@ static int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) return -EOPNOTSUPP; } } +EXPORT_SYMBOL(otx2_ioctl); static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac) { @@ -2358,7 +2368,7 @@ static int otx2_wq_init(struct otx2_nic *pf) if (!pf->otx2_wq) return -ENOMEM; - INIT_WORK(&pf->rx_mode_work, otx2_do_set_rx_mode); + INIT_WORK(&pf->rx_mode_work, otx2_rx_mode_wrk_handler); INIT_WORK(&pf->reset_task, otx2_reset_task); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index ec9e49985c2cef..977a8a40d7d12a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -27,6 +27,23 @@ static int otx2_ptp_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) return otx2_sync_mbox_msg(&ptp->nic->mbox); } +static int ptp_set_thresh(struct otx2_ptp *ptp, u64 thresh) +{ + struct ptp_req *req; + + if (!ptp->nic) + return -ENODEV; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return -ENOMEM; + + req->op = PTP_OP_SET_THRESH; + req->thresh = thresh; + + return otx2_sync_mbox_msg(&ptp->nic->mbox); +} + static u64 ptp_cc_read(const struct cyclecounter *cc) { struct otx2_ptp *ptp = container_of(cc, struct otx2_ptp, cycle_counter); @@ -55,6 +72,33 @@ static u64 ptp_cc_read(const struct cyclecounter *cc) return rsp->clk; } +static u64 ptp_tstmp_read(struct otx2_ptp *ptp) +{ + struct ptp_req *req; + struct ptp_rsp *rsp; + int err; + + if (!ptp->nic) + return 0; + + req = otx2_mbox_alloc_msg_ptp_op(&ptp->nic->mbox); + if (!req) + return 0; + + req->op = PTP_OP_GET_TSTMP; + + err = otx2_sync_mbox_msg(&ptp->nic->mbox); + if (err) + return 0; + + rsp = (struct ptp_rsp *)otx2_mbox_get_rsp(&ptp->nic->mbox.mbox, 0, + &req->hdr); + if (IS_ERR(rsp)) + return 0; + + return rsp->clk; +} + static int otx2_ptp_adjtime(struct ptp_clock_info *ptp_info, s64 delta) { struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, @@ -102,9 +146,73 @@ static int otx2_ptp_settime(struct ptp_clock_info *ptp_info, return 0; } +static int otx2_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, + enum ptp_pin_function func, unsigned int chan) +{ + switch (func) { + case PTP_PF_NONE: + case PTP_PF_EXTTS: + break; + case PTP_PF_PEROUT: + case PTP_PF_PHYSYNC: + return -1; + } + return 0; +} + +static void otx2_ptp_extts_check(struct work_struct *work) +{ + struct otx2_ptp *ptp = container_of(work, struct otx2_ptp, + extts_work.work); + struct ptp_clock_event event; + u64 tstmp, new_thresh; + + mutex_lock(&ptp->nic->mbox.lock); + tstmp = ptp_tstmp_read(ptp); + mutex_unlock(&ptp->nic->mbox.lock); + + if (tstmp != ptp->last_extts) { + event.type = PTP_CLOCK_EXTTS; + event.index = 0; + event.timestamp = timecounter_cyc2time(&ptp->time_counter, tstmp); + ptp_clock_event(ptp->ptp_clock, &event); + ptp->last_extts = tstmp; + + new_thresh = tstmp % 500000000; + if (ptp->thresh != new_thresh) { + mutex_lock(&ptp->nic->mbox.lock); + ptp_set_thresh(ptp, new_thresh); + mutex_unlock(&ptp->nic->mbox.lock); + ptp->thresh = new_thresh; + } + } + schedule_delayed_work(&ptp->extts_work, msecs_to_jiffies(200)); +} + static int otx2_ptp_enable(struct ptp_clock_info *ptp_info, struct ptp_clock_request *rq, int on) { + struct otx2_ptp *ptp = container_of(ptp_info, struct otx2_ptp, + ptp_info); + int pin = -1; + + if (!ptp->nic) + return -ENODEV; + + switch (rq->type) { + case PTP_CLK_REQ_EXTTS: + pin = ptp_find_pin(ptp->ptp_clock, PTP_PF_EXTTS, + rq->extts.index); + if (pin < 0) + return -EBUSY; + if (on) + schedule_delayed_work(&ptp->extts_work, msecs_to_jiffies(200)); + else + cancel_delayed_work_sync(&ptp->extts_work); + return 0; + default: + break; + } return -EOPNOTSUPP; } @@ -115,6 +223,11 @@ int otx2_ptp_init(struct otx2_nic *pfvf) struct ptp_req *req; int err; + if (is_otx2_lbkvf(pfvf->pdev)) { + pfvf->ptp = NULL; + return 0; + } + mutex_lock(&pfvf->mbox.lock); /* check if PTP block is available */ req = otx2_mbox_alloc_msg_ptp_op(&pfvf->mbox); @@ -149,20 +262,28 @@ int otx2_ptp_init(struct otx2_nic *pfvf) timecounter_init(&ptp_ptr->time_counter, &ptp_ptr->cycle_counter, ktime_to_ns(ktime_get_real())); + snprintf(ptp_ptr->extts_config.name, sizeof(ptp_ptr->extts_config.name), "TSTAMP"); + ptp_ptr->extts_config.index = 0; + ptp_ptr->extts_config.func = PTP_PF_NONE; + ptp_ptr->ptp_info = (struct ptp_clock_info) { .owner = THIS_MODULE, .name = "OcteonTX2 PTP", .max_adj = 1000000000ull, - .n_ext_ts = 0, - .n_pins = 0, + .n_ext_ts = 1, + .n_pins = 1, .pps = 0, + .pin_config = &ptp_ptr->extts_config, .adjfine = otx2_ptp_adjfine, .adjtime = otx2_ptp_adjtime, .gettime64 = otx2_ptp_gettime, .settime64 = otx2_ptp_settime, .enable = otx2_ptp_enable, + .verify = otx2_ptp_verify_pin, }; + INIT_DELAYED_WORK(&ptp_ptr->extts_work, otx2_ptp_extts_check); + ptp_ptr->ptp_clock = ptp_clock_register(&ptp_ptr->ptp_info, pfvf->dev); if (IS_ERR_OR_NULL(ptp_ptr->ptp_clock)) { err = ptp_ptr->ptp_clock ? diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index f42b1d4e0c679e..3f3ec8ffc4ddfc 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -18,6 +18,31 @@ #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx))) +static int otx2_nix_cq_op_status(struct otx2_nic *pfvf, + struct otx2_cq_queue *cq) +{ + u64 incr = (u64)(cq->cq_idx) << 32; + u64 status; + + status = otx2_atomic64_fetch_add(incr, pfvf->cq_op_addr); + + if (unlikely(status & BIT_ULL(CQ_OP_STAT_OP_ERR) || + status & BIT_ULL(CQ_OP_STAT_CQ_ERR))) { + dev_err(pfvf->dev, "CQ stopped due to error"); + return -EINVAL; + } + + cq->cq_tail = status & 0xFFFFF; + cq->cq_head = (status >> 20) & 0xFFFFF; + if (cq->cq_tail < cq->cq_head) + cq->pend_cqe = (cq->cqe_cnt - cq->cq_head) + + cq->cq_tail; + else + cq->pend_cqe = cq->cq_tail - cq->cq_head; + + return 0; +} + static struct nix_cqe_hdr_s *otx2_get_next_cqe(struct otx2_cq_queue *cq) { struct nix_cqe_hdr_s *cqe_hdr; @@ -318,7 +343,14 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, struct nix_cqe_rx_s *cqe; int processed_cqe = 0; - while (likely(processed_cqe < budget)) { + if (cq->pend_cqe >= budget) + goto process_cqe; + + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return 0; + +process_cqe: + while (likely(processed_cqe < budget) && cq->pend_cqe) { cqe = (struct nix_cqe_rx_s *)CQE_ADDR(cq, cq->cq_head); if (cqe->hdr.cqe_type == NIX_XQE_TYPE_INVALID || !cqe->sg.seg_addr) { @@ -334,6 +366,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; cqe->sg.seg_addr = 0x00; processed_cqe++; + cq->pend_cqe--; } /* Free CQEs to HW */ @@ -368,7 +401,14 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, struct nix_cqe_tx_s *cqe; int processed_cqe = 0; - while (likely(processed_cqe < budget)) { + if (cq->pend_cqe >= budget) + goto process_cqe; + + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return 0; + +process_cqe: + while (likely(processed_cqe < budget) && cq->pend_cqe) { cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq); if (unlikely(!cqe)) { if (!processed_cqe) @@ -380,6 +420,7 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; processed_cqe++; + cq->pend_cqe--; } /* Free CQEs to HW */ @@ -936,10 +977,16 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) int processed_cqe = 0; u64 iova, pa; - while ((cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq))) { - if (!cqe->sg.subdc) - continue; + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return; + + while (cq->pend_cqe) { + cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq); processed_cqe++; + cq->pend_cqe--; + + if (!cqe) + continue; if (cqe->sg.segs > 1) { otx2_free_rcv_seg(pfvf, cqe, cq->cq_idx); continue; @@ -965,7 +1012,16 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) sq = &pfvf->qset.sq[cq->cint_idx]; - while ((cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq))) { + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return; + + while (cq->pend_cqe) { + cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq); + processed_cqe++; + cq->pend_cqe--; + + if (!cqe) + continue; sg = &sq->sg[cqe->comp.sqe_id]; skb = (struct sk_buff *)sg->skb; if (skb) { @@ -973,7 +1029,6 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) dev_kfree_skb_any(skb); sg->skb = (u64)NULL; } - processed_cqe++; } /* Free CQEs to HW */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 3ff1ad79c0011d..6a97631ff2269b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -56,6 +56,9 @@ */ #define CQ_QCOUNT_DEFAULT 1 +#define CQ_OP_STAT_OP_ERR 63 +#define CQ_OP_STAT_CQ_ERR 46 + struct queue_stats { u64 bytes; u64 pkts; @@ -122,6 +125,8 @@ struct otx2_cq_queue { u16 pool_ptrs; u32 cqe_cnt; u32 cq_head; + u32 cq_tail; + u32 pend_cqe; void *cqe_base; struct qmem *cqe; struct otx2_pool *rbpool; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 03b4ec630432be..f1fddae11eed22 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -8,9 +8,11 @@ #include <linux/etherdevice.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/net_tstamp.h> #include "otx2_common.h" #include "otx2_reg.h" +#include "otx2_ptp.h" #include "cn10k.h" #define DRV_NAME "rvu_nicvf" @@ -500,6 +502,7 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_set_features = otx2vf_set_features, .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, + .ndo_do_ioctl = otx2_ioctl, }; static int otx2_wq_init(struct otx2_nic *vf) @@ -640,6 +643,9 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_detach_rsrc; + /* Don't check for error. Proceed without ptp */ + otx2_ptp_init(vf); + /* Assign default mac address */ otx2_get_mac_from_af(netdev); diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c index 68b442eb6d6943..06279cd6da6746 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.c @@ -345,8 +345,6 @@ static struct prestera_trap prestera_trap_items_arr[] = { }, }; -static void prestera_devlink_traps_fini(struct prestera_switch *sw); - static int prestera_drop_counter_get(struct devlink *devlink, const struct devlink_trap *trap, u64 *p_drops); @@ -381,8 +379,6 @@ static int prestera_trap_action_set(struct devlink *devlink, enum devlink_trap_action action, struct netlink_ext_ack *extack); -static int prestera_devlink_traps_register(struct prestera_switch *sw); - static const struct devlink_ops prestera_dl_ops = { .info_get = prestera_dl_info_get, .trap_init = prestera_trap_init, @@ -407,38 +403,18 @@ void prestera_devlink_free(struct prestera_switch *sw) devlink_free(dl); } -int prestera_devlink_register(struct prestera_switch *sw) +void prestera_devlink_register(struct prestera_switch *sw) { struct devlink *dl = priv_to_devlink(sw); - int err; - - err = devlink_register(dl); - if (err) { - dev_err(prestera_dev(sw), "devlink_register failed: %d\n", err); - return err; - } - err = prestera_devlink_traps_register(sw); - if (err) { - devlink_unregister(dl); - dev_err(sw->dev->dev, "devlink_traps_register failed: %d\n", - err); - return err; - } - - return 0; + devlink_register(dl); } void prestera_devlink_unregister(struct prestera_switch *sw) { - struct prestera_trap_data *trap_data = sw->trap_data; struct devlink *dl = priv_to_devlink(sw); - prestera_devlink_traps_fini(sw); devlink_unregister(dl); - - kfree(trap_data->trap_items_arr); - kfree(trap_data); } int prestera_devlink_port_register(struct prestera_port *port) @@ -486,7 +462,7 @@ struct devlink_port *prestera_devlink_get_port(struct net_device *dev) return &port->dl_port; } -static int prestera_devlink_traps_register(struct prestera_switch *sw) +int prestera_devlink_traps_register(struct prestera_switch *sw) { const u32 groups_count = ARRAY_SIZE(prestera_trap_groups_arr); const u32 traps_count = ARRAY_SIZE(prestera_trap_items_arr); @@ -625,8 +601,9 @@ static int prestera_drop_counter_get(struct devlink *devlink, cpu_code_type, p_drops); } -static void prestera_devlink_traps_fini(struct prestera_switch *sw) +void prestera_devlink_traps_unregister(struct prestera_switch *sw) { + struct prestera_trap_data *trap_data = sw->trap_data; struct devlink *dl = priv_to_devlink(sw); const struct devlink_trap *trap; int i; @@ -638,4 +615,6 @@ static void prestera_devlink_traps_fini(struct prestera_switch *sw) devlink_trap_groups_unregister(dl, prestera_trap_groups_arr, ARRAY_SIZE(prestera_trap_groups_arr)); + kfree(trap_data->trap_items_arr); + kfree(trap_data); } diff --git a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h index cc34c3db13a2f8..b322295bad3ad3 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_devlink.h +++ b/drivers/net/ethernet/marvell/prestera/prestera_devlink.h @@ -9,7 +9,7 @@ struct prestera_switch *prestera_devlink_alloc(struct prestera_device *dev); void prestera_devlink_free(struct prestera_switch *sw); -int prestera_devlink_register(struct prestera_switch *sw); +void prestera_devlink_register(struct prestera_switch *sw); void prestera_devlink_unregister(struct prestera_switch *sw); int prestera_devlink_port_register(struct prestera_port *port); @@ -22,5 +22,7 @@ struct devlink_port *prestera_devlink_get_port(struct net_device *dev); void prestera_devlink_trap_report(struct prestera_port *port, struct sk_buff *skb, u8 cpu_code); +int prestera_devlink_traps_register(struct prestera_switch *sw); +void prestera_devlink_traps_unregister(struct prestera_switch *sw); #endif /* _PRESTERA_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 44c670807fb3cd..78a7a00bce2221 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -851,7 +851,7 @@ static int prestera_switch_init(struct prestera_switch *sw) if (err) goto err_span_init; - err = prestera_devlink_register(sw); + err = prestera_devlink_traps_register(sw); if (err) goto err_dl_register; @@ -863,12 +863,13 @@ static int prestera_switch_init(struct prestera_switch *sw) if (err) goto err_ports_create; + prestera_devlink_register(sw); return 0; err_ports_create: prestera_lag_fini(sw); err_lag_init: - prestera_devlink_unregister(sw); + prestera_devlink_traps_unregister(sw); err_dl_register: prestera_span_fini(sw); err_span_init: @@ -888,9 +889,10 @@ err_swdev_register: static void prestera_switch_fini(struct prestera_switch *sw) { + prestera_devlink_unregister(sw); prestera_destroy_ports(sw); prestera_lag_fini(sw); - prestera_devlink_unregister(sw); + prestera_devlink_traps_unregister(sw); prestera_span_fini(sw); prestera_acl_fini(sw); prestera_event_handlers_unregister(sw); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index e9fc74e54b22e5..3cb9c1271328a6 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4440,86 +4440,6 @@ static const struct ethtool_ops sky2_ethtool_ops = { static struct dentry *sky2_debug; - -/* - * Read and parse the first part of Vital Product Data - */ -#define VPD_SIZE 128 -#define VPD_MAGIC 0x82 - -static const struct vpd_tag { - char tag[2]; - char *label; -} vpd_tags[] = { - { "PN", "Part Number" }, - { "EC", "Engineering Level" }, - { "MN", "Manufacturer" }, - { "SN", "Serial Number" }, - { "YA", "Asset Tag" }, - { "VL", "First Error Log Message" }, - { "VF", "Second Error Log Message" }, - { "VB", "Boot Agent ROM Configuration" }, - { "VE", "EFI UNDI Configuration" }, -}; - -static void sky2_show_vpd(struct seq_file *seq, struct sky2_hw *hw) -{ - size_t vpd_size; - loff_t offs; - u8 len; - unsigned char *buf; - u16 reg2; - - reg2 = sky2_pci_read16(hw, PCI_DEV_REG2); - vpd_size = 1 << ( ((reg2 & PCI_VPD_ROM_SZ) >> 14) + 8); - - seq_printf(seq, "%s Product Data\n", pci_name(hw->pdev)); - buf = kmalloc(vpd_size, GFP_KERNEL); - if (!buf) { - seq_puts(seq, "no memory!\n"); - return; - } - - if (pci_read_vpd(hw->pdev, 0, vpd_size, buf) < 0) { - seq_puts(seq, "VPD read failed\n"); - goto out; - } - - if (buf[0] != VPD_MAGIC) { - seq_printf(seq, "VPD tag mismatch: %#x\n", buf[0]); - goto out; - } - len = buf[1]; - if (len == 0 || len > vpd_size - 4) { - seq_printf(seq, "Invalid id length: %d\n", len); - goto out; - } - - seq_printf(seq, "%.*s\n", len, buf + 3); - offs = len + 3; - - while (offs < vpd_size - 4) { - int i; - - if (!memcmp("RW", buf + offs, 2)) /* end marker */ - break; - len = buf[offs + 2]; - if (offs + len + 3 >= vpd_size) - break; - - for (i = 0; i < ARRAY_SIZE(vpd_tags); i++) { - if (!memcmp(vpd_tags[i].tag, buf + offs, 2)) { - seq_printf(seq, " %s: %.*s\n", - vpd_tags[i].label, len, buf + offs + 3); - break; - } - } - offs += len + 3; - } -out: - kfree(buf); -} - static int sky2_debug_show(struct seq_file *seq, void *v) { struct net_device *dev = seq->private; @@ -4529,9 +4449,7 @@ static int sky2_debug_show(struct seq_file *seq, void *v) unsigned idx, last; int sop; - sky2_show_vpd(seq, hw); - - seq_printf(seq, "\nIRQ src=%x mask=%x control=%x\n", + seq_printf(seq, "IRQ src=%x mask=%x control=%x\n", sky2_read32(hw, B0_ISRC), sky2_read32(hw, B0_IMSK), sky2_read32(hw, B0_Y2_SP_ICR)); diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index f7053a74e6a80f..4d4f9cf9facb87 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -314,7 +314,8 @@ static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size) buf += PAGE_SIZE; } } else { - err = copy_to_user((void __user *)buf, init_ents, entries * cqe_size) ? + err = copy_to_user((void __user *)buf, init_ents, + array_size(entries, cqe_size)) ? -EFAULT : 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 7f6d3b82c29b29..557d7daac2d36d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -669,6 +669,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud struct bpf_prog *xdp_prog; int cq_ring = cq->ring; bool doorbell_pending; + bool xdp_redir_flush; struct mlx4_cqe *cqe; struct xdp_buff xdp; int polled = 0; @@ -682,6 +683,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud xdp_prog = rcu_dereference_bh(ring->xdp_prog); xdp_init_buff(&xdp, priv->frag_info[0].frag_stride, &ring->xdp_rxq); doorbell_pending = false; + xdp_redir_flush = false; /* We assume a 1:1 mapping between CQEs and Rx descriptors, so Rx * descriptor offset can be deduced from the CQE index instead of @@ -790,6 +792,14 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud switch (act) { case XDP_PASS: break; + case XDP_REDIRECT: + if (xdp_do_redirect(dev, &xdp, xdp_prog) >= 0) { + xdp_redir_flush = true; + frags[0].page = NULL; + goto next; + } + trace_xdp_exception(dev, xdp_prog, act); + goto xdp_drop_no_cnt; case XDP_TX: if (likely(!mlx4_en_xmit_frame(ring, frags, priv, length, cq_ring, @@ -897,6 +907,9 @@ next: break; } + if (xdp_redir_flush) + xdp_do_flush(); + if (likely(polled)) { if (doorbell_pending) { priv->tx_cq[TX_XDP][cq_ring]->xdp_busy = true; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5a6b0fcaf7f8a5..9541f3a920c8c2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4015,9 +4015,6 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) mutex_init(&dev->persist->interface_state_mutex); mutex_init(&dev->persist->pci_status_mutex); - ret = devlink_register(devlink); - if (ret) - goto err_persist_free; ret = devlink_params_register(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); if (ret) @@ -4027,17 +4024,15 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_params_unregister; - devlink_params_publish(devlink); - devlink_reload_enable(devlink); pci_save_state(pdev); + devlink_register(devlink); + devlink_reload_enable(devlink); return 0; err_params_unregister: devlink_params_unregister(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); err_devlink_unregister: - devlink_unregister(devlink); -err_persist_free: kfree(dev->persist); err_devlink_free: devlink_free(devlink); @@ -4141,6 +4136,7 @@ static void mlx4_remove_one(struct pci_dev *pdev) int active_vfs = 0; devlink_reload_disable(devlink); + devlink_unregister(devlink); if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; @@ -4176,7 +4172,6 @@ static void mlx4_remove_one(struct pci_dev *pdev) mlx4_pci_disable_device(dev); devlink_params_unregister(devlink, mlx4_devlink_params, ARRAY_SIZE(mlx4_devlink_params)); - devlink_unregister(devlink); kfree(dev->persist); devlink_free(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index dcf9f27ba2efdf..d7576b6fa43b77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -625,7 +625,6 @@ static int mlx5_devlink_eth_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, value); - devlink_param_publish(devlink, &enable_eth_param); return 0; } @@ -636,7 +635,6 @@ static void mlx5_devlink_eth_param_unregister(struct devlink *devlink) if (!mlx5_eth_supported(dev)) return; - devlink_param_unpublish(devlink, &enable_eth_param); devlink_param_unregister(devlink, &enable_eth_param); } @@ -672,7 +670,6 @@ static int mlx5_devlink_rdma_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, value); - devlink_param_publish(devlink, &enable_rdma_param); return 0; } @@ -681,7 +678,6 @@ static void mlx5_devlink_rdma_param_unregister(struct devlink *devlink) if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND)) return; - devlink_param_unpublish(devlink, &enable_rdma_param); devlink_param_unregister(devlink, &enable_rdma_param); } @@ -706,7 +702,6 @@ static int mlx5_devlink_vnet_param_register(struct devlink *devlink) devlink_param_driverinit_value_set(devlink, DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, value); - devlink_param_publish(devlink, &enable_rdma_param); return 0; } @@ -717,7 +712,6 @@ static void mlx5_devlink_vnet_param_unregister(struct devlink *devlink) if (!mlx5_vnet_supported(dev)) return; - devlink_param_unpublish(devlink, &enable_vnet_param); devlink_param_unregister(devlink, &enable_vnet_param); } @@ -799,16 +793,12 @@ int mlx5_devlink_register(struct devlink *devlink) { int err; - err = devlink_register(devlink); - if (err) - return err; - err = devlink_params_register(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); if (err) - goto params_reg_err; + return err; + mlx5_devlink_set_params_init_values(devlink); - devlink_params_publish(devlink); err = mlx5_devlink_auxdev_params_register(devlink); if (err) @@ -825,8 +815,6 @@ traps_reg_err: auxdev_reg_err: devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); -params_reg_err: - devlink_unregister(devlink); return err; } @@ -834,8 +822,6 @@ void mlx5_devlink_unregister(struct devlink *devlink) { mlx5_devlink_traps_unregister(devlink); mlx5_devlink_auxdev_params_unregister(devlink); - devlink_params_unpublish(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, ARRAY_SIZE(mlx5_devlink_params)); - devlink_unregister(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7b8c8187543a9d..f5d147c3141aa6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -220,8 +220,6 @@ struct mlx5e_umr_wqe { struct mlx5_mtt inline_mtts[0]; }; -extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; - enum mlx5e_priv_flag { MLX5E_PFLAG_RX_CQE_BASED_MODER, MLX5E_PFLAG_TX_CQE_BASED_MODER, @@ -916,6 +914,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) void mlx5e_init_l2_addr(struct mlx5e_priv *priv); int mlx5e_self_test_num(struct mlx5e_priv *priv); +int mlx5e_self_test_fill_strings(struct mlx5e_priv *priv, u8 *data); void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, u64 *buf); void mlx5e_set_rx_mode_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index de03684528bbf9..398c6761eeb3bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -3,6 +3,7 @@ #include <net/dst_metadata.h> #include <linux/netdevice.h> +#include <linux/if_macvlan.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> @@ -409,6 +410,13 @@ static void mlx5e_rep_indr_block_unbind(void *cb_priv) static LIST_HEAD(mlx5e_block_cb_list); +static bool mlx5e_rep_macvlan_mode_supported(const struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->mode == MACVLAN_MODE_PASSTHRU; +} + static int mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct mlx5e_rep_priv *rpriv, @@ -422,8 +430,14 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch, struct flow_block_cb *block_cb; if (!mlx5e_tc_tun_device_to_offload(priv, netdev) && - !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) - return -EOPNOTSUPP; + !(is_vlan_dev(netdev) && vlan_dev_real_dev(netdev) == rpriv->netdev)) { + if (!(netif_is_macvlan(netdev) && macvlan_dev_real_dev(netdev) == rpriv->netdev)) + return -EOPNOTSUPP; + if (!mlx5e_rep_macvlan_mode_supported(netdev)) { + netdev_warn(netdev, "Offloading ingress filter is supported only with macvlan passthru mode"); + return -EOPNOTSUPP; + } + } if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; @@ -647,9 +661,7 @@ static void mlx5e_restore_skb_sample(struct mlx5e_priv *priv, struct sk_buff *sk "Failed to restore tunnel info for sampled packet\n"); return; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_skb(skb, mapped_obj); -#endif /* CONFIG_MLX5_TC_SAMPLE */ mlx5_rep_tc_post_napi_receive(tc_priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index 625cd49ef96c59..b8b481b335cff3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -391,7 +391,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, return 0; } -static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) +static int mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) { int err; @@ -399,6 +399,7 @@ static void mlx5e_rss_apply(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_r if (err) mlx5e_rss_warn(rss->mdev, "Failed to redirect RQT %#x to channels: err = %d\n", mlx5e_rqt_get_rqtn(&rss->rqt), err); + return err; } void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns) @@ -490,6 +491,14 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, { bool changed_indir = false; bool changed_hash = false; + struct mlx5e_rss *old_rss; + int err = 0; + + old_rss = mlx5e_rss_alloc(); + if (!old_rss) + return -ENOMEM; + + *old_rss = *rss; if (hfunc && *hfunc != rss->hash.hfunc) { switch (*hfunc) { @@ -497,7 +506,8 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, case ETH_RSS_HASH_TOP: break; default: - return -EINVAL; + err = -EINVAL; + goto out; } changed_hash = true; changed_indir = true; @@ -520,13 +530,20 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, rss->indir.table[i] = indir[i]; } - if (changed_indir && rss->enabled) - mlx5e_rss_apply(rss, rqns, num_rqns); + if (changed_indir && rss->enabled) { + err = mlx5e_rss_apply(rss, rqns, num_rqns); + if (err) { + *rss = *old_rss; + goto out; + } + } if (changed_hash) mlx5e_rss_update_tirs(rss); - return 0; +out: + mlx5e_rss_free(old_rss); + return err; } struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h index db0146df9b3038..9ef8a49d780148 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.h @@ -19,6 +19,8 @@ struct mlx5e_sample_attr { struct mlx5e_sample_flow *sample_flow; }; +#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) + void mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj); struct mlx5_flow_handle * @@ -38,4 +40,29 @@ mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act); void mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample); +#else /* CONFIG_MLX5_TC_SAMPLE */ + +static inline struct mlx5_flow_handle * +mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, + struct mlx5_flow_spec *spec, + struct mlx5_flow_attr *attr, + u32 tunnel_id) +{ return ERR_PTR(-EOPNOTSUPP); } + +static inline void +mlx5e_tc_sample_unoffload(struct mlx5e_tc_psample *tc_psample, + struct mlx5_flow_handle *rule, + struct mlx5_flow_attr *attr) {} + +static inline struct mlx5e_tc_psample * +mlx5e_tc_sample_init(struct mlx5_eswitch *esw, struct mlx5e_post_act *post_act) +{ return ERR_PTR(-EOPNOTSUPP); } + +static inline void +mlx5e_tc_sample_cleanup(struct mlx5e_tc_psample *tc_psample) {} + +static inline void +mlx5e_tc_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj) {} + +#endif /* CONFIG_MLX5_TC_SAMPLE */ #endif /* __MLX5_EN_TC_SAMPLE_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 6c949abcd2e140..225748a9e52a71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2127,12 +2127,20 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, ct_priv->post_act = post_act; mutex_init(&ct_priv->control_lock); - rhashtable_init(&ct_priv->zone_ht, &zone_params); - rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params); - rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params); + if (rhashtable_init(&ct_priv->zone_ht, &zone_params)) + goto err_ct_zone_ht; + if (rhashtable_init(&ct_priv->ct_tuples_ht, &tuples_ht_params)) + goto err_ct_tuples_ht; + if (rhashtable_init(&ct_priv->ct_tuples_nat_ht, &tuples_nat_ht_params)) + goto err_ct_tuples_nat_ht; return ct_priv; +err_ct_tuples_nat_ht: + rhashtable_destroy(&ct_priv->ct_tuples_ht); +err_ct_tuples_ht: + rhashtable_destroy(&ct_priv->zone_ht); +err_ct_zone_ht: err_ct_nat_tbl: mlx5_chains_destroy_global_table(chains, ct_priv->ct); err_ct_tbl: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 306fb5d6a36d35..485f208691eaa4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -267,9 +267,7 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data) break; case ETH_SS_TEST: - for (i = 0; i < mlx5e_self_test_num(priv); i++) - strcpy(data + i * ETH_GSTRING_LEN, - mlx5e_self_tests[i]); + mlx5e_self_test_fill_strings(priv, data); break; case ETH_SS_STATS: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index ce8ab1f0187693..8c9163d2c64684 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -35,30 +35,7 @@ #include <net/udp.h> #include "en.h" #include "en/port.h" - -enum { - MLX5E_ST_LINK_STATE, - MLX5E_ST_LINK_SPEED, - MLX5E_ST_HEALTH_INFO, -#ifdef CONFIG_INET - MLX5E_ST_LOOPBACK, -#endif - MLX5E_ST_NUM, -}; - -const char mlx5e_self_tests[MLX5E_ST_NUM][ETH_GSTRING_LEN] = { - "Link Test", - "Speed Test", - "Health Test", -#ifdef CONFIG_INET - "Loopback Test", -#endif -}; - -int mlx5e_self_test_num(struct mlx5e_priv *priv) -{ - return ARRAY_SIZE(mlx5e_self_tests); -} +#include "eswitch.h" static int mlx5e_test_health_info(struct mlx5e_priv *priv) { @@ -265,6 +242,14 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, mlx5e_refresh_tirs(priv, false, false); } +static int mlx5e_cond_loopback(struct mlx5e_priv *priv) +{ + if (is_mdev_switchdev_mode(priv->mdev)) + return -EOPNOTSUPP; + + return 0; +} + #define MLX5E_LB_VERIFY_TIMEOUT (msecs_to_jiffies(200)) static int mlx5e_test_loopback(struct mlx5e_priv *priv) { @@ -313,37 +298,47 @@ out: } #endif -static int (*mlx5e_st_func[MLX5E_ST_NUM])(struct mlx5e_priv *) = { - mlx5e_test_link_state, - mlx5e_test_link_speed, - mlx5e_test_health_info, +typedef int (*mlx5e_st_func)(struct mlx5e_priv *); + +struct mlx5e_st { + char name[ETH_GSTRING_LEN]; + mlx5e_st_func st_func; + mlx5e_st_func cond_func; +}; + +static struct mlx5e_st mlx5e_sts[] = { + { "Link Test", mlx5e_test_link_state }, + { "Speed Test", mlx5e_test_link_speed }, + { "Health Test", mlx5e_test_health_info }, #ifdef CONFIG_INET - mlx5e_test_loopback, + { "Loopback Test", mlx5e_test_loopback, mlx5e_cond_loopback }, #endif }; +#define MLX5E_ST_NUM ARRAY_SIZE(mlx5e_sts) + void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { struct mlx5e_priv *priv = netdev_priv(ndev); - int i; - - memset(buf, 0, sizeof(u64) * MLX5E_ST_NUM); + int i, count = 0; mutex_lock(&priv->state_lock); netdev_info(ndev, "Self test begin..\n"); for (i = 0; i < MLX5E_ST_NUM; i++) { - netdev_info(ndev, "\t[%d] %s start..\n", - i, mlx5e_self_tests[i]); - buf[i] = mlx5e_st_func[i](priv); - netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", - i, mlx5e_self_tests[i], buf[i]); + struct mlx5e_st st = mlx5e_sts[i]; + + if (st.cond_func && st.cond_func(priv)) + continue; + netdev_info(ndev, "\t[%d] %s start..\n", i, st.name); + buf[count] = st.st_func(priv); + netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", i, st.name, buf[count]); } mutex_unlock(&priv->state_lock); - for (i = 0; i < MLX5E_ST_NUM; i++) { + for (i = 0; i < count; i++) { if (buf[i]) { etest->flags |= ETH_TEST_FL_FAILED; break; @@ -352,3 +347,24 @@ void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, netdev_info(ndev, "Self test out: status flags(0x%x)\n", etest->flags); } + +int mlx5e_self_test_fill_strings(struct mlx5e_priv *priv, u8 *data) +{ + int i, count = 0; + + for (i = 0; i < MLX5E_ST_NUM; i++) { + struct mlx5e_st st = mlx5e_sts[i]; + + if (st.cond_func && st.cond_func(priv)) + continue; + if (data) + strcpy(data + count * ETH_GSTRING_LEN, st.name); + count++; + } + return count; +} + +int mlx5e_self_test_num(struct mlx5e_priv *priv) +{ + return mlx5e_self_test_fill_strings(priv, NULL); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index ba81647920167d..0e03cefc5eeb2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -39,6 +39,7 @@ #include <linux/rhashtable.h> #include <linux/refcount.h> #include <linux/completion.h> +#include <linux/if_macvlan.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_csum.h> #include <net/psample.h> @@ -246,7 +247,6 @@ get_ct_priv(struct mlx5e_priv *priv) return priv->fs.tc.ct; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) static struct mlx5e_tc_psample * get_sample_priv(struct mlx5e_priv *priv) { @@ -263,7 +263,6 @@ get_sample_priv(struct mlx5e_priv *priv) return NULL; } -#endif struct mlx5_flow_handle * mlx5_tc_rule_insert(struct mlx5e_priv *priv, @@ -1146,11 +1145,9 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, rule = mlx5_tc_ct_flow_offload(get_ct_priv(flow->priv), flow, spec, attr, mod_hdr_acts); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) } else if (flow_flag_test(flow, SAMPLE)) { rule = mlx5e_tc_sample_offload(get_sample_priv(flow->priv), spec, attr, mlx5e_tc_get_flow_tun_id(flow)); -#endif } else { rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr); } @@ -1186,12 +1183,10 @@ void mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, return; } -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) if (flow_flag_test(flow, SAMPLE)) { mlx5e_tc_sample_unoffload(get_sample_priv(flow->priv), flow->rule[0], attr); return; } -#endif if (attr->esw_attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); @@ -1688,8 +1683,8 @@ enc_opts_is_dont_care_or_full_match(struct mlx5e_priv *priv, if (opt->opt_class != htons(U16_MAX) || opt->type != U8_MAX) { - NL_SET_ERR_MSG(extack, - "Partial match of tunnel options in chain > 0 isn't supported"); + NL_SET_ERR_MSG_MOD(extack, + "Partial match of tunnel options in chain > 0 isn't supported"); netdev_warn(priv->netdev, "Partial match of tunnel options in chain > 0 isn't supported"); return -EOPNOTSUPP; @@ -1905,8 +1900,8 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv, if ((needs_mapping || sets_mapping) && !mlx5_eswitch_reg_c1_loopback_enabled(esw)) { - NL_SET_ERR_MSG(extack, - "Chains on tunnel devices isn't supported without register loopback support"); + NL_SET_ERR_MSG_MOD(extack, + "Chains on tunnel devices isn't supported without register loopback support"); netdev_warn(priv->netdev, "Chains on tunnel devices isn't supported without register loopback support"); return -EOPNOTSUPP; @@ -2910,8 +2905,7 @@ out_err: } static int -parse_pedit_to_reformat(struct mlx5e_priv *priv, - const struct flow_action_entry *act, +parse_pedit_to_reformat(const struct flow_action_entry *act, struct mlx5e_tc_flow_parse_attr *parse_attr, struct netlink_ext_ack *extack) { @@ -2943,7 +2937,7 @@ static int parse_tc_pedit_action(struct mlx5e_priv *priv, struct netlink_ext_ack *extack) { if (flow && flow_flag_test(flow, L3_TO_L2_DECAP)) - return parse_pedit_to_reformat(priv, act, parse_attr, extack); + return parse_pedit_to_reformat(act, parse_attr, extack); return parse_pedit_to_modify_hdr(priv, act, namespace, parse_attr, hdrs, extack); @@ -3025,10 +3019,10 @@ struct ipv6_hoplimit_word { __u8 hop_limit; }; -static int is_action_keys_supported(const struct flow_action_entry *act, - bool ct_flow, bool *modify_ip_header, - bool *modify_tuple, - struct netlink_ext_ack *extack) +static bool +is_action_keys_supported(const struct flow_action_entry *act, bool ct_flow, + bool *modify_ip_header, bool *modify_tuple, + struct netlink_ext_ack *extack) { u32 mask, offset; u8 htype; @@ -3056,7 +3050,7 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv4 address with action ct"); - return -EOPNOTSUPP; + return false; } } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) { struct ipv6_hoplimit_word *hoplimit_word = @@ -3074,7 +3068,7 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow && *modify_tuple) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of ipv6 address with action ct"); - return -EOPNOTSUPP; + return false; } } else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_TCP || htype == FLOW_ACT_MANGLE_HDR_TYPE_UDP) { @@ -3082,11 +3076,11 @@ static int is_action_keys_supported(const struct flow_action_entry *act, if (ct_flow) { NL_SET_ERR_MSG_MOD(extack, "can't offload re-write of transport header ports with action ct"); - return -EOPNOTSUPP; + return false; } } - return 0; + return true; } static bool modify_tuple_supported(bool modify_tuple, bool ct_clear, @@ -3133,7 +3127,7 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, void *headers_v; u16 ethertype; u8 ip_proto; - int i, err; + int i; headers_c = get_match_headers_criteria(actions, spec); headers_v = get_match_headers_value(actions, spec); @@ -3151,11 +3145,10 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, act->id != FLOW_ACTION_ADD) continue; - err = is_action_keys_supported(act, ct_flow, - &modify_ip_header, - &modify_tuple, extack); - if (err) - return err; + if (!is_action_keys_supported(act, ct_flow, + &modify_ip_header, + &modify_tuple, extack)) + return false; } if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack, @@ -3190,6 +3183,12 @@ static bool actions_match_supported(struct mlx5e_priv *priv, ct_flow = flow_flag_test(flow, CT) && !ct_clear; actions = flow->attr->action; + if (!(actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule must have at least one forward/drop action"); + return false; + } + if (mlx5e_is_eswitch_flow(flow)) { if (flow->attr->esw_attr->split_count && ct_flow && !MLX5_CAP_GEN(flow->attr->esw_attr->in_mdev, reg_c_preserve)) { @@ -3451,7 +3450,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (err) return err; - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: @@ -3484,17 +3484,11 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, attr->action = action; - if (attr->dest_chain) { - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { - NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); - return -EOPNOTSUPP; - } - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + if (attr->dest_chain && parse_attr->mirred_ifindex[0]) { + NL_SET_ERR_MSG(extack, "Mirroring goto chain rules isn't supported"); + return -EOPNOTSUPP; } - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; @@ -3914,6 +3908,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return err; } + if (netif_is_macvlan(out_dev)) + out_dev = macvlan_dev_real_dev(out_dev); + err = verify_uplink_forwarding(priv, flow, out_dev, extack); if (err) return err; @@ -3998,7 +3995,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (err) return err; - action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = act->chain_index; break; case FLOW_ACTION_CT: @@ -4068,30 +4066,17 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; - if (attr->dest_chain) { - if (decap) { - /* It can be supported if we'll create a mapping for - * the tunnel device only (without tunnel), and set - * this tunnel id with this decap flow. - * - * On restore (miss), we'll just set this saved tunnel - * device. - */ - - NL_SET_ERR_MSG(extack, - "Decap with goto isn't supported"); - netdev_warn(priv->netdev, - "Decap with goto isn't supported"); - return -EOPNOTSUPP; - } - - attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - } + if (attr->dest_chain && decap) { + /* It can be supported if we'll create a mapping for + * the tunnel device only (without tunnel), and set + * this tunnel id with this decap flow. + * + * On restore (miss), we'll just set this saved tunnel + * device. + */ - if (!(attr->action & - (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { - NL_SET_ERR_MSG_MOD(extack, - "Rule must have at least one forward/drop action"); + NL_SET_ERR_MSG(extack, "Decap with goto isn't supported"); + netdev_warn(priv->netdev, "Decap with goto isn't supported"); return -EOPNOTSUPP; } @@ -5006,9 +4991,7 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht) MLX5_FLOW_NAMESPACE_FDB, uplink_priv->post_act); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act); -#endif mapping_id = mlx5_query_nic_system_image_guid(esw->dev); @@ -5052,9 +5035,7 @@ err_ht_init: err_enc_opts_mapping: mapping_destroy(uplink_priv->tunnel_mapping); err_tun_mapping: -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); -#endif mlx5_tc_ct_clean(uplink_priv->ct_priv); netdev_warn(priv->netdev, "Failed to initialize tc (eswitch), err: %d", err); @@ -5074,9 +5055,7 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) mapping_destroy(uplink_priv->tunnel_enc_opts_mapping); mapping_destroy(uplink_priv->tunnel_mapping); -#if IS_ENABLED(CONFIG_MLX5_TC_SAMPLE) mlx5e_tc_sample_cleanup(uplink_priv->tc_psample); -#endif mlx5_tc_ct_clean(uplink_priv->ct_priv); mlx5e_tc_post_act_destroy(uplink_priv->post_act); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 79482824c64ff2..92b08fa07efae2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1537,6 +1537,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id) dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err); pci_save_state(pdev); + devlink_register(devlink); if (!mlx5_core_is_mp_slave(dev)) devlink_reload_enable(devlink); return 0; @@ -1559,6 +1560,7 @@ static void remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(dev); devlink_reload_disable(devlink); + devlink_unregister(devlink); mlx5_crdump_disable(dev); mlx5_drain_health_wq(dev); mlx5_uninit_one(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 052f48068dc16f..3cf272fa21646a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -46,6 +46,7 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia mlx5_core_warn(mdev, "mlx5_init_one err=%d\n", err); goto init_one_err; } + devlink_register(devlink); devlink_reload_enable(devlink); return 0; @@ -65,6 +66,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev) devlink = priv_to_devlink(sf_dev->mdev); devlink_reload_disable(devlink); + devlink_unregister(devlink); mlx5_uninit_one(sf_dev->mdev); iounmap(sf_dev->mdev->iseg); mlx5_mdev_uninit(sf_dev->mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index b2481c99da79a6..33e6299026f7f9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -1791,7 +1791,7 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, else return -EINVAL; - misc->source_eswitch_owner_vhca_id = 0; + misc->source_eswitch_owner_vhca_id = 0; } else { caps = &dmn->info.caps; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index f080fab3de2b54..9e831e8b607a46 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -90,7 +90,6 @@ struct mlxsw_core { struct devlink_health_reporter *fw_fatal; } health; struct mlxsw_env *env; - bool is_initialized; /* Denotes if core was already initialized. */ unsigned long driver_priv[]; /* driver_priv has to be always the last item */ }; @@ -1975,12 +1974,6 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_emad_init; if (!reload) { - err = devlink_register(devlink); - if (err) - goto err_devlink_register; - } - - if (!reload) { err = mlxsw_core_params_register(mlxsw_core); if (err) goto err_register_params; @@ -1995,12 +1988,6 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_health_init; - if (mlxsw_driver->init) { - err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); - if (err) - goto err_driver_init; - } - err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon); if (err) goto err_hwmon_init; @@ -2014,31 +2001,32 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_env_init; - mlxsw_core->is_initialized = true; - devlink_params_publish(devlink); + if (mlxsw_driver->init) { + err = mlxsw_driver->init(mlxsw_core, mlxsw_bus_info, extack); + if (err) + goto err_driver_init; + } - if (!reload) + if (!reload) { + devlink_register(devlink); devlink_reload_enable(devlink); + } return 0; +err_driver_init: + mlxsw_env_fini(mlxsw_core->env); err_env_init: mlxsw_thermal_fini(mlxsw_core->thermal); err_thermal_init: mlxsw_hwmon_fini(mlxsw_core->hwmon); err_hwmon_init: - if (mlxsw_core->driver->fini) - mlxsw_core->driver->fini(mlxsw_core); -err_driver_init: mlxsw_core_health_fini(mlxsw_core); err_health_init: err_fw_rev_validate: if (!reload) mlxsw_core_params_unregister(mlxsw_core); err_register_params: - if (!reload) - devlink_unregister(devlink); -err_devlink_register: mlxsw_emad_fini(mlxsw_core); err_emad_init: kfree(mlxsw_core->lag.mapping); @@ -2087,8 +2075,10 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) + if (!reload) { devlink_reload_disable(devlink); + devlink_unregister(devlink); + } if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the @@ -2099,18 +2089,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, return; } - devlink_params_unpublish(devlink); - mlxsw_core->is_initialized = false; + if (mlxsw_core->driver->fini) + mlxsw_core->driver->fini(mlxsw_core); mlxsw_env_fini(mlxsw_core->env); mlxsw_thermal_fini(mlxsw_core->thermal); mlxsw_hwmon_fini(mlxsw_core->hwmon); - if (mlxsw_core->driver->fini) - mlxsw_core->driver->fini(mlxsw_core); mlxsw_core_health_fini(mlxsw_core); if (!reload) mlxsw_core_params_unregister(mlxsw_core); - if (!reload) - devlink_unregister(devlink); mlxsw_emad_fini(mlxsw_core); kfree(mlxsw_core->lag.mapping); mlxsw_ports_fini(mlxsw_core, reload); @@ -2124,7 +2110,6 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, reload_fail_deinit: mlxsw_core_params_unregister(mlxsw_core); - devlink_unregister(devlink); devlink_resources_unregister(devlink, NULL); devlink_free(devlink); } @@ -2939,49 +2924,6 @@ struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core) return mlxsw_core->env; } -bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core) -{ - return mlxsw_core->is_initialized; -} - -int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module) -{ - enum mlxsw_reg_pmtm_module_type module_type; - char pmtm_pl[MLXSW_REG_PMTM_LEN]; - int err; - - mlxsw_reg_pmtm_pack(pmtm_pl, module); - err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtm), pmtm_pl); - if (err) - return err; - mlxsw_reg_pmtm_unpack(pmtm_pl, &module_type); - - /* Here we need to get the module width according to the module type. */ - - switch (module_type) { - case MLXSW_REG_PMTM_MODULE_TYPE_C2C8X: - case MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD: - case MLXSW_REG_PMTM_MODULE_TYPE_OSFP: - return 8; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C4X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_4X: - case MLXSW_REG_PMTM_MODULE_TYPE_QSFP: - return 4; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C2X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_2X: - case MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD: - case MLXSW_REG_PMTM_MODULE_TYPE_DSFP: - return 2; - case MLXSW_REG_PMTM_MODULE_TYPE_C2C1X: - case MLXSW_REG_PMTM_MODULE_TYPE_BP_1X: - case MLXSW_REG_PMTM_MODULE_TYPE_SFP: - return 1; - default: - return -EINVAL; - } -} -EXPORT_SYMBOL(mlxsw_core_module_max_width); - static void mlxsw_core_buf_dump_dbg(struct mlxsw_core *mlxsw_core, const char *buf, size_t size) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 80712dc803d0f5..12023a550007be 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -249,8 +249,6 @@ mlxsw_core_port_devlink_port_get(struct mlxsw_core *mlxsw_core, u8 local_port); bool mlxsw_core_port_is_xm(const struct mlxsw_core *mlxsw_core, u8 local_port); struct mlxsw_env *mlxsw_core_env(const struct mlxsw_core *mlxsw_core); -bool mlxsw_core_is_initialized(const struct mlxsw_core *mlxsw_core); -int mlxsw_core_module_max_width(struct mlxsw_core *mlxsw_core, u8 module); int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay); bool mlxsw_core_schedule_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c index 3713c45cfa1ed5..9e367174743d9c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -5,6 +5,7 @@ #include <linux/err.h> #include <linux/ethtool.h> #include <linux/sfp.h> +#include <linux/mutex.h> #include "core.h" #include "core_env.h" @@ -14,12 +15,14 @@ struct mlxsw_env_module_info { u64 module_overheat_counter; bool is_overheat; + int num_ports_mapped; + int num_ports_up; }; struct mlxsw_env { struct mlxsw_core *core; u8 module_count; - spinlock_t module_info_lock; /* Protects 'module_info'. */ + struct mutex module_info_lock; /* Protects 'module_info'. */ struct mlxsw_env_module_info module_info[]; }; @@ -389,6 +392,59 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, } EXPORT_SYMBOL(mlxsw_env_get_module_eeprom_by_page); +static int mlxsw_env_module_reset(struct mlxsw_core *mlxsw_core, u8 module) +{ + char pmaos_pl[MLXSW_REG_PMAOS_LEN]; + + mlxsw_reg_pmaos_pack(pmaos_pl, module); + mlxsw_reg_pmaos_rst_set(pmaos_pl, true); + + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl); +} + +int mlxsw_env_reset_module(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, u8 module, u32 *flags) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + u32 req = *flags; + int err; + + if (!(req & ETH_RESET_PHY) && + !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) + return 0; + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + mutex_lock(&mlxsw_env->module_info_lock); + + if (mlxsw_env->module_info[module].num_ports_up) { + netdev_err(netdev, "Cannot reset module when ports using it are administratively up\n"); + err = -EINVAL; + goto out; + } + + if (mlxsw_env->module_info[module].num_ports_mapped > 1 && + !(req & (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT))) { + netdev_err(netdev, "Cannot reset module without \"phy-shared\" flag when shared by multiple ports\n"); + err = -EINVAL; + goto out; + } + + err = mlxsw_env_module_reset(mlxsw_core, module); + if (err) { + netdev_err(netdev, "Failed to reset module\n"); + goto out; + } + + *flags &= ~(ETH_RESET_PHY | (ETH_RESET_PHY << ETH_RESET_SHARED_SHIFT)); + +out: + mutex_unlock(&mlxsw_env->module_info_lock); + return err; +} +EXPORT_SYMBOL(mlxsw_env_reset_module); + static int mlxsw_env_module_has_temp_sensor(struct mlxsw_core *mlxsw_core, u8 module, bool *p_has_temp_sensor) @@ -482,22 +538,32 @@ static int mlxsw_env_module_temp_event_enable(struct mlxsw_core *mlxsw_core, return 0; } -static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, - char *mtwe_pl, void *priv) +struct mlxsw_env_module_temp_warn_event { + struct mlxsw_env *mlxsw_env; + char mtwe_pl[MLXSW_REG_MTWE_LEN]; + struct work_struct work; +}; + +static void mlxsw_env_mtwe_event_work(struct work_struct *work) { - struct mlxsw_env *mlxsw_env = priv; + struct mlxsw_env_module_temp_warn_event *event; + struct mlxsw_env *mlxsw_env; int i, sensor_warning; bool is_overheat; + event = container_of(work, struct mlxsw_env_module_temp_warn_event, + work); + mlxsw_env = event->mlxsw_env; + for (i = 0; i < mlxsw_env->module_count; i++) { /* 64-127 of sensor_index are mapped to the port modules * sequentially (module 0 is mapped to sensor_index 64, * module 1 to sensor_index 65 and so on) */ sensor_warning = - mlxsw_reg_mtwe_sensor_warning_get(mtwe_pl, + mlxsw_reg_mtwe_sensor_warning_get(event->mtwe_pl, i + MLXSW_REG_MTMP_MODULE_INDEX_MIN); - spin_lock(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); is_overheat = mlxsw_env->module_info[i].is_overheat; @@ -507,13 +573,13 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, * warning OR current state in "no warning" and MTWE * does not report warning. */ - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); continue; } else if (is_overheat && !sensor_warning) { /* MTWE reports "no warning", turn is_overheat off. */ mlxsw_env->module_info[i].is_overheat = false; - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); } else { /* Current state is "no warning" and MTWE reports * "warning", increase the counter and turn is_overheat @@ -521,13 +587,32 @@ static void mlxsw_env_mtwe_event_func(const struct mlxsw_reg_info *reg, */ mlxsw_env->module_info[i].is_overheat = true; mlxsw_env->module_info[i].module_overheat_counter++; - spin_unlock(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); } } + + kfree(event); +} + +static void +mlxsw_env_mtwe_listener_func(const struct mlxsw_reg_info *reg, char *mtwe_pl, + void *priv) +{ + struct mlxsw_env_module_temp_warn_event *event; + struct mlxsw_env *mlxsw_env = priv; + + event = kmalloc(sizeof(*event), GFP_ATOMIC); + if (!event) + return; + + event->mlxsw_env = mlxsw_env; + memcpy(event->mtwe_pl, mtwe_pl, MLXSW_REG_MTWE_LEN); + INIT_WORK(&event->work, mlxsw_env_mtwe_event_work); + mlxsw_core_schedule_work(&event->work); } static const struct mlxsw_listener mlxsw_env_temp_warn_listener = - MLXSW_EVENTL(mlxsw_env_mtwe_event_func, MTWE, MTWE); + MLXSW_EVENTL(mlxsw_env_mtwe_listener_func, MTWE, MTWE); static int mlxsw_env_temp_warn_event_register(struct mlxsw_core *mlxsw_core) { @@ -568,9 +653,9 @@ static void mlxsw_env_pmpe_event_work(struct work_struct *work) work); mlxsw_env = event->mlxsw_env; - spin_lock_bh(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); mlxsw_env->module_info[event->module].is_overheat = false; - spin_unlock_bh(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); err = mlxsw_env_module_has_temp_sensor(mlxsw_env->core, event->module, &has_temp_sensor); @@ -652,8 +737,10 @@ mlxsw_env_module_oper_state_event_enable(struct mlxsw_core *mlxsw_core, for (i = 0; i < module_count; i++) { char pmaos_pl[MLXSW_REG_PMAOS_LEN]; - mlxsw_reg_pmaos_pack(pmaos_pl, i, - MLXSW_REG_PMAOS_E_GENERATE_EVENT); + mlxsw_reg_pmaos_pack(pmaos_pl, i); + mlxsw_reg_pmaos_e_set(pmaos_pl, + MLXSW_REG_PMAOS_E_GENERATE_EVENT); + mlxsw_reg_pmaos_ee_set(pmaos_pl, true); err = mlxsw_reg_write(mlxsw_core, MLXSW_REG(pmaos), pmaos_pl); if (err) return err; @@ -667,23 +754,71 @@ mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module, { struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); - /* Prevent switch driver from accessing uninitialized data. */ - if (!mlxsw_core_is_initialized(mlxsw_core)) { - *p_counter = 0; - return 0; - } - if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) return -EINVAL; - spin_lock_bh(&mlxsw_env->module_info_lock); + mutex_lock(&mlxsw_env->module_info_lock); *p_counter = mlxsw_env->module_info[module].module_overheat_counter; - spin_unlock_bh(&mlxsw_env->module_info_lock); + mutex_unlock(&mlxsw_env->module_info_lock); return 0; } EXPORT_SYMBOL(mlxsw_env_module_overheat_counter_get); +void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_mapped++; + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_map); + +void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_mapped--; + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_unmap); + +int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return -EINVAL; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_up++; + mutex_unlock(&mlxsw_env->module_info_lock); + + return 0; +} +EXPORT_SYMBOL(mlxsw_env_module_port_up); + +void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module) +{ + struct mlxsw_env *mlxsw_env = mlxsw_core_env(mlxsw_core); + + if (WARN_ON_ONCE(module >= mlxsw_env->module_count)) + return; + + mutex_lock(&mlxsw_env->module_info_lock); + mlxsw_env->module_info[module].num_ports_up--; + mutex_unlock(&mlxsw_env->module_info_lock); +} +EXPORT_SYMBOL(mlxsw_env_module_port_down); + int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) { char mgpir_pl[MLXSW_REG_MGPIR_LEN]; @@ -702,7 +837,7 @@ int mlxsw_env_init(struct mlxsw_core *mlxsw_core, struct mlxsw_env **p_env) if (!env) return -ENOMEM; - spin_lock_init(&env->module_info_lock); + mutex_init(&env->module_info_lock); env->core = mlxsw_core; env->module_count = module_count; *p_env = env; @@ -732,6 +867,7 @@ err_oper_state_event_enable: err_module_plug_event_register: mlxsw_env_temp_warn_event_unregister(env); err_temp_warn_event_register: + mutex_destroy(&env->module_info_lock); kfree(env); return err; } @@ -742,5 +878,6 @@ void mlxsw_env_fini(struct mlxsw_env *env) /* Make sure there is no more event work scheduled. */ mlxsw_core_flush_owq(); mlxsw_env_temp_warn_event_unregister(env); + mutex_destroy(&env->module_info_lock); kfree(env); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h index 0bf5bd0f8a7ee1..c486397f5dfec8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_env.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -24,9 +24,22 @@ mlxsw_env_get_module_eeprom_by_page(struct mlxsw_core *mlxsw_core, u8 module, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack); +int mlxsw_env_reset_module(struct net_device *netdev, + struct mlxsw_core *mlxsw_core, u8 module, + u32 *flags); + int mlxsw_env_module_overheat_counter_get(struct mlxsw_core *mlxsw_core, u8 module, u64 *p_counter); + +void mlxsw_env_module_port_map(struct mlxsw_core *mlxsw_core, u8 module); + +void mlxsw_env_module_port_unmap(struct mlxsw_core *mlxsw_core, u8 module); + +int mlxsw_env_module_port_up(struct mlxsw_core *mlxsw_core, u8 module); + +void mlxsw_env_module_port_down(struct mlxsw_core *mlxsw_core, u8 module); + int mlxsw_env_init(struct mlxsw_core *core, struct mlxsw_env **p_env); void mlxsw_env_fini(struct mlxsw_env *env); diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c index d9d56c44e994fd..9644e9c486b80b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c @@ -54,8 +54,20 @@ static int mlxsw_m_base_mac_get(struct mlxsw_m *mlxsw_m) return 0; } -static int mlxsw_m_port_dummy_open_stop(struct net_device *dev) +static int mlxsw_m_port_open(struct net_device *dev) { + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); + struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; + + return mlxsw_env_module_port_up(mlxsw_m->core, mlxsw_m_port->module); +} + +static int mlxsw_m_port_stop(struct net_device *dev) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev); + struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m; + + mlxsw_env_module_port_down(mlxsw_m->core, mlxsw_m_port->module); return 0; } @@ -70,8 +82,8 @@ mlxsw_m_port_get_devlink_port(struct net_device *dev) } static const struct net_device_ops mlxsw_m_port_netdev_ops = { - .ndo_open = mlxsw_m_port_dummy_open_stop, - .ndo_stop = mlxsw_m_port_dummy_open_stop, + .ndo_open = mlxsw_m_port_open, + .ndo_stop = mlxsw_m_port_stop, .ndo_get_devlink_port = mlxsw_m_port_get_devlink_port, }; @@ -124,11 +136,21 @@ mlxsw_m_get_module_eeprom_by_page(struct net_device *netdev, page, extack); } +static int mlxsw_m_reset(struct net_device *netdev, u32 *flags) +{ + struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev); + struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core; + + return mlxsw_env_reset_module(netdev, core, mlxsw_m_port->module, + flags); +} + static const struct ethtool_ops mlxsw_m_port_ethtool_ops = { .get_drvinfo = mlxsw_m_module_get_drvinfo, .get_module_info = mlxsw_m_get_module_info, .get_module_eeprom = mlxsw_m_get_module_eeprom, .get_module_eeprom_by_page = mlxsw_m_get_module_eeprom_by_page, + .reset = mlxsw_m_reset, }; static int @@ -266,6 +288,7 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, if (WARN_ON_ONCE(module >= max_ports)) return -EINVAL; + mlxsw_env_module_port_map(mlxsw_m->core, module); mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports; return 0; @@ -274,6 +297,7 @@ static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port, static void mlxsw_m_port_module_unmap(struct mlxsw_m *mlxsw_m, u8 module) { mlxsw_m->module_to_port[module] = -1; + mlxsw_env_module_port_unmap(mlxsw_m->core, module); } static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6fbda6ebd59013..c5fad3c94fac2e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5681,6 +5681,14 @@ static inline void mlxsw_reg_pspa_pack(char *payload, u8 swid, u8 local_port) MLXSW_REG_DEFINE(pmaos, MLXSW_REG_PMAOS_ID, MLXSW_REG_PMAOS_LEN); +/* reg_pmaos_rst + * Module reset toggle. + * Note: Setting reset while module is plugged-in will result in transition to + * "initializing" operational state. + * Access: OP + */ +MLXSW_ITEM32(reg, pmaos, rst, 0x00, 31, 1); + /* reg_pmaos_slot_index * Slot index. * Access: Index @@ -5693,6 +5701,24 @@ MLXSW_ITEM32(reg, pmaos, slot_index, 0x00, 24, 4); */ MLXSW_ITEM32(reg, pmaos, module, 0x00, 16, 8); +enum mlxsw_reg_pmaos_admin_status { + MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED = 1, + MLXSW_REG_PMAOS_ADMIN_STATUS_DISABLED = 2, + /* If the module is active and then unplugged, or experienced an error + * event, the operational status should go to "disabled" and can only + * be enabled upon explicit enable command. + */ + MLXSW_REG_PMAOS_ADMIN_STATUS_ENABLED_ONCE = 3, +}; + +/* reg_pmaos_admin_status + * Module administrative state (the desired state of the module). + * Note: To disable a module, all ports associated with the port must be + * administatively down first. + * Access: RW + */ +MLXSW_ITEM32(reg, pmaos, admin_status, 0x00, 8, 4); + /* reg_pmaos_ase * Admin state update enable. * If this bit is set, admin state will be updated based on admin_state field. @@ -5721,13 +5747,10 @@ enum mlxsw_reg_pmaos_e { */ MLXSW_ITEM32(reg, pmaos, e, 0x04, 0, 2); -static inline void mlxsw_reg_pmaos_pack(char *payload, u8 module, - enum mlxsw_reg_pmaos_e e) +static inline void mlxsw_reg_pmaos_pack(char *payload, u8 module) { MLXSW_REG_ZERO(pmaos, payload); mlxsw_reg_pmaos_module_set(payload, module); - mlxsw_reg_pmaos_e_set(payload, e); - mlxsw_reg_pmaos_ee_set(payload, true); } /* PPLR - Port Physical Loopback Register @@ -5766,6 +5789,69 @@ static inline void mlxsw_reg_pplr_pack(char *payload, u8 local_port, MLXSW_REG_PPLR_LB_TYPE_BIT_PHY_LOCAL : 0); } +/* PMTDB - Port Module To local DataBase Register + * ---------------------------------------------- + * The PMTDB register allows to query the possible module<->local port + * mapping than can be used in PMLP. It does not represent the actual/current + * mapping of the local to module. Actual mapping is only defined by PMLP. + */ +#define MLXSW_REG_PMTDB_ID 0x501A +#define MLXSW_REG_PMTDB_LEN 0x40 + +MLXSW_REG_DEFINE(pmtdb, MLXSW_REG_PMTDB_ID, MLXSW_REG_PMTDB_LEN); + +/* reg_pmtdb_slot_index + * Slot index (0: Main board). + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, slot_index, 0x00, 24, 4); + +/* reg_pmtdb_module + * Module number. + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, module, 0x00, 16, 8); + +/* reg_pmtdb_ports_width + * Port's width + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, ports_width, 0x00, 12, 4); + +/* reg_pmtdb_num_ports + * Number of ports in a single module (split/breakout) + * Access: Index + */ +MLXSW_ITEM32(reg, pmtdb, num_ports, 0x00, 8, 4); + +enum mlxsw_reg_pmtdb_status { + MLXSW_REG_PMTDB_STATUS_SUCCESS, +}; + +/* reg_pmtdb_status + * Status + * Access: RO + */ +MLXSW_ITEM32(reg, pmtdb, status, 0x00, 0, 4); + +/* reg_pmtdb_port_num + * The local_port value which can be assigned to the module. + * In case of more than one port, port<x> represent the /<x> port of + * the module. + * Access: RO + */ +MLXSW_ITEM16_INDEXED(reg, pmtdb, port_num, 0x04, 0, 8, 0x02, 0x00, false); + +static inline void mlxsw_reg_pmtdb_pack(char *payload, u8 slot_index, u8 module, + u8 ports_width, u8 num_ports) +{ + MLXSW_REG_ZERO(pmtdb, payload); + mlxsw_reg_pmtdb_slot_index_set(payload, slot_index); + mlxsw_reg_pmtdb_module_set(payload, module); + mlxsw_reg_pmtdb_ports_width_set(payload, ports_width); + mlxsw_reg_pmtdb_num_ports_set(payload, num_ports); +} + /* PMPE - Port Module Plug/Unplug Event Register * --------------------------------------------- * This register reports any operational status change of a module. @@ -5860,67 +5946,51 @@ static inline void mlxsw_reg_pddr_pack(char *payload, u8 local_port, mlxsw_reg_pddr_page_select_set(payload, page_select); } -/* PMTM - Port Module Type Mapping Register - * ---------------------------------------- - * The PMTM allows query or configuration of module types. +/* PLLP - Port Local port to Label Port mapping Register + * ----------------------------------------------------- + * The PLLP register returns the mapping from Local Port into Label Port. */ -#define MLXSW_REG_PMTM_ID 0x5067 -#define MLXSW_REG_PMTM_LEN 0x10 +#define MLXSW_REG_PLLP_ID 0x504A +#define MLXSW_REG_PLLP_LEN 0x10 -MLXSW_REG_DEFINE(pmtm, MLXSW_REG_PMTM_ID, MLXSW_REG_PMTM_LEN); +MLXSW_REG_DEFINE(pllp, MLXSW_REG_PLLP_ID, MLXSW_REG_PLLP_LEN); -/* reg_pmtm_module - * Module number. +/* reg_pllp_local_port + * Local port number. * Access: Index */ -MLXSW_ITEM32(reg, pmtm, module, 0x00, 16, 8); +MLXSW_ITEM32(reg, pllp, local_port, 0x00, 16, 8); -enum mlxsw_reg_pmtm_module_type { - /* Backplane with 4 lanes */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_4X, - /* QSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_QSFP, - /* SFP */ - MLXSW_REG_PMTM_MODULE_TYPE_SFP, - /* Backplane with single lane */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_1X = 4, - /* Backplane with two lane */ - MLXSW_REG_PMTM_MODULE_TYPE_BP_2X = 8, - /* Chip2Chip4x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C4X = 10, - /* Chip2Chip2x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C2X, - /* Chip2Chip1x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C1X, - /* QSFP-DD */ - MLXSW_REG_PMTM_MODULE_TYPE_QSFP_DD = 14, - /* OSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_OSFP, - /* SFP-DD */ - MLXSW_REG_PMTM_MODULE_TYPE_SFP_DD, - /* DSFP */ - MLXSW_REG_PMTM_MODULE_TYPE_DSFP, - /* Chip2Chip8x */ - MLXSW_REG_PMTM_MODULE_TYPE_C2C8X, -}; +/* reg_pllp_label_port + * Front panel label of the port. + * Access: RO + */ +MLXSW_ITEM32(reg, pllp, label_port, 0x00, 0, 8); -/* reg_pmtm_module_type - * Module type. - * Access: RW +/* reg_pllp_split_num + * Label split mapping for local_port. + * Access: RO + */ +MLXSW_ITEM32(reg, pllp, split_num, 0x04, 0, 4); + +/* reg_pllp_slot_index + * Slot index (0: Main board). + * Access: RO */ -MLXSW_ITEM32(reg, pmtm, module_type, 0x04, 0, 4); +MLXSW_ITEM32(reg, pllp, slot_index, 0x08, 0, 4); -static inline void mlxsw_reg_pmtm_pack(char *payload, u8 module) +static inline void mlxsw_reg_pllp_pack(char *payload, u8 local_port) { - MLXSW_REG_ZERO(pmtm, payload); - mlxsw_reg_pmtm_module_set(payload, module); + MLXSW_REG_ZERO(pllp, payload); + mlxsw_reg_pllp_local_port_set(payload, local_port); } -static inline void -mlxsw_reg_pmtm_unpack(char *payload, - enum mlxsw_reg_pmtm_module_type *module_type) +static inline void mlxsw_reg_pllp_unpack(char *payload, u8 *label_port, + u8 *split_num, u8 *slot_index) { - *module_type = mlxsw_reg_pmtm_module_type_get(payload); + *label_port = mlxsw_reg_pllp_label_port_get(payload); + *split_num = mlxsw_reg_pllp_split_num_get(payload); + *slot_index = mlxsw_reg_pllp_slot_index_get(payload); } /* HTGT - Host Trap Group Table @@ -6664,6 +6734,23 @@ mlxsw_reg_ritr_loopback_ipip4_pack(char *payload, mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip); } +static inline void +mlxsw_reg_ritr_loopback_ipip6_pack(char *payload, + enum mlxsw_reg_ritr_loopback_ipip_type ipip_type, + enum mlxsw_reg_ritr_loopback_ipip_options options, + u16 uvr_id, u16 underlay_rif, + const struct in6_addr *usip, u32 gre_key) +{ + enum mlxsw_reg_ritr_loopback_protocol protocol = + MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6; + + mlxsw_reg_ritr_loopback_protocol_set(payload, protocol); + mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options, + uvr_id, underlay_rif, gre_key); + mlxsw_reg_ritr_loopback_ipip_usip6_memcpy_to(payload, + (const char *)usip); +} + /* RTAR - Router TCAM Allocation Register * -------------------------------------- * This register is used for allocation of regions in the TCAM table. @@ -6932,6 +7019,12 @@ static inline void mlxsw_reg_ratr_ipip4_entry_pack(char *payload, u32 ipv4_udip) mlxsw_reg_ratr_ipip_ipv4_udip_set(payload, ipv4_udip); } +static inline void mlxsw_reg_ratr_ipip6_entry_pack(char *payload, u32 ipv6_ptr) +{ + mlxsw_reg_ratr_ipip_type_set(payload, MLXSW_REG_RATR_IPIP_TYPE_IPV6); + mlxsw_reg_ratr_ipip_ipv6_ptr_set(payload, ipv6_ptr); +} + static inline void mlxsw_reg_ratr_counter_pack(char *payload, u64 counter_index, bool counter_enable) { @@ -8117,19 +8210,71 @@ static inline void mlxsw_reg_rtdp_pack(char *payload, } static inline void -mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif, - enum mlxsw_reg_rtdp_ipip_sip_check sip_check, - unsigned int type_check, bool gre_key_check, - u32 ipv4_usip, u32 expected_gre_key) +mlxsw_reg_rtdp_ipip_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 expected_gre_key) { mlxsw_reg_rtdp_ipip_irif_set(payload, irif); mlxsw_reg_rtdp_ipip_sip_check_set(payload, sip_check); mlxsw_reg_rtdp_ipip_type_check_set(payload, type_check); mlxsw_reg_rtdp_ipip_gre_key_check_set(payload, gre_key_check); - mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip); mlxsw_reg_rtdp_ipip_expected_gre_key_set(payload, expected_gre_key); } +static inline void +mlxsw_reg_rtdp_ipip4_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 ipv4_usip, u32 expected_gre_key) +{ + mlxsw_reg_rtdp_ipip_pack(payload, irif, sip_check, type_check, + gre_key_check, expected_gre_key); + mlxsw_reg_rtdp_ipip_ipv4_usip_set(payload, ipv4_usip); +} + +static inline void +mlxsw_reg_rtdp_ipip6_pack(char *payload, u16 irif, + enum mlxsw_reg_rtdp_ipip_sip_check sip_check, + unsigned int type_check, bool gre_key_check, + u32 ipv6_usip_ptr, u32 expected_gre_key) +{ + mlxsw_reg_rtdp_ipip_pack(payload, irif, sip_check, type_check, + gre_key_check, expected_gre_key); + mlxsw_reg_rtdp_ipip_ipv6_usip_ptr_set(payload, ipv6_usip_ptr); +} + +/* RIPS - Router IP version Six Register + * ------------------------------------- + * The RIPS register is used to store IPv6 addresses for use by the NVE and + * IPinIP + */ +#define MLXSW_REG_RIPS_ID 0x8021 +#define MLXSW_REG_RIPS_LEN 0x14 + +MLXSW_REG_DEFINE(rips, MLXSW_REG_RIPS_ID, MLXSW_REG_RIPS_LEN); + +/* reg_rips_index + * Index to IPv6 address. + * For Spectrum, the index is to the KVD linear. + * Access: Index + */ +MLXSW_ITEM32(reg, rips, index, 0x00, 0, 24); + +/* reg_rips_ipv6 + * IPv6 address + * Access: RW + */ +MLXSW_ITEM_BUF(reg, rips, ipv6, 0x04, 16); + +static inline void mlxsw_reg_rips_pack(char *payload, u32 index, + const struct in6_addr *ipv6) +{ + MLXSW_REG_ZERO(rips, payload); + mlxsw_reg_rips_index_set(payload, index); + mlxsw_reg_rips_ipv6_memcpy_to(payload, (const char *)ipv6); +} + /* RATRAD - Router Adjacency Table Activity Dump Register * ------------------------------------------------------ * The RATRAD register is used to dump and optionally clear activity bits of @@ -12200,9 +12345,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(pspa), MLXSW_REG(pmaos), MLXSW_REG(pplr), + MLXSW_REG(pmtdb), MLXSW_REG(pmpe), MLXSW_REG(pddr), - MLXSW_REG(pmtm), + MLXSW_REG(pllp), MLXSW_REG(htgt), MLXSW_REG(hpkt), MLXSW_REG(rgcr), @@ -12210,6 +12356,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rtar), MLXSW_REG(ratr), MLXSW_REG(rtdp), + MLXSW_REG(rips), MLXSW_REG(ratrad), MLXSW_REG(rdpm), MLXSW_REG(ricnt), diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index a56c9e19a3904d..a1512be7786711 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -25,9 +25,6 @@ enum mlxsw_res_id { MLXSW_RES_ID_MAX_SYSTEM_PORT, MLXSW_RES_ID_MAX_LAG, MLXSW_RES_ID_MAX_LAG_MEMBERS, - MLXSW_RES_ID_LOCAL_PORTS_IN_1X, - MLXSW_RES_ID_LOCAL_PORTS_IN_2X, - MLXSW_RES_ID_LOCAL_PORTS_IN_4X, MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER, MLXSW_RES_ID_CELL_SIZE, MLXSW_RES_ID_MAX_HEADROOM_SIZE, @@ -84,9 +81,6 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_MAX_SYSTEM_PORT] = 0x2502, [MLXSW_RES_ID_MAX_LAG] = 0x2520, [MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521, - [MLXSW_RES_ID_LOCAL_PORTS_IN_1X] = 0x2610, - [MLXSW_RES_ID_LOCAL_PORTS_IN_2X] = 0x2611, - [MLXSW_RES_ID_LOCAL_PORTS_IN_4X] = 0x2612, [MLXSW_RES_ID_GUARANTEED_SHARED_BUFFER] = 0x2805, /* Bytes */ [MLXSW_RES_ID_CELL_SIZE] = 0x2803, /* Bytes */ [MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811, /* Bytes */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 250c5a24264dcc..0e81ae723bc858 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -47,7 +47,7 @@ #define MLXSW_SP1_FWREV_MAJOR 13 #define MLXSW_SP1_FWREV_MINOR 2008 -#define MLXSW_SP1_FWREV_SUBMINOR 2406 +#define MLXSW_SP1_FWREV_SUBMINOR 3326 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { @@ -64,7 +64,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { #define MLXSW_SP2_FWREV_MAJOR 29 #define MLXSW_SP2_FWREV_MINOR 2008 -#define MLXSW_SP2_FWREV_SUBMINOR 2406 +#define MLXSW_SP2_FWREV_SUBMINOR 3326 static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { .major = MLXSW_SP2_FWREV_MAJOR, @@ -79,7 +79,7 @@ static const struct mlxsw_fw_rev mlxsw_sp2_fw_rev = { #define MLXSW_SP3_FWREV_MAJOR 30 #define MLXSW_SP3_FWREV_MINOR 2008 -#define MLXSW_SP3_FWREV_SUBMINOR 2406 +#define MLXSW_SP3_FWREV_SUBMINOR 3326 static const struct mlxsw_fw_rev mlxsw_sp3_fw_rev = { .major = MLXSW_SP3_FWREV_MAJOR, @@ -351,12 +351,12 @@ static int mlxsw_sp_port_mtu_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 mtu) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmtu), pmtu_pl); } -static int mlxsw_sp_port_swid_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 swid) +static int mlxsw_sp_port_swid_set(struct mlxsw_sp *mlxsw_sp, + u8 local_port, u8 swid) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pspa_pl[MLXSW_REG_PSPA_LEN]; - mlxsw_reg_pspa_pack(pspa_pl, swid, mlxsw_sp_port->local_port); + mlxsw_reg_pspa_pack(pspa_pl, swid, local_port); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pspa), pspa_pl); } @@ -529,55 +529,80 @@ mlxsw_sp_port_module_info_get(struct mlxsw_sp *mlxsw_sp, u8 local_port, port_mapping->module = module; port_mapping->width = width; + port_mapping->module_width = width; port_mapping->lane = mlxsw_reg_pmlp_tx_lane_get(pmlp_pl, 0); return 0; } -static int mlxsw_sp_port_module_map(struct mlxsw_sp_port *mlxsw_sp_port) +static int +mlxsw_sp_port_module_map(struct mlxsw_sp *mlxsw_sp, u8 local_port, + const struct mlxsw_sp_port_mapping *port_mapping) { - struct mlxsw_sp_port_mapping *port_mapping = &mlxsw_sp_port->mapping; - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; - int i; + int i, err; + + mlxsw_env_module_port_map(mlxsw_sp->core, port_mapping->module); - mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); mlxsw_reg_pmlp_width_set(pmlp_pl, port_mapping->width); for (i = 0; i < port_mapping->width; i++) { mlxsw_reg_pmlp_module_set(pmlp_pl, i, port_mapping->module); mlxsw_reg_pmlp_tx_lane_set(pmlp_pl, i, port_mapping->lane + i); /* Rx & Tx */ } - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + if (err) + goto err_pmlp_write; + return 0; + +err_pmlp_write: + mlxsw_env_module_port_unmap(mlxsw_sp->core, port_mapping->module); + return err; } -static int mlxsw_sp_port_module_unmap(struct mlxsw_sp_port *mlxsw_sp_port) +static void mlxsw_sp_port_module_unmap(struct mlxsw_sp *mlxsw_sp, u8 local_port, + u8 module) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char pmlp_pl[MLXSW_REG_PMLP_LEN]; - mlxsw_reg_pmlp_pack(pmlp_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); mlxsw_reg_pmlp_width_set(pmlp_pl, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pmlp), pmlp_pl); + mlxsw_env_module_port_unmap(mlxsw_sp->core, module); } static int mlxsw_sp_port_open(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; int err; - err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + err = mlxsw_env_module_port_up(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); if (err) return err; + err = mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true); + if (err) + goto err_port_admin_status_set; netif_start_queue(dev); return 0; + +err_port_admin_status_set: + mlxsw_env_module_port_down(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); + return err; } static int mlxsw_sp_port_stop(struct net_device *dev) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; netif_stop_queue(dev); - return mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false); + mlxsw_env_module_port_down(mlxsw_sp->core, + mlxsw_sp_port->mapping.module); + return 0; } static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb, @@ -1442,29 +1467,68 @@ mlxsw_sp_port_vlan_classification_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvc), spvc_pl); } +static int mlxsw_sp_port_label_info_get(struct mlxsw_sp *mlxsw_sp, + u8 local_port, u8 *port_number, + u8 *split_port_subnumber, + u8 *slot_index) +{ + char pllp_pl[MLXSW_REG_PLLP_LEN]; + int err; + + mlxsw_reg_pllp_pack(pllp_pl, local_port); + err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pllp), pllp_pl); + if (err) + return err; + mlxsw_reg_pllp_unpack(pllp_pl, port_number, + split_port_subnumber, slot_index); + return 0; +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, - u8 split_base_local_port, + bool split, struct mlxsw_sp_port_mapping *port_mapping) { struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan; - bool split = !!split_base_local_port; struct mlxsw_sp_port *mlxsw_sp_port; u32 lanes = port_mapping->width; + u8 split_port_subnumber; struct net_device *dev; + u8 port_number; + u8 slot_index; bool splittable; int err; + err = mlxsw_sp_port_module_map(mlxsw_sp, local_port, port_mapping); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to map module\n", + local_port); + return err; + } + + err = mlxsw_sp_port_swid_set(mlxsw_sp, local_port, 0); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n", + local_port); + goto err_port_swid_set; + } + + err = mlxsw_sp_port_label_info_get(mlxsw_sp, local_port, &port_number, + &split_port_subnumber, &slot_index); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to get port label information\n", + local_port); + goto err_port_label_info_get; + } + splittable = lanes > 1 && !split; err = mlxsw_core_port_init(mlxsw_sp->core, local_port, - port_mapping->module + 1, split, - port_mapping->lane / lanes, - splittable, lanes, - mlxsw_sp->base_mac, + port_number, split, split_port_subnumber, + splittable, lanes, mlxsw_sp->base_mac, sizeof(mlxsw_sp->base_mac)); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to init core port\n", local_port); - return err; + goto err_core_port_init; } dev = alloc_etherdev(sizeof(struct mlxsw_sp_port)); @@ -1480,7 +1544,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, mlxsw_sp_port->local_port = local_port; mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID; mlxsw_sp_port->split = split; - mlxsw_sp_port->split_base_local_port = split_base_local_port; mlxsw_sp_port->mapping = *port_mapping; mlxsw_sp_port->link.autoneg = 1; INIT_LIST_HEAD(&mlxsw_sp_port->vlans_list); @@ -1498,20 +1561,6 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, dev->netdev_ops = &mlxsw_sp_port_netdev_ops; dev->ethtool_ops = &mlxsw_sp_port_ethtool_ops; - err = mlxsw_sp_port_module_map(mlxsw_sp_port); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to map module\n", - mlxsw_sp_port->local_port); - goto err_port_module_map; - } - - err = mlxsw_sp_port_swid_set(mlxsw_sp_port, 0); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set SWID\n", - mlxsw_sp_port->local_port); - goto err_port_swid_set; - } - err = mlxsw_sp_port_dev_addr_init(mlxsw_sp_port); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Unable to init port mac address\n", @@ -1712,21 +1761,24 @@ err_max_speed_get: err_port_speed_by_width_set: err_port_system_port_mapping_set: err_dev_addr_init: - mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); -err_port_swid_set: - mlxsw_sp_port_module_unmap(mlxsw_sp_port); -err_port_module_map: free_percpu(mlxsw_sp_port->pcpu_stats); err_alloc_stats: free_netdev(dev); err_alloc_etherdev: mlxsw_core_port_fini(mlxsw_sp->core, local_port); +err_core_port_init: +err_port_label_info_get: + mlxsw_sp_port_swid_set(mlxsw_sp, local_port, + MLXSW_PORT_SWID_DISABLED_PORT); +err_port_swid_set: + mlxsw_sp_port_module_unmap(mlxsw_sp, local_port, port_mapping->module); return err; } static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) { struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp->ports[local_port]; + u8 module = mlxsw_sp_port->mapping.module; cancel_delayed_work_sync(&mlxsw_sp_port->periodic_hw_stats.update_dw); cancel_delayed_work_sync(&mlxsw_sp_port->ptp.shaper_dw); @@ -1742,12 +1794,13 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_sp_port_dcb_fini(mlxsw_sp_port); mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false); mlxsw_sp_port_buffers_fini(mlxsw_sp_port); - mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); - mlxsw_sp_port_module_unmap(mlxsw_sp_port); free_percpu(mlxsw_sp_port->pcpu_stats); WARN_ON_ONCE(!list_empty(&mlxsw_sp_port->vlans_list)); free_netdev(mlxsw_sp_port->dev); mlxsw_core_port_fini(mlxsw_sp->core, local_port); + mlxsw_sp_port_swid_set(mlxsw_sp, local_port, + MLXSW_PORT_SWID_DISABLED_PORT); + mlxsw_sp_port_module_unmap(mlxsw_sp, local_port, module); } static int mlxsw_sp_cpu_port_create(struct mlxsw_sp *mlxsw_sp) @@ -1789,8 +1842,15 @@ static void mlxsw_sp_cpu_port_remove(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp_port); } +static bool mlxsw_sp_local_port_valid(u8 local_port) +{ + return local_port != MLXSW_PORT_CPU_PORT; +} + static bool mlxsw_sp_port_created(struct mlxsw_sp *mlxsw_sp, u8 local_port) { + if (!mlxsw_sp_local_port_valid(local_port)) + return false; return mlxsw_sp->ports[local_port] != NULL; } @@ -1827,7 +1887,7 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) port_mapping = mlxsw_sp->port_mapping[i]; if (!port_mapping) continue; - err = mlxsw_sp_port_create(mlxsw_sp, i, 0, port_mapping); + err = mlxsw_sp_port_create(mlxsw_sp, i, false, port_mapping); if (err) goto err_port_create; } @@ -1894,17 +1954,10 @@ static void mlxsw_sp_port_module_info_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->port_mapping); } -static u8 mlxsw_sp_cluster_base_port_get(u8 local_port, unsigned int max_width) -{ - u8 offset = (local_port - 1) % max_width; - - return local_port - offset; -} - static int -mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, +mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_port_mapping *port_mapping, - unsigned int count, u8 offset) + unsigned int count, const char *pmtdb_pl) { struct mlxsw_sp_port_mapping split_port_mapping; int err, i; @@ -1912,8 +1965,13 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, split_port_mapping = *port_mapping; split_port_mapping.width /= count; for (i = 0; i < count; i++) { - err = mlxsw_sp_port_create(mlxsw_sp, base_port + i * offset, - base_port, &split_port_mapping); + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + if (!mlxsw_sp_local_port_valid(s_local_port)) + continue; + + err = mlxsw_sp_port_create(mlxsw_sp, s_local_port, + true, &split_port_mapping); if (err) goto err_port_create; split_port_mapping.lane += split_port_mapping.width; @@ -1922,49 +1980,34 @@ mlxsw_sp_port_split_create(struct mlxsw_sp *mlxsw_sp, u8 base_port, return 0; err_port_create: - for (i--; i >= 0; i--) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); + for (i--; i >= 0; i--) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); + } return err; } static void mlxsw_sp_port_unsplit_create(struct mlxsw_sp *mlxsw_sp, - u8 base_port, - unsigned int count, u8 offset) + unsigned int count, + const char *pmtdb_pl) { struct mlxsw_sp_port_mapping *port_mapping; int i; /* Go over original unsplit ports in the gap and recreate them. */ - for (i = 0; i < count * offset; i++) { - port_mapping = mlxsw_sp->port_mapping[base_port + i]; - if (!port_mapping) + for (i = 0; i < count; i++) { + u8 local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); + + port_mapping = mlxsw_sp->port_mapping[local_port]; + if (!port_mapping || !mlxsw_sp_local_port_valid(local_port)) continue; - mlxsw_sp_port_create(mlxsw_sp, base_port + i, 0, port_mapping); + mlxsw_sp_port_create(mlxsw_sp, local_port, + false, port_mapping); } } -static int mlxsw_sp_local_ports_offset(struct mlxsw_core *mlxsw_core, - unsigned int count, - unsigned int max_width) -{ - enum mlxsw_res_id local_ports_in_x_res_id; - int split_width = max_width / count; - - if (split_width == 1) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_1X; - else if (split_width == 2) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_2X; - else if (split_width == 4) - local_ports_in_x_res_id = MLXSW_RES_ID_LOCAL_PORTS_IN_4X; - else - return -EINVAL; - - if (!mlxsw_core_res_valid(mlxsw_core, local_ports_in_x_res_id)) - return -EINVAL; - return mlxsw_core_res_get(mlxsw_core, local_ports_in_x_res_id); -} - static struct mlxsw_sp_port * mlxsw_sp_port_get_by_local_port(struct mlxsw_sp *mlxsw_sp, u8 local_port) { @@ -1980,9 +2023,8 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port_mapping port_mapping; struct mlxsw_sp_port *mlxsw_sp_port; - int max_width; - u8 base_port; - int offset; + enum mlxsw_reg_pmtdb_status status; + char pmtdb_pl[MLXSW_REG_PMTDB_LEN]; int i; int err; @@ -1994,57 +2036,37 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return -EINVAL; } - max_width = mlxsw_core_module_max_width(mlxsw_core, - mlxsw_sp_port->mapping.module); - if (max_width < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); - return max_width; + if (mlxsw_sp_port->split) { + NL_SET_ERR_MSG_MOD(extack, "Port is already split"); + return -EINVAL; } - /* Split port with non-max cannot be split. */ - if (mlxsw_sp_port->mapping.width != max_width) { - netdev_err(mlxsw_sp_port->dev, "Port cannot be split\n"); - NL_SET_ERR_MSG_MOD(extack, "Port cannot be split"); - return -EINVAL; + mlxsw_reg_pmtdb_pack(pmtdb_pl, 0, mlxsw_sp_port->mapping.module, + mlxsw_sp_port->mapping.module_width / count, + count); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtdb), pmtdb_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to query split info"); + return err; } - offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); - if (offset < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); + status = mlxsw_reg_pmtdb_status_get(pmtdb_pl); + if (status != MLXSW_REG_PMTDB_STATUS_SUCCESS) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported split configuration"); return -EINVAL; } - /* Only in case max split is being done, the local port and - * base port may differ. - */ - base_port = count == max_width ? - mlxsw_sp_cluster_base_port_get(local_port, max_width) : - local_port; + port_mapping = mlxsw_sp_port->mapping; - for (i = 0; i < count * offset; i++) { - /* Expect base port to exist and also the one in the middle in - * case of maximal split count. - */ - if (i == 0 || (count == max_width && i == count / 2)) - continue; + for (i = 0; i < count; i++) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i)) { - netdev_err(mlxsw_sp_port->dev, "Invalid split configuration\n"); - NL_SET_ERR_MSG_MOD(extack, "Invalid split configuration"); - return -EINVAL; - } + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); } - port_mapping = mlxsw_sp_port->mapping; - - for (i = 0; i < count; i++) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); - - err = mlxsw_sp_port_split_create(mlxsw_sp, base_port, &port_mapping, - count, offset); + err = mlxsw_sp_port_split_create(mlxsw_sp, &port_mapping, + count, pmtdb_pl); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to create split ports\n"); goto err_port_split_create; @@ -2053,7 +2075,7 @@ static int mlxsw_sp_port_split(struct mlxsw_core *mlxsw_core, u8 local_port, return 0; err_port_split_create: - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); + mlxsw_sp_port_unsplit_create(mlxsw_sp, count, pmtdb_pl); return err; } @@ -2062,11 +2084,10 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, { struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); struct mlxsw_sp_port *mlxsw_sp_port; + char pmtdb_pl[MLXSW_REG_PMTDB_LEN]; unsigned int count; - int max_width; - u8 base_port; - int offset; int i; + int err; mlxsw_sp_port = mlxsw_sp_port_get_by_local_port(mlxsw_sp, local_port); if (!mlxsw_sp_port) { @@ -2077,35 +2098,30 @@ static int mlxsw_sp_port_unsplit(struct mlxsw_core *mlxsw_core, u8 local_port, } if (!mlxsw_sp_port->split) { - netdev_err(mlxsw_sp_port->dev, "Port was not split\n"); NL_SET_ERR_MSG_MOD(extack, "Port was not split"); return -EINVAL; } - max_width = mlxsw_core_module_max_width(mlxsw_core, - mlxsw_sp_port->mapping.module); - if (max_width < 0) { - netdev_err(mlxsw_sp_port->dev, "Cannot get max width of port module\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot get max width of port module"); - return max_width; - } + count = mlxsw_sp_port->mapping.module_width / + mlxsw_sp_port->mapping.width; - count = max_width / mlxsw_sp_port->mapping.width; - - offset = mlxsw_sp_local_ports_offset(mlxsw_core, count, max_width); - if (WARN_ON(offset < 0)) { - netdev_err(mlxsw_sp_port->dev, "Cannot obtain local port offset\n"); - NL_SET_ERR_MSG_MOD(extack, "Cannot obtain local port offset"); - return -EINVAL; + mlxsw_reg_pmtdb_pack(pmtdb_pl, 0, mlxsw_sp_port->mapping.module, + mlxsw_sp_port->mapping.module_width / count, + count); + err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(pmtdb), pmtdb_pl); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to query split info"); + return err; } - base_port = mlxsw_sp_port->split_base_local_port; + for (i = 0; i < count; i++) { + u8 s_local_port = mlxsw_reg_pmtdb_port_num_get(pmtdb_pl, i); - for (i = 0; i < count; i++) - if (mlxsw_sp_port_created(mlxsw_sp, base_port + i * offset)) - mlxsw_sp_port_remove(mlxsw_sp, base_port + i * offset); + if (mlxsw_sp_port_created(mlxsw_sp, s_local_port)) + mlxsw_sp_port_remove(mlxsw_sp, s_local_port); + } - mlxsw_sp_port_unsplit_create(mlxsw_sp, base_port, count, offset); + mlxsw_sp_port_unsplit_create(mlxsw_sp, count, pmtdb_pl); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3a43cba6d23c2f..0ebbd9b04b891d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -144,7 +144,8 @@ struct mlxsw_sp_mall_entry; struct mlxsw_sp_port_mapping { u8 module; - u8 width; + u8 width; /* Number of lanes used by the port */ + u8 module_width; /* Number of lanes in the module (static) */ u8 lane; }; @@ -345,7 +346,6 @@ struct mlxsw_sp_port { u16 egr_types; struct mlxsw_sp_ptp_port_stats stats; } ptp; - u8 split_base_local_port; int max_mtu; u32 max_speed; struct mlxsw_sp_hdroom *hdroom; @@ -747,6 +747,7 @@ enum mlxsw_sp_kvdl_entry_type { MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET, MLXSW_SP_KVDL_ENTRY_TYPE_PBS, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR, + MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT, }; @@ -758,6 +759,7 @@ mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type) case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: + case MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS: case MLXSW_SP_KVDL_ENTRY_TYPE_TNUMT: default: return 1; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c index 3a73d654017fe5..10ae1115de6c84 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c @@ -35,6 +35,7 @@ static const struct mlxsw_sp2_kvdl_part_info mlxsw_sp2_kvdl_parts_info[] = { MAX_KVD_ACTION_SETS), MLXSW_SP2_KVDL_PART_INFO(PBS, 0x24, KVD_SIZE, KVD_SIZE), MLXSW_SP2_KVDL_PART_INFO(MCRIGR, 0x26, KVD_SIZE, KVD_SIZE), + MLXSW_SP2_KVDL_PART_INFO(IPV6_ADDRESS, 0x28, KVD_SIZE, KVD_SIZE), MLXSW_SP2_KVDL_PART_INFO(TNUMT, 0x29, KVD_SIZE, KVD_SIZE), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 267590a0eee78c..06f1645561c69a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1197,6 +1197,15 @@ mlxsw_sp_get_rmon_stats(struct net_device *dev, *ranges = mlxsw_rmon_ranges; } +static int mlxsw_sp_reset(struct net_device *dev, u32 *flags) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + u8 module = mlxsw_sp_port->mapping.module; + + return mlxsw_env_reset_module(dev, mlxsw_sp->core, module, flags); +} + const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .cap_link_lanes_supported = true, .get_drvinfo = mlxsw_sp_port_get_drvinfo, @@ -1218,6 +1227,7 @@ const struct ethtool_ops mlxsw_sp_port_ethtool_ops = { .get_eth_mac_stats = mlxsw_sp_get_eth_mac_stats, .get_eth_ctrl_stats = mlxsw_sp_get_eth_ctrl_stats, .get_rmon_stats = mlxsw_sp_get_rmon_stats, + .reset = mlxsw_sp_reset, }; struct mlxsw_sp1_port_link_mode { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 5facabd86882a5..ad3926de88f285 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -24,50 +24,72 @@ mlxsw_sp_ipip_netdev_parms6(const struct net_device *ol_dev) return tun->parms; } -static bool mlxsw_sp_ipip_parms4_has_ikey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_ikey(const struct ip_tunnel_parm *parms) { - return !!(parms.i_flags & TUNNEL_KEY); + return !!(parms->i_flags & TUNNEL_KEY); } -static bool mlxsw_sp_ipip_parms4_has_okey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms6_has_ikey(const struct __ip6_tnl_parm *parms) { - return !!(parms.o_flags & TUNNEL_KEY); + return !!(parms->i_flags & TUNNEL_KEY); } -static u32 mlxsw_sp_ipip_parms4_ikey(struct ip_tunnel_parm parms) +static bool mlxsw_sp_ipip_parms4_has_okey(const struct ip_tunnel_parm *parms) +{ + return !!(parms->o_flags & TUNNEL_KEY); +} + +static bool mlxsw_sp_ipip_parms6_has_okey(const struct __ip6_tnl_parm *parms) +{ + return !!(parms->o_flags & TUNNEL_KEY); +} + +static u32 mlxsw_sp_ipip_parms4_ikey(const struct ip_tunnel_parm *parms) { return mlxsw_sp_ipip_parms4_has_ikey(parms) ? - be32_to_cpu(parms.i_key) : 0; + be32_to_cpu(parms->i_key) : 0; } -static u32 mlxsw_sp_ipip_parms4_okey(struct ip_tunnel_parm parms) +static u32 mlxsw_sp_ipip_parms6_ikey(const struct __ip6_tnl_parm *parms) +{ + return mlxsw_sp_ipip_parms6_has_ikey(parms) ? + be32_to_cpu(parms->i_key) : 0; +} + +static u32 mlxsw_sp_ipip_parms4_okey(const struct ip_tunnel_parm *parms) { return mlxsw_sp_ipip_parms4_has_okey(parms) ? - be32_to_cpu(parms.o_key) : 0; + be32_to_cpu(parms->o_key) : 0; +} + +static u32 mlxsw_sp_ipip_parms6_okey(const struct __ip6_tnl_parm *parms) +{ + return mlxsw_sp_ipip_parms6_has_okey(parms) ? + be32_to_cpu(parms->o_key) : 0; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_saddr(struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms4_saddr(const struct ip_tunnel_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.saddr }; + return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.saddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms6_saddr(struct __ip6_tnl_parm parms) +mlxsw_sp_ipip_parms6_saddr(const struct __ip6_tnl_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr6 = parms.laddr }; + return (union mlxsw_sp_l3addr) { .addr6 = parms->laddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms4_daddr(struct ip_tunnel_parm parms) +mlxsw_sp_ipip_parms4_daddr(const struct ip_tunnel_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr4 = parms.iph.daddr }; + return (union mlxsw_sp_l3addr) { .addr4 = parms->iph.daddr }; } static union mlxsw_sp_l3addr -mlxsw_sp_ipip_parms6_daddr(struct __ip6_tnl_parm parms) +mlxsw_sp_ipip_parms6_daddr(const struct __ip6_tnl_parm *parms) { - return (union mlxsw_sp_l3addr) { .addr6 = parms.raddr }; + return (union mlxsw_sp_l3addr) { .addr6 = parms->raddr }; } union mlxsw_sp_l3addr @@ -80,10 +102,10 @@ mlxsw_sp_ipip_netdev_saddr(enum mlxsw_sp_l3proto proto, switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_saddr(parms4); + return mlxsw_sp_ipip_parms4_saddr(&parms4); case MLXSW_SP_L3_PROTO_IPV6: parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); - return mlxsw_sp_ipip_parms6_saddr(parms6); + return mlxsw_sp_ipip_parms6_saddr(&parms6); } WARN_ON(1); @@ -95,7 +117,7 @@ static __be32 mlxsw_sp_ipip_netdev_daddr4(const struct net_device *ol_dev) struct ip_tunnel_parm parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_daddr(parms4).addr4; + return mlxsw_sp_ipip_parms4_daddr(&parms4).addr4; } static union mlxsw_sp_l3addr @@ -108,10 +130,10 @@ mlxsw_sp_ipip_netdev_daddr(enum mlxsw_sp_l3proto proto, switch (proto) { case MLXSW_SP_L3_PROTO_IPV4: parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - return mlxsw_sp_ipip_parms4_daddr(parms4); + return mlxsw_sp_ipip_parms4_daddr(&parms4); case MLXSW_SP_L3_PROTO_IPV6: parms6 = mlxsw_sp_ipip_netdev_parms6(ol_dev); - return mlxsw_sp_ipip_parms6_daddr(parms6); + return mlxsw_sp_ipip_parms6_daddr(&parms6); } WARN_ON(1); @@ -125,6 +147,21 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr) return !memcmp(&addr, &naddr, sizeof(naddr)); } +static struct mlxsw_sp_ipip_parms +mlxsw_sp_ipip_netdev_parms_init_gre4(const struct net_device *ol_dev) +{ + struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); + + return (struct mlxsw_sp_ipip_parms) { + .proto = MLXSW_SP_L3_PROTO_IPV4, + .saddr = mlxsw_sp_ipip_parms4_saddr(&parms), + .daddr = mlxsw_sp_ipip_parms4_daddr(&parms), + .link = parms.link, + .ikey = mlxsw_sp_ipip_parms4_ikey(&parms), + .okey = mlxsw_sp_ipip_parms4_okey(&parms), + }; +} + static int mlxsw_sp_ipip_nexthop_update_gre4(struct mlxsw_sp *mlxsw_sp, u32 adj_index, struct mlxsw_sp_ipip_entry *ipip_entry, @@ -158,8 +195,8 @@ mlxsw_sp_ipip_decap_config_gre4(struct mlxsw_sp *mlxsw_sp, u32 ikey; parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - has_ikey = mlxsw_sp_ipip_parms4_has_ikey(parms); - ikey = mlxsw_sp_ipip_parms4_ikey(parms); + has_ikey = mlxsw_sp_ipip_parms4_has_ikey(&parms); + ikey = mlxsw_sp_ipip_parms4_ikey(&parms); mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id); @@ -218,12 +255,12 @@ mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, struct ip_tunnel_parm parms = mlxsw_sp_ipip_netdev_parms4(ol_dev); enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; - lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(parms) ? + lb_ipipt = mlxsw_sp_ipip_parms4_has_okey(&parms) ? MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; return (struct mlxsw_sp_rif_ipip_lb_config){ .lb_ipipt = lb_ipipt, - .okey = mlxsw_sp_ipip_parms4_okey(parms), + .okey = mlxsw_sp_ipip_parms4_okey(&parms), .ul_protocol = MLXSW_SP_L3_PROTO_IPV4, .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV4, ol_dev), @@ -231,48 +268,39 @@ mlxsw_sp_ipip_ol_loopback_config_gre4(struct mlxsw_sp *mlxsw_sp, } static int -mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_ipip_entry *ipip_entry, - struct netlink_ext_ack *extack) +mlxsw_sp_ipip_ol_netdev_change_gre(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + const struct mlxsw_sp_ipip_parms *new_parms, + struct netlink_ext_ack *extack) { - union mlxsw_sp_l3addr old_saddr, new_saddr; - union mlxsw_sp_l3addr old_daddr, new_daddr; - struct ip_tunnel_parm new_parms; + const struct mlxsw_sp_ipip_parms *old_parms = &ipip_entry->parms; bool update_tunnel = false; bool update_decap = false; bool update_nhs = false; int err = 0; - new_parms = mlxsw_sp_ipip_netdev_parms4(ipip_entry->ol_dev); - - new_saddr = mlxsw_sp_ipip_parms4_saddr(new_parms); - old_saddr = mlxsw_sp_ipip_parms4_saddr(ipip_entry->parms4); - new_daddr = mlxsw_sp_ipip_parms4_daddr(new_parms); - old_daddr = mlxsw_sp_ipip_parms4_daddr(ipip_entry->parms4); - - if (!mlxsw_sp_l3addr_eq(&new_saddr, &old_saddr)) { + if (!mlxsw_sp_l3addr_eq(&new_parms->saddr, &old_parms->saddr)) { u16 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(ipip_entry->ol_dev); /* Since the local address has changed, if there is another * tunnel with a matching saddr, both need to be demoted. */ if (mlxsw_sp_ipip_demote_tunnel_by_saddr(mlxsw_sp, - MLXSW_SP_L3_PROTO_IPV4, - new_saddr, ul_tb_id, + new_parms->proto, + new_parms->saddr, + ul_tb_id, ipip_entry)) { mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); return 0; } update_tunnel = true; - } else if ((mlxsw_sp_ipip_parms4_okey(ipip_entry->parms4) != - mlxsw_sp_ipip_parms4_okey(new_parms)) || - ipip_entry->parms4.link != new_parms.link) { + } else if (old_parms->okey != new_parms->okey || + old_parms->link != new_parms->link) { update_tunnel = true; - } else if (!mlxsw_sp_l3addr_eq(&new_daddr, &old_daddr)) { + } else if (!mlxsw_sp_l3addr_eq(&new_parms->daddr, &old_parms->daddr)) { update_nhs = true; - } else if (mlxsw_sp_ipip_parms4_ikey(ipip_entry->parms4) != - mlxsw_sp_ipip_parms4_ikey(new_parms)) { + } else if (old_parms->ikey != new_parms->ikey) { update_decap = true; } @@ -288,23 +316,308 @@ mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, err = __mlxsw_sp_ipip_entry_update_tunnel(mlxsw_sp, ipip_entry, false, false, false, extack); + if (err) + return err; - ipip_entry->parms4 = new_parms; - return err; + ipip_entry->parms = *new_parms; + return 0; +} + +static int +mlxsw_sp_ipip_ol_netdev_change_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_ipip_parms new_parms; + + new_parms = mlxsw_sp_ipip_netdev_parms_init_gre4(ipip_entry->ol_dev); + return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); +} + +static int +mlxsw_sp_ipip_rem_addr_set_gre4(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + return 0; +} + +static void +mlxsw_sp_ipip_rem_addr_unset_gre4(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ } static const struct mlxsw_sp_ipip_ops mlxsw_sp_ipip_gre4_ops = { .dev_type = ARPHRD_IPGRE, .ul_proto = MLXSW_SP_L3_PROTO_IPV4, + .inc_parsing_depth = false, + .parms_init = mlxsw_sp_ipip_netdev_parms_init_gre4, .nexthop_update = mlxsw_sp_ipip_nexthop_update_gre4, .decap_config = mlxsw_sp_ipip_decap_config_gre4, .can_offload = mlxsw_sp_ipip_can_offload_gre4, .ol_loopback_config = mlxsw_sp_ipip_ol_loopback_config_gre4, .ol_netdev_change = mlxsw_sp_ipip_ol_netdev_change_gre4, + .rem_ip_addr_set = mlxsw_sp_ipip_rem_addr_set_gre4, + .rem_ip_addr_unset = mlxsw_sp_ipip_rem_addr_unset_gre4, }; -const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[] = { +static struct mlxsw_sp_ipip_parms +mlxsw_sp1_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) +{ + struct mlxsw_sp_ipip_parms parms = {0}; + + WARN_ON_ONCE(1); + return parms; +} + +static int +mlxsw_sp1_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry, + bool force, char *ratr_pl) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int +mlxsw_sp1_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static bool mlxsw_sp1_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + return false; +} + +static struct mlxsw_sp_rif_ipip_lb_config +mlxsw_sp1_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct mlxsw_sp_rif_ipip_lb_config config = {0}; + + WARN_ON_ONCE(1); + return config; +} + +static int +mlxsw_sp1_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static int +mlxsw_sp1_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + WARN_ON_ONCE(1); + return -EINVAL; +} + +static void +mlxsw_sp1_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ + WARN_ON_ONCE(1); +} + +static const struct mlxsw_sp_ipip_ops mlxsw_sp1_ipip_gre6_ops = { + .dev_type = ARPHRD_IP6GRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV6, + .inc_parsing_depth = true, + .parms_init = mlxsw_sp1_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp1_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp1_ipip_decap_config_gre6, + .can_offload = mlxsw_sp1_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp1_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp1_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp1_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp1_ipip_rem_addr_unset_gre6, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[] = { [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, + [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp1_ipip_gre6_ops, +}; + +static struct mlxsw_sp_ipip_parms +mlxsw_sp2_ipip_netdev_parms_init_gre6(const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); + + return (struct mlxsw_sp_ipip_parms) { + .proto = MLXSW_SP_L3_PROTO_IPV6, + .saddr = mlxsw_sp_ipip_parms6_saddr(&parms), + .daddr = mlxsw_sp_ipip_parms6_daddr(&parms), + .link = parms.link, + .ikey = mlxsw_sp_ipip_parms6_ikey(&parms), + .okey = mlxsw_sp_ipip_parms6_okey(&parms), + }; +} + +static int +mlxsw_sp2_ipip_nexthop_update_gre6(struct mlxsw_sp *mlxsw_sp, u32 adj_index, + struct mlxsw_sp_ipip_entry *ipip_entry, + bool force, char *ratr_pl) +{ + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + enum mlxsw_reg_ratr_op op; + + op = force ? MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY : + MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY_ON_ACTIVITY; + mlxsw_reg_ratr_pack(ratr_pl, op, true, MLXSW_REG_RATR_TYPE_IPIP, + adj_index, rif_index); + mlxsw_reg_ratr_ipip6_entry_pack(ratr_pl, + ipip_entry->dip_kvdl_index); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); +} + +static int +mlxsw_sp2_ipip_decap_config_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + u32 tunnel_index) +{ + u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb); + u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb); + char rtdp_pl[MLXSW_REG_RTDP_LEN]; + struct __ip6_tnl_parm parms; + unsigned int type_check; + bool has_ikey; + u32 ikey; + + parms = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); + has_ikey = mlxsw_sp_ipip_parms6_has_ikey(&parms); + ikey = mlxsw_sp_ipip_parms6_ikey(&parms); + + mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index); + mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id); + + type_check = has_ikey ? + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY : + MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE; + + /* Linux demuxes tunnels based on packet SIP (which must match tunnel + * remote IP). Thus configure decap so that it filters out packets that + * are not IPv6 or have the wrong SIP. IPIP_DECAP_ERROR trap is + * generated for packets that fail this criterion. Linux then handles + * such packets in slow path and generates ICMP destination unreachable. + */ + mlxsw_reg_rtdp_ipip6_pack(rtdp_pl, rif_index, + MLXSW_REG_RTDP_IPIP_SIP_CHECK_FILTER_IPV6, + type_check, has_ikey, + ipip_entry->dip_kvdl_index, ikey); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl); +} + +static bool mlxsw_sp2_ipip_can_offload_gre6(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm tparm = mlxsw_sp_ipip_netdev_parms6(ol_dev); + bool inherit_tos = tparm.flags & IP6_TNL_F_USE_ORIG_TCLASS; + bool inherit_ttl = tparm.hop_limit == 0; + __be16 okflags = TUNNEL_KEY; /* We can't offload any other features. */ + + return (tparm.i_flags & ~okflags) == 0 && + (tparm.o_flags & ~okflags) == 0 && + inherit_ttl && inherit_tos && + mlxsw_sp_ipip_tunnel_complete(MLXSW_SP_L3_PROTO_IPV6, ol_dev); +} + +static struct mlxsw_sp_rif_ipip_lb_config +mlxsw_sp2_ipip_ol_loopback_config_gre6(struct mlxsw_sp *mlxsw_sp, + const struct net_device *ol_dev) +{ + struct __ip6_tnl_parm parms = mlxsw_sp_ipip_netdev_parms6(ol_dev); + enum mlxsw_reg_ritr_loopback_ipip_type lb_ipipt; + + lb_ipipt = mlxsw_sp_ipip_parms6_has_okey(&parms) ? + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_KEY_IN_IP : + MLXSW_REG_RITR_LOOPBACK_IPIP_TYPE_IP_IN_GRE_IN_IP; + return (struct mlxsw_sp_rif_ipip_lb_config){ + .lb_ipipt = lb_ipipt, + .okey = mlxsw_sp_ipip_parms6_okey(&parms), + .ul_protocol = MLXSW_SP_L3_PROTO_IPV6, + .saddr = mlxsw_sp_ipip_netdev_saddr(MLXSW_SP_L3_PROTO_IPV6, + ol_dev), + }; +} + +static int +mlxsw_sp2_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry, + struct netlink_ext_ack *extack) +{ + struct mlxsw_sp_ipip_parms new_parms; + + new_parms = mlxsw_sp2_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); + return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); +} + +static int +mlxsw_sp2_ipip_rem_addr_set_gre6(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) +{ + char rips_pl[MLXSW_REG_RIPS_LEN]; + struct __ip6_tnl_parm parms6; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, + MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + &ipip_entry->dip_kvdl_index); + if (err) + return err; + + parms6 = mlxsw_sp_ipip_netdev_parms6(ipip_entry->ol_dev); + mlxsw_reg_rips_pack(rips_pl, ipip_entry->dip_kvdl_index, + &parms6.raddr); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rips), rips_pl); + if (err) + goto err_rips_write; + + return 0; + +err_rips_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + ipip_entry->dip_kvdl_index); + return err; +} + +static void +mlxsw_sp2_ipip_rem_addr_unset_gre6(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry) +{ + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_IPV6_ADDRESS, 1, + ipip_entry->dip_kvdl_index); +} + +static const struct mlxsw_sp_ipip_ops mlxsw_sp2_ipip_gre6_ops = { + .dev_type = ARPHRD_IP6GRE, + .ul_proto = MLXSW_SP_L3_PROTO_IPV6, + .inc_parsing_depth = true, + .parms_init = mlxsw_sp2_ipip_netdev_parms_init_gre6, + .nexthop_update = mlxsw_sp2_ipip_nexthop_update_gre6, + .decap_config = mlxsw_sp2_ipip_decap_config_gre6, + .can_offload = mlxsw_sp2_ipip_can_offload_gre6, + .ol_loopback_config = mlxsw_sp2_ipip_ol_loopback_config_gre6, + .ol_netdev_change = mlxsw_sp2_ipip_ol_netdev_change_gre6, + .rem_ip_addr_set = mlxsw_sp2_ipip_rem_addr_set_gre6, + .rem_ip_addr_unset = mlxsw_sp2_ipip_rem_addr_unset_gre6, +}; + +const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[] = { + [MLXSW_SP_IPIP_TYPE_GRE4] = &mlxsw_sp_ipip_gre4_ops, + [MLXSW_SP_IPIP_TYPE_GRE6] = &mlxsw_sp2_ipip_gre6_ops, }; static int mlxsw_sp_ipip_ecn_encap_init_one(struct mlxsw_sp *mlxsw_sp, @@ -363,3 +676,22 @@ int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp) return 0; } + +struct net_device * +mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) +{ + struct net *net = dev_net(ol_dev); + struct ip_tunnel *tun4; + struct ip6_tnl *tun6; + + switch (ol_dev->type) { + case ARPHRD_IPGRE: + tun4 = netdev_priv(ol_dev); + return dev_get_by_index_rcu(net, tun4->parms.link); + case ARPHRD_IP6GRE: + tun6 = netdev_priv(ol_dev); + return dev_get_by_index_rcu(net, tun6->parms.link); + default: + return NULL; + } +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h index f0837b42d1d62e..8cc259dcc8d098 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h @@ -7,6 +7,7 @@ #include "spectrum_router.h" #include <net/ip_fib.h> #include <linux/if_tunnel.h> +#include <net/ip6_tunnel.h> struct ip_tunnel_parm mlxsw_sp_ipip_netdev_parms4(const struct net_device *ol_dev); @@ -21,23 +22,36 @@ bool mlxsw_sp_l3addr_is_zero(union mlxsw_sp_l3addr addr); enum mlxsw_sp_ipip_type { MLXSW_SP_IPIP_TYPE_GRE4, + MLXSW_SP_IPIP_TYPE_GRE6, MLXSW_SP_IPIP_TYPE_MAX, }; +struct mlxsw_sp_ipip_parms { + enum mlxsw_sp_l3proto proto; + union mlxsw_sp_l3addr saddr; + union mlxsw_sp_l3addr daddr; + int link; + u32 ikey; + u32 okey; +}; + struct mlxsw_sp_ipip_entry { enum mlxsw_sp_ipip_type ipipt; struct net_device *ol_dev; /* Overlay. */ struct mlxsw_sp_rif_ipip_lb *ol_lb; struct mlxsw_sp_fib_entry *decap_fib_entry; struct list_head ipip_list_node; - union { - struct ip_tunnel_parm parms4; - }; + struct mlxsw_sp_ipip_parms parms; + u32 dip_kvdl_index; }; struct mlxsw_sp_ipip_ops { int dev_type; enum mlxsw_sp_l3proto ul_proto; /* Underlay. */ + bool inc_parsing_depth; + + struct mlxsw_sp_ipip_parms + (*parms_init)(const struct net_device *ol_dev); int (*nexthop_update)(struct mlxsw_sp *mlxsw_sp, u32 adj_index, struct mlxsw_sp_ipip_entry *ipip_entry, @@ -58,8 +72,13 @@ struct mlxsw_sp_ipip_ops { int (*ol_netdev_change)(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct netlink_ext_ack *extack); + int (*rem_ip_addr_set)(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry); + void (*rem_ip_addr_unset)(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_ipip_entry *ipip_entry); }; -extern const struct mlxsw_sp_ipip_ops *mlxsw_sp_ipip_ops_arr[]; +extern const struct mlxsw_sp_ipip_ops *mlxsw_sp1_ipip_ops_arr[]; +extern const struct mlxsw_sp_ipip_ops *mlxsw_sp2_ipip_ops_arr[]; #endif /* _MLXSW_IPIP_H_*/ diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 19bb3ca0515e21..1e141b5944cd4f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -115,6 +115,7 @@ struct mlxsw_sp_rif_ops { struct mlxsw_sp_router_ops { int (*init)(struct mlxsw_sp *mlxsw_sp); + int (*ipips_init)(struct mlxsw_sp *mlxsw_sp); }; static struct mlxsw_sp_rif * @@ -1055,22 +1056,13 @@ static void mlxsw_sp_vrs_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->router->vrs); } -static struct net_device * -__mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev) -{ - struct ip_tunnel *tun = netdev_priv(ol_dev); - struct net *net = dev_net(ol_dev); - - return dev_get_by_index_rcu(net, tun->parms.link); -} - u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev) { struct net_device *d; u32 tb_id; rcu_read_lock(); - d = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + d = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); if (d) tb_id = l3mdev_fib_table(d) ? : RT_TABLE_MAIN; else @@ -1116,6 +1108,7 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; struct mlxsw_sp_ipip_entry *ret = NULL; + int err; ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; ipip_entry = kzalloc(sizeof(*ipip_entry), GFP_KERNEL); @@ -1131,26 +1124,30 @@ mlxsw_sp_ipip_entry_alloc(struct mlxsw_sp *mlxsw_sp, ipip_entry->ipipt = ipipt; ipip_entry->ol_dev = ol_dev; + ipip_entry->parms = ipip_ops->parms_init(ol_dev); - switch (ipip_ops->ul_proto) { - case MLXSW_SP_L3_PROTO_IPV4: - ipip_entry->parms4 = mlxsw_sp_ipip_netdev_parms4(ol_dev); - break; - case MLXSW_SP_L3_PROTO_IPV6: - WARN_ON(1); - break; + err = ipip_ops->rem_ip_addr_set(mlxsw_sp, ipip_entry); + if (err) { + ret = ERR_PTR(err); + goto err_rem_ip_addr_set; } return ipip_entry; +err_rem_ip_addr_set: + mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); err_ol_ipip_lb_create: kfree(ipip_entry); return ret; } -static void -mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp_ipip_entry *ipip_entry) +static void mlxsw_sp_ipip_entry_dealloc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_ipip_entry *ipip_entry) { + const struct mlxsw_sp_ipip_ops *ipip_ops = + mlxsw_sp->router->ipip_ops_arr[ipip_entry->ipipt]; + + ipip_ops->rem_ip_addr_unset(mlxsw_sp, ipip_entry); mlxsw_sp_rif_destroy(&ipip_entry->ol_lb->common); kfree(ipip_entry); } @@ -1174,6 +1171,32 @@ mlxsw_sp_ipip_entry_saddr_matches(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_l3addr_eq(&tun_saddr, &saddr); } +static int mlxsw_sp_ipip_decap_parsing_depth_inc(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt) +{ + const struct mlxsw_sp_ipip_ops *ipip_ops; + + ipip_ops = mlxsw_sp->router->ipip_ops_arr[ipipt]; + + /* Not all tunnels require to increase the default pasing depth + * (96 bytes). + */ + if (ipip_ops->inc_parsing_depth) + return mlxsw_sp_parsing_depth_inc(mlxsw_sp); + + return 0; +} + +static void mlxsw_sp_ipip_decap_parsing_depth_dec(struct mlxsw_sp *mlxsw_sp, + enum mlxsw_sp_ipip_type ipipt) +{ + const struct mlxsw_sp_ipip_ops *ipip_ops = + mlxsw_sp->router->ipip_ops_arr[ipipt]; + + if (ipip_ops->inc_parsing_depth) + mlxsw_sp_parsing_depth_dec(mlxsw_sp); +} + static int mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, @@ -1187,18 +1210,32 @@ mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp, if (err) return err; + err = mlxsw_sp_ipip_decap_parsing_depth_inc(mlxsw_sp, + ipip_entry->ipipt); + if (err) + goto err_parsing_depth_inc; + ipip_entry->decap_fib_entry = fib_entry; fib_entry->decap.ipip_entry = ipip_entry; fib_entry->decap.tunnel_index = tunnel_index; + return 0; + +err_parsing_depth_inc: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + fib_entry->decap.tunnel_index); + return err; } static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry) { + enum mlxsw_sp_ipip_type ipipt = fib_entry->decap.ipip_entry->ipipt; + /* Unlink this node from the IPIP entry that it's the decap entry of. */ fib_entry->decap.ipip_entry->decap_fib_entry = NULL; fib_entry->decap.ipip_entry = NULL; + mlxsw_sp_ipip_decap_parsing_depth_dec(mlxsw_sp, ipipt); mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, fib_entry->decap.tunnel_index); } @@ -1309,6 +1346,11 @@ mlxsw_sp_ipip_entry_find_decap(struct mlxsw_sp *mlxsw_sp, saddr_len = 4; saddr_prefix_len = 32; break; + case MLXSW_SP_L3_PROTO_IPV6: + saddrp = &saddr.addr6; + saddr_len = 16; + saddr_prefix_len = 128; + break; default: WARN_ON(1); return NULL; @@ -1345,7 +1387,7 @@ mlxsw_sp_ipip_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry) { list_del(&ipip_entry->ipip_list_node); - mlxsw_sp_ipip_entry_dealloc(ipip_entry); + mlxsw_sp_ipip_entry_dealloc(mlxsw_sp, ipip_entry); } static bool @@ -1450,7 +1492,7 @@ mlxsw_sp_ipip_entry_find_by_ul_dev(const struct mlxsw_sp *mlxsw_sp, struct net_device *ipip_ul_dev; rcu_read_lock(); - ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ipip_ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); rcu_read_unlock(); if (ipip_ul_dev == ul_dev) @@ -1536,23 +1578,34 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id, u16 ul_rif_id, bool enable) { struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config; + enum mlxsw_reg_ritr_loopback_ipip_options ipip_options; struct mlxsw_sp_rif *rif = &lb_rif->common; struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp; char ritr_pl[MLXSW_REG_RITR_LEN]; + struct in6_addr *saddr6; u32 saddr4; + ipip_options = MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET; switch (lb_cf.ul_protocol) { case MLXSW_SP_L3_PROTO_IPV4: saddr4 = be32_to_cpu(lb_cf.saddr.addr4); mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, rif->rif_index, rif->vr_id, rif->dev->mtu); mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt, - MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET, - ul_vr_id, ul_rif_id, saddr4, lb_cf.okey); + ipip_options, ul_vr_id, + ul_rif_id, saddr4, + lb_cf.okey); break; case MLXSW_SP_L3_PROTO_IPV6: - return -EAFNOSUPPORT; + saddr6 = &lb_cf.saddr.addr6; + mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF, + rif->rif_index, rif->vr_id, rif->dev->mtu); + mlxsw_reg_ritr_loopback_ipip6_pack(ritr_pl, lb_cf.lb_ipipt, + ipip_options, ul_vr_id, + ul_rif_id, saddr6, + lb_cf.okey); + break; } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); @@ -1827,7 +1880,7 @@ static void mlxsw_sp_ipip_demote_tunnel_by_ul_netdev(struct mlxsw_sp *mlxsw_sp, struct net_device *ipip_ul_dev; rcu_read_lock(); - ipip_ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ipip_ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); rcu_read_unlock(); if (ipip_ul_dev == ul_dev) mlxsw_sp_ipip_entry_demote_tunnel(mlxsw_sp, ipip_entry); @@ -4152,7 +4205,7 @@ static bool mlxsw_sp_ipip_netdev_ul_up(struct net_device *ol_dev) bool is_up; rcu_read_lock(); - ul_dev = __mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); + ul_dev = mlxsw_sp_ipip_netdev_ul_dev_get(ol_dev); is_up = ul_dev ? (ul_dev->flags & IFF_UP) : true; rcu_read_unlock(); @@ -4376,6 +4429,66 @@ static void mlxsw_sp_nexthop_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, } } +static int mlxsw_sp_adj_trap_entry_init(struct mlxsw_sp *mlxsw_sp) +{ + enum mlxsw_reg_ratr_trap_action trap_action; + char ratr_pl[MLXSW_REG_RATR_LEN]; + int err; + + err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + &mlxsw_sp->router->adj_trap_index); + if (err) + return err; + + trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP; + mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, + MLXSW_REG_RATR_TYPE_ETHERNET, + mlxsw_sp->router->adj_trap_index, + mlxsw_sp->router->lb_rif_index); + mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); + mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); + if (err) + goto err_ratr_write; + + return 0; + +err_ratr_write: + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_trap_index); + return err; +} + +static void mlxsw_sp_adj_trap_entry_fini(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, + mlxsw_sp->router->adj_trap_index); +} + +static int mlxsw_sp_nexthop_group_inc(struct mlxsw_sp *mlxsw_sp) +{ + int err; + + if (refcount_inc_not_zero(&mlxsw_sp->router->num_groups)) + return 0; + + err = mlxsw_sp_adj_trap_entry_init(mlxsw_sp); + if (err) + return err; + + refcount_set(&mlxsw_sp->router->num_groups, 1); + + return 0; +} + +static void mlxsw_sp_nexthop_group_dec(struct mlxsw_sp *mlxsw_sp) +{ + if (!refcount_dec_and_test(&mlxsw_sp->router->num_groups)) + return; + + mlxsw_sp_adj_trap_entry_fini(mlxsw_sp); +} + static void mlxsw_sp_nh_grp_activity_get(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_nexthop_group *nh_grp, @@ -4790,6 +4903,9 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop_obj_init; } + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) { NL_SET_ERR_MSG_MOD(info->extack, "Failed to write adjacency entries to the device"); @@ -4808,6 +4924,8 @@ mlxsw_sp_nexthop_obj_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop_obj_init: for (i--; i >= 0; i--) { @@ -4832,6 +4950,7 @@ mlxsw_sp_nexthop_obj_group_info_fini(struct mlxsw_sp *mlxsw_sp, cancel_delayed_work(&router->nh_grp_activity_dw); } + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -5223,6 +5342,9 @@ mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop4_init; } + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) goto err_group_refresh; @@ -5230,6 +5352,8 @@ mlxsw_sp_nexthop4_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop4_init: for (i--; i >= 0; i--) { @@ -5247,6 +5371,7 @@ mlxsw_sp_nexthop4_group_info_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; int i; + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -5725,41 +5850,6 @@ static int mlxsw_sp_fib_entry_commit(struct mlxsw_sp *mlxsw_sp, return err; } -static int mlxsw_sp_adj_discard_write(struct mlxsw_sp *mlxsw_sp) -{ - enum mlxsw_reg_ratr_trap_action trap_action; - char ratr_pl[MLXSW_REG_RATR_LEN]; - int err; - - if (mlxsw_sp->router->adj_discard_index_valid) - return 0; - - err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - &mlxsw_sp->router->adj_discard_index); - if (err) - return err; - - trap_action = MLXSW_REG_RATR_TRAP_ACTION_TRAP; - mlxsw_reg_ratr_pack(ratr_pl, MLXSW_REG_RATR_OP_WRITE_WRITE_ENTRY, true, - MLXSW_REG_RATR_TYPE_ETHERNET, - mlxsw_sp->router->adj_discard_index, - mlxsw_sp->router->lb_rif_index); - mlxsw_reg_ratr_trap_action_set(ratr_pl, trap_action); - mlxsw_reg_ratr_trap_id_set(ratr_pl, MLXSW_TRAP_ID_RTR_EGRESS0); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ratr), ratr_pl); - if (err) - goto err_ratr_write; - - mlxsw_sp->router->adj_discard_index_valid = true; - - return 0; - -err_ratr_write: - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - mlxsw_sp->router->adj_discard_index); - return err; -} - static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry_op_ctx *op_ctx, struct mlxsw_sp_fib_entry *fib_entry, @@ -5772,7 +5862,6 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, u16 trap_id = 0; u32 adjacency_index = 0; u16 ecmp_size = 0; - int err; /* In case the nexthop group adjacency index is valid, use it * with provided ECMP size. Otherwise, setup trap and pass @@ -5783,11 +5872,8 @@ static int mlxsw_sp_fib_entry_op_remote(struct mlxsw_sp *mlxsw_sp, adjacency_index = nhgi->adj_index; ecmp_size = nhgi->ecmp_size; } else if (!nhgi->adj_index_valid && nhgi->count && nhgi->nh_rif) { - err = mlxsw_sp_adj_discard_write(mlxsw_sp); - if (err) - return err; trap_action = MLXSW_REG_RALUE_TRAP_ACTION_NOP; - adjacency_index = mlxsw_sp->router->adj_discard_index; + adjacency_index = mlxsw_sp->router->adj_trap_index; ecmp_size = 1; } else { trap_action = MLXSW_REG_RALUE_TRAP_ACTION_TRAP; @@ -6036,8 +6122,8 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, } static void -mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry) +mlxsw_sp_fib_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry) { switch (fib_entry->type) { case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: @@ -6048,6 +6134,13 @@ mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, } } +static void +mlxsw_sp_fib4_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib4_entry *fib4_entry) +{ + mlxsw_sp_fib_entry_type_unset(mlxsw_sp, &fib4_entry->common); +} + static struct mlxsw_sp_fib4_entry * mlxsw_sp_fib4_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, @@ -6108,7 +6201,7 @@ static void mlxsw_sp_fib4_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node = fib4_entry->common.fib_node; fib_info_put(fib4_entry->fi); - mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, &fib4_entry->common); + mlxsw_sp_fib4_entry_type_unset(mlxsw_sp, fib4_entry); mlxsw_sp_nexthop_group_vr_unlink(fib4_entry->common.nh_group, fib_node->fib); mlxsw_sp_nexthop4_group_put(mlxsw_sp, &fib4_entry->common); @@ -6641,6 +6734,9 @@ mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_rt6 = list_next_entry(mlxsw_sp_rt6, list); } nh_grp->nhgi = nhgi; + err = mlxsw_sp_nexthop_group_inc(mlxsw_sp); + if (err) + goto err_group_inc; err = mlxsw_sp_nexthop_group_refresh(mlxsw_sp, nh_grp); if (err) goto err_group_refresh; @@ -6648,6 +6744,8 @@ mlxsw_sp_nexthop6_group_info_init(struct mlxsw_sp *mlxsw_sp, return 0; err_group_refresh: + mlxsw_sp_nexthop_group_dec(mlxsw_sp); +err_group_inc: i = nhgi->count; err_nexthop6_init: for (i--; i >= 0; i--) { @@ -6665,6 +6763,7 @@ mlxsw_sp_nexthop6_group_info_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group_info *nhgi = nh_grp->nhgi; int i; + mlxsw_sp_nexthop_group_dec(mlxsw_sp); for (i = nhgi->count - 1; i >= 0; i--) { struct mlxsw_sp_nexthop *nh = &nhgi->nexthops[i]; @@ -6888,11 +6987,38 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_nexthop6_group_update(mlxsw_sp, op_ctx, fib6_entry); } -static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_fib_entry *fib_entry, - const struct fib6_info *rt) +static int +mlxsw_sp_fib6_entry_type_set_local(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + const struct fib6_info *rt) { - if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) + struct mlxsw_sp_nexthop_group_info *nhgi = fib_entry->nh_group->nhgi; + union mlxsw_sp_l3addr dip = { .addr6 = rt->fib6_dst.addr }; + int ifindex = nhgi->nexthops[0].ifindex; + struct mlxsw_sp_ipip_entry *ipip_entry; + + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + ipip_entry = mlxsw_sp_ipip_entry_find_by_decap(mlxsw_sp, ifindex, + MLXSW_SP_L3_PROTO_IPV6, + dip); + + if (ipip_entry && ipip_entry->ol_dev->flags & IFF_UP) { + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP; + return mlxsw_sp_fib_entry_decap_init(mlxsw_sp, fib_entry, + ipip_entry); + } + + return 0; +} + +static int mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + const struct fib6_info *rt) +{ + if (rt->fib6_flags & RTF_LOCAL) + return mlxsw_sp_fib6_entry_type_set_local(mlxsw_sp, fib_entry, + rt); + if (rt->fib6_flags & RTF_ANYCAST) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; else if (rt->fib6_type == RTN_BLACKHOLE) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; @@ -6902,6 +7028,8 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; else fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; + + return 0; } static void @@ -6959,12 +7087,16 @@ mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_nexthop_group_vr_link; - mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); + err = mlxsw_sp_fib6_entry_type_set(mlxsw_sp, fib_entry, rt_arr[0]); + if (err) + goto err_fib6_entry_type_set; fib_entry->fib_node = fib_node; return fib6_entry; +err_fib6_entry_type_set: + mlxsw_sp_nexthop_group_vr_unlink(fib_entry->nh_group, fib_node->fib); err_nexthop_group_vr_link: mlxsw_sp_nexthop6_group_put(mlxsw_sp, fib_entry); err_nexthop6_group_get: @@ -6983,11 +7115,19 @@ err_fib_entry_priv_create: return ERR_PTR(err); } +static void +mlxsw_sp_fib6_entry_type_unset(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib6_entry *fib6_entry) +{ + mlxsw_sp_fib_entry_type_unset(mlxsw_sp, &fib6_entry->common); +} + static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry) { struct mlxsw_sp_fib_node *fib_node = fib6_entry->common.fib_node; + mlxsw_sp_fib6_entry_type_unset(mlxsw_sp, fib6_entry); mlxsw_sp_nexthop_group_vr_unlink(fib6_entry->common.nh_group, fib_node->fib); mlxsw_sp_nexthop6_group_put(mlxsw_sp, &fib6_entry->common); @@ -7340,16 +7480,6 @@ static void mlxsw_sp_router_fib_flush(struct mlxsw_sp *mlxsw_sp) continue; mlxsw_sp_vr_fib_flush(mlxsw_sp, vr, MLXSW_SP_L3_PROTO_IPV6); } - - /* After flushing all the routes, it is not possible anyone is still - * using the adjacency index that is discarding packets, so free it in - * case it was allocated. - */ - if (!mlxsw_sp->router->adj_discard_index_valid) - return; - mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ, 1, - mlxsw_sp->router->adj_discard_index); - mlxsw_sp->router->adj_discard_index_valid = false; } struct mlxsw_sp_fib6_event { @@ -9447,7 +9577,6 @@ static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) { int err; - mlxsw_sp->router->ipip_ops_arr = mlxsw_sp_ipip_ops_arr; INIT_LIST_HEAD(&mlxsw_sp->router->ipip_list); err = mlxsw_sp_ipip_ecn_encap_init(mlxsw_sp); @@ -9460,6 +9589,18 @@ static int mlxsw_sp_ipips_init(struct mlxsw_sp *mlxsw_sp) return mlxsw_sp_ipip_config_tigcr(mlxsw_sp); } +static int mlxsw_sp1_ipips_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->router->ipip_ops_arr = mlxsw_sp1_ipip_ops_arr; + return mlxsw_sp_ipips_init(mlxsw_sp); +} + +static int mlxsw_sp2_ipips_init(struct mlxsw_sp *mlxsw_sp) +{ + mlxsw_sp->router->ipip_ops_arr = mlxsw_sp2_ipip_ops_arr; + return mlxsw_sp_ipips_init(mlxsw_sp); +} + static void mlxsw_sp_ipips_fini(struct mlxsw_sp *mlxsw_sp) { WARN_ON(!list_empty(&mlxsw_sp->router->ipip_list)); @@ -9874,6 +10015,7 @@ static int mlxsw_sp1_router_init(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_router_ops mlxsw_sp1_router_ops = { .init = mlxsw_sp1_router_init, + .ipips_init = mlxsw_sp1_ipips_init, }; static int mlxsw_sp2_router_init(struct mlxsw_sp *mlxsw_sp) @@ -9889,6 +10031,7 @@ static int mlxsw_sp2_router_init(struct mlxsw_sp *mlxsw_sp) const struct mlxsw_sp_router_ops mlxsw_sp2_router_ops = { .init = mlxsw_sp2_router_init, + .ipips_init = mlxsw_sp2_ipips_init, }; int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, @@ -9934,7 +10077,7 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rifs_init; - err = mlxsw_sp_ipips_init(mlxsw_sp); + err = mlxsw_sp->router_ops->ipips_init(mlxsw_sp); if (err) goto err_ipips_init; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 25d3eae6350133..1d0d28f8ff05fc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -65,8 +65,6 @@ struct mlxsw_sp_router { struct notifier_block inet6addr_nb; const struct mlxsw_sp_rif_ops **rif_ops_arr; const struct mlxsw_sp_ipip_ops **ipip_ops_arr; - u32 adj_discard_index; - bool adj_discard_index_valid; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ struct work_struct fib_event_work; @@ -82,6 +80,8 @@ struct mlxsw_sp_router { struct delayed_work nh_grp_activity_dw; struct list_head nh_res_grp_list; bool inc_parsing_depth; + refcount_t num_groups; + u32 adj_trap_index; }; struct mlxsw_sp_fib_entry_priv { @@ -226,6 +226,8 @@ static inline bool mlxsw_sp_l3addr_eq(const union mlxsw_sp_l3addr *addr1, int mlxsw_sp_ipip_ecn_encap_init(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_ipip_ecn_decap_init(struct mlxsw_sp *mlxsw_sp); +struct net_device * +mlxsw_sp_ipip_netdev_ul_dev_get(const struct net_device *ol_dev); extern const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_xm_ops; diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index ee921a99e439a2..c548e637235295 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1122,4 +1122,3 @@ module_spi_driver(encx24j600_spi_net_driver); MODULE_DESCRIPTION(DRV_NAME " ethernet driver"); MODULE_AUTHOR("Jon Ringle <jringle@gridpoint.com>"); MODULE_LICENSE("GPL"); -MODULE_ALIAS("spi:" DRV_NAME); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index cbece6e9bff27a..c6eb0b70dd3f0d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -234,8 +234,7 @@ static int sparx5_create_targets(struct sparx5 *sparx5) } iomem[idx] = devm_ioremap(sparx5->dev, iores[idx]->start, - iores[idx]->end - iores[idx]->start - + 1); + resource_size(iores[idx])); if (!iomem[idx]) { dev_err(sparx5->dev, "Unable to get switch registers: %s\n", iores[idx]->name); diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 291ae6817c2607..5d01993f6be0e4 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -1134,10 +1134,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) if (err) goto out_put_ports; - err = devlink_register(devlink); - if (err) - goto out_ocelot_deinit; - err = mscc_ocelot_init_ports(pdev, ports); if (err) goto out_ocelot_devlink_unregister; @@ -1160,6 +1156,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); of_node_put(ports); + devlink_register(devlink); dev_info(&pdev->dev, "Ocelot switch probed\n"); @@ -1169,8 +1166,6 @@ out_ocelot_release_ports: mscc_ocelot_release_ports(ocelot); mscc_ocelot_teardown_devlink_ports(ocelot); out_ocelot_devlink_unregister: - devlink_unregister(devlink); -out_ocelot_deinit: ocelot_deinit(ocelot); out_put_ports: of_node_put(ports); @@ -1183,11 +1178,11 @@ static int mscc_ocelot_remove(struct platform_device *pdev) { struct ocelot *ocelot = platform_get_drvdata(pdev); + devlink_unregister(ocelot->devlink); ocelot_deinit_timestamp(ocelot); ocelot_devlink_sb_unregister(ocelot); mscc_ocelot_release_ports(ocelot); mscc_ocelot_teardown_devlink_ports(ocelot); - devlink_unregister(ocelot->devlink); ocelot_deinit(ocelot); unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); unregister_switchdev_notifier(&ocelot_switchdev_nb); diff --git a/drivers/net/ethernet/netronome/nfp/devlink_param.c b/drivers/net/ethernet/netronome/nfp/devlink_param.c index 36491835ac6553..db297ee4d7ad10 100644 --- a/drivers/net/ethernet/netronome/nfp/devlink_param.c +++ b/drivers/net/ethernet/netronome/nfp/devlink_param.c @@ -233,13 +233,8 @@ int nfp_devlink_params_register(struct nfp_pf *pf) if (err <= 0) return err; - err = devlink_params_register(devlink, nfp_devlink_params, - ARRAY_SIZE(nfp_devlink_params)); - if (err) - return err; - - devlink_params_publish(devlink); - return 0; + return devlink_params_register(devlink, nfp_devlink_params, + ARRAY_SIZE(nfp_devlink_params)); } void nfp_devlink_params_unregister(struct nfp_pf *pf) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index d10a938013445f..5fbb7c613ff16a 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -701,10 +701,6 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_unmap; - err = devlink_register(devlink); - if (err) - goto err_app_clean; - err = nfp_shared_buf_register(pf); if (err) goto err_devlink_unreg; @@ -734,6 +730,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf) goto err_stop_app; mutex_unlock(&pf->lock); + devlink_register(devlink); return 0; @@ -751,8 +748,6 @@ err_shared_buf_unreg: nfp_shared_buf_unregister(pf); err_devlink_unreg: cancel_work_sync(&pf->port_refresh_work); - devlink_unregister(devlink); -err_app_clean: nfp_net_pf_app_clean(pf); err_unmap: nfp_net_pci_unmap_mem(pf); @@ -763,6 +758,7 @@ void nfp_net_pci_remove(struct nfp_pf *pf) { struct nfp_net *nn, *next; + devlink_unregister(priv_to_devlink(pf)); mutex_lock(&pf->lock); list_for_each_entry_safe(nn, next, &pf->vnics, vnic_list) { if (!nfp_net_is_data_vnic(nn)) @@ -779,7 +775,6 @@ void nfp_net_pci_remove(struct nfp_pf *pf) nfp_devlink_params_unregister(pf); nfp_shared_buf_unregister(pf); - devlink_unregister(priv_to_devlink(pf)); nfp_net_pf_free_irqs(pf); nfp_net_pf_app_clean(pf); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 3b8e675087dea1..369f6ae700c7d8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -499,8 +499,7 @@ struct nfp_reprs *nfp_reprs_alloc(unsigned int num_reprs) { struct nfp_reprs *reprs; - reprs = kzalloc(sizeof(*reprs) + - num_reprs * sizeof(struct net_device *), GFP_KERNEL); + reprs = kzalloc(struct_size(reprs, reprs, num_reprs), GFP_KERNEL); if (!reprs) return NULL; reprs->num_reprs = num_reprs; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c index c7d0e195d17607..2267da95640bed 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -82,12 +82,6 @@ int ionic_devlink_register(struct ionic *ionic) struct devlink_port_attrs attrs = {}; int err; - err = devlink_register(dl); - if (err) { - dev_warn(ionic->dev, "devlink_register failed: %d\n", err); - return err; - } - attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; devlink_port_attrs_set(&ionic->dl_port, &attrs); err = devlink_port_register(dl, &ionic->dl_port, 0); @@ -98,6 +92,7 @@ int ionic_devlink_register(struct ionic *ionic) } devlink_port_type_eth_set(&ionic->dl_port, ionic->lif->netdev); + devlink_register(dl); return 0; } @@ -105,6 +100,6 @@ void ionic_devlink_unregister(struct ionic *ionic) { struct devlink *dl = priv_to_devlink(ionic); - devlink_port_unregister(&ionic->dl_port); devlink_unregister(dl); + devlink_port_unregister(&ionic->dl_port); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index 78070682f2dff3..6bb4e165b59206 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -215,10 +215,6 @@ struct devlink *qed_devlink_register(struct qed_dev *cdev) qdevlink = devlink_priv(dl); qdevlink->cdev = cdev; - rc = devlink_register(dl); - if (rc) - goto err_free; - rc = devlink_params_register(dl, qed_devlink_params, ARRAY_SIZE(qed_devlink_params)); if (rc) @@ -229,17 +225,13 @@ struct devlink *qed_devlink_register(struct qed_dev *cdev) QED_DEVLINK_PARAM_ID_IWARP_CMT, value); - devlink_params_publish(dl); cdev->iwarp_cmt = false; qed_fw_reporters_create(dl); - + devlink_register(dl); return dl; err_unregister: - devlink_unregister(dl); - -err_free: devlink_free(dl); return ERR_PTR(rc); @@ -250,11 +242,11 @@ void qed_devlink_unregister(struct devlink *devlink) if (!devlink) return; + devlink_unregister(devlink); qed_fw_reporters_destroy(devlink); devlink_params_unregister(devlink, qed_devlink_params, ARRAY_SIZE(qed_devlink_params)); - devlink_unregister(devlink); devlink_free(devlink); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index dfaf10edfabfd4..ba8c7a31cce1fb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2763,25 +2763,6 @@ static int qed_configure_filter_mcast(struct qed_dev *cdev, return qed_filter_mcast_cmd(cdev, &mcast, QED_SPQ_MODE_CB, NULL); } -static int qed_configure_filter(struct qed_dev *cdev, - struct qed_filter_params *params) -{ - enum qed_filter_rx_mode_type accept_flags; - - switch (params->type) { - case QED_FILTER_TYPE_UCAST: - return qed_configure_filter_ucast(cdev, ¶ms->filter.ucast); - case QED_FILTER_TYPE_MCAST: - return qed_configure_filter_mcast(cdev, ¶ms->filter.mcast); - case QED_FILTER_TYPE_RX_MODE: - accept_flags = params->filter.accept_flags; - return qed_configure_filter_rx_mode(cdev, accept_flags); - default: - DP_NOTICE(cdev, "Unknown filter type %d\n", (int)params->type); - return -EINVAL; - } -} - static int qed_configure_arfs_searcher(struct qed_dev *cdev, enum qed_filter_config_mode mode) { @@ -2904,7 +2885,9 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .q_rx_stop = &qed_stop_rxq, .q_tx_start = &qed_start_txq, .q_tx_stop = &qed_stop_txq, - .filter_config = &qed_configure_filter, + .filter_config_rx_mode = &qed_configure_filter_rx_mode, + .filter_config_ucast = &qed_configure_filter_ucast, + .filter_config_mcast = &qed_configure_filter_mcast, .fastpath_stop = &qed_fastpath_stop, .eth_cqe_completion = &qed_fp_cqe_completion, .get_vport_stats = &qed_get_vport_stats, diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index a2e4dfb5cb44e7..f99b085b56a54c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -619,30 +619,28 @@ static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char mac[ETH_ALEN]) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.mac_valid = 1; - ether_addr_copy(filter_cmd.filter.ucast.mac, mac); + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.mac_valid = 1; + ether_addr_copy(ucast.mac, mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_set_ucast_rx_vlan(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, u16 vid) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.vlan_valid = 1; - filter_cmd.filter.ucast.vlan = vid; + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.vlan_valid = 1; + ucast.vlan = vid; - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_config_accept_any_vlan(struct qede_dev *edev, bool action) @@ -1057,18 +1055,17 @@ static int qede_set_mcast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char *mac, int num_macs) { - struct qed_filter_params filter_cmd; + struct qed_filter_mcast_params mcast; int i; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_MCAST; - filter_cmd.filter.mcast.type = opcode; - filter_cmd.filter.mcast.num = num_macs; + memset(&mcast, 0, sizeof(mcast)); + mcast.type = opcode; + mcast.num = num_macs; for (i = 0; i < num_macs; i++, mac += ETH_ALEN) - ether_addr_copy(filter_cmd.filter.mcast.mac[i], mac); + ether_addr_copy(mcast.mac[i], mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_mcast(edev->cdev, &mcast); } int qede_set_mac_addr(struct net_device *ndev, void *p) @@ -1194,7 +1191,6 @@ void qede_config_rx_mode(struct net_device *ndev) { enum qed_filter_rx_mode_type accept_flags; struct qede_dev *edev = netdev_priv(ndev); - struct qed_filter_params rx_mode; unsigned char *uc_macs, *temp; struct netdev_hw_addr *ha; int rc, uc_count; @@ -1220,10 +1216,6 @@ void qede_config_rx_mode(struct net_device *ndev) netif_addr_unlock_bh(ndev); - /* Configure the struct for the Rx mode */ - memset(&rx_mode, 0, sizeof(struct qed_filter_params)); - rx_mode.type = QED_FILTER_TYPE_RX_MODE; - /* Remove all previous unicast secondary macs and multicast macs * (configure / leave the primary mac) */ @@ -1271,8 +1263,7 @@ void qede_config_rx_mode(struct net_device *ndev) qede_config_accept_any_vlan(edev, false); } - rx_mode.filter.accept_flags = accept_flags; - edev->ops->filter_config(edev->cdev, &rx_mode); + edev->ops->filter_config_rx_mode(edev->cdev, accept_flags); out: kfree(uc_macs); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 9837bdb89cd403..ee4c3bd28a934c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1176,19 +1176,17 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level, edev->devlink = qed_ops->common->devlink_register(cdev); if (IS_ERR(edev->devlink)) { DP_NOTICE(edev, "Cannot register devlink\n"); + rc = PTR_ERR(edev->devlink); edev->devlink = NULL; - /* Go on, we can live without devlink */ + goto err3; } } else { struct net_device *ndev = pci_get_drvdata(pdev); + struct qed_devlink *qdl; edev = netdev_priv(ndev); - - if (edev->devlink) { - struct qed_devlink *qdl = devlink_priv(edev->devlink); - - qdl->cdev = cdev; - } + qdl = devlink_priv(edev->devlink); + qdl->cdev = cdev; edev->cdev = cdev; memset(&edev->stats, 0, sizeof(edev->stats)); memcpy(&edev->dev_info, &dev_info, sizeof(dev_info)); diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h index 2728df46ec4105..8da4b66b71b5de 100644 --- a/drivers/net/ethernet/realtek/r8169.h +++ b/drivers/net/ethernet/realtek/r8169.h @@ -37,7 +37,7 @@ enum mac_version { RTL_GIGA_MAC_VER_24, RTL_GIGA_MAC_VER_25, RTL_GIGA_MAC_VER_26, - RTL_GIGA_MAC_VER_27, + /* support for RTL_GIGA_MAC_VER_27 has been removed */ RTL_GIGA_MAC_VER_28, RTL_GIGA_MAC_VER_29, RTL_GIGA_MAC_VER_30, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 46a6ff9a782d75..0199914440abc4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -118,7 +118,6 @@ static const struct { [RTL_GIGA_MAC_VER_24] = {"RTL8168cp/8111cp" }, [RTL_GIGA_MAC_VER_25] = {"RTL8168d/8111d", FIRMWARE_8168D_1}, [RTL_GIGA_MAC_VER_26] = {"RTL8168d/8111d", FIRMWARE_8168D_2}, - [RTL_GIGA_MAC_VER_27] = {"RTL8168dp/8111dp" }, [RTL_GIGA_MAC_VER_28] = {"RTL8168dp/8111dp" }, [RTL_GIGA_MAC_VER_29] = {"RTL8105e", FIRMWARE_8105E_1}, [RTL_GIGA_MAC_VER_30] = {"RTL8105e", FIRMWARE_8105E_1}, @@ -985,33 +984,6 @@ DECLARE_RTL_COND(rtl_ocpar_cond) return RTL_R32(tp, OCPAR) & OCPAR_FLAG; } -static void r8168dp_1_mdio_access(struct rtl8169_private *tp, int reg, u32 data) -{ - RTL_W32(tp, OCPDR, data | ((reg & OCPDR_REG_MASK) << OCPDR_GPHY_REG_SHIFT)); - RTL_W32(tp, OCPAR, OCPAR_GPHY_WRITE_CMD); - RTL_W32(tp, EPHY_RXER_NUM, 0); - - rtl_loop_wait_low(tp, &rtl_ocpar_cond, 1000, 100); -} - -static void r8168dp_1_mdio_write(struct rtl8169_private *tp, int reg, int value) -{ - r8168dp_1_mdio_access(tp, reg, - OCPDR_WRITE_CMD | (value & OCPDR_DATA_MASK)); -} - -static int r8168dp_1_mdio_read(struct rtl8169_private *tp, int reg) -{ - r8168dp_1_mdio_access(tp, reg, OCPDR_READ_CMD); - - mdelay(1); - RTL_W32(tp, OCPAR, OCPAR_GPHY_READ_CMD); - RTL_W32(tp, EPHY_RXER_NUM, 0); - - return rtl_loop_wait_high(tp, &rtl_ocpar_cond, 1000, 100) ? - RTL_R32(tp, OCPDR) & OCPDR_DATA_MASK : -ETIMEDOUT; -} - #define R8168DP_1_MDIO_ACCESS_BIT 0x00020000 static void r8168dp_2_mdio_start(struct rtl8169_private *tp) @@ -1053,9 +1025,6 @@ static int r8168dp_2_mdio_read(struct rtl8169_private *tp, int reg) static void rtl_writephy(struct rtl8169_private *tp, int location, int val) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_27: - r8168dp_1_mdio_write(tp, location, val); - break; case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: r8168dp_2_mdio_write(tp, location, val); @@ -1072,8 +1041,6 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val) static int rtl_readphy(struct rtl8169_private *tp, int location) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_27: - return r8168dp_1_mdio_read(tp, location); case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_2_mdio_read(tp, location); @@ -1235,7 +1202,6 @@ static bool r8168ep_check_dash(struct rtl8169_private *tp) static enum rtl_dash_type rtl_check_dash(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_27: case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_check_dash(tp) ? RTL_DASH_DP : RTL_DASH_NONE; @@ -2040,8 +2006,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) /* 8168DP family. */ /* It seems this early RTL8168dp version never made it to - * the wild. Let's see whether somebody complains, if not - * we'll remove support for this chip version completely. + * the wild. Support has been removed. * { 0x7cf, 0x288, RTL_GIGA_MAC_VER_27 }, */ { 0x7cf, 0x28a, RTL_GIGA_MAC_VER_28 }, @@ -2371,7 +2336,7 @@ static void rtl_jumbo_config(struct rtl8169_private *tp) r8168c_hw_jumbo_disable(tp); } break; - case RTL_GIGA_MAC_VER_27 ... RTL_GIGA_MAC_VER_28: + case RTL_GIGA_MAC_VER_28: if (jumbo) r8168dp_hw_jumbo_enable(tp); else @@ -3719,7 +3684,6 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_24] = rtl_hw_start_8168cp_3, [RTL_GIGA_MAC_VER_25] = rtl_hw_start_8168d, [RTL_GIGA_MAC_VER_26] = rtl_hw_start_8168d, - [RTL_GIGA_MAC_VER_27] = rtl_hw_start_8168d, [RTL_GIGA_MAC_VER_28] = rtl_hw_start_8168d_4, [RTL_GIGA_MAC_VER_29] = rtl_hw_start_8105e_1, [RTL_GIGA_MAC_VER_30] = rtl_hw_start_8105e_2, @@ -3982,7 +3946,6 @@ static void rtl8169_cleanup(struct rtl8169_private *tp, bool going_down) goto no_reset; switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_27: case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: rtl_loop_wait_low(tp, &rtl_npq_cond, 20, 2000); diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c index 50f0f621b1aa8a..f7ad5487879b83 100644 --- a/drivers/net/ethernet/realtek/r8169_phy_config.c +++ b/drivers/net/ethernet/realtek/r8169_phy_config.c @@ -548,64 +548,6 @@ static void rtl8168d_2_hw_phy_config(struct rtl8169_private *tp, rtl8168d_apply_firmware_cond(tp, phydev, 0xb300); } -static void rtl8168d_3_hw_phy_config(struct rtl8169_private *tp, - struct phy_device *phydev) -{ - static const struct phy_reg phy_reg_init[] = { - { 0x1f, 0x0002 }, - { 0x10, 0x0008 }, - { 0x0d, 0x006c }, - - { 0x1f, 0x0000 }, - { 0x0d, 0xf880 }, - - { 0x1f, 0x0001 }, - { 0x17, 0x0cc0 }, - - { 0x1f, 0x0001 }, - { 0x0b, 0xa4d8 }, - { 0x09, 0x281c }, - { 0x07, 0x2883 }, - { 0x0a, 0x6b35 }, - { 0x1d, 0x3da4 }, - { 0x1c, 0xeffd }, - { 0x14, 0x7f52 }, - { 0x18, 0x7fc6 }, - { 0x08, 0x0601 }, - { 0x06, 0x4063 }, - { 0x10, 0xf074 }, - { 0x1f, 0x0003 }, - { 0x13, 0x0789 }, - { 0x12, 0xf4bd }, - { 0x1a, 0x04fd }, - { 0x14, 0x84b0 }, - { 0x1f, 0x0000 }, - { 0x00, 0x9200 }, - - { 0x1f, 0x0005 }, - { 0x01, 0x0340 }, - { 0x1f, 0x0001 }, - { 0x04, 0x4000 }, - { 0x03, 0x1d21 }, - { 0x02, 0x0c32 }, - { 0x01, 0x0200 }, - { 0x00, 0x5554 }, - { 0x04, 0x4800 }, - { 0x04, 0x4000 }, - { 0x04, 0xf000 }, - { 0x03, 0xdf01 }, - { 0x02, 0xdf20 }, - { 0x01, 0x101a }, - { 0x00, 0xa0ff }, - { 0x04, 0xf800 }, - { 0x04, 0xf000 }, - { 0x1f, 0x0000 }, - }; - - rtl_writephy_batch(phydev, phy_reg_init); - r8168d_modify_extpage(phydev, 0x0023, 0x16, 0xffff, 0x0000); -} - static void rtl8168d_4_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev) { @@ -1332,7 +1274,6 @@ void r8169_hw_phy_config(struct rtl8169_private *tp, struct phy_device *phydev, [RTL_GIGA_MAC_VER_24] = rtl8168cp_2_hw_phy_config, [RTL_GIGA_MAC_VER_25] = rtl8168d_1_hw_phy_config, [RTL_GIGA_MAC_VER_26] = rtl8168d_2_hw_phy_config, - [RTL_GIGA_MAC_VER_27] = rtl8168d_3_hw_phy_config, [RTL_GIGA_MAC_VER_28] = rtl8168d_4_hw_phy_config, [RTL_GIGA_MAC_VER_29] = rtl8105e_hw_phy_config, [RTL_GIGA_MAC_VER_30] = rtl8105e_hw_phy_config, diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 3d1a18a01ce505..be4d772e68cfb0 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -1070,7 +1070,7 @@ static int sis190_open(struct net_device *dev) /* * Rx and Tx descriptors need 256 bytes alignment. - * pci_alloc_consistent() guarantees a stronger alignment. + * dma_alloc_coherent() guarantees a stronger alignment. */ tp->TxDescRing = dma_alloc_coherent(&pdev->dev, TX_RING_BYTES, &tp->tx_dma, GFP_KERNEL); diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index fdbd2a43e26754..3d1176588f7dd7 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -788,7 +788,7 @@ static int smsc9420_alloc_rx_buffer(struct smsc9420_pdata *pd, int index) PKT_BUF_SZ, DMA_FROM_DEVICE); if (dma_mapping_error(&pd->pdev->dev, mapping)) { dev_kfree_skb_any(skb); - netif_warn(pd, rx_err, pd->dev, "pci_map_single failed!\n"); + netif_warn(pd, rx_err, pd->dev, "dma_map_single failed!\n"); return -ENOMEM; } @@ -940,7 +940,7 @@ static netdev_tx_t smsc9420_hard_start_xmit(struct sk_buff *skb, DMA_TO_DEVICE); if (dma_mapping_error(&pd->pdev->dev, mapping)) { netif_warn(pd, tx_err, pd->dev, - "pci_map_single failed, dropping packet\n"); + "dma_map_single failed, dropping packet\n"); return NETDEV_TX_BUSY; } @@ -1551,7 +1551,7 @@ smsc9420_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (!pd->rx_ring) goto out_free_io_4; - /* descriptors are aligned due to the nature of pci_alloc_consistent */ + /* descriptors are aligned due to the nature of dma_alloc_coherent */ pd->tx_ring = (pd->rx_ring + RX_RING_SIZE); pd->tx_dma_addr = pd->rx_dma_addr + sizeof(struct smsc9420_dma_desc) * RX_RING_SIZE; diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 1f46af136aa8cd..f80a2aef99722e 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1860,10 +1860,9 @@ static int netsec_of_probe(struct platform_device *pdev, *phy_addr = of_mdio_parse_addr(&pdev->dev, priv->phy_np); priv->clk = devm_clk_get(&pdev->dev, NULL); /* get by 'phy_ref_clk' */ - if (IS_ERR(priv->clk)) { - dev_err(&pdev->dev, "phy_ref_clk not found\n"); - return PTR_ERR(priv->clk); - } + if (IS_ERR(priv->clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(priv->clk), + "phy_ref_clk not found\n"); priv->freq = clk_get_rate(priv->clk); return 0; @@ -1886,19 +1885,17 @@ static int netsec_acpi_probe(struct platform_device *pdev, priv->phy_interface = PHY_INTERFACE_MODE_NA; ret = device_property_read_u32(&pdev->dev, "phy-channel", phy_addr); - if (ret) { - dev_err(&pdev->dev, - "missing required property 'phy-channel'\n"); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, + "missing required property 'phy-channel'\n"); ret = device_property_read_u32(&pdev->dev, "socionext,phy-clock-frequency", &priv->freq); if (ret) - dev_err(&pdev->dev, - "missing required property 'socionext,phy-clock-frequency'\n"); - return ret; + return dev_err_probe(&pdev->dev, ret, + "missing required property 'socionext,phy-clock-frequency'\n"); + return 0; } static void netsec_unregister_mdio(struct netsec_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index d046e33b8a2976..66fc8be34bb717 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -171,10 +171,9 @@ static int visconti_eth_clock_probe(struct platform_device *pdev, int err; dwmac->phy_ref_clk = devm_clk_get(&pdev->dev, "phy_ref_clk"); - if (IS_ERR(dwmac->phy_ref_clk)) { - dev_err(&pdev->dev, "phy_ref_clk clock not found.\n"); - return PTR_ERR(dwmac->phy_ref_clk); - } + if (IS_ERR(dwmac->phy_ref_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(dwmac->phy_ref_clk), + "phy_ref_clk clock not found.\n"); err = clk_prepare_enable(dwmac->phy_ref_clk); if (err < 0) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 553c4403258aa2..fd4c6517125e3a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3502,6 +3502,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) /* Request Rx MSI irq */ for (i = 0; i < priv->plat->rx_queues_to_use; i++) { + if (i >= MTL_MAX_RX_QUEUES) + break; if (priv->rx_irq[i] == 0) continue; @@ -3525,6 +3527,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) /* Request Tx MSI irq */ for (i = 0; i < priv->plat->tx_queues_to_use; i++) { + if (i >= MTL_MAX_TX_QUEUES) + break; if (priv->tx_irq[i] == 0) continue; diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c index 6e4d4f9e32e06d..b05de9b61ad619 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c +++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c @@ -61,7 +61,7 @@ struct am65_cpsw_regdump_item { #define AM65_CPSW_REGDUMP_REC(mod, start, end) { \ .hdr.module_id = (mod), \ - .hdr.len = (((u32 *)(end)) - ((u32 *)(start)) + 1) * sizeof(u32) * 2 + \ + .hdr.len = (end + 4 - start) * 2 + \ sizeof(struct am65_cpsw_regdump_hdr), \ .start_ofs = (start), \ .end_ofs = end, \ diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 130346f74ee8a1..0de5f4a4fe0893 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -2429,12 +2429,6 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common) dl_priv = devlink_priv(common->devlink); dl_priv->common = common; - ret = devlink_register(common->devlink); - if (ret) { - dev_err(dev, "devlink reg fail ret:%d\n", ret); - goto dl_free; - } - /* Provide devlink hook to switch mode when multiple external ports * are present NUSS switchdev driver is enabled. */ @@ -2447,7 +2441,6 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common) dev_err(dev, "devlink params reg fail ret:%d\n", ret); goto dl_unreg; } - devlink_params_publish(common->devlink); } for (i = 1; i <= common->port_num; i++) { @@ -2468,7 +2461,7 @@ static int am65_cpsw_nuss_register_devlink(struct am65_cpsw_common *common) } devlink_port_type_eth_set(dl_port, port->ndev); } - + devlink_register(common->devlink); return ret; dl_port_unreg: @@ -2479,10 +2472,7 @@ dl_port_unreg: devlink_port_unregister(dl_port); } dl_unreg: - devlink_unregister(common->devlink); -dl_free: devlink_free(common->devlink); - return ret; } @@ -2492,6 +2482,8 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) struct am65_cpsw_port *port; int i; + devlink_unregister(common->devlink); + for (i = 1; i <= common->port_num; i++) { port = am65_common_get_port(common, i); dl_port = &port->devlink_port; @@ -2500,13 +2492,11 @@ static void am65_cpsw_unregister_devlink(struct am65_cpsw_common *common) } if (!AM65_CPSW_IS_CPSW2G(common) && - IS_ENABLED(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV)) { - devlink_params_unpublish(common->devlink); - devlink_params_unregister(common->devlink, am65_cpsw_devlink_params, + IS_ENABLED(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV)) + devlink_params_unregister(common->devlink, + am65_cpsw_devlink_params, ARRAY_SIZE(am65_cpsw_devlink_params)); - } - devlink_unregister(common->devlink); devlink_free(common->devlink); } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 7968f24d99c855..1530532748a86a 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1810,12 +1810,6 @@ static int cpsw_register_devlink(struct cpsw_common *cpsw) dl_priv = devlink_priv(cpsw->devlink); dl_priv->cpsw = cpsw; - ret = devlink_register(cpsw->devlink); - if (ret) { - dev_err(dev, "DL reg fail ret:%d\n", ret); - goto dl_free; - } - ret = devlink_params_register(cpsw->devlink, cpsw_devlink_params, ARRAY_SIZE(cpsw_devlink_params)); if (ret) { @@ -1823,22 +1817,19 @@ static int cpsw_register_devlink(struct cpsw_common *cpsw) goto dl_unreg; } - devlink_params_publish(cpsw->devlink); + devlink_register(cpsw->devlink); return ret; dl_unreg: - devlink_unregister(cpsw->devlink); -dl_free: devlink_free(cpsw->devlink); return ret; } static void cpsw_unregister_devlink(struct cpsw_common *cpsw) { - devlink_params_unpublish(cpsw->devlink); + devlink_unregister(cpsw->devlink); devlink_params_unregister(cpsw->devlink, cpsw_devlink_params, ARRAY_SIZE(cpsw_devlink_params)); - devlink_unregister(cpsw->devlink); devlink_free(cpsw->devlink); } diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 6d1e3f49a3d3da..5810e84737894c 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -1028,7 +1028,7 @@ static void dfx_bus_config_check(DFX_board_t *bp) * or read adapter MAC address * * Assumptions: - * Memory allocated from pci_alloc_consistent() call is physically + * Memory allocated from dma_alloc_coherent() call is physically * contiguous, locked memory. * * Side Effects: @@ -3249,7 +3249,7 @@ static void dfx_rcv_queue_process( * is contained in a single physically contiguous buffer * in which the virtual address of the start of packet * (skb->data) can be converted to a physical address - * by using pci_map_single(). + * by using dma_map_single(). * * Since the adapter architecture requires a three byte * packet request header to prepend the start of packet, @@ -3402,7 +3402,7 @@ static netdev_tx_t dfx_xmt_queue_pkt(struct sk_buff *skb, * skb->data. * 6. The physical address of the start of packet * can be determined from the virtual address - * by using pci_map_single() and is only 32-bits + * by using dma_map_single() and is only 32-bits * wide. */ diff --git a/drivers/net/fddi/skfp/skfddi.c b/drivers/net/fddi/skfp/skfddi.c index c5cb421f9890d6..cc5126ea7ef5fb 100644 --- a/drivers/net/fddi/skfp/skfddi.c +++ b/drivers/net/fddi/skfp/skfddi.c @@ -1012,7 +1012,7 @@ static int skfp_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __ * is contained in a single physically contiguous buffer * in which the virtual address of the start of packet * (skb->data) can be converted to a physical address - * by using pci_map_single(). + * by using dma_map_single(). * * We have an internal queue for packets we can not send * immediately. Packets in this queue can be given to the diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 54313bd5779731..cb6645012a3096 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -1470,10 +1470,6 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) if (err) goto err_devlink_free; - err = devlink_register(devlink); - if (err) - goto err_resources_unregister; - err = devlink_params_register(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); if (err) @@ -1514,9 +1510,9 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) if (err) goto err_psample_exit; - devlink_params_publish(devlink); - devlink_reload_enable(devlink); nsim_dev->esw_mode = DEVLINK_ESWITCH_MODE_LEGACY; + devlink_register(devlink); + devlink_reload_enable(devlink); return 0; err_psample_exit: @@ -1537,8 +1533,6 @@ err_params_unregister: devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); err_dl_unregister: - devlink_unregister(devlink); -err_resources_unregister: devlink_resources_unregister(devlink, NULL); err_devlink_free: devlink_free(devlink); @@ -1573,6 +1567,7 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) struct devlink *devlink = priv_to_devlink(nsim_dev); devlink_reload_disable(devlink); + devlink_unregister(devlink); nsim_dev_reload_destroy(nsim_dev); @@ -1580,7 +1575,6 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) nsim_dev_debugfs_exit(nsim_dev); devlink_params_unregister(devlink, nsim_devlink_params, ARRAY_SIZE(nsim_devlink_params)); - devlink_unregister(devlink); devlink_resources_unregister(devlink, NULL); devlink_free(devlink); } diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index b03a0513eb7e7b..0ab6a40be61147 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -81,6 +81,30 @@ static int nsim_set_ringparam(struct net_device *dev, return 0; } +static void +nsim_get_channels(struct net_device *dev, struct ethtool_channels *ch) +{ + struct netdevsim *ns = netdev_priv(dev); + + ch->max_combined = ns->nsim_bus_dev->num_queues; + ch->combined_count = ns->ethtool.channels; +} + +static int +nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch) +{ + struct netdevsim *ns = netdev_priv(dev); + int err; + + err = netif_set_real_num_queues(dev, ch->combined_count, + ch->combined_count); + if (err) + return err; + + ns->ethtool.channels = ch->combined_count; + return 0; +} + static int nsim_get_fecparam(struct net_device *dev, struct ethtool_fecparam *fecparam) { @@ -118,6 +142,8 @@ static const struct ethtool_ops nsim_ethtool_ops = { .get_coalesce = nsim_get_coalesce, .get_ringparam = nsim_get_ringparam, .set_ringparam = nsim_set_ringparam, + .get_channels = nsim_get_channels, + .set_channels = nsim_set_channels, .get_fecparam = nsim_get_fecparam, .set_fecparam = nsim_set_fecparam, }; @@ -141,6 +167,8 @@ void nsim_ethtool_init(struct netdevsim *ns) ns->ethtool.fec.fec = ETHTOOL_FEC_NONE; ns->ethtool.fec.active_fec = ETHTOOL_FEC_NONE; + ns->ethtool.channels = ns->nsim_bus_dev->num_queues; + ethtool = debugfs_create_dir("ethtool", ns->nsim_dev_port->ddir); debugfs_create_u32("get_err", 0600, ethtool, &ns->ethtool.get_err); diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index 04aebdf8574744..aa77af4a68df6f 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -110,26 +110,6 @@ static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) if (err) return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_bool_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_bool_put(fmsg, true); - if (err) - return err; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u8_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_u8_put(fmsg, i); - if (err) - return err; - } err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) return err; @@ -146,18 +126,6 @@ static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) if (err) return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u64_array"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_u64_put(fmsg, i); - if (err) - return err; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_array_of_objects"); if (err) return err; diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 793c86dc5a9c17..d42eec05490f42 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -62,6 +62,7 @@ struct nsim_ethtool_pauseparam { struct nsim_ethtool { u32 get_err; u32 set_err; + u32 channels; struct nsim_ethtool_pauseparam pauseparam; struct ethtool_coalesce coalesce; struct ethtool_ringparam ring; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index bdac087058b266..3feee4d59030d1 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -150,7 +150,8 @@ #define ATH8035_PHY_ID 0x004dd072 #define AT8030_PHY_ID_MASK 0xffffffef -#define QCA8327_PHY_ID 0x004dd034 +#define QCA8327_A_PHY_ID 0x004dd033 +#define QCA8327_B_PHY_ID 0x004dd034 #define QCA8337_PHY_ID 0x004dd036 #define QCA8K_PHY_ID_MASK 0xffffffff @@ -1409,17 +1410,49 @@ static struct phy_driver at803x_driver[] = { .config_aneg = at803x_config_aneg, }, { /* QCA8337 */ - .phy_id = QCA8337_PHY_ID, - .phy_id_mask = QCA8K_PHY_ID_MASK, - .name = "QCA PHY 8337", + .phy_id = QCA8337_PHY_ID, + .phy_id_mask = QCA8K_PHY_ID_MASK, + .name = "Qualcomm Atheros 8337 internal PHY", /* PHY_GBIT_FEATURES */ - .probe = at803x_probe, - .flags = PHY_IS_INTERNAL, - .config_init = qca83xx_config_init, - .soft_reset = genphy_soft_reset, - .get_sset_count = at803x_get_sset_count, - .get_strings = at803x_get_strings, - .get_stats = at803x_get_stats, + .probe = at803x_probe, + .flags = PHY_IS_INTERNAL, + .config_init = qca83xx_config_init, + .soft_reset = genphy_soft_reset, + .get_sset_count = at803x_get_sset_count, + .get_strings = at803x_get_strings, + .get_stats = at803x_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, +}, { + /* QCA8327-A from switch QCA8327-AL1A */ + .phy_id = QCA8327_A_PHY_ID, + .phy_id_mask = QCA8K_PHY_ID_MASK, + .name = "Qualcomm Atheros 8327-A internal PHY", + /* PHY_GBIT_FEATURES */ + .probe = at803x_probe, + .flags = PHY_IS_INTERNAL, + .config_init = qca83xx_config_init, + .soft_reset = genphy_soft_reset, + .get_sset_count = at803x_get_sset_count, + .get_strings = at803x_get_strings, + .get_stats = at803x_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, +}, { + /* QCA8327-B from switch QCA8327-BL1A */ + .phy_id = QCA8327_B_PHY_ID, + .phy_id_mask = QCA8K_PHY_ID_MASK, + .name = "Qualcomm Atheros 8327-B internal PHY", + /* PHY_GBIT_FEATURES */ + .probe = at803x_probe, + .flags = PHY_IS_INTERNAL, + .config_init = qca83xx_config_init, + .soft_reset = genphy_soft_reset, + .get_sset_count = at803x_get_sset_count, + .get_strings = at803x_get_strings, + .get_stats = at803x_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, }, }; module_phy_driver(at803x_driver); @@ -1430,6 +1463,9 @@ static struct mdio_device_id __maybe_unused atheros_tbl[] = { { PHY_ID_MATCH_EXACT(ATH8032_PHY_ID) }, { PHY_ID_MATCH_EXACT(ATH8035_PHY_ID) }, { PHY_ID_MATCH_EXACT(ATH9331_PHY_ID) }, + { PHY_ID_MATCH_EXACT(QCA8337_PHY_ID) }, + { PHY_ID_MATCH_EXACT(QCA8327_A_PHY_ID) }, + { PHY_ID_MATCH_EXACT(QCA8327_B_PHY_ID) }, { } }; diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 27b6a3f507ae60..6e0c435336b9cf 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -502,6 +502,190 @@ reset_shadow_mode: MII_BCM7XXX_SHD_MODE_2); } +static int bcm7xxx_16nm_ephy_afe_config(struct phy_device *phydev) +{ + int tmp, rcalcode, rcalnewcodelp, rcalnewcode11, rcalnewcode11d2; + + /* Reset PHY */ + tmp = genphy_soft_reset(phydev); + if (tmp) + return tmp; + + /* Reset AFE and PLL */ + bcm_phy_write_exp_sel(phydev, 0x0003, 0x0006); + /* Clear reset */ + bcm_phy_write_exp_sel(phydev, 0x0003, 0x0000); + + /* Write PLL/AFE control register to select 54MHz crystal */ + bcm_phy_write_misc(phydev, 0x0030, 0x0001, 0x0000); + bcm_phy_write_misc(phydev, 0x0031, 0x0000, 0x044a); + + /* Change Ka,Kp,Ki to pdiv=1 */ + bcm_phy_write_misc(phydev, 0x0033, 0x0002, 0x71a1); + /* Configuration override */ + bcm_phy_write_misc(phydev, 0x0033, 0x0001, 0x8000); + + /* Change PLL_NDIV and PLL_NUDGE */ + bcm_phy_write_misc(phydev, 0x0031, 0x0001, 0x2f68); + bcm_phy_write_misc(phydev, 0x0031, 0x0002, 0x0000); + + /* Reference frequency is 54Mhz, config_mode[15:14] = 3 (low + * phase) + */ + bcm_phy_write_misc(phydev, 0x0030, 0x0003, 0xc036); + + /* Initialize bypass mode */ + bcm_phy_write_misc(phydev, 0x0032, 0x0003, 0x0000); + /* Bypass code, default: VCOCLK enabled */ + bcm_phy_write_misc(phydev, 0x0033, 0x0000, 0x0002); + /* LDOs at default setting */ + bcm_phy_write_misc(phydev, 0x0030, 0x0002, 0x01c0); + /* Release PLL reset */ + bcm_phy_write_misc(phydev, 0x0030, 0x0001, 0x0001); + + /* Bandgap curvature correction to correct default */ + bcm_phy_write_misc(phydev, 0x0038, 0x0000, 0x0010); + + /* Run RCAL */ + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x0038); + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x003b); + udelay(2); + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x003f); + mdelay(5); + + /* AFE_CAL_CONFIG_0, Vref=1000, Target=10, averaging enabled */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x1c82); + /* AFE_CAL_CONFIG_0, no reset and analog powerup */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9e82); + udelay(2); + /* AFE_CAL_CONFIG_0, start calibration */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9f82); + udelay(100); + /* AFE_CAL_CONFIG_0, clear start calibration, set HiBW */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9e86); + udelay(2); + /* AFE_CAL_CONFIG_0, start calibration with hi BW mode set */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9f86); + udelay(100); + + /* Adjust 10BT amplitude additional +7% and 100BT +2% */ + bcm_phy_write_misc(phydev, 0x0038, 0x0001, 0xe7ea); + /* Adjust 1G mode amplitude and 1G testmode1 */ + bcm_phy_write_misc(phydev, 0x0038, 0x0002, 0xede0); + + /* Read CORE_EXPA9 */ + tmp = bcm_phy_read_exp(phydev, 0x00a9); + /* CORE_EXPA9[6:1] is rcalcode[5:0] */ + rcalcode = (tmp & 0x7e) / 2; + /* Correct RCAL code + 1 is -1% rprogr, LP: +16 */ + rcalnewcodelp = rcalcode + 16; + /* Correct RCAL code + 1 is -15 rprogr, 11: +10 */ + rcalnewcode11 = rcalcode + 10; + /* Saturate if necessary */ + if (rcalnewcodelp > 0x3f) + rcalnewcodelp = 0x3f; + if (rcalnewcode11 > 0x3f) + rcalnewcode11 = 0x3f; + /* REXT=1 BYP=1 RCAL_st1<5:0>=new rcal code */ + tmp = 0x00f8 + rcalnewcodelp * 256; + /* Program into AFE_CAL_CONFIG_2 */ + bcm_phy_write_misc(phydev, 0x0039, 0x0003, tmp); + /* AFE_BIAS_CONFIG_0 10BT bias code (Bias: E4) */ + bcm_phy_write_misc(phydev, 0x0038, 0x0001, 0xe7e4); + /* invert adc clock output and 'adc refp ldo current To correct + * default + */ + bcm_phy_write_misc(phydev, 0x003b, 0x0000, 0x8002); + /* 100BT stair case, high BW, 1G stair case, alternate encode */ + bcm_phy_write_misc(phydev, 0x003c, 0x0003, 0xf882); + /* 1000BT DAC transition method per Erol, bits[32], DAC Shuffle + * sequence 1 + 10BT imp adjust bits + */ + bcm_phy_write_misc(phydev, 0x003d, 0x0000, 0x3201); + /* Non-overlap fix */ + bcm_phy_write_misc(phydev, 0x003a, 0x0002, 0x0c00); + + /* pwdb override (rxconfig<5>) to turn on RX LDO indpendent of + * pwdb controls from DSP_TAP10 + */ + bcm_phy_write_misc(phydev, 0x003a, 0x0001, 0x0020); + + /* Remove references to channel 2 and 3 */ + bcm_phy_write_misc(phydev, 0x003b, 0x0002, 0x0000); + bcm_phy_write_misc(phydev, 0x003b, 0x0003, 0x0000); + + /* Set cal_bypassb bit rxconfig<43> */ + bcm_phy_write_misc(phydev, 0x003a, 0x0003, 0x0800); + udelay(2); + + /* Revert pwdb_override (rxconfig<5>) to 0 so that the RX pwr + * is controlled by DSP. + */ + bcm_phy_write_misc(phydev, 0x003a, 0x0001, 0x0000); + + /* Drop LSB */ + rcalnewcode11d2 = (rcalnewcode11 & 0xfffe) / 2; + tmp = bcm_phy_read_misc(phydev, 0x003d, 0x0001); + /* Clear bits [11:5] */ + tmp &= ~0xfe0; + /* set txcfg_ch0<5>=1 (enable + set local rcal) */ + tmp |= 0x0020 | (rcalnewcode11d2 * 64); + bcm_phy_write_misc(phydev, 0x003d, 0x0001, tmp); + bcm_phy_write_misc(phydev, 0x003d, 0x0002, tmp); + + tmp = bcm_phy_read_misc(phydev, 0x003d, 0x0000); + /* set txcfg<45:44>=11 (enable Rextra + invert fullscaledetect) + */ + tmp &= ~0x3000; + tmp |= 0x3000; + bcm_phy_write_misc(phydev, 0x003d, 0x0000, tmp); + + return 0; +} + +static int bcm7xxx_16nm_ephy_config_init(struct phy_device *phydev) +{ + int ret, val; + + ret = bcm7xxx_16nm_ephy_afe_config(phydev); + if (ret) + return ret; + + ret = bcm_phy_set_eee(phydev, true); + if (ret) + return ret; + + ret = bcm_phy_read_shadow(phydev, BCM54XX_SHD_SCR3); + if (ret < 0) + return ret; + + val = ret; + + /* Auto power down of DLL enabled, + * TXC/RXC disabled during auto power down. + */ + val &= ~BCM54XX_SHD_SCR3_DLLAPD_DIS; + val |= BIT(8); + + ret = bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); + if (ret < 0) + return ret; + + return bcm_phy_enable_apd(phydev, true); +} + +static int bcm7xxx_16nm_ephy_resume(struct phy_device *phydev) +{ + int ret; + + /* Re-apply workarounds coming out suspend/resume */ + ret = bcm7xxx_16nm_ephy_config_init(phydev); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) { int ret; @@ -716,9 +900,25 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev) .resume = bcm7xxx_config_init, \ } +#define BCM7XXX_16NM_EPHY(_oui, _name) \ +{ \ + .phy_id = (_oui), \ + .phy_id_mask = 0xfffffff0, \ + .name = _name, \ + /* PHY_BASIC_FEATURES */ \ + .flags = PHY_IS_INTERNAL, \ + .probe = bcm7xxx_28nm_probe, \ + .remove = bcm7xxx_28nm_remove, \ + .config_init = bcm7xxx_16nm_ephy_config_init, \ + .config_aneg = genphy_config_aneg, \ + .read_status = genphy_read_status, \ + .resume = bcm7xxx_16nm_ephy_resume, \ +} + static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_EPHY(PHY_ID_BCM72113, "Broadcom BCM72113"), BCM7XXX_28NM_EPHY(PHY_ID_BCM72116, "Broadcom BCM72116"), + BCM7XXX_16NM_EPHY(PHY_ID_BCM72165, "Broadcom BCM72165"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"), BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"), BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"), @@ -741,6 +941,7 @@ static struct phy_driver bcm7xxx_driver[] = { static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM72113, 0xfffffff0 }, { PHY_ID_BCM72116, 0xfffffff0, }, + { PHY_ID_BCM72165, 0xfffffff0, }, { PHY_ID_BCM7250, 0xfffffff0, }, { PHY_ID_BCM7255, 0xfffffff0, }, { PHY_ID_BCM7260, 0xfffffff0, }, diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 83aea5c5cd03c2..bb5104ae46104c 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -392,10 +392,50 @@ static int bcm54xx_config_init(struct phy_device *phydev) return 0; } +static int bcm54xx_iddq_set(struct phy_device *phydev, bool enable) +{ + int ret = 0; + + if (!(phydev->dev_flags & PHY_BRCM_IDDQ_SUSPEND)) + return ret; + + ret = bcm_phy_read_exp(phydev, BCM54XX_TOP_MISC_IDDQ_CTRL); + if (ret < 0) + goto out; + + if (enable) + ret |= BCM54XX_TOP_MISC_IDDQ_SR | BCM54XX_TOP_MISC_IDDQ_LP; + else + ret &= ~(BCM54XX_TOP_MISC_IDDQ_SR | BCM54XX_TOP_MISC_IDDQ_LP); + + ret = bcm_phy_write_exp(phydev, BCM54XX_TOP_MISC_IDDQ_CTRL, ret); +out: + return ret; +} + +static int bcm54xx_suspend(struct phy_device *phydev) +{ + int ret; + + /* We cannot use a read/modify/write here otherwise the PHY gets into + * a bad state where its LEDs keep flashing, thus defeating the purpose + * of low power mode. + */ + ret = phy_write(phydev, MII_BMCR, BMCR_PDOWN); + if (ret < 0) + return ret; + + return bcm54xx_iddq_set(phydev, true); +} + static int bcm54xx_resume(struct phy_device *phydev) { int ret; + ret = bcm54xx_iddq_set(phydev, false); + if (ret < 0) + return ret; + /* Writes to register other than BMCR would be ignored * unless we clear the PDOWN bit first */ @@ -408,6 +448,15 @@ static int bcm54xx_resume(struct phy_device *phydev) */ fsleep(40); + /* Issue a soft reset after clearing the power down bit + * and before doing any other configuration. + */ + if (phydev->dev_flags & PHY_BRCM_IDDQ_SUSPEND) { + ret = genphy_soft_reset(phydev); + if (ret < 0) + return ret; + } + return bcm54xx_config_init(phydev); } @@ -702,6 +751,36 @@ static void bcm54xx_get_stats(struct phy_device *phydev, bcm_phy_get_stats(phydev, priv->stats, stats, data); } +static void bcm54xx_link_change_notify(struct phy_device *phydev) +{ + u16 mask = MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE | + MII_BCM54XX_EXP_EXP08_FORCE_DAC_WAKE; + int ret; + + if (phydev->state != PHY_RUNNING) + return; + + /* Don't change the DAC wake settings if auto power down + * is not requested. + */ + if (!(phydev->dev_flags & PHY_BRCM_AUTO_PWRDWN_ENABLE)) + return; + + ret = bcm_phy_read_exp(phydev, MII_BCM54XX_EXP_EXP08); + if (ret < 0) + return; + + /* Enable/disable 10BaseT auto and forced early DAC wake depending + * on the negotiated speed, those settings should only be done + * for 10Mbits/sec. + */ + if (phydev->speed == SPEED_10) + ret |= mask; + else + ret &= ~mask; + bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP08, ret); +} + static struct phy_driver broadcom_drivers[] = { { .phy_id = PHY_ID_BCM5411, @@ -715,6 +794,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5421, .phy_id_mask = 0xfffffff0, @@ -727,6 +807,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54210E, .phy_id_mask = 0xfffffff0, @@ -739,6 +820,9 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, + .suspend = bcm54xx_suspend, + .resume = bcm54xx_resume, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, @@ -751,6 +835,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54612E, .phy_id_mask = 0xfffffff0, @@ -763,6 +848,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54616S, .phy_id_mask = 0xfffffff0, @@ -774,6 +860,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .read_status = bcm54616s_read_status, .probe = bcm54616s_probe, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5464, .phy_id_mask = 0xfffffff0, @@ -788,6 +875,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5481, .phy_id_mask = 0xfffffff0, @@ -801,6 +889,7 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54810, .phy_id_mask = 0xfffffff0, @@ -814,8 +903,9 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, - .suspend = genphy_suspend, + .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54811, .phy_id_mask = 0xfffffff0, @@ -829,8 +919,9 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, - .suspend = genphy_suspend, + .suspend = bcm54xx_suspend, .resume = bcm54xx_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5482, .phy_id_mask = 0xfffffff0, @@ -843,6 +934,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM50610, .phy_id_mask = 0xfffffff0, @@ -855,6 +947,9 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, + .suspend = bcm54xx_suspend, + .resume = bcm54xx_resume, }, { .phy_id = PHY_ID_BCM50610M, .phy_id_mask = 0xfffffff0, @@ -867,6 +962,9 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, + .suspend = bcm54xx_suspend, + .resume = bcm54xx_resume, }, { .phy_id = PHY_ID_BCM57780, .phy_id_mask = 0xfffffff0, @@ -879,6 +977,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCMAC131, .phy_id_mask = 0xfffffff0, @@ -905,6 +1004,7 @@ static struct phy_driver broadcom_drivers[] = { .get_strings = bcm_phy_get_strings, .get_stats = bcm54xx_get_stats, .probe = bcm54xx_phy_probe, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM53125, .phy_id_mask = 0xfffffff0, @@ -918,6 +1018,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM89610, .phy_id_mask = 0xfffffff0, @@ -930,6 +1031,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, } }; module_phy_driver(broadcom_drivers); diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 5c928f827173c3..c330a5a9f66514 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1537,6 +1537,65 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, return ret; } +#define LAN_EXT_PAGE_ACCESS_CONTROL 0x16 +#define LAN_EXT_PAGE_ACCESS_ADDRESS_DATA 0x17 +#define LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC 0x4000 + +#define LAN8804_ALIGN_SWAP 0x4a +#define LAN8804_ALIGN_TX_A_B_SWAP 0x1 +#define LAN8804_ALIGN_TX_A_B_SWAP_MASK GENMASK(2, 0) +#define LAN8814_CLOCK_MANAGEMENT 0xd +#define LAN8814_LINK_QUALITY 0x8e + +static int lanphy_read_page_reg(struct phy_device *phydev, int page, u32 addr) +{ + u32 data; + + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, addr); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, + (page | LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC)); + data = phy_read(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA); + + return data; +} + +static int lanphy_write_page_reg(struct phy_device *phydev, int page, u16 addr, + u16 val) +{ + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, addr); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, + (page | LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC)); + + val = phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, val); + if (val) { + phydev_err(phydev, "Error: phy_write has returned error %d\n", + val); + return val; + } + return 0; +} + +static int lan8804_config_init(struct phy_device *phydev) +{ + int val; + + /* MDI-X setting for swap A,B transmit */ + val = lanphy_read_page_reg(phydev, 2, LAN8804_ALIGN_SWAP); + val &= ~LAN8804_ALIGN_TX_A_B_SWAP_MASK; + val |= LAN8804_ALIGN_TX_A_B_SWAP; + lanphy_write_page_reg(phydev, 2, LAN8804_ALIGN_SWAP, val); + + /* Make sure that the PHY will not stop generating the clock when the + * link partner goes down + */ + lanphy_write_page_reg(phydev, 31, LAN8814_CLOCK_MANAGEMENT, 0x27e); + lanphy_read_page_reg(phydev, 1, LAN8814_LINK_QUALITY); + + return 0; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -1719,6 +1778,20 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = kszphy_resume, }, { + .phy_id = PHY_ID_LAN8804, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Microchip LAN966X Gigabit PHY", + .config_init = lan8804_config_init, + .driver_data = &ksz9021_type, + .probe = kszphy_probe, + .soft_reset = genphy_soft_reset, + .read_status = ksz9031_read_status, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = kszphy_resume, +}, { .phy_id = PHY_ID_KSZ9131, .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Microchip KSZ9131 Gigabit PHY", @@ -1794,6 +1867,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ886X, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8814, MICREL_PHY_ID_MASK }, + { PHY_ID_LAN8804, MICREL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 0a0abe8e4be0b6..5a58c77d00022f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1333,7 +1333,10 @@ void phylink_suspend(struct phylink *pl, bool mac_wol) * but one would hope all packets have been sent. This * also means phylink_resolve() will do nothing. */ - netif_carrier_off(pl->netdev); + if (pl->netdev) + netif_carrier_off(pl->netdev); + else + pl->old_link_state = false; /* We do not call mac_link_down() here as we want the * link to remain up to receive the WoL packets. diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 79bd2585ec6b2d..2ed49884565f0f 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -80,6 +80,7 @@ struct virtnet_sq_stats { u64 xdp_tx; u64 xdp_tx_drops; u64 kicks; + u64 tx_timeouts; }; struct virtnet_rq_stats { @@ -103,6 +104,7 @@ static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = { { "xdp_tx", VIRTNET_SQ_STAT(xdp_tx) }, { "xdp_tx_drops", VIRTNET_SQ_STAT(xdp_tx_drops) }, { "kicks", VIRTNET_SQ_STAT(kicks) }, + { "tx_timeouts", VIRTNET_SQ_STAT(tx_timeouts) }, }; static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = { @@ -1860,7 +1862,7 @@ static void virtnet_stats(struct net_device *dev, int i; for (i = 0; i < vi->max_queue_pairs; i++) { - u64 tpackets, tbytes, rpackets, rbytes, rdrops; + u64 tpackets, tbytes, terrors, rpackets, rbytes, rdrops; struct receive_queue *rq = &vi->rq[i]; struct send_queue *sq = &vi->sq[i]; @@ -1868,6 +1870,7 @@ static void virtnet_stats(struct net_device *dev, start = u64_stats_fetch_begin_irq(&sq->stats.syncp); tpackets = sq->stats.packets; tbytes = sq->stats.bytes; + terrors = sq->stats.tx_timeouts; } while (u64_stats_fetch_retry_irq(&sq->stats.syncp, start)); do { @@ -1882,6 +1885,7 @@ static void virtnet_stats(struct net_device *dev, tot->rx_bytes += rbytes; tot->tx_bytes += tbytes; tot->rx_dropped += rdrops; + tot->tx_errors += terrors; } tot->tx_dropped = dev->stats.tx_dropped; @@ -2534,8 +2538,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, /* XDP requires extra queues for XDP_TX */ if (curr_qp + xdp_qp > vi->max_queue_pairs) { - netdev_warn(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n", - curr_qp + xdp_qp, vi->max_queue_pairs); + netdev_warn_once(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n", + curr_qp + xdp_qp, vi->max_queue_pairs); xdp_qp = 0; } @@ -2663,6 +2667,21 @@ static int virtnet_set_features(struct net_device *dev, return 0; } +static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + struct virtnet_info *priv = netdev_priv(dev); + struct send_queue *sq = &priv->sq[txqueue]; + struct netdev_queue *txq = netdev_get_tx_queue(dev, txqueue); + + u64_stats_update_begin(&sq->stats.syncp); + sq->stats.tx_timeouts++; + u64_stats_update_end(&sq->stats.syncp); + + netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n", + txqueue, sq->name, sq->vq->index, sq->vq->name, + jiffies_to_usecs(jiffies - txq->trans_start)); +} + static const struct net_device_ops virtnet_netdev = { .ndo_open = virtnet_open, .ndo_stop = virtnet_close, @@ -2678,6 +2697,7 @@ static const struct net_device_ops virtnet_netdev = { .ndo_features_check = passthru_features_check, .ndo_get_phys_port_name = virtnet_get_phys_port_name, .ndo_set_features = virtnet_set_features, + .ndo_tx_timeout = virtnet_tx_timeout, }; static void virtnet_config_changed_work(struct work_struct *work) diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig index 77dbfc418bced7..17543be14665b7 100644 --- a/drivers/net/wwan/Kconfig +++ b/drivers/net/wwan/Kconfig @@ -71,6 +71,7 @@ config RPMSG_WWAN_CTRL config IOSM tristate "IOSM Driver for Intel M.2 WWAN Device" depends on INTEL_IOMMU + select NET_DEVLINK help This driver enables Intel M.2 WWAN Device communication. diff --git a/drivers/net/wwan/iosm/Makefile b/drivers/net/wwan/iosm/Makefile index 4f9f0ae398e159..b838034bb120e5 100644 --- a/drivers/net/wwan/iosm/Makefile +++ b/drivers/net/wwan/iosm/Makefile @@ -18,6 +18,9 @@ iosm-y = \ iosm_ipc_protocol.o \ iosm_ipc_protocol_ops.o \ iosm_ipc_mux.o \ - iosm_ipc_mux_codec.o + iosm_ipc_mux_codec.o \ + iosm_ipc_devlink.o \ + iosm_ipc_flash.o \ + iosm_ipc_coredump.o obj-$(CONFIG_IOSM) := iosm.o diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c index 519361ec40dfcb..128c999e08bb93 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.c @@ -8,7 +8,7 @@ #include "iosm_ipc_chnl_cfg.h" /* Max. sizes of a downlink buffers */ -#define IPC_MEM_MAX_DL_FLASH_BUF_SIZE (16 * 1024) +#define IPC_MEM_MAX_DL_FLASH_BUF_SIZE (64 * 1024) #define IPC_MEM_MAX_DL_LOOPBACK_SIZE (1 * 1024 * 1024) #define IPC_MEM_MAX_DL_AT_BUF_SIZE 2048 #define IPC_MEM_MAX_DL_RPC_BUF_SIZE (32 * 1024) @@ -60,6 +60,10 @@ static struct ipc_chnl_cfg modem_cfg[] = { { IPC_MEM_CTRL_CHL_ID_6, IPC_MEM_PIPE_12, IPC_MEM_PIPE_13, IPC_MEM_MAX_TDS_MBIM, IPC_MEM_MAX_TDS_MBIM, IPC_MEM_MAX_DL_MBIM_BUF_SIZE, WWAN_PORT_MBIM }, + /* Flash Channel/Coredump Channel */ + { IPC_MEM_CTRL_CHL_ID_7, IPC_MEM_PIPE_0, IPC_MEM_PIPE_1, + IPC_MEM_MAX_TDS_FLASH_UL, IPC_MEM_MAX_TDS_FLASH_DL, + IPC_MEM_MAX_DL_FLASH_BUF_SIZE, WWAN_PORT_UNKNOWN }, }; int ipc_chnl_cfg_get(struct ipc_chnl_cfg *chnl_cfg, int index) diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h index 422471367f7823..e77084e7671857 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h @@ -23,6 +23,7 @@ enum ipc_channel_id { IPC_MEM_CTRL_CHL_ID_4, IPC_MEM_CTRL_CHL_ID_5, IPC_MEM_CTRL_CHL_ID_6, + IPC_MEM_CTRL_CHL_ID_7, }; /** diff --git a/drivers/net/wwan/iosm/iosm_ipc_coredump.c b/drivers/net/wwan/iosm/iosm_ipc_coredump.c new file mode 100644 index 00000000000000..9acd87724c9de4 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_coredump.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#include "iosm_ipc_coredump.h" + +/** + * ipc_coredump_collect - To collect coredump + * @devlink: Pointer to devlink instance. + * @data: Pointer to snapshot + * @entry: ID of requested snapshot + * @region_size: Region size + * + * Returns: 0 on success, error on failure + */ +int ipc_coredump_collect(struct iosm_devlink *devlink, u8 **data, int entry, + u32 region_size) +{ + int ret, bytes_to_read, bytes_read = 0, i = 0; + s32 remaining; + u8 *data_ptr; + + data_ptr = vmalloc(region_size); + if (!data_ptr) + return -ENOMEM; + + remaining = devlink->cd_file_info[entry].actual_size; + ret = ipc_devlink_send_cmd(devlink, rpsi_cmd_coredump_get, entry); + if (ret) { + dev_err(devlink->dev, "Send coredump_get cmd failed"); + goto get_cd_fail; + } + while (remaining > 0) { + bytes_to_read = min(remaining, MAX_DATA_SIZE); + bytes_read = 0; + ret = ipc_imem_sys_devlink_read(devlink, data_ptr + i, + bytes_to_read, &bytes_read); + if (ret) { + dev_err(devlink->dev, "CD data read failed"); + goto get_cd_fail; + } + remaining -= bytes_read; + i += bytes_read; + } + + *data = data_ptr; + + return 0; + +get_cd_fail: + vfree(data_ptr); + return ret; +} + +/** + * ipc_coredump_get_list - Get coredump list from modem + * @devlink: Pointer to devlink instance. + * @cmd: RPSI command to be sent + * + * Returns: 0 on success, error on failure + */ +int ipc_coredump_get_list(struct iosm_devlink *devlink, u16 cmd) +{ + u32 byte_read, num_entries, file_size; + struct iosm_cd_table *cd_table; + u8 size[MAX_SIZE_LEN], i; + char *filename; + int ret; + + cd_table = kzalloc(MAX_CD_LIST_SIZE, GFP_KERNEL); + if (!cd_table) { + ret = -ENOMEM; + goto cd_init_fail; + } + + ret = ipc_devlink_send_cmd(devlink, cmd, MAX_CD_LIST_SIZE); + if (ret) { + dev_err(devlink->dev, "rpsi_cmd_coredump_start failed"); + goto cd_init_fail; + } + + ret = ipc_imem_sys_devlink_read(devlink, (u8 *)cd_table, + MAX_CD_LIST_SIZE, &byte_read); + if (ret) { + dev_err(devlink->dev, "Coredump data is invalid"); + goto cd_init_fail; + } + + if (byte_read != MAX_CD_LIST_SIZE) + goto cd_init_fail; + + if (cmd == rpsi_cmd_coredump_start) { + num_entries = le32_to_cpu(cd_table->list.num_entries); + if (num_entries == 0 || num_entries > IOSM_NOF_CD_REGION) { + ret = -EINVAL; + goto cd_init_fail; + } + + for (i = 0; i < num_entries; i++) { + file_size = le32_to_cpu(cd_table->list.entry[i].size); + filename = cd_table->list.entry[i].filename; + + if (file_size > devlink->cd_file_info[i].default_size) { + ret = -EINVAL; + goto cd_init_fail; + } + + devlink->cd_file_info[i].actual_size = file_size; + dev_dbg(devlink->dev, "file: %s actual size %d", + filename, file_size); + devlink_flash_update_status_notify(devlink->devlink_ctx, + filename, + "FILENAME", 0, 0); + snprintf(size, sizeof(size), "%d", file_size); + devlink_flash_update_status_notify(devlink->devlink_ctx, + size, "FILE SIZE", + 0, 0); + } + } + +cd_init_fail: + kfree(cd_table); + return ret; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_coredump.h b/drivers/net/wwan/iosm/iosm_ipc_coredump.h new file mode 100644 index 00000000000000..0809ba6642768f --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_coredump.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#ifndef _IOSM_IPC_COREDUMP_H_ +#define _IOSM_IPC_COREDUMP_H_ + +#include "iosm_ipc_devlink.h" + +/* Max number of bytes to receive for Coredump list structure */ +#define MAX_CD_LIST_SIZE 0x1000 + +/* Max buffer allocated to receive coredump data */ +#define MAX_DATA_SIZE 0x00010000 + +/* Max number of file entries */ +#define MAX_NOF_ENTRY 256 + +/* Max length */ +#define MAX_SIZE_LEN 32 + +/** + * struct iosm_cd_list_entry - Structure to hold coredump file info. + * @size: Number of bytes for the entry + * @filename: Coredump filename to be generated on host + */ +struct iosm_cd_list_entry { + __le32 size; + char filename[IOSM_MAX_FILENAME_LEN]; +} __packed; + +/** + * struct iosm_cd_list - Structure to hold list of coredump files + * to be collected. + * @num_entries: Number of entries to be received + * @entry: Contains File info + */ +struct iosm_cd_list { + __le32 num_entries; + struct iosm_cd_list_entry entry[MAX_NOF_ENTRY]; +} __packed; + +/** + * struct iosm_cd_table - Common Coredump table + * @version: Version of coredump structure + * @list: Coredump list structure + */ +struct iosm_cd_table { + __le32 version; + struct iosm_cd_list list; +} __packed; + +int ipc_coredump_collect(struct iosm_devlink *devlink, u8 **data, int entry, + u32 region_size); + +int ipc_coredump_get_list(struct iosm_devlink *devlink, u16 cmd); + +#endif /* _IOSM_IPC_COREDUMP_H_ */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.c b/drivers/net/wwan/iosm/iosm_ipc_devlink.c new file mode 100644 index 00000000000000..6fe56f73011bbf --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.c @@ -0,0 +1,372 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_coredump.h" +#include "iosm_ipc_devlink.h" +#include "iosm_ipc_flash.h" + +/* Coredump list */ +static struct iosm_coredump_file_info list[IOSM_NOF_CD_REGION] = { + {"report.json", REPORT_JSON_SIZE,}, + {"coredump.fcd", COREDUMP_FCD_SIZE,}, + {"cdd.log", CDD_LOG_SIZE,}, + {"eeprom.bin", EEPROM_BIN_SIZE,}, + {"bootcore_trace.bin", BOOTCORE_TRC_BIN_SIZE,}, + {"bootcore_prev_trace.bin", BOOTCORE_PREV_TRC_BIN_SIZE,}, +}; + +/* Get the param values for the specific param ID's */ +static int ipc_devlink_get_param(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct iosm_devlink *ipc_devlink = devlink_priv(dl); + int rc = 0; + + switch (id) { + case IOSM_DEVLINK_PARAM_ID_ERASE_FULL_FLASH: + ctx->val.vu8 = ipc_devlink->param.erase_full_flash; + break; + + case IOSM_DEVLINK_PARAM_ID_DOWNLOAD_REGION: + ctx->val.vu8 = ipc_devlink->param.download_region; + break; + + case IOSM_DEVLINK_PARAM_ID_ADDRESS: + ctx->val.vu32 = ipc_devlink->param.address; + break; + + case IOSM_DEVLINK_PARAM_ID_REGION_COUNT: + ctx->val.vu8 = ipc_devlink->param.region_count; + break; + + default: + rc = -EOPNOTSUPP; + break; + } + + return rc; +} + +/* Set the param values for the specific param ID's */ +static int ipc_devlink_set_param(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct iosm_devlink *ipc_devlink = devlink_priv(dl); + int rc = 0; + + switch (id) { + case IOSM_DEVLINK_PARAM_ID_ERASE_FULL_FLASH: + ipc_devlink->param.erase_full_flash = ctx->val.vu8; + break; + + case IOSM_DEVLINK_PARAM_ID_DOWNLOAD_REGION: + ipc_devlink->param.download_region = ctx->val.vu8; + break; + + case IOSM_DEVLINK_PARAM_ID_ADDRESS: + ipc_devlink->param.address = ctx->val.vu32; + break; + + case IOSM_DEVLINK_PARAM_ID_REGION_COUNT: + ipc_devlink->param.region_count = ctx->val.vu8; + break; + + default: + rc = -EOPNOTSUPP; + break; + } + + return rc; +} + +/* Devlink param structure array */ +static const struct devlink_param iosm_devlink_params[] = { + DEVLINK_PARAM_DRIVER(IOSM_DEVLINK_PARAM_ID_ERASE_FULL_FLASH, + "erase_full_flash", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ipc_devlink_get_param, ipc_devlink_set_param, + NULL), + DEVLINK_PARAM_DRIVER(IOSM_DEVLINK_PARAM_ID_DOWNLOAD_REGION, + "download_region", DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ipc_devlink_get_param, ipc_devlink_set_param, + NULL), + DEVLINK_PARAM_DRIVER(IOSM_DEVLINK_PARAM_ID_ADDRESS, + "address", DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ipc_devlink_get_param, ipc_devlink_set_param, + NULL), + DEVLINK_PARAM_DRIVER(IOSM_DEVLINK_PARAM_ID_REGION_COUNT, + "region_count", DEVLINK_PARAM_TYPE_U8, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ipc_devlink_get_param, ipc_devlink_set_param, + NULL), +}; + +/* Get devlink flash component type */ +static enum iosm_flash_comp_type +ipc_devlink_get_flash_comp_type(const char comp_str[], u32 len) +{ + enum iosm_flash_comp_type fls_type; + + if (!strncmp("PSI", comp_str, len)) + fls_type = FLASH_COMP_TYPE_PSI; + else if (!strncmp("EBL", comp_str, len)) + fls_type = FLASH_COMP_TYPE_EBL; + else if (!strncmp("FLS", comp_str, len)) + fls_type = FLASH_COMP_TYPE_FLS; + else + fls_type = FLASH_COMP_TYPE_INVAL; + + return fls_type; +} + +/* Function triggered on devlink flash command + * Flash update function which calls multiple functions based on + * component type specified in the flash command + */ +static int ipc_devlink_flash_update(struct devlink *devlink, + struct devlink_flash_update_params *params, + struct netlink_ext_ack *extack) +{ + struct iosm_devlink *ipc_devlink = devlink_priv(devlink); + enum iosm_flash_comp_type fls_type; + int rc = -EINVAL; + u8 *mdm_rsp; + + if (!params->component) + return -EINVAL; + + mdm_rsp = kzalloc(IOSM_EBL_DW_PACK_SIZE, GFP_KERNEL); + if (!mdm_rsp) + return -ENOMEM; + + fls_type = ipc_devlink_get_flash_comp_type(params->component, + strlen(params->component)); + + switch (fls_type) { + case FLASH_COMP_TYPE_PSI: + rc = ipc_flash_boot_psi(ipc_devlink, params->fw); + break; + case FLASH_COMP_TYPE_EBL: + rc = ipc_flash_boot_ebl(ipc_devlink, params->fw); + if (rc) + break; + rc = ipc_flash_boot_set_capabilities(ipc_devlink, mdm_rsp); + if (rc) + break; + rc = ipc_flash_read_swid(ipc_devlink, mdm_rsp); + break; + case FLASH_COMP_TYPE_FLS: + rc = ipc_flash_send_fls(ipc_devlink, params->fw, mdm_rsp); + break; + default: + devlink_flash_update_status_notify(devlink, "Invalid component", + params->component, 0, 0); + break; + } + + if (!rc) + devlink_flash_update_status_notify(devlink, "Flashing success", + params->component, 0, 0); + else + devlink_flash_update_status_notify(devlink, "Flashing failed", + params->component, 0, 0); + + kfree(mdm_rsp); + return rc; +} + +/* Call back function for devlink ops */ +static const struct devlink_ops devlink_flash_ops = { + .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT, + .flash_update = ipc_devlink_flash_update, +}; + +/** + * ipc_devlink_send_cmd - Send command to Modem + * @ipc_devlink: Pointer to struct iosm_devlink + * @cmd: Command to be sent to modem + * @entry: Command entry number + * + * Returns: 0 on success and failure value on error + */ +int ipc_devlink_send_cmd(struct iosm_devlink *ipc_devlink, u16 cmd, u32 entry) +{ + struct iosm_rpsi_cmd rpsi_cmd; + + rpsi_cmd.param.dword = cpu_to_le32(entry); + rpsi_cmd.cmd = cpu_to_le16(cmd); + rpsi_cmd.crc = rpsi_cmd.param.word[0] ^ rpsi_cmd.param.word[1] ^ + rpsi_cmd.cmd; + + return ipc_imem_sys_devlink_write(ipc_devlink, (u8 *)&rpsi_cmd, + sizeof(rpsi_cmd)); +} + +/* Function to create snapshot */ +static int ipc_devlink_coredump_snapshot(struct devlink *dl, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u8 **data) +{ + struct iosm_devlink *ipc_devlink = devlink_priv(dl); + struct iosm_coredump_file_info *cd_list = ops->priv; + u32 region_size; + int rc; + + dev_dbg(ipc_devlink->dev, "Region:%s, ID:%d", ops->name, + cd_list->entry); + region_size = cd_list->default_size; + rc = ipc_coredump_collect(ipc_devlink, data, cd_list->entry, + region_size); + if (rc) { + dev_err(ipc_devlink->dev, "Fail to create snapshot,err %d", rc); + goto coredump_collect_err; + } + + /* Send coredump end cmd indicating end of coredump collection */ + if (cd_list->entry == (IOSM_NOF_CD_REGION - 1)) + ipc_coredump_get_list(ipc_devlink, rpsi_cmd_coredump_end); + + return 0; + +coredump_collect_err: + ipc_coredump_get_list(ipc_devlink, rpsi_cmd_coredump_end); + return rc; +} + +/* To create regions for coredump files */ +static int ipc_devlink_create_region(struct iosm_devlink *devlink) +{ + struct devlink_region_ops *mdm_coredump; + int rc = 0; + int i; + + mdm_coredump = devlink->iosm_devlink_mdm_coredump; + for (i = 0; i < IOSM_NOF_CD_REGION; i++) { + mdm_coredump[i].name = list[i].filename; + mdm_coredump[i].snapshot = ipc_devlink_coredump_snapshot; + mdm_coredump[i].destructor = vfree; + devlink->cd_regions[i] = + devlink_region_create(devlink->devlink_ctx, + &mdm_coredump[i], MAX_SNAPSHOTS, + list[i].default_size); + + if (IS_ERR(devlink->cd_regions[i])) { + rc = PTR_ERR(devlink->cd_regions[i]); + dev_err(devlink->dev, "Devlink region fail,err %d", rc); + /* Delete previously created regions */ + for ( ; i >= 0; i--) + devlink_region_destroy(devlink->cd_regions[i]); + goto region_create_fail; + } + list[i].entry = i; + mdm_coredump[i].priv = list + i; + } +region_create_fail: + return rc; +} + +/* To Destroy devlink regions */ +static void ipc_devlink_destroy_region(struct iosm_devlink *ipc_devlink) +{ + u8 i; + + for (i = 0; i < IOSM_NOF_CD_REGION; i++) + devlink_region_destroy(ipc_devlink->cd_regions[i]); +} + +/** + * ipc_devlink_init - Initialize/register devlink to IOSM driver + * @ipc_imem: Pointer to struct iosm_imem + * + * Returns: Pointer to iosm_devlink on success and NULL on failure + */ +struct iosm_devlink *ipc_devlink_init(struct iosm_imem *ipc_imem) +{ + struct ipc_chnl_cfg chnl_cfg_flash = { 0 }; + struct iosm_devlink *ipc_devlink; + struct devlink *devlink_ctx; + int rc; + + devlink_ctx = devlink_alloc(&devlink_flash_ops, + sizeof(struct iosm_devlink), + ipc_imem->dev); + if (!devlink_ctx) { + dev_err(ipc_imem->dev, "devlink_alloc failed"); + goto devlink_alloc_fail; + } + + ipc_devlink = devlink_priv(devlink_ctx); + ipc_devlink->devlink_ctx = devlink_ctx; + ipc_devlink->pcie = ipc_imem->pcie; + ipc_devlink->dev = ipc_imem->dev; + + rc = devlink_params_register(devlink_ctx, iosm_devlink_params, + ARRAY_SIZE(iosm_devlink_params)); + if (rc) { + dev_err(ipc_devlink->dev, + "devlink_params_register failed. rc %d", rc); + goto param_reg_fail; + } + + ipc_devlink->cd_file_info = list; + + rc = ipc_devlink_create_region(ipc_devlink); + if (rc) { + dev_err(ipc_devlink->dev, "Devlink Region create failed, rc %d", + rc); + goto region_create_fail; + } + + if (ipc_chnl_cfg_get(&chnl_cfg_flash, IPC_MEM_CTRL_CHL_ID_7) < 0) + goto chnl_get_fail; + + ipc_imem_channel_init(ipc_imem, IPC_CTYPE_CTRL, + chnl_cfg_flash, IRQ_MOD_OFF); + + init_completion(&ipc_devlink->devlink_sio.read_sem); + skb_queue_head_init(&ipc_devlink->devlink_sio.rx_list); + + devlink_register(devlink_ctx); + dev_dbg(ipc_devlink->dev, "iosm devlink register success"); + + return ipc_devlink; + +chnl_get_fail: + ipc_devlink_destroy_region(ipc_devlink); +region_create_fail: + devlink_params_unregister(devlink_ctx, iosm_devlink_params, + ARRAY_SIZE(iosm_devlink_params)); +param_reg_fail: + devlink_free(devlink_ctx); +devlink_alloc_fail: + return NULL; +} + +/** + * ipc_devlink_deinit - To unintialize the devlink from IOSM driver. + * @ipc_devlink: Devlink instance + */ +void ipc_devlink_deinit(struct iosm_devlink *ipc_devlink) +{ + struct devlink *devlink_ctx = ipc_devlink->devlink_ctx; + + devlink_unregister(devlink_ctx); + ipc_devlink_destroy_region(ipc_devlink); + devlink_params_unregister(devlink_ctx, iosm_devlink_params, + ARRAY_SIZE(iosm_devlink_params)); + if (ipc_devlink->devlink_sio.devlink_read_pend) { + complete(&ipc_devlink->devlink_sio.read_sem); + complete(&ipc_devlink->devlink_sio.channel->ul_sem); + } + if (!ipc_devlink->devlink_sio.devlink_read_pend) + skb_queue_purge(&ipc_devlink->devlink_sio.rx_list); + + ipc_imem_sys_devlink_close(ipc_devlink); + devlink_free(devlink_ctx); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_devlink.h b/drivers/net/wwan/iosm/iosm_ipc_devlink.h new file mode 100644 index 00000000000000..fa2b388a2f8a3e --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_devlink.h @@ -0,0 +1,189 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#ifndef _IOSM_IPC_DEVLINK_H_ +#define _IOSM_IPC_DEVLINK_H_ + +#include <net/devlink.h> + +#include "iosm_ipc_imem.h" +#include "iosm_ipc_imem_ops.h" +#include "iosm_ipc_pcie.h" + +/* MAX file name length */ +#define IOSM_MAX_FILENAME_LEN 32 +/* EBL response size */ +#define IOSM_EBL_RSP_SIZE 76 +/* MAX number of regions supported */ +#define IOSM_NOF_CD_REGION 6 +/* MAX number of SNAPSHOTS supported */ +#define MAX_SNAPSHOTS 1 +/* Default Coredump file size */ +#define REPORT_JSON_SIZE 0x800 +#define COREDUMP_FCD_SIZE 0x10E00000 +#define CDD_LOG_SIZE 0x30000 +#define EEPROM_BIN_SIZE 0x10000 +#define BOOTCORE_TRC_BIN_SIZE 0x8000 +#define BOOTCORE_PREV_TRC_BIN_SIZE 0x20000 + +/** + * enum iosm_devlink_param_id - Enum type to different devlink params + * @IOSM_DEVLINK_PARAM_ID_BASE: Devlink param base ID + * @IOSM_DEVLINK_PARAM_ID_ERASE_FULL_FLASH: Set if full erase required + * @IOSM_DEVLINK_PARAM_ID_DOWNLOAD_REGION: Set if fls file to be + * flashed is Loadmap/region file + * @IOSM_DEVLINK_PARAM_ID_ADDRESS: Address of the region to be + * flashed + * @IOSM_DEVLINK_PARAM_ID_REGION_COUNT: Max region count + */ + +enum iosm_devlink_param_id { + IOSM_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + IOSM_DEVLINK_PARAM_ID_ERASE_FULL_FLASH, + IOSM_DEVLINK_PARAM_ID_DOWNLOAD_REGION, + IOSM_DEVLINK_PARAM_ID_ADDRESS, + IOSM_DEVLINK_PARAM_ID_REGION_COUNT, +}; + +/** + * enum iosm_rpsi_cmd_code - Enum type for RPSI command list + * @rpsi_cmd_code_ebl: Command to load ebl + * @rpsi_cmd_coredump_start: Command to get list of files and + * file size info from PSI + * @rpsi_cmd_coredump_get: Command to get the coredump data + * @rpsi_cmd_coredump_end: Command to stop receiving the coredump + */ +enum iosm_rpsi_cmd_code { + rpsi_cmd_code_ebl = 0x02, + rpsi_cmd_coredump_start = 0x10, + rpsi_cmd_coredump_get = 0x11, + rpsi_cmd_coredump_end = 0x12, +}; + +/** + * enum iosm_flash_comp_type - Enum for different flash component types + * @FLASH_COMP_TYPE_PSI: PSI flash comp type + * @FLASH_COMP_TYPE_EBL: EBL flash comp type + * @FLASH_COMP_TYPE_FLS: FLS flash comp type + * @FLASH_COMP_TYPE_INVAL: Invalid flash comp type + */ +enum iosm_flash_comp_type { + FLASH_COMP_TYPE_PSI, + FLASH_COMP_TYPE_EBL, + FLASH_COMP_TYPE_FLS, + FLASH_COMP_TYPE_INVAL, +}; + +/** + * struct iosm_devlink_sio - SIO instance + * @rx_list: Downlink skbuf list received from CP + * @read_sem: Needed for the blocking read or downlink transfer + * @channel_id: Reserved channel id for flashing/CD collection to RAM + * @channel: Channel instance for flashing and coredump + * @devlink_read_pend: Check if read is pending + */ +struct iosm_devlink_sio { + struct sk_buff_head rx_list; + struct completion read_sem; + int channel_id; + struct ipc_mem_channel *channel; + u32 devlink_read_pend; +}; + +/** + * struct iosm_flash_params - List of flash params required for flashing + * @address: Address of the region file to be flashed + * @region_count: Maximum no of regions for each fls file + * @download_region: To be set if region is being flashed + * @erase_full_flash: To set the flashing mode + * erase_full_flash = 1; full erase + * erase_full_flash = 0; no erase + * @erase_full_flash_done: Flag to check if it is a full erase + */ +struct iosm_flash_params { + u32 address; + u8 region_count; + u8 download_region; + u8 erase_full_flash; + u8 erase_full_flash_done; +}; + +/** + * struct iosm_ebl_ctx_data - EBL ctx data used during flashing + * @ebl_sw_info_version: SWID version info obtained from EBL + * @m_ebl_resp: Buffer used to read and write the ebl data + */ +struct iosm_ebl_ctx_data { + u8 ebl_sw_info_version; + u8 m_ebl_resp[IOSM_EBL_RSP_SIZE]; +}; + +/** + * struct iosm_coredump_file_info - Coredump file info + * @filename: Name of coredump file + * @default_size: Default size of coredump file + * @actual_size: Actual size of coredump file + * @entry: Index of the coredump file + */ +struct iosm_coredump_file_info { + char filename[IOSM_MAX_FILENAME_LEN]; + u32 default_size; + u32 actual_size; + u32 entry; +}; + +/** + * struct iosm_devlink - IOSM Devlink structure + * @devlink_sio: SIO instance for read/write functionality + * @pcie: Pointer to PCIe component + * @dev: Pointer to device struct + * @devlink_ctx: Pointer to devlink context + * @param: Params required for flashing + * @ebl_ctx: Data to be read and written to Modem + * @cd_file_info: coredump file info + * @iosm_devlink_mdm_coredump: region ops for coredump collection + * @cd_regions: coredump regions + */ +struct iosm_devlink { + struct iosm_devlink_sio devlink_sio; + struct iosm_pcie *pcie; + struct device *dev; + struct devlink *devlink_ctx; + struct iosm_flash_params param; + struct iosm_ebl_ctx_data ebl_ctx; + struct iosm_coredump_file_info *cd_file_info; + struct devlink_region_ops iosm_devlink_mdm_coredump[IOSM_NOF_CD_REGION]; + struct devlink_region *cd_regions[IOSM_NOF_CD_REGION]; +}; + +/** + * union iosm_rpsi_param_u - RPSI cmd param for CRC calculation + * @word: Words member used in CRC calculation + * @dword: Actual data + */ +union iosm_rpsi_param_u { + __le16 word[2]; + __le32 dword; +}; + +/** + * struct iosm_rpsi_cmd - Structure for RPSI Command + * @param: Used to calculate CRC + * @cmd: Stores the RPSI command + * @crc: Stores the CRC value + */ +struct iosm_rpsi_cmd { + union iosm_rpsi_param_u param; + __le16 cmd; + __le16 crc; +}; + +struct iosm_devlink *ipc_devlink_init(struct iosm_imem *ipc_imem); + +void ipc_devlink_deinit(struct iosm_devlink *ipc_devlink); + +int ipc_devlink_send_cmd(struct iosm_devlink *ipc_devlink, u16 cmd, u32 entry); + +#endif /* _IOSM_IPC_DEVLINK_H */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_flash.c b/drivers/net/wwan/iosm/iosm_ipc_flash.c new file mode 100644 index 00000000000000..ebceedf7c9f5b1 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_flash.c @@ -0,0 +1,588 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#include "iosm_ipc_coredump.h" +#include "iosm_ipc_devlink.h" +#include "iosm_ipc_flash.h" + +/* This function will pack the data to be sent to the modem using the + * payload, payload length and pack id + */ +static int ipc_flash_proc_format_ebl_pack(struct iosm_flash_data *flash_req, + u32 pack_length, u16 pack_id, + u8 *payload, u32 payload_length) +{ + u16 checksum = pack_id; + u32 i; + + if (payload_length + IOSM_EBL_HEAD_SIZE > pack_length) + return -EINVAL; + + flash_req->pack_id = cpu_to_le16(pack_id); + flash_req->msg_length = cpu_to_le32(payload_length); + checksum += (payload_length >> IOSM_EBL_PAYL_SHIFT) + + (payload_length & IOSM_EBL_CKSM); + + for (i = 0; i < payload_length; i++) + checksum += payload[i]; + + flash_req->checksum = cpu_to_le16(checksum); + + return 0; +} + +/* validate the response received from modem and + * check the type of errors received + */ +static int ipc_flash_proc_check_ebl_rsp(void *hdr_rsp, void *payload_rsp) +{ + struct iosm_ebl_error *err_info = payload_rsp; + u16 *rsp_code = hdr_rsp; + u32 i; + + if (*rsp_code == IOSM_EBL_RSP_BUFF) { + for (i = 0; i < IOSM_MAX_ERRORS; i++) { + if (!err_info->error[i].error_code) { + pr_err("EBL: error_class = %d, error_code = %d", + err_info->error[i].error_class, + err_info->error[i].error_code); + } + } + return -EINVAL; + } + + return 0; +} + +/* Send data to the modem */ +static int ipc_flash_send_data(struct iosm_devlink *ipc_devlink, u32 size, + u16 pack_id, u8 *payload, u32 payload_length) +{ + struct iosm_flash_data flash_req; + int ret; + + ret = ipc_flash_proc_format_ebl_pack(&flash_req, size, + pack_id, payload, payload_length); + if (ret) { + dev_err(ipc_devlink->dev, "EBL2 pack failed for pack_id:%d", + pack_id); + goto ipc_free_payload; + } + + ret = ipc_imem_sys_devlink_write(ipc_devlink, (u8 *)&flash_req, + IOSM_EBL_HEAD_SIZE); + if (ret) { + dev_err(ipc_devlink->dev, "EBL Header write failed for Id:%x", + pack_id); + goto ipc_free_payload; + } + + ret = ipc_imem_sys_devlink_write(ipc_devlink, payload, payload_length); + if (ret) { + dev_err(ipc_devlink->dev, "EBL Payload write failed for Id:%x", + pack_id); + } + +ipc_free_payload: + return ret; +} + +/** + * ipc_flash_link_establish - Flash link establishment + * @ipc_imem: Pointer to struct iosm_imem + * + * Returns: 0 on success and failure value on error + */ +int ipc_flash_link_establish(struct iosm_imem *ipc_imem) +{ + u8 ler_data[IOSM_LER_RSP_SIZE]; + u32 bytes_read; + + /* Allocate channel for flashing/cd collection */ + ipc_imem->ipc_devlink->devlink_sio.channel = + ipc_imem_sys_devlink_open(ipc_imem); + + if (!ipc_imem->ipc_devlink->devlink_sio.channel) + goto chl_open_fail; + + if (ipc_imem_sys_devlink_read(ipc_imem->ipc_devlink, ler_data, + IOSM_LER_RSP_SIZE, &bytes_read)) + goto devlink_read_fail; + + if (bytes_read != IOSM_LER_RSP_SIZE) + goto devlink_read_fail; + + return 0; + +devlink_read_fail: + ipc_imem_sys_devlink_close(ipc_imem->ipc_devlink); +chl_open_fail: + return -EIO; +} + +/* Receive data from the modem */ +static int ipc_flash_receive_data(struct iosm_devlink *ipc_devlink, u32 size, + u8 *mdm_rsp) +{ + u8 mdm_rsp_hdr[IOSM_EBL_HEAD_SIZE]; + u32 bytes_read; + int ret; + + ret = ipc_imem_sys_devlink_read(ipc_devlink, mdm_rsp_hdr, + IOSM_EBL_HEAD_SIZE, &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "EBL rsp to read %d bytes failed", + IOSM_EBL_HEAD_SIZE); + goto ipc_flash_recv_err; + } + + if (bytes_read != IOSM_EBL_HEAD_SIZE) { + ret = -EINVAL; + goto ipc_flash_recv_err; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, mdm_rsp, size, + &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "EBL rsp to read %d bytes failed", + size); + goto ipc_flash_recv_err; + } + + if (bytes_read != size) { + ret = -EINVAL; + goto ipc_flash_recv_err; + } + + ret = ipc_flash_proc_check_ebl_rsp(mdm_rsp_hdr + 2, mdm_rsp); + +ipc_flash_recv_err: + return ret; +} + +/* Function to send command to modem and receive response */ +static int ipc_flash_send_receive(struct iosm_devlink *ipc_devlink, u16 pack_id, + u8 *payload, u32 payload_length, u8 *mdm_rsp) +{ + size_t frame_len = IOSM_EBL_DW_PACK_SIZE; + int ret; + + if (pack_id == FLASH_SET_PROT_CONF) + frame_len = IOSM_EBL_W_PACK_SIZE; + + ret = ipc_flash_send_data(ipc_devlink, frame_len, pack_id, payload, + payload_length); + if (ret) + goto ipc_flash_send_rcv; + + ret = ipc_flash_receive_data(ipc_devlink, + frame_len - IOSM_EBL_HEAD_SIZE, mdm_rsp); + +ipc_flash_send_rcv: + return ret; +} + +/** + * ipc_flash_boot_set_capabilities - Set modem boot capabilities in flash + * @ipc_devlink: Pointer to devlink structure + * @mdm_rsp: Pointer to modem response buffer + * + * Returns: 0 on success and failure value on error + */ +int ipc_flash_boot_set_capabilities(struct iosm_devlink *ipc_devlink, + u8 *mdm_rsp) +{ + ipc_devlink->ebl_ctx.ebl_sw_info_version = + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_RSP_SW_INFO_VER]; + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_SKIP_ERASE] = IOSM_CAP_NOT_ENHANCED; + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_SKIP_CRC] = IOSM_CAP_NOT_ENHANCED; + + if (ipc_devlink->ebl_ctx.m_ebl_resp[EBL_CAPS_FLAG] & + IOSM_CAP_USE_EXT_CAP) { + if (ipc_devlink->param.erase_full_flash) + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_OOS_CONFIG] &= + ~((u8)IOSM_EXT_CAP_ERASE_ALL); + else + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_OOS_CONFIG] &= + ~((u8)IOSM_EXT_CAP_COMMIT_ALL); + ipc_devlink->ebl_ctx.m_ebl_resp[EBL_EXT_CAPS_HANDLED] = + IOSM_CAP_USE_EXT_CAP; + } + + /* Write back the EBL capability to modem + * Request Set Protcnf command + */ + return ipc_flash_send_receive(ipc_devlink, FLASH_SET_PROT_CONF, + ipc_devlink->ebl_ctx.m_ebl_resp, + IOSM_EBL_RSP_SIZE, mdm_rsp); +} + +/* Read the SWID type and SWID value from the EBL */ +int ipc_flash_read_swid(struct iosm_devlink *ipc_devlink, u8 *mdm_rsp) +{ + struct iosm_flash_msg_control cmd_msg; + struct iosm_swid_table *swid; + char ebl_swid[IOSM_SWID_STR]; + int ret; + + if (ipc_devlink->ebl_ctx.ebl_sw_info_version != + IOSM_EXT_CAP_SWID_OOS_PACK) + return -EINVAL; + + cmd_msg.action = cpu_to_le32(FLASH_OOSC_ACTION_READ); + cmd_msg.type = cpu_to_le32(FLASH_OOSC_TYPE_SWID_TABLE); + cmd_msg.length = cpu_to_le32(IOSM_MSG_LEN_ARG); + cmd_msg.arguments = cpu_to_le32(IOSM_MSG_LEN_ARG); + + ret = ipc_flash_send_receive(ipc_devlink, FLASH_OOS_CONTROL, + (u8 *)&cmd_msg, IOSM_MDM_SEND_16, mdm_rsp); + if (ret) + goto ipc_swid_err; + + cmd_msg.action = cpu_to_le32(*((u32 *)mdm_rsp)); + + ret = ipc_flash_send_receive(ipc_devlink, FLASH_OOS_DATA_READ, + (u8 *)&cmd_msg, IOSM_MDM_SEND_4, mdm_rsp); + if (ret) + goto ipc_swid_err; + + swid = (struct iosm_swid_table *)mdm_rsp; + dev_dbg(ipc_devlink->dev, "SWID %x RF_ENGINE_ID %x", swid->sw_id_val, + swid->rf_engine_id_val); + + snprintf(ebl_swid, sizeof(ebl_swid), "SWID: %x, RF_ENGINE_ID: %x", + swid->sw_id_val, swid->rf_engine_id_val); + + devlink_flash_update_status_notify(ipc_devlink->devlink_ctx, ebl_swid, + NULL, 0, 0); +ipc_swid_err: + return ret; +} + +/* Function to check if full erase or conditional erase was successful */ +static int ipc_flash_erase_check(struct iosm_devlink *ipc_devlink, u8 *mdm_rsp) +{ + int ret, count = 0; + u16 mdm_rsp_data; + + /* Request Flash Erase Check */ + do { + mdm_rsp_data = IOSM_MDM_SEND_DATA; + ret = ipc_flash_send_receive(ipc_devlink, FLASH_ERASE_CHECK, + (u8 *)&mdm_rsp_data, + IOSM_MDM_SEND_2, mdm_rsp); + if (ret) + goto ipc_erase_chk_err; + + mdm_rsp_data = *((u16 *)mdm_rsp); + if (mdm_rsp_data > IOSM_MDM_ERASE_RSP) { + dev_err(ipc_devlink->dev, + "Flash Erase Check resp wrong 0x%04X", + mdm_rsp_data); + ret = -EINVAL; + goto ipc_erase_chk_err; + } + count++; + msleep(IOSM_FLASH_ERASE_CHECK_INTERVAL); + } while ((mdm_rsp_data != IOSM_MDM_ERASE_RSP) && + (count < (IOSM_FLASH_ERASE_CHECK_TIMEOUT / + IOSM_FLASH_ERASE_CHECK_INTERVAL))); + + if (mdm_rsp_data != IOSM_MDM_ERASE_RSP) { + dev_err(ipc_devlink->dev, "Modem erase check timeout failure!"); + ret = -ETIMEDOUT; + } + +ipc_erase_chk_err: + return ret; +} + +/* Full erase function which will erase the nand flash through EBL command */ +static int ipc_flash_full_erase(struct iosm_devlink *ipc_devlink, u8 *mdm_rsp) +{ + u32 erase_address = IOSM_ERASE_START_ADDR; + struct iosm_flash_msg_control cmd_msg; + u32 erase_length = IOSM_ERASE_LEN; + int ret; + + dev_dbg(ipc_devlink->dev, "Erase full nand flash"); + cmd_msg.action = cpu_to_le32(FLASH_OOSC_ACTION_ERASE); + cmd_msg.type = cpu_to_le32(FLASH_OOSC_TYPE_ALL_FLASH); + cmd_msg.length = cpu_to_le32(erase_length); + cmd_msg.arguments = cpu_to_le32(erase_address); + + ret = ipc_flash_send_receive(ipc_devlink, FLASH_OOS_CONTROL, + (unsigned char *)&cmd_msg, + IOSM_MDM_SEND_16, mdm_rsp); + if (ret) + goto ipc_flash_erase_err; + + ipc_devlink->param.erase_full_flash_done = IOSM_SET_FLAG; + ret = ipc_flash_erase_check(ipc_devlink, mdm_rsp); + +ipc_flash_erase_err: + return ret; +} + +/* Logic for flashing all the Loadmaps available for individual fls file */ +static int ipc_flash_download_region(struct iosm_devlink *ipc_devlink, + const struct firmware *fw, u8 *mdm_rsp) +{ + __le32 reg_info[2]; /* 0th position region address, 1st position size */ + char *file_ptr; + u32 rest_len; + u32 raw_len; + int ret; + + file_ptr = (char *)fw->data; + reg_info[0] = cpu_to_le32(ipc_devlink->param.address); + + if (!ipc_devlink->param.erase_full_flash_done) { + reg_info[1] = cpu_to_le32(ipc_devlink->param.address + + fw->size - 2); + ret = ipc_flash_send_receive(ipc_devlink, FLASH_ERASE_START, + (u8 *)reg_info, IOSM_MDM_SEND_8, + mdm_rsp); + if (ret) + goto dl_region_fail; + + ret = ipc_flash_erase_check(ipc_devlink, mdm_rsp); + if (ret) + goto dl_region_fail; + } + + /* Request Flash Set Address */ + ret = ipc_flash_send_receive(ipc_devlink, FLASH_SET_ADDRESS, + (u8 *)reg_info, IOSM_MDM_SEND_4, mdm_rsp); + if (ret) + goto dl_region_fail; + + rest_len = fw->size; + + /* Request Flash Write Raw Image */ + ret = ipc_flash_send_data(ipc_devlink, IOSM_EBL_DW_PACK_SIZE, + FLASH_WRITE_IMAGE_RAW, (u8 *)&rest_len, + IOSM_MDM_SEND_4); + if (ret) + goto dl_region_fail; + + do { + raw_len = (rest_len > IOSM_FLS_BUF_SIZE) ? IOSM_FLS_BUF_SIZE : + rest_len; + ret = ipc_imem_sys_devlink_write(ipc_devlink, file_ptr, + raw_len); + if (ret) { + dev_err(ipc_devlink->dev, "Image write failed"); + goto dl_region_fail; + } + file_ptr += raw_len; + rest_len -= raw_len; + } while (rest_len); + + ret = ipc_flash_receive_data(ipc_devlink, IOSM_EBL_DW_PAYL_SIZE, + mdm_rsp); + +dl_region_fail: + return ret; +} + +/** + * ipc_flash_send_fls - Inject Modem subsystem fls file to device + * @ipc_devlink: Pointer to devlink structure + * @fw: FW image + * @mdm_rsp: Pointer to modem response buffer + * + * Returns: 0 on success and failure value on error + */ +int ipc_flash_send_fls(struct iosm_devlink *ipc_devlink, + const struct firmware *fw, u8 *mdm_rsp) +{ + u16 flash_cmd; + int ret; + + if (ipc_devlink->param.erase_full_flash) { + ipc_devlink->param.erase_full_flash = false; + ret = ipc_flash_full_erase(ipc_devlink, mdm_rsp); + if (ret) + goto ipc_flash_err; + } + + /* Request Sec Start */ + if (!ipc_devlink->param.download_region) { + ret = ipc_flash_send_receive(ipc_devlink, FLASH_SEC_START, + (u8 *)fw->data, fw->size, mdm_rsp); + if (ret) + goto ipc_flash_err; + } else { + /* Download regions */ + ipc_devlink->param.region_count -= IOSM_SET_FLAG; + ret = ipc_flash_download_region(ipc_devlink, fw, mdm_rsp); + if (ret) + goto ipc_flash_err; + + if (!ipc_devlink->param.region_count) { + /* Request Sec End */ + flash_cmd = IOSM_MDM_SEND_DATA; + ret = ipc_flash_send_receive(ipc_devlink, FLASH_SEC_END, + (u8 *)&flash_cmd, + IOSM_MDM_SEND_2, mdm_rsp); + } + } + +ipc_flash_err: + return ret; +} + +/** + * ipc_flash_boot_psi - Inject PSI image + * @ipc_devlink: Pointer to devlink structure + * @fw: FW image + * + * Returns: 0 on success and failure value on error + */ +int ipc_flash_boot_psi(struct iosm_devlink *ipc_devlink, + const struct firmware *fw) +{ + u8 psi_ack_byte[IOSM_PSI_ACK], read_data[2]; + u32 bytes_read; + u8 *psi_code; + int ret; + + dev_dbg(ipc_devlink->dev, "Boot transfer PSI"); + psi_code = kmemdup(fw->data, fw->size, GFP_KERNEL); + if (!psi_code) + return -ENOMEM; + + ret = ipc_imem_sys_devlink_write(ipc_devlink, psi_code, fw->size); + if (ret) { + dev_err(ipc_devlink->dev, "RPSI Image write failed"); + goto ipc_flash_psi_free; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, read_data, + IOSM_LER_ACK_SIZE, &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "ipc_devlink_sio_read ACK failed"); + goto ipc_flash_psi_free; + } + + if (bytes_read != IOSM_LER_ACK_SIZE) { + ret = -EINVAL; + goto ipc_flash_psi_free; + } + + snprintf(psi_ack_byte, sizeof(psi_ack_byte), "%x%x", read_data[0], + read_data[1]); + devlink_flash_update_status_notify(ipc_devlink->devlink_ctx, + psi_ack_byte, "PSI ACK", 0, 0); + + if (read_data[0] == 0x00 && read_data[1] == 0xCD) { + dev_dbg(ipc_devlink->dev, "Coredump detected"); + ret = ipc_coredump_get_list(ipc_devlink, + rpsi_cmd_coredump_start); + if (ret) + dev_err(ipc_devlink->dev, "Failed to get cd list"); + } + +ipc_flash_psi_free: + kfree(psi_code); + return ret; +} + +/** + * ipc_flash_boot_ebl - Inject EBL image + * @ipc_devlink: Pointer to devlink structure + * @fw: FW image + * + * Returns: 0 on success and failure value on error + */ +int ipc_flash_boot_ebl(struct iosm_devlink *ipc_devlink, + const struct firmware *fw) +{ + u32 ebl_size = fw->size; + u8 read_data[2]; + u32 bytes_read; + int ret; + + if (ipc_mmio_get_exec_stage(ipc_devlink->pcie->imem->mmio) != + IPC_MEM_EXEC_STAGE_PSI) { + devlink_flash_update_status_notify(ipc_devlink->devlink_ctx, + "Invalid execution stage", + NULL, 0, 0); + return -EINVAL; + } + + dev_dbg(ipc_devlink->dev, "Boot transfer EBL"); + ret = ipc_devlink_send_cmd(ipc_devlink, rpsi_cmd_code_ebl, + IOSM_RPSI_LOAD_SIZE); + if (ret) { + dev_err(ipc_devlink->dev, "Sending rpsi_cmd_code_ebl failed"); + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, read_data, IOSM_READ_SIZE, + &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "rpsi_cmd_code_ebl read failed"); + goto ipc_flash_ebl_err; + } + + if (bytes_read != IOSM_READ_SIZE) { + ret = -EINVAL; + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_write(ipc_devlink, (u8 *)&ebl_size, + sizeof(ebl_size)); + if (ret) { + dev_err(ipc_devlink->dev, "EBL length write failed"); + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, read_data, IOSM_READ_SIZE, + &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "EBL read failed"); + goto ipc_flash_ebl_err; + } + + if (bytes_read != IOSM_READ_SIZE) { + ret = -EINVAL; + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_write(ipc_devlink, (unsigned char *)fw->data, + fw->size); + if (ret) { + dev_err(ipc_devlink->dev, "EBL data transfer failed"); + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, read_data, IOSM_READ_SIZE, + &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "EBL read failed"); + goto ipc_flash_ebl_err; + } + + if (bytes_read != IOSM_READ_SIZE) { + ret = -EINVAL; + goto ipc_flash_ebl_err; + } + + ret = ipc_imem_sys_devlink_read(ipc_devlink, + ipc_devlink->ebl_ctx.m_ebl_resp, + IOSM_EBL_RSP_SIZE, &bytes_read); + if (ret) { + dev_err(ipc_devlink->dev, "EBL response read failed"); + goto ipc_flash_ebl_err; + } + + if (bytes_read != IOSM_EBL_RSP_SIZE) + ret = -EINVAL; + +ipc_flash_ebl_err: + return ret; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_flash.h b/drivers/net/wwan/iosm/iosm_ipc_flash.h new file mode 100644 index 00000000000000..132d59d60fbe75 --- /dev/null +++ b/drivers/net/wwan/iosm/iosm_ipc_flash.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Copyright (C) 2020-2021 Intel Corporation. + */ + +#ifndef _IOSM_IPC_FLASH_H +#define _IOSM_IPC_FLASH_H + +/* Buffer size used to read the fls image */ +#define IOSM_FLS_BUF_SIZE 0x00100000 +/* Full erase start address */ +#define IOSM_ERASE_START_ADDR 0x00000000 +/* Erase length for NAND flash */ +#define IOSM_ERASE_LEN 0xFFFFFFFF +/* EBL response Header size */ +#define IOSM_EBL_HEAD_SIZE 8 +/* EBL payload size */ +#define IOSM_EBL_W_PAYL_SIZE 2048 +/* Total EBL pack size */ +#define IOSM_EBL_W_PACK_SIZE (IOSM_EBL_HEAD_SIZE + IOSM_EBL_W_PAYL_SIZE) +/* EBL payload size */ +#define IOSM_EBL_DW_PAYL_SIZE 16384 +/* Total EBL pack size */ +#define IOSM_EBL_DW_PACK_SIZE (IOSM_EBL_HEAD_SIZE + IOSM_EBL_DW_PAYL_SIZE) +/* EBL name size */ +#define IOSM_EBL_NAME 32 +/* Maximum supported error types */ +#define IOSM_MAX_ERRORS 8 +/* Read size for RPSI/EBL response */ +#define IOSM_READ_SIZE 2 +/* Link establishment response ack size */ +#define IOSM_LER_ACK_SIZE 2 +/* PSI ACK len */ +#define IOSM_PSI_ACK 8 +/* SWID capability for packed swid type */ +#define IOSM_EXT_CAP_SWID_OOS_PACK 0x02 +/* EBL error response buffer */ +#define IOSM_EBL_RSP_BUFF 0x0041 +/* SWID string length */ +#define IOSM_SWID_STR 64 +/* Load EBL command size */ +#define IOSM_RPSI_LOAD_SIZE 0 +/* EBL payload checksum */ +#define IOSM_EBL_CKSM 0x0000FFFF +/* SWID msg len and argument */ +#define IOSM_MSG_LEN_ARG 0 +/* Data to be sent to modem */ +#define IOSM_MDM_SEND_DATA 0x0000 +/* Data received from modem as part of erase check */ +#define IOSM_MDM_ERASE_RSP 0x0001 +/* Bit shift to calculate Checksum */ +#define IOSM_EBL_PAYL_SHIFT 16 +/* Flag To be set */ +#define IOSM_SET_FLAG 1 +/* Set flash erase check timeout to 100 msec */ +#define IOSM_FLASH_ERASE_CHECK_TIMEOUT 100 +/* Set flash erase check interval to 20 msec */ +#define IOSM_FLASH_ERASE_CHECK_INTERVAL 20 +/* Link establishment response ack size */ +#define IOSM_LER_RSP_SIZE 60 + +/** + * enum iosm_flash_package_type - Enum for the flashing operations + * @FLASH_SET_PROT_CONF: Write EBL capabilities + * @FLASH_SEC_START: Start writing the secpack + * @FLASH_SEC_END: Validate secpack end + * @FLASH_SET_ADDRESS: Set the address for flashing + * @FLASH_ERASE_START: Start erase before flashing + * @FLASH_ERASE_CHECK: Validate the erase functionality + * @FLASH_OOS_CONTROL: Retrieve data based on oos actions + * @FLASH_OOS_DATA_READ: Read data from EBL + * @FLASH_WRITE_IMAGE_RAW: Write the raw image to flash + */ +enum iosm_flash_package_type { + FLASH_SET_PROT_CONF = 0x0086, + FLASH_SEC_START = 0x0204, + FLASH_SEC_END, + FLASH_SET_ADDRESS = 0x0802, + FLASH_ERASE_START = 0x0805, + FLASH_ERASE_CHECK, + FLASH_OOS_CONTROL = 0x080C, + FLASH_OOS_DATA_READ = 0x080E, + FLASH_WRITE_IMAGE_RAW, +}; + +/** + * enum iosm_out_of_session_action - Actions possible over the + * OutOfSession command interface + * @FLASH_OOSC_ACTION_READ: Read data according to its type + * @FLASH_OOSC_ACTION_ERASE: Erase data according to its type + */ +enum iosm_out_of_session_action { + FLASH_OOSC_ACTION_READ = 2, + FLASH_OOSC_ACTION_ERASE = 3, +}; + +/** + * enum iosm_out_of_session_type - Data types that can be handled over the + * Out Of Session command Interface + * @FLASH_OOSC_TYPE_ALL_FLASH: The whole flash area + * @FLASH_OOSC_TYPE_SWID_TABLE: Read the swid table from the target + */ +enum iosm_out_of_session_type { + FLASH_OOSC_TYPE_ALL_FLASH = 8, + FLASH_OOSC_TYPE_SWID_TABLE = 16, +}; + +/** + * enum iosm_ebl_caps - EBL capability settings + * @IOSM_CAP_NOT_ENHANCED: If capability not supported + * @IOSM_CAP_USE_EXT_CAP: To be set if extended capability is set + * @IOSM_EXT_CAP_ERASE_ALL: Set Erase all capability + * @IOSM_EXT_CAP_COMMIT_ALL: Set the commit all capability + */ +enum iosm_ebl_caps { + IOSM_CAP_NOT_ENHANCED = 0x00, + IOSM_CAP_USE_EXT_CAP = 0x01, + IOSM_EXT_CAP_ERASE_ALL = 0x08, + IOSM_EXT_CAP_COMMIT_ALL = 0x20, +}; + +/** + * enum iosm_ebl_rsp - EBL response field + * @EBL_CAPS_FLAG: EBL capability flag + * @EBL_SKIP_ERASE: EBL skip erase flag + * @EBL_SKIP_CRC: EBL skip wr_pack crc + * @EBL_EXT_CAPS_HANDLED: EBL extended capability handled flag + * @EBL_OOS_CONFIG: EBL oos configuration + * @EBL_RSP_SW_INFO_VER: EBL SW info version + */ +enum iosm_ebl_rsp { + EBL_CAPS_FLAG = 50, + EBL_SKIP_ERASE = 54, + EBL_SKIP_CRC = 55, + EBL_EXT_CAPS_HANDLED = 57, + EBL_OOS_CONFIG = 64, + EBL_RSP_SW_INFO_VER = 70, +}; + +/** + * enum iosm_mdm_send_recv_data - Data to send to modem + * @IOSM_MDM_SEND_2: Send 2 bytes of payload + * @IOSM_MDM_SEND_4: Send 4 bytes of payload + * @IOSM_MDM_SEND_8: Send 8 bytes of payload + * @IOSM_MDM_SEND_16: Send 16 bytes of payload + */ +enum iosm_mdm_send_recv_data { + IOSM_MDM_SEND_2 = 2, + IOSM_MDM_SEND_4 = 4, + IOSM_MDM_SEND_8 = 8, + IOSM_MDM_SEND_16 = 16, +}; + +/** + * struct iosm_ebl_one_error - Structure containing error details + * @error_class: Error type- standard, security and text error + * @error_code: Specific error from error type + */ +struct iosm_ebl_one_error { + u16 error_class; + u16 error_code; +}; + +/** + * struct iosm_ebl_error- Structure with max error type supported + * @error: Array of one_error structure with max errors + */ +struct iosm_ebl_error { + struct iosm_ebl_one_error error[IOSM_MAX_ERRORS]; +}; + +/** + * struct iosm_swid_table - SWID table data for modem + * @number_of_data_sets: Number of swid types + * @sw_id_type: SWID type - SWID + * @sw_id_val: SWID value + * @rf_engine_id_type: RF engine ID type - RF_ENGINE_ID + * @rf_engine_id_val: RF engine ID value + */ +struct iosm_swid_table { + u32 number_of_data_sets; + char sw_id_type[IOSM_EBL_NAME]; + u32 sw_id_val; + char rf_engine_id_type[IOSM_EBL_NAME]; + u32 rf_engine_id_val; +}; + +/** + * struct iosm_flash_msg_control - Data sent to modem + * @action: Action to be performed + * @type: Type of action + * @length: Length of the action + * @arguments: Argument value sent to modem + */ +struct iosm_flash_msg_control { + __le32 action; + __le32 type; + __le32 length; + __le32 arguments; +}; + +/** + * struct iosm_flash_data - Header Data to be sent to modem + * @checksum: Checksum value calculated for the payload data + * @pack_id: Flash Action type + * @msg_length: Payload length + */ +struct iosm_flash_data { + __le16 checksum; + __le16 pack_id; + __le32 msg_length; +}; + +int ipc_flash_boot_psi(struct iosm_devlink *ipc_devlink, + const struct firmware *fw); + +int ipc_flash_boot_ebl(struct iosm_devlink *ipc_devlink, + const struct firmware *fw); + +int ipc_flash_boot_set_capabilities(struct iosm_devlink *ipc_devlink, + u8 *mdm_rsp); + +int ipc_flash_link_establish(struct iosm_imem *ipc_imem); + +int ipc_flash_read_swid(struct iosm_devlink *ipc_devlink, u8 *mdm_rsp); + +int ipc_flash_send_fls(struct iosm_devlink *ipc_devlink, + const struct firmware *fw, u8 *mdm_rsp); +#endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 9f00e36b7f7909..cff3b43ca4d7d3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -6,6 +6,8 @@ #include <linux/delay.h> #include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_devlink.h" +#include "iosm_ipc_flash.h" #include "iosm_ipc_imem.h" #include "iosm_ipc_port.h" @@ -263,9 +265,12 @@ static void ipc_imem_dl_skb_process(struct iosm_imem *ipc_imem, switch (pipe->channel->ctype) { case IPC_CTYPE_CTRL: port_id = pipe->channel->channel_id; - - /* Pass the packet to the wwan layer. */ - wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, skb); + if (port_id == IPC_MEM_CTRL_CHL_ID_7) + ipc_imem_sys_devlink_notify_rx(ipc_imem->ipc_devlink, + skb); + else + wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, + skb); break; case IPC_CTYPE_WWAN: @@ -399,19 +404,8 @@ static void ipc_imem_rom_irq_exec(struct iosm_imem *ipc_imem) { struct ipc_mem_channel *channel; - if (ipc_imem->flash_channel_id < 0) { - ipc_imem->rom_exit_code = IMEM_ROM_EXIT_FAIL; - dev_err(ipc_imem->dev, "Missing flash app:%d", - ipc_imem->flash_channel_id); - return; - } - + channel = ipc_imem->ipc_devlink->devlink_sio.channel; ipc_imem->rom_exit_code = ipc_mmio_get_rom_exit_code(ipc_imem->mmio); - - /* Wake up the flash app to continue or to terminate depending - * on the CP ROM exit code. - */ - channel = &ipc_imem->channels[ipc_imem->flash_channel_id]; complete(&channel->ul_sem); } @@ -482,8 +476,8 @@ static enum hrtimer_restart ipc_imem_startup_timer_cb(struct hrtimer *hr_timer) container_of(hr_timer, struct iosm_imem, startup_timer); if (ktime_to_ns(ipc_imem->hrtimer_period)) { - hrtimer_forward(&ipc_imem->startup_timer, ktime_get(), - ipc_imem->hrtimer_period); + hrtimer_forward_now(&ipc_imem->startup_timer, + ipc_imem->hrtimer_period); result = HRTIMER_RESTART; } @@ -572,7 +566,7 @@ static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) enum ipc_phase old_phase, phase; bool retry_allocation = false; bool ul_pending = false; - int ch_id, i; + int i; if (irq != IMEM_IRQ_DONT_CARE) ipc_imem->ev_irq_pending[irq] = false; @@ -696,11 +690,8 @@ static void ipc_imem_handle_irq(struct iosm_imem *ipc_imem, int irq) if ((phase == IPC_P_PSI || phase == IPC_P_EBL) && ipc_imem->ipc_requested_state == IPC_MEM_DEVICE_IPC_RUNNING && ipc_mmio_get_ipc_state(ipc_imem->mmio) == - IPC_MEM_DEVICE_IPC_RUNNING && - ipc_imem->flash_channel_id >= 0) { - /* Wake up the flash app to open the pipes. */ - ch_id = ipc_imem->flash_channel_id; - complete(&ipc_imem->channels[ch_id].ul_sem); + IPC_MEM_DEVICE_IPC_RUNNING) { + complete(&ipc_imem->ipc_devlink->devlink_sio.channel->ul_sem); } /* Reset the expected CP state. */ @@ -1176,6 +1167,9 @@ void ipc_imem_cleanup(struct iosm_imem *ipc_imem) ipc_port_deinit(ipc_imem->ipc_port); } + if (ipc_imem->ipc_devlink) + ipc_devlink_deinit(ipc_imem->ipc_devlink); + ipc_imem_device_ipc_uninit(ipc_imem); ipc_imem_channel_reset(ipc_imem); @@ -1258,6 +1252,7 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, void __iomem *mmio, struct device *dev) { struct iosm_imem *ipc_imem = kzalloc(sizeof(*pcie->imem), GFP_KERNEL); + enum ipc_mem_exec_stage stage; if (!ipc_imem) return NULL; @@ -1272,9 +1267,6 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, ipc_imem->cp_version = 0; ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP; - /* Reset the flash channel id. */ - ipc_imem->flash_channel_id = -1; - /* Reset the max number of configured channels */ ipc_imem->nr_of_channels = 0; @@ -1328,8 +1320,21 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, goto imem_config_fail; } - return ipc_imem; + stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); + if (stage == IPC_MEM_EXEC_STAGE_BOOT) { + /* Alloc and Register devlink */ + ipc_imem->ipc_devlink = ipc_devlink_init(ipc_imem); + if (!ipc_imem->ipc_devlink) { + dev_err(ipc_imem->dev, "Devlink register failed"); + goto imem_config_fail; + } + if (ipc_flash_link_establish(ipc_imem)) + goto devlink_channel_fail; + } + return ipc_imem; +devlink_channel_fail: + ipc_devlink_deinit(ipc_imem->ipc_devlink); imem_config_fail: hrtimer_cancel(&ipc_imem->td_alloc_timer); hrtimer_cancel(&ipc_imem->fast_update_timer); @@ -1361,3 +1366,51 @@ void ipc_imem_td_update_timer_suspend(struct iosm_imem *ipc_imem, bool suspend) { ipc_imem->td_update_timer_suspended = suspend; } + +/* Verify the CP execution state, copy the chip info, + * change the execution phase to ROM + */ +static int ipc_imem_devlink_trigger_chip_info_cb(struct iosm_imem *ipc_imem, + int arg, void *msg, + size_t msgsize) +{ + enum ipc_mem_exec_stage stage; + struct sk_buff *skb; + int rc = -EINVAL; + size_t size; + + /* Test the CP execution state. */ + stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); + if (stage != IPC_MEM_EXEC_STAGE_BOOT) { + dev_err(ipc_imem->dev, + "Execution_stage: expected BOOT, received = %X", stage); + goto trigger_chip_info_fail; + } + /* Allocate a new sk buf for the chip info. */ + size = ipc_imem->mmio->chip_info_size; + if (size > IOSM_CHIP_INFO_SIZE_MAX) + goto trigger_chip_info_fail; + + skb = ipc_pcie_alloc_local_skb(ipc_imem->pcie, GFP_ATOMIC, size); + if (!skb) { + dev_err(ipc_imem->dev, "exhausted skbuf kernel DL memory"); + rc = -ENOMEM; + goto trigger_chip_info_fail; + } + /* Copy the chip info characters into the ipc_skb. */ + ipc_mmio_copy_chip_info(ipc_imem->mmio, skb_put(skb, size), size); + /* First change to the ROM boot phase. */ + dev_dbg(ipc_imem->dev, "execution_stage[%X] eq. BOOT", stage); + ipc_imem->phase = ipc_imem_phase_update(ipc_imem); + ipc_imem_sys_devlink_notify_rx(ipc_imem->ipc_devlink, skb); + rc = 0; +trigger_chip_info_fail: + return rc; +} + +int ipc_imem_devlink_trigger_chip_info(struct iosm_imem *ipc_imem) +{ + return ipc_task_queue_send_task(ipc_imem, + ipc_imem_devlink_trigger_chip_info_cb, + 0, NULL, 0, true); +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index dc65b0712261f1..6be6708b4eec86 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -69,7 +69,7 @@ struct ipc_chnl_cfg; #define IMEM_IRQ_DONT_CARE (-1) -#define IPC_MEM_MAX_CHANNELS 7 +#define IPC_MEM_MAX_CHANNELS 8 #define IPC_MEM_MUX_IP_SESSION_ENTRIES 8 @@ -98,6 +98,7 @@ struct ipc_chnl_cfg; #define IPC_MEM_DL_ETH_OFFSET 16 #define IPC_CB(skb) ((struct ipc_skb_cb *)((skb)->cb)) +#define IOSM_CHIP_INFO_SIZE_MAX 100 #define FULLY_FUNCTIONAL 0 @@ -304,9 +305,9 @@ enum ipc_phase { * @ipc_port: IPC PORT data structure pointer * @pcie: IPC PCIe * @dev: Pointer to device structure - * @flash_channel_id: Reserved channel id for flashing to RAM. * @ipc_requested_state: Expected IPC state on CP. * @channels: Channel list with UL/DL pipe pairs. + * @ipc_devlink: IPC Devlink data structure pointer * @ipc_status: local ipc_status * @nr_of_channels: number of configured channels * @startup_timer: startup timer for NAND support. @@ -349,9 +350,9 @@ struct iosm_imem { struct iosm_cdev *ipc_port[IPC_MEM_MAX_CHANNELS]; struct iosm_pcie *pcie; struct device *dev; - int flash_channel_id; enum ipc_mem_device_ipc_state ipc_requested_state; struct ipc_mem_channel channels[IPC_MEM_MAX_CHANNELS]; + struct iosm_devlink *ipc_devlink; u32 ipc_status; u32 nr_of_channels; struct hrtimer startup_timer; @@ -575,4 +576,15 @@ void ipc_imem_ipc_init_check(struct iosm_imem *ipc_imem); */ void ipc_imem_channel_init(struct iosm_imem *ipc_imem, enum ipc_ctype ctype, struct ipc_chnl_cfg chnl_cfg, u32 irq_moderation); + +/** + * ipc_imem_devlink_trigger_chip_info - Inform devlink that the chip + * information are available if the + * flashing to RAM interworking shall be + * executed. + * @ipc_imem: Pointer to imem structure + * + * Returns: 0 on success, -1 on failure + */ +int ipc_imem_devlink_trigger_chip_info(struct iosm_imem *ipc_imem); #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c index 0a472ce773700d..b885a657023598 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.c @@ -6,6 +6,7 @@ #include <linux/delay.h> #include "iosm_ipc_chnl_cfg.h" +#include "iosm_ipc_devlink.h" #include "iosm_ipc_imem.h" #include "iosm_ipc_imem_ops.h" #include "iosm_ipc_port.h" @@ -331,3 +332,319 @@ int ipc_imem_sys_cdev_write(struct iosm_cdev *ipc_cdev, struct sk_buff *skb) out: return ret; } + +/* Open a SIO link to CP and return the channel instance */ +struct ipc_mem_channel *ipc_imem_sys_devlink_open(struct iosm_imem *ipc_imem) +{ + struct ipc_mem_channel *channel; + enum ipc_phase phase; + int channel_id; + + phase = ipc_imem_phase_update(ipc_imem); + switch (phase) { + case IPC_P_OFF: + case IPC_P_ROM: + /* Get a channel id as flash id and reserve it. */ + channel_id = ipc_imem_channel_alloc(ipc_imem, + IPC_MEM_CTRL_CHL_ID_7, + IPC_CTYPE_CTRL); + + if (channel_id < 0) { + dev_err(ipc_imem->dev, + "reservation of a flash channel id failed"); + goto error; + } + + ipc_imem->ipc_devlink->devlink_sio.channel_id = channel_id; + channel = &ipc_imem->channels[channel_id]; + + /* Enqueue chip info data to be read */ + if (ipc_imem_devlink_trigger_chip_info(ipc_imem)) { + dev_err(ipc_imem->dev, "Enqueue of chip info failed"); + channel->state = IMEM_CHANNEL_FREE; + goto error; + } + + return channel; + + case IPC_P_PSI: + case IPC_P_EBL: + ipc_imem->cp_version = ipc_mmio_get_cp_version(ipc_imem->mmio); + if (ipc_imem->cp_version == -1) { + dev_err(ipc_imem->dev, "invalid CP version"); + goto error; + } + + channel_id = ipc_imem->ipc_devlink->devlink_sio.channel_id; + return ipc_imem_channel_open(ipc_imem, channel_id, + IPC_HP_CDEV_OPEN); + + default: + /* CP is in the wrong state (e.g. CRASH or CD_READY) */ + dev_err(ipc_imem->dev, "SIO open refused, phase %d", phase); + } +error: + return NULL; +} + +/* Release a SIO channel link to CP. */ +void ipc_imem_sys_devlink_close(struct iosm_devlink *ipc_devlink) +{ + struct iosm_imem *ipc_imem = ipc_devlink->pcie->imem; + int boot_check_timeout = BOOT_CHECK_DEFAULT_TIMEOUT; + enum ipc_mem_exec_stage exec_stage; + struct ipc_mem_channel *channel; + enum ipc_phase curr_phase; + int status = 0; + u32 tail = 0; + + channel = ipc_imem->ipc_devlink->devlink_sio.channel; + curr_phase = ipc_imem->phase; + /* Increase the total wait time to boot_check_timeout */ + do { + exec_stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); + if (exec_stage == IPC_MEM_EXEC_STAGE_RUN || + exec_stage == IPC_MEM_EXEC_STAGE_PSI) + break; + msleep(20); + boot_check_timeout -= 20; + } while (boot_check_timeout > 0); + + /* If there are any pending TDs then wait for Timeout/Completion before + * closing pipe. + */ + if (channel->ul_pipe.old_tail != channel->ul_pipe.old_head) { + status = wait_for_completion_interruptible_timeout + (&ipc_imem->ul_pend_sem, + msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT)); + if (status == 0) { + dev_dbg(ipc_imem->dev, + "Data Timeout on UL-Pipe:%d Head:%d Tail:%d", + channel->ul_pipe.pipe_nr, + channel->ul_pipe.old_head, + channel->ul_pipe.old_tail); + } + } + + ipc_protocol_get_head_tail_index(ipc_imem->ipc_protocol, + &channel->dl_pipe, NULL, &tail); + + if (tail != channel->dl_pipe.old_tail) { + status = wait_for_completion_interruptible_timeout + (&ipc_imem->dl_pend_sem, + msecs_to_jiffies(IPC_PEND_DATA_TIMEOUT)); + if (status == 0) { + dev_dbg(ipc_imem->dev, + "Data Timeout on DL-Pipe:%d Head:%d Tail:%d", + channel->dl_pipe.pipe_nr, + channel->dl_pipe.old_head, + channel->dl_pipe.old_tail); + } + } + + /* Due to wait for completion in messages, there is a small window + * between closing the pipe and updating the channel is closed. In this + * small window there could be HP update from Host Driver. Hence update + * the channel state as CLOSING to aviod unnecessary interrupt + * towards CP. + */ + channel->state = IMEM_CHANNEL_CLOSING; + /* Release the pipe resources */ + ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe); + ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe); +} + +void ipc_imem_sys_devlink_notify_rx(struct iosm_devlink *ipc_devlink, + struct sk_buff *skb) +{ + skb_queue_tail(&ipc_devlink->devlink_sio.rx_list, skb); + complete(&ipc_devlink->devlink_sio.read_sem); +} + +/* PSI transfer */ +static int ipc_imem_sys_psi_transfer(struct iosm_imem *ipc_imem, + struct ipc_mem_channel *channel, + unsigned char *buf, int count) +{ + int psi_start_timeout = PSI_START_DEFAULT_TIMEOUT; + enum ipc_mem_exec_stage exec_stage; + + dma_addr_t mapping = 0; + int ret; + + ret = ipc_pcie_addr_map(ipc_imem->pcie, buf, count, &mapping, + DMA_TO_DEVICE); + if (ret) + goto pcie_addr_map_fail; + + /* Save the PSI information for the CP ROM driver on the doorbell + * scratchpad. + */ + ipc_mmio_set_psi_addr_and_size(ipc_imem->mmio, mapping, count); + ipc_doorbell_fire(ipc_imem->pcie, 0, IPC_MEM_EXEC_STAGE_BOOT); + + ret = wait_for_completion_interruptible_timeout + (&channel->ul_sem, + msecs_to_jiffies(IPC_PSI_TRANSFER_TIMEOUT)); + + if (ret <= 0) { + dev_err(ipc_imem->dev, "Failed PSI transfer to CP, Error-%d", + ret); + goto psi_transfer_fail; + } + /* If the PSI download fails, return the CP boot ROM exit code */ + if (ipc_imem->rom_exit_code != IMEM_ROM_EXIT_OPEN_EXT && + ipc_imem->rom_exit_code != IMEM_ROM_EXIT_CERT_EXT) { + ret = (-1) * ((int)ipc_imem->rom_exit_code); + goto psi_transfer_fail; + } + + dev_dbg(ipc_imem->dev, "PSI image successfully downloaded"); + + /* Wait psi_start_timeout milliseconds until the CP PSI image is + * running and updates the execution_stage field with + * IPC_MEM_EXEC_STAGE_PSI. Verify the execution stage. + */ + do { + exec_stage = ipc_mmio_get_exec_stage(ipc_imem->mmio); + + if (exec_stage == IPC_MEM_EXEC_STAGE_PSI) + break; + + msleep(20); + psi_start_timeout -= 20; + } while (psi_start_timeout > 0); + + if (exec_stage != IPC_MEM_EXEC_STAGE_PSI) + goto psi_transfer_fail; /* Unknown status of CP PSI process. */ + + ipc_imem->phase = IPC_P_PSI; + + /* Enter the PSI phase. */ + dev_dbg(ipc_imem->dev, "execution_stage[%X] eq. PSI", exec_stage); + + /* Request the RUNNING state from CP and wait until it was reached + * or timeout. + */ + ipc_imem_ipc_init_check(ipc_imem); + + ret = wait_for_completion_interruptible_timeout + (&channel->ul_sem, msecs_to_jiffies(IPC_PSI_TRANSFER_TIMEOUT)); + if (ret <= 0) { + dev_err(ipc_imem->dev, + "Failed PSI RUNNING state on CP, Error-%d", ret); + goto psi_transfer_fail; + } + + if (ipc_mmio_get_ipc_state(ipc_imem->mmio) != + IPC_MEM_DEVICE_IPC_RUNNING) { + dev_err(ipc_imem->dev, + "ch[%d] %s: unexpected CP IPC state %d, not RUNNING", + channel->channel_id, + ipc_imem_phase_get_string(ipc_imem->phase), + ipc_mmio_get_ipc_state(ipc_imem->mmio)); + + goto psi_transfer_fail; + } + + /* Create the flash channel for the transfer of the images. */ + if (!ipc_imem_sys_devlink_open(ipc_imem)) { + dev_err(ipc_imem->dev, "can't open flash_channel"); + goto psi_transfer_fail; + } + + ret = 0; +psi_transfer_fail: + ipc_pcie_addr_unmap(ipc_imem->pcie, count, mapping, DMA_TO_DEVICE); +pcie_addr_map_fail: + return ret; +} + +int ipc_imem_sys_devlink_write(struct iosm_devlink *ipc_devlink, + unsigned char *buf, int count) +{ + struct iosm_imem *ipc_imem = ipc_devlink->pcie->imem; + struct ipc_mem_channel *channel; + struct sk_buff *skb; + dma_addr_t mapping; + int ret; + + channel = ipc_imem->ipc_devlink->devlink_sio.channel; + + /* In the ROM phase the PSI image is passed to CP about a specific + * shared memory area and doorbell scratchpad directly. + */ + if (ipc_imem->phase == IPC_P_ROM) { + ret = ipc_imem_sys_psi_transfer(ipc_imem, channel, buf, count); + /* If the PSI transfer fails then send crash + * Signature. + */ + if (ret > 0) + ipc_imem_msg_send_feature_set(ipc_imem, + IPC_MEM_INBAND_CRASH_SIG, + false); + goto out; + } + + /* Allocate skb memory for the uplink buffer. */ + skb = ipc_pcie_alloc_skb(ipc_devlink->pcie, count, GFP_KERNEL, &mapping, + DMA_TO_DEVICE, 0); + if (!skb) { + ret = -ENOMEM; + goto out; + } + + memcpy(skb_put(skb, count), buf, count); + + IPC_CB(skb)->op_type = UL_USR_OP_BLOCKED; + + /* Add skb to the uplink skbuf accumulator. */ + skb_queue_tail(&channel->ul_list, skb); + + /* Inform the IPC tasklet to pass uplink IP packets to CP. */ + if (!ipc_imem_call_cdev_write(ipc_imem)) { + ret = wait_for_completion_interruptible(&channel->ul_sem); + + if (ret < 0) { + dev_err(ipc_imem->dev, + "ch[%d] no CP confirmation, status = %d", + channel->channel_id, ret); + ipc_pcie_kfree_skb(ipc_devlink->pcie, skb); + goto out; + } + } + ret = 0; +out: + return ret; +} + +int ipc_imem_sys_devlink_read(struct iosm_devlink *devlink, u8 *data, + u32 bytes_to_read, u32 *bytes_read) +{ + struct sk_buff *skb = NULL; + int rc = 0; + + /* check skb is available in rx_list or wait for skb */ + devlink->devlink_sio.devlink_read_pend = 1; + while (!skb && !(skb = skb_dequeue(&devlink->devlink_sio.rx_list))) { + if (!wait_for_completion_interruptible_timeout + (&devlink->devlink_sio.read_sem, + msecs_to_jiffies(IPC_READ_TIMEOUT))) { + dev_err(devlink->dev, "Read timedout"); + rc = -ETIMEDOUT; + goto devlink_read_fail; + } + } + devlink->devlink_sio.devlink_read_pend = 0; + if (bytes_to_read < skb->len) { + dev_err(devlink->dev, "Invalid size,expected len %d", skb->len); + rc = -EINVAL; + goto devlink_read_fail; + } + *bytes_read = skb->len; + memcpy(data, skb->data, skb->len); + +devlink_read_fail: + ipc_pcie_kfree_skb(devlink->pcie, skb); + return rc; +} diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index 2007fe23e9a567..f0c88ac5643c62 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -9,7 +9,7 @@ #include "iosm_ipc_mux_codec.h" /* Maximum wait time for blocking read */ -#define IPC_READ_TIMEOUT 500 +#define IPC_READ_TIMEOUT 3000 /* The delay in ms for defering the unregister */ #define SIO_UNREGISTER_DEFER_DELAY_MS 1 @@ -98,4 +98,51 @@ int ipc_imem_sys_wwan_transmit(struct iosm_imem *ipc_imem, int if_id, */ void ipc_imem_wwan_channel_init(struct iosm_imem *ipc_imem, enum ipc_mux_protocol mux_type); + +/** + * ipc_imem_sys_devlink_open - Open a Flash/CD Channel link to CP + * @ipc_imem: iosm_imem instance + * + * Return: channel instance on success, NULL for failure + */ +struct ipc_mem_channel *ipc_imem_sys_devlink_open(struct iosm_imem *ipc_imem); + +/** + * ipc_imem_sys_devlink_close - Release a Flash/CD channel link to CP + * @ipc_devlink: Pointer to ipc_devlink data-struct + * + */ +void ipc_imem_sys_devlink_close(struct iosm_devlink *ipc_devlink); + +/** + * ipc_imem_sys_devlink_notify_rx - Receive downlink characters from CP, + * the downlink skbuf is added at the end of the + * downlink or rx list + * @ipc_devlink: Pointer to ipc_devlink data-struct + * @skb: Pointer to sk buffer + */ +void ipc_imem_sys_devlink_notify_rx(struct iosm_devlink *ipc_devlink, + struct sk_buff *skb); + +/** + * ipc_imem_sys_devlink_read - Copy the rx data and free the skbuf + * @ipc_devlink: Devlink instance + * @data: Buffer to read the data from modem + * @bytes_to_read: Size of destination buffer + * @bytes_read: Number of bytes read + * + * Return: 0 on success and failure value on error + */ +int ipc_imem_sys_devlink_read(struct iosm_devlink *ipc_devlink, u8 *data, + u32 bytes_to_read, u32 *bytes_read); + +/** + * ipc_imem_sys_devlink_write - Route the uplink buffer to CP + * @ipc_devlink: Devlink_sio instance + * @buf: Pointer to buffer + * @count: Number of data bytes to write + * Return: 0 on success and failure value on error + */ +int ipc_imem_sys_devlink_write(struct iosm_devlink *ipc_devlink, + unsigned char *buf, int count); #endif diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 051c43a2a52f86..f78670bf41e01c 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -335,7 +335,6 @@ static int fdp_nci_i2c_probe(struct i2c_client *client) return r; } - dev_dbg(dev, "I2C driver loaded\n"); return 0; } diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index 8edf761a6b2abb..00689e18dc46a0 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -26,10 +26,8 @@ static int microread_mei_probe(struct mei_cl_device *cldev, pr_info("Probing NFC microread\n"); phy = nfc_mei_phy_alloc(cldev); - if (!phy) { - pr_err("Cannot allocate memory for microread mei phy.\n"); + if (!phy) return -ENOMEM; - } r = microread_probe(phy, &mei_phy_ops, LLC_NOP_NAME, MEI_NFC_HEADER_SIZE, 0, MEI_NFC_MAX_HCI_PAYLOAD, diff --git a/drivers/nfc/nfcmrvl/fw_dnld.c b/drivers/nfc/nfcmrvl/fw_dnld.c index edac56b01fd13e..e83f65596a88a0 100644 --- a/drivers/nfc/nfcmrvl/fw_dnld.c +++ b/drivers/nfc/nfcmrvl/fw_dnld.c @@ -76,10 +76,8 @@ static struct sk_buff *alloc_lc_skb(struct nfcmrvl_private *priv, uint8_t plen) struct nci_data_hdr *hdr; skb = nci_skb_alloc(priv->ndev, (NCI_DATA_HDR_SIZE + plen), GFP_KERNEL); - if (!skb) { - pr_err("no memory for data\n"); + if (!skb) return NULL; - } hdr = skb_put(skb, NCI_DATA_HDR_SIZE); hdr->conn_id = NCI_CORE_LC_CONNID_PROP_FW_DL; diff --git a/drivers/nfc/pn533/i2c.c b/drivers/nfc/pn533/i2c.c index e6bf8cfe3aa7c9..f5610b6b989480 100644 --- a/drivers/nfc/pn533/i2c.c +++ b/drivers/nfc/pn533/i2c.c @@ -128,7 +128,6 @@ static int pn533_i2c_read(struct pn533_i2c_phy *phy, struct sk_buff **skb) static irqreturn_t pn533_i2c_irq_thread_fn(int irq, void *data) { struct pn533_i2c_phy *phy = data; - struct i2c_client *client; struct sk_buff *skb = NULL; int r; @@ -137,9 +136,6 @@ static irqreturn_t pn533_i2c_irq_thread_fn(int irq, void *data) return IRQ_NONE; } - client = phy->i2c_dev; - dev_dbg(&client->dev, "IRQ\n"); - if (phy->hard_fault != 0) return IRQ_HANDLED; diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c index 2f3f3fe9a0baa8..da180335422c84 100644 --- a/drivers/nfc/pn533/pn533.c +++ b/drivers/nfc/pn533/pn533.c @@ -1235,8 +1235,6 @@ static void pn533_listen_mode_timer(struct timer_list *t) { struct pn533 *dev = from_timer(dev, t, listen_timer); - dev_dbg(dev->dev, "Listen mode timeout\n"); - dev->cancel_listen = 1; pn533_poll_next_mod(dev); @@ -2173,7 +2171,7 @@ void pn533_recv_frame(struct pn533 *dev, struct sk_buff *skb, int status) } if (skb == NULL) { - pr_err("NULL Frame -> link is dead\n"); + dev_err(dev->dev, "NULL Frame -> link is dead\n"); goto sched_wq; } diff --git a/drivers/nfc/pn544/mei.c b/drivers/nfc/pn544/mei.c index 5c10aac085a415..c493f2dbd0e211 100644 --- a/drivers/nfc/pn544/mei.c +++ b/drivers/nfc/pn544/mei.c @@ -22,13 +22,9 @@ static int pn544_mei_probe(struct mei_cl_device *cldev, struct nfc_mei_phy *phy; int r; - pr_info("Probing NFC pn544\n"); - phy = nfc_mei_phy_alloc(cldev); - if (!phy) { - pr_err("Cannot allocate memory for pn544 mei phy.\n"); + if (!phy) return -ENOMEM; - } r = pn544_hci_probe(phy, &mei_phy_ops, LLC_NOP_NAME, MEI_NFC_HEADER_SIZE, 0, MEI_NFC_MAX_HCI_PAYLOAD, @@ -46,8 +42,6 @@ static void pn544_mei_remove(struct mei_cl_device *cldev) { struct nfc_mei_phy *phy = mei_cldev_get_drvdata(cldev); - pr_info("Removing pn544\n"); - pn544_hci_remove(phy->hdev); nfc_mei_phy_free(phy); diff --git a/drivers/ptp/idt8a340_reg.h b/drivers/ptp/idt8a340_reg.h deleted file mode 100644 index ac524cf0f31fbf..00000000000000 --- a/drivers/ptp/idt8a340_reg.h +++ /dev/null @@ -1,720 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* idt8a340_reg.h - * - * Originally generated by regen.tcl on Thu Feb 14 19:23:44 PST 2019 - * https://github.com/richardcochran/regen - * - * Hand modified to include some HW registers. - * Based on 4.8.0, SCSR rev C commit a03c7ae5 - */ -#ifndef HAVE_IDT8A340_REG -#define HAVE_IDT8A340_REG - -#define PAGE_ADDR_BASE 0x0000 -#define PAGE_ADDR 0x00fc - -#define HW_REVISION 0x8180 -#define REV_ID 0x007a - -#define HW_DPLL_0 (0x8a00) -#define HW_DPLL_1 (0x8b00) -#define HW_DPLL_2 (0x8c00) -#define HW_DPLL_3 (0x8d00) -#define HW_DPLL_4 (0x8e00) -#define HW_DPLL_5 (0x8f00) -#define HW_DPLL_6 (0x9000) -#define HW_DPLL_7 (0x9100) - -#define HW_DPLL_TOD_SW_TRIG_ADDR__0 (0x080) -#define HW_DPLL_TOD_CTRL_1 (0x089) -#define HW_DPLL_TOD_CTRL_2 (0x08A) -#define HW_DPLL_TOD_OVR__0 (0x098) -#define HW_DPLL_TOD_OUT_0__0 (0x0B0) - -#define HW_Q0_Q1_CH_SYNC_CTRL_0 (0xa740) -#define HW_Q0_Q1_CH_SYNC_CTRL_1 (0xa741) -#define HW_Q2_Q3_CH_SYNC_CTRL_0 (0xa742) -#define HW_Q2_Q3_CH_SYNC_CTRL_1 (0xa743) -#define HW_Q4_Q5_CH_SYNC_CTRL_0 (0xa744) -#define HW_Q4_Q5_CH_SYNC_CTRL_1 (0xa745) -#define HW_Q6_Q7_CH_SYNC_CTRL_0 (0xa746) -#define HW_Q6_Q7_CH_SYNC_CTRL_1 (0xa747) -#define HW_Q8_CH_SYNC_CTRL_0 (0xa748) -#define HW_Q8_CH_SYNC_CTRL_1 (0xa749) -#define HW_Q9_CH_SYNC_CTRL_0 (0xa74a) -#define HW_Q9_CH_SYNC_CTRL_1 (0xa74b) -#define HW_Q10_CH_SYNC_CTRL_0 (0xa74c) -#define HW_Q10_CH_SYNC_CTRL_1 (0xa74d) -#define HW_Q11_CH_SYNC_CTRL_0 (0xa74e) -#define HW_Q11_CH_SYNC_CTRL_1 (0xa74f) - -#define SYNC_SOURCE_DPLL0_TOD_PPS 0x14 -#define SYNC_SOURCE_DPLL1_TOD_PPS 0x15 -#define SYNC_SOURCE_DPLL2_TOD_PPS 0x16 -#define SYNC_SOURCE_DPLL3_TOD_PPS 0x17 - -#define SYNCTRL1_MASTER_SYNC_RST BIT(7) -#define SYNCTRL1_MASTER_SYNC_TRIG BIT(5) -#define SYNCTRL1_TOD_SYNC_TRIG BIT(4) -#define SYNCTRL1_FBDIV_FRAME_SYNC_TRIG BIT(3) -#define SYNCTRL1_FBDIV_SYNC_TRIG BIT(2) -#define SYNCTRL1_Q1_DIV_SYNC_TRIG BIT(1) -#define SYNCTRL1_Q0_DIV_SYNC_TRIG BIT(0) - -#define HW_Q8_CTRL_SPARE (0xa7d4) -#define HW_Q11_CTRL_SPARE (0xa7ec) - -/** - * Select FOD5 as sync_trigger for Q8 divider. - * Transition from logic zero to one - * sets trigger to sync Q8 divider. - * - * Unused when FOD4 is driving Q8 divider (normal operation). - */ -#define Q9_TO_Q8_SYNC_TRIG BIT(1) - -/** - * Enable FOD5 as driver for clock and sync for Q8 divider. - * Enable fanout buffer for FOD5. - * - * Unused when FOD4 is driving Q8 divider (normal operation). - */ -#define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) - -/** - * Select FOD6 as sync_trigger for Q11 divider. - * Transition from logic zero to one - * sets trigger to sync Q11 divider. - * - * Unused when FOD7 is driving Q11 divider (normal operation). - */ -#define Q10_TO_Q11_SYNC_TRIG BIT(1) - -/** - * Enable FOD6 as driver for clock and sync for Q11 divider. - * Enable fanout buffer for FOD6. - * - * Unused when FOD7 is driving Q11 divider (normal operation). - */ -#define Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) - -#define RESET_CTRL 0xc000 -#define SM_RESET 0x0012 -#define SM_RESET_CMD 0x5A - -#define GENERAL_STATUS 0xc014 -#define BOOT_STATUS 0x0000 -#define HW_REV_ID 0x000A -#define BOND_ID 0x000B -#define HW_CSR_ID 0x000C -#define HW_IRQ_ID 0x000E - -#define MAJ_REL 0x0010 -#define MIN_REL 0x0011 -#define HOTFIX_REL 0x0012 - -#define PIPELINE_ID 0x0014 -#define BUILD_ID 0x0018 - -#define JTAG_DEVICE_ID 0x001c -#define PRODUCT_ID 0x001e - -#define OTP_SCSR_CONFIG_SELECT 0x0022 - -#define STATUS 0xc03c -#define DPLL_SYS_STATUS 0x0020 -#define DPLL_SYS_APLL_STATUS 0x0021 -#define USER_GPIO0_TO_7_STATUS 0x008a -#define USER_GPIO8_TO_15_STATUS 0x008b - -#define GPIO_USER_CONTROL 0xc160 -#define GPIO0_TO_7_OUT 0x0000 -#define GPIO8_TO_15_OUT 0x0001 - -#define STICKY_STATUS_CLEAR 0xc164 - -#define GPIO_TOD_NOTIFICATION_CLEAR 0xc16c - -#define ALERT_CFG 0xc188 - -#define SYS_DPLL_XO 0xc194 - -#define SYS_APLL 0xc19c - -#define INPUT_0 0xc1b0 - -#define INPUT_1 0xc1c0 - -#define INPUT_2 0xc1d0 - -#define INPUT_3 0xc200 - -#define INPUT_4 0xc210 - -#define INPUT_5 0xc220 - -#define INPUT_6 0xc230 - -#define INPUT_7 0xc240 - -#define INPUT_8 0xc250 - -#define INPUT_9 0xc260 - -#define INPUT_10 0xc280 - -#define INPUT_11 0xc290 - -#define INPUT_12 0xc2a0 - -#define INPUT_13 0xc2b0 - -#define INPUT_14 0xc2c0 - -#define INPUT_15 0xc2d0 - -#define REF_MON_0 0xc2e0 - -#define REF_MON_1 0xc2ec - -#define REF_MON_2 0xc300 - -#define REF_MON_3 0xc30c - -#define REF_MON_4 0xc318 - -#define REF_MON_5 0xc324 - -#define REF_MON_6 0xc330 - -#define REF_MON_7 0xc33c - -#define REF_MON_8 0xc348 - -#define REF_MON_9 0xc354 - -#define REF_MON_10 0xc360 - -#define REF_MON_11 0xc36c - -#define REF_MON_12 0xc380 - -#define REF_MON_13 0xc38c - -#define REF_MON_14 0xc398 - -#define REF_MON_15 0xc3a4 - -#define DPLL_0 0xc3b0 -#define DPLL_CTRL_REG_0 0x0002 -#define DPLL_CTRL_REG_1 0x0003 -#define DPLL_CTRL_REG_2 0x0004 -#define DPLL_TOD_SYNC_CFG 0x0031 -#define DPLL_COMBO_SLAVE_CFG_0 0x0032 -#define DPLL_COMBO_SLAVE_CFG_1 0x0033 -#define DPLL_SLAVE_REF_CFG 0x0034 -#define DPLL_REF_MODE 0x0035 -#define DPLL_PHASE_MEASUREMENT_CFG 0x0036 -#define DPLL_MODE 0x0037 - -#define DPLL_1 0xc400 - -#define DPLL_2 0xc438 - -#define DPLL_3 0xc480 - -#define DPLL_4 0xc4b8 - -#define DPLL_5 0xc500 - -#define DPLL_6 0xc538 - -#define DPLL_7 0xc580 - -#define SYS_DPLL 0xc5b8 - -#define DPLL_CTRL_0 0xc600 -#define DPLL_CTRL_DPLL_MANU_REF_CFG 0x0001 -#define DPLL_CTRL_COMBO_MASTER_CFG 0x003a - -#define DPLL_CTRL_1 0xc63c - -#define DPLL_CTRL_2 0xc680 - -#define DPLL_CTRL_3 0xc6bc - -#define DPLL_CTRL_4 0xc700 - -#define DPLL_CTRL_5 0xc73c - -#define DPLL_CTRL_6 0xc780 - -#define DPLL_CTRL_7 0xc7bc - -#define SYS_DPLL_CTRL 0xc800 - -#define DPLL_PHASE_0 0xc818 - -/* Signed 42-bit FFO in units of 2^(-53) */ -#define DPLL_WR_PHASE 0x0000 - -#define DPLL_PHASE_1 0xc81c - -#define DPLL_PHASE_2 0xc820 - -#define DPLL_PHASE_3 0xc824 - -#define DPLL_PHASE_4 0xc828 - -#define DPLL_PHASE_5 0xc82c - -#define DPLL_PHASE_6 0xc830 - -#define DPLL_PHASE_7 0xc834 - -#define DPLL_FREQ_0 0xc838 - -/* Signed 42-bit FFO in units of 2^(-53) */ -#define DPLL_WR_FREQ 0x0000 - -#define DPLL_FREQ_1 0xc840 - -#define DPLL_FREQ_2 0xc848 - -#define DPLL_FREQ_3 0xc850 - -#define DPLL_FREQ_4 0xc858 - -#define DPLL_FREQ_5 0xc860 - -#define DPLL_FREQ_6 0xc868 - -#define DPLL_FREQ_7 0xc870 - -#define DPLL_PHASE_PULL_IN_0 0xc880 -#define PULL_IN_OFFSET 0x0000 /* Signed 32 bit */ -#define PULL_IN_SLOPE_LIMIT 0x0004 /* Unsigned 24 bit */ -#define PULL_IN_CTRL 0x0007 - -#define DPLL_PHASE_PULL_IN_1 0xc888 - -#define DPLL_PHASE_PULL_IN_2 0xc890 - -#define DPLL_PHASE_PULL_IN_3 0xc898 - -#define DPLL_PHASE_PULL_IN_4 0xc8a0 - -#define DPLL_PHASE_PULL_IN_5 0xc8a8 - -#define DPLL_PHASE_PULL_IN_6 0xc8b0 - -#define DPLL_PHASE_PULL_IN_7 0xc8b8 - -#define GPIO_CFG 0xc8c0 -#define GPIO_CFG_GBL 0x0000 - -#define GPIO_0 0xc8c2 -#define GPIO_DCO_INC_DEC 0x0000 -#define GPIO_OUT_CTRL_0 0x0001 -#define GPIO_OUT_CTRL_1 0x0002 -#define GPIO_TOD_TRIG 0x0003 -#define GPIO_DPLL_INDICATOR 0x0004 -#define GPIO_LOS_INDICATOR 0x0005 -#define GPIO_REF_INPUT_DSQ_0 0x0006 -#define GPIO_REF_INPUT_DSQ_1 0x0007 -#define GPIO_REF_INPUT_DSQ_2 0x0008 -#define GPIO_REF_INPUT_DSQ_3 0x0009 -#define GPIO_MAN_CLK_SEL_0 0x000a -#define GPIO_MAN_CLK_SEL_1 0x000b -#define GPIO_MAN_CLK_SEL_2 0x000c -#define GPIO_SLAVE 0x000d -#define GPIO_ALERT_OUT_CFG 0x000e -#define GPIO_TOD_NOTIFICATION_CFG 0x000f -#define GPIO_CTRL 0x0010 - -#define GPIO_1 0xc8d4 - -#define GPIO_2 0xc8e6 - -#define GPIO_3 0xc900 - -#define GPIO_4 0xc912 - -#define GPIO_5 0xc924 - -#define GPIO_6 0xc936 - -#define GPIO_7 0xc948 - -#define GPIO_8 0xc95a - -#define GPIO_9 0xc980 - -#define GPIO_10 0xc992 - -#define GPIO_11 0xc9a4 - -#define GPIO_12 0xc9b6 - -#define GPIO_13 0xc9c8 - -#define GPIO_14 0xc9da - -#define GPIO_15 0xca00 - -#define OUT_DIV_MUX 0xca12 - -#define OUTPUT_0 0xca14 -/* FOD frequency output divider value */ -#define OUT_DIV 0x0000 -#define OUT_DUTY_CYCLE_HIGH 0x0004 -#define OUT_CTRL_0 0x0008 -#define OUT_CTRL_1 0x0009 -/* Phase adjustment in FOD cycles */ -#define OUT_PHASE_ADJ 0x000c - -#define OUTPUT_1 0xca24 - -#define OUTPUT_2 0xca34 - -#define OUTPUT_3 0xca44 - -#define OUTPUT_4 0xca54 - -#define OUTPUT_5 0xca64 - -#define OUTPUT_6 0xca80 - -#define OUTPUT_7 0xca90 - -#define OUTPUT_8 0xcaa0 - -#define OUTPUT_9 0xcab0 - -#define OUTPUT_10 0xcac0 - -#define OUTPUT_11 0xcad0 - -#define SERIAL 0xcae0 - -#define PWM_ENCODER_0 0xcb00 - -#define PWM_ENCODER_1 0xcb08 - -#define PWM_ENCODER_2 0xcb10 - -#define PWM_ENCODER_3 0xcb18 - -#define PWM_ENCODER_4 0xcb20 - -#define PWM_ENCODER_5 0xcb28 - -#define PWM_ENCODER_6 0xcb30 - -#define PWM_ENCODER_7 0xcb38 - -#define PWM_DECODER_0 0xcb40 - -#define PWM_DECODER_1 0xcb48 - -#define PWM_DECODER_2 0xcb50 - -#define PWM_DECODER_3 0xcb58 - -#define PWM_DECODER_4 0xcb60 - -#define PWM_DECODER_5 0xcb68 - -#define PWM_DECODER_6 0xcb70 - -#define PWM_DECODER_7 0xcb80 - -#define PWM_DECODER_8 0xcb88 - -#define PWM_DECODER_9 0xcb90 - -#define PWM_DECODER_10 0xcb98 - -#define PWM_DECODER_11 0xcba0 - -#define PWM_DECODER_12 0xcba8 - -#define PWM_DECODER_13 0xcbb0 - -#define PWM_DECODER_14 0xcbb8 - -#define PWM_DECODER_15 0xcbc0 - -#define PWM_USER_DATA 0xcbc8 - -#define TOD_0 0xcbcc - -/* Enable TOD counter, output channel sync and even-PPS mode */ -#define TOD_CFG 0x0000 - -#define TOD_1 0xcbce - -#define TOD_2 0xcbd0 - -#define TOD_3 0xcbd2 - - -#define TOD_WRITE_0 0xcc00 -/* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_WRITE 0x0000 -/* Counter increments after TOD write is completed */ -#define TOD_WRITE_COUNTER 0x000c -/* TOD write trigger configuration */ -#define TOD_WRITE_SELECT_CFG_0 0x000d -/* TOD write trigger selection */ -#define TOD_WRITE_CMD 0x000f - -#define TOD_WRITE_1 0xcc10 - -#define TOD_WRITE_2 0xcc20 - -#define TOD_WRITE_3 0xcc30 - -#define TOD_READ_PRIMARY_0 0xcc40 -/* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_READ_PRIMARY 0x0000 -/* Counter increments after TOD write is completed */ -#define TOD_READ_PRIMARY_COUNTER 0x000b -/* Read trigger configuration */ -#define TOD_READ_PRIMARY_SEL_CFG_0 0x000c -/* Read trigger selection */ -#define TOD_READ_PRIMARY_CMD 0x000e - -#define TOD_READ_PRIMARY_1 0xcc50 - -#define TOD_READ_PRIMARY_2 0xcc60 - -#define TOD_READ_PRIMARY_3 0xcc80 - -#define TOD_READ_SECONDARY_0 0xcc90 - -#define TOD_READ_SECONDARY_1 0xcca0 - -#define TOD_READ_SECONDARY_2 0xccb0 - -#define TOD_READ_SECONDARY_3 0xccc0 - -#define OUTPUT_TDC_CFG 0xccd0 - -#define OUTPUT_TDC_0 0xcd00 - -#define OUTPUT_TDC_1 0xcd08 - -#define OUTPUT_TDC_2 0xcd10 - -#define OUTPUT_TDC_3 0xcd18 - -#define INPUT_TDC 0xcd20 - -#define SCRATCH 0xcf50 - -#define EEPROM 0xcf68 - -#define OTP 0xcf70 - -#define BYTE 0xcf80 - -/* Bit definitions for the MAJ_REL register */ -#define MAJOR_SHIFT (1) -#define MAJOR_MASK (0x7f) -#define PR_BUILD BIT(0) - -/* Bit definitions for the USER_GPIO0_TO_7_STATUS register */ -#define GPIO0_LEVEL BIT(0) -#define GPIO1_LEVEL BIT(1) -#define GPIO2_LEVEL BIT(2) -#define GPIO3_LEVEL BIT(3) -#define GPIO4_LEVEL BIT(4) -#define GPIO5_LEVEL BIT(5) -#define GPIO6_LEVEL BIT(6) -#define GPIO7_LEVEL BIT(7) - -/* Bit definitions for the USER_GPIO8_TO_15_STATUS register */ -#define GPIO8_LEVEL BIT(0) -#define GPIO9_LEVEL BIT(1) -#define GPIO10_LEVEL BIT(2) -#define GPIO11_LEVEL BIT(3) -#define GPIO12_LEVEL BIT(4) -#define GPIO13_LEVEL BIT(5) -#define GPIO14_LEVEL BIT(6) -#define GPIO15_LEVEL BIT(7) - -/* Bit definitions for the GPIO0_TO_7_OUT register */ -#define GPIO0_DRIVE_LEVEL BIT(0) -#define GPIO1_DRIVE_LEVEL BIT(1) -#define GPIO2_DRIVE_LEVEL BIT(2) -#define GPIO3_DRIVE_LEVEL BIT(3) -#define GPIO4_DRIVE_LEVEL BIT(4) -#define GPIO5_DRIVE_LEVEL BIT(5) -#define GPIO6_DRIVE_LEVEL BIT(6) -#define GPIO7_DRIVE_LEVEL BIT(7) - -/* Bit definitions for the GPIO8_TO_15_OUT register */ -#define GPIO8_DRIVE_LEVEL BIT(0) -#define GPIO9_DRIVE_LEVEL BIT(1) -#define GPIO10_DRIVE_LEVEL BIT(2) -#define GPIO11_DRIVE_LEVEL BIT(3) -#define GPIO12_DRIVE_LEVEL BIT(4) -#define GPIO13_DRIVE_LEVEL BIT(5) -#define GPIO14_DRIVE_LEVEL BIT(6) -#define GPIO15_DRIVE_LEVEL BIT(7) - -/* Bit definitions for the DPLL_TOD_SYNC_CFG register */ -#define TOD_SYNC_SOURCE_SHIFT (1) -#define TOD_SYNC_SOURCE_MASK (0x3) -#define TOD_SYNC_EN BIT(0) - -/* Bit definitions for the DPLL_MODE register */ -#define WRITE_TIMER_MODE BIT(6) -#define PLL_MODE_SHIFT (3) -#define PLL_MODE_MASK (0x7) -#define STATE_MODE_SHIFT (0) -#define STATE_MODE_MASK (0x7) - -/* Bit definitions for the GPIO_CFG_GBL register */ -#define SUPPLY_MODE_SHIFT (0) -#define SUPPLY_MODE_MASK (0x3) - -/* Bit definitions for the GPIO_DCO_INC_DEC register */ -#define INCDEC_DPLL_INDEX_SHIFT (0) -#define INCDEC_DPLL_INDEX_MASK (0x7) - -/* Bit definitions for the GPIO_OUT_CTRL_0 register */ -#define CTRL_OUT_0 BIT(0) -#define CTRL_OUT_1 BIT(1) -#define CTRL_OUT_2 BIT(2) -#define CTRL_OUT_3 BIT(3) -#define CTRL_OUT_4 BIT(4) -#define CTRL_OUT_5 BIT(5) -#define CTRL_OUT_6 BIT(6) -#define CTRL_OUT_7 BIT(7) - -/* Bit definitions for the GPIO_OUT_CTRL_1 register */ -#define CTRL_OUT_8 BIT(0) -#define CTRL_OUT_9 BIT(1) -#define CTRL_OUT_10 BIT(2) -#define CTRL_OUT_11 BIT(3) -#define CTRL_OUT_12 BIT(4) -#define CTRL_OUT_13 BIT(5) -#define CTRL_OUT_14 BIT(6) -#define CTRL_OUT_15 BIT(7) - -/* Bit definitions for the GPIO_TOD_TRIG register */ -#define TOD_TRIG_0 BIT(0) -#define TOD_TRIG_1 BIT(1) -#define TOD_TRIG_2 BIT(2) -#define TOD_TRIG_3 BIT(3) - -/* Bit definitions for the GPIO_DPLL_INDICATOR register */ -#define IND_DPLL_INDEX_SHIFT (0) -#define IND_DPLL_INDEX_MASK (0x7) - -/* Bit definitions for the GPIO_LOS_INDICATOR register */ -#define REFMON_INDEX_SHIFT (0) -#define REFMON_INDEX_MASK (0xf) -/* Active level of LOS indicator, 0=low 1=high */ -#define ACTIVE_LEVEL BIT(4) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_0 register */ -#define DSQ_INP_0 BIT(0) -#define DSQ_INP_1 BIT(1) -#define DSQ_INP_2 BIT(2) -#define DSQ_INP_3 BIT(3) -#define DSQ_INP_4 BIT(4) -#define DSQ_INP_5 BIT(5) -#define DSQ_INP_6 BIT(6) -#define DSQ_INP_7 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_1 register */ -#define DSQ_INP_8 BIT(0) -#define DSQ_INP_9 BIT(1) -#define DSQ_INP_10 BIT(2) -#define DSQ_INP_11 BIT(3) -#define DSQ_INP_12 BIT(4) -#define DSQ_INP_13 BIT(5) -#define DSQ_INP_14 BIT(6) -#define DSQ_INP_15 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_2 register */ -#define DSQ_DPLL_0 BIT(0) -#define DSQ_DPLL_1 BIT(1) -#define DSQ_DPLL_2 BIT(2) -#define DSQ_DPLL_3 BIT(3) -#define DSQ_DPLL_4 BIT(4) -#define DSQ_DPLL_5 BIT(5) -#define DSQ_DPLL_6 BIT(6) -#define DSQ_DPLL_7 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_3 register */ -#define DSQ_DPLL_SYS BIT(0) -#define GPIO_DSQ_LEVEL BIT(1) - -/* Bit definitions for the GPIO_TOD_NOTIFICATION_CFG register */ -#define DPLL_TOD_SHIFT (0) -#define DPLL_TOD_MASK (0x3) -#define TOD_READ_SECONDARY BIT(2) -#define GPIO_ASSERT_LEVEL BIT(3) - -/* Bit definitions for the GPIO_CTRL register */ -#define GPIO_FUNCTION_EN BIT(0) -#define GPIO_CMOS_OD_MODE BIT(1) -#define GPIO_CONTROL_DIR BIT(2) -#define GPIO_PU_PD_MODE BIT(3) -#define GPIO_FUNCTION_SHIFT (4) -#define GPIO_FUNCTION_MASK (0xf) - -/* Bit definitions for the OUT_CTRL_1 register */ -#define OUT_SYNC_DISABLE BIT(7) -#define SQUELCH_VALUE BIT(6) -#define SQUELCH_DISABLE BIT(5) -#define PAD_VDDO_SHIFT (2) -#define PAD_VDDO_MASK (0x7) -#define PAD_CMOSDRV_SHIFT (0) -#define PAD_CMOSDRV_MASK (0x3) - -/* Bit definitions for the TOD_CFG register */ -#define TOD_EVEN_PPS_MODE BIT(2) -#define TOD_OUT_SYNC_ENABLE BIT(1) -#define TOD_ENABLE BIT(0) - -/* Bit definitions for the TOD_WRITE_SELECT_CFG_0 register */ -#define WR_PWM_DECODER_INDEX_SHIFT (4) -#define WR_PWM_DECODER_INDEX_MASK (0xf) -#define WR_REF_INDEX_SHIFT (0) -#define WR_REF_INDEX_MASK (0xf) - -/* Bit definitions for the TOD_WRITE_CMD register */ -#define TOD_WRITE_SELECTION_SHIFT (0) -#define TOD_WRITE_SELECTION_MASK (0xf) -/* 4.8.7 */ -#define TOD_WRITE_TYPE_SHIFT (4) -#define TOD_WRITE_TYPE_MASK (0x3) - -/* Bit definitions for the TOD_READ_PRIMARY_SEL_CFG_0 register */ -#define RD_PWM_DECODER_INDEX_SHIFT (4) -#define RD_PWM_DECODER_INDEX_MASK (0xf) -#define RD_REF_INDEX_SHIFT (0) -#define RD_REF_INDEX_MASK (0xf) - -/* Bit definitions for the TOD_READ_PRIMARY_CMD register */ -#define TOD_READ_TRIGGER_MODE BIT(4) -#define TOD_READ_TRIGGER_SHIFT (0) -#define TOD_READ_TRIGGER_MASK (0xf) - -/* Bit definitions for the DPLL_CTRL_COMBO_MASTER_CFG register */ -#define COMBO_MASTER_HOLD BIT(0) - -/* Bit definitions for DPLL_SYS_STATUS register */ -#define DPLL_SYS_STATE_MASK (0xf) - -/* Bit definitions for SYS_APLL_STATUS register */ -#define SYS_APLL_LOSS_LOCK_LIVE_MASK BIT(0) -#define SYS_APLL_LOSS_LOCK_LIVE_LOCKED 0 -#define SYS_APLL_LOSS_LOCK_LIVE_UNLOCKED 1 - -#endif diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index fa636951169e58..6bc5791a7ec5bb 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -6,7 +6,7 @@ * Copyright (C) 2019 Integrated Device Technology, Inc., a Renesas Company. */ #include <linux/firmware.h> -#include <linux/i2c.h> +#include <linux/platform_device.h> #include <linux/module.h> #include <linux/ptp_clock_kernel.h> #include <linux/delay.h> @@ -14,6 +14,10 @@ #include <linux/kernel.h> #include <linux/timekeeping.h> #include <linux/string.h> +#include <linux/of.h> +#include <linux/mfd/rsmu.h> +#include <linux/mfd/idt8a340_reg.h> +#include <asm/unaligned.h> #include "ptp_private.h" #include "ptp_clockmatrix.h" @@ -32,16 +36,43 @@ static char *firmware; module_param(firmware, charp, 0); #define SETTIME_CORRECTION (0) +#define EXTTS_PERIOD_MS (95) -static int contains_full_configuration(const struct firmware *fw) +static int _idtcm_adjfine(struct idtcm_channel *channel, long scaled_ppm); + +static inline int idtcm_read(struct idtcm *idtcm, + u16 module, + u16 regaddr, + u8 *buf, + u16 count) +{ + return regmap_bulk_read(idtcm->regmap, module + regaddr, buf, count); +} + +static inline int idtcm_write(struct idtcm *idtcm, + u16 module, + u16 regaddr, + u8 *buf, + u16 count) +{ + return regmap_bulk_write(idtcm->regmap, module + regaddr, buf, count); +} + +static int contains_full_configuration(struct idtcm *idtcm, + const struct firmware *fw) { - s32 full_count = FULL_FW_CFG_BYTES - FULL_FW_CFG_SKIPPED_BYTES; struct idtcm_fwrc *rec = (struct idtcm_fwrc *)fw->data; + u16 scratch = IDTCM_FW_REG(idtcm->fw_ver, V520, SCRATCH); + s32 full_count; s32 count = 0; u16 regaddr; u8 loaddr; s32 len; + /* 4 bytes skipped every 0x80 */ + full_count = (scratch - GPIO_USER_CONTROL) - + ((scratch >> 7) - (GPIO_USER_CONTROL >> 7)) * 4; + /* If the firmware contains 'full configuration' SM_RESET can be used * to ensure proper configuration. * @@ -57,7 +88,7 @@ static int contains_full_configuration(const struct firmware *fw) rec++; /* Top (status registers) and bottom are read-only */ - if (regaddr < GPIO_USER_CONTROL || regaddr >= SCRATCH) + if (regaddr < GPIO_USER_CONTROL || regaddr >= scratch) continue; /* Page size 128, last 4 bytes of page skipped */ @@ -152,132 +183,17 @@ static int idtcm_strverscmp(const char *version1, const char *version2) return 0; } -static int idtcm_xfer_read(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count) -{ - struct i2c_client *client = idtcm->client; - struct i2c_msg msg[2]; - int cnt; - - msg[0].addr = client->addr; - msg[0].flags = 0; - msg[0].len = 1; - msg[0].buf = ®addr; - - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].len = count; - msg[1].buf = buf; - - cnt = i2c_transfer(client->adapter, msg, 2); - - if (cnt < 0) { - dev_err(&client->dev, - "i2c_transfer failed at %d in %s, at addr: %04x!", - __LINE__, __func__, regaddr); - return cnt; - } else if (cnt != 2) { - dev_err(&client->dev, - "i2c_transfer sent only %d of %d messages", cnt, 2); - return -EIO; - } - - return 0; -} - -static int idtcm_xfer_write(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count) -{ - struct i2c_client *client = idtcm->client; - /* we add 1 byte for device register */ - u8 msg[IDTCM_MAX_WRITE_COUNT + 1]; - int cnt; - - if (count > IDTCM_MAX_WRITE_COUNT) - return -EINVAL; - - msg[0] = regaddr; - memcpy(&msg[1], buf, count); - - cnt = i2c_master_send(client, msg, count + 1); - - if (cnt < 0) { - dev_err(&client->dev, - "i2c_master_send failed at %d in %s, at addr: %04x!", - __LINE__, __func__, regaddr); - return cnt; - } - - return 0; -} - -static int idtcm_page_offset(struct idtcm *idtcm, u8 val) -{ - u8 buf[4]; - int err; - - if (idtcm->page_offset == val) - return 0; - - buf[0] = 0x0; - buf[1] = val; - buf[2] = 0x10; - buf[3] = 0x20; - - err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf)); - if (err) { - idtcm->page_offset = 0xff; - dev_err(&idtcm->client->dev, "failed to set page offset"); - } else { - idtcm->page_offset = val; - } - - return err; -} - -static int _idtcm_rdwr(struct idtcm *idtcm, - u16 regaddr, - u8 *buf, - u16 count, - bool write) +static enum fw_version idtcm_fw_version(const char *version) { - u8 hi; - u8 lo; - int err; + enum fw_version ver = V_DEFAULT; - hi = (regaddr >> 8) & 0xff; - lo = regaddr & 0xff; - - err = idtcm_page_offset(idtcm, hi); - if (err) - return err; - - if (write) - return idtcm_xfer_write(idtcm, lo, buf, count); - - return idtcm_xfer_read(idtcm, lo, buf, count); -} + if (idtcm_strverscmp(version, "4.8.7") >= 0) + ver = V487; -static int idtcm_read(struct idtcm *idtcm, - u16 module, - u16 regaddr, - u8 *buf, - u16 count) -{ - return _idtcm_rdwr(idtcm, module + regaddr, buf, count, false); -} + if (idtcm_strverscmp(version, "5.2.0") >= 0) + ver = V520; -static int idtcm_write(struct idtcm *idtcm, - u16 module, - u16 regaddr, - u8 *buf, - u16 count) -{ - return _idtcm_rdwr(idtcm, module + regaddr, buf, count, true); + return ver; } static int clear_boot_status(struct idtcm *idtcm) @@ -318,11 +234,82 @@ static int wait_for_boot_status_ready(struct idtcm *idtcm) } while (i); - dev_warn(&idtcm->client->dev, "%s timed out", __func__); + dev_warn(idtcm->dev, "%s timed out", __func__); return -EBUSY; } +static int _idtcm_set_scsr_read_trig(struct idtcm_channel *channel, + enum scsr_read_trig_sel trig, u8 ref) +{ + struct idtcm *idtcm = channel->idtcm; + u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD); + u8 val; + int err; + + if (trig == SCSR_TOD_READ_TRIG_SEL_REFCLK) { + err = idtcm_read(idtcm, channel->tod_read_primary, + TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val)); + if (err) + return err; + + val &= ~(WR_REF_INDEX_MASK << WR_REF_INDEX_SHIFT); + val |= (ref << WR_REF_INDEX_SHIFT); + + err = idtcm_write(idtcm, channel->tod_read_primary, + TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val)); + if (err) + return err; + } + + err = idtcm_read(idtcm, channel->tod_read_primary, + tod_read_cmd, &val, sizeof(val)); + if (err) + return err; + + val &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT); + val |= (trig << TOD_READ_TRIGGER_SHIFT); + val &= ~TOD_READ_TRIGGER_MODE; /* single shot */ + + err = idtcm_write(idtcm, channel->tod_read_primary, + tod_read_cmd, &val, sizeof(val)); + return err; +} + +static int idtcm_enable_extts(struct idtcm_channel *channel, u8 todn, u8 ref, + bool enable) +{ + struct idtcm *idtcm = channel->idtcm; + u8 old_mask = idtcm->extts_mask; + u8 mask = 1 << todn; + int err = 0; + + if (todn >= MAX_TOD) + return -EINVAL; + + if (enable) { + if (ref > 0xF) /* E_REF_CLK15 */ + return -EINVAL; + if (idtcm->extts_mask & mask) + return 0; + err = _idtcm_set_scsr_read_trig(&idtcm->channel[todn], + SCSR_TOD_READ_TRIG_SEL_REFCLK, + ref); + if (err == 0) { + idtcm->extts_mask |= mask; + idtcm->event_channel[todn] = channel; + idtcm->channel[todn].refn = ref; + } + } else + idtcm->extts_mask &= ~mask; + + if (old_mask == 0 && idtcm->extts_mask) + schedule_delayed_work(&idtcm->extts_work, + msecs_to_jiffies(EXTTS_PERIOD_MS)); + + return err; +} + static int read_sys_apll_status(struct idtcm *idtcm, u8 *status) { return idtcm_read(idtcm, STATUS, DPLL_SYS_APLL_STATUS, status, @@ -359,7 +346,7 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) } else if (dpll == DPLL_STATE_FREERUN || dpll == DPLL_STATE_HOLDOVER || dpll == DPLL_STATE_OPEN_LOOP) { - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "No wait state: DPLL_SYS_STATE %d", dpll); return -EPERM; } @@ -367,7 +354,7 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) msleep(LOCK_POLL_INTERVAL_MS); } while (time_is_after_jiffies(timeout)); - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "%d ms lock timeout: SYS APLL Loss Lock %d SYS DPLL state %d", LOCK_TIMEOUT_MS, apll, dpll); @@ -377,50 +364,36 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) static void wait_for_chip_ready(struct idtcm *idtcm) { if (wait_for_boot_status_ready(idtcm)) - dev_warn(&idtcm->client->dev, "BOOT_STATUS != 0xA0"); + dev_warn(idtcm->dev, "BOOT_STATUS != 0xA0"); if (wait_for_sys_apll_dpll_lock(idtcm)) - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "Continuing while SYS APLL/DPLL is not locked"); } static int _idtcm_gettime(struct idtcm_channel *channel, - struct timespec64 *ts) + struct timespec64 *ts, u8 timeout) { struct idtcm *idtcm = channel->idtcm; + u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD); u8 buf[TOD_BYTE_COUNT]; - u8 timeout = 10; u8 trigger; int err; - err = idtcm_read(idtcm, channel->tod_read_primary, - TOD_READ_PRIMARY_CMD, &trigger, sizeof(trigger)); - if (err) - return err; - - trigger &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT); - trigger |= (1 << TOD_READ_TRIGGER_SHIFT); - trigger &= ~TOD_READ_TRIGGER_MODE; /* single shot */ - - err = idtcm_write(idtcm, channel->tod_read_primary, - TOD_READ_PRIMARY_CMD, &trigger, sizeof(trigger)); - if (err) - return err; - /* wait trigger to be 0 */ - while (trigger & TOD_READ_TRIGGER_MASK) { + do { + if (timeout-- == 0) + return -EIO; + if (idtcm->calculate_overhead_flag) idtcm->start_time = ktime_get_raw(); err = idtcm_read(idtcm, channel->tod_read_primary, - TOD_READ_PRIMARY_CMD, &trigger, + tod_read_cmd, &trigger, sizeof(trigger)); if (err) return err; - - if (--timeout == 0) - return -EIO; - } + } while (trigger & TOD_READ_TRIGGER_MASK); err = idtcm_read(idtcm, channel->tod_read_primary, TOD_READ_PRIMARY, buf, sizeof(buf)); @@ -432,6 +405,79 @@ static int _idtcm_gettime(struct idtcm_channel *channel, return err; } +static int idtcm_extts_check_channel(struct idtcm *idtcm, u8 todn) +{ + struct idtcm_channel *ptp_channel, *extts_channel; + struct ptp_clock_event event; + struct timespec64 ts; + u32 dco_delay = 0; + int err; + + extts_channel = &idtcm->channel[todn]; + ptp_channel = idtcm->event_channel[todn]; + if (extts_channel == ptp_channel) + dco_delay = ptp_channel->dco_delay; + + err = _idtcm_gettime(extts_channel, &ts, 1); + if (err == 0) { + event.type = PTP_CLOCK_EXTTS; + event.index = todn; + event.timestamp = timespec64_to_ns(&ts) - dco_delay; + ptp_clock_event(ptp_channel->ptp_clock, &event); + } + return err; +} + +static u8 idtcm_enable_extts_mask(struct idtcm_channel *channel, + u8 extts_mask, bool enable) +{ + struct idtcm *idtcm = channel->idtcm; + int i, err; + + for (i = 0; i < MAX_TOD; i++) { + u8 mask = 1 << i; + u8 refn = idtcm->channel[i].refn; + + if (extts_mask & mask) { + /* check extts before disabling it */ + if (enable == false) { + err = idtcm_extts_check_channel(idtcm, i); + /* trigger happened so we won't re-enable it */ + if (err == 0) + extts_mask &= ~mask; + } + (void)idtcm_enable_extts(channel, i, refn, enable); + } + } + + return extts_mask; +} + +static int _idtcm_gettime_immediate(struct idtcm_channel *channel, + struct timespec64 *ts) +{ + struct idtcm *idtcm = channel->idtcm; + u8 extts_mask = 0; + int err; + + /* Disable extts */ + if (idtcm->extts_mask) { + extts_mask = idtcm_enable_extts_mask(channel, idtcm->extts_mask, + false); + } + + err = _idtcm_set_scsr_read_trig(channel, + SCSR_TOD_READ_TRIG_SEL_IMMEDIATE, 0); + if (err == 0) + err = _idtcm_gettime(channel, ts, 10); + + /* Re-enable extts */ + if (extts_mask) + idtcm_enable_extts_mask(channel, extts_mask, true); + + return err; +} + static int _sync_pll_output(struct idtcm *idtcm, u8 pll, u8 sync_src, @@ -559,35 +605,10 @@ static int _sync_pll_output(struct idtcm *idtcm, return err; } -static int sync_source_dpll_tod_pps(u16 tod_addr, u8 *sync_src) -{ - int err = 0; - - switch (tod_addr) { - case TOD_0: - *sync_src = SYNC_SOURCE_DPLL0_TOD_PPS; - break; - case TOD_1: - *sync_src = SYNC_SOURCE_DPLL1_TOD_PPS; - break; - case TOD_2: - *sync_src = SYNC_SOURCE_DPLL2_TOD_PPS; - break; - case TOD_3: - *sync_src = SYNC_SOURCE_DPLL3_TOD_PPS; - break; - default: - err = -EINVAL; - } - - return err; -} - static int idtcm_sync_pps_output(struct idtcm_channel *channel) { struct idtcm *idtcm = channel->idtcm; u8 pll; - u8 sync_src; u8 qn; u8 qn_plus_1; int err = 0; @@ -596,10 +617,6 @@ static int idtcm_sync_pps_output(struct idtcm_channel *channel) u8 temp; u16 output_mask = channel->output_mask; - err = sync_source_dpll_tod_pps(channel->tod_n, &sync_src); - if (err) - return err; - err = idtcm_read(idtcm, 0, HW_Q8_CTRL_SPARE, &temp, sizeof(temp)); if (err) @@ -655,8 +672,8 @@ static int idtcm_sync_pps_output(struct idtcm_channel *channel) } if (qn != 0 || qn_plus_1 != 0) - err = _sync_pll_output(idtcm, pll, sync_src, qn, - qn_plus_1); + err = _sync_pll_output(idtcm, pll, channel->sync_src, + qn, qn_plus_1); if (err) return err; @@ -666,8 +683,8 @@ static int idtcm_sync_pps_output(struct idtcm_channel *channel) } static int _idtcm_set_dpll_hw_tod(struct idtcm_channel *channel, - struct timespec64 const *ts, - enum hw_tod_write_trig_sel wr_trig) + struct timespec64 const *ts, + enum hw_tod_write_trig_sel wr_trig) { struct idtcm *idtcm = channel->idtcm; u8 buf[TOD_BYTE_COUNT]; @@ -784,7 +801,7 @@ static int _idtcm_set_dpll_scsr_tod(struct idtcm_channel *channel, break; if (++count > 20) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Timed out waiting for the write counter"); return -EIO; } @@ -793,46 +810,46 @@ static int _idtcm_set_dpll_scsr_tod(struct idtcm_channel *channel, return 0; } -static int get_output_base_addr(u8 outn) +static int get_output_base_addr(enum fw_version ver, u8 outn) { int base; switch (outn) { case 0: - base = OUTPUT_0; + base = IDTCM_FW_REG(ver, V520, OUTPUT_0); break; case 1: - base = OUTPUT_1; + base = IDTCM_FW_REG(ver, V520, OUTPUT_1); break; case 2: - base = OUTPUT_2; + base = IDTCM_FW_REG(ver, V520, OUTPUT_2); break; case 3: - base = OUTPUT_3; + base = IDTCM_FW_REG(ver, V520, OUTPUT_3); break; case 4: - base = OUTPUT_4; + base = IDTCM_FW_REG(ver, V520, OUTPUT_4); break; case 5: - base = OUTPUT_5; + base = IDTCM_FW_REG(ver, V520, OUTPUT_5); break; case 6: - base = OUTPUT_6; + base = IDTCM_FW_REG(ver, V520, OUTPUT_6); break; case 7: - base = OUTPUT_7; + base = IDTCM_FW_REG(ver, V520, OUTPUT_7); break; case 8: - base = OUTPUT_8; + base = IDTCM_FW_REG(ver, V520, OUTPUT_8); break; case 9: - base = OUTPUT_9; + base = IDTCM_FW_REG(ver, V520, OUTPUT_9); break; case 10: - base = OUTPUT_10; + base = IDTCM_FW_REG(ver, V520, OUTPUT_10); break; case 11: - base = OUTPUT_11; + base = IDTCM_FW_REG(ver, V520, OUTPUT_11); break; default: base = -EINVAL; @@ -849,7 +866,7 @@ static int _idtcm_settime_deprecated(struct idtcm_channel *channel, err = _idtcm_set_dpll_hw_tod(channel, ts, HW_TOD_WR_TRIG_SEL_MSB); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "%s: Set HW ToD failed", __func__); return err; } @@ -929,9 +946,9 @@ static int idtcm_start_phase_pull_in(struct idtcm_channel *channel) return err; } -static int idtcm_do_phase_pull_in(struct idtcm_channel *channel, - s32 offset_ns, - u32 max_ffo_ppb) +static int do_phase_pull_in_fw(struct idtcm_channel *channel, + s32 offset_ns, + u32 max_ffo_ppb) { int err; @@ -1000,7 +1017,7 @@ static int _idtcm_adjtime_deprecated(struct idtcm_channel *channel, s64 delta) s64 now; if (abs(delta) < PHASE_PULL_IN_THRESHOLD_NS_DEPRECATED) { - err = idtcm_do_phase_pull_in(channel, delta, 0); + err = channel->do_phase_pull_in(channel, delta, 0); } else { idtcm->calculate_overhead_flag = 1; @@ -1008,7 +1025,7 @@ static int _idtcm_adjtime_deprecated(struct idtcm_channel *channel, s64 delta) if (err) return err; - err = _idtcm_gettime(channel, &ts); + err = _idtcm_gettime_immediate(channel, &ts); if (err) return err; @@ -1032,7 +1049,9 @@ static int idtcm_state_machine_reset(struct idtcm *idtcm) clear_boot_status(idtcm); - err = idtcm_write(idtcm, RESET_CTRL, SM_RESET, &byte, sizeof(byte)); + err = idtcm_write(idtcm, RESET_CTRL, + IDTCM_FW_REG(idtcm->fw_ver, V520, SM_RESET), + &byte, sizeof(byte)); if (!err) { for (i = 0; i < 30; i++) { @@ -1040,14 +1059,14 @@ static int idtcm_state_machine_reset(struct idtcm *idtcm) read_boot_status(idtcm, &status); if (status == 0xA0) { - dev_dbg(&idtcm->client->dev, + dev_dbg(idtcm->dev, "SM_RESET completed in %d ms", i * 100); break; } } if (!status) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Timed out waiting for CM_RESET to complete"); } @@ -1144,12 +1163,12 @@ static int set_pll_output_mask(struct idtcm *idtcm, u16 addr, u8 val) static int set_tod_ptp_pll(struct idtcm *idtcm, u8 index, u8 pll) { if (index >= MAX_TOD) { - dev_err(&idtcm->client->dev, "ToD%d not supported", index); + dev_err(idtcm->dev, "ToD%d not supported", index); return -EINVAL; } if (pll >= MAX_PLL) { - dev_err(&idtcm->client->dev, "Pll%d not supported", pll); + dev_err(idtcm->dev, "Pll%d not supported", pll); return -EINVAL; } @@ -1167,7 +1186,7 @@ static int check_and_set_masks(struct idtcm *idtcm, switch (regaddr) { case TOD_MASK_ADDR: if ((val & 0xf0) || !(val & 0x0f)) { - dev_err(&idtcm->client->dev, "Invalid TOD mask 0x%02x", val); + dev_err(idtcm->dev, "Invalid TOD mask 0x%02x", val); err = -EINVAL; } else { idtcm->tod_mask = val; @@ -1198,13 +1217,13 @@ static void display_pll_and_masks(struct idtcm *idtcm) u8 i; u8 mask; - dev_dbg(&idtcm->client->dev, "tod_mask = 0x%02x", idtcm->tod_mask); + dev_dbg(idtcm->dev, "tod_mask = 0x%02x", idtcm->tod_mask); for (i = 0; i < MAX_TOD; i++) { mask = 1 << i; if (mask & idtcm->tod_mask) - dev_dbg(&idtcm->client->dev, + dev_dbg(idtcm->dev, "TOD%d pll = %d output_mask = 0x%04x", i, idtcm->channel[i].pll, idtcm->channel[i].output_mask); @@ -1214,6 +1233,7 @@ static void display_pll_and_masks(struct idtcm *idtcm) static int idtcm_load_firmware(struct idtcm *idtcm, struct device *dev) { + u16 scratch = IDTCM_FW_REG(idtcm->fw_ver, V520, SCRATCH); char fname[128] = FW_FILENAME; const struct firmware *fw; struct idtcm_fwrc *rec; @@ -1226,25 +1246,25 @@ static int idtcm_load_firmware(struct idtcm *idtcm, if (firmware) /* module parameter */ snprintf(fname, sizeof(fname), "%s", firmware); - dev_dbg(&idtcm->client->dev, "requesting firmware '%s'", fname); + dev_info(idtcm->dev, "requesting firmware '%s'", fname); err = request_firmware(&fw, fname, dev); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); return err; } - dev_dbg(&idtcm->client->dev, "firmware size %zu bytes", fw->size); + dev_dbg(idtcm->dev, "firmware size %zu bytes", fw->size); rec = (struct idtcm_fwrc *) fw->data; - if (contains_full_configuration(fw)) + if (contains_full_configuration(idtcm, fw)) idtcm_state_machine_reset(idtcm); for (len = fw->size; len > 0; len -= sizeof(*rec)) { if (rec->reserved) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "bad firmware, reserved field non-zero"); err = -EINVAL; } else { @@ -1263,7 +1283,7 @@ static int idtcm_load_firmware(struct idtcm *idtcm, err = 0; /* Top (status registers) and bottom are read-only */ - if (regaddr < GPIO_USER_CONTROL || regaddr >= SCRATCH) + if (regaddr < GPIO_USER_CONTROL || regaddr >= scratch) continue; /* Page size 128, last 4 bytes of page skipped */ @@ -1292,10 +1312,10 @@ static int idtcm_output_enable(struct idtcm_channel *channel, int err; u8 val; - base = get_output_base_addr(outn); + base = get_output_base_addr(idtcm->fw_ver, outn); if (!(base > 0)) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "%s - Unsupported out%d", __func__, outn); return base; } @@ -1337,8 +1357,8 @@ static int idtcm_output_mask_enable(struct idtcm_channel *channel, } static int idtcm_perout_enable(struct idtcm_channel *channel, - bool enable, - struct ptp_perout_request *perout) + struct ptp_perout_request *perout, + bool enable) { struct idtcm *idtcm = channel->idtcm; unsigned int flags = perout->flags; @@ -1351,7 +1371,7 @@ static int idtcm_perout_enable(struct idtcm_channel *channel, err = idtcm_output_enable(channel, enable, perout->index); if (err) { - dev_err(&idtcm->client->dev, "Unable to set output enable"); + dev_err(idtcm->dev, "Unable to set output enable"); return err; } @@ -1360,53 +1380,331 @@ static int idtcm_perout_enable(struct idtcm_channel *channel, } static int idtcm_get_pll_mode(struct idtcm_channel *channel, - enum pll_mode *pll_mode) + enum pll_mode *mode) { struct idtcm *idtcm = channel->idtcm; int err; u8 dpll_mode; - err = idtcm_read(idtcm, channel->dpll_n, DPLL_MODE, + err = idtcm_read(idtcm, channel->dpll_n, + IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_MODE), &dpll_mode, sizeof(dpll_mode)); if (err) return err; - *pll_mode = (dpll_mode >> PLL_MODE_SHIFT) & PLL_MODE_MASK; + *mode = (dpll_mode >> PLL_MODE_SHIFT) & PLL_MODE_MASK; return 0; } static int idtcm_set_pll_mode(struct idtcm_channel *channel, - enum pll_mode pll_mode) + enum pll_mode mode) { struct idtcm *idtcm = channel->idtcm; int err; u8 dpll_mode; - err = idtcm_read(idtcm, channel->dpll_n, DPLL_MODE, + err = idtcm_read(idtcm, channel->dpll_n, + IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_MODE), &dpll_mode, sizeof(dpll_mode)); if (err) return err; dpll_mode &= ~(PLL_MODE_MASK << PLL_MODE_SHIFT); - dpll_mode |= (pll_mode << PLL_MODE_SHIFT); - - channel->pll_mode = pll_mode; + dpll_mode |= (mode << PLL_MODE_SHIFT); - err = idtcm_write(idtcm, channel->dpll_n, DPLL_MODE, + err = idtcm_write(idtcm, channel->dpll_n, + IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_MODE), &dpll_mode, sizeof(dpll_mode)); + return err; +} + +static int idtcm_get_manual_reference(struct idtcm_channel *channel, + enum manual_reference *ref) +{ + struct idtcm *idtcm = channel->idtcm; + u8 dpll_manu_ref_cfg; + int err; + + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_MANU_REF_CFG, + &dpll_manu_ref_cfg, sizeof(dpll_manu_ref_cfg)); if (err) return err; + dpll_manu_ref_cfg &= (MANUAL_REFERENCE_MASK << MANUAL_REFERENCE_SHIFT); + + *ref = dpll_manu_ref_cfg >> MANUAL_REFERENCE_SHIFT; + return 0; } +static int idtcm_set_manual_reference(struct idtcm_channel *channel, + enum manual_reference ref) +{ + struct idtcm *idtcm = channel->idtcm; + u8 dpll_manu_ref_cfg; + int err; + + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_MANU_REF_CFG, + &dpll_manu_ref_cfg, sizeof(dpll_manu_ref_cfg)); + if (err) + return err; + + dpll_manu_ref_cfg &= ~(MANUAL_REFERENCE_MASK << MANUAL_REFERENCE_SHIFT); + + dpll_manu_ref_cfg |= (ref << MANUAL_REFERENCE_SHIFT); + + err = idtcm_write(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_MANU_REF_CFG, + &dpll_manu_ref_cfg, sizeof(dpll_manu_ref_cfg)); + + return err; +} + +static int configure_dpll_mode_write_frequency(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + int err; + + err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_FREQUENCY); + + if (err) + dev_err(idtcm->dev, "Failed to set pll mode to write frequency"); + else + channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; + + return err; +} + +static int configure_dpll_mode_write_phase(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + int err; + + err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_PHASE); + + if (err) + dev_err(idtcm->dev, "Failed to set pll mode to write phase"); + else + channel->mode = PTP_PLL_MODE_WRITE_PHASE; + + return err; +} + +static int configure_manual_reference_write_frequency(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + int err; + + err = idtcm_set_manual_reference(channel, MANU_REF_WRITE_FREQUENCY); + + if (err) + dev_err(idtcm->dev, "Failed to set manual reference to write frequency"); + else + channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; + + return err; +} + +static int configure_manual_reference_write_phase(struct idtcm_channel *channel) +{ + struct idtcm *idtcm = channel->idtcm; + int err; + + err = idtcm_set_manual_reference(channel, MANU_REF_WRITE_PHASE); + + if (err) + dev_err(idtcm->dev, "Failed to set manual reference to write phase"); + else + channel->mode = PTP_PLL_MODE_WRITE_PHASE; + + return err; +} + +static int idtcm_stop_phase_pull_in(struct idtcm_channel *channel) +{ + int err; + + err = _idtcm_adjfine(channel, channel->current_freq_scaled_ppm); + if (err) + return err; + + channel->phase_pull_in = false; + + return 0; +} + +static long idtcm_work_handler(struct ptp_clock_info *ptp) +{ + struct idtcm_channel *channel = container_of(ptp, struct idtcm_channel, caps); + struct idtcm *idtcm = channel->idtcm; + + mutex_lock(idtcm->lock); + + (void)idtcm_stop_phase_pull_in(channel); + + mutex_unlock(idtcm->lock); + + /* Return a negative value here to not reschedule */ + return -1; +} + +static s32 phase_pull_in_scaled_ppm(s32 current_ppm, s32 phase_pull_in_ppb) +{ + /* ppb = scaled_ppm * 125 / 2^13 */ + /* scaled_ppm = ppb * 2^13 / 125 */ + + s64 max_scaled_ppm = div_s64((s64)PHASE_PULL_IN_MAX_PPB << 13, 125); + s64 scaled_ppm = div_s64((s64)phase_pull_in_ppb << 13, 125); + + current_ppm += scaled_ppm; + + if (current_ppm > max_scaled_ppm) + current_ppm = max_scaled_ppm; + else if (current_ppm < -max_scaled_ppm) + current_ppm = -max_scaled_ppm; + + return current_ppm; +} + +static int do_phase_pull_in_sw(struct idtcm_channel *channel, + s32 delta_ns, + u32 max_ffo_ppb) +{ + s32 current_ppm = channel->current_freq_scaled_ppm; + u32 duration_ms = MSEC_PER_SEC; + s32 delta_ppm; + s32 ppb; + int err; + + /* If the ToD correction is less than PHASE_PULL_IN_MIN_THRESHOLD_NS, + * skip. The error introduced by the ToD adjustment procedure would + * be bigger than the required ToD correction + */ + if (abs(delta_ns) < PHASE_PULL_IN_MIN_THRESHOLD_NS) + return 0; + + if (max_ffo_ppb == 0) + max_ffo_ppb = PHASE_PULL_IN_MAX_PPB; + + /* For most cases, keep phase pull-in duration 1 second */ + ppb = delta_ns; + while (abs(ppb) > max_ffo_ppb) { + duration_ms *= 2; + ppb /= 2; + } + + delta_ppm = phase_pull_in_scaled_ppm(current_ppm, ppb); + + err = _idtcm_adjfine(channel, delta_ppm); + + if (err) + return err; + + /* schedule the worker to cancel phase pull-in */ + ptp_schedule_worker(channel->ptp_clock, + msecs_to_jiffies(duration_ms) - 1); + + channel->phase_pull_in = true; + + return 0; +} + +static int initialize_operating_mode_with_manual_reference(struct idtcm_channel *channel, + enum manual_reference ref) +{ + struct idtcm *idtcm = channel->idtcm; + + channel->mode = PTP_PLL_MODE_UNSUPPORTED; + channel->configure_write_frequency = configure_manual_reference_write_frequency; + channel->configure_write_phase = configure_manual_reference_write_phase; + channel->do_phase_pull_in = do_phase_pull_in_sw; + + switch (ref) { + case MANU_REF_WRITE_PHASE: + channel->mode = PTP_PLL_MODE_WRITE_PHASE; + break; + case MANU_REF_WRITE_FREQUENCY: + channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; + break; + default: + dev_warn(idtcm->dev, + "Unsupported MANUAL_REFERENCE: 0x%02x", ref); + } + + return 0; +} + +static int initialize_operating_mode_with_pll_mode(struct idtcm_channel *channel, + enum pll_mode mode) +{ + struct idtcm *idtcm = channel->idtcm; + int err = 0; + + channel->mode = PTP_PLL_MODE_UNSUPPORTED; + channel->configure_write_frequency = configure_dpll_mode_write_frequency; + channel->configure_write_phase = configure_dpll_mode_write_phase; + channel->do_phase_pull_in = do_phase_pull_in_fw; + + switch (mode) { + case PLL_MODE_WRITE_PHASE: + channel->mode = PTP_PLL_MODE_WRITE_PHASE; + break; + case PLL_MODE_WRITE_FREQUENCY: + channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; + break; + default: + dev_err(idtcm->dev, + "Unsupported PLL_MODE: 0x%02x", mode); + err = -EINVAL; + } + + return err; +} + +static int initialize_dco_operating_mode(struct idtcm_channel *channel) +{ + enum manual_reference ref = MANU_REF_XO_DPLL; + enum pll_mode mode = PLL_MODE_DISABLED; + struct idtcm *idtcm = channel->idtcm; + int err; + + channel->mode = PTP_PLL_MODE_UNSUPPORTED; + + err = idtcm_get_pll_mode(channel, &mode); + if (err) { + dev_err(idtcm->dev, "Unable to read pll mode!"); + return err; + } + + if (mode == PLL_MODE_PLL) { + err = idtcm_get_manual_reference(channel, &ref); + if (err) { + dev_err(idtcm->dev, "Unable to read manual reference!"); + return err; + } + err = initialize_operating_mode_with_manual_reference(channel, ref); + } else { + err = initialize_operating_mode_with_pll_mode(channel, mode); + } + + if (channel->mode == PTP_PLL_MODE_WRITE_PHASE) + channel->configure_write_frequency(channel); + + return err; +} + /* PTP Hardware Clock interface */ -/* +/** * Maximum absolute value for write phase offset in picoseconds * + * @channel: channel + * @delta_ns: delta in nanoseconds + * * Destination signed register is 32-bit register in resolution of 50ps * * 0x7fffffff * 50 = 2147483647 * 50 = 107374182350 @@ -1420,8 +1718,8 @@ static int _idtcm_adjphase(struct idtcm_channel *channel, s32 delta_ns) s32 phase_50ps; s64 offset_ps; - if (channel->pll_mode != PLL_MODE_WRITE_PHASE) { - err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_PHASE); + if (channel->mode != PTP_PLL_MODE_WRITE_PHASE) { + err = channel->configure_write_phase(channel); if (err) return err; } @@ -1459,8 +1757,8 @@ static int _idtcm_adjfine(struct idtcm_channel *channel, long scaled_ppm) u8 buf[6] = {0}; s64 fcw; - if (channel->pll_mode != PLL_MODE_WRITE_FREQUENCY) { - err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_FREQUENCY); + if (channel->mode != PTP_PLL_MODE_WRITE_FREQUENCY) { + err = channel->configure_write_frequency(channel); if (err) return err; } @@ -1501,15 +1799,14 @@ static int idtcm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); + err = _idtcm_gettime_immediate(channel, ts); + mutex_unlock(idtcm->lock); - err = _idtcm_gettime(channel, ts); if (err) - dev_err(&idtcm->client->dev, "Failed at line %d in %s!", + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1520,15 +1817,14 @@ static int idtcm_settime_deprecated(struct ptp_clock_info *ptp, struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_settime_deprecated(channel, ts); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1539,15 +1835,14 @@ static int idtcm_settime(struct ptp_clock_info *ptp, struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_settime(channel, ts, SCSR_TOD_WR_TYPE_SEL_ABSOLUTE); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1557,15 +1852,14 @@ static int idtcm_adjtime_deprecated(struct ptp_clock_info *ptp, s64 delta) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_adjtime_deprecated(channel, delta); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1577,31 +1871,30 @@ static int idtcm_adjtime(struct ptp_clock_info *ptp, s64 delta) enum scsr_tod_write_type_sel type; int err; - if (abs(delta) < PHASE_PULL_IN_THRESHOLD_NS) { - err = idtcm_do_phase_pull_in(channel, delta, 0); - if (err) - dev_err(&idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); - return err; - } + if (channel->phase_pull_in == true) + return 0; - if (delta >= 0) { - ts = ns_to_timespec64(delta); - type = SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS; + mutex_lock(idtcm->lock); + + if (abs(delta) < PHASE_PULL_IN_THRESHOLD_NS) { + err = channel->do_phase_pull_in(channel, delta, 0); } else { - ts = ns_to_timespec64(-delta); - type = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS; + if (delta >= 0) { + ts = ns_to_timespec64(delta); + type = SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS; + } else { + ts = ns_to_timespec64(-delta); + type = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS; + } + err = _idtcm_settime(channel, &ts, type); } - mutex_lock(&idtcm->reg_lock); + mutex_unlock(idtcm->lock); - err = _idtcm_settime(channel, &ts, type); if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1611,15 +1904,14 @@ static int idtcm_adjphase(struct ptp_clock_info *ptp, s32 delta) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_adjphase(channel, delta); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1629,14 +1921,21 @@ static int idtcm_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); + if (channel->phase_pull_in == true) + return 0; + if (scaled_ppm == channel->current_freq_scaled_ppm) + return 0; + + mutex_lock(idtcm->lock); err = _idtcm_adjfine(channel, scaled_ppm); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - - mutex_unlock(&idtcm->reg_lock); + else + channel->current_freq_scaled_ppm = scaled_ppm; return err; } @@ -1644,249 +1943,36 @@ static int idtcm_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) static int idtcm_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { - int err; struct idtcm_channel *channel = container_of(ptp, struct idtcm_channel, caps); + struct idtcm *idtcm = channel->idtcm; + int err = -EOPNOTSUPP; + + mutex_lock(idtcm->lock); switch (rq->type) { case PTP_CLK_REQ_PEROUT: - if (!on) { - err = idtcm_perout_enable(channel, false, &rq->perout); - if (err) - dev_err(&channel->idtcm->client->dev, - "Failed at line %d in %s!", - __LINE__, __func__); - return err; - } - + if (!on) + err = idtcm_perout_enable(channel, &rq->perout, false); /* Only accept a 1-PPS aligned to the second. */ - if (rq->perout.start.nsec || rq->perout.period.sec != 1 || - rq->perout.period.nsec) - return -ERANGE; - - err = idtcm_perout_enable(channel, true, &rq->perout); - if (err) - dev_err(&channel->idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); - return err; - default: - break; - } - - return -EOPNOTSUPP; -} - -static int _enable_pll_tod_sync(struct idtcm *idtcm, - u8 pll, - u8 sync_src, - u8 qn, - u8 qn_plus_1) -{ - int err; - u8 val; - u16 dpll; - u16 out0 = 0, out1 = 0; - - if (qn == 0 && qn_plus_1 == 0) - return 0; - - switch (pll) { - case 0: - dpll = DPLL_0; - if (qn) - out0 = OUTPUT_0; - if (qn_plus_1) - out1 = OUTPUT_1; + else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || + rq->perout.period.nsec) + err = -ERANGE; + else + err = idtcm_perout_enable(channel, &rq->perout, true); break; - case 1: - dpll = DPLL_1; - if (qn) - out0 = OUTPUT_2; - if (qn_plus_1) - out1 = OUTPUT_3; - break; - case 2: - dpll = DPLL_2; - if (qn) - out0 = OUTPUT_4; - if (qn_plus_1) - out1 = OUTPUT_5; - break; - case 3: - dpll = DPLL_3; - if (qn) - out0 = OUTPUT_6; - if (qn_plus_1) - out1 = OUTPUT_7; - break; - case 4: - dpll = DPLL_4; - if (qn) - out0 = OUTPUT_8; - break; - case 5: - dpll = DPLL_5; - if (qn) - out0 = OUTPUT_9; - if (qn_plus_1) - out1 = OUTPUT_8; - break; - case 6: - dpll = DPLL_6; - if (qn) - out0 = OUTPUT_10; - if (qn_plus_1) - out1 = OUTPUT_11; - break; - case 7: - dpll = DPLL_7; - if (qn) - out0 = OUTPUT_11; + case PTP_CLK_REQ_EXTTS: + err = idtcm_enable_extts(channel, rq->extts.index, + rq->extts.rsv[0], on); break; default: - return -EINVAL; - } - - /* - * Enable OUTPUT OUT_SYNC. - */ - if (out0) { - err = idtcm_read(idtcm, out0, OUT_CTRL_1, &val, sizeof(val)); - if (err) - return err; - - val &= ~OUT_SYNC_DISABLE; - - err = idtcm_write(idtcm, out0, OUT_CTRL_1, &val, sizeof(val)); - if (err) - return err; - } - - if (out1) { - err = idtcm_read(idtcm, out1, OUT_CTRL_1, &val, sizeof(val)); - if (err) - return err; - - val &= ~OUT_SYNC_DISABLE; - - err = idtcm_write(idtcm, out1, OUT_CTRL_1, &val, sizeof(val)); - if (err) - return err; - } - - /* enable dpll sync tod pps, must be set before dpll_mode */ - err = idtcm_read(idtcm, dpll, DPLL_TOD_SYNC_CFG, &val, sizeof(val)); - if (err) - return err; - - val &= ~(TOD_SYNC_SOURCE_MASK << TOD_SYNC_SOURCE_SHIFT); - val |= (sync_src << TOD_SYNC_SOURCE_SHIFT); - val |= TOD_SYNC_EN; - - return idtcm_write(idtcm, dpll, DPLL_TOD_SYNC_CFG, &val, sizeof(val)); -} - -static int idtcm_enable_tod_sync(struct idtcm_channel *channel) -{ - struct idtcm *idtcm = channel->idtcm; - u8 pll; - u8 sync_src; - u8 qn; - u8 qn_plus_1; - u8 cfg; - int err = 0; - u16 output_mask = channel->output_mask; - u8 out8_mux = 0; - u8 out11_mux = 0; - u8 temp; - - /* - * set tod_out_sync_enable to 0. - */ - err = idtcm_read(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); - if (err) - return err; - - cfg &= ~TOD_OUT_SYNC_ENABLE; - - err = idtcm_write(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); - if (err) - return err; - - switch (channel->tod_n) { - case TOD_0: - sync_src = 0; - break; - case TOD_1: - sync_src = 1; - break; - case TOD_2: - sync_src = 2; - break; - case TOD_3: - sync_src = 3; break; - default: - return -EINVAL; } - err = idtcm_read(idtcm, 0, HW_Q8_CTRL_SPARE, &temp, sizeof(temp)); - if (err) - return err; - - if ((temp & Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == - Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) - out8_mux = 1; + mutex_unlock(idtcm->lock); - err = idtcm_read(idtcm, 0, HW_Q11_CTRL_SPARE, &temp, sizeof(temp)); if (err) - return err; - - if ((temp & Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) == - Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK) - out11_mux = 1; - - for (pll = 0; pll < 8; pll++) { - qn = 0; - qn_plus_1 = 0; - - if (pll < 4) { - /* First 4 pll has 2 outputs */ - qn = output_mask & 0x1; - output_mask = output_mask >> 1; - qn_plus_1 = output_mask & 0x1; - output_mask = output_mask >> 1; - } else if (pll == 4) { - if (out8_mux == 0) { - qn = output_mask & 0x1; - output_mask = output_mask >> 1; - } - } else if (pll == 5) { - if (out8_mux) { - qn_plus_1 = output_mask & 0x1; - output_mask = output_mask >> 1; - } - qn = output_mask & 0x1; - output_mask = output_mask >> 1; - } else if (pll == 6) { - qn = output_mask & 0x1; - output_mask = output_mask >> 1; - if (out11_mux) { - qn_plus_1 = output_mask & 0x1; - output_mask = output_mask >> 1; - } - } else if (pll == 7) { - if (out11_mux == 0) { - qn = output_mask & 0x1; - output_mask = output_mask >> 1; - } - } - - if (qn != 0 || qn_plus_1 != 0) - err = _enable_pll_tod_sync(idtcm, pll, sync_src, qn, - qn_plus_1); - if (err) - return err; - } + dev_err(channel->idtcm->dev, + "Failed in %s with err %d!", __func__, err); return err; } @@ -1895,23 +1981,31 @@ static int idtcm_enable_tod(struct idtcm_channel *channel) { struct idtcm *idtcm = channel->idtcm; struct timespec64 ts = {0, 0}; + u16 tod_cfg = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_CFG); u8 cfg; int err; + /* STEELAI-366 - Temporary workaround for ts2phc compatibility */ + if (0) { + err = idtcm_output_mask_enable(channel, false); + if (err) + return err; + } + /* * Start the TOD clock ticking. */ - err = idtcm_read(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); + err = idtcm_read(idtcm, channel->tod_n, tod_cfg, &cfg, sizeof(cfg)); if (err) return err; cfg |= TOD_ENABLE; - err = idtcm_write(idtcm, channel->tod_n, TOD_CFG, &cfg, sizeof(cfg)); + err = idtcm_write(idtcm, channel->tod_n, tod_cfg, &cfg, sizeof(cfg)); if (err) return err; - if (idtcm->deprecated) + if (idtcm->fw_ver < V487) return _idtcm_settime_deprecated(channel, &ts); else return _idtcm_settime(channel, &ts, @@ -1939,12 +2033,9 @@ static void idtcm_set_version_info(struct idtcm *idtcm) snprintf(idtcm->version, sizeof(idtcm->version), "%u.%u.%u", major, minor, hotfix); - if (idtcm_strverscmp(idtcm->version, "4.8.7") >= 0) - idtcm->deprecated = 0; - else - idtcm->deprecated = 1; + idtcm->fw_ver = idtcm_fw_version(idtcm->version); - dev_info(&idtcm->client->dev, + dev_info(idtcm->dev, "%d.%d.%d, Id: 0x%04x HW Rev: %d OTP Config Select: %d", major, minor, hotfix, product_id, hw_rev_id, config_select); @@ -1954,28 +2045,33 @@ static const struct ptp_clock_info idtcm_caps = { .owner = THIS_MODULE, .max_adj = 244000, .n_per_out = 12, + .n_ext_ts = MAX_TOD, .adjphase = &idtcm_adjphase, .adjfine = &idtcm_adjfine, .adjtime = &idtcm_adjtime, .gettime64 = &idtcm_gettime, .settime64 = &idtcm_settime, .enable = &idtcm_enable, + .do_aux_work = &idtcm_work_handler, }; static const struct ptp_clock_info idtcm_caps_deprecated = { .owner = THIS_MODULE, .max_adj = 244000, .n_per_out = 12, + .n_ext_ts = MAX_TOD, .adjphase = &idtcm_adjphase, .adjfine = &idtcm_adjfine, .adjtime = &idtcm_adjtime_deprecated, .gettime64 = &idtcm_gettime, .settime64 = &idtcm_settime_deprecated, .enable = &idtcm_enable, + .do_aux_work = &idtcm_work_handler, }; static int configure_channel_pll(struct idtcm_channel *channel) { + struct idtcm *idtcm = channel->idtcm; int err = 0; switch (channel->pll) { @@ -1997,7 +2093,7 @@ static int configure_channel_pll(struct idtcm_channel *channel) break; case 2: channel->dpll_freq = DPLL_FREQ_2; - channel->dpll_n = DPLL_2; + channel->dpll_n = IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_2); channel->hw_dpll_n = HW_DPLL_2; channel->dpll_phase = DPLL_PHASE_2; channel->dpll_ctrl_n = DPLL_CTRL_2; @@ -2013,7 +2109,7 @@ static int configure_channel_pll(struct idtcm_channel *channel) break; case 4: channel->dpll_freq = DPLL_FREQ_4; - channel->dpll_n = DPLL_4; + channel->dpll_n = IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_4); channel->hw_dpll_n = HW_DPLL_4; channel->dpll_phase = DPLL_PHASE_4; channel->dpll_ctrl_n = DPLL_CTRL_4; @@ -2029,7 +2125,7 @@ static int configure_channel_pll(struct idtcm_channel *channel) break; case 6: channel->dpll_freq = DPLL_FREQ_6; - channel->dpll_n = DPLL_6; + channel->dpll_n = IDTCM_FW_REG(idtcm->fw_ver, V520, DPLL_6); channel->hw_dpll_n = HW_DPLL_6; channel->dpll_phase = DPLL_PHASE_6; channel->dpll_ctrl_n = DPLL_CTRL_6; @@ -2050,50 +2146,104 @@ static int configure_channel_pll(struct idtcm_channel *channel) return err; } -static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +/* + * Compensate for the PTP DCO input-to-output delay. + * This delay is 18 FOD cycles. + */ +static u32 idtcm_get_dco_delay(struct idtcm_channel *channel) { - struct idtcm_channel *channel; + struct idtcm *idtcm = channel->idtcm; + u8 mbuf[8] = {0}; + u8 nbuf[2] = {0}; + u32 fodFreq; int err; + u64 m; + u16 n; - if (!(index < MAX_TOD)) - return -EINVAL; - - channel = &idtcm->channel[index]; + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_FOD_FREQ, mbuf, 6); + if (err) + return 0; - /* Set pll addresses */ - err = configure_channel_pll(channel); + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_FOD_FREQ + 6, nbuf, 2); if (err) - return err; + return 0; + + m = get_unaligned_le64(mbuf); + n = get_unaligned_le16(nbuf); + + if (n == 0) + n = 1; + + fodFreq = (u32)div_u64(m, n); + if (fodFreq >= 500000000) + return 18 * (u32)div_u64(NSEC_PER_SEC, fodFreq); + + return 0; +} + +static int configure_channel_tod(struct idtcm_channel *channel, u32 index) +{ + enum fw_version fw_ver = channel->idtcm->fw_ver; /* Set tod addresses */ switch (index) { case 0: - channel->tod_read_primary = TOD_READ_PRIMARY_0; - channel->tod_write = TOD_WRITE_0; - channel->tod_n = TOD_0; + channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_0); + channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_0); + channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_0); + channel->sync_src = SYNC_SOURCE_DPLL0_TOD_PPS; break; case 1: - channel->tod_read_primary = TOD_READ_PRIMARY_1; - channel->tod_write = TOD_WRITE_1; - channel->tod_n = TOD_1; + channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_1); + channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_1); + channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_1); + channel->sync_src = SYNC_SOURCE_DPLL1_TOD_PPS; break; case 2: - channel->tod_read_primary = TOD_READ_PRIMARY_2; - channel->tod_write = TOD_WRITE_2; - channel->tod_n = TOD_2; + channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_2); + channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_2); + channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_2); + channel->sync_src = SYNC_SOURCE_DPLL2_TOD_PPS; break; case 3: - channel->tod_read_primary = TOD_READ_PRIMARY_3; - channel->tod_write = TOD_WRITE_3; - channel->tod_n = TOD_3; + channel->tod_read_primary = IDTCM_FW_REG(fw_ver, V520, TOD_READ_PRIMARY_3); + channel->tod_write = IDTCM_FW_REG(fw_ver, V520, TOD_WRITE_3); + channel->tod_n = IDTCM_FW_REG(fw_ver, V520, TOD_3); + channel->sync_src = SYNC_SOURCE_DPLL3_TOD_PPS; break; default: return -EINVAL; } + return 0; +} + +static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +{ + struct idtcm_channel *channel; + int err; + + if (!(index < MAX_TOD)) + return -EINVAL; + + channel = &idtcm->channel[index]; + channel->idtcm = idtcm; + channel->current_freq_scaled_ppm = 0; + + /* Set pll addresses */ + err = configure_channel_pll(channel); + if (err) + return err; - if (idtcm->deprecated) + /* Set tod addresses */ + err = configure_channel_tod(channel, index); + if (err) + return err; + + if (idtcm->fw_ver < V487) channel->caps = idtcm_caps_deprecated; else channel->caps = idtcm_caps; @@ -2101,30 +2251,19 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) snprintf(channel->caps.name, sizeof(channel->caps.name), "IDT CM TOD%u", index); - if (!idtcm->deprecated) { - err = idtcm_enable_tod_sync(channel); - if (err) { - dev_err(&idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); - return err; - } - } - - /* Sync pll mode with hardware */ - err = idtcm_get_pll_mode(channel, &channel->pll_mode); - if (err) { - dev_err(&idtcm->client->dev, - "Error: %s - Unable to read pll mode", __func__); + err = initialize_dco_operating_mode(channel); + if (err) return err; - } err = idtcm_enable_tod(channel); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); return err; } + channel->dco_delay = idtcm_get_dco_delay(channel); + channel->ptp_clock = ptp_clock_register(&channel->caps, NULL); if (IS_ERR(channel->ptp_clock)) { @@ -2136,12 +2275,59 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) if (!channel->ptp_clock) return -ENOTSUPP; - dev_info(&idtcm->client->dev, "PLL%d registered as ptp%d", + dev_info(idtcm->dev, "PLL%d registered as ptp%d", index, channel->ptp_clock->index); return 0; } +static int idtcm_enable_extts_channel(struct idtcm *idtcm, u32 index) +{ + struct idtcm_channel *channel; + int err; + + if (!(index < MAX_TOD)) + return -EINVAL; + + channel = &idtcm->channel[index]; + channel->idtcm = idtcm; + + /* Set tod addresses */ + err = configure_channel_tod(channel, index); + if (err) + return err; + + channel->idtcm = idtcm; + + return 0; +} + +static void idtcm_extts_check(struct work_struct *work) +{ + struct idtcm *idtcm = container_of(work, struct idtcm, extts_work.work); + int err, i; + + if (idtcm->extts_mask == 0) + return; + + mutex_lock(idtcm->lock); + for (i = 0; i < MAX_TOD; i++) { + u8 mask = 1 << i; + + if (idtcm->extts_mask & mask) { + err = idtcm_extts_check_channel(idtcm, i); + /* trigger clears itself, so clear the mask */ + if (err == 0) + idtcm->extts_mask &= ~mask; + } + } + + if (idtcm->extts_mask) + schedule_delayed_work(&idtcm->extts_work, + msecs_to_jiffies(EXTTS_PERIOD_MS)); + mutex_unlock(idtcm->lock); +} + static void ptp_clock_unregister_all(struct idtcm *idtcm) { u8 i; @@ -2149,7 +2335,6 @@ static void ptp_clock_unregister_all(struct idtcm *idtcm) for (i = 0; i < MAX_TOD; i++) { channel = &idtcm->channel[i]; - if (channel->ptp_clock) ptp_clock_unregister(channel->ptp_clock); } @@ -2158,6 +2343,7 @@ static void ptp_clock_unregister_all(struct idtcm *idtcm) static void set_default_masks(struct idtcm *idtcm) { idtcm->tod_mask = DEFAULT_TOD_MASK; + idtcm->extts_mask = 0; idtcm->channel[0].pll = DEFAULT_TOD0_PTP_PLL; idtcm->channel[1].pll = DEFAULT_TOD1_PTP_PLL; @@ -2170,158 +2356,86 @@ static void set_default_masks(struct idtcm *idtcm) idtcm->channel[3].output_mask = DEFAULT_OUTPUT_MASK_PLL3; } -static int idtcm_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int idtcm_probe(struct platform_device *pdev) { + struct rsmu_ddata *ddata = dev_get_drvdata(pdev->dev.parent); struct idtcm *idtcm; int err; u8 i; - /* Unused for now */ - (void)id; - - idtcm = devm_kzalloc(&client->dev, sizeof(struct idtcm), GFP_KERNEL); + idtcm = devm_kzalloc(&pdev->dev, sizeof(struct idtcm), GFP_KERNEL); if (!idtcm) return -ENOMEM; - idtcm->client = client; - idtcm->page_offset = 0xff; + idtcm->dev = &pdev->dev; + idtcm->mfd = pdev->dev.parent; + idtcm->lock = &ddata->lock; + idtcm->regmap = ddata->regmap; idtcm->calculate_overhead_flag = 0; + INIT_DELAYED_WORK(&idtcm->extts_work, idtcm_extts_check); + set_default_masks(idtcm); - mutex_init(&idtcm->reg_lock); - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); idtcm_set_version_info(idtcm); - err = idtcm_load_firmware(idtcm, &client->dev); + err = idtcm_load_firmware(idtcm, &pdev->dev); + if (err) - dev_warn(&idtcm->client->dev, "loading firmware failed with %d", err); + dev_warn(idtcm->dev, "loading firmware failed with %d", err); wait_for_chip_ready(idtcm); if (idtcm->tod_mask) { for (i = 0; i < MAX_TOD; i++) { - if (idtcm->tod_mask & (1 << i)) { + if (idtcm->tod_mask & (1 << i)) err = idtcm_enable_channel(idtcm, i); - if (err) { - dev_err(&idtcm->client->dev, - "idtcm_enable_channel %d failed!", i); - break; - } + else + err = idtcm_enable_extts_channel(idtcm, i); + if (err) { + dev_err(idtcm->dev, + "idtcm_enable_channel %d failed!", i); + break; } } } else { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "no PLLs flagged as PHCs, nothing to do"); err = -ENODEV; } - mutex_unlock(&idtcm->reg_lock); + mutex_unlock(idtcm->lock); if (err) { ptp_clock_unregister_all(idtcm); return err; } - i2c_set_clientdata(client, idtcm); + platform_set_drvdata(pdev, idtcm); return 0; } -static int idtcm_remove(struct i2c_client *client) +static int idtcm_remove(struct platform_device *pdev) { - struct idtcm *idtcm = i2c_get_clientdata(client); + struct idtcm *idtcm = platform_get_drvdata(pdev); ptp_clock_unregister_all(idtcm); - mutex_destroy(&idtcm->reg_lock); + cancel_delayed_work_sync(&idtcm->extts_work); return 0; } -#ifdef CONFIG_OF -static const struct of_device_id idtcm_dt_id[] = { - { .compatible = "idt,8a34000" }, - { .compatible = "idt,8a34001" }, - { .compatible = "idt,8a34002" }, - { .compatible = "idt,8a34003" }, - { .compatible = "idt,8a34004" }, - { .compatible = "idt,8a34005" }, - { .compatible = "idt,8a34006" }, - { .compatible = "idt,8a34007" }, - { .compatible = "idt,8a34008" }, - { .compatible = "idt,8a34009" }, - { .compatible = "idt,8a34010" }, - { .compatible = "idt,8a34011" }, - { .compatible = "idt,8a34012" }, - { .compatible = "idt,8a34013" }, - { .compatible = "idt,8a34014" }, - { .compatible = "idt,8a34015" }, - { .compatible = "idt,8a34016" }, - { .compatible = "idt,8a34017" }, - { .compatible = "idt,8a34018" }, - { .compatible = "idt,8a34019" }, - { .compatible = "idt,8a34040" }, - { .compatible = "idt,8a34041" }, - { .compatible = "idt,8a34042" }, - { .compatible = "idt,8a34043" }, - { .compatible = "idt,8a34044" }, - { .compatible = "idt,8a34045" }, - { .compatible = "idt,8a34046" }, - { .compatible = "idt,8a34047" }, - { .compatible = "idt,8a34048" }, - { .compatible = "idt,8a34049" }, - {}, -}; -MODULE_DEVICE_TABLE(of, idtcm_dt_id); -#endif - -static const struct i2c_device_id idtcm_i2c_id[] = { - { "8a34000" }, - { "8a34001" }, - { "8a34002" }, - { "8a34003" }, - { "8a34004" }, - { "8a34005" }, - { "8a34006" }, - { "8a34007" }, - { "8a34008" }, - { "8a34009" }, - { "8a34010" }, - { "8a34011" }, - { "8a34012" }, - { "8a34013" }, - { "8a34014" }, - { "8a34015" }, - { "8a34016" }, - { "8a34017" }, - { "8a34018" }, - { "8a34019" }, - { "8a34040" }, - { "8a34041" }, - { "8a34042" }, - { "8a34043" }, - { "8a34044" }, - { "8a34045" }, - { "8a34046" }, - { "8a34047" }, - { "8a34048" }, - { "8a34049" }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, idtcm_i2c_id); - -static struct i2c_driver idtcm_driver = { +static struct platform_driver idtcm_driver = { .driver = { - .of_match_table = of_match_ptr(idtcm_dt_id), - .name = "idtcm", + .name = "8a3400x-phc", }, - .probe = idtcm_probe, - .remove = idtcm_remove, - .id_table = idtcm_i2c_id, + .probe = idtcm_probe, + .remove = idtcm_remove, }; -module_i2c_driver(idtcm_driver); +module_platform_driver(idtcm_driver); diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index fb323271063e26..0f3059ae1fffa7 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -9,8 +9,8 @@ #define PTP_IDTCLOCKMATRIX_H #include <linux/ktime.h> - -#include "idt8a340_reg.h" +#include <linux/mfd/idt8a340_reg.h> +#include <linux/regmap.h> #define FW_FILENAME "idtcm.bin" #define MAX_TOD (4) @@ -44,7 +44,6 @@ #define DEFAULT_TOD2_PTP_PLL (2) #define DEFAULT_TOD3_PTP_PLL (3) -#define POST_SM_RESET_DELAY_MS (3000) #define PHASE_PULL_IN_THRESHOLD_NS_DEPRECATED (150000) #define PHASE_PULL_IN_THRESHOLD_NS (15000) #define TOD_WRITE_OVERHEAD_COUNT_MAX (2) @@ -57,66 +56,26 @@ #define IDTCM_MAX_WRITE_COUNT (512) -#define FULL_FW_CFG_BYTES (SCRATCH - GPIO_USER_CONTROL) -#define FULL_FW_CFG_SKIPPED_BYTES (((SCRATCH >> 7) \ - - (GPIO_USER_CONTROL >> 7)) \ - * 4) /* 4 bytes skipped every 0x80 */ - -/* Values of DPLL_N.DPLL_MODE.PLL_MODE */ -enum pll_mode { - PLL_MODE_MIN = 0, - PLL_MODE_NORMAL = PLL_MODE_MIN, - PLL_MODE_WRITE_PHASE = 1, - PLL_MODE_WRITE_FREQUENCY = 2, - PLL_MODE_GPIO_INC_DEC = 3, - PLL_MODE_SYNTHESIS = 4, - PLL_MODE_PHASE_MEASUREMENT = 5, - PLL_MODE_DISABLED = 6, - PLL_MODE_MAX = PLL_MODE_DISABLED, -}; - -enum hw_tod_write_trig_sel { - HW_TOD_WR_TRIG_SEL_MIN = 0, - HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, - HW_TOD_WR_TRIG_SEL_RESERVED = 1, - HW_TOD_WR_TRIG_SEL_TOD_PPS = 2, - HW_TOD_WR_TRIG_SEL_IRIGB_PPS = 3, - HW_TOD_WR_TRIG_SEL_PWM_PPS = 4, - HW_TOD_WR_TRIG_SEL_GPIO = 5, - HW_TOD_WR_TRIG_SEL_FOD_SYNC = 6, - WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_FOD_SYNC, -}; - -/* 4.8.7 only */ -enum scsr_tod_write_trig_sel { - SCSR_TOD_WR_TRIG_SEL_DISABLE = 0, - SCSR_TOD_WR_TRIG_SEL_IMMEDIATE = 1, - SCSR_TOD_WR_TRIG_SEL_REFCLK = 2, - SCSR_TOD_WR_TRIG_SEL_PWMPPS = 3, - SCSR_TOD_WR_TRIG_SEL_TODPPS = 4, - SCSR_TOD_WR_TRIG_SEL_SYNCFOD = 5, - SCSR_TOD_WR_TRIG_SEL_GPIO = 6, - SCSR_TOD_WR_TRIG_SEL_MAX = SCSR_TOD_WR_TRIG_SEL_GPIO, -}; +#define PHASE_PULL_IN_MAX_PPB (144000) +#define PHASE_PULL_IN_MIN_THRESHOLD_NS (2) -/* 4.8.7 only */ -enum scsr_tod_write_type_sel { - SCSR_TOD_WR_TYPE_SEL_ABSOLUTE = 0, - SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS = 1, - SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS = 2, - SCSR_TOD_WR_TYPE_SEL_MAX = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS, +/* + * Return register address based on passed in firmware version + */ +#define IDTCM_FW_REG(FW, VER, REG) (((FW) < (VER)) ? (REG) : (REG##_##VER)) +enum fw_version { + V_DEFAULT = 0, + V487 = 1, + V520 = 2, }; -/* Values STATUS.DPLL_SYS_STATUS.DPLL_SYS_STATE */ -enum dpll_state { - DPLL_STATE_MIN = 0, - DPLL_STATE_FREERUN = DPLL_STATE_MIN, - DPLL_STATE_LOCKACQ = 1, - DPLL_STATE_LOCKREC = 2, - DPLL_STATE_LOCKED = 3, - DPLL_STATE_HOLDOVER = 4, - DPLL_STATE_OPEN_LOOP = 5, - DPLL_STATE_MAX = DPLL_STATE_OPEN_LOOP, +/* PTP PLL Mode */ +enum ptp_pll_mode { + PTP_PLL_MODE_MIN = 0, + PTP_PLL_MODE_WRITE_FREQUENCY = PTP_PLL_MODE_MIN, + PTP_PLL_MODE_WRITE_PHASE, + PTP_PLL_MODE_UNSUPPORTED, + PTP_PLL_MODE_MAX = PTP_PLL_MODE_UNSUPPORTED, }; struct idtcm; @@ -134,26 +93,40 @@ struct idtcm_channel { u16 tod_write; u16 tod_n; u16 hw_dpll_n; - enum pll_mode pll_mode; + u8 sync_src; + enum ptp_pll_mode mode; + int (*configure_write_frequency)(struct idtcm_channel *channel); + int (*configure_write_phase)(struct idtcm_channel *channel); + int (*do_phase_pull_in)(struct idtcm_channel *channel, + s32 offset_ns, u32 max_ffo_ppb); + s32 current_freq_scaled_ppm; + bool phase_pull_in; + u32 dco_delay; + /* last input trigger for extts */ + u8 refn; u8 pll; u16 output_mask; }; struct idtcm { struct idtcm_channel channel[MAX_TOD]; - struct i2c_client *client; - u8 page_offset; + struct device *dev; u8 tod_mask; char version[16]; - u8 deprecated; - + enum fw_version fw_ver; + /* Polls for external time stamps */ + u8 extts_mask; + struct delayed_work extts_work; + /* Remember the ptp channel to report extts */ + struct idtcm_channel *event_channel[MAX_TOD]; + /* Mutex to protect operations from being interrupted */ + struct mutex *lock; + struct device *mfd; + struct regmap *regmap; /* Overhead calculation for adjtime */ u8 calculate_overhead_flag; s64 tod_write_overhead_ns; ktime_t start_time; - - /* Protects I2C read/modify/write registers from concurrent access */ - struct mutex reg_lock; }; struct idtcm_fwrc { diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index caf9b37c5eb1e0..34f943c8c9fd84 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4,6 +4,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/debugfs.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/serial_8250.h> @@ -72,7 +73,7 @@ struct tod_reg { u32 status; u32 uart_polarity; u32 version; - u32 correction_sec; + u32 adj_sec; u32 __pad0[3]; u32 uart_baud; u32 __pad1[3]; @@ -124,6 +125,55 @@ struct img_reg { u32 version; }; +struct gpio_reg { + u32 gpio1; + u32 __pad0; + u32 gpio2; + u32 __pad1; +}; + +struct irig_master_reg { + u32 ctrl; + u32 status; + u32 __pad0; + u32 version; + u32 adj_sec; + u32 mode_ctrl; +}; + +#define IRIG_M_CTRL_ENABLE BIT(0) + +struct irig_slave_reg { + u32 ctrl; + u32 status; + u32 __pad0; + u32 version; + u32 adj_sec; + u32 mode_ctrl; +}; + +#define IRIG_S_CTRL_ENABLE BIT(0) + +struct dcf_master_reg { + u32 ctrl; + u32 status; + u32 __pad0; + u32 version; + u32 adj_sec; +}; + +#define DCF_M_CTRL_ENABLE BIT(0) + +struct dcf_slave_reg { + u32 ctrl; + u32 status; + u32 __pad0; + u32 version; + u32 adj_sec; +}; + +#define DCF_S_CTRL_ENABLE BIT(0) + struct ptp_ocp_flash_info { const char *name; int pci_offset; @@ -131,11 +181,17 @@ struct ptp_ocp_flash_info { void *data; }; -struct ptp_ocp_ext_info { +struct ptp_ocp_i2c_info { const char *name; + unsigned long fixed_rate; + size_t data_size; + void *data; +}; + +struct ptp_ocp_ext_info { int index; irqreturn_t (*irq_fcn)(int irq, void *priv); - int (*enable)(void *priv, bool enable); + int (*enable)(void *priv, u32 req, bool enable); }; struct ptp_ocp_ext_src { @@ -153,9 +209,17 @@ struct ptp_ocp { struct tod_reg __iomem *tod; struct pps_reg __iomem *pps_to_ext; struct pps_reg __iomem *pps_to_clk; + struct gpio_reg __iomem *pps_select; + struct gpio_reg __iomem *sma; + struct irig_master_reg __iomem *irig_out; + struct irig_slave_reg __iomem *irig_in; + struct dcf_master_reg __iomem *dcf_out; + struct dcf_slave_reg __iomem *dcf_in; + struct tod_reg __iomem *nmea_out; struct ptp_ocp_ext_src *pps; struct ptp_ocp_ext_src *ts0; struct ptp_ocp_ext_src *ts1; + struct ptp_ocp_ext_src *ts2; struct img_reg __iomem *image; struct ptp_clock *ptp; struct ptp_clock_info ptp_info; @@ -163,16 +227,25 @@ struct ptp_ocp { struct platform_device *spi_flash; struct clk_hw *i2c_clk; struct timer_list watchdog; + struct dentry *debug_root; time64_t gnss_lost; int id; int n_irqs; int gnss_port; + int gnss2_port; int mac_port; /* miniature atomic clock */ + int nmea_port; u8 serial[6]; - int flash_start; bool has_serial; + u32 pps_req_map; + int flash_start; + u32 utc_tai_offset; + u32 ts_window_adjust; }; +#define OCP_REQ_TIMESTAMP BIT(0) +#define OCP_REQ_PPS BIT(1) + struct ocp_resource { unsigned long offset; int size; @@ -180,6 +253,7 @@ struct ocp_resource { int (*setup)(struct ptp_ocp *bp, struct ocp_resource *r); void *extra; unsigned long bp_offset; + const char * const name; }; static int ptp_ocp_register_mem(struct ptp_ocp *bp, struct ocp_resource *r); @@ -189,7 +263,7 @@ static int ptp_ocp_register_serial(struct ptp_ocp *bp, struct ocp_resource *r); static int ptp_ocp_register_ext(struct ptp_ocp *bp, struct ocp_resource *r); static int ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r); static irqreturn_t ptp_ocp_ts_irq(int irq, void *priv); -static int ptp_ocp_ts_enable(void *priv, bool enable); +static int ptp_ocp_ts_enable(void *priv, u32 req, bool enable); #define bp_assign_entry(bp, res, val) ({ \ uintptr_t addr = (uintptr_t)(bp) + (res)->bp_offset; \ @@ -197,7 +271,7 @@ static int ptp_ocp_ts_enable(void *priv, bool enable); }) #define OCP_RES_LOCATION(member) \ - .bp_offset = offsetof(struct ptp_ocp, member) + .name = #member, .bp_offset = offsetof(struct ptp_ocp, member) #define OCP_MEM_RESOURCE(member) \ OCP_RES_LOCATION(member), .setup = ptp_ocp_register_mem @@ -215,16 +289,17 @@ static int ptp_ocp_ts_enable(void *priv, bool enable); OCP_RES_LOCATION(member), .setup = ptp_ocp_register_ext /* This is the MSI vector mapping used. - * 0: N/C + * 0: TS3 (and PPS) * 1: TS0 * 2: TS1 - * 3: GPS - * 4: GPS2 (n/c) + * 3: GNSS + * 4: GNSS2 * 5: MAC - * 6: SPI IMU (inertial measurement unit) - * 7: I2C oscillator - * 8: HWICAP + * 6: TS2 + * 7: I2C controller + * 8: HWICAP (notused) * 9: SPI Flash + * 10: NMEA */ static struct ocp_resource ocp_fb_resource[] = { @@ -236,7 +311,7 @@ static struct ocp_resource ocp_fb_resource[] = { OCP_EXT_RESOURCE(ts0), .offset = 0x01010000, .size = 0x10000, .irq_vec = 1, .extra = &(struct ptp_ocp_ext_info) { - .name = "ts0", .index = 0, + .index = 0, .irq_fcn = ptp_ocp_ts_irq, .enable = ptp_ocp_ts_enable, }, @@ -245,7 +320,25 @@ static struct ocp_resource ocp_fb_resource[] = { OCP_EXT_RESOURCE(ts1), .offset = 0x01020000, .size = 0x10000, .irq_vec = 2, .extra = &(struct ptp_ocp_ext_info) { - .name = "ts1", .index = 1, + .index = 1, + .irq_fcn = ptp_ocp_ts_irq, + .enable = ptp_ocp_ts_enable, + }, + }, + { + OCP_EXT_RESOURCE(ts2), + .offset = 0x01060000, .size = 0x10000, .irq_vec = 6, + .extra = &(struct ptp_ocp_ext_info) { + .index = 2, + .irq_fcn = ptp_ocp_ts_irq, + .enable = ptp_ocp_ts_enable, + }, + }, + { + OCP_EXT_RESOURCE(pps), + .offset = 0x010C0000, .size = 0x10000, .irq_vec = 0, + .extra = &(struct ptp_ocp_ext_info) { + .index = 3, .irq_fcn = ptp_ocp_ts_irq, .enable = ptp_ocp_ts_enable, }, @@ -263,22 +356,62 @@ static struct ocp_resource ocp_fb_resource[] = { .offset = 0x01050000, .size = 0x10000, }, { + OCP_MEM_RESOURCE(irig_in), + .offset = 0x01070000, .size = 0x10000, + }, + { + OCP_MEM_RESOURCE(irig_out), + .offset = 0x01080000, .size = 0x10000, + }, + { + OCP_MEM_RESOURCE(dcf_in), + .offset = 0x01090000, .size = 0x10000, + }, + { + OCP_MEM_RESOURCE(dcf_out), + .offset = 0x010A0000, .size = 0x10000, + }, + { + OCP_MEM_RESOURCE(nmea_out), + .offset = 0x010B0000, .size = 0x10000, + }, + { OCP_MEM_RESOURCE(image), .offset = 0x00020000, .size = 0x1000, }, { + OCP_MEM_RESOURCE(pps_select), + .offset = 0x00130000, .size = 0x1000, + }, + { + OCP_MEM_RESOURCE(sma), + .offset = 0x00140000, .size = 0x1000, + }, + { OCP_I2C_RESOURCE(i2c_ctrl), .offset = 0x00150000, .size = 0x10000, .irq_vec = 7, + .extra = &(struct ptp_ocp_i2c_info) { + .name = "xiic-i2c", + .fixed_rate = 50000000, + }, }, { OCP_SERIAL_RESOURCE(gnss_port), .offset = 0x00160000 + 0x1000, .irq_vec = 3, }, { + OCP_SERIAL_RESOURCE(gnss2_port), + .offset = 0x00170000 + 0x1000, .irq_vec = 4, + }, + { OCP_SERIAL_RESOURCE(mac_port), .offset = 0x00180000 + 0x1000, .irq_vec = 5, }, { + OCP_SERIAL_RESOURCE(nmea_port), + .offset = 0x00190000 + 0x1000, .irq_vec = 10, + }, + { OCP_SPI_RESOURCE(spi_flash), .offset = 0x00310000, .size = 0x10000, .irq_vec = 9, .extra = &(struct ptp_ocp_flash_info) { @@ -309,10 +442,12 @@ MODULE_DEVICE_TABLE(pci, ptp_ocp_pcidev_id); static DEFINE_MUTEX(ptp_ocp_lock); static DEFINE_IDR(ptp_ocp_idr); -static struct { +struct ocp_selector { const char *name; int value; -} ptp_ocp_clock[] = { +}; + +static struct ocp_selector ptp_ocp_clock[] = { { .name = "NONE", .value = 0 }, { .name = "TOD", .value = 1 }, { .name = "IRIG", .value = 2 }, @@ -322,33 +457,71 @@ static struct { { .name = "DCF", .value = 6 }, { .name = "REGS", .value = 0xfe }, { .name = "EXT", .value = 0xff }, + { } +}; + +static struct ocp_selector ptp_ocp_sma_in[] = { + { .name = "10Mhz", .value = 0x00 }, + { .name = "PPS1", .value = 0x01 }, + { .name = "PPS2", .value = 0x02 }, + { .name = "TS1", .value = 0x04 }, + { .name = "TS2", .value = 0x08 }, + { .name = "IRIG", .value = 0x10 }, + { .name = "DCF", .value = 0x20 }, + { } +}; + +static struct ocp_selector ptp_ocp_sma_out[] = { + { .name = "10Mhz", .value = 0x00 }, + { .name = "PHC", .value = 0x01 }, + { .name = "MAC", .value = 0x02 }, + { .name = "GNSS", .value = 0x04 }, + { .name = "GNSS2", .value = 0x08 }, + { .name = "IRIG", .value = 0x10 }, + { .name = "DCF", .value = 0x20 }, + { } }; static const char * -ptp_ocp_clock_name_from_val(int val) +ptp_ocp_select_name_from_val(struct ocp_selector *tbl, int val) { int i; - for (i = 0; i < ARRAY_SIZE(ptp_ocp_clock); i++) - if (ptp_ocp_clock[i].value == val) - return ptp_ocp_clock[i].name; + for (i = 0; tbl[i].name; i++) + if (tbl[i].value == val) + return tbl[i].name; return NULL; } static int -ptp_ocp_clock_val_from_name(const char *name) +ptp_ocp_select_val_from_name(struct ocp_selector *tbl, const char *name) { - const char *clk; + const char *select; int i; - for (i = 0; i < ARRAY_SIZE(ptp_ocp_clock); i++) { - clk = ptp_ocp_clock[i].name; - if (!strncasecmp(name, clk, strlen(clk))) - return ptp_ocp_clock[i].value; + for (i = 0; tbl[i].name; i++) { + select = tbl[i].name; + if (!strncasecmp(name, select, strlen(select))) + return tbl[i].value; } return -EINVAL; } +static ssize_t +ptp_ocp_select_table_show(struct ocp_selector *tbl, char *buf) +{ + ssize_t count; + int i; + + count = 0; + for (i = 0; tbl[i].name; i++) + count += sysfs_emit_at(buf, count, "%s ", tbl[i].name); + if (count) + count--; + count += sysfs_emit_at(buf, count, "\n"); + return count; +} + static int __ptp_ocp_gettime_locked(struct ptp_ocp *bp, struct timespec64 *ts, struct ptp_system_timestamp *sts) @@ -356,10 +529,9 @@ __ptp_ocp_gettime_locked(struct ptp_ocp *bp, struct timespec64 *ts, u32 ctrl, time_sec, time_ns; int i; - ctrl = ioread32(&bp->reg->ctrl); - ctrl |= OCP_CTRL_READ_TIME_REQ; - ptp_read_system_prets(sts); + + ctrl = OCP_CTRL_READ_TIME_REQ | OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); for (i = 0; i < 100; i++) { @@ -369,6 +541,12 @@ __ptp_ocp_gettime_locked(struct ptp_ocp *bp, struct timespec64 *ts, } ptp_read_system_postts(sts); + if (sts && bp->ts_window_adjust) { + s64 ns = timespec64_to_ns(&sts->post_ts); + + sts->post_ts = ns_to_timespec64(ns - bp->ts_window_adjust); + } + time_ns = ioread32(&bp->reg->time_ns); time_sec = ioread32(&bp->reg->time_sec); @@ -408,8 +586,7 @@ __ptp_ocp_settime_locked(struct ptp_ocp *bp, const struct timespec64 *ts) iowrite32(time_ns, &bp->reg->adjust_ns); iowrite32(time_sec, &bp->reg->adjust_sec); - ctrl = ioread32(&bp->reg->ctrl); - ctrl |= OCP_CTRL_ADJUST_TIME; + ctrl = OCP_CTRL_ADJUST_TIME | OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); /* restore clock selection */ @@ -422,9 +599,6 @@ ptp_ocp_settime(struct ptp_clock_info *ptp_info, const struct timespec64 *ts) struct ptp_ocp *bp = container_of(ptp_info, struct ptp_ocp, ptp_info); unsigned long flags; - if (ioread32(&bp->reg->status) & OCP_STATUS_IN_SYNC) - return 0; - spin_lock_irqsave(&bp->lock, flags); __ptp_ocp_settime_locked(bp, ts); spin_unlock_irqrestore(&bp->lock, flags); @@ -432,26 +606,39 @@ ptp_ocp_settime(struct ptp_clock_info *ptp_info, const struct timespec64 *ts) return 0; } +static void +__ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u64 adj_val) +{ + u32 select, ctrl; + + select = ioread32(&bp->reg->select); + iowrite32(OCP_SELECT_CLK_REG, &bp->reg->select); + + iowrite32(adj_val, &bp->reg->offset_ns); + iowrite32(adj_val & 0x7f, &bp->reg->offset_window_ns); + + ctrl = OCP_CTRL_ADJUST_OFFSET | OCP_CTRL_ENABLE; + iowrite32(ctrl, &bp->reg->ctrl); + + /* restore clock selection */ + iowrite32(select >> 16, &bp->reg->select); +} + static int ptp_ocp_adjtime(struct ptp_clock_info *ptp_info, s64 delta_ns) { struct ptp_ocp *bp = container_of(ptp_info, struct ptp_ocp, ptp_info); - struct timespec64 ts; unsigned long flags; - int err; + u32 adj_ns, sign; - if (ioread32(&bp->reg->status) & OCP_STATUS_IN_SYNC) - return 0; + sign = delta_ns < 0 ? BIT(31) : 0; + adj_ns = sign ? -delta_ns : delta_ns; spin_lock_irqsave(&bp->lock, flags); - err = __ptp_ocp_gettime_locked(bp, &ts, NULL); - if (likely(!err)) { - timespec64_add_ns(&ts, delta_ns); - __ptp_ocp_settime_locked(bp, &ts); - } + __ptp_ocp_adjtime_locked(bp, sign | adj_ns); spin_unlock_irqrestore(&bp->lock, flags); - return err; + return 0; } static int @@ -464,7 +651,7 @@ ptp_ocp_null_adjfine(struct ptp_clock_info *ptp_info, long scaled_ppm) } static int -ptp_ocp_adjphase(struct ptp_clock_info *ptp_info, s32 phase_ns) +ptp_ocp_null_adjphase(struct ptp_clock_info *ptp_info, s32 phase_ns) { return -EOPNOTSUPP; } @@ -475,10 +662,12 @@ ptp_ocp_enable(struct ptp_clock_info *ptp_info, struct ptp_clock_request *rq, { struct ptp_ocp *bp = container_of(ptp_info, struct ptp_ocp, ptp_info); struct ptp_ocp_ext_src *ext = NULL; + u32 req; int err; switch (rq->type) { case PTP_CLK_REQ_EXTTS: + req = OCP_REQ_TIMESTAMP; switch (rq->extts.index) { case 0: ext = bp->ts0; @@ -486,18 +675,33 @@ ptp_ocp_enable(struct ptp_clock_info *ptp_info, struct ptp_clock_request *rq, case 1: ext = bp->ts1; break; + case 2: + ext = bp->ts2; + break; + case 3: + ext = bp->pps; + break; } break; case PTP_CLK_REQ_PPS: + req = OCP_REQ_PPS; ext = bp->pps; break; + case PTP_CLK_REQ_PEROUT: + if (on && + (rq->perout.period.sec != 1 || rq->perout.period.nsec != 0)) + return -EINVAL; + /* This is a request for 1PPS on an output SMA. + * Allow, but assume manual configuration. + */ + return 0; default: return -EOPNOTSUPP; } err = -ENXIO; if (ext) - err = ext->info->enable(ext, on); + err = ext->info->enable(ext, req, on); return err; } @@ -510,10 +714,11 @@ static const struct ptp_clock_info ptp_ocp_clock_info = { .settime64 = ptp_ocp_settime, .adjtime = ptp_ocp_adjtime, .adjfine = ptp_ocp_null_adjfine, - .adjphase = ptp_ocp_adjphase, + .adjphase = ptp_ocp_null_adjphase, .enable = ptp_ocp_enable, .pps = true, - .n_ext_ts = 2, + .n_ext_ts = 4, + .n_per_out = 1, }; static void @@ -526,8 +731,7 @@ __ptp_ocp_clear_drift_locked(struct ptp_ocp *bp) iowrite32(0, &bp->reg->drift_ns); - ctrl = ioread32(&bp->reg->ctrl); - ctrl |= OCP_CTRL_ADJUST_DRIFT; + ctrl = OCP_CTRL_ADJUST_DRIFT | OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); /* restore clock selection */ @@ -559,6 +763,28 @@ ptp_ocp_watchdog(struct timer_list *t) mod_timer(&bp->watchdog, jiffies + HZ); } +static void +ptp_ocp_estimate_pci_timing(struct ptp_ocp *bp) +{ + ktime_t start, end; + ktime_t delay; + u32 ctrl; + + ctrl = ioread32(&bp->reg->ctrl); + ctrl = OCP_CTRL_READ_TIME_REQ | OCP_CTRL_ENABLE; + + iowrite32(ctrl, &bp->reg->ctrl); + + start = ktime_get_ns(); + + ctrl = ioread32(&bp->reg->ctrl); + + end = ktime_get_ns(); + + delay = end - start; + bp->ts_window_adjust = (delay >> 5) * 3; +} + static int ptp_ocp_init_clock(struct ptp_ocp *bp) { @@ -566,9 +792,7 @@ ptp_ocp_init_clock(struct ptp_ocp *bp) bool sync; u32 ctrl; - /* make sure clock is enabled */ - ctrl = ioread32(&bp->reg->ctrl); - ctrl |= OCP_CTRL_ENABLE; + ctrl = OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); /* NO DRIFT Correction */ @@ -587,23 +811,58 @@ ptp_ocp_init_clock(struct ptp_ocp *bp) return -ENODEV; } + ptp_ocp_estimate_pci_timing(bp); + sync = ioread32(&bp->reg->status) & OCP_STATUS_IN_SYNC; if (!sync) { - ktime_get_real_ts64(&ts); + ktime_get_clocktai_ts64(&ts); ptp_ocp_settime(&bp->ptp_info, &ts); } - if (!ptp_ocp_gettimex(&bp->ptp_info, &ts, NULL)) - dev_info(&bp->pdev->dev, "Time: %lld.%ld, %s\n", - ts.tv_sec, ts.tv_nsec, - sync ? "in-sync" : "UNSYNCED"); - timer_setup(&bp->watchdog, ptp_ocp_watchdog, 0); - mod_timer(&bp->watchdog, jiffies + HZ); + /* If there is a clock supervisor, then enable the watchdog */ + if (bp->pps_to_clk) { + timer_setup(&bp->watchdog, ptp_ocp_watchdog, 0); + mod_timer(&bp->watchdog, jiffies + HZ); + } return 0; } static void +ptp_ocp_utc_distribute(struct ptp_ocp *bp, u32 val) +{ + unsigned long flags; + + spin_lock_irqsave(&bp->lock, flags); + + bp->utc_tai_offset = val; + + if (bp->irig_out) + iowrite32(val, &bp->irig_out->adj_sec); + if (bp->dcf_out) + iowrite32(val, &bp->dcf_out->adj_sec); + if (bp->nmea_out) + iowrite32(val, &bp->nmea_out->adj_sec); + + spin_unlock_irqrestore(&bp->lock, flags); +} + +static void +ptp_ocp_tod_init(struct ptp_ocp *bp) +{ + u32 ctrl, reg; + + ctrl = ioread32(&bp->tod->ctrl); + ctrl |= TOD_CTRL_PROTOCOL | TOD_CTRL_ENABLE; + ctrl &= ~(TOD_CTRL_DISABLE_FMT_A | TOD_CTRL_DISABLE_FMT_B); + iowrite32(ctrl, &bp->tod->ctrl); + + reg = ioread32(&bp->tod->utc_status); + if (reg & TOD_STATUS_UTC_VALID) + ptp_ocp_utc_distribute(bp, reg & TOD_STATUS_UTC_MASK); +} + +static void ptp_ocp_tod_info(struct ptp_ocp *bp) { static const char * const proto_name[] = { @@ -621,11 +880,6 @@ ptp_ocp_tod_info(struct ptp_ocp *bp) version >> 24, (version >> 16) & 0xff, version & 0xffff); ctrl = ioread32(&bp->tod->ctrl); - ctrl |= TOD_CTRL_PROTOCOL | TOD_CTRL_ENABLE; - ctrl &= ~(TOD_CTRL_DISABLE_FMT_A | TOD_CTRL_DISABLE_FMT_B); - iowrite32(ctrl, &bp->tod->ctrl); - - ctrl = ioread32(&bp->tod->ctrl); idx = ctrl & TOD_CTRL_PROTOCOL ? 4 : 0; idx += (ctrl >> 16) & 3; dev_info(&bp->pdev->dev, "control: %x\n", ctrl); @@ -639,7 +893,7 @@ ptp_ocp_tod_info(struct ptp_ocp *bp) reg = ioread32(&bp->tod->status); dev_info(&bp->pdev->dev, "status: %x\n", reg); - reg = ioread32(&bp->tod->correction_sec); + reg = ioread32(&bp->tod->adj_sec); dev_info(&bp->pdev->dev, "correction: %d\n", reg); reg = ioread32(&bp->tod->utc_status); @@ -695,6 +949,9 @@ ptp_ocp_get_serial_number(struct ptp_ocp *bp) struct device *dev; int err; + if (!bp->i2c_ctrl) + return; + dev = device_find_child(&bp->i2c_ctrl->dev, NULL, ptp_ocp_firstchild); if (!dev) { dev_err(&bp->pdev->dev, "Can't find I2C adapter\n"); @@ -720,21 +977,6 @@ out: put_device(dev); } -static void -ptp_ocp_info(struct ptp_ocp *bp) -{ - u32 version, select; - - version = ioread32(&bp->reg->version); - select = ioread32(&bp->reg->select); - dev_info(&bp->pdev->dev, "Version %d.%d.%d, clock %s, device ptp%d\n", - version >> 24, (version >> 16) & 0xff, version & 0xffff, - ptp_ocp_clock_name_from_val(select >> 16), - ptp_clock_index(bp->ptp)); - - ptp_ocp_tod_info(bp); -} - static struct device * ptp_ocp_find_flash(struct ptp_ocp *bp) { @@ -910,18 +1152,6 @@ ptp_ocp_register_spi(struct ptp_ocp *bp, struct ocp_resource *r) unsigned long start; int id; - /* XXX hack to work around old FPGA */ - if (bp->n_irqs < 10) { - dev_err(&bp->pdev->dev, "FPGA does not have SPI devices\n"); - return 0; - } - - if (r->irq_vec > bp->n_irqs) { - dev_err(&bp->pdev->dev, "spi device irq %d out of range\n", - r->irq_vec); - return 0; - } - start = pci_resource_start(pdev, 0) + r->offset; ptp_ocp_set_mem_resource(&res[0], start, r->size); ptp_ocp_set_irq_resource(&res[1], pci_irq_vector(pdev, r->irq_vec)); @@ -944,41 +1174,41 @@ ptp_ocp_register_spi(struct ptp_ocp *bp, struct ocp_resource *r) static struct platform_device * ptp_ocp_i2c_bus(struct pci_dev *pdev, struct ocp_resource *r, int id) { + struct ptp_ocp_i2c_info *info; struct resource res[2]; unsigned long start; + info = r->extra; start = pci_resource_start(pdev, 0) + r->offset; ptp_ocp_set_mem_resource(&res[0], start, r->size); ptp_ocp_set_irq_resource(&res[1], pci_irq_vector(pdev, r->irq_vec)); - return platform_device_register_resndata(&pdev->dev, "xiic-i2c", - id, res, 2, NULL, 0); + return platform_device_register_resndata(&pdev->dev, info->name, + id, res, 2, + info->data, info->data_size); } static int ptp_ocp_register_i2c(struct ptp_ocp *bp, struct ocp_resource *r) { struct pci_dev *pdev = bp->pdev; + struct ptp_ocp_i2c_info *info; struct platform_device *p; struct clk_hw *clk; char buf[32]; int id; - if (r->irq_vec > bp->n_irqs) { - dev_err(&bp->pdev->dev, "i2c device irq %d out of range\n", - r->irq_vec); - return 0; - } - + info = r->extra; id = pci_dev_id(bp->pdev); sprintf(buf, "AXI.%d", id); - clk = clk_hw_register_fixed_rate(&pdev->dev, buf, NULL, 0, 50000000); + clk = clk_hw_register_fixed_rate(&pdev->dev, buf, NULL, 0, + info->fixed_rate); if (IS_ERR(clk)) return PTR_ERR(clk); bp->i2c_clk = clk; - sprintf(buf, "xiic-i2c.%d", id); + sprintf(buf, "%s.%d", info->name, id); devm_clk_hw_register_clkdev(&pdev->dev, clk, NULL, buf); p = ptp_ocp_i2c_bus(bp->pdev, r, id); if (IS_ERR(p)) @@ -997,26 +1227,51 @@ ptp_ocp_ts_irq(int irq, void *priv) struct ptp_clock_event ev; u32 sec, nsec; + if (ext == ext->bp->pps) { + if (ext->bp->pps_req_map & OCP_REQ_PPS) { + ev.type = PTP_CLOCK_PPS; + ptp_clock_event(ext->bp->ptp, &ev); + } + + if ((ext->bp->pps_req_map & ~OCP_REQ_PPS) == 0) + goto out; + } + /* XXX should fix API - this converts s/ns -> ts -> s/ns */ sec = ioread32(®->time_sec); nsec = ioread32(®->time_ns); ev.type = PTP_CLOCK_EXTTS; ev.index = ext->info->index; - ev.timestamp = sec * 1000000000ULL + nsec; + ev.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(ext->bp->ptp, &ev); +out: iowrite32(1, ®->intr); /* write 1 to ack */ return IRQ_HANDLED; } static int -ptp_ocp_ts_enable(void *priv, bool enable) +ptp_ocp_ts_enable(void *priv, u32 req, bool enable) { struct ptp_ocp_ext_src *ext = priv; struct ts_reg __iomem *reg = ext->mem; + struct ptp_ocp *bp = ext->bp; + + if (ext == bp->pps) { + u32 old_map = bp->pps_req_map; + + if (enable) + bp->pps_req_map |= req; + else + bp->pps_req_map &= ~req; + + /* if no state change, just return */ + if ((!!old_map ^ !!bp->pps_req_map) == 0) + return 0; + } if (enable) { iowrite32(1, ®->enable); @@ -1033,7 +1288,7 @@ ptp_ocp_ts_enable(void *priv, bool enable) static void ptp_ocp_unregister_ext(struct ptp_ocp_ext_src *ext) { - ext->info->enable(ext, false); + ext->info->enable(ext, ~0, false); pci_free_irq(ext->bp->pdev, ext->irq_vec, ext); kfree(ext); } @@ -1059,7 +1314,7 @@ ptp_ocp_register_ext(struct ptp_ocp *bp, struct ocp_resource *r) ext->irq_vec = r->irq_vec; err = pci_request_irq(pdev, r->irq_vec, ext->info->irq_fcn, NULL, - ext, "ocp%d.%s", bp->id, ext->info->name); + ext, "ocp%d.%s", bp->id, r->name); if (err) { dev_err(&pdev->dev, "Could not get irq %d\n", r->irq_vec); goto out; @@ -1101,12 +1356,6 @@ ptp_ocp_register_serial(struct ptp_ocp *bp, struct ocp_resource *r) { int port; - if (r->irq_vec > bp->n_irqs) { - dev_err(&bp->pdev->dev, "serial device irq %d out of range\n", - r->irq_vec); - return 0; - } - port = ptp_ocp_serial_line(bp, r); if (port < 0) return port; @@ -1130,15 +1379,40 @@ ptp_ocp_register_mem(struct ptp_ocp *bp, struct ocp_resource *r) return 0; } +static void +ptp_ocp_nmea_out_init(struct ptp_ocp *bp) +{ + if (!bp->nmea_out) + return; + + iowrite32(0, &bp->nmea_out->ctrl); /* disable */ + iowrite32(7, &bp->nmea_out->uart_baud); /* 115200 */ + iowrite32(1, &bp->nmea_out->ctrl); /* enable */ +} + /* FB specific board initializers; last "resource" registered. */ static int ptp_ocp_fb_board_init(struct ptp_ocp *bp, struct ocp_resource *r) { bp->flash_start = 1024 * 4096; + ptp_ocp_tod_init(bp); + ptp_ocp_nmea_out_init(bp); + return ptp_ocp_init_clock(bp); } +static bool +ptp_ocp_allow_irq(struct ptp_ocp *bp, struct ocp_resource *r) +{ + bool allow = !r->irq_vec || r->irq_vec < bp->n_irqs; + + if (!allow) + dev_err(&bp->pdev->dev, "irq %d out of range, skipping %s\n", + r->irq_vec, r->name); + return allow; +} + static int ptp_ocp_register_resources(struct ptp_ocp *bp, kernel_ulong_t driver_data) { @@ -1147,13 +1421,373 @@ ptp_ocp_register_resources(struct ptp_ocp *bp, kernel_ulong_t driver_data) table = (struct ocp_resource *)driver_data; for (r = table; r->setup; r++) { + if (!ptp_ocp_allow_irq(bp, r)) + continue; err = r->setup(bp, r); - if (err) + if (err) { + dev_err(&bp->pdev->dev, + "Could not register %s: err %d\n", + r->name, err); break; + } } return err; } +static void +ptp_ocp_enable_fpga(u32 __iomem *reg, u32 bit, bool enable) +{ + u32 ctrl; + bool on; + + ctrl = ioread32(reg); + on = ctrl & bit; + if (on ^ enable) { + ctrl &= ~bit; + ctrl |= enable ? bit : 0; + iowrite32(ctrl, reg); + } +} + +static void +ptp_ocp_irig_out(struct ptp_ocp *bp, bool enable) +{ + return ptp_ocp_enable_fpga(&bp->irig_out->ctrl, + IRIG_M_CTRL_ENABLE, enable); +} + +static void +ptp_ocp_irig_in(struct ptp_ocp *bp, bool enable) +{ + return ptp_ocp_enable_fpga(&bp->irig_in->ctrl, + IRIG_S_CTRL_ENABLE, enable); +} + +static void +ptp_ocp_dcf_out(struct ptp_ocp *bp, bool enable) +{ + return ptp_ocp_enable_fpga(&bp->dcf_out->ctrl, + DCF_M_CTRL_ENABLE, enable); +} + +static void +ptp_ocp_dcf_in(struct ptp_ocp *bp, bool enable) +{ + return ptp_ocp_enable_fpga(&bp->dcf_in->ctrl, + DCF_S_CTRL_ENABLE, enable); +} + +static void +__handle_signal_outputs(struct ptp_ocp *bp, u32 val) +{ + ptp_ocp_irig_out(bp, val & 0x00100010); + ptp_ocp_dcf_out(bp, val & 0x00200020); +} + +static void +__handle_signal_inputs(struct ptp_ocp *bp, u32 val) +{ + ptp_ocp_irig_in(bp, val & 0x00100010); + ptp_ocp_dcf_in(bp, val & 0x00200020); +} + +/* + * ANT0 == gps (in) + * ANT1 == sma1 (in) + * ANT2 == sma2 (in) + * ANT3 == sma3 (out) + * ANT4 == sma4 (out) + */ + +enum ptp_ocp_sma_mode { + SMA_MODE_IN, + SMA_MODE_OUT, +}; + +static struct ptp_ocp_sma_connector { + enum ptp_ocp_sma_mode mode; + bool fixed_mode; + u16 default_out_idx; +} ptp_ocp_sma_map[4] = { + { + .mode = SMA_MODE_IN, + .fixed_mode = true, + }, + { + .mode = SMA_MODE_IN, + .fixed_mode = true, + }, + { + .mode = SMA_MODE_OUT, + .fixed_mode = true, + .default_out_idx = 0, /* 10Mhz */ + }, + { + .mode = SMA_MODE_OUT, + .fixed_mode = true, + .default_out_idx = 1, /* PHC */ + }, +}; + +static ssize_t +ptp_ocp_show_output(u32 val, char *buf, int default_idx) +{ + const char *name; + ssize_t count; + + count = sysfs_emit(buf, "OUT: "); + name = ptp_ocp_select_name_from_val(ptp_ocp_sma_out, val); + if (!name) + name = ptp_ocp_sma_out[default_idx].name; + count += sysfs_emit_at(buf, count, "%s\n", name); + return count; +} + +static ssize_t +ptp_ocp_show_inputs(u32 val, char *buf, const char *zero_in) +{ + const char *name; + ssize_t count; + int i; + + count = sysfs_emit(buf, "IN: "); + for (i = 0; i < ARRAY_SIZE(ptp_ocp_sma_in); i++) { + if (val & ptp_ocp_sma_in[i].value) { + name = ptp_ocp_sma_in[i].name; + count += sysfs_emit_at(buf, count, "%s ", name); + } + } + if (!val && zero_in) + count += sysfs_emit_at(buf, count, "%s ", zero_in); + if (count) + count--; + count += sysfs_emit_at(buf, count, "\n"); + return count; +} + +static int +sma_parse_inputs(const char *buf, enum ptp_ocp_sma_mode *mode) +{ + struct ocp_selector *tbl[] = { ptp_ocp_sma_in, ptp_ocp_sma_out }; + int idx, count, dir; + char **argv; + int ret; + + argv = argv_split(GFP_KERNEL, buf, &count); + if (!argv) + return -ENOMEM; + + ret = -EINVAL; + if (!count) + goto out; + + idx = 0; + dir = *mode == SMA_MODE_IN ? 0 : 1; + if (!strcasecmp("IN:", argv[idx])) { + dir = 0; + idx++; + } + if (!strcasecmp("OUT:", argv[0])) { + dir = 1; + idx++; + } + *mode = dir == 0 ? SMA_MODE_IN : SMA_MODE_OUT; + + ret = 0; + for (; idx < count; idx++) + ret |= ptp_ocp_select_val_from_name(tbl[dir], argv[idx]); + if (ret < 0) + ret = -EINVAL; + +out: + argv_free(argv); + return ret; +} + +static ssize_t +ptp_ocp_sma_show(struct ptp_ocp *bp, int sma_nr, u32 val, char *buf, + const char *zero_in) +{ + struct ptp_ocp_sma_connector *sma = &ptp_ocp_sma_map[sma_nr - 1]; + + if (sma->mode == SMA_MODE_IN) + return ptp_ocp_show_inputs(val, buf, zero_in); + + return ptp_ocp_show_output(val, buf, sma->default_out_idx); +} + +static ssize_t +sma1_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + + val = ioread32(&bp->sma->gpio1) & 0x3f; + return ptp_ocp_sma_show(bp, 1, val, buf, ptp_ocp_sma_in[0].name); +} + +static ssize_t +sma2_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + + val = (ioread32(&bp->sma->gpio1) >> 16) & 0x3f; + return ptp_ocp_sma_show(bp, 2, val, buf, NULL); +} + +static ssize_t +sma3_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + + val = ioread32(&bp->sma->gpio2) & 0x3f; + return ptp_ocp_sma_show(bp, 3, val, buf, NULL); +} + +static ssize_t +sma4_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + + val = (ioread32(&bp->sma->gpio2) >> 16) & 0x3f; + return ptp_ocp_sma_show(bp, 4, val, buf, NULL); +} + +static void +ptp_ocp_sma_store_output(struct ptp_ocp *bp, u32 val, u32 shift) +{ + unsigned long flags; + u32 gpio, mask; + + mask = 0xffff << (16 - shift); + + spin_lock_irqsave(&bp->lock, flags); + + gpio = ioread32(&bp->sma->gpio2); + gpio = (gpio & mask) | (val << shift); + + __handle_signal_outputs(bp, gpio); + + iowrite32(gpio, &bp->sma->gpio2); + + spin_unlock_irqrestore(&bp->lock, flags); +} + +static void +ptp_ocp_sma_store_inputs(struct ptp_ocp *bp, u32 val, u32 shift) +{ + unsigned long flags; + u32 gpio, mask; + + mask = 0xffff << (16 - shift); + + spin_lock_irqsave(&bp->lock, flags); + + gpio = ioread32(&bp->sma->gpio1); + gpio = (gpio & mask) | (val << shift); + + __handle_signal_inputs(bp, gpio); + + iowrite32(gpio, &bp->sma->gpio1); + + spin_unlock_irqrestore(&bp->lock, flags); +} + +static ssize_t +ptp_ocp_sma_store(struct ptp_ocp *bp, const char *buf, int sma_nr, u32 shift) +{ + struct ptp_ocp_sma_connector *sma = &ptp_ocp_sma_map[sma_nr - 1]; + enum ptp_ocp_sma_mode mode; + int val; + + mode = sma->mode; + val = sma_parse_inputs(buf, &mode); + if (val < 0) + return val; + + if (mode != sma->mode && sma->fixed_mode) + return -EOPNOTSUPP; + + if (mode != sma->mode) { + pr_err("Mode changes not supported yet.\n"); + return -EOPNOTSUPP; + } + + if (sma->mode == SMA_MODE_IN) + ptp_ocp_sma_store_inputs(bp, val, shift); + else + ptp_ocp_sma_store_output(bp, val, shift); + + return 0; +} + +static ssize_t +sma1_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + + err = ptp_ocp_sma_store(bp, buf, 1, 0); + return err ? err : count; +} + +static ssize_t +sma2_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + + err = ptp_ocp_sma_store(bp, buf, 2, 16); + return err ? err : count; +} + +static ssize_t +sma3_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + + err = ptp_ocp_sma_store(bp, buf, 3, 0); + return err ? err : count; +} + +static ssize_t +sma4_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + + err = ptp_ocp_sma_store(bp, buf, 4, 16); + return err ? err : count; +} +static DEVICE_ATTR_RW(sma1); +static DEVICE_ATTR_RW(sma2); +static DEVICE_ATTR_RW(sma3); +static DEVICE_ATTR_RW(sma4); + +static ssize_t +available_sma_inputs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return ptp_ocp_select_table_show(ptp_ocp_sma_in, buf); +} +static DEVICE_ATTR_RO(available_sma_inputs); + +static ssize_t +available_sma_outputs_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return ptp_ocp_select_table_show(ptp_ocp_sma_out, buf); +} +static DEVICE_ATTR_RO(available_sma_outputs); + static ssize_t serialnum_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1182,6 +1816,102 @@ gnss_sync_show(struct device *dev, struct device_attribute *attr, char *buf) static DEVICE_ATTR_RO(gnss_sync); static ssize_t +utc_tai_offset_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", bp->utc_tai_offset); +} + +static ssize_t +utc_tai_offset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + u32 val; + + err = kstrtou32(buf, 0, &val); + if (err) + return err; + + ptp_ocp_utc_distribute(bp, val); + + return count; +} +static DEVICE_ATTR_RW(utc_tai_offset); + +static ssize_t +ts_window_adjust_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + + return sysfs_emit(buf, "%d\n", bp->ts_window_adjust); +} + +static ssize_t +ts_window_adjust_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + int err; + u32 val; + + err = kstrtou32(buf, 0, &val); + if (err) + return err; + + bp->ts_window_adjust = val; + + return count; +} +static DEVICE_ATTR_RW(ts_window_adjust); + +static ssize_t +irig_b_mode_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + u32 val; + + val = ioread32(&bp->irig_out->ctrl); + val = (val >> 16) & 0x07; + return sysfs_emit(buf, "%d\n", val); +} + +static ssize_t +irig_b_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ptp_ocp *bp = dev_get_drvdata(dev); + unsigned long flags; + int err; + u32 reg; + u8 val; + + err = kstrtou8(buf, 0, &val); + if (err) + return err; + if (val > 7) + return -EINVAL; + + reg = ((val & 0x7) << 16); + + spin_lock_irqsave(&bp->lock, flags); + iowrite32(0, &bp->irig_out->ctrl); /* disable */ + iowrite32(reg, &bp->irig_out->ctrl); /* change mode */ + iowrite32(reg | IRIG_M_CTRL_ENABLE, &bp->irig_out->ctrl); + spin_unlock_irqrestore(&bp->lock, flags); + + return count; +} +static DEVICE_ATTR_RW(irig_b_mode); + +static ssize_t clock_source_show(struct device *dev, struct device_attribute *attr, char *buf) { struct ptp_ocp *bp = dev_get_drvdata(dev); @@ -1189,7 +1919,7 @@ clock_source_show(struct device *dev, struct device_attribute *attr, char *buf) u32 select; select = ioread32(&bp->reg->select); - p = ptp_ocp_clock_name_from_val(select >> 16); + p = ptp_ocp_select_name_from_val(ptp_ocp_clock, select >> 16); return sysfs_emit(buf, "%s\n", p); } @@ -1202,7 +1932,7 @@ clock_source_store(struct device *dev, struct device_attribute *attr, unsigned long flags; int val; - val = ptp_ocp_clock_val_from_name(buf); + val = ptp_ocp_select_val_from_name(ptp_ocp_clock, buf); if (val < 0) return val; @@ -1218,19 +1948,7 @@ static ssize_t available_clock_sources_show(struct device *dev, struct device_attribute *attr, char *buf) { - const char *clk; - ssize_t count; - int i; - - count = 0; - for (i = 0; i < ARRAY_SIZE(ptp_ocp_clock); i++) { - clk = ptp_ocp_clock[i].name; - count += sysfs_emit_at(buf, count, "%s ", clk); - } - if (count) - count--; - count += sysfs_emit_at(buf, count, "\n"); - return count; + return ptp_ocp_select_table_show(ptp_ocp_clock, buf); } static DEVICE_ATTR_RO(available_clock_sources); @@ -1239,10 +1957,258 @@ static struct attribute *timecard_attrs[] = { &dev_attr_gnss_sync.attr, &dev_attr_clock_source.attr, &dev_attr_available_clock_sources.attr, + &dev_attr_sma1.attr, + &dev_attr_sma2.attr, + &dev_attr_sma3.attr, + &dev_attr_sma4.attr, + &dev_attr_available_sma_inputs.attr, + &dev_attr_available_sma_outputs.attr, + &dev_attr_irig_b_mode.attr, + &dev_attr_utc_tai_offset.attr, + &dev_attr_ts_window_adjust.attr, NULL, }; ATTRIBUTE_GROUPS(timecard); +static const char * +gpio_map(u32 gpio, u32 bit, const char *pri, const char *sec, const char *def) +{ + const char *ans; + + if (gpio & (1 << bit)) + ans = pri; + else if (gpio & (1 << (bit + 16))) + ans = sec; + else + ans = def; + return ans; +} + +static void +gpio_multi_map(char *buf, u32 gpio, u32 bit, + const char *pri, const char *sec, const char *def) +{ + char *ans = buf; + + strcpy(ans, def); + if (gpio & (1 << bit)) + ans += sprintf(ans, "%s ", pri); + if (gpio & (1 << (bit + 16))) + ans += sprintf(ans, "%s ", sec); +} + +static int +ptp_ocp_summary_show(struct seq_file *s, void *data) +{ + struct device *dev = s->private; + struct ptp_system_timestamp sts; + u32 sma_in, sma_out, ctrl, val; + struct ts_reg __iomem *ts_reg; + struct timespec64 ts; + struct ptp_ocp *bp; + const char *src; + bool on, map; + char *buf; + + buf = (char *)__get_free_page(GFP_KERNEL); + if (!buf) + return -ENOMEM; + + bp = dev_get_drvdata(dev); + sma_in = ioread32(&bp->sma->gpio1); + sma_out = ioread32(&bp->sma->gpio2); + + seq_printf(s, "%7s: /dev/ptp%d\n", "PTP", ptp_clock_index(bp->ptp)); + + sma1_show(dev, NULL, buf); + seq_printf(s, " sma1: %s", buf); + + sma2_show(dev, NULL, buf); + seq_printf(s, " sma2: %s", buf); + + sma3_show(dev, NULL, buf); + seq_printf(s, " sma3: %s", buf); + + sma4_show(dev, NULL, buf); + seq_printf(s, " sma4: %s", buf); + + if (bp->ts0) { + ts_reg = bp->ts0->mem; + on = ioread32(&ts_reg->enable); + src = "GNSS"; + seq_printf(s, "%7s: %s, src: %s\n", "TS0", + on ? " ON" : "OFF", src); + } + + if (bp->ts1) { + ts_reg = bp->ts1->mem; + on = ioread32(&ts_reg->enable); + src = gpio_map(sma_in, 2, "sma1", "sma2", "----"); + seq_printf(s, "%7s: %s, src: %s\n", "TS1", + on ? " ON" : "OFF", src); + } + + if (bp->ts2) { + ts_reg = bp->ts2->mem; + on = ioread32(&ts_reg->enable); + src = gpio_map(sma_in, 3, "sma1", "sma2", "----"); + seq_printf(s, "%7s: %s, src: %s\n", "TS2", + on ? " ON" : "OFF", src); + } + + if (bp->pps) { + ts_reg = bp->pps->mem; + src = "PHC"; + on = ioread32(&ts_reg->enable); + map = !!(bp->pps_req_map & OCP_REQ_TIMESTAMP); + seq_printf(s, "%7s: %s, src: %s\n", "TS3", + on && map ? " ON" : "OFF", src); + + map = !!(bp->pps_req_map & OCP_REQ_PPS); + seq_printf(s, "%7s: %s, src: %s\n", "PPS", + on && map ? " ON" : "OFF", src); + } + + if (bp->irig_out) { + ctrl = ioread32(&bp->irig_out->ctrl); + on = ctrl & IRIG_M_CTRL_ENABLE; + val = ioread32(&bp->irig_out->status); + gpio_multi_map(buf, sma_out, 4, "sma3", "sma4", "----"); + seq_printf(s, "%7s: %s, error: %d, mode %d, out: %s\n", "IRIG", + on ? " ON" : "OFF", val, (ctrl >> 16), buf); + } + + if (bp->irig_in) { + on = ioread32(&bp->irig_in->ctrl) & IRIG_S_CTRL_ENABLE; + val = ioread32(&bp->irig_in->status); + src = gpio_map(sma_in, 4, "sma1", "sma2", "----"); + seq_printf(s, "%7s: %s, error: %d, src: %s\n", "IRIG in", + on ? " ON" : "OFF", val, src); + } + + if (bp->dcf_out) { + on = ioread32(&bp->dcf_out->ctrl) & DCF_M_CTRL_ENABLE; + val = ioread32(&bp->dcf_out->status); + gpio_multi_map(buf, sma_out, 5, "sma3", "sma4", "----"); + seq_printf(s, "%7s: %s, error: %d, out: %s\n", "DCF", + on ? " ON" : "OFF", val, buf); + } + + if (bp->dcf_in) { + on = ioread32(&bp->dcf_in->ctrl) & DCF_S_CTRL_ENABLE; + val = ioread32(&bp->dcf_in->status); + src = gpio_map(sma_in, 5, "sma1", "sma2", "----"); + seq_printf(s, "%7s: %s, error: %d, src: %s\n", "DCF in", + on ? " ON" : "OFF", val, src); + } + + if (bp->nmea_out) { + on = ioread32(&bp->nmea_out->ctrl) & 1; + val = ioread32(&bp->nmea_out->status); + seq_printf(s, "%7s: %s, error: %d\n", "NMEA", + on ? " ON" : "OFF", val); + } + + /* compute src for PPS1, used below. */ + if (bp->pps_select) { + val = ioread32(&bp->pps_select->gpio1); + if (val & 0x01) + src = gpio_map(sma_in, 0, "sma1", "sma2", "----"); + else if (val & 0x02) + src = "MAC"; + else if (val & 0x04) + src = "GNSS"; + else + src = "----"; + } else { + src = "?"; + } + + /* assumes automatic switchover/selection */ + val = ioread32(&bp->reg->select); + switch (val >> 16) { + case 0: + sprintf(buf, "----"); + break; + case 2: + sprintf(buf, "IRIG"); + break; + case 3: + sprintf(buf, "%s via PPS1", src); + break; + case 6: + sprintf(buf, "DCF"); + break; + default: + strcpy(buf, "unknown"); + break; + } + val = ioread32(&bp->reg->status); + seq_printf(s, "%7s: %s, state: %s\n", "PHC src", buf, + val & OCP_STATUS_IN_SYNC ? "sync" : "unsynced"); + + /* reuses PPS1 src from earlier */ + seq_printf(s, "MAC PPS1 src: %s\n", src); + + src = gpio_map(sma_in, 1, "sma1", "sma2", "GNSS2"); + seq_printf(s, "MAC PPS2 src: %s\n", src); + + if (!ptp_ocp_gettimex(&bp->ptp_info, &ts, &sts)) { + struct timespec64 sys_ts; + s64 pre_ns, post_ns, ns; + + pre_ns = timespec64_to_ns(&sts.pre_ts); + post_ns = timespec64_to_ns(&sts.post_ts); + ns = (pre_ns + post_ns) / 2; + ns += (s64)bp->utc_tai_offset * NSEC_PER_SEC; + sys_ts = ns_to_timespec64(ns); + + seq_printf(s, "%7s: %lld.%ld == %ptT TAI\n", "PHC", + ts.tv_sec, ts.tv_nsec, &ts); + seq_printf(s, "%7s: %lld.%ld == %ptT UTC offset %d\n", "SYS", + sys_ts.tv_sec, sys_ts.tv_nsec, &sys_ts, + bp->utc_tai_offset); + seq_printf(s, "%7s: PHC:SYS offset: %lld window: %lld\n", "", + timespec64_to_ns(&ts) - ns, + post_ns - pre_ns); + } + + free_page((unsigned long)buf); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(ptp_ocp_summary); + +static struct dentry *ptp_ocp_debugfs_root; + +static void +ptp_ocp_debugfs_add_device(struct ptp_ocp *bp) +{ + struct dentry *d; + + d = debugfs_create_dir(dev_name(&bp->dev), ptp_ocp_debugfs_root); + bp->debug_root = d; + debugfs_create_file("summary", 0444, bp->debug_root, + &bp->dev, &ptp_ocp_summary_fops); +} + +static void +ptp_ocp_debugfs_remove_device(struct ptp_ocp *bp) +{ + debugfs_remove_recursive(bp->debug_root); +} + +static void +ptp_ocp_debugfs_init(void) +{ + ptp_ocp_debugfs_root = debugfs_create_dir("timecard", NULL); +} + +static void +ptp_ocp_debugfs_fini(void) +{ + debugfs_remove_recursive(ptp_ocp_debugfs_root); +} + static void ptp_ocp_dev_release(struct device *dev) { @@ -1270,7 +2236,9 @@ ptp_ocp_device_init(struct ptp_ocp *bp, struct pci_dev *pdev) bp->ptp_info = ptp_ocp_clock_info; spin_lock_init(&bp->lock); bp->gnss_port = -1; + bp->gnss2_port = -1; bp->mac_port = -1; + bp->nmea_port = -1; bp->pdev = pdev; device_initialize(&bp->dev); @@ -1332,10 +2300,18 @@ ptp_ocp_complete(struct ptp_ocp *bp) sprintf(buf, "ttyS%d", bp->gnss_port); ptp_ocp_link_child(bp, buf, "ttyGNSS"); } + if (bp->gnss2_port != -1) { + sprintf(buf, "ttyS%d", bp->gnss2_port); + ptp_ocp_link_child(bp, buf, "ttyGNSS2"); + } if (bp->mac_port != -1) { sprintf(buf, "ttyS%d", bp->mac_port); ptp_ocp_link_child(bp, buf, "ttyMAC"); } + if (bp->nmea_port != -1) { + sprintf(buf, "ttyS%d", bp->nmea_port); + ptp_ocp_link_child(bp, buf, "ttyNMEA"); + } sprintf(buf, "ptp%d", ptp_clock_index(bp->ptp)); ptp_ocp_link_child(bp, buf, "ptp"); @@ -1346,13 +2322,53 @@ ptp_ocp_complete(struct ptp_ocp *bp) if (device_add_groups(&bp->dev, timecard_groups)) pr_err("device add groups failed\n"); + ptp_ocp_debugfs_add_device(bp); + return 0; } static void -ptp_ocp_resource_summary(struct ptp_ocp *bp) +ptp_ocp_phc_info(struct ptp_ocp *bp) { + struct timespec64 ts; + u32 version, select; + bool sync; + + version = ioread32(&bp->reg->version); + select = ioread32(&bp->reg->select); + dev_info(&bp->pdev->dev, "Version %d.%d.%d, clock %s, device ptp%d\n", + version >> 24, (version >> 16) & 0xff, version & 0xffff, + ptp_ocp_select_name_from_val(ptp_ocp_clock, select >> 16), + ptp_clock_index(bp->ptp)); + + sync = ioread32(&bp->reg->status) & OCP_STATUS_IN_SYNC; + if (!ptp_ocp_gettimex(&bp->ptp_info, &ts, NULL)) + dev_info(&bp->pdev->dev, "Time: %lld.%ld, %s\n", + ts.tv_sec, ts.tv_nsec, + sync ? "in-sync" : "UNSYNCED"); +} + +static void +ptp_ocp_serial_info(struct device *dev, const char *name, int port, int baud) +{ + if (port != -1) + dev_info(dev, "%5s: /dev/ttyS%-2d @ %6d\n", name, port, baud); +} + +static void +ptp_ocp_info(struct ptp_ocp *bp) +{ + static int nmea_baud[] = { + 1200, 2400, 4800, 9600, 19200, 38400, + 57600, 115200, 230400, 460800, 921600, + 1000000, 2000000 + }; struct device *dev = &bp->pdev->dev; + u32 reg; + + ptp_ocp_phc_info(bp); + if (bp->tod) + ptp_ocp_tod_info(bp); if (bp->image) { u32 ver = ioread32(&bp->image->version); @@ -1365,10 +2381,17 @@ ptp_ocp_resource_summary(struct ptp_ocp *bp) dev_info(dev, "golden image, version %d\n", ver >> 16); } - if (bp->gnss_port != -1) - dev_info(dev, "GNSS @ /dev/ttyS%d 115200\n", bp->gnss_port); - if (bp->mac_port != -1) - dev_info(dev, "MAC @ /dev/ttyS%d 57600\n", bp->mac_port); + ptp_ocp_serial_info(dev, "GNSS", bp->gnss_port, 115200); + ptp_ocp_serial_info(dev, "GNSS2", bp->gnss2_port, 115200); + ptp_ocp_serial_info(dev, "MAC", bp->mac_port, 57600); + if (bp->nmea_out && bp->nmea_port != -1) { + int baud = -1; + + reg = ioread32(&bp->nmea_out->uart_baud); + if (reg < ARRAY_SIZE(nmea_baud)) + baud = nmea_baud[reg]; + ptp_ocp_serial_info(dev, "NMEA", bp->nmea_port, baud); + } } static void @@ -1386,6 +2409,7 @@ ptp_ocp_detach_sysfs(struct ptp_ocp *bp) static void ptp_ocp_detach(struct ptp_ocp *bp) { + ptp_ocp_debugfs_remove_device(bp); ptp_ocp_detach_sysfs(bp); if (timer_pending(&bp->watchdog)) del_timer_sync(&bp->watchdog); @@ -1393,12 +2417,18 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_unregister_ext(bp->ts0); if (bp->ts1) ptp_ocp_unregister_ext(bp->ts1); + if (bp->ts2) + ptp_ocp_unregister_ext(bp->ts2); if (bp->pps) ptp_ocp_unregister_ext(bp->pps); if (bp->gnss_port != -1) serial8250_unregister_port(bp->gnss_port); + if (bp->gnss2_port != -1) + serial8250_unregister_port(bp->gnss2_port); if (bp->mac_port != -1) serial8250_unregister_port(bp->mac_port); + if (bp->nmea_port != -1) + serial8250_unregister_port(bp->nmea_port); if (bp->spi_flash) platform_device_unregister(bp->spi_flash); if (bp->i2c_ctrl) @@ -1425,10 +2455,6 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; } - err = devlink_register(devlink); - if (err) - goto out_free; - err = pci_enable_device(pdev); if (err) { dev_err(&pdev->dev, "pci_enable_device\n"); @@ -1445,7 +2471,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) * allow this - if not all of the IRQ's are returned, skip the * extra devices and just register the clock. */ - err = pci_alloc_irq_vectors(pdev, 1, 10, PCI_IRQ_MSI | PCI_IRQ_MSIX); + err = pci_alloc_irq_vectors(pdev, 1, 11, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (err < 0) { dev_err(&pdev->dev, "alloc_irq_vectors err: %d\n", err); goto out; @@ -1470,8 +2496,7 @@ ptp_ocp_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto out; ptp_ocp_info(bp); - ptp_ocp_resource_summary(bp); - + devlink_register(devlink); return 0; out: @@ -1480,10 +2505,7 @@ out: out_disable: pci_disable_device(pdev); out_unregister: - devlink_unregister(devlink); -out_free: devlink_free(devlink); - return err; } @@ -1493,11 +2515,11 @@ ptp_ocp_remove(struct pci_dev *pdev) struct ptp_ocp *bp = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(bp); + devlink_unregister(devlink); ptp_ocp_detach(bp); pci_set_drvdata(pdev, NULL); pci_disable_device(pdev); - devlink_unregister(devlink); devlink_free(devlink); } @@ -1554,6 +2576,8 @@ ptp_ocp_init(void) const char *what; int err; + ptp_ocp_debugfs_init(); + what = "timecard class"; err = class_register(&timecard_class); if (err) @@ -1576,6 +2600,7 @@ out_register: out_notifier: class_unregister(&timecard_class); out: + ptp_ocp_debugfs_fini(); pr_err(KBUILD_MODNAME ": failed to register %s: %d\n", what, err); return err; } @@ -1586,6 +2611,7 @@ ptp_ocp_fini(void) bus_unregister_notifier(&i2c_bus_type, &ptp_ocp_i2c_notifier); pci_unregister_driver(&ptp_ocp_driver); class_unregister(&timecard_class); + ptp_ocp_debugfs_fini(); } module_init(ptp_ocp_init); diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index 06281a0a055210..de2423c72b022d 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -182,7 +182,7 @@ static void ctcmpc_chx_attnbusy(fsm_instance *, int, void *); static void ctcmpc_chx_resend(fsm_instance *, int, void *); static void ctcmpc_chx_send_sweep(fsm_instance *fsm, int event, void *arg); -/** +/* * Check return code of a preceding ccw_device call, halt_IO etc... * * ch : The channel, the error belongs to. @@ -223,7 +223,7 @@ void ctcm_purge_skb_queue(struct sk_buff_head *q) } } -/** +/* * NOP action for statemachines */ static void ctcm_action_nop(fsm_instance *fi, int event, void *arg) @@ -234,7 +234,7 @@ static void ctcm_action_nop(fsm_instance *fi, int event, void *arg) * Actions for channel - statemachines. */ -/** +/* * Normal data has been send. Free the corresponding * skb (it's in io_queue), reset dev->tbusy and * revert to idle state. @@ -322,7 +322,7 @@ static void chx_txdone(fsm_instance *fi, int event, void *arg) ctcm_clear_busy_do(dev); } -/** +/* * Initial data is sent. * Notify device statemachine that we are up and * running. @@ -344,7 +344,7 @@ void ctcm_chx_txidle(fsm_instance *fi, int event, void *arg) fsm_event(priv->fsm, DEV_EVENT_TXUP, ch->netdev); } -/** +/* * Got normal data, check for sanity, queue it up, allocate new buffer * trigger bottom half, and initiate next read. * @@ -421,7 +421,7 @@ static void chx_rx(fsm_instance *fi, int event, void *arg) ctcm_ccw_check_rc(ch, rc, "normal RX"); } -/** +/* * Initialize connection by sending a __u16 of value 0. * * fi An instance of a channel statemachine. @@ -497,7 +497,7 @@ static void chx_firstio(fsm_instance *fi, int event, void *arg) } } -/** +/* * Got initial data, check it. If OK, * notify device statemachine that we are up and * running. @@ -538,7 +538,7 @@ static void chx_rxidle(fsm_instance *fi, int event, void *arg) } } -/** +/* * Set channel into extended mode. * * fi An instance of a channel statemachine. @@ -578,7 +578,7 @@ static void ctcm_chx_setmode(fsm_instance *fi, int event, void *arg) ch->retry = 0; } -/** +/* * Setup channel. * * fi An instance of a channel statemachine. @@ -641,7 +641,7 @@ static void ctcm_chx_start(fsm_instance *fi, int event, void *arg) } } -/** +/* * Shutdown a channel. * * fi An instance of a channel statemachine. @@ -682,7 +682,7 @@ static void ctcm_chx_haltio(fsm_instance *fi, int event, void *arg) } } -/** +/* * Cleanup helper for chx_fail and chx_stopped * cleanup channels queue and notify interface statemachine. * @@ -728,7 +728,7 @@ static void ctcm_chx_cleanup(fsm_instance *fi, int state, } } -/** +/* * A channel has successfully been halted. * Cleanup it's queue and notify interface statemachine. * @@ -741,7 +741,7 @@ static void ctcm_chx_stopped(fsm_instance *fi, int event, void *arg) ctcm_chx_cleanup(fi, CTC_STATE_STOPPED, arg); } -/** +/* * A stop command from device statemachine arrived and we are in * not operational mode. Set state to stopped. * @@ -754,7 +754,7 @@ static void ctcm_chx_stop(fsm_instance *fi, int event, void *arg) fsm_newstate(fi, CTC_STATE_STOPPED); } -/** +/* * A machine check for no path, not operational status or gone device has * happened. * Cleanup queue and notify interface statemachine. @@ -768,7 +768,7 @@ static void ctcm_chx_fail(fsm_instance *fi, int event, void *arg) ctcm_chx_cleanup(fi, CTC_STATE_NOTOP, arg); } -/** +/* * Handle error during setup of channel. * * fi An instance of a channel statemachine. @@ -817,7 +817,7 @@ static void ctcm_chx_setuperr(fsm_instance *fi, int event, void *arg) } } -/** +/* * Restart a channel after an error. * * fi An instance of a channel statemachine. @@ -858,7 +858,7 @@ static void ctcm_chx_restart(fsm_instance *fi, int event, void *arg) } } -/** +/* * Handle error during RX initial handshake (exchange of * 0-length block header) * @@ -893,7 +893,7 @@ static void ctcm_chx_rxiniterr(fsm_instance *fi, int event, void *arg) } } -/** +/* * Notify device statemachine if we gave up initialization * of RX channel. * @@ -914,7 +914,7 @@ static void ctcm_chx_rxinitfail(fsm_instance *fi, int event, void *arg) fsm_event(priv->fsm, DEV_EVENT_RXDOWN, dev); } -/** +/* * Handle RX Unit check remote reset (remote disconnected) * * fi An instance of a channel statemachine. @@ -946,7 +946,7 @@ static void ctcm_chx_rxdisc(fsm_instance *fi, int event, void *arg) ccw_device_halt(ch2->cdev, 0); } -/** +/* * Handle error during TX channel initialization. * * fi An instance of a channel statemachine. @@ -978,7 +978,7 @@ static void ctcm_chx_txiniterr(fsm_instance *fi, int event, void *arg) } } -/** +/* * Handle TX timeout by retrying operation. * * fi An instance of a channel statemachine. @@ -1050,7 +1050,7 @@ done: return; } -/** +/* * Handle fatal errors during an I/O command. * * fi An instance of a channel statemachine. @@ -1198,7 +1198,7 @@ int ch_fsm_len = ARRAY_SIZE(ch_fsm); * Actions for mpc channel statemachine. */ -/** +/* * Normal data has been send. Free the corresponding * skb (it's in io_queue), reset dev->tbusy and * revert to idle state. @@ -1361,7 +1361,7 @@ done: return; } -/** +/* * Got normal data, check for sanity, queue it up, allocate new buffer * trigger bottom half, and initiate next read. * @@ -1464,7 +1464,7 @@ again: } -/** +/* * Initialize connection by sending a __u16 of value 0. * * fi An instance of a channel statemachine. @@ -1516,7 +1516,7 @@ done: return; } -/** +/* * Got initial data, check it. If OK, * notify device statemachine that we are up and * running. @@ -2043,7 +2043,7 @@ int mpc_ch_fsm_len = ARRAY_SIZE(ctcmpc_ch_fsm); * Actions for interface - statemachine. */ -/** +/* * Startup channels by sending CTC_EVENT_START to each channel. * * fi An instance of an interface statemachine. @@ -2068,7 +2068,7 @@ static void dev_action_start(fsm_instance *fi, int event, void *arg) } } -/** +/* * Shutdown channels by sending CTC_EVENT_STOP to each channel. * * fi An instance of an interface statemachine. @@ -2122,7 +2122,7 @@ static void dev_action_restart(fsm_instance *fi, int event, void *arg) DEV_EVENT_START, dev); } -/** +/* * Called from channel statemachine * when a channel is up and running. * @@ -2183,7 +2183,7 @@ static void dev_action_chup(fsm_instance *fi, int event, void *arg) } } -/** +/* * Called from device statemachine * when a channel has been shutdown. * diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index fd705429708e80..5ea7eeb07002b5 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -55,7 +55,7 @@ /* Some common global variables */ -/** +/* * The root device for ctcm group devices */ static struct device *ctcm_root_dev; @@ -65,7 +65,7 @@ static struct device *ctcm_root_dev; */ struct channel *channels; -/** +/* * Unpack a just received skb and hand it over to * upper layers. * @@ -180,7 +180,7 @@ void ctcm_unpack_skb(struct channel *ch, struct sk_buff *pskb) } } -/** +/* * Release a specific channel in the channel list. * * ch Pointer to channel struct to be released. @@ -192,7 +192,7 @@ static void channel_free(struct channel *ch) fsm_newstate(ch->fsm, CTC_STATE_IDLE); } -/** +/* * Remove a specific channel in the channel list. * * ch Pointer to channel struct to be released. @@ -240,7 +240,7 @@ static void channel_remove(struct channel *ch) chid, ok ? "OK" : "failed"); } -/** +/* * Get a specific channel from the channel list. * * type Type of channel we are interested in. @@ -300,7 +300,7 @@ static long ctcm_check_irb_error(struct ccw_device *cdev, struct irb *irb) } -/** +/* * Check sense of a unit check. * * ch The channel, the sense code belongs to. @@ -414,7 +414,7 @@ int ctcm_ch_alloc_buffer(struct channel *ch) * Interface API for upper network layers */ -/** +/* * Open an interface. * Called from generic network layer when ifconfig up is run. * @@ -432,7 +432,7 @@ int ctcm_open(struct net_device *dev) return 0; } -/** +/* * Close an interface. * Called from generic network layer when ifconfig down is run. * @@ -451,7 +451,7 @@ int ctcm_close(struct net_device *dev) } -/** +/* * Transmit a packet. * This is a helper function for ctcm_tx(). * @@ -822,7 +822,7 @@ done: return rc; } -/** +/* * Start transmission of a packet. * Called from generic network device layer. * @@ -975,7 +975,7 @@ done: } -/** +/* * Sets MTU of an interface. * * dev Pointer to interface struct. @@ -1007,7 +1007,7 @@ static int ctcm_change_mtu(struct net_device *dev, int new_mtu) return 0; } -/** +/* * Returns interface statistics of a device. * * dev Pointer to interface struct. @@ -1144,7 +1144,7 @@ static struct net_device *ctcm_init_netdevice(struct ctcm_priv *priv) return dev; } -/** +/* * Main IRQ handler. * * cdev The ccw_device the interrupt is for. @@ -1257,7 +1257,7 @@ static const struct device_type ctcm_devtype = { .groups = ctcm_attr_groups, }; -/** +/* * Add ctcm specific attributes. * Add ctcm private data. * @@ -1293,7 +1293,7 @@ static int ctcm_probe_device(struct ccwgroup_device *cgdev) return 0; } -/** +/* * Add a new channel to the list of channels. * Keeps the channel list sorted. * @@ -1343,7 +1343,7 @@ static int add_channel(struct ccw_device *cdev, enum ctcm_channel_types type, snprintf(ch->id, CTCM_ID_SIZE, "ch-%s", dev_name(&cdev->dev)); ch->type = type; - /** + /* * "static" ccws are used in the following way: * * ccw[0..2] (Channel program for generic I/O): @@ -1471,7 +1471,7 @@ static enum ctcm_channel_types get_channel_type(struct ccw_device_id *id) return type; } -/** +/* * * Setup an interface. * @@ -1595,7 +1595,7 @@ out_err_result: return result; } -/** +/* * Shutdown an interface. * * cgdev Device to be shut down. @@ -1738,7 +1738,7 @@ static void print_banner(void) pr_info("CTCM driver initialized\n"); } -/** +/* * Initialize module. * This is called just after the module is loaded. * diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index f0436f555c62a5..88abfb5e8045c6 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -1016,7 +1016,7 @@ done: CTCM_PR_DEBUG("exit %s: ch=0x%p id=%s\n", __func__, ch, ch->id); } -/** +/* * Unpack a just received skb and hand it over to * upper layers. * special MPC version of unpack_skb. @@ -1211,7 +1211,7 @@ done: __func__, dev->name, ch, ch->id); } -/** +/* * tasklet helper for mpc's skb unpacking. * * ch The channel to work on. @@ -1320,7 +1320,7 @@ struct mpc_group *ctcmpc_init_mpc_group(struct ctcm_priv *priv) * CTCM_PROTO_MPC only */ -/** +/* * NOP action for statemachines */ static void mpc_action_nop(fsm_instance *fi, int event, void *arg) @@ -1426,7 +1426,7 @@ static void mpc_action_go_inop(fsm_instance *fi, int event, void *arg) } } -/** +/* * Handle mpc group action timeout. * MPC Group Station FSM action * CTCM_PROTO_MPC only diff --git a/drivers/s390/net/fsm.c b/drivers/s390/net/fsm.c index eb07862bd36a03..98c4864932d221 100644 --- a/drivers/s390/net/fsm.c +++ b/drivers/s390/net/fsm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * A generic FSM based on fsm used in isdn4linux * */ diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 26cc943d203404..5f7e28de8b1504 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -555,7 +555,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_disable; - ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (ret) goto err_resource; diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index 440219bcaa2bed..c18fd48e02b61e 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -40,18 +40,18 @@ #error Cannot compile lcs.c without some net devices switched on. #endif -/** +/* * initialization string for output */ static char version[] __initdata = "LCS driver"; -/** +/* * the root device for lcs group devices */ static struct device *lcs_root_dev; -/** +/* * Some prototypes. */ static void lcs_tasklet(unsigned long); @@ -62,14 +62,14 @@ static int lcs_send_delipm(struct lcs_card *, struct lcs_ipm_list *); #endif /* CONFIG_IP_MULTICAST */ static int lcs_recovery(void *ptr); -/** +/* * Debug Facility Stuff */ static char debug_buffer[255]; static debug_info_t *lcs_dbf_setup; static debug_info_t *lcs_dbf_trace; -/** +/* * LCS Debug Facility functions */ static void @@ -96,7 +96,7 @@ lcs_register_debug_facility(void) return 0; } -/** +/* * Allocate io buffers. */ static int @@ -123,7 +123,7 @@ lcs_alloc_channel(struct lcs_channel *channel) return 0; } -/** +/* * Free io buffers. */ static void @@ -151,7 +151,7 @@ lcs_cleanup_channel(struct lcs_channel *channel) lcs_free_channel(channel); } -/** +/* * LCS free memory for card and channels. */ static void @@ -162,7 +162,7 @@ lcs_free_card(struct lcs_card *card) kfree(card); } -/** +/* * LCS alloc memory for card and channels */ static struct lcs_card * @@ -402,7 +402,7 @@ lcs_do_start_thread(struct lcs_card *card, unsigned long thread) return rc; } -/** +/* * Initialize channels,card and state machines. */ static void @@ -451,7 +451,8 @@ static void lcs_clear_multicast_list(struct lcs_card *card) spin_unlock_irqrestore(&card->ipm_lock, flags); #endif } -/** + +/* * Cleanup channels,card and state machines. */ static void @@ -468,7 +469,7 @@ lcs_cleanup_card(struct lcs_card *card) lcs_cleanup_channel(&card->read); } -/** +/* * Start channel. */ static int @@ -517,7 +518,7 @@ lcs_clear_channel(struct lcs_channel *channel) } -/** +/* * Stop channel. */ static int @@ -545,7 +546,7 @@ lcs_stop_channel(struct lcs_channel *channel) return 0; } -/** +/* * start read and write channel */ static int @@ -565,7 +566,7 @@ lcs_start_channels(struct lcs_card *card) return rc; } -/** +/* * stop read and write channel */ static int @@ -577,7 +578,7 @@ lcs_stop_channels(struct lcs_card *card) return 0; } -/** +/* * Get empty buffer. */ static struct lcs_buffer * @@ -610,7 +611,7 @@ lcs_get_buffer(struct lcs_channel *channel) return buffer; } -/** +/* * Resume channel program if the channel is suspended. */ static int @@ -636,7 +637,7 @@ __lcs_resume_channel(struct lcs_channel *channel) } -/** +/* * Make a buffer ready for processing. */ static void __lcs_ready_buffer_bits(struct lcs_channel *channel, int index) @@ -678,7 +679,7 @@ lcs_ready_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer) return rc; } -/** +/* * Mark the buffer as processed. Take care of the suspend bit * of the previous buffer. This function is called from * interrupt context, so the lock must not be taken. @@ -712,7 +713,7 @@ __lcs_processed_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer) return __lcs_resume_channel(channel); } -/** +/* * Put a processed buffer back to state empty. */ static void @@ -728,7 +729,7 @@ lcs_release_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer) spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); } -/** +/* * Get buffer for a lan command. */ static struct lcs_buffer * @@ -785,7 +786,7 @@ lcs_alloc_reply(struct lcs_cmd *cmd) return reply; } -/** +/* * Notifier function for lancmd replies. Called from read irq. */ static void @@ -813,7 +814,7 @@ lcs_notify_lancmd_waiters(struct lcs_card *card, struct lcs_cmd *cmd) spin_unlock(&card->lock); } -/** +/* * Emit buffer of a lan command. */ static void @@ -877,7 +878,7 @@ lcs_send_lancmd(struct lcs_card *card, struct lcs_buffer *buffer, return rc ? -EIO : 0; } -/** +/* * LCS startup command */ static int @@ -895,7 +896,7 @@ lcs_send_startup(struct lcs_card *card, __u8 initiator) return lcs_send_lancmd(card, buffer, NULL); } -/** +/* * LCS shutdown command */ static int @@ -912,7 +913,7 @@ lcs_send_shutdown(struct lcs_card *card) return lcs_send_lancmd(card, buffer, NULL); } -/** +/* * LCS lanstat command */ static void @@ -939,7 +940,7 @@ lcs_send_lanstat(struct lcs_card *card) return lcs_send_lancmd(card, buffer, __lcs_lanstat_cb); } -/** +/* * send stoplan command */ static int @@ -958,7 +959,7 @@ lcs_send_stoplan(struct lcs_card *card, __u8 initiator) return lcs_send_lancmd(card, buffer, NULL); } -/** +/* * send startlan command */ static void @@ -986,7 +987,7 @@ lcs_send_startlan(struct lcs_card *card, __u8 initiator) } #ifdef CONFIG_IP_MULTICAST -/** +/* * send setipm command (Multicast) */ static int @@ -1010,7 +1011,7 @@ lcs_send_setipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list) return lcs_send_lancmd(card, buffer, NULL); } -/** +/* * send delipm command (Multicast) */ static int @@ -1034,7 +1035,7 @@ lcs_send_delipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list) return lcs_send_lancmd(card, buffer, NULL); } -/** +/* * check if multicast is supported by LCS */ static void @@ -1074,7 +1075,7 @@ lcs_check_multicast_support(struct lcs_card *card) return -EOPNOTSUPP; } -/** +/* * set or del multicast address on LCS card */ static void @@ -1129,7 +1130,7 @@ list_modified: spin_unlock_irqrestore(&card->ipm_lock, flags); } -/** +/* * get mac address for the relevant Multicast address */ static void @@ -1139,7 +1140,7 @@ lcs_get_mac_for_ipm(__be32 ipm, char *mac, struct net_device *dev) ip_eth_mc_map(ipm, mac); } -/** +/* * function called by net device to handle multicast address relevant things */ static void lcs_remove_mc_addresses(struct lcs_card *card, @@ -1260,7 +1261,7 @@ out: } #endif /* CONFIG_IP_MULTICAST */ -/** +/* * function called by net device to * handle multicast address relevant things */ @@ -1355,7 +1356,7 @@ lcs_schedule_recovery(struct lcs_card *card) schedule_work(&card->kernel_thread_starter); } -/** +/* * IRQ Handler for LCS channels */ static void @@ -1439,7 +1440,7 @@ lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) tasklet_schedule(&channel->irq_tasklet); } -/** +/* * Tasklet for IRQ handler */ static void @@ -1476,7 +1477,7 @@ lcs_tasklet(unsigned long data) wake_up(&channel->wait_q); } -/** +/* * Finish current tx buffer and make it ready for transmit. */ static void @@ -1490,7 +1491,7 @@ __lcs_emit_txbuffer(struct lcs_card *card) card->tx_emitted++; } -/** +/* * Callback for finished tx buffers. */ static void @@ -1515,7 +1516,7 @@ lcs_txbuffer_cb(struct lcs_channel *channel, struct lcs_buffer *buffer) spin_unlock(&card->lock); } -/** +/* * Packet transmit function called by network stack */ static int @@ -1593,7 +1594,7 @@ lcs_start_xmit(struct sk_buff *skb, struct net_device *dev) return rc; } -/** +/* * send startlan and lanstat command to make LCS device ready */ static int @@ -1648,7 +1649,7 @@ lcs_startlan(struct lcs_card *card) return rc; } -/** +/* * LCS detect function * setup channels and make them I/O ready */ @@ -1680,7 +1681,7 @@ lcs_detect(struct lcs_card *card) return rc; } -/** +/* * LCS Stop card */ static int @@ -1705,7 +1706,7 @@ lcs_stopcard(struct lcs_card *card) return rc; } -/** +/* * Kernel Thread helper functions for LGW initiated commands */ static void @@ -1721,7 +1722,7 @@ lcs_start_kernel_thread(struct work_struct *work) #endif } -/** +/* * Process control frames. */ static void @@ -1748,7 +1749,7 @@ lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd) lcs_notify_lancmd_waiters(card, cmd); } -/** +/* * Unpack network packet. */ static void @@ -1779,7 +1780,7 @@ lcs_get_skb(struct lcs_card *card, char *skb_data, unsigned int skb_len) netif_rx(skb); } -/** +/* * LCS main routine to get packets and lancmd replies from the buffers */ static void @@ -1829,7 +1830,7 @@ lcs_get_frames_cb(struct lcs_channel *channel, struct lcs_buffer *buffer) lcs_ready_buffer(&card->read, buffer); } -/** +/* * get network statistics for ifconfig and other user programs */ static struct net_device_stats * @@ -1842,7 +1843,7 @@ lcs_getstats(struct net_device *dev) return &card->stats; } -/** +/* * stop lcs device * This function will be called by user doing ifconfig xxx down */ @@ -1866,7 +1867,7 @@ lcs_stop_device(struct net_device *dev) return rc; } -/** +/* * start lcs device and make it runnable * This function will be called by user doing ifconfig xxx up */ @@ -1892,7 +1893,7 @@ lcs_open_device(struct net_device *dev) return rc; } -/** +/* * show function for portno called by cat or similar things */ static ssize_t @@ -1908,7 +1909,7 @@ lcs_portno_show (struct device *dev, struct device_attribute *attr, char *buf) return sprintf(buf, "%d\n", card->portno); } -/** +/* * store the value which is piped to file portno */ static ssize_t @@ -2033,7 +2034,7 @@ static const struct device_type lcs_devtype = { .groups = lcs_attr_groups, }; -/** +/* * lcs_probe_device is called on establishing a new ccwgroup_device. */ static int @@ -2077,7 +2078,7 @@ lcs_register_netdev(struct ccwgroup_device *ccwgdev) return register_netdev(card->dev); } -/** +/* * lcs_new_device will be called by setting the group device online. */ static const struct net_device_ops lcs_netdev_ops = { @@ -2199,7 +2200,7 @@ out_err: return -ENODEV; } -/** +/* * lcs_shutdown_device, called when setting the group device offline. */ static int @@ -2240,7 +2241,7 @@ lcs_shutdown_device(struct ccwgroup_device *ccwgdev) return __lcs_shutdown_device(ccwgdev, 0); } -/** +/* * drive lcs recovery after startup and startlan initiated by Lan Gateway */ static int @@ -2271,7 +2272,7 @@ lcs_recovery(void *ptr) return 0; } -/** +/* * lcs_remove_device, free buffers and card */ static void @@ -2315,7 +2316,7 @@ static struct ccw_driver lcs_ccw_driver = { .int_class = IRQIO_LCS, }; -/** +/* * LCS ccwgroup driver registration */ static struct ccwgroup_driver lcs_group_driver = { @@ -2351,7 +2352,7 @@ static const struct attribute_group *lcs_drv_attr_groups[] = { NULL, }; -/** +/* * LCS Module/Kernel initialization function */ static int @@ -2389,7 +2390,7 @@ out_err: } -/** +/* * LCS module cleanup function */ static void diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 5a0c2f07a3a252..981e7b1c6b9622 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -58,7 +58,7 @@ MODULE_AUTHOR ("(C) 2001 IBM Corporation by Fritz Elfert (felfert@millenux.com)"); MODULE_DESCRIPTION ("Linux for S/390 IUCV network driver"); -/** +/* * Debug Facility stuff */ #define IUCV_DBF_SETUP_NAME "iucv_setup" @@ -107,7 +107,7 @@ DECLARE_PER_CPU(char[256], iucv_dbf_txt_buf); debug_sprintf_event(iucv_dbf_trace, level, text ); \ } while (0) -/** +/* * some more debug stuff */ #define PRINTK_HEADER " iucv: " /* for debugging */ @@ -118,7 +118,7 @@ static struct device_driver netiucv_driver = { .bus = &iucv_bus, }; -/** +/* * Per connection profiling data */ struct connection_profile { @@ -133,7 +133,7 @@ struct connection_profile { unsigned long tx_max_pending; }; -/** +/* * Representation of one iucv connection */ struct iucv_connection { @@ -154,13 +154,13 @@ struct iucv_connection { char userdata[17]; }; -/** +/* * Linked list of all connection structs. */ static LIST_HEAD(iucv_connection_list); static DEFINE_RWLOCK(iucv_connection_rwlock); -/** +/* * Representation of event-data for the * connection state machine. */ @@ -169,7 +169,7 @@ struct iucv_event { void *data; }; -/** +/* * Private part of the network device structure */ struct netiucv_priv { @@ -180,7 +180,7 @@ struct netiucv_priv { struct device *dev; }; -/** +/* * Link level header for a packet. */ struct ll_header { @@ -195,7 +195,7 @@ struct ll_header { #define NETIUCV_QUEUELEN_DEFAULT 50 #define NETIUCV_TIMEOUT_5SEC 5000 -/** +/* * Compatibility macros for busy handling * of network devices. */ @@ -223,7 +223,7 @@ static u8 iucvMagic_ebcdic[16] = { 0xF0, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 }; -/** +/* * Convert an iucv userId to its printable * form (strip whitespace at end). * @@ -262,7 +262,7 @@ static char *netiucv_printuser(struct iucv_connection *conn) return netiucv_printname(conn->userid, 8); } -/** +/* * States of the interface statemachine. */ enum dev_states { @@ -270,7 +270,7 @@ enum dev_states { DEV_STATE_STARTWAIT, DEV_STATE_STOPWAIT, DEV_STATE_RUNNING, - /** + /* * MUST be always the last element!! */ NR_DEV_STATES @@ -283,7 +283,7 @@ static const char *dev_state_names[] = { "Running", }; -/** +/* * Events of the interface statemachine. */ enum dev_events { @@ -291,7 +291,7 @@ enum dev_events { DEV_EVENT_STOP, DEV_EVENT_CONUP, DEV_EVENT_CONDOWN, - /** + /* * MUST be always the last element!! */ NR_DEV_EVENTS @@ -304,11 +304,11 @@ static const char *dev_event_names[] = { "Connection down", }; -/** +/* * Events of the connection statemachine */ enum conn_events { - /** + /* * Events, representing callbacks from * lowlevel iucv layer) */ @@ -320,23 +320,23 @@ enum conn_events { CONN_EVENT_RX, CONN_EVENT_TXDONE, - /** + /* * Events, representing errors return codes from * calls to lowlevel iucv layer */ - /** + /* * Event, representing timer expiry. */ CONN_EVENT_TIMER, - /** + /* * Events, representing commands from upper levels. */ CONN_EVENT_START, CONN_EVENT_STOP, - /** + /* * MUST be always the last element!! */ NR_CONN_EVENTS, @@ -357,55 +357,55 @@ static const char *conn_event_names[] = { "Stop", }; -/** +/* * States of the connection statemachine. */ enum conn_states { - /** + /* * Connection not assigned to any device, * initial state, invalid */ CONN_STATE_INVALID, - /** + /* * Userid assigned but not operating */ CONN_STATE_STOPPED, - /** + /* * Connection registered, * no connection request sent yet, * no connection request received */ CONN_STATE_STARTWAIT, - /** + /* * Connection registered and connection request sent, * no acknowledge and no connection request received yet. */ CONN_STATE_SETUPWAIT, - /** + /* * Connection up and running idle */ CONN_STATE_IDLE, - /** + /* * Data sent, awaiting CONN_EVENT_TXDONE */ CONN_STATE_TX, - /** + /* * Error during registration. */ CONN_STATE_REGERR, - /** + /* * Error during registration. */ CONN_STATE_CONNERR, - /** + /* * MUST be always the last element!! */ NR_CONN_STATES, @@ -424,7 +424,7 @@ static const char *conn_state_names[] = { }; -/** +/* * Debug Facility Stuff */ static debug_info_t *iucv_dbf_setup = NULL; @@ -556,7 +556,7 @@ static void netiucv_callback_connres(struct iucv_path *path, u8 *ipuser) fsm_event(conn->fsm, CONN_EVENT_CONN_RES, conn); } -/** +/* * NOP action for statemachines */ static void netiucv_action_nop(fsm_instance *fi, int event, void *arg) @@ -567,7 +567,7 @@ static void netiucv_action_nop(fsm_instance *fi, int event, void *arg) * Actions of the connection statemachine */ -/** +/* * netiucv_unpack_skb * @conn: The connection where this skb has been received. * @pskb: The received skb. @@ -993,7 +993,7 @@ static const int CONN_FSM_LEN = sizeof(conn_fsm) / sizeof(fsm_node); * Actions for interface - statemachine. */ -/** +/* * dev_action_start * @fi: An instance of an interface statemachine. * @event: The event, just happened. @@ -1012,7 +1012,7 @@ static void dev_action_start(fsm_instance *fi, int event, void *arg) fsm_event(privptr->conn->fsm, CONN_EVENT_START, privptr->conn); } -/** +/* * Shutdown connection by sending CONN_EVENT_STOP to it. * * @param fi An instance of an interface statemachine. @@ -1034,7 +1034,7 @@ dev_action_stop(fsm_instance *fi, int event, void *arg) fsm_event(privptr->conn->fsm, CONN_EVENT_STOP, &ev); } -/** +/* * Called from connection statemachine * when a connection is up and running. * @@ -1067,7 +1067,7 @@ dev_action_connup(fsm_instance *fi, int event, void *arg) } } -/** +/* * Called from connection statemachine * when a connection has been shutdown. * @@ -1107,7 +1107,7 @@ static const fsm_node dev_fsm[] = { static const int DEV_FSM_LEN = sizeof(dev_fsm) / sizeof(fsm_node); -/** +/* * Transmit a packet. * This is a helper function for netiucv_tx(). * @@ -1144,7 +1144,7 @@ static int netiucv_transmit_skb(struct iucv_connection *conn, spin_unlock_irqrestore(&conn->collect_lock, saveflags); } else { struct sk_buff *nskb = skb; - /** + /* * Copy the skb to a new allocated skb in lowmem only if the * data is located above 2G in memory or tailroom is < 2. */ @@ -1164,7 +1164,7 @@ static int netiucv_transmit_skb(struct iucv_connection *conn, } copied = 1; } - /** + /* * skb now is below 2G and has enough room. Add headers. */ header.next = nskb->len + NETIUCV_HDRLEN; @@ -1194,7 +1194,7 @@ static int netiucv_transmit_skb(struct iucv_connection *conn, if (copied) dev_kfree_skb(nskb); else { - /** + /* * Remove our headers. They get added * again on retransmit. */ @@ -1217,7 +1217,7 @@ static int netiucv_transmit_skb(struct iucv_connection *conn, * Interface API for upper network layers */ -/** +/* * Open an interface. * Called from generic network layer when ifconfig up is run. * @@ -1233,7 +1233,7 @@ static int netiucv_open(struct net_device *dev) return 0; } -/** +/* * Close an interface. * Called from generic network layer when ifconfig down is run. * @@ -1249,7 +1249,7 @@ static int netiucv_close(struct net_device *dev) return 0; } -/** +/* * Start transmission of a packet. * Called from generic network device layer. * @@ -1266,7 +1266,7 @@ static int netiucv_tx(struct sk_buff *skb, struct net_device *dev) int rc; IUCV_DBF_TEXT(trace, 4, __func__); - /** + /* * Some sanity checks ... */ if (skb == NULL) { @@ -1282,7 +1282,7 @@ static int netiucv_tx(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } - /** + /* * If connection is not running, try to restart it * and throw away packet. */ @@ -1304,7 +1304,7 @@ static int netiucv_tx(struct sk_buff *skb, struct net_device *dev) return rc ? NETDEV_TX_BUSY : NETDEV_TX_OK; } -/** +/* * netiucv_stats * @dev: Pointer to interface struct. * @@ -1745,7 +1745,7 @@ static void netiucv_unregister_device(struct device *dev) device_unregister(dev); } -/** +/* * Allocate and initialize a new connection structure. * Add it to the list of netiucv connections; */ @@ -1802,7 +1802,7 @@ out: return NULL; } -/** +/* * Release a connection structure and remove it from the * list of netiucv connections. */ @@ -1826,7 +1826,7 @@ static void netiucv_remove_connection(struct iucv_connection *conn) kfree_skb(conn->tx_buff); } -/** +/* * Release everything of a net device. */ static void netiucv_free_netdevice(struct net_device *dev) @@ -1848,7 +1848,7 @@ static void netiucv_free_netdevice(struct net_device *dev) } } -/** +/* * Initialize a net device. (Called from kernel in alloc_netdev()) */ static const struct net_device_ops netiucv_netdev_ops = { @@ -1873,7 +1873,7 @@ static void netiucv_setup_netdevice(struct net_device *dev) dev->netdev_ops = &netiucv_netdev_ops; } -/** +/* * Allocate and initialize everything of a net device. */ static struct net_device *netiucv_init_netdevice(char *username, char *userdata) diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 42d0d941dba5c3..94ee08fab46a56 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -3416,7 +3416,9 @@ retry_probe: qedf->devlink = qed_ops->common->devlink_register(qedf->cdev); if (IS_ERR(qedf->devlink)) { QEDF_ERR(&qedf->dbg_ctx, "Cannot register devlink\n"); + rc = PTR_ERR(qedf->devlink); qedf->devlink = NULL; + goto err2; } } diff --git a/drivers/staging/qlge/qlge_main.c b/drivers/staging/qlge/qlge_main.c index 8fcdf89da8aa9c..1dc849378a0fec 100644 --- a/drivers/staging/qlge/qlge_main.c +++ b/drivers/staging/qlge/qlge_main.c @@ -4614,14 +4614,9 @@ static int qlge_probe(struct pci_dev *pdev, goto netdev_free; } - err = devlink_register(devlink); - if (err) - goto netdev_free; - err = qlge_health_create_reporters(qdev); - if (err) - goto devlink_unregister; + goto netdev_free; /* Start up the timer to trigger EEH if * the bus goes dead @@ -4632,10 +4627,9 @@ static int qlge_probe(struct pci_dev *pdev, qlge_display_dev_info(ndev); atomic_set(&qdev->lb_count, 0); cards_found++; + devlink_register(devlink); return 0; -devlink_unregister: - devlink_unregister(devlink); netdev_free: free_netdev(ndev); devlink_free: @@ -4660,13 +4654,13 @@ static void qlge_remove(struct pci_dev *pdev) struct net_device *ndev = qdev->ndev; struct devlink *devlink = priv_to_devlink(qdev); + devlink_unregister(devlink); del_timer_sync(&qdev->timer); qlge_cancel_all_work_sync(qdev); unregister_netdev(ndev); qlge_release_all(pdev); pci_disable_device(pdev); devlink_health_reporter_destroy(qdev->reporter); - devlink_unregister(devlink); devlink_free(devlink); free_netdev(ndev); } diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index c2c2147dfeb8cb..27d9b6683f0e15 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -32,6 +32,7 @@ #define PHY_ID_BCM72113 0x35905310 #define PHY_ID_BCM72116 0x35905350 +#define PHY_ID_BCM72165 0x35905340 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 @@ -66,6 +67,7 @@ #define PHY_BRCM_CLEAR_RGMII_MODE 0x00000004 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000008 #define PHY_BRCM_EN_MASTER_MODE 0x00000010 +#define PHY_BRCM_IDDQ_SUSPEND 0x00000020 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) @@ -83,6 +85,7 @@ #define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */ #define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ +#define MII_BCM54XX_EXP_SEL_TOP 0x0d00 /* TOP_MISC expansion register select */ #define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ #define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ #define MII_BCM54XX_EXP_SEL_ETC 0x0d00 /* Expansion register spare + 2k mem */ @@ -233,6 +236,7 @@ #define MII_BCM54XX_EXP_EXP08 0x0F08 #define MII_BCM54XX_EXP_EXP08_RJCT_2MHZ 0x0001 #define MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE 0x0200 +#define MII_BCM54XX_EXP_EXP08_FORCE_DAC_WAKE 0x0100 #define MII_BCM54XX_EXP_EXP75 0x0f75 #define MII_BCM54XX_EXP_EXP75_VDACCTRL 0x003c #define MII_BCM54XX_EXP_EXP75_CM_OSC 0x0001 @@ -241,6 +245,12 @@ #define MII_BCM54XX_EXP_EXP97 0x0f97 #define MII_BCM54XX_EXP_EXP97_MYST 0x0c0c +/* Top-MISC expansion registers */ +#define BCM54XX_TOP_MISC_IDDQ_CTRL (MII_BCM54XX_EXP_SEL_TOP + 0x06) +#define BCM54XX_TOP_MISC_IDDQ_LP (1 << 0) +#define BCM54XX_TOP_MISC_IDDQ_SD (1 << 2) +#define BCM54XX_TOP_MISC_IDDQ_SR (1 << 3) + /* * BCM5482: Secondary SerDes registers */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 171106202fe5be..e6c78be40bde71 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -48,6 +48,10 @@ struct sja1105_tagger_data { spinlock_t meta_lock; unsigned long state; u8 ts_id; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; }; struct sja1105_skb_cb { @@ -65,46 +69,27 @@ struct sja1105_port { struct kthread_work xmit_work; struct sk_buff_head xmit_queue; struct sja1105_tagger_data *data; - struct dsa_port *dp; bool hwts_tx_en; }; -enum sja1110_meta_tstamp { - SJA1110_META_TSTAMP_TX = 0, - SJA1110_META_TSTAMP_RX = 1, -}; - -#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) - -void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, - enum sja1110_meta_tstamp dir, u64 tstamp); - -#else +/* Timestamps are in units of 8 ns clock ticks (equivalent to + * a fixed 125 MHz clock). + */ +#define SJA1105_TICK_NS 8 -static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, - u8 ts_id, enum sja1110_meta_tstamp dir, - u64 tstamp) +static inline s64 ns_to_sja1105_ticks(s64 ns) { + return ns / SJA1105_TICK_NS; } -#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ - -#if IS_ENABLED(CONFIG_NET_DSA_SJA1105) - -extern const struct dsa_switch_ops sja1105_switch_ops; - -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +static inline s64 sja1105_ticks_to_ns(s64 ticks) { - return dp->ds->ops == &sja1105_switch_ops; + return ticks * SJA1105_TICK_NS; } -#else - static inline bool dsa_port_is_sja1105(struct dsa_port *dp) { - return false; + return true; } -#endif - #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index 92d763230bdf66..a18c1539a152a0 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -506,6 +506,10 @@ #define STATE_MODE_SHIFT (0) #define STATE_MODE_MASK (0x7) +/* Bit definitions for the DPLL_MANU_REF_CFG register */ +#define MANUAL_REFERENCE_SHIFT (0) +#define MANUAL_REFERENCE_MASK (0x1f) + /* Bit definitions for the GPIO_CFG_GBL register */ #define SUPPLY_MODE_SHIFT (0) #define SUPPLY_MODE_MASK (0x3) @@ -654,7 +658,7 @@ /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, - PLL_MODE_NORMAL = PLL_MODE_MIN, + PLL_MODE_PLL = PLL_MODE_MIN, PLL_MODE_WRITE_PHASE = 1, PLL_MODE_WRITE_FREQUENCY = 2, PLL_MODE_GPIO_INC_DEC = 3, @@ -664,6 +668,31 @@ enum pll_mode { PLL_MODE_MAX = PLL_MODE_DISABLED, }; +/* Values of DPLL_CTRL_n.DPLL_MANU_REF_CFG.MANUAL_REFERENCE */ +enum manual_reference { + MANU_REF_MIN = 0, + MANU_REF_CLK0 = MANU_REF_MIN, + MANU_REF_CLK1, + MANU_REF_CLK2, + MANU_REF_CLK3, + MANU_REF_CLK4, + MANU_REF_CLK5, + MANU_REF_CLK6, + MANU_REF_CLK7, + MANU_REF_CLK8, + MANU_REF_CLK9, + MANU_REF_CLK10, + MANU_REF_CLK11, + MANU_REF_CLK12, + MANU_REF_CLK13, + MANU_REF_CLK14, + MANU_REF_CLK15, + MANU_REF_WRITE_PHASE, + MANU_REF_WRITE_FREQUENCY, + MANU_REF_XO_DPLL, + MANU_REF_MAX = MANU_REF_XO_DPLL, +}; + enum hw_tod_write_trig_sel { HW_TOD_WR_TRIG_SEL_MIN = 0, HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 3d43c60b49fa8d..1f7c33b2f5a3f4 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -28,6 +28,7 @@ #define PHY_ID_KSZ9031 0x00221620 #define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_LAN8814 0x00221660 +#define PHY_ID_LAN8804 0x00221670 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe156a8170aa39..0cbc5dfe111021 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -57,6 +57,7 @@ struct perf_guest_info_callbacks { #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> +#include <linux/static_call.h> #include <asm/local.h> struct perf_callchain_entry { @@ -1612,4 +1613,26 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event, extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); #endif +/* + * Snapshot branch stack on software events. + * + * Branch stack can be very useful in understanding software events. For + * example, when a long function, e.g. sys_perf_event_open, returns an + * errno, it is not obvious why the function failed. Branch stack could + * provide very helpful information in this type of scenarios. + * + * On software event, it is necessary to stop the hardware branch recorder + * fast. Otherwise, the hardware register/buffer will be flushed with + * entries of the triggering event. Therefore, static call is used to + * stop the hardware recorder. + */ + +/* + * cnt is the number of entries allocated for entries. + * Return number of entries copied to . + */ +typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, + unsigned int cnt); +DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); + #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 812a4d75116338..4df0bf0a0864e3 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -145,12 +145,6 @@ struct qed_filter_mcast_params { unsigned char mac[64][ETH_ALEN]; }; -union qed_filter_type_params { - enum qed_filter_rx_mode_type accept_flags; - struct qed_filter_ucast_params ucast; - struct qed_filter_mcast_params mcast; -}; - enum qed_filter_type { QED_FILTER_TYPE_UCAST, QED_FILTER_TYPE_MCAST, @@ -158,11 +152,6 @@ enum qed_filter_type { QED_MAX_FILTER_TYPES, }; -struct qed_filter_params { - enum qed_filter_type type; - union qed_filter_type_params filter; -}; - struct qed_tunn_params { u16 vxlan_port; u8 update_vxlan_port; @@ -314,8 +303,14 @@ struct qed_eth_ops { int (*q_tx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle); - int (*filter_config)(struct qed_dev *cdev, - struct qed_filter_params *params); + int (*filter_config_rx_mode)(struct qed_dev *cdev, + enum qed_filter_rx_mode_type type); + + int (*filter_config_ucast)(struct qed_dev *cdev, + struct qed_filter_ucast_params *params); + + int (*filter_config_mcast)(struct qed_dev *cdev, + struct qed_filter_mcast_params *params); int (*fastpath_stop)(struct qed_dev *cdev); diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index fa1d6af0164ee9..0f79fd7f81a1ce 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -34,9 +34,23 @@ : [rf] "+r"(val) \ : [rs] "r"(addr)); \ }) + +static inline u64 otx2_atomic64_fetch_add(u64 incr, u64 *ptr) +{ + u64 result; + + asm volatile (".cpu generic+lse\n" + "ldadda %x[i], %x[r], [%[b]]" + : [r] "=r" (result), "+m" (*ptr) + : [i] "r" (incr), [b] "r" (ptr) + : "memory"); + return result; +} + #else #define otx2_lmt_flush(ioaddr) ({ 0; }) #define cn10k_lmt_flush(val, addr) ({ addr = val; }) +#define otx2_atomic64_fetch_add(incr, ptr) ({ incr; }) #endif #endif /* __SOC_OTX2_ASM_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index 041d6032a34899..7612d760b6a9bd 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -364,6 +364,7 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/devlink.h b/include/net/devlink.h index 154cf0dbca3727..a7852a257bf654 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1566,7 +1566,7 @@ static inline struct devlink *devlink_alloc(const struct devlink_ops *ops, { return devlink_alloc_ns(ops, priv_size, &init_net, dev); } -int devlink_register(struct devlink *devlink); +void devlink_register(struct devlink *devlink); void devlink_unregister(struct devlink *devlink); void devlink_reload_enable(struct devlink *devlink); void devlink_reload_disable(struct devlink *devlink); @@ -1653,32 +1653,11 @@ void devlink_param_unregister(struct devlink *devlink, const struct devlink_param *param); void devlink_params_publish(struct devlink *devlink); void devlink_params_unpublish(struct devlink *devlink); -void devlink_param_publish(struct devlink *devlink, - const struct devlink_param *param); -void devlink_param_unpublish(struct devlink *devlink, - const struct devlink_param *param); -int devlink_port_params_register(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count); -void devlink_port_params_unregister(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count); int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); -int -devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value *init_val); -int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); -void devlink_port_param_value_changed(struct devlink_port *devlink_port, - u32 param_id); -void devlink_param_value_str_fill(union devlink_param_value *dst_val, - const char *src); struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, @@ -1723,10 +1702,7 @@ int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg); -int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value); -int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); -int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, u16 value_len); diff --git a/include/net/mctp.h b/include/net/mctp.h index a824d47c3c6d86..b9ed62a63c2446 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -62,35 +62,46 @@ struct mctp_sock { * by sk->net->keys_lock */ struct hlist_head keys; + + /* mechanism for expiring allocated keys; will release an allocated + * tag, and any netdev state for a request/response pairing + */ + struct timer_list key_expiry; }; /* Key for matching incoming packets to sockets or reassembly contexts. * Packets are matched on (src,dest,tag). * - * Lifetime requirements: + * Lifetime / locking requirements: + * + * - individual key data (ie, the struct itself) is protected by key->lock; + * changes must be made with that lock held. * - * - keys are free()ed via RCU + * - the lookup fields: peer_addr, local_addr and tag are set before the + * key is added to lookup lists, and never updated. + * + * - A ref to the key must be held (throuh key->refs) if a pointer to the + * key is to be accessed after key->lock is released. * * - a mctp_sk_key contains a reference to a struct sock; this is valid * for the life of the key. On sock destruction (through unhash), the key is - * removed from lists (see below), and will not be observable after a RCU - * grace period. - * - * any RX occurring within that grace period may still queue to the socket, - * but will hit the SOCK_DEAD case before the socket is freed. + * removed from lists (see below), and marked invalid. * * - these mctp_sk_keys appear on two lists: * 1) the struct mctp_sock->keys list * 2) the struct netns_mctp->keys list * - * updates to either list are performed under the netns_mctp->keys - * lock. + * presences on these lists requires a (single) refcount to be held; both + * lists are updated as a single operation. + * + * Updates and lookups in either list are performed under the + * netns_mctp->keys lock. Lookup functions will need to lock the key and + * take a reference before unlocking the keys_lock. Consequently, the list's + * keys_lock *cannot* be acquired with the individual key->lock held. * * - a key may have a sk_buff attached as part of an in-progress message - * reassembly (->reasm_head). The reassembly context is protected by - * reasm_lock, which may be acquired with the keys lock (above) held, if - * necessary. Consequently, keys lock *cannot* be acquired with the - * reasm_lock held. + * reassembly (->reasm_head). The reasm data is protected by the individual + * key->lock. * * - there are two destruction paths for a mctp_sk_key: * @@ -101,6 +112,8 @@ struct mctp_sock { * the (complete) reply, or during reassembly errors. Here, we clean up * the reassembly context (marking reasm_dead, to prevent another from * starting), and remove the socket from the netns & socket lists. + * + * - through an expiry timeout, on a per-socket timer */ struct mctp_sk_key { mctp_eid_t peer_addr; @@ -116,14 +129,25 @@ struct mctp_sk_key { /* per-socket list */ struct hlist_node sklist; + /* lock protects against concurrent updates to the reassembly and + * expiry data below. + */ + spinlock_t lock; + + /* Keys are referenced during the output path, which may sleep */ + refcount_t refs; + /* incoming fragment reassembly context */ - spinlock_t reasm_lock; struct sk_buff *reasm_head; struct sk_buff **reasm_tailp; bool reasm_dead; u8 last_seq; - struct rcu_head rcu; + /* key validity */ + bool valid; + + /* expiry timeout; valid (above) cleared on expiry */ + unsigned long expiry; }; struct mctp_skb_cb { @@ -191,6 +215,8 @@ int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); +void mctp_key_unref(struct mctp_sk_key *key); + /* routing <--> device interface */ unsigned int mctp_default_net(struct net *net); int mctp_default_net_set(struct net *net, unsigned int index); diff --git a/include/net/mctpdevice.h b/include/net/mctpdevice.h index 71a11012fac7c4..3a439463f05503 100644 --- a/include/net/mctpdevice.h +++ b/include/net/mctpdevice.h @@ -17,6 +17,8 @@ struct mctp_dev { struct net_device *dev; + refcount_t refs; + unsigned int net; /* Only modified under RTNL. Reads have addrs_lock held */ @@ -32,4 +34,7 @@ struct mctp_dev { struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev); struct mctp_dev *__mctp_dev_get(const struct net_device *dev); +void mctp_dev_hold(struct mctp_dev *mdev); +void mctp_dev_put(struct mctp_dev *mdev); + #endif /* __NET_MCTPDEVICE_H */ diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 6026bbefbffd88..f83fa48408b3d5 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -12,6 +12,8 @@ #include <linux/tcp.h> #include <linux/types.h> +struct mptcp_info; +struct mptcp_sock; struct seq_file; /* MPTCP sk_buff extension data */ @@ -121,6 +123,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb); void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, struct mptcp_out_options *opts); +void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info); + /* move the skb extension owership, with the assumption that 'to' is * newly allocated */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c0069ac00e62d2..5a011f8d394ea4 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -308,6 +308,8 @@ struct Qdisc_ops { struct netlink_ext_ack *extack); void (*attach)(struct Qdisc *sch); int (*change_tx_queue_len)(struct Qdisc *, unsigned int); + void (*change_real_num_tx)(struct Qdisc *sch, + unsigned int new_real_tx); int (*dump)(struct Qdisc *, struct sk_buff *); int (*dump_stats)(struct Qdisc *, struct gnet_dump *); @@ -684,6 +686,8 @@ void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); void qdisc_class_hash_destroy(struct Qdisc_class_hash *); int dev_qdisc_change_tx_queue_len(struct net_device *dev); +void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx); void dev_init_scheduler(struct net_device *dev); void dev_shutdown(struct net_device *dev); void dev_activate(struct net_device *dev); @@ -1341,6 +1345,8 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); +void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); + int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); #endif diff --git a/include/net/sock.h b/include/net/sock.h index c005c3c750e89b..879980de3dcdac 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -262,7 +262,6 @@ struct bpf_local_storage; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy - * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -328,7 +327,6 @@ struct bpf_local_storage; * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] - * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -393,7 +391,6 @@ struct sock { atomic_t sk_drops; int sk_rcvlowat; struct sk_buff_head sk_error_queue; - struct sk_buff *sk_rx_skb_cache; struct sk_buff_head sk_receive_queue; /* * The backlog queue is special, it is always used with @@ -442,7 +439,6 @@ struct sock { struct sk_buff *sk_send_head; struct rb_root tcp_rtx_queue; }; - struct sk_buff *sk_tx_skb_cache; struct sk_buff_head sk_write_queue; __s32 sk_peek_off; int sk_write_pending; @@ -1555,18 +1551,10 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) __sk_mem_reclaim(sk, 1 << 20); } -DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); - if (static_branch_unlikely(&tcp_tx_skb_cache_key) && - !sk->sk_tx_skb_cache && !skb_cloned(skb)) { - skb_ext_reset(skb); - skb_zcopy_clear(skb, true); - sk->sk_tx_skb_cache = skb; - return; - } __kfree_skb(skb); } @@ -2576,7 +2564,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2588,12 +2575,6 @@ DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); - if (static_branch_unlikely(&tcp_rx_skb_cache_key) && - !sk->sk_rx_skb_cache) { - sk->sk_rx_skb_cache = skb; - skb_orphan(skb); - return; - } __kfree_skb(skb); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 3166dc15d7d634..32cf6c01f40336 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -330,8 +330,6 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags); -struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, - struct page *page, int offset, size_t *size); ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); @@ -581,6 +579,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ +void tcp_skb_entail(struct sock *sk, struct sk_buff *skb); +void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb); void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle); int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs); @@ -874,10 +874,11 @@ struct tcp_skb_cb { __u32 ack_seq; /* Sequence number ACK'd */ union { struct { +#define TCPCB_DELIVERED_CE_MASK ((1U<<20) - 1) /* There is space for up to 24 bytes */ - __u32 in_flight:30,/* Bytes in flight at transmit */ - is_app_limited:1, /* cwnd not fully used? */ - unused:1; + __u32 is_app_limited:1, /* cwnd not fully used? */ + delivered_ce:20, + unused:11; /* pkts S/ACKed so far upon tx of skb, incl retrans: */ __u32 delivered; /* start of send pipeline phase */ @@ -1029,7 +1030,9 @@ struct ack_sample { struct rate_sample { u64 prior_mstamp; /* starting timestamp for interval */ u32 prior_delivered; /* tp->delivered at "prior_mstamp" */ + u32 prior_delivered_ce;/* tp->delivered_ce at "prior_mstamp" */ s32 delivered; /* number of packets delivered over interval */ + s32 delivered_ce; /* number of packets delivered w/ CE marks*/ long interval_us; /* time for tp->delivered to incr "delivered" */ u32 snd_interval_us; /* snd interval for delivered packets */ u32 rcv_interval_us; /* rcv interval for delivered packets */ diff --git a/include/net/tls.h b/include/net/tls.h index be4b3e1cac4622..b6d40642afdd11 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -66,7 +66,7 @@ #define MAX_IV_SIZE 16 #define TLS_MAX_REC_SEQ_SIZE 8 -/* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. +/* For CCM mode, the full 16-bytes of IV is made of '4' fields of given sizes. * * IV[16] = b0[1] || implicit nonce[4] || explicit nonce[8] || length[3] * @@ -74,6 +74,7 @@ * Hence b0 contains (3 - 1) = 2. */ #define TLS_AES_CCM_IV_B0_BYTE 2 +#define TLS_SM4_CCM_IV_B0_BYTE 2 #define __TLS_INC_STATS(net, field) \ __SNMP_INC_STATS((net)->mib.tls_statistics, field) diff --git a/include/trace/events/mctp.h b/include/trace/events/mctp.h new file mode 100644 index 00000000000000..175b057c507fd3 --- /dev/null +++ b/include/trace/events/mctp.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mctp + +#if !defined(_TRACE_MCTP_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MCTP_H + +#include <linux/tracepoint.h> + +#ifndef __TRACE_MCTP_ENUMS +#define __TRACE_MCTP_ENUMS +enum { + MCTP_TRACE_KEY_TIMEOUT, + MCTP_TRACE_KEY_REPLIED, + MCTP_TRACE_KEY_INVALIDATED, + MCTP_TRACE_KEY_CLOSED, +}; +#endif /* __TRACE_MCTP_ENUMS */ + +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_TIMEOUT); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_REPLIED); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_INVALIDATED); +TRACE_DEFINE_ENUM(MCTP_TRACE_KEY_CLOSED); + +TRACE_EVENT(mctp_key_acquire, + TP_PROTO(const struct mctp_sk_key *key), + TP_ARGS(key), + TP_STRUCT__entry( + __field(__u8, paddr) + __field(__u8, laddr) + __field(__u8, tag) + ), + TP_fast_assign( + __entry->paddr = key->peer_addr; + __entry->laddr = key->local_addr; + __entry->tag = key->tag; + ), + TP_printk("local %d, peer %d, tag %1x", + __entry->laddr, + __entry->paddr, + __entry->tag + ) +); + +TRACE_EVENT(mctp_key_release, + TP_PROTO(const struct mctp_sk_key *key, int reason), + TP_ARGS(key, reason), + TP_STRUCT__entry( + __field(__u8, paddr) + __field(__u8, laddr) + __field(__u8, tag) + __field(int, reason) + ), + TP_fast_assign( + __entry->paddr = key->peer_addr; + __entry->laddr = key->local_addr; + __entry->tag = key->tag; + __entry->reason = reason; + ), + TP_printk("local %d, peer %d, tag %1x %s", + __entry->laddr, + __entry->paddr, + __entry->tag, + __print_symbolic(__entry->reason, + { MCTP_TRACE_KEY_TIMEOUT, "timeout" }, + { MCTP_TRACE_KEY_REPLIED, "replied" }, + { MCTP_TRACE_KEY_INVALIDATED, "invalidated" }, + { MCTP_TRACE_KEY_CLOSED, "closed" }) + ) +); + +#endif + +#include <trace/define_trace.h> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 791f31dd0abee7..3e9785f1064a23 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5284,6 +5306,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index d27b1708efe919..642b6ecb37d7ec 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -56,25 +56,29 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -170,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f66038b9551fa0..c8cc46f80a1619 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -4,6 +4,13 @@ #include <linux/const.h> #include <linux/types.h> +#include <linux/in.h> /* for sockaddr_in */ +#include <linux/in6.h> /* for sockaddr_in6 */ +#include <linux/socket.h> /* for sockaddr_storage and sa_family */ + +#ifndef __KERNEL__ +#include <sys/socket.h> /* for struct sockaddr */ +#endif #define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) #define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) @@ -193,4 +200,32 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + +/* MPTCP socket options */ +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 + #endif /* _UAPI_MPTCP_H */ diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 0f7f87c70baf59..b175bd0165a101 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -38,6 +38,9 @@ enum { /* SMC PNET Table commands */ #define SMC_GENL_FAMILY_VERSION 1 #define SMC_PCI_ID_STR_LEN 16 /* Max length of pci id string */ +#define SMC_MAX_HOSTNAME_LEN 32 /* Max length of the hostname */ +#define SMC_MAX_UEID 4 /* Max number of user EIDs */ +#define SMC_MAX_EID_LEN 32 /* Max length of an EID */ /* SMC_GENL_FAMILY commands */ enum { @@ -49,6 +52,13 @@ enum { SMC_NETLINK_GET_DEV_SMCR, SMC_NETLINK_GET_STATS, SMC_NETLINK_GET_FBACK_STATS, + SMC_NETLINK_DUMP_UEID, + SMC_NETLINK_ADD_UEID, + SMC_NETLINK_REMOVE_UEID, + SMC_NETLINK_FLUSH_UEID, + SMC_NETLINK_DUMP_SEID, + SMC_NETLINK_ENABLE_SEID, + SMC_NETLINK_DISABLE_SEID, }; /* SMC_GENL_FAMILY top level attributes */ @@ -242,4 +252,21 @@ enum { __SMC_NLA_FBACK_STATS_MAX, SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1 }; + +/* SMC_NETLINK_UEID attributes */ +enum { + SMC_NLA_EID_TABLE_UNSPEC, + SMC_NLA_EID_TABLE_ENTRY, /* string */ + __SMC_NLA_EID_TABLE_MAX, + SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1 +}; + +/* SMC_NETLINK_SEID attributes */ +enum { + SMC_NLA_SEID_UNSPEC, + SMC_NLA_SEID_ENTRY, /* string */ + SMC_NLA_SEID_ENABLED, /* u8 */ + __SMC_NLA_SEID_TABLE_MAX, + SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 0d54baea1d8dbe..5f38be0ec0f31a 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -84,6 +84,20 @@ #define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16 #define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8 +#define TLS_CIPHER_SM4_GCM 55 +#define TLS_CIPHER_SM4_GCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_GCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_GCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_GCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE 8 + +#define TLS_CIPHER_SM4_CCM 56 +#define TLS_CIPHER_SM4_CCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_CCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_CCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_CCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -124,6 +138,22 @@ struct tls12_crypto_info_chacha20_poly1305 { unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_sm4_gcm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_GCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_GCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_GCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE]; +}; + +struct tls12_crypto_info_sm4_ccm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_CCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_CCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_CCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE]; +}; + enum { TLS_INFO_UNSPEC, TLS_INFO_VERSION, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dfe61df4f974d1..c3d605b2247390 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,6 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -459,6 +460,17 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } +static bool btf_type_is_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; +} + +static bool btf_type_is_tag_target(const struct btf_type *t) +{ + return btf_type_is_func(t) || btf_type_is_struct(t) || + btf_type_is_var(t); +} + u32 btf_nr_types(const struct btf *btf) { u32 total = 0; @@ -537,6 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -563,6 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -616,6 +630,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } +static const struct btf_tag *btf_type_tag(const struct btf_type *t) +{ + return (const struct btf_tag *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -3801,6 +3820,110 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; +static s32 btf_tag_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_tag *tag; + u32 meta_needed = sizeof(*tag); + s32 component_idx; + const char *value; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid value"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx < -1) { + btf_verifier_log_type(env, t, "Invalid component_idx"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_tag_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + s32 component_idx; + u32 vlen; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || !btf_type_is_tag_target(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx != -1) { + if (btf_type_is_var(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + + if (btf_type_is_struct(next_type)) { + vlen = btf_type_vlen(next_type); + } else { + /* next_type should be a function */ + next_type = btf_type_by_id(btf, next_type->type); + vlen = btf_type_vlen(next_type); + } + + if ((u32)component_idx >= vlen) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + btf_verifier_log(env, "type=%u component_idx=%d", t->type, + btf_type_tag(t)->component_idx); +} + +static const struct btf_kind_operations tag_ops = { + .check_meta = btf_tag_check_meta, + .resolve = btf_tag_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_tag_log, + .show = btf_df_show, +}; + static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { @@ -3935,6 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, + [BTF_KIND_TAG] = &tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4019,6 +4143,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); + if (btf_type_is_tag(t)) + return btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); + if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index fe1e857324e668..39eaaff81953da 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -10,6 +10,7 @@ #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #include <linux/module.h> +#include <linux/static_call.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -526,7 +527,7 @@ out: } #define NO_START_TIME 1 -static u64 notrace bpf_prog_start_time(void) +static __always_inline u64 notrace bpf_prog_start_time(void) { u64 start = NO_START_TIME; diff --git a/kernel/events/core.c b/kernel/events/core.c index 0c000cb01eeb15..20367196fa9a37 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13435,3 +13435,5 @@ struct cgroup_subsys perf_event_cgrp_subsys = { .threaded = true, }; #endif /* CONFIG_CGROUP_PERF */ + +DEFINE_STATIC_CALL_RET0(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8e2eb950aa8297..067e88c3d2ee59 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1017,6 +1017,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + u32 entry_cnt = size / br_entry_size; + + entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); + + if (unlikely(flags)) + return -EINVAL; + + if (!entry_cnt) + return -ENOENT; + + return entry_cnt * br_entry_size; +#endif +} + +static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { + .func = bpf_get_branch_snapshot, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1132,6 +1160,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_snprintf_proto; case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; + case BPF_FUNC_get_branch_snapshot: + return &bpf_get_branch_snapshot_proto; default: return bpf_base_func_proto(func_id); } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 830a18ecffc887..0018d51b93b0a3 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -8800,6 +8800,7 @@ static __init struct sk_buff *build_test_skb(void) skb_shinfo(skb[0])->gso_type |= SKB_GSO_DODGY; skb_shinfo(skb[0])->gso_segs = 0; skb_shinfo(skb[0])->frag_list = skb[1]; + skb_shinfo(skb[0])->hwtstamps.hwtstamp = 1000; /* adjust skb[0]'s len */ skb[0]->len += skb[1]->len; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index b5f4ef35357c80..bf1cb629f61891 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -483,11 +483,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) return -EINVAL; /* priority is allowed */ - - if (!range_is_zero(__skb, offsetofend(struct __sk_buff, priority), - offsetof(struct __sk_buff, ifindex))) - return -EINVAL; - + /* ingress_ifindex is allowed */ /* ifindex is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, ifindex), @@ -511,11 +507,18 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) /* gso_size is allowed */ if (!range_is_zero(__skb, offsetofend(struct __sk_buff, gso_size), + offsetof(struct __sk_buff, hwtstamp))) + return -EINVAL; + + /* hwtstamp is allowed */ + + if (!range_is_zero(__skb, offsetofend(struct __sk_buff, hwtstamp), sizeof(struct __sk_buff))) return -EINVAL; skb->mark = __skb->mark; skb->priority = __skb->priority; + skb->skb_iif = __skb->ingress_ifindex; skb->tstamp = __skb->tstamp; memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN); @@ -532,6 +535,7 @@ static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb) return -EINVAL; skb_shinfo(skb)->gso_segs = __skb->gso_segs; skb_shinfo(skb)->gso_size = __skb->gso_size; + skb_shinfo(skb)->hwtstamps.hwtstamp = __skb->hwtstamp; return 0; } @@ -545,11 +549,13 @@ static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb) __skb->mark = skb->mark; __skb->priority = skb->priority; + __skb->ingress_ifindex = skb->skb_iif; __skb->ifindex = skb->dev->ifindex; __skb->tstamp = skb->tstamp; memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN); __skb->wire_len = cb->pkt_len; __skb->gso_segs = skb_shinfo(skb)->gso_segs; + __skb->hwtstamp = skb_shinfo(skb)->hwtstamps.hwtstamp; } static struct proto bpf_dummy_proto = { diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index 793b0db9d9a36f..49c268871fc11b 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -71,7 +71,8 @@ static int get_fdb_entries(struct net_bridge *br, void __user *userbuf, num = br_fdb_fillbuf(br, buf, maxnum, offset); if (num > 0) { - if (copy_to_user(userbuf, buf, num*sizeof(struct __fdb_entry))) + if (copy_to_user(userbuf, buf, + array_size(num, sizeof(struct __fdb_entry)))) num = -EFAULT; } kfree(buf); @@ -188,7 +189,7 @@ int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq, void __user return -ENOMEM; get_port_ifindices(br, indices, num); - if (copy_to_user(argp, indices, num * sizeof(int))) + if (copy_to_user(argp, indices, array_size(num, sizeof(int)))) num = -EFAULT; kfree(indices); return num; @@ -336,7 +337,8 @@ static int old_deviceless(struct net *net, void __user *uarg) args[2] = get_bridge_ifindices(net, indices, args[2]); - ret = copy_to_user(uarg, indices, args[2]*sizeof(int)) + ret = copy_to_user(uarg, indices, + array_size(args[2], sizeof(int))) ? -EFAULT : args[2]; kfree(indices); diff --git a/net/core/dev.c b/net/core/dev.c index 7ee9fecd3affc4..fa989ab63f29cb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2921,6 +2921,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); + dev_qdisc_change_real_num_tx(dev, txq); + dev->real_num_tx_queues = txq; if (disabling) { @@ -6898,19 +6900,25 @@ EXPORT_SYMBOL(netif_napi_add); void napi_disable(struct napi_struct *n) { + unsigned long val, new; + might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); - while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) - msleep(1); + do { + val = READ_ONCE(n->state); + if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { + usleep_range(20, 200); + continue; + } + + new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; + new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); + } while (cmpxchg(&n->state, val, new) != val); hrtimer_cancel(&n->timer); - clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state); - clear_bit(NAPI_STATE_THREADED, &n->state); } EXPORT_SYMBOL(napi_disable); diff --git a/net/core/devlink.c b/net/core/devlink.c index a856ae401ea5c1..b64303085d0e9c 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -742,6 +742,7 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) int err; WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -1040,11 +1041,15 @@ nla_put_failure: static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { + struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -1055,19 +1060,22 @@ static void devlink_port_notify(struct devlink_port *devlink_port, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(devlink_port->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static void devlink_rate_notify(struct devlink_rate *devlink_rate, enum devlink_command cmd) { + struct devlink *devlink = devlink_rate->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -1078,9 +1086,8 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(devlink_rate->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, @@ -4150,6 +4157,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -5145,17 +5153,19 @@ static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { + struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(region->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } /** @@ -6269,23 +6279,21 @@ static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, return 0; } -int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } -EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); -int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } -EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { @@ -6296,14 +6304,13 @@ int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); -int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } -EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { @@ -6923,10 +6930,12 @@ genlmsg_cancel: static void devlink_recover_notify(struct devlink_health_reporter *reporter, enum devlink_command cmd) { + struct devlink *devlink = reporter->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -6938,9 +6947,8 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(reporter->devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } void @@ -8958,18 +8966,95 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, } EXPORT_SYMBOL_GPL(devlink_alloc_ns); +static void +devlink_trap_policer_notify(struct devlink *devlink, + const struct devlink_trap_policer_item *policer_item, + enum devlink_command cmd); +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd); +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd); + +static void devlink_notify_register(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_rate *rate_node; + struct devlink_region *region; + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + + list_for_each_entry(policer_item, &devlink->trap_policer_list, list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW); + + list_for_each_entry(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + list_for_each_entry(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + list_for_each_entry(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + + list_for_each_entry(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + devlink_params_publish(devlink); +} + +static void devlink_notify_unregister(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_rate *rate_node; + struct devlink_region *region; + + devlink_params_unpublish(devlink); + + list_for_each_entry_reverse(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); + + list_for_each_entry_reverse(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + + list_for_each_entry_reverse(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + + list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list, + list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_DEL); + + list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); +} + /** * devlink_register - Register devlink instance * * @devlink: devlink */ -int devlink_register(struct devlink *devlink) +void devlink_register(struct devlink *devlink) { mutex_lock(&devlink_mutex); xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - devlink_notify(devlink, DEVLINK_CMD_NEW); + devlink_notify_register(devlink); mutex_unlock(&devlink_mutex); - return 0; } EXPORT_SYMBOL_GPL(devlink_register); @@ -8986,7 +9071,7 @@ void devlink_unregister(struct devlink *devlink) mutex_lock(&devlink_mutex); WARN_ON(devlink_reload_supported(devlink->ops) && devlink->reload_enabled); - devlink_notify(devlink, DEVLINK_CMD_DEL); + devlink_notify_unregister(devlink); xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); mutex_unlock(&devlink_mutex); } @@ -10090,6 +10175,9 @@ void devlink_params_publish(struct devlink *devlink) { struct devlink_param_item *param_item; + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + list_for_each_entry(param_item, &devlink->param_list, list) { if (param_item->published) continue; @@ -10122,102 +10210,25 @@ void devlink_params_unpublish(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_params_unpublish); /** - * devlink_param_publish - publish one configuration parameter - * - * @devlink: devlink - * @param: one configuration parameter - * - * Publish previously registered configuration parameter. - */ -void devlink_param_publish(struct devlink *devlink, - const struct devlink_param *param) -{ - struct devlink_param_item *param_item; - - list_for_each_entry(param_item, &devlink->param_list, list) { - if (param_item->param != param || param_item->published) - continue; - param_item->published = true; - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_NEW); - break; - } -} -EXPORT_SYMBOL_GPL(devlink_param_publish); - -/** - * devlink_param_unpublish - unpublish one configuration parameter + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing * - * @devlink: devlink - * @param: one configuration parameter + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode * - * Unpublish previously registered configuration parameter. + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. */ -void devlink_param_unpublish(struct devlink *devlink, - const struct devlink_param *param) +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) { struct devlink_param_item *param_item; - list_for_each_entry(param_item, &devlink->param_list, list) { - if (param_item->param != param || !param_item->published) - continue; - param_item->published = false; - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_DEL); - break; - } -} -EXPORT_SYMBOL_GPL(devlink_param_unpublish); - -/** - * devlink_port_params_register - register port configuration parameters - * - * @devlink_port: devlink port - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the port. - */ -int devlink_port_params_register(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ - return __devlink_params_register(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, params, - params_count, - DEVLINK_CMD_PORT_PARAM_NEW, - DEVLINK_CMD_PORT_PARAM_DEL); -} -EXPORT_SYMBOL_GPL(devlink_port_params_register); - -/** - * devlink_port_params_unregister - unregister port configuration - * parameters - * - * @devlink_port: devlink port - * @params: configuration parameters array - * @params_count: number of parameters provided - */ -void devlink_port_params_unregister(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ - return __devlink_params_unregister(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, - params, params_count, - DEVLINK_CMD_PORT_PARAM_DEL); -} -EXPORT_SYMBOL_GPL(devlink_port_params_unregister); - -static int -__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, - union devlink_param_value *init_val) -{ - struct devlink_param_item *param_item; + if (!devlink_reload_supported(devlink->ops)) + return -EOPNOTSUPP; - param_item = devlink_param_find_by_id(param_list, param_id); + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); if (!param_item) return -EINVAL; @@ -10233,54 +10244,6 @@ __devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, return 0; } - -static int -__devlink_param_driverinit_value_set(struct devlink *devlink, - unsigned int port_index, - struct list_head *param_list, u32 param_id, - union devlink_param_value init_val, - enum devlink_command cmd) -{ - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(param_list, param_id); - if (!param_item) - return -EINVAL; - - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) - return -EOPNOTSUPP; - - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; - - devlink_param_notify(devlink, port_index, param_item, cmd); - return 0; -} - -/** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) -{ - if (!devlink_reload_supported(devlink->ops)) - return -EOPNOTSUPP; - - return __devlink_param_driverinit_value_get(&devlink->param_list, - param_id, init_val); -} EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); /** @@ -10298,61 +10261,26 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - return __devlink_param_driverinit_value_set(devlink, 0, - &devlink->param_list, - param_id, init_val, - DEVLINK_CMD_PARAM_NEW); -} -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); + struct devlink_param_item *param_item; -/** - * devlink_port_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value *init_val) -{ - struct devlink *devlink = devlink_port->devlink; + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; - if (!devlink_reload_supported(devlink->ops)) + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - return __devlink_param_driverinit_value_get(&devlink_port->param_list, - param_id, init_val); -} -EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; -/** - * devlink_port_param_driverinit_value_set - set value of configuration - * parameter for driverinit - * configuration mode - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * @init_val: value of parameter to set for driverinit configuration mode - * - * This function should be used by the driver to set driverinit - * configuration mode default value. - */ -int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value init_val) -{ - return __devlink_param_driverinit_value_set(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, - param_id, init_val, - DEVLINK_CMD_PORT_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); + return 0; } -EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); /** * devlink_param_value_changed - notify devlink on a parameter's value @@ -10378,50 +10306,6 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** - * devlink_port_param_value_changed - notify devlink on a parameter's value - * change. Should be called by the driver - * right after the change. - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * - * This function should be used by the driver to notify devlink on value - * change, excluding driverinit configuration mode. - * For driverinit configuration mode driver should use the function - * devlink_port_param_driverinit_value_set() instead. - */ -void devlink_port_param_value_changed(struct devlink_port *devlink_port, - u32 param_id) -{ - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(&devlink_port->param_list, - param_id); - WARN_ON(!param_item); - - devlink_param_notify(devlink_port->devlink, devlink_port->index, - param_item, DEVLINK_CMD_PORT_PARAM_NEW); -} -EXPORT_SYMBOL_GPL(devlink_port_param_value_changed); - -/** - * devlink_param_value_str_fill - Safely fill-up the string preventing - * from overflow of the preallocated buffer - * - * @dst_val: destination devlink_param_value - * @src: source buffer - */ -void devlink_param_value_str_fill(union devlink_param_value *dst_val, - const char *src) -{ - size_t len; - - len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE); - WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE); -} -EXPORT_SYMBOL_GPL(devlink_param_value_str_fill); - -/** * devlink_region_create - create a new address region * * @devlink: devlink @@ -10839,6 +10723,8 @@ devlink_trap_group_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && cmd != DEVLINK_CMD_TRAP_GROUP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -10880,6 +10766,8 @@ static void devlink_trap_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && cmd != DEVLINK_CMD_TRAP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -11261,6 +11149,8 @@ devlink_trap_policer_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW && cmd != DEVLINK_CMD_TRAP_POLICER_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) diff --git a/net/core/filter.c b/net/core/filter.c index 2e32cee2c46900..4bace37a6a4495 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7765,6 +7765,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; + case bpf_ctx_range(struct __sk_buff, hwtstamp): + if (type == BPF_WRITE || size != sizeof(__u64)) + return false; + break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -7774,6 +7778,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; + case offsetofend(struct __sk_buff, gso_size) ... offsetof(struct __sk_buff, hwtstamp) - 1: + /* Explicitly prohibit access to padding in __sk_buff. */ + return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -7802,6 +7809,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -7872,6 +7880,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8373,6 +8382,7 @@ static bool sk_skb_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8884,6 +8894,17 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; + case offsetof(struct __sk_buff, hwtstamp): + BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); + BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); + + insn = bpf_convert_shinfo_access(si, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + break; } return insn - insn_buf; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a448a9b5bb2d6c..202fa5eacd0f9b 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -473,7 +473,9 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) { put_userns: +#ifdef CONFIG_KEYS key_remove_domain(net->key_domain); +#endif put_user_ns(user_ns); net_free(net); dec_ucounts: @@ -605,7 +607,9 @@ static void cleanup_net(struct work_struct *work) list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); +#ifdef CONFIG_KEYS key_remove_domain(net->key_domain); +#endif put_user_ns(net->user_ns); net_free(net); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 972c8cb303a514..327ca6bc6e6de6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -301,7 +301,7 @@ int rtnl_unregister(int protocol, int msgtype) } link = rtnl_dereference(tab[msgindex]); - rcu_assign_pointer(tab[msgindex], NULL); + RCU_INIT_POINTER(tab[msgindex], NULL); rtnl_unlock(); kfree_rcu(link, rcu); @@ -337,7 +337,7 @@ void rtnl_unregister_all(int protocol) if (!link) continue; - rcu_assign_pointer(tab[msgindex], NULL); + RCU_INIT_POINTER(tab[msgindex], NULL); kfree_rcu(link, rcu); } rtnl_unlock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2170bea2c7de72..74601bbc56ac17 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -134,34 +134,31 @@ struct napi_alloc_cache { static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); -static void *__alloc_frag_align(unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align_mask); -} - -void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) -{ fragsz = SKB_DATA_ALIGN(fragsz); - return __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); + return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { - struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { - nc = this_cpu_ptr(&netdev_alloc_cache); + struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { + struct napi_alloc_cache *nc; + local_bh_disable(); - data = __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); + nc = this_cpu_ptr(&napi_alloc_cache); + data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); local_bh_enable(); } return data; @@ -397,8 +394,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - u8 *data; + unsigned int osize; bool pfmemalloc; + u8 *data; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; @@ -430,7 +428,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(ksize(data)); + osize = ksize(data); + size = SKB_WITH_OVERHEAD(osize); prefetchw(data + size); /* @@ -439,7 +438,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, 0); + __build_skb_around(skb, data, osize); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 54828553975236..bca1b5d66df229 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -138,7 +138,6 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - depends on NET_DSA_SJA1105 || !NET_DSA_SJA1105 select PACKING help Say Y or M if you want to enable support for tagging frames with the diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index b29262eee00bf3..8ca6a1170c9d02 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -848,10 +848,6 @@ static int dsa_switch_setup(struct dsa_switch *ds) dl_priv = devlink_priv(ds->devlink); dl_priv->ds = ds; - err = devlink_register(ds->devlink); - if (err) - goto free_devlink; - /* Setup devlink port instances now, so that the switch * setup() can register regions etc, against the ports */ @@ -877,8 +873,6 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto teardown; - devlink_params_publish(ds->devlink); - if (!ds->slave_mii_bus && ds->ops->phy_read) { ds->slave_mii_bus = mdiobus_alloc(); if (!ds->slave_mii_bus) { @@ -894,7 +888,7 @@ static int dsa_switch_setup(struct dsa_switch *ds) } ds->setup = true; - + devlink_register(ds->devlink); return 0; free_slave_mii_bus: @@ -909,11 +903,8 @@ unregister_devlink_ports: list_for_each_entry(dp, &ds->dst->ports, list) if (dp->ds == ds) dsa_port_devlink_teardown(dp); - devlink_unregister(ds->devlink); -free_devlink: devlink_free(ds->devlink); ds->devlink = NULL; - return err; } @@ -924,6 +915,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds) if (!ds->setup) return; + if (ds->devlink) + devlink_unregister(ds->devlink); + if (ds->slave_mii_bus && ds->ops->phy_read) { mdiobus_unregister(ds->slave_mii_bus); mdiobus_free(ds->slave_mii_bus); @@ -939,7 +933,6 @@ static void dsa_switch_teardown(struct dsa_switch *ds) list_for_each_entry(dp, &ds->dst->ports, list) if (dp->ds == ds) dsa_port_devlink_teardown(dp); - devlink_unregister(ds->devlink); devlink_free(ds->devlink); ds->devlink = NULL; } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index f8f7b7c34e7da3..935d0264ebd8ef 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -6,7 +6,6 @@ * dsa_8021q_netdev_ops is registered for API compliance and not used * directly by callers. */ -#include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/dsa/8021q.h> diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index fa1d60d13ad903..3509fc967ca9d6 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -6,7 +6,6 @@ #include <linux/etherdevice.h> #include <linux/list.h> -#include <linux/slab.h> #include <net/dsa.h> #include "dsa_priv.h" diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index f920487ae1458e..6d928ee3ef7a2f 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -54,7 +54,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, p = (__be16 *)tag; *p = htons(RTL4_A_ETHERTYPE); - out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT) | (2 << 8); + out = (RTL4_A_PROTOCOL_RTL8366RB << RTL4_A_PROTOCOL_SHIFT); /* The lower bits indicate the port number */ out |= BIT(dp->index); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index c054f48541c8d6..2edede9ddac93b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -4,6 +4,7 @@ #include <linux/if_vlan.h> #include <linux/dsa/sja1105.h> #include <linux/dsa/8021q.h> +#include <linux/skbuff.h> #include <linux/packing.h> #include "dsa_priv.h" @@ -53,6 +54,11 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -520,6 +526,43 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct dsa_port *dp = dsa_to_port(ds, port); + struct skb_shared_hwtstamps shwt = {0}; + struct sja1105_port *sp = dp->priv; + + if (!dsa_port_is_sja1105(dp)) + return; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&sp->data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&sp->data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &sp->data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&sp->data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} + static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) { u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index f2abc315288839..bf6e8c2f9bf738 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -89,7 +89,8 @@ static int ethtool_get_features(struct net_device *dev, void __user *useraddr) if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; useraddr += sizeof(cmd); - if (copy_to_user(useraddr, features, copy_size * sizeof(*features))) + if (copy_to_user(useraddr, features, + array_size(copy_size, sizeof(*features)))) return -EFAULT; return 0; @@ -799,7 +800,7 @@ static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, goto out; useraddr += offsetof(struct ethtool_sset_info, data); - if (copy_to_user(useraddr, info_buf, idx * sizeof(u32))) + if (copy_to_user(useraddr, info_buf, array_size(idx, sizeof(u32)))) goto out; ret = 0; @@ -1022,7 +1023,7 @@ static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, { int i; - if (copy_from_user(indir, useraddr, size * sizeof(indir[0]))) + if (copy_from_user(indir, useraddr, array_size(size, sizeof(indir[0])))) return -EFAULT; /* Validate ring indices */ @@ -1537,6 +1538,10 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, ret = getter(dev, &eeprom, data); if (ret) break; + if (!eeprom.len) { + ret = -EIO; + break; + } if (copy_to_user(userbuf, data, eeprom.len)) { ret = -EFAULT; break; @@ -1891,7 +1896,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) if (copy_to_user(useraddr, &test, sizeof(test))) goto out; useraddr += sizeof(test); - if (copy_to_user(useraddr, data, test.len * sizeof(u64))) + if (copy_to_user(useraddr, data, array_size(test.len, sizeof(u64)))) goto out; ret = 0; @@ -1933,7 +1938,8 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) goto out; useraddr += sizeof(gstrings); if (gstrings.len && - copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + copy_to_user(useraddr, data, + array_size(gstrings.len, ETH_GSTRING_LEN))) goto out; ret = 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1d816a5fd3eb91..40558033f857c0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -133,10 +133,6 @@ void inet_sock_destruct(struct sock *sk) struct inet_sock *inet = inet_sk(sk); __skb_queue_purge(&sk->sk_receive_queue); - if (sk->sk_rx_skb_cache) { - __kfree_skb(sk->sk_rx_skb_cache); - sk->sk_rx_skb_cache = NULL; - } __skb_queue_purge(&sk->sk_error_queue); sk_mem_reclaim(sk); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 099259fc826aa2..62d5f99760aacd 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -73,7 +73,7 @@ struct cipso_v4_map_cache_entry { static struct cipso_v4_map_cache_bkt *cipso_v4_cache; /* Restricted bitmap (tag #1) flags */ -int cipso_v4_rbm_optfmt = 0; +int cipso_v4_rbm_optfmt; int cipso_v4_rbm_strictvalid = 1; /* diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 4a8550c49202db..48f337ccf94951 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -9,7 +9,6 @@ #include <linux/types.h> #include <linux/module.h> -#include <linux/ip.h> #include <linux/in.h> #include <net/ip.h> #include <net/sock.h> diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index 0c28bd469a6810..0e23ade74493ce 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -6,7 +6,6 @@ #include <linux/export.h> #include <net/net_namespace.h> #include <net/fib_notifier.h> -#include <net/netns/ipv4.h> #include <net/ip_fib.h> int call_fib4_notifier(struct notifier_block *nb, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d6899ab5fb39b3..0b4103b1e6220f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -61,15 +61,11 @@ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> -#include <linux/uaccess.h> #include <linux/bitops.h> -#include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> -#include <linux/string.h> #include <linux/socket.h> -#include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> @@ -84,20 +80,17 @@ #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> -#include <linux/times.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/net_namespace.h> -#include <net/protocol.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> -#include <net/arp.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> @@ -109,7 +102,6 @@ #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> -#include <net/l3mdev.h> #include "fib_lookup.h" diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 33792cf55a7934..8696dc343ad2cd 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -7,8 +7,6 @@ */ #include <linux/tcp.h> -#include <linux/slab.h> -#include <linux/random.h> #include <linux/siphash.h> #include <linux/kernel.h> #include <linux/export.h> diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 6f1e64d4923287..97eb5477492447 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -6,25 +6,16 @@ * Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS] */ -#include <linux/mm.h> -#include <linux/module.h> #include <linux/sysctl.h> -#include <linux/igmp.h> -#include <linux/inetdevice.h> #include <linux/seqlock.h> #include <linux/init.h> #include <linux/slab.h> -#include <linux/nsproxy.h> -#include <linux/swap.h> -#include <net/snmp.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_fib.h> -#include <net/route.h> #include <net/tcp.h> #include <net/udp.h> #include <net/cipso_ipv4.h> -#include <net/inet_frag.h> #include <net/ping.h> #include <net/protocol.h> #include <net/netevent.h> @@ -594,18 +585,6 @@ static struct ctl_table ipv4_table[] = { .extra1 = &sysctl_fib_sync_mem_min, .extra2 = &sysctl_fib_sync_mem_max, }, - { - .procname = "tcp_rx_skb_cache", - .data = &tcp_rx_skb_cache_key.key, - .mode = 0644, - .proc_handler = proc_do_static_key, - }, - { - .procname = "tcp_tx_skb_cache", - .data = &tcp_tx_skb_cache_key.key, - .mode = 0644, - .proc_handler = proc_do_static_key, - }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e8b48df73c852a..414c179c28e0dd 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -325,11 +325,6 @@ struct tcp_splice_state { unsigned long tcp_memory_pressure __read_mostly; EXPORT_SYMBOL_GPL(tcp_memory_pressure); -DEFINE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); -EXPORT_SYMBOL(tcp_rx_skb_cache_key); - -DEFINE_STATIC_KEY_FALSE(tcp_tx_skb_cache_key); - void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; @@ -647,7 +642,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) } EXPORT_SYMBOL(tcp_ioctl); -static inline void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) +void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; tp->pushed_seq = tp->write_seq; @@ -658,7 +653,7 @@ static inline bool forced_push(const struct tcp_sock *tp) return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1)); } -static void skb_entail(struct sock *sk, struct sk_buff *skb) +void tcp_skb_entail(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); @@ -866,18 +861,6 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, { struct sk_buff *skb; - if (likely(!size)) { - skb = sk->sk_tx_skb_cache; - if (skb) { - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - sk->sk_tx_skb_cache = NULL; - pskb_trim(skb, 0); - INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); - skb_shinfo(skb)->tx_flags = 0; - memset(TCP_SKB_CB(skb), 0, sizeof(struct tcp_skb_cb)); - return skb; - } - } /* The TCP header must be at least 32-bit aligned. */ size = ALIGN(size, 4); @@ -963,8 +946,8 @@ void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) } } -struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, - struct page *page, int offset, size_t *size) +static struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, + struct page *page, int offset, size_t *size) { struct sk_buff *skb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -985,7 +968,7 @@ new_segment: #ifdef CONFIG_TLS_DEVICE skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED); #endif - skb_entail(sk, skb); + tcp_skb_entail(sk, skb); copy = size_goal; } @@ -1314,7 +1297,7 @@ new_segment: process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; - skb_entail(sk, skb); + tcp_skb_entail(sk, skb); copy = size_goal; /* All packets are restored as if they have @@ -2920,11 +2903,6 @@ void tcp_write_queue_purge(struct sock *sk) sk_wmem_free_skb(sk, skb); } tcp_rtx_queue_purge(sk); - skb = sk->sk_tx_skb_cache; - if (skb) { - __kfree_skb(skb); - sk->sk_tx_skb_cache = NULL; - } INIT_LIST_HEAD(&tcp_sk(sk)->tsorted_sent_queue); sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); @@ -2961,10 +2939,6 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); - if (sk->sk_rx_skb_cache) { - __kfree_skb(sk->sk_rx_skb_cache); - sk->sk_rx_skb_cache = NULL; - } WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 59412d6354a01a..fdbcf2a6d08ef4 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -1,13 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 -#include <linux/crypto.h> -#include <linux/err.h> -#include <linux/init.h> #include <linux/kernel.h> -#include <linux/list.h> #include <linux/tcp.h> #include <linux/rcupdate.h> -#include <linux/rculist.h> -#include <net/inetpeer.h> #include <net/tcp.h> void tcp_fastopen_init_key_once(struct net *net) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 141e85e6422b1f..53675e28484110 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3221,7 +3221,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, long seq_rtt_us = -1L; long ca_rtt_us = -1L; u32 pkts_acked = 0; - u32 last_in_flight = 0; bool rtt_update; int flag = 0; @@ -3257,7 +3256,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, if (!first_ackt) first_ackt = last_ackt; - last_in_flight = TCP_SKB_CB(skb)->tx.in_flight; if (before(start_seq, reord)) reord = start_seq; if (!after(scb->end_seq, tp->high_seq)) @@ -3323,8 +3321,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, seq_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, first_ackt); ca_rtt_us = tcp_stamp_us_delta(tp->tcp_mstamp, last_ackt); - if (pkts_acked == 1 && last_in_flight < tp->mss_cache && - last_in_flight && !prior_sacked && fully_acked && + if (pkts_acked == 1 && fully_acked && !prior_sacked && + (tp->snd_una - prior_snd_una) < tp->mss_cache && sack->rate->prior_delivered + 1 == tp->delivered && !(flag & (FLAG_CA_ALERT | FLAG_SYN_ACKED))) { /* Conservatively mark a delayed ACK. It's typically @@ -3381,9 +3379,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb, if (icsk->icsk_ca_ops->pkts_acked) { struct ack_sample sample = { .pkts_acked = pkts_acked, - .rtt_us = sack->rate->rtt_us, - .in_flight = last_in_flight }; + .rtt_us = sack->rate->rtt_us }; + sample.in_flight = tp->mss_cache * + (tp->delivered - sack->rate->prior_delivered); icsk->icsk_ca_ops->pkts_acked(sk, &sample); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2e62e0d6373a6e..29a57bd159f0aa 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1941,7 +1941,6 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); - struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; @@ -2082,17 +2081,12 @@ process: tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { - skb_to_free = sk->sk_rx_skb_cache; - sk->sk_rx_skb_cache = NULL; ret = tcp_v4_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb)) goto discard_and_relse; - skb_to_free = NULL; } bh_unlock_sock(sk); - if (skb_to_free) - __kfree_skb(skb_to_free); put_and_return: if (refcounted) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0a4f3f16140ad8..cf913a66df1702 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -19,14 +19,7 @@ * Jorge Cwik, <jorge@laser.satlink.net> */ -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/sysctl.h> -#include <linux/workqueue.h> -#include <linux/static_key.h> #include <net/tcp.h> -#include <net/inet_common.h> #include <net/xfrm.h> #include <net/busy_poll.h> diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c index 95db7a11ba2ada..ab552356bdba8f 100644 --- a/net/ipv4/tcp_nv.c +++ b/net/ipv4/tcp_nv.c @@ -25,7 +25,6 @@ * 1) Add mechanism to deal with reverse congestion. */ -#include <linux/mm.h> #include <linux/module.h> #include <linux/math64.h> #include <net/tcp.h> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6d72f3ea48c4ef..fdc39b4fbbfa0b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1256,8 +1256,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); skb->skb_mstamp_ns = tp->tcp_wstamp_ns; if (clone_it) { - TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - - tp->snd_una; oskb = skb; tcp_skb_tsorted_save(oskb) { diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index 0de6935659635f..fbab921670cc91 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -65,6 +65,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tx.first_tx_mstamp = tp->first_tx_mstamp; TCP_SKB_CB(skb)->tx.delivered_mstamp = tp->delivered_mstamp; TCP_SKB_CB(skb)->tx.delivered = tp->delivered; + TCP_SKB_CB(skb)->tx.delivered_ce = tp->delivered_ce; TCP_SKB_CB(skb)->tx.is_app_limited = tp->app_limited ? 1 : 0; } @@ -86,6 +87,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, if (!rs->prior_delivered || after(scb->tx.delivered, rs->prior_delivered)) { + rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; @@ -138,6 +140,10 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, } rs->delivered = tp->delivered - rs->prior_delivered; + rs->delivered_ce = tp->delivered_ce - rs->prior_delivered_ce; + /* delivered_ce occupies less than 32 bits in the skb control block */ + rs->delivered_ce &= TCPCB_DELIVERED_CE_MASK; + /* Model sending data and receiving ACKs as separate pipeline phases * for a window. Usually the ACK phase is longer, but with ACK * compression the send phase can be longer. To be safe we use the diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index b97e3635acf50b..8efaf8c3fe2a9a 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -2,11 +2,8 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> -#include <linux/udp.h> -#include <linux/types.h> #include <linux/kernel.h> #include <net/dst_metadata.h> -#include <net/net_namespace.h> #include <net/udp.h> #include <net/udp_tunnel.h> diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 1bc7e143217b4d..3036a45e8a1ecd 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -5,16 +5,14 @@ obj-$(CONFIG_IPV6) += ipv6.o -ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ +ipv6-y := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ addrlabel.o \ route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \ raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \ udp_offload.o seg6.o fib6_notifier.o rpl.o ioam6.o -ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o - -ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o +ipv6-$(CONFIG_SYSCTL) += sysctl_net_ipv6.o ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ @@ -29,8 +27,6 @@ ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o ipv6-$(CONFIG_IPV6_RPL_LWTUNNEL) += rpl_iptunnel.o ipv6-$(CONFIG_IPV6_IOAM6_LWTUNNEL) += ioam6_iptunnel.o -ipv6-objs += $(ipv6-y) - obj-$(CONFIG_INET6_AH) += ah6.o obj-$(CONFIG_INET6_ESP) += esp6.o obj-$(CONFIG_INET6_ESP_OFFLOAD) += esp6_offload.o @@ -48,7 +44,8 @@ obj-$(CONFIG_IPV6_GRE) += ip6_gre.o obj-$(CONFIG_IPV6_FOU) += fou6.o obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o -obj-$(CONFIG_INET) += output_core.o protocol.o $(ipv6-offload) +obj-$(CONFIG_INET) += output_core.o protocol.o \ + ip6_offload.o tcpv6_offload.o exthdrs_offload.o obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c index a1ac0e3d8c60c5..47447f0241df60 100644 --- a/net/ipv6/ila/ila_xlat.c +++ b/net/ipv6/ila/ila_xlat.c @@ -610,7 +610,11 @@ int ila_xlat_init_net(struct net *net) if (err) return err; - rhashtable_init(&ilan->xlat.rhash_table, &rht_params); + err = rhashtable_init(&ilan->xlat.rhash_table, &rht_params); + if (err) { + free_bucket_spinlocks(ilan->xlat.locks); + return err; + } return 0; } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index e412817fba2f32..65744f2d38da35 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -374,7 +374,11 @@ static int __net_init seg6_net_init(struct net *net) net->ipv6.seg6_data = sdata; #ifdef CONFIG_IPV6_SEG6_HMAC - seg6_hmac_net_init(net); + if (seg6_hmac_net_init(net)) { + kfree(sdata); + kfree(rcu_dereference_raw(sdata->tun_src)); + return -ENOMEM; + }; #endif return 0; @@ -388,7 +392,7 @@ static void __net_exit seg6_net_exit(struct net *net) seg6_hmac_net_exit(net); #endif - kfree(sdata->tun_src); + kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 687d95dce08522..29bc4e7c3046e2 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -405,9 +405,7 @@ int __net_init seg6_hmac_net_init(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); - rhashtable_init(&sdata->hmac_infos, &rht_params); - - return 0; + return rhashtable_init(&sdata->hmac_infos, &rht_params); } EXPORT_SYMBOL(seg6_hmac_net_init); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0ce52d46e4f81b..8cf5ff2e95043e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1618,7 +1618,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { - struct sk_buff *skb_to_free; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; @@ -1754,17 +1753,12 @@ process: tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { - skb_to_free = sk->sk_rx_skb_cache; - sk->sk_rx_skb_cache = NULL; ret = tcp_v6_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb)) goto discard_and_relse; - skb_to_free = NULL; } bh_unlock_sock(sk); - if (skb_to_free) - __kfree_skb(skb_to_free); put_and_return: if (refcounted) sock_put(sk); diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index a9526ac29dffec..66a411d60b6ce2 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -16,6 +16,9 @@ #include <net/mctpdevice.h> #include <net/sock.h> +#define CREATE_TRACE_POINTS +#include <trace/events/mctp.h> + /* socket implementation */ static int mctp_release(struct socket *sock) @@ -223,16 +226,61 @@ static const struct proto_ops mctp_dgram_ops = { .sendpage = sock_no_sendpage, }; +static void mctp_sk_expire_keys(struct timer_list *timer) +{ + struct mctp_sock *msk = container_of(timer, struct mctp_sock, + key_expiry); + struct net *net = sock_net(&msk->sk); + unsigned long next_expiry, flags; + struct mctp_sk_key *key; + struct hlist_node *tmp; + bool next_expiry_valid = false; + + spin_lock_irqsave(&net->mctp.keys_lock, flags); + + hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { + spin_lock(&key->lock); + + if (!time_after_eq(key->expiry, jiffies)) { + trace_mctp_key_release(key, MCTP_TRACE_KEY_TIMEOUT); + key->valid = false; + hlist_del_rcu(&key->hlist); + hlist_del_rcu(&key->sklist); + spin_unlock(&key->lock); + mctp_key_unref(key); + continue; + } + + if (next_expiry_valid) { + if (time_before(key->expiry, next_expiry)) + next_expiry = key->expiry; + } else { + next_expiry = key->expiry; + next_expiry_valid = true; + } + spin_unlock(&key->lock); + } + + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + if (next_expiry_valid) + mod_timer(timer, next_expiry); +} + static int mctp_sk_init(struct sock *sk) { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); INIT_HLIST_HEAD(&msk->keys); + timer_setup(&msk->key_expiry, mctp_sk_expire_keys, 0); return 0; } static void mctp_sk_close(struct sock *sk, long timeout) { + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); + + del_timer_sync(&msk->key_expiry); sk_common_release(sk); } @@ -263,21 +311,23 @@ static void mctp_sk_unhash(struct sock *sk) /* remove tag allocations */ spin_lock_irqsave(&net->mctp.keys_lock, flags); hlist_for_each_entry_safe(key, tmp, &msk->keys, sklist) { - hlist_del_rcu(&key->sklist); - hlist_del_rcu(&key->hlist); + hlist_del(&key->sklist); + hlist_del(&key->hlist); - spin_lock(&key->reasm_lock); + trace_mctp_key_release(key, MCTP_TRACE_KEY_CLOSED); + + spin_lock(&key->lock); if (key->reasm_head) kfree_skb(key->reasm_head); key->reasm_head = NULL; key->reasm_dead = true; - spin_unlock(&key->reasm_lock); + key->valid = false; + spin_unlock(&key->lock); - kfree_rcu(key, rcu); + /* key is no longer on the lookup lists, unref */ + mctp_key_unref(key); } spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - - synchronize_rcu(); } static struct proto mctp_proto = { @@ -385,7 +435,7 @@ static __exit void mctp_exit(void) sock_unregister(PF_MCTP); } -module_init(mctp_init); +subsys_initcall(mctp_init); module_exit(mctp_exit); MODULE_DESCRIPTION("MCTP core"); diff --git a/net/mctp/device.c b/net/mctp/device.c index b9f38e765f6193..3827d62f52c9bf 100644 --- a/net/mctp/device.c +++ b/net/mctp/device.c @@ -35,14 +35,6 @@ struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->mctp_ptr); } -static void mctp_dev_destroy(struct mctp_dev *mdev) -{ - struct net_device *dev = mdev->dev; - - dev_put(dev); - kfree_rcu(mdev, rcu); -} - static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb, struct mctp_dev *mdev, mctp_eid_t eid) { @@ -255,6 +247,19 @@ static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } +void mctp_dev_hold(struct mctp_dev *mdev) +{ + refcount_inc(&mdev->refs); +} + +void mctp_dev_put(struct mctp_dev *mdev) +{ + if (refcount_dec_and_test(&mdev->refs)) { + dev_put(mdev->dev); + kfree_rcu(mdev, rcu); + } +} + static struct mctp_dev *mctp_add_dev(struct net_device *dev) { struct mctp_dev *mdev; @@ -270,7 +275,9 @@ static struct mctp_dev *mctp_add_dev(struct net_device *dev) mdev->net = mctp_default_net(dev_net(dev)); /* associate to net_device */ + refcount_set(&mdev->refs, 1); rcu_assign_pointer(dev->mctp_ptr, mdev); + dev_hold(dev); mdev->dev = dev; @@ -330,12 +337,26 @@ static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr, return 0; } +/* Matches netdev types that should have MCTP handling */ +static bool mctp_known(struct net_device *dev) +{ + /* only register specific types (inc. NONE for TUN devices) */ + return dev->type == ARPHRD_MCTP || + dev->type == ARPHRD_LOOPBACK || + dev->type == ARPHRD_NONE; +} + static void mctp_unregister(struct net_device *dev) { struct mctp_dev *mdev; mdev = mctp_dev_get_rtnl(dev); - + if (mctp_known(dev) != (bool)mdev) { + // Sanity check, should match what was set in mctp_register + netdev_warn(dev, "%s: mdev pointer %d but type (%d) match is %d", + __func__, (bool)mdev, mctp_known(dev), dev->type); + return; + } if (!mdev) return; @@ -345,7 +366,7 @@ static void mctp_unregister(struct net_device *dev) mctp_neigh_remove_dev(mdev); kfree(mdev->addrs); - mctp_dev_destroy(mdev); + mctp_dev_put(mdev); } static int mctp_register(struct net_device *dev) @@ -353,11 +374,17 @@ static int mctp_register(struct net_device *dev) struct mctp_dev *mdev; /* Already registered? */ - if (rtnl_dereference(dev->mctp_ptr)) + mdev = rtnl_dereference(dev->mctp_ptr); + + if (mdev) { + if (!mctp_known(dev)) + netdev_warn(dev, "%s: mctp_dev set for unknown type %d", + __func__, dev->type); return 0; + } - /* only register specific types; MCTP-specific and loopback for now */ - if (dev->type != ARPHRD_MCTP && dev->type != ARPHRD_LOOPBACK) + /* only register specific types */ + if (!mctp_known(dev)) return 0; mdev = mctp_add_dev(dev); diff --git a/net/mctp/neigh.c b/net/mctp/neigh.c index 90ed2f02d1fb02..5cc04212149383 100644 --- a/net/mctp/neigh.c +++ b/net/mctp/neigh.c @@ -47,7 +47,7 @@ static int mctp_neigh_add(struct mctp_dev *mdev, mctp_eid_t eid, } INIT_LIST_HEAD(&neigh->list); neigh->dev = mdev; - dev_hold(neigh->dev->dev); + mctp_dev_hold(neigh->dev); neigh->eid = eid; neigh->source = source; memcpy(neigh->ha, lladdr, lladdr_len); @@ -63,7 +63,7 @@ static void __mctp_neigh_free(struct rcu_head *rcu) { struct mctp_neigh *neigh = container_of(rcu, struct mctp_neigh, rcu); - dev_put(neigh->dev->dev); + mctp_dev_put(neigh->dev); kfree(neigh); } diff --git a/net/mctp/route.c b/net/mctp/route.c index 5ca186d53cb0f1..e20f3096d06723 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -23,7 +23,10 @@ #include <net/netlink.h> #include <net/sock.h> +#include <trace/events/mctp.h> + static const unsigned int mctp_message_maxlen = 64 * 1024; +static const unsigned long mctp_key_lifetime = 6 * CONFIG_HZ; /* route output callbacks */ static int mctp_route_discard(struct mctp_route *route, struct sk_buff *skb) @@ -83,25 +86,43 @@ static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local, return true; } +/* returns a key (with key->lock held, and refcounted), or NULL if no such + * key exists. + */ static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb, - mctp_eid_t peer) + mctp_eid_t peer, + unsigned long *irqflags) + __acquires(&key->lock) { struct mctp_sk_key *key, *ret; + unsigned long flags; struct mctp_hdr *mh; u8 tag; - WARN_ON(!rcu_read_lock_held()); - mh = mctp_hdr(skb); tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); ret = NULL; + spin_lock_irqsave(&net->mctp.keys_lock, flags); + + hlist_for_each_entry(key, &net->mctp.keys, hlist) { + if (!mctp_key_match(key, mh->dest, peer, tag)) + continue; - hlist_for_each_entry_rcu(key, &net->mctp.keys, hlist) { - if (mctp_key_match(key, mh->dest, peer, tag)) { + spin_lock(&key->lock); + if (key->valid) { + refcount_inc(&key->refs); ret = key; break; } + spin_unlock(&key->lock); + } + + if (ret) { + spin_unlock(&net->mctp.keys_lock); + *irqflags = flags; + } else { + spin_unlock_irqrestore(&net->mctp.keys_lock, flags); } return ret; @@ -121,11 +142,19 @@ static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk, key->local_addr = local; key->tag = tag; key->sk = &msk->sk; - spin_lock_init(&key->reasm_lock); + key->valid = true; + spin_lock_init(&key->lock); + refcount_set(&key->refs, 1); return key; } +void mctp_key_unref(struct mctp_sk_key *key) +{ + if (refcount_dec_and_test(&key->refs)) + kfree(key); +} + static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) { struct net *net = sock_net(&msk->sk); @@ -138,12 +167,20 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) hlist_for_each_entry(tmp, &net->mctp.keys, hlist) { if (mctp_key_match(tmp, key->local_addr, key->peer_addr, key->tag)) { - rc = -EEXIST; - break; + spin_lock(&tmp->lock); + if (tmp->valid) + rc = -EEXIST; + spin_unlock(&tmp->lock); + if (rc) + break; } } if (!rc) { + refcount_inc(&key->refs); + key->expiry = jiffies + mctp_key_lifetime; + timer_reduce(&msk->key_expiry, key->expiry); + hlist_add_head(&key->hlist, &net->mctp.keys); hlist_add_head(&key->sklist, &msk->keys); } @@ -153,28 +190,35 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) return rc; } -/* Must be called with key->reasm_lock, which it will release. Will schedule - * the key for an RCU free. +/* We're done with the key; unset valid and remove from lists. There may still + * be outstanding refs on the key though... */ static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net, unsigned long flags) - __releases(&key->reasm_lock) + __releases(&key->lock) { struct sk_buff *skb; skb = key->reasm_head; key->reasm_head = NULL; key->reasm_dead = true; - spin_unlock_irqrestore(&key->reasm_lock, flags); + key->valid = false; + spin_unlock_irqrestore(&key->lock, flags); spin_lock_irqsave(&net->mctp.keys_lock, flags); - hlist_del_rcu(&key->hlist); - hlist_del_rcu(&key->sklist); + hlist_del(&key->hlist); + hlist_del(&key->sklist); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); - kfree_rcu(key, rcu); + + /* one unref for the lists */ + mctp_key_unref(key); + + /* and one for the local reference */ + mctp_key_unref(key); if (skb) kfree_skb(skb); + } static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) @@ -248,8 +292,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) rcu_read_lock(); - /* lookup socket / reasm context, exactly matching (src,dest,tag) */ - key = mctp_lookup_key(net, skb, mh->src); + /* lookup socket / reasm context, exactly matching (src,dest,tag). + * we hold a ref on the key, and key->lock held. + */ + key = mctp_lookup_key(net, skb, mh->src, &f); if (flags & MCTP_HDR_FLAG_SOM) { if (key) { @@ -260,10 +306,12 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * key for reassembly - we'll create a more specific * one for future packets if required (ie, !EOM). */ - key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY); + key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f); if (key) { msk = container_of(key->sk, struct mctp_sock, sk); + spin_unlock_irqrestore(&key->lock, f); + mctp_key_unref(key); key = NULL; } } @@ -282,11 +330,13 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) if (flags & MCTP_HDR_FLAG_EOM) { sock_queue_rcv_skb(&msk->sk, skb); if (key) { - spin_lock_irqsave(&key->reasm_lock, f); /* we've hit a pending reassembly; not much we * can do but drop it */ + trace_mctp_key_release(key, + MCTP_TRACE_KEY_REPLIED); __mctp_key_unlock_drop(key, net, f); + key = NULL; } rc = 0; goto out_unlock; @@ -303,7 +353,7 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) goto out_unlock; } - /* we can queue without the reasm lock here, as the + /* we can queue without the key lock here, as the * key isn't observable yet */ mctp_frag_queue(key, skb); @@ -318,17 +368,21 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) if (rc) kfree(key); - } else { - /* existing key: start reassembly */ - spin_lock_irqsave(&key->reasm_lock, f); + trace_mctp_key_acquire(key); + /* we don't need to release key->lock on exit */ + key = NULL; + + } else { if (key->reasm_head || key->reasm_dead) { /* duplicate start? drop everything */ + trace_mctp_key_release(key, + MCTP_TRACE_KEY_INVALIDATED); __mctp_key_unlock_drop(key, net, f); rc = -EEXIST; + key = NULL; } else { rc = mctp_frag_queue(key, skb); - spin_unlock_irqrestore(&key->reasm_lock, f); } } @@ -337,8 +391,6 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * using the message-specific key */ - spin_lock_irqsave(&key->reasm_lock, f); - /* we need to be continuing an existing reassembly... */ if (!key->reasm_head) rc = -EINVAL; @@ -351,9 +403,9 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) if (!rc && flags & MCTP_HDR_FLAG_EOM) { sock_queue_rcv_skb(key->sk, key->reasm_head); key->reasm_head = NULL; + trace_mctp_key_release(key, MCTP_TRACE_KEY_REPLIED); __mctp_key_unlock_drop(key, net, f); - } else { - spin_unlock_irqrestore(&key->reasm_lock, f); + key = NULL; } } else { @@ -363,6 +415,10 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) out_unlock: rcu_read_unlock(); + if (key) { + spin_unlock_irqrestore(&key->lock, f); + mctp_key_unref(key); + } out: if (rc) kfree_skb(skb); @@ -412,7 +468,7 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) static void mctp_route_release(struct mctp_route *rt) { if (refcount_dec_and_test(&rt->refs)) { - dev_put(rt->dev->dev); + mctp_dev_put(rt->dev); kfree_rcu(rt, rcu); } } @@ -454,11 +510,15 @@ static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key, lockdep_assert_held(&mns->keys_lock); + key->expiry = jiffies + mctp_key_lifetime; + timer_reduce(&msk->key_expiry, key->expiry); + /* we hold the net->key_lock here, allowing updates to both * then net and sk */ hlist_add_head_rcu(&key->hlist, &mns->keys); hlist_add_head_rcu(&key->sklist, &msk->keys); + refcount_inc(&key->refs); } /* Allocate a locally-owned tag value for (saddr, daddr), and reserve @@ -474,6 +534,10 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk, int rc = -EAGAIN; u8 tagbits; + /* for NULL destination EIDs, we may get a response from any peer */ + if (daddr == MCTP_ADDR_NULL) + daddr = MCTP_ADDR_ANY; + /* be optimistic, alloc now */ key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL); if (!key) @@ -488,14 +552,26 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk, * tags. If we find a conflict, clear that bit from tagbits */ hlist_for_each_entry(tmp, &mns->keys, hlist) { + /* We can check the lookup fields (*_addr, tag) without the + * lock held, they don't change over the lifetime of the key. + */ + /* if we don't own the tag, it can't conflict */ if (tmp->tag & MCTP_HDR_FLAG_TO) continue; - if ((tmp->peer_addr == daddr || - tmp->peer_addr == MCTP_ADDR_ANY) && - tmp->local_addr == saddr) + if (!((tmp->peer_addr == daddr || + tmp->peer_addr == MCTP_ADDR_ANY) && + tmp->local_addr == saddr)) + continue; + + spin_lock(&tmp->lock); + /* key must still be valid. If we find a match, clear the + * potential tag value + */ + if (tmp->valid) tagbits &= ~(1 << tmp->tag); + spin_unlock(&tmp->lock); if (!tagbits) break; @@ -504,6 +580,8 @@ static int mctp_alloc_local_tag(struct mctp_sock *msk, if (tagbits) { key->tag = __ffs(tagbits); mctp_reserve_tag(net, key, msk); + trace_mctp_key_acquire(key); + *tagp = key->tag; rc = 0; } @@ -552,6 +630,20 @@ struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, return rt; } +static struct mctp_route *mctp_route_lookup_null(struct net *net, + struct net_device *dev) +{ + struct mctp_route *rt; + + list_for_each_entry_rcu(rt, &net->mctp.routes, list) { + if (rt->dev->dev == dev && rt->type == RTN_LOCAL && + refcount_inc_not_zero(&rt->refs)) + return rt; + } + + return NULL; +} + /* sends a skb to rt and releases the route. */ int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb) { @@ -741,7 +833,7 @@ static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start, rt->max = daddr_start + daddr_extent; rt->mtu = mtu; rt->dev = mdev; - dev_hold(rt->dev->dev); + mctp_dev_hold(rt->dev); rt->type = type; rt->output = rtfn; @@ -821,13 +913,18 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, struct net_device *orig_dev) { struct net *net = dev_net(dev); + struct mctp_dev *mdev; struct mctp_skb_cb *cb; struct mctp_route *rt; struct mctp_hdr *mh; - /* basic non-data sanity checks */ - if (dev->type != ARPHRD_MCTP) + rcu_read_lock(); + mdev = __mctp_dev_get(dev); + rcu_read_unlock(); + if (!mdev) { + /* basic non-data sanity checks */ goto err_drop; + } if (!pskb_may_pull(skb, sizeof(struct mctp_hdr))) goto err_drop; @@ -841,11 +938,14 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, goto err_drop; cb = __mctp_cb(skb); - rcu_read_lock(); - cb->net = READ_ONCE(__mctp_dev_get(dev)->net); - rcu_read_unlock(); + cb->net = READ_ONCE(mdev->net); rt = mctp_route_lookup(net, cb->net, mh->dest); + + /* NULL EID, but addressed to our physical address */ + if (!rt && mh->dest == MCTP_ADDR_NULL && skb->pkt_type == PACKET_HOST) + rt = mctp_route_lookup_null(net, dev); + if (!rt) goto err_drop; @@ -926,10 +1026,15 @@ static int mctp_route_nlparse(struct sk_buff *skb, struct nlmsghdr *nlh, return 0; } +static const struct nla_policy rta_metrics_policy[RTAX_MAX + 1] = { + [RTAX_MTU] = { .type = NLA_U32 }, +}; + static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct nlattr *tb[RTA_MAX + 1]; + struct nlattr *tbx[RTAX_MAX + 1]; mctp_eid_t daddr_start; struct mctp_dev *mdev; struct rtmsg *rtm; @@ -946,8 +1051,15 @@ static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; } - /* TODO: parse mtu from nlparse */ mtu = 0; + if (tb[RTA_METRICS]) { + rc = nla_parse_nested(tbx, RTAX_MAX, tb[RTA_METRICS], + rta_metrics_policy, NULL); + if (rc < 0) + return rc; + if (tbx[RTAX_MTU]) + mtu = nla_get_u32(tbx[RTAX_MTU]); + } if (rtm->rtm_type != RTN_UNICAST) return -EINVAL; diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 292374fb077928..f44125dd669712 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -113,37 +113,13 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, { struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_info *info = _info; - u32 flags = 0; - bool slow; - u8 val; r->idiag_rqueue = sk_rmem_alloc_get(sk); r->idiag_wqueue = sk_wmem_alloc_get(sk); if (!info) return; - slow = lock_sock_fast(sk); - info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); - info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); - info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); - info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); - info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk); - val = mptcp_pm_get_add_addr_signal_max(msk); - info->mptcpi_add_addr_signal_max = val; - val = mptcp_pm_get_add_addr_accept_max(msk); - info->mptcpi_add_addr_accepted_max = val; - info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk); - if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) - flags |= MPTCP_INFO_FLAG_FALLBACK; - if (READ_ONCE(msk->can_ack)) - flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; - info->mptcpi_flags = flags; - info->mptcpi_token = READ_ONCE(msk->token); - info->mptcpi_write_seq = READ_ONCE(msk->write_seq); - info->mptcpi_snd_una = READ_ONCE(msk->snd_una); - info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); - info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); - unlock_sock_fast(sk, slow); + mptcp_diag_fill_info(msk, info); } static const struct inet_diag_handler mptcp_diag_handler = { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c41273cefc51f4..422f4acfb3e6d6 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -748,9 +748,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, /* can't send MP_PRIO with MPC, as they share the same option space: * 'backup'. Also it makes no sense at all */ - if (!subflow->send_mp_prio || - ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | - OPTION_MPTCP_MPC_ACK) & opts->suboptions)) + if (!subflow->send_mp_prio || (opts->suboptions & OPTIONS_MPTCP_MPC)) return false; /* account for the trailing 'nop' option */ @@ -1019,11 +1017,9 @@ static void ack_update_msk(struct mptcp_sock *msk, old_snd_una = msk->snd_una; new_snd_una = mptcp_expand_seq(old_snd_una, mp_opt->data_ack, mp_opt->ack64); - /* ACK for data not even sent yet and even above recovery bound? Ignore.*/ - if (unlikely(after64(new_snd_una, snd_nxt))) { - if (!msk->recovery || after64(new_snd_una, msk->recovery_snd_nxt)) - new_snd_una = old_snd_una; - } + /* ACK for data not even sent yet? Ignore.*/ + if (unlikely(after64(new_snd_una, snd_nxt))) + new_snd_una = old_snd_una; new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd; @@ -1329,8 +1325,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); } } - } else if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK | - OPTION_MPTCP_MPC_ACK) & opts->suboptions) { + } else if (OPTIONS_MPTCP_MPC & opts->suboptions) { u8 len, flag = MPTCP_CAP_HMAC_SHA256; if (OPTION_MPTCP_MPC_SYN & opts->suboptions) { diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dbcebf56798fa8..8029bbbe1c9eb3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -956,9 +956,7 @@ static void __mptcp_update_wmem(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); -#ifdef CONFIG_LOCKDEP - WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock)); -#endif + lockdep_assert_held_once(&sk->sk_lock.slock); if (!msk->wmem_reserved) return; @@ -1107,7 +1105,8 @@ out: if (cleaned && tcp_under_memory_pressure(sk)) __mptcp_mem_reclaim_partial(sk); - if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) { + if (snd_una == READ_ONCE(msk->snd_nxt) && + snd_una == READ_ONCE(msk->write_seq)) { if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_timer(sk); } else { @@ -1117,9 +1116,8 @@ out: static void __mptcp_clean_una_wakeup(struct sock *sk) { -#ifdef CONFIG_LOCKDEP - WARN_ON_ONCE(!lockdep_is_held(&sk->sk_lock.slock)); -#endif + lockdep_assert_held_once(&sk->sk_lock.slock); + __mptcp_clean_una(sk); mptcp_write_space(sk); } @@ -1224,6 +1222,7 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) if (likely(__mptcp_add_ext(skb, gfp))) { skb_reserve(skb, MAX_TCP_HEADER); skb->reserved_tailroom = skb->end - skb->tail; + INIT_LIST_HEAD(&skb->tcp_tsorted_anchor); return skb; } __kfree_skb(skb); @@ -1233,31 +1232,23 @@ static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp) return NULL; } -static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) +static struct sk_buff *__mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp) { struct sk_buff *skb; - if (ssk->sk_tx_skb_cache) { - skb = ssk->sk_tx_skb_cache; - if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) && - !__mptcp_add_ext(skb, gfp))) - return false; - return true; - } - skb = __mptcp_do_alloc_tx_skb(sk, gfp); if (!skb) - return false; + return NULL; if (likely(sk_wmem_schedule(ssk, skb->truesize))) { - ssk->sk_tx_skb_cache = skb; - return true; + tcp_skb_entail(ssk, skb); + return skb; } kfree_skb(skb); - return false; + return NULL; } -static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) +static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, bool data_lock_held) { gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation; @@ -1287,23 +1278,29 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, struct mptcp_sendmsg_info *info) { u64 data_seq = dfrag->data_seq + info->sent; + int offset = dfrag->offset + info->sent; struct mptcp_sock *msk = mptcp_sk(sk); bool zero_window_probe = false; struct mptcp_ext *mpext = NULL; - struct sk_buff *skb, *tail; - bool must_collapse = false; - int size_bias = 0; - int avail_size; - size_t ret = 0; + bool can_coalesce = false; + bool reuse_skb = true; + struct sk_buff *skb; + size_t copy; + int i; pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u", msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent); + if (WARN_ON_ONCE(info->sent > info->limit || + info->limit > dfrag->data_len)) + return 0; + /* compute send limit */ info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags); - avail_size = info->size_goal; + copy = info->size_goal; + skb = tcp_write_queue_tail(ssk); - if (skb) { + if (skb && copy > skb->len) { /* Limit the write to the size available in the * current skb, if any, so that we create at most a new skb. * Explicitly tells TCP internals to avoid collapsing on later @@ -1316,62 +1313,80 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, goto alloc_skb; } - must_collapse = (info->size_goal > skb->len) && - (skb_shinfo(skb)->nr_frags < sysctl_max_skb_frags); - if (must_collapse) { - size_bias = skb->len; - avail_size = info->size_goal - skb->len; + i = skb_shinfo(skb)->nr_frags; + can_coalesce = skb_can_coalesce(skb, i, dfrag->page, offset); + if (!can_coalesce && i >= sysctl_max_skb_frags) { + tcp_mark_push(tcp_sk(ssk), skb); + goto alloc_skb; } - } + copy -= skb->len; + } else { alloc_skb: - if (!must_collapse && - !mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held)) - return 0; + skb = mptcp_alloc_tx_skb(sk, ssk, info->data_lock_held); + if (!skb) + return -ENOMEM; + + i = skb_shinfo(skb)->nr_frags; + reuse_skb = false; + mpext = skb_ext_find(skb, SKB_EXT_MPTCP); + } /* Zero window and all data acked? Probe. */ - avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size); - if (avail_size == 0) { + copy = mptcp_check_allowed_size(msk, data_seq, copy); + if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (skb || snd_una != msk->snd_nxt) + if (snd_una != msk->snd_nxt) { + tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk)); return 0; + } + zero_window_probe = true; data_seq = snd_una - 1; - avail_size = 1; - } + copy = 1; - if (WARN_ON_ONCE(info->sent > info->limit || - info->limit > dfrag->data_len)) - return 0; + /* all mptcp-level data is acked, no skbs should be present into the + * ssk write queue + */ + WARN_ON_ONCE(reuse_skb); + } - ret = info->limit - info->sent; - tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags, - dfrag->page, dfrag->offset + info->sent, &ret); - if (!tail) { - tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk)); + copy = min_t(size_t, copy, info->limit - info->sent); + if (!sk_wmem_schedule(ssk, copy)) { + tcp_remove_empty_skb(ssk, tcp_write_queue_tail(ssk)); return -ENOMEM; } - /* if the tail skb is still the cached one, collapsing really happened. - */ - if (skb == tail) { - TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH; - mpext->data_len += ret; + if (can_coalesce) { + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); + } else { + get_page(dfrag->page); + skb_fill_page_desc(skb, i, dfrag->page, offset, copy); + } + + skb->len += copy; + skb->data_len += copy; + skb->truesize += copy; + sk_wmem_queued_add(ssk, copy); + sk_mem_charge(ssk, copy); + skb->ip_summed = CHECKSUM_PARTIAL; + WRITE_ONCE(tcp_sk(ssk)->write_seq, tcp_sk(ssk)->write_seq + copy); + TCP_SKB_CB(skb)->end_seq += copy; + tcp_skb_pcount_set(skb, 0); + + /* on skb reuse we just need to update the DSS len */ + if (reuse_skb) { + TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; + mpext->data_len += copy; WARN_ON_ONCE(zero_window_probe); goto out; } - mpext = skb_ext_find(tail, SKB_EXT_MPTCP); - if (WARN_ON_ONCE(!mpext)) { - /* should never reach here, stream corrupted */ - return -EINVAL; - } - memset(mpext, 0, sizeof(*mpext)); mpext->data_seq = data_seq; mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq; - mpext->data_len = ret; + mpext->data_len = copy; mpext->use_map = 1; mpext->dsn64 = 1; @@ -1380,18 +1395,18 @@ alloc_skb: mpext->dsn64); if (zero_window_probe) { - mptcp_subflow_ctx(ssk)->rel_write_seq += ret; + mptcp_subflow_ctx(ssk)->rel_write_seq += copy; mpext->frozen = 1; if (READ_ONCE(msk->csum_enabled)) - mptcp_update_data_checksum(tail, ret); + mptcp_update_data_checksum(skb, copy); tcp_push_pending_frames(ssk); return 0; } out: if (READ_ONCE(msk->csum_enabled)) - mptcp_update_data_checksum(tail, ret); - mptcp_subflow_ctx(ssk)->rel_write_seq += ret; - return ret; + mptcp_update_data_checksum(skb, copy); + mptcp_subflow_ctx(ssk)->rel_write_seq += copy; + return copy; } #define MPTCP_SEND_BURST_SIZE ((1 << 16) - \ @@ -1508,6 +1523,38 @@ static void mptcp_push_release(struct sock *sk, struct sock *ssk, release_sock(ssk); } +static void mptcp_update_post_push(struct mptcp_sock *msk, + struct mptcp_data_frag *dfrag, + u32 sent) +{ + u64 snd_nxt_new = dfrag->data_seq; + + dfrag->already_sent += sent; + + msk->snd_burst -= sent; + + snd_nxt_new += dfrag->already_sent; + + /* snd_nxt_new can be smaller than snd_nxt in case mptcp + * is recovering after a failover. In that event, this re-sends + * old segments. + * + * Thus compute snd_nxt_new candidate based on + * the dfrag->data_seq that was sent and the data + * that has been handed to the subflow for transmission + * and skip update in case it was old dfrag. + */ + if (likely(after64(snd_nxt_new, msk->snd_nxt))) + msk->snd_nxt = snd_nxt_new; +} + +static void mptcp_check_and_set_pending(struct sock *sk) +{ + if (mptcp_send_head(sk) && + !test_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); +} + void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; @@ -1551,12 +1598,10 @@ void __mptcp_push_pending(struct sock *sk, unsigned int flags) } info.sent += ret; - dfrag->already_sent += ret; - msk->snd_nxt += ret; - msk->snd_burst -= ret; - msk->tx_pending_data -= ret; copied += ret; len -= ret; + + mptcp_update_post_push(msk, dfrag, ret); } WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); } @@ -1609,13 +1654,11 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) goto out; info.sent += ret; - dfrag->already_sent += ret; - msk->snd_nxt += ret; - msk->snd_burst -= ret; - msk->tx_pending_data -= ret; copied += ret; len -= ret; first = false; + + mptcp_update_post_push(msk, dfrag, ret); } WRITE_ONCE(msk->first_pending, mptcp_send_next(sk)); } @@ -1725,7 +1768,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) frag_truesize += psize; pfrag->offset += frag_truesize; WRITE_ONCE(msk->write_seq, msk->write_seq + psize); - msk->tx_pending_data += psize; /* charge data on mptcp pending queue to the msk socket * Note: we charge such data both to sk and ssk @@ -2213,15 +2255,11 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) return false; } - /* will accept ack for reijected data before re-sending them */ - if (!msk->recovery || after64(msk->snd_nxt, msk->recovery_snd_nxt)) - msk->recovery_snd_nxt = msk->snd_nxt; + msk->recovery_snd_nxt = msk->snd_nxt; msk->recovery = true; mptcp_data_unlock(sk); msk->first_pending = rtx_head; - msk->tx_pending_data += msk->snd_nxt - rtx_head->data_seq; - msk->snd_nxt = rtx_head->data_seq; msk->snd_burst = 0; /* be sure to clear the "sent status" on all re-injected fragments */ @@ -2384,6 +2422,9 @@ static void __mptcp_retrans(struct sock *sk) int ret; mptcp_clean_una_wakeup(sk); + + /* first check ssk: need to kick "stale" logic */ + ssk = mptcp_subflow_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { @@ -2396,10 +2437,12 @@ static void __mptcp_retrans(struct sock *sk) goto reset_timer; } - return; + if (!mptcp_send_head(sk)) + return; + + goto reset_timer; } - ssk = mptcp_subflow_get_retrans(msk); if (!ssk) goto reset_timer; @@ -2426,6 +2469,8 @@ static void __mptcp_retrans(struct sock *sk) release_sock(ssk); reset_timer: + mptcp_check_and_set_pending(sk); + if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); } @@ -2492,7 +2537,6 @@ static int __mptcp_init_sock(struct sock *sk) msk->first_pending = NULL; msk->wmem_reserved = 0; WRITE_ONCE(msk->rmem_released, 0); - msk->tx_pending_data = 0; msk->timer_ival = TCP_RTO_MIN; msk->first = NULL; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index dc984676c5eb15..7379ab580a7e5b 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -254,7 +254,6 @@ struct mptcp_sock { struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; struct sk_buff_head receive_queue; - int tx_pending_data; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 8c03afac5ca034..8137cc3a429608 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -14,6 +14,8 @@ #include <net/mptcp.h> #include "protocol.h" +#define MIN_INFO_OPTLEN_SIZE 16 + static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); @@ -670,6 +672,263 @@ out: return ret; } +void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) +{ + struct sock *sk = &msk->sk.icsk_inet.sk; + u32 flags = 0; + bool slow; + u8 val; + + memset(info, 0, sizeof(*info)); + + slow = lock_sock_fast(sk); + + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); + info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); + info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); + info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); + info->mptcpi_subflows_max = mptcp_pm_get_subflows_max(msk); + val = mptcp_pm_get_add_addr_signal_max(msk); + info->mptcpi_add_addr_signal_max = val; + val = mptcp_pm_get_add_addr_accept_max(msk); + info->mptcpi_add_addr_accepted_max = val; + info->mptcpi_local_addr_max = mptcp_pm_get_local_addr_max(msk); + if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) + flags |= MPTCP_INFO_FLAG_FALLBACK; + if (READ_ONCE(msk->can_ack)) + flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; + info->mptcpi_flags = flags; + info->mptcpi_token = READ_ONCE(msk->token); + info->mptcpi_write_seq = READ_ONCE(msk->write_seq); + info->mptcpi_snd_una = READ_ONCE(msk->snd_una); + info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); + info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); + + unlock_sock_fast(sk, slow); +} +EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); + +static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) +{ + struct mptcp_info m_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); + + mptcp_diag_fill_info(msk, &m_info); + + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &m_info, len)) + return -EFAULT; + + return 0; +} + +static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, + u32 copied, + int __user *optlen) +{ + u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd)); + + if (copied) + copied += sfd->size_subflow_data; + else + copied = copylen; + + if (put_user(copied, optlen)) + return -EFAULT; + + if (copy_to_user(optval, sfd, copylen)) + return -EFAULT; + + return 0; +} + +static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, int __user *optlen) +{ + int len, copylen; + + if (get_user(len, optlen)) + return -EFAULT; + + /* if mptcp_subflow_data size is changed, need to adjust + * this function to deal with programs using old version. + */ + BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE); + + if (len < MIN_INFO_OPTLEN_SIZE) + return -EINVAL; + + memset(sfd, 0, sizeof(*sfd)); + + copylen = min_t(unsigned int, len, sizeof(*sfd)); + if (copy_from_user(sfd, optval, copylen)) + return -EFAULT; + + /* size_subflow_data is u32, but len is signed */ + if (sfd->size_subflow_data > INT_MAX || + sfd->size_user > INT_MAX) + return -EINVAL; + + if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE || + sfd->size_subflow_data > len) + return -EINVAL; + + if (sfd->num_subflows || sfd->size_kernel) + return -EINVAL; + + return len - sfd->size_subflow_data; +} + +static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = &msk->sk.icsk_inet.sk; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *infoptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct tcp_info); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct tcp_info)); + + infoptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct tcp_info info; + + tcp_get_info(ssk, &info); + + if (copy_to_user(infoptr, &info, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + infoptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + +static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a) +{ + struct inet_sock *inet = inet_sk(sk); + + memset(a, 0, sizeof(*a)); + + if (sk->sk_family == AF_INET) { + a->sin_local.sin_family = AF_INET; + a->sin_local.sin_port = inet->inet_sport; + a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr; + + if (!a->sin_local.sin_addr.s_addr) + a->sin_local.sin_addr.s_addr = inet->inet_saddr; + + a->sin_remote.sin_family = AF_INET; + a->sin_remote.sin_port = inet->inet_dport; + a->sin_remote.sin_addr.s_addr = inet->inet_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + a->sin6_local.sin6_family = AF_INET6; + a->sin6_local.sin6_port = inet->inet_sport; + + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + a->sin6_local.sin6_addr = np->saddr; + else + a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr; + + a->sin6_remote.sin6_family = AF_INET6; + a->sin6_remote.sin6_port = inet->inet_dport; + a->sin6_remote.sin6_addr = sk->sk_v6_daddr; +#endif + } +} + +static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct sock *sk = &msk->sk.icsk_inet.sk; + struct mptcp_subflow_context *subflow; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *addrptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct mptcp_subflow_addrs); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct mptcp_subflow_addrs)); + + addrptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct mptcp_subflow_addrs a; + + mptcp_get_sub_addrs(ssk, &a); + + if (copy_to_user(addrptr, &a, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + addrptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -684,6 +943,21 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return -EOPNOTSUPP; } +static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, + char __user *optval, int __user *optlen) +{ + switch (optname) { + case MPTCP_INFO: + return mptcp_getsockopt_info(msk, optval, optlen); + case MPTCP_TCPINFO: + return mptcp_getsockopt_tcpinfo(msk, optval, optlen); + case MPTCP_SUBFLOW_ADDRS: + return mptcp_getsockopt_subflow_addrs(msk, optval, optlen); + } + + return -EOPNOTSUPP; +} + int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { @@ -706,6 +980,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); + if (level == SOL_MPTCP) + return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option); return -EOPNOTSUPP; } diff --git a/net/nfc/hci/llc_shdlc.c b/net/nfc/hci/llc_shdlc.c index aef750d7787c86..71e10347e6a909 100644 --- a/net/nfc/hci/llc_shdlc.c +++ b/net/nfc/hci/llc_shdlc.c @@ -201,8 +201,7 @@ static void llc_shdlc_reset_t2(struct llc_shdlc *shdlc, int y_nr) del_timer_sync(&shdlc->t2_timer); shdlc->t2_active = false; - pr_debug - ("All sent frames acked. Stopped T2(retransmit)\n"); + pr_debug("All sent frames acked. Stopped T2(retransmit)\n"); } } else { skb = skb_peek(&shdlc->ack_pending_q); @@ -211,8 +210,7 @@ static void llc_shdlc_reset_t2(struct llc_shdlc *shdlc, int y_nr) msecs_to_jiffies(SHDLC_T2_VALUE_MS)); shdlc->t2_active = true; - pr_debug - ("Start T2(retransmit) for remaining unacked sent frames\n"); + pr_debug("Start T2(retransmit) for remaining unacked sent frames\n"); } } @@ -522,12 +520,11 @@ static void llc_shdlc_handle_send_queue(struct llc_shdlc *shdlc) unsigned long time_sent; if (shdlc->send_q.qlen) - pr_debug - ("sendQlen=%d ns=%d dnr=%d rnr=%s w_room=%d unackQlen=%d\n", - shdlc->send_q.qlen, shdlc->ns, shdlc->dnr, - shdlc->rnr == false ? "false" : "true", - shdlc->w - llc_shdlc_w_used(shdlc->ns, shdlc->dnr), - shdlc->ack_pending_q.qlen); + pr_debug("sendQlen=%d ns=%d dnr=%d rnr=%s w_room=%d unackQlen=%d\n", + shdlc->send_q.qlen, shdlc->ns, shdlc->dnr, + shdlc->rnr == false ? "false" : "true", + shdlc->w - llc_shdlc_w_used(shdlc->ns, shdlc->dnr), + shdlc->ack_pending_q.qlen); while (shdlc->send_q.qlen && shdlc->ack_pending_q.qlen < shdlc->w && (shdlc->rnr == false)) { @@ -649,8 +646,7 @@ static void llc_shdlc_sm_work(struct work_struct *work) llc_shdlc_handle_send_queue(shdlc); if (shdlc->t1_active && timer_pending(&shdlc->t1_timer) == 0) { - pr_debug - ("Handle T1(send ack) elapsed (T1 now inactive)\n"); + pr_debug("Handle T1(send ack) elapsed (T1 now inactive)\n"); shdlc->t1_active = false; r = llc_shdlc_send_s_frame(shdlc, S_FRAME_RR, @@ -660,8 +656,7 @@ static void llc_shdlc_sm_work(struct work_struct *work) } if (shdlc->t2_active && timer_pending(&shdlc->t2_timer) == 0) { - pr_debug - ("Handle T2(retransmit) elapsed (T2 inactive)\n"); + pr_debug("Handle T2(retransmit) elapsed (T2 inactive)\n"); shdlc->t2_active = false; diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index 1b1411d158a732..8e0605f88a73d9 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_QRTR) := qrtr.o ns.o +obj-$(CONFIG_QRTR) += qrtr.o +qrtr-y := af_qrtr.o ns.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o diff --git a/net/qrtr/qrtr.c b/net/qrtr/af_qrtr.c index ec232252972782..ec232252972782 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/af_qrtr.c diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index 4e565eeab42607..be61d6f5be8d15 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -22,7 +22,7 @@ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) { - return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); + return usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); } static u32 rxrpc_bound_rto(u32 rto) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a8dd06c74e318c..8c64a552a64fe4 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1330,6 +1330,39 @@ static int qdisc_change_tx_queue_len(struct net_device *dev, return 0; } +void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx) +{ + struct Qdisc *qdisc = dev->qdisc; + + if (qdisc->ops->change_real_num_tx) + qdisc->ops->change_real_num_tx(qdisc, new_real_tx); +} + +void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) +{ +#ifdef CONFIG_NET_SCHED + struct net_device *dev = qdisc_dev(sch); + struct Qdisc *qdisc; + unsigned int i; + + for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + /* Only update the default qdiscs we created, + * qdiscs with handles are always hashed. + */ + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_del(qdisc); + } + for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc_sleeping; + if (qdisc != &noop_qdisc && !qdisc->handle) + qdisc_hash_add(qdisc, false); + } +#endif +} +EXPORT_SYMBOL(mq_change_real_num_tx); + int dev_qdisc_change_tx_queue_len(struct net_device *dev) { bool up = dev->flags & IFF_UP; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index e79f1afe0cfd6f..e04f1a87642b9f 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -288,6 +288,7 @@ struct Qdisc_ops mq_qdisc_ops __read_mostly = { .init = mq_init, .destroy = mq_destroy, .attach = mq_attach, + .change_real_num_tx = mq_change_real_num_tx, .dump = mq_dump, .owner = THIS_MODULE, }; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 8766ab5b878804..0bc10234e30660 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -623,6 +623,7 @@ static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { .init = mqprio_init, .destroy = mqprio_destroy, .attach = mqprio_attach, + .change_real_num_tx = mq_change_real_num_tx, .dump = mqprio_dump, .owner = THIS_MODULE, }; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c038efc23ce386..f69ef3f2019fb1 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -829,7 +829,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_rmb_sync_sg_for_device(&smc->conn); reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, - SMC_V1); + SMC_V1, NULL); if (reason_code) goto connect_abort; @@ -883,6 +883,7 @@ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { + u8 *eid = NULL; int rc = 0; ini->is_smcd = true; @@ -918,8 +919,15 @@ static int smc_connect_ism(struct smc_sock *smc, smc_rx_init(smc); smc_tx_init(smc); + if (aclc->hdr.version > SMC_V1) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + eid = clc_v2->eid; + } + rc = smc_clc_send_confirm(smc, ini->first_contact_local, - aclc->hdr.version); + aclc->hdr.version, eid); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); @@ -1533,9 +1541,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); - if (!smcd_v2_ext || - !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */ - smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini); + if (!smcd_v2_ext) { + smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini); goto not_found; } @@ -1555,13 +1562,13 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } mutex_unlock(&smcd_dev_list.mutex); - if (ini->ism_dev[0]) { - smc_ism_get_system_eid(ini->ism_dev[0], &eid); - if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN)) - goto not_found; - } else { + if (!ini->ism_dev[0]) + goto not_found; + + smc_ism_get_system_eid(&eid); + if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, + smcd_v2_ext->system_eid, eid)) goto not_found; - } /* separate - outside the smcd_dev_list.lock */ smcd_version = ini->smcd_version; @@ -1579,6 +1586,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } /* no V2 ISM device could be initialized */ ini->smcd_version = smcd_version; /* restore original value */ + ini->negotiated_eid[0] = 0; not_found: ini->smcd_version &= ~SMC_V2; @@ -1788,7 +1796,8 @@ static void smc_listen_work(struct work_struct *work) /* send SMC Accept CLC message */ rc = smc_clc_send_accept(new_smc, ini->first_contact_local, - ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1); + ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1, + ini->negotiated_eid); if (rc) goto out_unlock; @@ -2662,6 +2671,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + smc_clc_exit(); unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); diff --git a/net/smc/smc.h b/net/smc/smc.h index d65e15f0c944c1..5e7def3ab73008 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -29,9 +29,6 @@ * devices */ -#define SMC_MAX_HOSTNAME_LEN 32 -#define SMC_MAX_EID_LEN 32 - extern struct proto smc_proto; extern struct proto smc_proto6; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 6ec1ebe878ae0e..1cc8a76b39f9d4 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -26,6 +26,7 @@ #include "smc_clc.h" #include "smc_ib.h" #include "smc_ism.h" +#include "smc_netlink.h" #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 @@ -39,6 +40,285 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN]; +struct smc_clc_eid_table { + rwlock_t lock; + struct list_head list; + u8 ueid_cnt; + u8 seid_enabled; +}; + +static struct smc_clc_eid_table smc_clc_eid_table; + +struct smc_clc_eid_entry { + struct list_head list; + u8 eid[SMC_MAX_EID_LEN]; +}; + +/* The size of a user EID is 32 characters. + * Valid characters should be (single-byte character set) A-Z, 0-9, '.' and '-'. + * Blanks should only be used to pad to the expected size. + * First character must be alphanumeric. + */ +static bool smc_clc_ueid_valid(char *ueid) +{ + char *end = ueid + SMC_MAX_EID_LEN; + + while (--end >= ueid && isspace(*end)) + ; + if (end < ueid) + return false; + if (!isalnum(*ueid) || islower(*ueid)) + return false; + while (ueid <= end) { + if ((!isalnum(*ueid) || islower(*ueid)) && *ueid != '.' && + *ueid != '-') + return false; + ueid++; + } + return true; +} + +static int smc_clc_ueid_add(char *ueid) +{ + struct smc_clc_eid_entry *new_ueid, *tmp_ueid; + int rc; + + if (!smc_clc_ueid_valid(ueid)) + return -EINVAL; + + /* add a new ueid entry to the ueid table if there isn't one */ + new_ueid = kzalloc(sizeof(*new_ueid), GFP_KERNEL); + if (!new_ueid) + return -ENOMEM; + memcpy(new_ueid->eid, ueid, SMC_MAX_EID_LEN); + + write_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.ueid_cnt >= SMC_MAX_UEID) { + rc = -ERANGE; + goto err_out; + } + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + rc = -EEXIST; + goto err_out; + } + } + list_add_tail(&new_ueid->list, &smc_clc_eid_table.list); + smc_clc_eid_table.ueid_cnt++; + write_unlock(&smc_clc_eid_table.lock); + return 0; + +err_out: + write_unlock(&smc_clc_eid_table.lock); + kfree(new_ueid); + return rc; +} + +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_add(ueid); +} + +/* remove one or all ueid entries from the table */ +static int smc_clc_ueid_remove(char *ueid) +{ + struct smc_clc_eid_entry *lst_ueid, *tmp_ueid; + int rc = -ENOENT; + + /* remove table entry */ + write_lock(&smc_clc_eid_table.lock); + list_for_each_entry_safe(lst_ueid, tmp_ueid, &smc_clc_eid_table.list, + list) { + if (!ueid || !memcmp(lst_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + list_del(&lst_ueid->list); + smc_clc_eid_table.ueid_cnt--; + kfree(lst_ueid); + rc = 0; + } + } + if (!rc && !smc_clc_eid_table.ueid_cnt) { + smc_clc_eid_table.seid_enabled = 1; + rc = -EAGAIN; /* indicate success and enabling of seid */ + } + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_remove(ueid); +} + +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info) +{ + smc_clc_ueid_remove(NULL); + return 0; +} + +static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, + u32 flags, char *ueid) +{ + char ueid_str[SMC_MAX_EID_LEN + 1]; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &smc_gen_nl_family, + flags, SMC_NETLINK_DUMP_UEID); + if (!hdr) + return -ENOMEM; + snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; + } + genlmsg_end(skb, hdr); + return 0; +} + +static int _smc_nl_ueid_dump(struct sk_buff *skb, u32 portid, u32 seq, + int start_idx) +{ + struct smc_clc_eid_entry *lst_ueid; + int idx = 0; + + read_lock(&smc_clc_eid_table.lock); + list_for_each_entry(lst_ueid, &smc_clc_eid_table.list, list) { + if (idx++ < start_idx) + continue; + if (smc_nl_ueid_dumpinfo(skb, portid, seq, NLM_F_MULTI, + lst_ueid->eid)) { + --idx; + break; + } + } + read_unlock(&smc_clc_eid_table.lock); + return idx; +} + +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + int idx; + + idx = _smc_nl_ueid_dump(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, cb_ctx->pos[0]); + + cb_ctx->pos[0] = idx; + return skb->len; +} + +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + char seid_str[SMC_MAX_EID_LEN + 1]; + u8 seid_enabled; + void *hdr; + u8 *seid; + + if (cb_ctx->pos[0]) + return skb->len; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_SEID); + if (!hdr) + return -ENOMEM; + if (!smc_ism_is_v2_capable()) + goto end; + + smc_ism_get_system_eid(&seid); + snprintf(seid_str, sizeof(seid_str), "%s", seid); + if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) + goto err; + read_lock(&smc_clc_eid_table.lock); + seid_enabled = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); + if (nla_put_u8(skb, SMC_NLA_SEID_ENABLED, seid_enabled)) + goto err; +end: + genlmsg_end(skb, hdr); + cb_ctx->pos[0]++; + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) +{ + write_lock(&smc_clc_eid_table.lock); + smc_clc_eid_table.seid_enabled = 1; + write_unlock(&smc_clc_eid_table.lock); + return 0; +} + +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) +{ + int rc = 0; + + write_lock(&smc_clc_eid_table.lock); + if (!smc_clc_eid_table.ueid_cnt) + rc = -ENOENT; + else + smc_clc_eid_table.seid_enabled = 0; + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + +static bool _smc_clc_match_ueid(u8 *peer_ueid) +{ + struct smc_clc_eid_entry *tmp_ueid; + + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, peer_ueid, SMC_MAX_EID_LEN)) + return true; + } + return false; +} + +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid) +{ + bool match = false; + int i; + + negotiated_eid[0] = 0; + read_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.seid_enabled && + smc_v2_ext->hdr.flag.seid && + !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { + memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); + match = true; + goto out; + } + + for (i = 0; i < smc_v2_ext->hdr.eid_cnt; i++) { + if (_smc_clc_match_ueid(smc_v2_ext->user_eids[i])) { + memcpy(negotiated_eid, smc_v2_ext->user_eids[i], + SMC_MAX_EID_LEN); + match = true; + goto out; + } + } +out: + read_unlock(&smc_clc_eid_table.lock); + return match; +} + /* check arriving CLC proposal */ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) { @@ -551,6 +831,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) if (ini->smc_type_v2 == SMC_TYPE_N) { pclc_smcd->v2_ext_offset = 0; } else { + struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; u8 *eid = NULL; @@ -561,19 +842,25 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); - v2_ext->hdr.eid_cnt = 0; + + read_lock(&smc_clc_eid_table.lock); + v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; + plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN; + i = 0; + list_for_each_entry(ueident, &smc_clc_eid_table.list, list) { + memcpy(v2_ext->user_eids[i++], ueident->eid, + sizeof(ueident->eid)); + } + v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; v2_ext->hdr.flag.release = SMC_RELEASE; - v2_ext->hdr.flag.seid = 1; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); - if (ini->ism_dev[0]) - smc_ism_get_system_eid(ini->ism_dev[0], &eid); - else - smc_ism_get_system_eid(ini->ism_dev[1], &eid); - if (eid) + smc_ism_get_system_eid(&eid); + if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -608,7 +895,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } if (ini->smc_type_v2 != SMC_TYPE_N) { vec[i].iov_base = v2_ext; - vec[i++].iov_len = sizeof(*v2_ext); + vec[i++].iov_len = sizeof(*v2_ext) + + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); vec[i].iov_base = smcd_v2_ext; vec[i++].iov_len = sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -636,7 +924,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) /* build and send CLC CONFIRM / ACCEPT message */ static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2, - int first_contact, u8 version) + int first_contact, u8 version, + u8 *eid) { struct smc_connection *conn = &smc->conn; struct smc_clc_msg_accept_confirm *clc; @@ -664,11 +953,8 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - u8 *eid = NULL; - clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); - smc_ism_get_system_eid(conn->lgr->smcd, &eid); - if (eid) + if (eid[0]) memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) @@ -733,7 +1019,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version) + u8 version, u8 *eid) { struct smc_clc_msg_accept_confirm_v2 cclc_v2; int reason_code = 0; @@ -743,7 +1029,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, memset(&cclc_v2, 0, sizeof(cclc_v2)); cclc_v2.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, - version); + version, eid); if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -758,7 +1044,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, /* send CLC ACCEPT message across internal TCP socket */ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, - u8 version) + u8 version, u8 *negotiated_eid) { struct smc_clc_msg_accept_confirm_v2 aclc_v2; int len; @@ -766,7 +1052,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, memset(&aclc_v2, 0, sizeof(aclc_v2)); aclc_v2.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, - version); + version, negotiated_eid); if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; @@ -786,4 +1072,14 @@ void __init smc_clc_init(void) u = utsname(); memcpy(smc_hostname, u->nodename, min_t(size_t, strlen(u->nodename), sizeof(smc_hostname))); + + INIT_LIST_HEAD(&smc_clc_eid_table.list); + rwlock_init(&smc_clc_eid_table.lock); + smc_clc_eid_table.ueid_cnt = 0; + smc_clc_eid_table.seid_enabled = 1; +} + +void smc_clc_exit(void) +{ + smc_clc_ueid_remove(NULL); } diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 32d37f7b70f2b5..974d01d16bb5bd 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -14,8 +14,10 @@ #define _SMC_CLC_H #include <rdma/ib_verbs.h> +#include <linux/smc.h> #include "smc.h" +#include "smc_netlink.h" #define SMC_CLC_PROPOSAL 0x01 #define SMC_CLC_ACCEPT 0x02 @@ -158,6 +160,7 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ } __aligned(4); #define SMC_CLC_MAX_V6_PREFIX 8 +#define SMC_CLC_MAX_UEID 8 struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal pclc_base; @@ -165,6 +168,7 @@ struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal_prefix pclc_prfx; struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; struct smc_clc_v2_extension pclc_v2_ext; + u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN]; struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; struct smc_clc_smcd_gid_chid pclc_gidchids[SMC_MAX_ISM_DEVS]; struct smc_clc_msg_trail pclc_trl; @@ -330,10 +334,21 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version); + u8 version, u8 *eid); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, - u8 version); + u8 version, u8 *negotiated_eid); void smc_clc_init(void) __init; +void smc_clc_exit(void); void smc_clc_get_hostname(u8 **host); +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid); +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 8280c938be8010..f57449089a1610 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -223,7 +223,6 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); char hostname[SMC_MAX_HOSTNAME_LEN + 1]; char smc_seid[SMC_MAX_EID_LEN + 1]; - struct smcd_dev *smcd_dev; struct nlattr *attrs; u8 *seid = NULL; u8 *host = NULL; @@ -252,13 +251,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname)) goto errattr; } - mutex_lock(&smcd_dev_list.mutex); - smcd_dev = list_first_entry_or_null(&smcd_dev_list.list, - struct smcd_dev, list); - if (smcd_dev) - smc_ism_get_system_eid(smcd_dev, &seid); - mutex_unlock(&smcd_dev_list.mutex); - if (seid && smc_ism_is_v2_capable()) { + if (smc_ism_is_v2_capable()) { + smc_ism_get_system_eid(&seid); memcpy(smc_seid, seid, SMC_MAX_EID_LEN); smc_seid[SMC_MAX_EID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid)) diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c043ecdca5c445..83d30b06016fbf 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -310,6 +310,7 @@ struct smc_init_info { u8 first_contact_local; unsigned short vlan_id; u32 rc; + u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 9cb2df28996364..fd28cc498b984b 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -23,6 +23,7 @@ struct smcd_dev_list smcd_dev_list = { }; static bool smc_ism_v2_capable; +static u8 smc_ism_v2_system_eid[SMC_MAX_EID_LEN]; /* Test if an ISM communication is possible - same CPC */ int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd) @@ -42,9 +43,12 @@ int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos, return rc < 0 ? rc : 0; } -void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid) +void smc_ism_get_system_eid(u8 **eid) { - smcd->ops->get_system_eid(smcd, eid); + if (!smc_ism_v2_capable) + *eid = NULL; + else + *eid = smc_ism_v2_system_eid; } u16 smc_ism_get_chid(struct smcd_dev *smcd) @@ -435,9 +439,12 @@ int smcd_register_dev(struct smcd_dev *smcd) if (list_empty(&smcd_dev_list.list)) { u8 *system_eid = NULL; - smc_ism_get_system_eid(smcd, &system_eid); - if (system_eid[24] != '0' || system_eid[28] != '0') + smcd->ops->get_system_eid(smcd, &system_eid); + if (system_eid[24] != '0' || system_eid[28] != '0') { smc_ism_v2_capable = true; + memcpy(smc_ism_v2_system_eid, system_eid, + SMC_MAX_EID_LEN); + } } /* sort list: devices without pnetid before devices with pnetid */ if (smcd->pnetid[0]) @@ -533,4 +540,5 @@ EXPORT_SYMBOL_GPL(smcd_handle_irq); void __init smc_ism_init(void) { smc_ism_v2_capable = false; + memset(smc_ism_v2_system_eid, 0, SMC_MAX_EID_LEN); } diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 113efc7352ed67..004b22a13ffadd 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -48,7 +48,7 @@ int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc); int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos, void *data, size_t len); int smc_ism_signal_shutdown(struct smc_link_group *lgr); -void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid); +void smc_ism_get_system_eid(u8 **eid); u16 smc_ism_get_chid(struct smcd_dev *dev); bool smc_ism_is_v2_capable(void); void smc_ism_init(void); diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 6fb6f96c1d1775..f13ab0661ed5ee 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,11 +19,19 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_clc.h" #include "smc_stats.h" #include "smc_netlink.h" -#define SMC_CMD_MAX_ATTR 1 +const struct nla_policy +smc_gen_ueid_policy[SMC_NLA_EID_TABLE_MAX + 1] = { + [SMC_NLA_EID_TABLE_UNSPEC] = { .type = NLA_UNSPEC }, + [SMC_NLA_EID_TABLE_ENTRY] = { .type = NLA_STRING, + .len = SMC_MAX_EID_LEN, + }, +}; +#define SMC_CMD_MAX_ATTR 1 /* SMC_GENL generic netlink operation definition */ static const struct genl_ops smc_gen_nl_ops[] = { { @@ -66,6 +74,43 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smc_nl_get_fback_stats, }, + { + .cmd = SMC_NETLINK_DUMP_UEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_ueid, + }, + { + .cmd = SMC_NETLINK_ADD_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_add_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_REMOVE_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_remove_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_FLUSH_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_flush_ueid, + }, + { + .cmd = SMC_NETLINK_DUMP_SEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_seid, + }, + { + .cmd = SMC_NETLINK_ENABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_enable_seid, + }, + { + .cmd = SMC_NETLINK_DISABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_disable_seid, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 5ce2c0a89ccda1..e8c6c3f0e98ca1 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -17,6 +17,8 @@ extern struct genl_family smc_gen_nl_family; +extern const struct nla_policy smc_gen_ueid_policy[]; + struct smc_nl_dmp_ctx { int pos[3]; }; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index fde56ff491637b..d44399efeac62c 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -421,6 +421,46 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_gcm, info); + + if (len != sizeof(*sm4_gcm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_gcm_info->iv, + cctx->iv + TLS_CIPHER_SM4_GCM_SALT_SIZE, + TLS_CIPHER_SM4_GCM_IV_SIZE); + memcpy(sm4_gcm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_gcm_info, sizeof(*sm4_gcm_info))) + rc = -EFAULT; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_ccm, info); + + if (len != sizeof(*sm4_ccm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_ccm_info->iv, + cctx->iv + TLS_CIPHER_SM4_CCM_SALT_SIZE, + TLS_CIPHER_SM4_CCM_IV_SIZE); + memcpy(sm4_ccm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_ccm_info, sizeof(*sm4_ccm_info))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -524,6 +564,12 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, case TLS_CIPHER_CHACHA20_POLY1305: optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305); break; + case TLS_CIPHER_SM4_GCM: + optsize = sizeof(struct tls12_crypto_info_sm4_gcm); + break; + case TLS_CIPHER_SM4_CCM: + optsize = sizeof(struct tls12_crypto_info_sm4_ccm); + break; default: rc = -EINVAL; goto err_crypto_info; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4feb95e34b64ba..4147bb2e705730 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -498,9 +498,15 @@ static int tls_do_encryption(struct sock *sk, int rc, iv_offset = 0; /* For CCM based ciphers, first byte of IV is a constant */ - if (prot->cipher_type == TLS_CIPHER_AES_CCM_128) { + switch (prot->cipher_type) { + case TLS_CIPHER_AES_CCM_128: rec->iv_data[0] = TLS_AES_CCM_IV_B0_BYTE; iv_offset = 1; + break; + case TLS_CIPHER_SM4_CCM: + rec->iv_data[0] = TLS_SM4_CCM_IV_B0_BYTE; + iv_offset = 1; + break; } memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv, @@ -1457,10 +1463,16 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, aad = (u8 *)(sgout + n_sgout); iv = aad + prot->aad_size; - /* For CCM based ciphers, first byte of nonce+iv is always '2' */ - if (prot->cipher_type == TLS_CIPHER_AES_CCM_128) { - iv[0] = 2; + /* For CCM based ciphers, first byte of nonce+iv is a constant */ + switch (prot->cipher_type) { + case TLS_CIPHER_AES_CCM_128: + iv[0] = TLS_AES_CCM_IV_B0_BYTE; + iv_offset = 1; + break; + case TLS_CIPHER_SM4_CCM: + iv[0] = TLS_SM4_CCM_IV_B0_BYTE; iv_offset = 1; + break; } /* Prepare IV */ @@ -2424,6 +2436,40 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cipher_name = "rfc7539(chacha20,poly1305)"; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info; + + sm4_gcm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_GCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + iv = sm4_gcm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE; + rec_seq = sm4_gcm_info->rec_seq; + keysize = TLS_CIPHER_SM4_GCM_KEY_SIZE; + key = sm4_gcm_info->key; + salt = sm4_gcm_info->salt; + salt_size = TLS_CIPHER_SM4_GCM_SALT_SIZE; + cipher_name = "gcm(sm4)"; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info; + + sm4_ccm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_CCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + iv = sm4_ccm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE; + rec_seq = sm4_ccm_info->rec_seq; + keysize = TLS_CIPHER_SM4_CCM_KEY_SIZE; + key = sm4_ccm_info->key; + salt = sm4_ccm_info->salt; + salt_size = TLS_CIPHER_SM4_CCM_SALT_SIZE; + cipher_name = "ccm(sm4)"; + break; + } default: rc = -EINVAL; goto free_priv; diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index d73232be1e9912..1fcf5b01a193c3 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -137,7 +137,10 @@ endif BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o) +$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP) + OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o +$(OBJS): $(LIBBPF) VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \ diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index f7e5ff3586c9b4..49743ad9685134 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -37,6 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; struct btf_attach_table { @@ -347,6 +348,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } + case BTF_KIND_TAG: { + const struct btf_tag *tag = (const void *)(t + 1); + + if (json_output) { + jsonw_uint_field(w, "type_id", t->type); + jsonw_int_field(w, "component_idx", tag->component_idx); + } else { + printf(" type_id=%u component_idx=%d", t->type, tag->component_idx); + } + break; + } default: break; } diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index d40d92bbf0e484..e3ec47a6a61216 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -238,8 +238,8 @@ static void codegen(const char *template, ...) } else if (c == '\n') { break; } else { - p_err("unrecognized character at pos %td in template '%s'", - src - template - 1, template); + p_err("unrecognized character at pos %td in template '%s': '%c'", + src - template - 1, template, c); free(s); exit(-1); } @@ -406,7 +406,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name) } bpf_object__for_each_map(map, obj) { - const char * ident; + const char *ident; ident = get_map_ident(map); if (!ident) @@ -862,6 +862,8 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ + static inline const void *%1$s__elf_bytes(size_t *sz); \n\ + \n\ static inline int \n\ %1$s__create_skeleton(struct %1$s *obj) \n\ { \n\ @@ -943,10 +945,20 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \n\ - s->data_sz = %d; \n\ - s->data = (void *)\"\\ \n\ - ", - file_sz); + s->data = (void *)%2$s__elf_bytes(&s->data_sz); \n\ + \n\ + return 0; \n\ + err: \n\ + bpf_object__destroy_skeleton(s); \n\ + return -ENOMEM; \n\ + } \n\ + \n\ + static inline const void *%2$s__elf_bytes(size_t *sz) \n\ + { \n\ + *sz = %1$d; \n\ + return (const void *)\"\\ \n\ + " + , file_sz, obj_name); /* embed contents of BPF object file */ print_hex(obj_data, file_sz); @@ -954,11 +966,6 @@ static int do_skeleton(int argc, char **argv) codegen("\ \n\ \"; \n\ - \n\ - return 0; \n\ - err: \n\ - bpf_object__destroy_skeleton(s); \n\ - return -ENOMEM; \n\ } \n\ \n\ #endif /* %s */ \n\ diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index bb9fa8de7e625a..08b75e314ae7e3 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -26,6 +26,7 @@ LIBBPF_SRC := $(srctree)/tools/lib/bpf/ SUBCMD_SRC := $(srctree)/tools/lib/subcmd/ BPFOBJ := $(OUTPUT)/libbpf/libbpf.a +LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/ SUBCMDOBJ := $(OUTPUT)/libsubcmd/libsubcmd.a BINARY := $(OUTPUT)/resolve_btfids @@ -41,7 +42,7 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd $(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf - $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@) + $(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT) $(abspath $@) CFLAGS := -g \ -I$(srctree)/tools/include \ @@ -54,7 +55,7 @@ LIBS = -lelf -lz export srctree OUTPUT CFLAGS Q include $(srctree)/tools/build/Makefile.include -$(BINARY_IN): fixdep FORCE | $(OUTPUT) +$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT) $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 791f31dd0abee7..3e9785f1064a23 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -5284,6 +5306,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index d27b1708efe919..642b6ecb37d7ec 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -56,25 +56,29 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. @@ -170,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore index 5d4cfac671d540..0da84cb9e66d0e 100644 --- a/tools/lib/bpf/.gitignore +++ b/tools/lib/bpf/.gitignore @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -libbpf_version.h libbpf.pc libbpf.so.* TAGS diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 74c3b73a5fbe89..0f766345506f2c 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map LIBBPF_VERSION := $(shell \ grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \ sort -rV | head -n1 | cut -d'_' -f2) -LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION))) +LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION))) MAKEFLAGS += --no-print-directory @@ -59,7 +60,8 @@ ifndef VERBOSE VERBOSE = 0 endif -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi +INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.) \ + -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi export prefix libdir src obj @@ -112,6 +114,7 @@ STATIC_OBJDIR := $(OUTPUT)staticobjs/ BPF_IN_SHARED := $(SHARED_OBJDIR)libbpf-in.o BPF_IN_STATIC := $(STATIC_OBJDIR)libbpf-in.o BPF_HELPER_DEFS := $(OUTPUT)bpf_helper_defs.h +BPF_GENERATED := $(BPF_HELPER_DEFS) LIB_TARGET := $(addprefix $(OUTPUT),$(LIB_TARGET)) LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE)) @@ -136,7 +139,7 @@ all: fixdep all_cmd: $(CMD_TARGETS) check -$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS) +$(BPF_IN_SHARED): force $(BPF_GENERATED) @(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \ (diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \ echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true @@ -154,7 +157,7 @@ $(BPF_IN_SHARED): force $(BPF_HELPER_DEFS) echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)" -$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS) +$(BPF_IN_STATIC): force $(BPF_GENERATED) $(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR) $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h @@ -179,7 +182,7 @@ $(OUTPUT)libbpf.pc: -e "s|@VERSION@|$(LIBBPF_VERSION)|" \ < libbpf.pc.template > $@ -check: check_abi +check: check_abi check_version check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) @if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then \ @@ -205,6 +208,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT) exit 1; \ fi +HDR_MAJ_VERSION := $(shell grep -oE '^\#define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) +HDR_MIN_VERSION := $(shell grep -oE '^\#define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3) + +check_version: $(VERSION_SCRIPT) libbpf_version.h + @if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then \ + echo "Error: libbpf major version mismatch detected: " \ + "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2; \ + exit 1; \ + fi + @if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then \ + echo "Error: libbpf minor version mismatch detected: " \ + "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2; \ + exit 1; \ + fi + define do_install_mkdir if [ ! -d '$(DESTDIR_SQ)$1' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \ @@ -224,10 +242,11 @@ install_lib: all_cmd cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ) INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \ - bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h \ - bpf_endian.h bpf_core_read.h skel_internal.h + bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h \ + bpf_endian.h bpf_core_read.h skel_internal.h \ + libbpf_version.h -install_headers: $(BPF_HELPER_DEFS) +install_headers: $(BPF_GENERATED) $(call QUIET_INSTALL, headers) \ $(foreach hdr,$(INSTALL_HEADERS), \ $(call do_install,$(hdr),$(prefix)/include/bpf,644);) @@ -240,12 +259,12 @@ install: install_lib install_pkgconfig install_headers clean: $(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS) \ - *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS) \ + *~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED) \ $(SHARED_OBJDIR) $(STATIC_OBJDIR) \ $(addprefix $(OUTPUT), \ *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc) -PHONY += force cscope tags +PHONY += force cscope tags check check_abi check_version force: cscope: diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 77dc24d58302dc..6ad63e4d418a23 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -304,6 +304,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_TAG: + return base_size + sizeof(struct btf_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -376,6 +378,9 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; + case BTF_KIND_TAG: + btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx); + return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -586,6 +591,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: + case BTF_KIND_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -2440,6 +2446,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ return 0; } +/* + * Append new BTF_KIND_TAG type with: + * - *value* - non-empty/non-NULL string; + * - *ref_type_id* - referenced type ID, it might not exist yet; + * - *component_idx* - -1 for tagging reference type, otherwise struct/union + * member or function argument index; + * Returns: + * - >0, type ID of newly added BTF type; + * - <0, on error. + */ +int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx) +{ + struct btf_type *t; + int sz, value_off; + + if (!value || !value[0] || component_idx < -1) + return libbpf_err(-EINVAL); + + if (validate_type_id(ref_type_id)) + return libbpf_err(-EINVAL); + + if (btf_ensure_modifiable(btf)) + return libbpf_err(-ENOMEM); + + sz = sizeof(struct btf_type) + sizeof(struct btf_tag); + t = btf_add_type_mem(btf, sz); + if (!t) + return libbpf_err(-ENOMEM); + + value_off = btf__add_str(btf, value); + if (value_off < 0) + return value_off; + + t->name_off = value_off; + t->info = btf_type_info(BTF_KIND_TAG, 0, false); + t->type = ref_type_id; + btf_tag(t)->component_idx = component_idx; + + return btf_commit_type(btf, sz); +} + struct btf_ext_sec_setup_param { __u32 off; __u32 len; @@ -3256,8 +3304,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) t1->size == t2->size; } -/* Calculate type signature hash of INT. */ -static long btf_hash_int(struct btf_type *t) +/* Calculate type signature hash of INT or TAG. */ +static long btf_hash_int_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3267,8 +3315,8 @@ static long btf_hash_int(struct btf_type *t) return h; } -/* Check structural equality of two INTs. */ -static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) +/* Check structural equality of two INTs or TAGs. */ +static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2) { __u32 info1, info2; @@ -3535,7 +3583,8 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_common(t); break; case BTF_KIND_INT: - h = btf_hash_int(t); + case BTF_KIND_TAG: + h = btf_hash_int_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3590,14 +3639,15 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int(t); + h = btf_hash_int_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); - if (btf_equal_int(t, cand)) { + if (btf_equal_int_tag(t, cand)) { new_id = cand_id; break; } @@ -3881,7 +3931,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, switch (cand_kind) { case BTF_KIND_INT: - return btf_equal_int(cand_type, canon_type); + return btf_equal_int_tag(cand_type, canon_type); case BTF_KIND_ENUM: if (d->opts.dont_resolve_fwds) @@ -4210,6 +4260,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; + case BTF_KIND_TAG: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_int_tag(t); + for_each_dedup_cand(d, hash_entry, h) { + cand_id = (__u32)(long)hash_entry->value; + cand = btf_type_by_id(d->btf, cand_id); + if (btf_equal_int_tag(t, cand)) { + new_id = cand_id; + break; + } + } + break; + case BTF_KIND_ARRAY: { struct btf_array *info = btf_array(t); @@ -4482,6 +4549,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 4a711f990904b4..2cfe3132792046 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ /* Copyright (c) 2018 Facebook */ +/*! \file */ #ifndef __LIBBPF_BTF_H #define __LIBBPF_BTF_H @@ -30,11 +31,80 @@ enum btf_endianness { BTF_BIG_ENDIAN = 1, }; +/** + * @brief **btf__free()** frees all data of a BTF object + * @param btf BTF object to free + */ LIBBPF_API void btf__free(struct btf *btf); +/** + * @brief **btf__new()** creates a new instance of a BTF object from the raw + * bytes of an ELF's BTF section + * @param data raw bytes + * @param size number of bytes passed in `data` + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new(const void *data, __u32 size); + +/** + * @brief **btf__new_split()** create a new instance of a BTF object from the + * provided raw data bytes. It takes another BTF instance, **base_btf**, which + * serves as a base BTF, which is extended by types in a newly created BTF + * instance + * @param data raw bytes + * @param size length of raw bytes + * @param base_btf the base BTF object + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and + * creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf); + +/** + * @brief **btf__new_empty()** creates an empty BTF object. Use + * `btf__add_*()` to populate such BTF object. + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty(void); + +/** + * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an + * ELF BTF section except with a base BTF on top of which split BTF should be + * based + * @return new BTF object instance which has to be eventually freed with + * **btf__free()** + * + * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to + * `btf__new_empty()` and creates non-split BTF. + * + * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract + * error code from such a pointer `libbpf_get_error()` should be used. If + * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is + * returned on error instead. In both cases thread-local `errno` variable is + * always set to error code as well. + */ LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf); LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext); @@ -50,9 +120,11 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void); LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id); LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead") LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf); +LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead") LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API int btf__load_into_kernel(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, @@ -141,6 +213,10 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); +/* tag construction API */ +LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, + int component_idx); + struct btf_dedup_opts { unsigned int dedup_table_size; bool dont_resolve_fwds; @@ -328,6 +404,11 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } +static inline bool btf_is_tag(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_TAG; +} + static inline __u8 btf_int_encoding(const struct btf_type *t) { return BTF_INT_ENCODING(*(__u32 *)(t + 1)); @@ -396,6 +477,12 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } +struct btf_tag; +static inline struct btf_tag *btf_tag(const struct btf_type *t) +{ + return (struct btf_tag *)(t + 1); +} + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index e4b483f15fb99a..ad6df97295ae2b 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -316,6 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: + case BTF_KIND_TAG: d->type_states[t->type].referenced = 1; break; @@ -583,6 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: + case BTF_KIND_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -2215,6 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: + case BTF_KIND_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 88d8825fc6f61f..da65a1666a5e97 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,6 +195,8 @@ enum kern_feature_id { FEAT_BTF_FLOAT, /* BPF perf link support */ FEAT_PERF_LINK, + /* BTF_KIND_TAG support */ + FEAT_BTF_TAG, __FEAT_CNT, }; @@ -218,8 +220,7 @@ struct reloc_desc { struct bpf_sec_def; -typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec, - struct bpf_program *prog); +typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog); struct bpf_sec_def { const char *sec; @@ -1987,6 +1988,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; + case BTF_KIND_TAG: return "tag"; default: return "unknown"; } } @@ -2486,8 +2488,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float; + return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2496,14 +2499,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); + bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); struct btf_type *t; int i, j, vlen; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if (!has_datasec && btf_is_var(t)) { - /* replace VAR with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) { + /* replace VAR/TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -2993,6 +2997,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj) } } + if (!obj->efile.symbols) { + pr_warn("elf: couldn't find symbol table in %s, stripped object file?\n", + obj->path); + return -ENOENT; + } + scn = NULL; while ((scn = elf_nextscn(elf, scn)) != NULL) { idx++; @@ -4207,6 +4217,23 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } +static int probe_kern_btf_tag(void) +{ + static const char strs[] = "\0tag"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* VAR x */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), + BTF_VAR_STATIC, + /* attr */ + BTF_TYPE_TAG_ENC(1, 2, -1), + }; + + return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), + strs, sizeof(strs))); +} + static int probe_kern_array_mmap(void) { struct bpf_create_map_attr attr = { @@ -4423,6 +4450,9 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, + [FEAT_BTF_TAG] = { + "BTF_KIND_TAG support", probe_kern_btf_tag, + }, }; static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id) @@ -6367,12 +6397,40 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level) static const struct bpf_sec_def *find_sec_def(const char *sec_name); +static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts) +{ + struct bpf_program *prog; + + bpf_object__for_each_program(prog, obj) { + prog->sec_def = find_sec_def(prog->sec_name); + if (!prog->sec_def) { + /* couldn't guess, but user might manually specify */ + pr_debug("prog '%s': unrecognized ELF section name '%s'\n", + prog->name, prog->sec_name); + continue; + } + + if (prog->sec_def->is_sleepable) + prog->prog_flags |= BPF_F_SLEEPABLE; + bpf_program__set_type(prog, prog->sec_def->prog_type); + bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type); + +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wdeprecated-declarations" + if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || + prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) + prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); +#pragma GCC diagnostic pop + } + + return 0; +} + static struct bpf_object * __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, const struct bpf_object_open_opts *opts) { const char *obj_name, *kconfig, *btf_tmp_path; - struct bpf_program *prog; struct bpf_object *obj; char tmp_name[64]; int err; @@ -6430,30 +6488,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, err = err ? : bpf_object__collect_externs(obj); err = err ? : bpf_object__finalize_btf(obj); err = err ? : bpf_object__init_maps(obj, opts); + err = err ? : bpf_object_init_progs(obj, opts); err = err ? : bpf_object__collect_relos(obj); if (err) goto out; - bpf_object__elf_finish(obj); - bpf_object__for_each_program(prog, obj) { - prog->sec_def = find_sec_def(prog->sec_name); - if (!prog->sec_def) { - /* couldn't guess, but user might manually specify */ - pr_debug("prog '%s': unrecognized ELF section name '%s'\n", - prog->name, prog->sec_name); - continue; - } - - if (prog->sec_def->is_sleepable) - prog->prog_flags |= BPF_F_SLEEPABLE; - bpf_program__set_type(prog, prog->sec_def->prog_type); - bpf_program__set_expected_attach_type(prog, - prog->sec_def->expected_attach_type); - - if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING || - prog->sec_def->prog_type == BPF_PROG_TYPE_EXT) - prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0); - } + bpf_object__elf_finish(obj); return obj; out: @@ -7907,18 +7947,12 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, __VA_ARGS__ \ } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog); -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog); +static struct bpf_link *attach_kprobe(const struct bpf_program *prog); +static struct bpf_link *attach_tp(const struct bpf_program *prog); +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog); +static struct bpf_link *attach_trace(const struct bpf_program *prog); +static struct bpf_link *attach_lsm(const struct bpf_program *prog); +static struct bpf_link *attach_iter(const struct bpf_program *prog); static const struct bpf_sec_def section_defs[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), @@ -8244,35 +8278,37 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, return -EINVAL; } - if (prog->type == BPF_PROG_TYPE_UNSPEC) { - const struct bpf_sec_def *sec_def; - - sec_def = find_sec_def(prog->sec_name); - if (sec_def && - sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) { - /* for pr_warn */ - prog->type = sec_def->prog_type; - goto invalid_prog; - } + /* prevent the use of BPF prog with invalid type */ + if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) { + pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n", + map->name, prog->name); + return -EINVAL; + } - prog->type = BPF_PROG_TYPE_STRUCT_OPS; + /* if we haven't yet processed this BPF program, record proper + * attach_btf_id and member_idx + */ + if (!prog->attach_btf_id) { prog->attach_btf_id = st_ops->type_id; prog->expected_attach_type = member_idx; - } else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->attach_btf_id != st_ops->type_id || - prog->expected_attach_type != member_idx) { - goto invalid_prog; } + + /* struct_ops BPF prog can be re-used between multiple + * .struct_ops as long as it's the same struct_ops struct + * definition and the same function pointer field + */ + if (prog->attach_btf_id != st_ops->type_id || + prog->expected_attach_type != member_idx) { + pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", + map->name, prog->name, prog->sec_name, prog->type, + prog->attach_btf_id, prog->expected_attach_type, name); + return -EINVAL; + } + st_ops->progs[member_idx] = prog; } return 0; - -invalid_prog: - pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n", - map->name, prog->name, prog->sec_name, prog->type, - prog->attach_btf_id, prog->expected_attach_type, name); - return -EINVAL; } #define BTF_TRACE_PREFIX "btf_trace_" @@ -8428,28 +8464,15 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *name = prog->sec_name, *attach_name; - const struct bpf_sec_def *sec = NULL; - int i, err = 0; - - if (!name) - return -EINVAL; - - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (!section_defs[i].is_attach_btf) - continue; - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - - sec = §ion_defs[i]; - break; - } + const char *attach_name; + int err = 0; - if (!sec) { - pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name); + if (!prog->sec_def || !prog->sec_def->is_attach_btf) { + pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", + prog->sec_name); return -ESRCH; } - attach_name = name + sec->len; + attach_name = prog->sec_name + prog->sec_def->len; /* BPF program's BTF ID */ if (attach_prog_fd) { @@ -8483,27 +8506,28 @@ int libbpf_attach_type_by_name(const char *name, enum bpf_attach_type *attach_type) { char *type_names; - int i; + const struct bpf_sec_def *sec_def; if (!name) return libbpf_err(-EINVAL); - for (i = 0; i < ARRAY_SIZE(section_defs); i++) { - if (strncmp(name, section_defs[i].sec, section_defs[i].len)) - continue; - if (!section_defs[i].is_attachable) - return libbpf_err(-EINVAL); - *attach_type = section_defs[i].expected_attach_type; - return 0; - } - pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); - type_names = libbpf_get_type_names(true); - if (type_names != NULL) { - pr_debug("attachable section(type) names are:%s\n", type_names); - free(type_names); + sec_def = find_sec_def(name); + if (!sec_def) { + pr_debug("failed to guess attach type based on ELF section name '%s'\n", name); + type_names = libbpf_get_type_names(true); + if (type_names != NULL) { + pr_debug("attachable section(type) names are:%s\n", type_names); + free(type_names); + } + + return libbpf_err(-EINVAL); } - return libbpf_err(-EINVAL); + if (!sec_def->is_attachable) + return libbpf_err(-EINVAL); + + *attach_type = sec_def->expected_attach_type; + return 0; } int bpf_map__fd(const struct bpf_map *map) @@ -8987,9 +9011,57 @@ int bpf_link__unpin(struct bpf_link *link) return 0; } +static int poke_kprobe_events(bool add, const char *name, bool retprobe, uint64_t offset) +{ + int fd, ret = 0; + pid_t p = getpid(); + char cmd[260], probename[128], probefunc[128]; + const char *file = "/sys/kernel/debug/tracing/kprobe_events"; + + if (retprobe) + snprintf(probename, sizeof(probename), "kretprobes/%s_libbpf_%u", name, p); + else + snprintf(probename, sizeof(probename), "kprobes/%s_libbpf_%u", name, p); + + if (offset) + snprintf(probefunc, sizeof(probefunc), "%s+%zu", name, (size_t)offset); + + if (add) { + snprintf(cmd, sizeof(cmd), "%c:%s %s", + retprobe ? 'r' : 'p', + probename, + offset ? probefunc : name); + } else { + snprintf(cmd, sizeof(cmd), "-:%s", probename); + } + + fd = open(file, O_WRONLY | O_APPEND, 0); + if (!fd) + return -errno; + ret = write(fd, cmd, strlen(cmd)); + if (ret < 0) + ret = -errno; + close(fd); + + return ret; +} + +static inline int add_kprobe_event_legacy(const char *name, bool retprobe, uint64_t offset) +{ + return poke_kprobe_events(true, name, retprobe, offset); +} + +static inline int remove_kprobe_event_legacy(const char *name, bool retprobe) +{ + return poke_kprobe_events(false, name, retprobe, 0); +} + struct bpf_link_perf { struct bpf_link link; int perf_event_fd; + /* legacy kprobe support: keep track of probe identifier and type */ + char *legacy_probe_name; + bool legacy_is_retprobe; }; static int bpf_link_perf_detach(struct bpf_link *link) @@ -9004,17 +9076,23 @@ static int bpf_link_perf_detach(struct bpf_link *link) close(perf_link->perf_event_fd); close(link->fd); - return libbpf_err(err); + /* legacy kprobe needs to be removed after perf event fd closure */ + if (perf_link->legacy_probe_name) + err = remove_kprobe_event_legacy(perf_link->legacy_probe_name, + perf_link->legacy_is_retprobe); + + return err; } static void bpf_link_perf_dealloc(struct bpf_link *link) { struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + free(perf_link->legacy_probe_name); free(perf_link); } -struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts) { char errmsg[STRERR_BUFSIZE]; @@ -9089,7 +9167,7 @@ err_out: return libbpf_err_ptr(err); } -struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd) +struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd) { return bpf_program__attach_perf_event_opts(prog, pfd, NULL); } @@ -9124,6 +9202,18 @@ static int parse_uint_from_file(const char *file, const char *fmt) return ret; } +static int determine_kprobe_perf_type_legacy(const char *func_name, bool is_retprobe) +{ + char file[192]; + + snprintf(file, sizeof(file), + "/sys/kernel/debug/tracing/events/%s/%s_libbpf_%d/id", + is_retprobe ? "kretprobes" : "kprobes", + func_name, getpid()); + + return parse_uint_from_file(file, "%d\n"); +} + static int determine_kprobe_perf_type(void) { const char *file = "/sys/bus/event_source/devices/kprobe/type"; @@ -9206,16 +9296,52 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name, return pfd; } +static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64_t offset, int pid) +{ + struct perf_event_attr attr = {}; + char errmsg[STRERR_BUFSIZE]; + int type, pfd, err; + + err = add_kprobe_event_legacy(name, retprobe, offset); + if (err < 0) { + pr_warn("failed to add legacy kprobe event: %s\n", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + type = determine_kprobe_perf_type_legacy(name, retprobe); + if (type < 0) { + pr_warn("failed to determine legacy kprobe event id: %s\n", + libbpf_strerror_r(type, errmsg, sizeof(errmsg))); + return type; + } + attr.size = sizeof(attr); + attr.config = type; + attr.type = PERF_TYPE_TRACEPOINT; + + pfd = syscall(__NR_perf_event_open, &attr, + pid < 0 ? -1 : pid, /* pid */ + pid == -1 ? 0 : -1, /* cpu */ + -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC); + if (pfd < 0) { + err = -errno; + pr_warn("legacy kprobe perf_event_open() failed: %s\n", + libbpf_strerror_r(err, errmsg, sizeof(errmsg))); + return err; + } + return pfd; +} + struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts); char errmsg[STRERR_BUFSIZE]; + char *legacy_probe = NULL; struct bpf_link *link; unsigned long offset; - bool retprobe; + bool retprobe, legacy; int pfd, err; if (!OPTS_VALID(opts, bpf_kprobe_opts)) @@ -9225,8 +9351,19 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog, offset = OPTS_GET(opts, offset, 0); pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0); - pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name, - offset, -1 /* pid */, 0 /* ref_ctr_off */); + legacy = determine_kprobe_perf_type() < 0; + if (!legacy) { + pfd = perf_event_open_probe(false /* uprobe */, retprobe, + func_name, offset, + -1 /* pid */, 0 /* ref_ctr_off */); + } else { + legacy_probe = strdup(func_name); + if (!legacy_probe) + return libbpf_err_ptr(-ENOMEM); + + pfd = perf_event_kprobe_open_legacy(retprobe, func_name, + offset, -1 /* pid */); + } if (pfd < 0) { pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n", prog->name, retprobe ? "kretprobe" : "kprobe", func_name, @@ -9242,10 +9379,17 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog, libbpf_strerror_r(err, errmsg, sizeof(errmsg))); return libbpf_err_ptr(err); } + if (legacy) { + struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link); + + perf_link->legacy_probe_name = legacy_probe; + perf_link->legacy_is_retprobe = retprobe; + } + return link; } -struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name) { @@ -9256,8 +9400,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog, return bpf_program__attach_kprobe_opts(prog, func_name, &opts); } -static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_kprobe(const struct bpf_program *prog) { DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts); unsigned long offset = 0; @@ -9266,8 +9409,8 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, char *func; int n, err; - func_name = prog->sec_name + sec->len; - opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0; + func_name = prog->sec_name + prog->sec_def->len; + opts.retprobe = strcmp(prog->sec_def->sec, "kretprobe/") == 0; n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset); if (n < 1) { @@ -9289,7 +9432,7 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec, } LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts) { @@ -9329,7 +9472,7 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, return link; } -struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset) @@ -9389,7 +9532,7 @@ static int perf_event_open_tracepoint(const char *tp_category, return pfd; } -struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts) @@ -9423,15 +9566,14 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog, return link; } -struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name) { return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL); } -static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_tp(const struct bpf_program *prog) { char *sec_name, *tp_cat, *tp_name; struct bpf_link *link; @@ -9441,7 +9583,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, return libbpf_err_ptr(-ENOMEM); /* extract "tp/<category>/<name>" */ - tp_cat = sec_name + sec->len; + tp_cat = sec_name + prog->sec_def->len; tp_name = strchr(tp_cat, '/'); if (!tp_name) { free(sec_name); @@ -9455,7 +9597,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec, return link; } -struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name) { char errmsg[STRERR_BUFSIZE]; @@ -9485,16 +9627,15 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog, return link; } -static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_raw_tp(const struct bpf_program *prog) { - const char *tp_name = prog->sec_name + sec->len; + const char *tp_name = prog->sec_name + prog->sec_def->len; return bpf_program__attach_raw_tracepoint(prog, tp_name); } /* Common logic for all BPF program types that attach to a btf_id */ -static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) +static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog) { char errmsg[STRERR_BUFSIZE]; struct bpf_link *link; @@ -9523,30 +9664,28 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog) return (struct bpf_link *)link; } -struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog) +struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog) { return bpf_program__attach_btf_id(prog); } -struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog) +struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog) { return bpf_program__attach_btf_id(prog); } -static struct bpf_link *attach_trace(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_trace(const struct bpf_program *prog) { return bpf_program__attach_trace(prog); } -static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_lsm(const struct bpf_program *prog) { return bpf_program__attach_lsm(prog); } static struct bpf_link * -bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, +bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id, const char *target_name) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts, @@ -9582,24 +9721,24 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id, } struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd) +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd) { return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup"); } struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd) +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd) { return bpf_program__attach_fd(prog, netns_fd, 0, "netns"); } -struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex) +struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex) { /* target_fd/target_ifindex use the same field in LINK_CREATE */ return bpf_program__attach_fd(prog, ifindex, 0, "xdp"); } -struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, +struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name) { @@ -9632,7 +9771,7 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog, } struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts) { DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); @@ -9671,21 +9810,17 @@ bpf_program__attach_iter(struct bpf_program *prog, return link; } -static struct bpf_link *attach_iter(const struct bpf_sec_def *sec, - struct bpf_program *prog) +static struct bpf_link *attach_iter(const struct bpf_program *prog) { return bpf_program__attach_iter(prog, NULL); } -struct bpf_link *bpf_program__attach(struct bpf_program *prog) +struct bpf_link *bpf_program__attach(const struct bpf_program *prog) { - const struct bpf_sec_def *sec_def; - - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + if (!prog->sec_def || !prog->sec_def->attach_fn) return libbpf_err_ptr(-ESRCH); - return sec_def->attach_fn(sec_def, prog); + return prog->sec_def->attach_fn(prog); } static int bpf_link__detach_struct_ops(struct bpf_link *link) @@ -9698,7 +9833,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link) return 0; } -struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map) +struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map) { struct bpf_struct_ops *st_ops; struct bpf_link *link; @@ -10511,18 +10646,29 @@ int bpf_program__set_attach_target(struct bpf_program *prog, { int btf_obj_fd = 0, btf_id = 0, err; - if (!prog || attach_prog_fd < 0 || !attach_func_name) + if (!prog || attach_prog_fd < 0) return libbpf_err(-EINVAL); if (prog->obj->loaded) return libbpf_err(-EINVAL); + if (attach_prog_fd && !attach_func_name) { + /* remember attach_prog_fd and let bpf_program__load() find + * BTF ID during the program load + */ + prog->attach_prog_fd = attach_prog_fd; + return 0; + } + if (attach_prog_fd) { btf_id = libbpf_find_prog_btf_id(attach_func_name, attach_prog_fd); if (btf_id < 0) return libbpf_err(btf_id); } else { + if (!attach_func_name) + return libbpf_err(-EINVAL); + /* load btf_vmlinux, if not yet */ err = bpf_object__load_vmlinux_btf(prog->obj, true); if (err) @@ -10764,16 +10910,15 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s) for (i = 0; i < s->prog_cnt; i++) { struct bpf_program *prog = *s->progs[i].prog; struct bpf_link **link = s->progs[i].link; - const struct bpf_sec_def *sec_def; if (!prog->load) continue; - sec_def = find_sec_def(prog->sec_name); - if (!sec_def || !sec_def->attach_fn) + /* auto-attaching not supported for this program */ + if (!prog->sec_def || !prog->sec_def->attach_fn) continue; - *link = sec_def->attach_fn(sec_def, prog); + *link = bpf_program__attach(prog); err = libbpf_get_error(*link); if (err) { pr_warn("failed to auto-attach program '%s': %d\n", diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index f177d897c5f716..c90e3d79e72cfe 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -83,12 +83,15 @@ struct bpf_object_open_opts { * Non-relocatable instructions are replaced with invalid ones to * prevent accidental errors. * */ + LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect") bool relaxed_core_relocs; /* maps that set the 'pinning' attribute in their definition will have * their pin_path attribute set to a file in this directory, and be * auto-pinned to that path on load; defaults to "/sys/fs/bpf". */ const char *pin_root_path; + + LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program") __u32 attach_prog_fd; /* Additional kernel config content that augments and overrides * system Kconfig for CONFIG_xxx externs. @@ -243,7 +246,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link); LIBBPF_API int bpf_link__destroy(struct bpf_link *link); LIBBPF_API struct bpf_link * -bpf_program__attach(struct bpf_program *prog); +bpf_program__attach(const struct bpf_program *prog); struct bpf_perf_event_opts { /* size of this struct, for forward/backward compatiblity */ @@ -254,10 +257,10 @@ struct bpf_perf_event_opts { #define bpf_perf_event_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event(struct bpf_program *prog, int pfd); +bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd); LIBBPF_API struct bpf_link * -bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd, +bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd, const struct bpf_perf_event_opts *opts); struct bpf_kprobe_opts { @@ -274,10 +277,10 @@ struct bpf_kprobe_opts { #define bpf_kprobe_opts__last_field retprobe LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe, const char *func_name); LIBBPF_API struct bpf_link * -bpf_program__attach_kprobe_opts(struct bpf_program *prog, +bpf_program__attach_kprobe_opts(const struct bpf_program *prog, const char *func_name, const struct bpf_kprobe_opts *opts); @@ -297,11 +300,11 @@ struct bpf_uprobe_opts { #define bpf_uprobe_opts__last_field retprobe LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe, +bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe, pid_t pid, const char *binary_path, size_t func_offset); LIBBPF_API struct bpf_link * -bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid, +bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid, const char *binary_path, size_t func_offset, const struct bpf_uprobe_opts *opts); @@ -314,35 +317,35 @@ struct bpf_tracepoint_opts { #define bpf_tracepoint_opts__last_field bpf_cookie LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint(struct bpf_program *prog, +bpf_program__attach_tracepoint(const struct bpf_program *prog, const char *tp_category, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_tracepoint_opts(struct bpf_program *prog, +bpf_program__attach_tracepoint_opts(const struct bpf_program *prog, const char *tp_category, const char *tp_name, const struct bpf_tracepoint_opts *opts); LIBBPF_API struct bpf_link * -bpf_program__attach_raw_tracepoint(struct bpf_program *prog, +bpf_program__attach_raw_tracepoint(const struct bpf_program *prog, const char *tp_name); LIBBPF_API struct bpf_link * -bpf_program__attach_trace(struct bpf_program *prog); +bpf_program__attach_trace(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_lsm(struct bpf_program *prog); +bpf_program__attach_lsm(const struct bpf_program *prog); LIBBPF_API struct bpf_link * -bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd); +bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_netns(struct bpf_program *prog, int netns_fd); +bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd); LIBBPF_API struct bpf_link * -bpf_program__attach_xdp(struct bpf_program *prog, int ifindex); +bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex); LIBBPF_API struct bpf_link * -bpf_program__attach_freplace(struct bpf_program *prog, +bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name); struct bpf_map; -LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map); +LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); struct bpf_iter_attach_opts { size_t sz; /* size of this struct for forward/backward compatibility */ @@ -352,7 +355,7 @@ struct bpf_iter_attach_opts { #define bpf_iter_attach_opts__last_field link_info_len LIBBPF_API struct bpf_link * -bpf_program__attach_iter(struct bpf_program *prog, +bpf_program__attach_iter(const struct bpf_program *prog, const struct bpf_iter_attach_opts *opts); struct bpf_insn; @@ -854,7 +857,7 @@ struct bpf_object_skeleton { size_t sz; /* size of this struct, for forward/backward compatibility */ const char *name; - void *data; + const void *data; size_t data_sz; struct bpf_object **obj; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index bbc53bb25f68f0..9e649cf9e77153 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -386,3 +386,8 @@ LIBBPF_0.5.0 { btf_dump__dump_type_data; libbpf_set_strict_mode; } LIBBPF_0.4.0; + +LIBBPF_0.6.0 { + global: + btf__add_tag; +} LIBBPF_0.5.0; diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h index 947d8bd8a7bb63..aaa1efbf6f5109 100644 --- a/tools/lib/bpf/libbpf_common.h +++ b/tools/lib/bpf/libbpf_common.h @@ -10,6 +10,7 @@ #define __LIBBPF_LIBBPF_COMMON_H #include <string.h> +#include "libbpf_version.h" #ifndef LIBBPF_API #define LIBBPF_API __attribute__((visibility("default"))) @@ -17,6 +18,29 @@ #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg))) +/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */ +#define LIBBPF_DEPRECATED_SINCE(major, minor, msg) \ + __LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor \ + (LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg)) + +#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor) \ + (LIBBPF_MAJOR_VERSION > (major) || \ + (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor))) + +/* Add checks for other versions below when planning deprecation of API symbols + * with the LIBBPF_DEPRECATED_SINCE macro. + */ +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6) +#define __LIBBPF_MARK_DEPRECATED_0_6(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_6(X) +#endif +#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7) +#define __LIBBPF_MARK_DEPRECATED_0_7(X) X +#else +#define __LIBBPF_MARK_DEPRECATED_0_7(X) +#endif + /* Helper macro to declare and initialize libbpf options struct * * This dance with uninitialized declaration, followed by memset to zero, diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index 533b0211f40ac6..ceb0c98979bc6b 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -69,6 +69,8 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TYPE_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) @@ -90,17 +92,30 @@ /* Symbol versioning is different between static and shared library. * Properly versioned symbols are needed for shared library, but * only the symbol of the new version is needed for static library. + * Starting with GNU C 10, use symver attribute instead of .symver assembler + * directive, which works better with GCC LTO builds. */ -#ifdef SHARED -# define COMPAT_VERSION(internal_name, api_name, version) \ +#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10 + +#define DEFAULT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@@" #version))) +#define COMPAT_VERSION(internal_name, api_name, version) \ + __attribute__((symver(#api_name "@" #version))) + +#elif defined(SHARED) + +#define COMPAT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@" #version); -# define DEFAULT_VERSION(internal_name, api_name, version) \ +#define DEFAULT_VERSION(internal_name, api_name, version) \ asm(".symver " #internal_name "," #api_name "@@" #version); -#else -# define COMPAT_VERSION(internal_name, api_name, version) -# define DEFAULT_VERSION(internal_name, api_name, version) \ + +#else /* !SHARED */ + +#define COMPAT_VERSION(internal_name, api_name, version) +#define DEFAULT_VERSION(internal_name, api_name, version) \ extern typeof(internal_name) api_name \ __attribute__((alias(#internal_name))); + #endif extern void libbpf_print(enum libbpf_print_level level, diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h new file mode 100644 index 00000000000000..dd56d76f291cde --- /dev/null +++ b/tools/lib/bpf/libbpf_version.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (C) 2021 Facebook */ +#ifndef __LIBBPF_VERSION_H +#define __LIBBPF_VERSION_H + +#define LIBBPF_MAJOR_VERSION 0 +#define LIBBPF_MINOR_VERSION 6 + +#endif /* __LIBBPF_VERSION_H */ diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index e9b619aa0cdf3b..a2111696ba916f 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -281,6 +281,7 @@ out_mmap: return err; } +DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -345,6 +346,7 @@ struct xsk_umem_config_v1 { __u32 frame_headroom; }; +COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, __u64 size, struct xsk_ring_prod *fill, struct xsk_ring_cons *comp, @@ -358,8 +360,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area, return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp, &config); } -COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2) -DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4) static enum xsk_prog get_xsk_prog(void) { diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 433f8bef261e29..1dad8d617da81e 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -9,8 +9,9 @@ test_tag FEATURE-DUMP.libbpf fixdep test_dev_cgroup -/test_progs* -!test_progs.h +/test_progs +/test_progs-no_alu32 +/test_progs-bpf_gcc test_verifier_log feature test_sock diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 799b88152e9e8d..5f058058aeed69 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -513,14 +513,14 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner -$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h +$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) $(call msg,CC,,$@) $(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@ $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \ $(OUTPUT)/perfbuf_bench.skel.h -$(OUTPUT)/bench.o: bench.h testing_helpers.h +$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ) $(OUTPUT)/bench: LDLIBS += -lm $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ $(OUTPUT)/bench_count.o \ diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 9b17f2867488aa..8200c0da2769ab 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -201,6 +201,20 @@ Without it, the error from compiling bpf selftests looks like: __ https://reviews.llvm.org/D93563 +btf_tag test and Clang version +============================== + +The btf_tag selftest require LLVM support to recognize the btf_tag attribute. +It was introduced in `Clang 14`__. + +Without it, the btf_tag selftest will be skipped and you will observe: + +.. code-block:: console + + #<test_num> btf_tag:SKIP + +__ https://reviews.llvm.org/D106614 + Clang dependencies for static linking tests =========================================== diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 141d8da687d21f..50fc5561110a47 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -13,6 +13,18 @@ DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; +noinline int bpf_testmod_loop_test(int n) +{ + int i, sum = 0; + + /* the primary goal of this test is to test LBR. Create a lot of + * branches in the function, so we can catch it easily. + */ + for (i = 0; i < n; i++) + sum += i; + return sum; +} + noinline ssize_t bpf_testmod_test_read(struct file *file, struct kobject *kobj, struct bin_attribute *bin_attr, @@ -24,7 +36,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj, .len = len, }; - trace_bpf_testmod_test_read(current, &ctx); + /* This is always true. Use the check to make sure the compiler + * doesn't remove bpf_testmod_loop_test. + */ + if (bpf_testmod_loop_test(101) > 100) + trace_bpf_testmod_test_read(current, &ctx); return -EIO; /* always fail */ } @@ -71,4 +87,3 @@ module_exit(bpf_testmod_exit); MODULE_AUTHOR("Andrii Nakryiko"); MODULE_DESCRIPTION("BPF selftests module"); MODULE_LICENSE("Dual BSD/GPL"); - diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index b692e6ead9b55e..ce103fb0ad1b29 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,11 +24,12 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_DATASEC) + if (kind > BTF_KIND_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -177,6 +178,10 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; + case BTF_KIND_TAG: + fprintf(out, " type_id=%u component_idx=%d", + t->type, btf_tag(t)->component_idx); + break; default: break; } diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 77ac24b191d4ca..9454331aaf85fe 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -589,7 +589,7 @@ out: static void test_bpf_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_hash_map *skel; int err, i, len, map_fd, iter_fd; @@ -638,7 +638,6 @@ static void test_bpf_hash_map(void) val = i + 4; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; expected_val += val; err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); @@ -685,7 +684,7 @@ out: static void test_bpf_percpu_hash_map(void) { - __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0; + __u32 expected_key_a = 0, expected_key_b = 0; DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts); struct bpf_iter_bpf_percpu_hash_map *skel; int err, i, j, len, map_fd, iter_fd; @@ -722,7 +721,6 @@ static void test_bpf_percpu_hash_map(void) key.c = i + 3; expected_key_a += key.a; expected_key_b += key.b; - expected_key_c += key.c; for (j = 0; j < bpf_num_possible_cpus(); j++) { *(__u32 *)(val + j * 8) = i + j; diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 649f87382c8d87..9c85d7d27409bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -39,8 +39,8 @@ static bool always_log; #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f -#define NAME_NTH(N) (0xffff0000 | N) -#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000) +#define NAME_NTH(N) (0xfffe0000 | N) +#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xfffe0000) #define GET_NAME_NTH_IDX(X) (X & 0x0000ffff) #define MAX_NR_RAW_U32 1024 @@ -3661,6 +3661,249 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type_size", }, +{ + .descr = "tag test #1, struct/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, +}, +{ + .descr = "tag test #2, union/member, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, +}, +{ + .descr = "tag test #3, variable, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 2, -1), + BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0global\0tag1\0tag2"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ + .descr = "tag test #4, func/parameter, well-formed", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_TAG_ENC(NAME_TBD, 3, 0), + BTF_TAG_ENC(NAME_TBD, 3, 1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, +}, +{ + .descr = "tag test #5, invalid value", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TAG_ENC(0, 2, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid value", +}, +{ + .descr = "tag test #6, invalid target type", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TAG_ENC(NAME_TBD, 1, -1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid type", +}, +{ + .descr = "tag test #7, invalid vlen", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "vlen != 0", +}, +{ + .descr = "tag test #8, invalid kflag", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid btf_info kind_flag", +}, +{ + .descr = "tag test #9, var, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ + BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_END_RAW, + }, + BTF_STR_SEC("\0local\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "tag test #10, struct member, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(0, 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_MEMBER_ENC(NAME_TBD, 1, 32), + BTF_TAG_ENC(NAME_TBD, 2, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0m1\0m2\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 8, + .key_type_id = 1, + .value_type_id = 2, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "tag test #11, func parameter, invalid component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, 2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, +{ + .descr = "tag test #12, < -1 component_idx", + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ + BTF_TAG_ENC(NAME_TBD, 3, -2), + BTF_END_RAW, + }, + BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "tag_type_check_btf", + .key_size = sizeof(int), + .value_size = 4, + .key_type_id = 1, + .value_type_id = 1, + .max_entries = 1, + .btf_load_err = true, + .err_str = "Invalid component_idx", +}, + }; /* struct btf_raw_test raw_tests[] */ static const char *get_next_str(const char *start, const char *end) @@ -6421,27 +6664,33 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(4), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(5), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(6), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ + /* tag -> [3] struct s */ + BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + /* tag -> [3] struct s, member 1 */ + BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ - BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [7] */ - BTF_TYPE_ARRAY_ENC(7, 7, 16), /* [8] */ - BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [9] */ - BTF_MEMBER_ENC(NAME_NTH(3), 10, 0), - BTF_MEMBER_ENC(NAME_NTH(4), 11, 64), - BTF_MEMBER_ENC(NAME_NTH(5), 8, 128), - BTF_MEMBER_ENC(NAME_NTH(6), 7, 640), - BTF_MEMBER_ENC(NAME_NTH(8), 13, 672), - BTF_PTR_ENC(9), /* [10] */ - BTF_PTR_ENC(12), /* [11] */ - BTF_CONST_ENC(7), /* [12] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [13] */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ + BTF_TYPE_ARRAY_ENC(9, 9, 16), /* [10] */ + BTF_STRUCT_ENC(NAME_NTH(2), 5, 88), /* [11] */ + BTF_MEMBER_ENC(NAME_NTH(3), 12, 0), + BTF_MEMBER_ENC(NAME_NTH(4), 13, 64), + BTF_MEMBER_ENC(NAME_NTH(5), 10, 128), + BTF_MEMBER_ENC(NAME_NTH(6), 9, 640), + BTF_MEMBER_ENC(NAME_NTH(8), 15, 672), + BTF_PTR_ENC(11), /* [12] */ + BTF_PTR_ENC(14), /* [13] */ + BTF_CONST_ENC(9), /* [14] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ + BTF_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6458,14 +6707,16 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(1), 5, 64), /* const int *a; */ BTF_MEMBER_ENC(NAME_NTH(2), 2, 128), /* int b[16]; */ BTF_MEMBER_ENC(NAME_NTH(3), 1, 640), /* int c; */ - BTF_MEMBER_ENC(NAME_NTH(4), 7, 672), /* float d; */ + BTF_MEMBER_ENC(NAME_NTH(4), 9, 672), /* float d; */ /* ptr -> [3] struct s */ BTF_PTR_ENC(3), /* [4] */ /* ptr -> [6] const int */ BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [7] */ + BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a\0b\0c\0d\0int\0float\0next\0s"), @@ -6590,9 +6841,11 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), }, .expect = { .raw_types = { @@ -6616,9 +6869,11 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ + BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, - BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"), + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), }, .opts = { .dont_resolve_fwds = false, @@ -6767,6 +7022,152 @@ const struct btf_dedup_test dedup_tests[] = { .dedup_table_size = 1 }, }, +{ + .descr = "dedup: func/func_arg/var tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* static int t */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + /* tag -> t */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + /* tag -> func */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + /* tag -> func arg a1 */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_VAR_ENC(NAME_NTH(1), 1, 0), /* [2] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), + BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: func/func_param tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + /* void f(int a1, int a2) */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ + /* tag -> f: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + /* tag -> f/a2: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + /* tag -> f: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + /* tag -> f/a2: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), + BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: struct/struct_member tags", + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + /* tag -> t: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + /* tag -> t/m2: tag1, tag2 */ + BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + /* tag -> t: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + /* tag -> t/m2: tag1, tag3 */ + BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ + BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), + BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), + BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, }; @@ -6801,6 +7202,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); + case BTF_KIND_TAG: + return base_size + sizeof(struct btf_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c new file mode 100644 index 00000000000000..91821f42714dad --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "tag.skel.h" + +void test_btf_tag(void) +{ + struct tag *skel; + + skel = tag__open_and_load(); + if (!ASSERT_OK_PTR(skel, "btf_tag")) + return; + + if (skel->rodata->skip_tests) { + printf("%s:SKIP: btf_tag attribute not supported", __func__); + test__skip(); + } + + tag__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 022c7d89d6f462..76548eecce2c2d 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -281,5 +281,26 @@ void test_btf_write() { "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); + /* TAG */ + id = btf__add_tag(btf, "tag1", 16, -1); + ASSERT_EQ(id, 18, "tag_id"); + t = btf__type_by_id(btf, 18); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(t->type, 16, "tag_type"); + ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 18), + "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + + id = btf__add_tag(btf, "tag2", 14, 1); + ASSERT_EQ(id, 19, "tag_id"); + t = btf__type_by_id(btf, 19); + ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); + ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(t->type, 14, "tag_type"); + ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_STREQ(btf_type_raw_dump(btf, 19), + "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + btf__free(btf); } diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 4739b15b2a979a..763302e63a2948 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -30,7 +30,7 @@ static int duration = 0; .output_len = sizeof(struct core_reloc_module_output), \ .prog_sec_name = sec_name, \ .raw_tp_name = tp_name, \ - .trigger = trigger_module_test_read, \ + .trigger = __trigger_module_test_read, \ .needs_testmod = true, \ } @@ -249,8 +249,7 @@ static int duration = 0; #define SIZE_CASE_COMMON(name) \ .case_name = #name, \ .bpf_obj_file = "test_core_reloc_size.o", \ - .btf_src_file = "btf__core_reloc_" #name ".o", \ - .relaxed_core_relocs = true + .btf_src_file = "btf__core_reloc_" #name ".o" #define SIZE_OUTPUT_DATA(type) \ STRUCT_TO_CHAR_PTR(core_reloc_size_output) { \ @@ -475,19 +474,11 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test) return 0; } -static int trigger_module_test_read(const struct core_reloc_test_case *test) +static int __trigger_module_test_read(const struct core_reloc_test_case *test) { struct core_reloc_module_output *exp = (void *)test->output; - int fd, err; - - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) - return err; - - read(fd, NULL, exp->len); /* request expected number of bytes */ - close(fd); + trigger_module_test_read(exp->len); return 0; } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index 73b4c76e6b869b..c7c1816899bf64 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -60,7 +60,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, struct bpf_object *obj = NULL, *tgt_obj; __u32 retval, tgt_prog_id, info_len; struct bpf_prog_info prog_info = {}; - struct bpf_program **prog = NULL; + struct bpf_program **prog = NULL, *p; struct bpf_link **link = NULL; int err, tgt_fd, i; struct btf *btf; @@ -69,9 +69,6 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, &tgt_obj, &tgt_fd); if (!ASSERT_OK(err, "tgt_prog_load")) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = tgt_fd, - ); info_len = sizeof(prog_info); err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len); @@ -89,10 +86,15 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, if (!ASSERT_OK_PTR(prog, "prog_ptr")) goto close_prog; - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + bpf_object__for_each_program(p, obj) { + err = bpf_program__set_attach_target(p, tgt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + } + err = bpf_object__load(obj); if (!ASSERT_OK(err, "obj_load")) goto close_prog; @@ -270,7 +272,7 @@ static void test_fmod_ret_freplace(void) struct bpf_link *freplace_link = NULL; struct bpf_program *prog; __u32 duration = 0; - int err, pkt_fd; + int err, pkt_fd, attach_prog_fd; err = bpf_prog_load(tgt_name, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); @@ -278,26 +280,32 @@ static void test_fmod_ret_freplace(void) if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", tgt_name, err, errno)) return; - opts.attach_prog_fd = pkt_fd; - freplace_obj = bpf_object__open_file(freplace_name, &opts); + freplace_obj = bpf_object__open_file(freplace_name, NULL); if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open")) goto out; + prog = bpf_program__next(NULL, freplace_obj); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "freplace__set_attach_target"); + err = bpf_object__load(freplace_obj); if (CHECK(err, "freplace_obj_load", "err %d\n", err)) goto out; - prog = bpf_program__next(NULL, freplace_obj); freplace_link = bpf_program__attach_trace(prog); if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace")) goto out; - opts.attach_prog_fd = bpf_program__fd(prog); - fmod_obj = bpf_object__open_file(fmod_ret_name, &opts); + fmod_obj = bpf_object__open_file(fmod_ret_name, NULL); if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open")) goto out; + attach_prog_fd = bpf_program__fd(prog); + prog = bpf_program__next(NULL, fmod_obj); + err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL); + ASSERT_OK(err, "fmod_ret_set_attach_target"); + err = bpf_object__load(fmod_obj); if (CHECK(!err, "fmod_obj_load", "loading fmod_ret should fail\n")) goto out; @@ -322,14 +330,14 @@ static void test_func_sockmap_update(void) } static void test_obj_load_failure_common(const char *obj_file, - const char *target_obj_file) - + const char *target_obj_file) { /* * standalone test that asserts failure to load freplace prog * because of invalid return code. */ struct bpf_object *obj = NULL, *pkt_obj; + struct bpf_program *prog; int err, pkt_fd; __u32 duration = 0; @@ -339,14 +347,15 @@ static void test_obj_load_failure_common(const char *obj_file, if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n", target_obj_file, err, errno)) return; - DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, - .attach_prog_fd = pkt_fd, - ); - obj = bpf_object__open_file(obj_file, &opts); + obj = bpf_object__open_file(obj_file, NULL); if (!ASSERT_OK_PTR(obj, "obj_open")) goto close_prog; + prog = bpf_program__next(NULL, obj); + err = bpf_program__set_attach_target(prog, pkt_fd, NULL); + ASSERT_OK(err, "set_attach_target"); + /* It should fail to load the program */ err = bpf_object__load(obj); if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err)) diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c new file mode 100644 index 00000000000000..f81db9135ae42f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include <test_progs.h> +#include "get_branch_snapshot.skel.h" + +static int *pfd_array; +static int cpu_cnt; + +static int create_perf_events(void) +{ + struct perf_event_attr attr = {0}; + int cpu; + + /* create perf event */ + attr.size = sizeof(attr); + attr.type = PERF_TYPE_RAW; + attr.config = 0x1b00; + attr.sample_type = PERF_SAMPLE_BRANCH_STACK; + attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL | + PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY; + + cpu_cnt = libbpf_num_possible_cpus(); + pfd_array = malloc(sizeof(int) * cpu_cnt); + if (!pfd_array) { + cpu_cnt = 0; + return 1; + } + + for (cpu = 0; cpu < cpu_cnt; cpu++) { + pfd_array[cpu] = syscall(__NR_perf_event_open, &attr, + -1, cpu, -1, PERF_FLAG_FD_CLOEXEC); + if (pfd_array[cpu] < 0) + break; + } + + return cpu == 0; +} + +static void close_perf_events(void) +{ + int cpu = 0; + int fd; + + while (cpu++ < cpu_cnt) { + fd = pfd_array[cpu]; + if (fd < 0) + break; + close(fd); + } + free(pfd_array); +} + +void test_get_branch_snapshot(void) +{ + struct get_branch_snapshot *skel = NULL; + int err; + + if (create_perf_events()) { + test__skip(); /* system doesn't support LBR */ + goto cleanup; + } + + skel = get_branch_snapshot__open_and_load(); + if (!ASSERT_OK_PTR(skel, "get_branch_snapshot__open_and_load")) + goto cleanup; + + err = kallsyms_find("bpf_testmod_loop_test", &skel->bss->address_low); + if (!ASSERT_OK(err, "kallsyms_find")) + goto cleanup; + + err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high); + if (!ASSERT_OK(err, "kallsyms_find_next")) + goto cleanup; + + err = get_branch_snapshot__attach(skel); + if (!ASSERT_OK(err, "get_branch_snapshot__attach")) + goto cleanup; + + trigger_module_test_read(100); + + if (skel->bss->total_entries < 16) { + /* too few entries for the hit/waste test */ + test__skip(); + goto cleanup; + } + + ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr"); + + /* Given we stop LBR in software, we will waste a few entries. + * But we should try to waste as few as possible entries. We are at + * about 7 on x86_64 systems. + * Add a check for < 10 so that we get heads-up when something + * changes and wastes too many entries. + */ + ASSERT_LT(skel->bss->wasted_entries, 10, "check_wasted_entries"); + +cleanup: + get_branch_snapshot__destroy(skel); + close_perf_events(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c index d85a69b7ce4491..1797a6e4d6d843 100644 --- a/tools/testing/selftests/bpf/prog_tests/module_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -6,45 +6,6 @@ static int duration; -static int trigger_module_test_read(int read_sz) -{ - int fd, err; - - fd = open("/sys/kernel/bpf_testmod", O_RDONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) - return err; - - read(fd, NULL, read_sz); - close(fd); - - return 0; -} - -static int trigger_module_test_write(int write_sz) -{ - int fd, err; - char *buf = malloc(write_sz); - - if (!buf) - return -ENOMEM; - - memset(buf, 'a', write_sz); - buf[write_sz-1] = '\0'; - - fd = open("/sys/kernel/bpf_testmod", O_WRONLY); - err = -errno; - if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) { - free(buf); - return err; - } - - write(fd, buf, write_sz); - close(fd); - free(buf); - return 0; -} - static int delete_module(const char *name, int flags) { return syscall(__NR_delete_module, name, flags); diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index fafeddaad6a998..c437e6ba8fe202 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -11,12 +11,14 @@ void test_skb_ctx(void) .cb[3] = 4, .cb[4] = 5, .priority = 6, + .ingress_ifindex = 11, .ifindex = 1, .tstamp = 7, .wire_len = 100, .gso_segs = 8, .mark = 9, .gso_size = 10, + .hwtstamp = 11, }; struct bpf_prog_test_run_attr tattr = { .data_in = &pkt_v4, @@ -97,6 +99,10 @@ void test_skb_ctx(void) "ctx_out_ifindex", "skb->ifindex == %d, expected %d\n", skb.ifindex, 1); + CHECK_ATTR(skb.ingress_ifindex != 11, + "ctx_out_ingress_ifindex", + "skb->ingress_ifindex == %d, expected %d\n", + skb.ingress_ifindex, 11); CHECK_ATTR(skb.tstamp != 8, "ctx_out_tstamp", "skb->tstamp == %lld, expected %d\n", diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c index f6f130c99b8cb8..fe1e204a65c6de 100644 --- a/tools/testing/selftests/bpf/prog_tests/skeleton.c +++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c @@ -18,6 +18,8 @@ void test_skeleton(void) struct test_skeleton__data *data; struct test_skeleton__rodata *rodata; struct test_skeleton__kconfig *kcfg; + const void *elf_bytes; + size_t elf_bytes_sz = 0; skel = test_skeleton__open(); if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) @@ -91,6 +93,10 @@ void test_skeleton(void) CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2", "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION); + elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz); + ASSERT_OK_PTR(elf_bytes, "elf_bytes"); + ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz"); + cleanup: test_skeleton__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c index b5940e6ca67cb7..7bf3a7a97d7bd5 100644 --- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c +++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c @@ -219,10 +219,7 @@ out: bpf_object__close(obj); } -/* test_tailcall_3 checks that the count value of the tail call limit - * enforcement matches with expectations. - */ -static void test_tailcall_3(void) +static void test_tailcall_count(const char *which) { int err, map_fd, prog_fd, main_fd, data_fd, i, val; struct bpf_map *prog_array, *data_map; @@ -231,7 +228,7 @@ static void test_tailcall_3(void) __u32 retval, duration; char buff[128] = {}; - err = bpf_prog_load("tailcall3.o", BPF_PROG_TYPE_SCHED_CLS, &obj, + err = bpf_prog_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); if (CHECK_FAIL(err)) return; @@ -296,6 +293,22 @@ out: bpf_object__close(obj); } +/* test_tailcall_3 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses direct jump. + */ +static void test_tailcall_3(void) +{ + test_tailcall_count("tailcall3.o"); +} + +/* test_tailcall_6 checks that the count value of the tail call limit + * enforcement matches with expectations. JIT uses indirect jump. + */ +static void test_tailcall_6(void) +{ + test_tailcall_count("tailcall6.o"); +} + /* test_tailcall_4 checks that the kernel properly selects indirect jump * for the case where the key is not known. Latter is passed via global * data to select different targets we can compare return value of. @@ -822,6 +835,8 @@ void test_tailcalls(void) test_tailcall_4(); if (test__start_subtest("tailcall_5")) test_tailcall_5(); + if (test__start_subtest("tailcall_6")) + test_tailcall_6(); if (test__start_subtest("tailcall_bpf2bpf_1")) test_tailcall_bpf2bpf_1(); if (test__start_subtest("tailcall_bpf2bpf_2")) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index e7201ba29ccd62..e87bc4466d9acd 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -633,7 +633,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) struct nstoken *nstoken = NULL; int err; int tunnel_pid = -1; - int src_fd, target_fd; + int src_fd, target_fd = -1; int ifindex; /* Start a L3 TUN/TAP tunnel between the src and dst namespaces. diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c index f62df4d023f9f0..d9660e7200e2d1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_cubic.c +++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c @@ -169,11 +169,7 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -/* "struct_ops/" prefix is not a requirement - * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS - * as long as it is used in one of the func ptr - * under SEC(".struct_ops"). - */ +/* "struct_ops/" prefix is a requirement */ SEC("struct_ops/bpf_cubic_init") void BPF_PROG(bpf_cubic_init, struct sock *sk) { @@ -188,10 +184,8 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -/* No prefix in SEC will also work. - * The remaining tcp-cubic functions have an easier way. - */ -SEC("no-sec-prefix-bictcp_cwnd_event") +/* "struct_ops" prefix is a requirement */ +SEC("struct_ops/bpf_cubic_cwnd_event") void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c new file mode 100644 index 00000000000000..a1b139888048c9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +__u64 test1_hits = 0; +__u64 address_low = 0; +__u64 address_high = 0; +int wasted_entries = 0; +long total_entries = 0; + +#define ENTRY_CNT 32 +struct perf_branch_entry entries[ENTRY_CNT] = {}; + +static inline bool in_range(__u64 val) +{ + return (val >= address_low) && (val < address_high); +} + +SEC("fexit/bpf_testmod_loop_test") +int BPF_PROG(test1, int n, int ret) +{ + long i; + + total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0); + total_entries /= sizeof(struct perf_branch_entry); + + for (i = 0; i < ENTRY_CNT; i++) { + if (i >= total_entries) + break; + if (in_range(entries[i].from) && in_range(entries[i].to)) + test1_hits++; + else if (!test1_hits) + wasted_entries++; + } + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c new file mode 100644 index 00000000000000..b46b1bfac7da3b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tag.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +#ifndef __has_attribute +#define __has_attribute(x) 0 +#endif + +#if __has_attribute(btf_tag) +#define __tag1 __attribute__((btf_tag("tag1"))) +#define __tag2 __attribute__((btf_tag("tag2"))) +volatile const bool skip_tests __tag1 __tag2 = false; +#else +#define __tag1 +#define __tag2 +volatile const bool skip_tests = true; +#endif + +struct key_t { + int a; + int b __tag1 __tag2; + int c; +} __tag1 __tag2; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 3); + __type(key, struct key_t); + __type(value, __u64); +} hashmap1 SEC(".maps"); + + +static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2 +{ + struct key_t key; + __u64 val = 1; + + key.a = key.b = key.c = x; + bpf_map_update_elem(&hashmap1, &key, &val, 0); + return 0; +} + +SEC("fentry/bpf_fentry_test1") +int BPF_PROG(sub, int x) +{ + return foo(x); +} diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c new file mode 100644 index 00000000000000..0f4a811cc02886 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tailcall6.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> + +#include <bpf/bpf_helpers.h> + +struct { + __uint(type, BPF_MAP_TYPE_PROG_ARRAY); + __uint(max_entries, 1); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(__u32)); +} jmp_table SEC(".maps"); + +int count, which; + +SEC("classifier/0") +int bpf_func_0(struct __sk_buff *skb) +{ + count++; + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 1; +} + +SEC("classifier") +int entry(struct __sk_buff *skb) +{ + if (__builtin_constant_p(which)) + __bpf_unreachable(); + bpf_tail_call(skb, &jmp_table, which); + return 0; +} + +char __license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c index b02ea589ce7eaa..ba4dab09d19c40 100644 --- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c +++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c @@ -25,6 +25,12 @@ int process(struct __sk_buff *skb) return 1; if (skb->gso_size != 10) return 1; + if (skb->ingress_ifindex != 11) + return 1; + if (skb->ifindex != 1) + return 1; + if (skb->hwtstamp != 11) + return 1; return 0; } diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index e2394eea4b7f83..0619e06d745e1d 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,4 +69,7 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) +#define BTF_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) + #endif /* _TEST_BTF_H */ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index cc1cd240445d27..2ed01f615d20fb 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -743,6 +743,45 @@ int cd_flavor_subdir(const char *exec_name) return chdir(flavor); } +int trigger_module_test_read(int read_sz) +{ + int fd, err; + + fd = open("/sys/kernel/bpf_testmod", O_RDONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) + return err; + + read(fd, NULL, read_sz); + close(fd); + + return 0; +} + +int trigger_module_test_write(int write_sz) +{ + int fd, err; + char *buf = malloc(write_sz); + + if (!buf) + return -ENOMEM; + + memset(buf, 'a', write_sz); + buf[write_sz-1] = '\0'; + + fd = open("/sys/kernel/bpf_testmod", O_WRONLY); + err = -errno; + if (!ASSERT_GE(fd, 0, "testmod_file_open")) { + free(buf); + return err; + } + + write(fd, buf, write_sz); + close(fd); + free(buf); + return 0; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index c8c2bf878f67cc..94bef0aa74cf5e 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -291,6 +291,8 @@ int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); int extract_build_id(char *build_id, size_t size); int kern_sync_rcu(void); +int trigger_module_test_read(int read_sz); +int trigger_module_test_write(int write_sz); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index e7a19b04d4eaf8..5100a169b72b1c 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <ctype.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -117,6 +118,42 @@ out: return err; } +/* find the address of the next symbol of the same type, this can be used + * to determine the end of a function. + */ +int kallsyms_find_next(const char *sym, unsigned long long *addr) +{ + char type, found_type, name[500]; + unsigned long long value; + bool found = false; + int err = 0; + FILE *f; + + f = fopen("/proc/kallsyms", "r"); + if (!f) + return -EINVAL; + + while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) { + /* Different types of symbols in kernel modules are mixed + * in /proc/kallsyms. Only return the next matching type. + * Use tolower() for type so that 'T' matches 't'. + */ + if (found && found_type == tolower(type)) { + *addr = value; + goto out; + } + if (strcmp(name, sym) == 0) { + found = true; + found_type = tolower(type); + } + } + err = -ENOENT; + +out: + fclose(f); + return err; +} + void read_trace_pipe(void) { int trace_fd; diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index d907b445524d52..bc8ed86105d94c 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -16,6 +16,11 @@ long ksym_get_addr(const char *name); /* open kallsyms and find addresses on the fly, faster than load + search. */ int kallsyms_find(const char *sym, unsigned long long *addr); +/* find the address of the next symbol, this can be used to determine the + * end of a function + */ +int kallsyms_find_next(const char *sym, unsigned long long *addr); + void read_trace_pipe(void); ssize_t get_uprobe_offset(const void *addr, ssize_t base); diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index 2022c0f2cd759b..9e1a30b9419728 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -1058,6 +1058,66 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "padding after gso_size is not accessible", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetofend(struct __sk_buff, gso_size)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=180 size=4", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CGROUP_SKB", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "write hwtstamp from CGROUP_SKB", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .result_unpriv = REJECT, + .errstr = "invalid bpf_context access off=184 size=8", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "read hwtstamp from CLS", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, hwtstamp)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, +{ "check wire_len is not readable by sockets", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c index df215e0045664c..eedcb752bf7073 100644 --- a/tools/testing/selftests/bpf/verifier/jit.c +++ b/tools/testing/selftests/bpf/verifier/jit.c @@ -62,6 +62,11 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_MOV32_REG(BPF_REG_2, BPF_REG_2), BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1), @@ -73,11 +78,22 @@ BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0xefefef), + BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL), + BPF_LD_IMM64(BPF_REG_2, 0x2ad4d4aaULL), + BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, 0x2b), + BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL), BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL), - BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL), - BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1), - BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2), + BPF_LD_IMM64(BPF_REG_5, 0xeeff0d413122ULL), + BPF_ALU32_REG(BPF_MUL, BPF_REG_5, BPF_REG_1), + BPF_JMP_REG(BPF_JEQ, BPF_REG_5, BPF_REG_0, 2), BPF_MOV64_IMM(BPF_REG_0, 1), BPF_EXIT_INSN(), BPF_MOV64_IMM(BPF_REG_0, 2), diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c index f53ce2683f8d92..127bcde06c86e6 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.c +++ b/tools/testing/selftests/bpf/xdpxceiver.c @@ -19,7 +19,7 @@ * Virtual Ethernet interfaces. * * For each mode, the following tests are run: - * a. nopoll - soft-irq processing + * a. nopoll - soft-irq processing in run-to-completion mode * b. poll - using poll() syscall * c. Socket Teardown * Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy @@ -45,6 +45,10 @@ * Configure sockets at indexes 0 and 1, run a traffic on queue ids 0, * then remove xsk sockets from queue 0 on both veth interfaces and * finally run a traffic on queues ids 1 + * g. unaligned mode + * h. tests for invalid and corner case Tx descriptors so that the correct ones + * are discarded and let through, respectively. + * i. 2K frame size tests * * Total tests: 12 * @@ -112,13 +116,10 @@ static void __exit_with_error(int error, const char *file, const char *func, int #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__) -#define print_ksft_result(void)\ - (ksft_test_result_pass("PASS: %s %s %s%s%s%s\n", configured_mode ? "DRV" : "SKB",\ - test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\ - test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\ - test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\ - test_type == TEST_TYPE_STATS ? "Stats" : "",\ - test_type == TEST_TYPE_BPF_RES ? "BPF RES" : "")) +#define mode_string(test) (test)->ifobj_tx->xdp_flags & XDP_FLAGS_SKB_MODE ? "SKB" : "DRV" + +#define print_ksft_result(test) \ + (ksft_test_result_pass("PASS: %s %s\n", mode_string(test), (test)->name)) static void memset32_htonl(void *dest, u32 val, u32 size) { @@ -235,80 +236,46 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr) udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr); } -static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, int idx) +static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size) { struct xsk_umem_config cfg = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, - .frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE, - .frame_headroom = frame_headroom, + .frame_size = umem->frame_size, + .frame_headroom = umem->frame_headroom, .flags = XSK_UMEM__DEFAULT_FLAGS }; - struct xsk_umem_info *umem; int ret; - umem = calloc(1, sizeof(struct xsk_umem_info)); - if (!umem) - exit_with_error(errno); + if (umem->unaligned_mode) + cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG; ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, &cfg); if (ret) - exit_with_error(-ret); + return ret; umem->buffer = buffer; - - data->umem_arr[idx] = umem; -} - -static void xsk_populate_fill_ring(struct xsk_umem_info *umem) -{ - int ret, i; - u32 idx = 0; - - ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); - if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) - exit_with_error(-ret); - for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) - *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE; - xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); + return 0; } -static int xsk_configure_socket(struct ifobject *ifobject, int idx) +static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem, + struct ifobject *ifobject, u32 qid) { struct xsk_socket_config cfg; - struct xsk_socket_info *xsk; struct xsk_ring_cons *rxr; struct xsk_ring_prod *txr; - int ret; - xsk = calloc(1, sizeof(struct xsk_socket_info)); - if (!xsk) - exit_with_error(errno); - - xsk->umem = ifobject->umem; - cfg.rx_size = rxqsize; + xsk->umem = umem; + cfg.rx_size = xsk->rxqsize; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; cfg.libbpf_flags = 0; - cfg.xdp_flags = xdp_flags; - cfg.bind_flags = xdp_bind_flags; - - if (test_type != TEST_TYPE_BIDI) { - rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL; - txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL; - } else { - rxr = &xsk->rx; - txr = &xsk->tx; - } - - ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx, - ifobject->umem->umem, rxr, txr, &cfg); - if (ret) - return 1; + cfg.xdp_flags = ifobject->xdp_flags; + cfg.bind_flags = ifobject->bind_flags; - ifobject->xsk_arr[idx] = xsk; - - return 0; + txr = ifobject->tx_on ? &xsk->tx : NULL; + rxr = ifobject->rx_on ? &xsk->rx : NULL; + return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg); } static struct option long_options[] = { @@ -354,45 +321,44 @@ static int switch_namespace(const char *nsname) return nsfd; } -static int validate_interfaces(void) +static bool validate_interface(struct ifobject *ifobj) { - bool ret = true; - - for (int i = 0; i < MAX_INTERFACES; i++) { - if (!strcmp(ifdict[i]->ifname, "")) { - ret = false; - ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>."); - } - } - return ret; + if (!strcmp(ifobj->ifname, "")) + return false; + return true; } -static void parse_command_line(int argc, char **argv) +static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx, int argc, + char **argv) { - int option_index, interface_index = 0, c; + struct ifobject *ifobj; + u32 interface_nb = 0; + int option_index, c; opterr = 0; for (;;) { - c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); + char *sptr, *token; + c = getopt_long(argc, argv, "i:Dv", long_options, &option_index); if (c == -1) break; switch (c) { case 'i': - if (interface_index == MAX_INTERFACES) + if (interface_nb == 0) + ifobj = ifobj_tx; + else if (interface_nb == 1) + ifobj = ifobj_rx; + else break; - char *sptr, *token; sptr = strndupa(optarg, strlen(optarg)); - memcpy(ifdict[interface_index]->ifname, - strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); + memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS); token = strsep(&sptr, ","); if (token) - memcpy(ifdict[interface_index]->nsname, token, - MAX_INTERFACES_NAMESPACE_CHARS); - interface_index++; + memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS); + interface_nb++; break; case 'D': opt_pkt_dump = true; @@ -405,11 +371,78 @@ static void parse_command_line(int argc, char **argv) ksft_exit_xfail(); } } +} - if (!validate_interfaces()) { - usage(basename(argv[0])); - ksft_exit_xfail(); +static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx) +{ + u32 i, j; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->umem = &ifobj->umem_arr[0]; + ifobj->xsk = &ifobj->xsk_arr[0]; + ifobj->use_poll = false; + ifobj->pkt_stream = test->pkt_stream_default; + + if (i == 0) { + ifobj->rx_on = false; + ifobj->tx_on = true; + } else { + ifobj->rx_on = true; + ifobj->tx_on = false; + } + + for (j = 0; j < MAX_SOCKETS; j++) { + memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j])); + memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j])); + ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS; + ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; + ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; + } } + + test->ifobj_tx = ifobj_tx; + test->ifobj_rx = ifobj_rx; + test->current_step = 0; + test->total_steps = 1; + test->nb_sockets = 1; +} + +static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx, + struct ifobject *ifobj_rx, enum test_mode mode) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = test->pkt_stream_default; + memset(test, 0, sizeof(*test)); + test->pkt_stream_default = pkt_stream; + + for (i = 0; i < MAX_INTERFACES; i++) { + struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx; + + ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; + if (mode == TEST_MODE_SKB) + ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE; + else + ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE; + + ifobj->bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; + } + + __test_spec_init(test, ifobj_tx, ifobj_rx); +} + +static void test_spec_reset(struct test_spec *test) +{ + __test_spec_init(test, test->ifobj_tx, test->ifobj_rx); +} + +static void test_spec_set_name(struct test_spec *test, const char *name) +{ + strncpy(test->name, name, MAX_TEST_NAME_SIZE); } static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) @@ -420,29 +453,105 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb) return &pkt_stream->pkts[pkt_nb]; } -static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len) +static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream) +{ + while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) { + if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid) + return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++]; + pkt_stream->rx_pkt_nb++; + } + return NULL; +} + +static void pkt_stream_delete(struct pkt_stream *pkt_stream) +{ + free(pkt_stream->pkts); + free(pkt_stream); +} + +static void pkt_stream_restore_default(struct test_spec *test) +{ + if (test->ifobj_tx->pkt_stream != test->pkt_stream_default) { + pkt_stream_delete(test->ifobj_tx->pkt_stream); + test->ifobj_tx->pkt_stream = test->pkt_stream_default; + } + test->ifobj_rx->pkt_stream = test->pkt_stream_default; +} + +static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts) { struct pkt_stream *pkt_stream; - u32 i; - pkt_stream = malloc(sizeof(*pkt_stream)); + pkt_stream = calloc(1, sizeof(*pkt_stream)); if (!pkt_stream) - exit_with_error(ENOMEM); + return NULL; pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts)); - if (!pkt_stream->pkts) + if (!pkt_stream->pkts) { + free(pkt_stream); + return NULL; + } + + pkt_stream->nb_pkts = nb_pkts; + return pkt_stream; +} + +static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) exit_with_error(ENOMEM); pkt_stream->nb_pkts = nb_pkts; for (i = 0; i < nb_pkts; i++) { - pkt_stream->pkts[i].addr = (i % num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE; + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + + DEFAULT_OFFSET; pkt_stream->pkts[i].len = pkt_len; pkt_stream->pkts[i].payload = i; + + if (pkt_len > umem->frame_size) + pkt_stream->pkts[i].valid = false; + else + pkt_stream->pkts[i].valid = true; } return pkt_stream; } +static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem, + struct pkt_stream *pkt_stream) +{ + return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len); +} + +static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len) +{ + struct pkt_stream *pkt_stream; + + pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len); + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + +static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset) +{ + struct xsk_umem_info *umem = test->ifobj_tx->umem; + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default); + for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) { + pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset; + pkt_stream->pkts[i].len = pkt_len; + } + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; +} + static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) { struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb); @@ -453,6 +562,8 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) if (!pkt) return NULL; + if (!pkt->valid || pkt->len < PKT_SIZE) + return pkt; data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr); udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr)); @@ -467,6 +578,26 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb) return pkt; } +static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts) +{ + struct pkt_stream *pkt_stream; + u32 i; + + pkt_stream = __pkt_stream_alloc(nb_pkts); + if (!pkt_stream) + exit_with_error(ENOMEM); + + test->ifobj_tx->pkt_stream = pkt_stream; + test->ifobj_rx->pkt_stream = pkt_stream; + + for (i = 0; i < nb_pkts; i++) { + pkt_stream->pkts[i].addr = pkts[i].addr; + pkt_stream->pkts[i].len = pkts[i].len; + pkt_stream->pkts[i].payload = i; + pkt_stream->pkts[i].valid = pkts[i].valid; + } +} + static void pkt_dump(void *pkt, u32 len) { char s[INET_ADDRSTRLEN]; @@ -504,9 +635,9 @@ static void pkt_dump(void *pkt, u32 len) fprintf(stdout, "---------------------------------------\n"); } -static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc) +static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len) { - void *data = xsk_umem__get_data(buffer, desc->addr); + void *data = xsk_umem__get_data(buffer, addr); struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr)); if (!pkt) { @@ -514,19 +645,24 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d return false; } + if (len < PKT_SIZE) { + /*Do not try to verify packets that are smaller than minimum size. */ + return true; + } + + if (pkt->len != len) { + ksft_test_result_fail + ("ERROR: [%s] expected length [%d], got length [%d]\n", + __func__, pkt->len, len); + return false; + } + if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) { u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE))); - if (opt_pkt_dump && test_type != TEST_TYPE_STATS) + if (opt_pkt_dump) pkt_dump(data, PKT_SIZE); - if (pkt->len != desc->len) { - ksft_test_result_fail - ("ERROR: [%s] expected length [%d], got length [%d]\n", - __func__, pkt->len, desc->len); - return false; - } - if (pkt->payload != seqnum) { ksft_test_result_fail ("ERROR: [%s] expected seqnum [%d], got seqnum [%d]\n", @@ -558,14 +694,20 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) unsigned int rcvd; u32 idx; - if (!xsk->outstanding_tx) - return; - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) kick_tx(xsk); rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx); if (rcvd) { + if (rcvd > xsk->outstanding_tx) { + u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1); + + ksft_test_result_fail("ERROR: [%s] Too many packets completed\n", + __func__); + ksft_print_msg("Last completion address: %llx\n", addr); + return; + } + xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; } @@ -574,11 +716,10 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size) static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *xsk, struct pollfd *fds) { - u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkt_count = 0; - struct pkt *pkt; + struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream); + u32 idx_rx = 0, idx_fq = 0, rcvd, i; int ret; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); while (pkt) { rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx); if (!rcvd) { @@ -606,13 +747,21 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++); u64 addr = desc->addr, orig; + if (!pkt) { + ksft_test_result_fail("ERROR: [%s] Received too many packets.\n", + __func__); + ksft_print_msg("Last packet has addr: %llx len: %u\n", + addr, desc->len); + return; + } + orig = xsk_umem__extract_addr(addr); addr = xsk_umem__add_offset_to_addr(addr); - if (!is_pkt_valid(pkt, xsk->umem->buffer, desc)) + if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len)) return; *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig; - pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++); + pkt = pkt_stream_get_next_rx_pkt(pkt_stream); } xsk_ring_prod__submit(&xsk->umem->fq, rcvd); @@ -623,7 +772,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info * static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) { struct xsk_socket_info *xsk = ifobject->xsk; - u32 i, idx; + u32 i, idx, valid_pkts = 0; while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE) complete_pkts(xsk, BATCH_SIZE); @@ -638,14 +787,13 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb) tx_desc->addr = pkt->addr; tx_desc->len = pkt->len; pkt_nb++; + if (pkt->valid) + valid_pkts++; } xsk_ring_prod__submit(&xsk->tx, i); - if (stat_test_type != STAT_TEST_TX_INVALID) - xsk->outstanding_tx += i; - else if (xsk_ring_prod__needs_wakeup(&xsk->tx)) - kick_tx(xsk); - complete_pkts(xsk, i); + xsk->outstanding_tx += valid_pkts; + complete_pkts(xsk, BATCH_SIZE); return i; } @@ -658,23 +806,23 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk) static void send_pkts(struct ifobject *ifobject) { - struct pollfd fds[MAX_SOCKS] = { }; + struct pollfd fds = { }; u32 pkt_cnt = 0; - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLOUT; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLOUT; while (pkt_cnt < ifobject->pkt_stream->nb_pkts) { u32 sent; - if (test_type == TEST_TYPE_POLL) { + if (ifobject->use_poll) { int ret; - ret = poll(fds, 1, POLL_TMOUT); + ret = poll(&fds, 1, POLL_TMOUT); if (ret <= 0) continue; - if (!(fds[0].revents & POLLOUT)) + if (!(fds.revents & POLLOUT)) continue; } @@ -698,7 +846,7 @@ static bool rx_stats_are_valid(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Rx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return true; } @@ -739,7 +887,7 @@ static void tx_stats_validate(struct ifobject *ifobject) optlen = sizeof(stats); err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen); if (err) { - ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", + ksft_test_result_fail("ERROR Tx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n", __func__, -err, strerror(-err)); return; } @@ -751,71 +899,63 @@ static void tx_stats_validate(struct ifobject *ifobject) __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts); } -static void thread_common_ops(struct ifobject *ifobject, void *bufs) +static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject) { - u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE; int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE; - size_t mmap_sz = umem_sz; - int ctr = 0; - int ret; + u32 i; ifobject->ns_fd = switch_namespace(ifobject->nsname); - if (test_type == TEST_TYPE_BPF_RES) - mmap_sz *= 2; + if (ifobject->umem->unaligned_mode) + mmap_flags |= MAP_HUGETLB; - bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); - if (bufs == MAP_FAILED) - exit_with_error(errno); + for (i = 0; i < test->nb_sockets; i++) { + u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size; + u32 ctr = 0; + void *bufs; - while (ctr++ < SOCK_RECONF_CTR) { - xsk_configure_umem(ifobject, bufs, umem_sz, 0); - ifobject->umem = ifobject->umem_arr[0]; - ret = xsk_configure_socket(ifobject, 0); - if (!ret) - break; + bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0); + if (bufs == MAP_FAILED) + exit_with_error(errno); - /* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */ - usleep(USLEEP_MAX); - if (ctr >= SOCK_RECONF_CTR) - exit_with_error(-ret); - } + while (ctr++ < SOCK_RECONF_CTR) { + int ret; - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; + ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz); + if (ret) + exit_with_error(-ret); - if (test_type == TEST_TYPE_BPF_RES) { - xsk_configure_umem(ifobject, (u8 *)bufs + umem_sz, umem_sz, 1); - ifobject->umem = ifobject->umem_arr[1]; - ret = xsk_configure_socket(ifobject, 1); - } + ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i], + ifobject, i); + if (!ret) + break; - ifobject->umem = ifobject->umem_arr[0]; - ifobject->xsk = ifobject->xsk_arr[0]; - print_verbose("Interface [%s] vector [%s]\n", - ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx"); -} + /* Retry if it fails as xsk_socket__create() is asynchronous */ + if (ctr >= SOCK_RECONF_CTR) + exit_with_error(-ret); + usleep(USLEEP_MAX); + } + } -static bool testapp_is_test_two_stepped(void) -{ - return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step; + ifobject->umem = &ifobject->umem_arr[0]; + ifobject->xsk = &ifobject->xsk_arr[0]; } static void testapp_cleanup_xsk_res(struct ifobject *ifobj) { - if (testapp_is_test_two_stepped()) { - xsk_socket__delete(ifobj->xsk->xsk); - (void)xsk_umem__delete(ifobj->umem->umem); - } + print_verbose("Destroying socket\n"); + xsk_socket__delete(ifobj->xsk->xsk); + munmap(ifobj->umem->buffer, ifobj->umem->num_frames * ifobj->umem->frame_size); + xsk_umem__delete(ifobj->umem->umem); } static void *worker_testapp_validate_tx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_tx; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts, ifobject->ifname); @@ -824,24 +964,50 @@ static void *worker_testapp_validate_tx(void *arg) if (stat_test_type == STAT_TEST_TX_INVALID) tx_stats_validate(ifobject); - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } +static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream) +{ + u32 idx = 0, i; + int ret; + + ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx); + if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) + exit_with_error(ENOSPC); + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) { + u64 addr; + + if (pkt_stream->use_addr_for_fill) { + struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i); + + if (!pkt) + break; + addr = pkt->addr; + } else { + addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET; + } + + *xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr; + } + xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); +} + static void *worker_testapp_validate_rx(void *arg) { - struct ifobject *ifobject = (struct ifobject *)arg; - struct pollfd fds[MAX_SOCKS] = { }; - void *bufs = NULL; + struct test_spec *test = (struct test_spec *)arg; + struct ifobject *ifobject = test->ifobj_rx; + struct pollfd fds = { }; - if (!second_step) - thread_common_ops(ifobject, bufs); + if (test->current_step == 1) + thread_common_ops(test, ifobject); - if (stat_test_type != STAT_TEST_RX_FILL_EMPTY) - xsk_populate_fill_ring(ifobject->umem); + xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream); - fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk); - fds[0].events = POLLIN; + fds.fd = xsk_socket__fd(ifobject->xsk->xsk); + fds.events = POLLIN; pthread_barrier_wait(&barr); @@ -849,151 +1015,219 @@ static void *worker_testapp_validate_rx(void *arg) while (!rx_stats_are_valid(ifobject)) continue; else - receive_pkts(ifobject->pkt_stream, ifobject->xsk, fds); - - if (test_type == TEST_TYPE_TEARDOWN) - print_verbose("Destroying socket\n"); + receive_pkts(ifobject->pkt_stream, ifobject->xsk, &fds); - testapp_cleanup_xsk_res(ifobject); + if (test->total_steps == test->current_step) + testapp_cleanup_xsk_res(ifobject); pthread_exit(NULL); } -static void testapp_validate(void) +static void testapp_validate_traffic(struct test_spec *test) { - bool bidi = test_type == TEST_TYPE_BIDI; - bool bpf = test_type == TEST_TYPE_BPF_RES; - struct pkt_stream *pkt_stream; + struct ifobject *ifobj_tx = test->ifobj_tx; + struct ifobject *ifobj_rx = test->ifobj_rx; + pthread_t t0, t1; if (pthread_barrier_init(&barr, NULL, 2)) exit_with_error(errno); - if (stat_test_type == STAT_TEST_TX_INVALID) - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); - else - pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE); - ifdict_tx->pkt_stream = pkt_stream; - ifdict_rx->pkt_stream = pkt_stream; + test->current_step++; /*Spawn RX thread */ - pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx); + pthread_create(&t0, NULL, ifobj_rx->func_ptr, test); pthread_barrier_wait(&barr); if (pthread_barrier_destroy(&barr)) exit_with_error(errno); /*Spawn TX thread */ - pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx); + pthread_create(&t1, NULL, ifobj_tx->func_ptr, test); pthread_join(t1, NULL); pthread_join(t0, NULL); - - if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS)) - print_ksft_result(); } -static void testapp_teardown(void) +static void testapp_teardown(struct test_spec *test) { int i; + test_spec_set_name(test, "TEARDOWN"); for (i = 0; i < MAX_TEARDOWN_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); + testapp_validate_traffic(test); + test_spec_reset(test); } - - print_ksft_result(); } -static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2) +static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2) { - void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr; - enum fvector tmp_vector = ifobj1->fv.vector; + thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr; + struct ifobject *tmp_ifobj = (*ifobj1); - ifobj1->func_ptr = ifobj2->func_ptr; - ifobj1->fv.vector = ifobj2->fv.vector; + (*ifobj1)->func_ptr = (*ifobj2)->func_ptr; + (*ifobj2)->func_ptr = tmp_func_ptr; - ifobj2->func_ptr = tmp_func_ptr; - ifobj2->fv.vector = tmp_vector; - - ifdict_tx = ifobj1; - ifdict_rx = ifobj2; + *ifobj1 = *ifobj2; + *ifobj2 = tmp_ifobj; } -static void testapp_bidi(void) +static void testapp_bidi(struct test_spec *test) { - for (int i = 0; i < MAX_BIDI_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) { - print_verbose("Switching Tx/Rx vectors\n"); - swap_vectors(ifdict[1], ifdict[0]); - } - second_step = true; - } + test_spec_set_name(test, "BIDIRECTIONAL"); + test->ifobj_tx->rx_on = true; + test->ifobj_rx->tx_on = true; + test->total_steps = 2; + testapp_validate_traffic(test); - swap_vectors(ifdict[0], ifdict[1]); + print_verbose("Switching Tx/Rx vectors\n"); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); + testapp_validate_traffic(test); - print_ksft_result(); + swap_directions(&test->ifobj_rx, &test->ifobj_tx); } -static void swap_xsk_res(void) +static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx) { - xsk_socket__delete(ifdict_tx->xsk->xsk); - xsk_umem__delete(ifdict_tx->umem->umem); - xsk_socket__delete(ifdict_rx->xsk->xsk); - xsk_umem__delete(ifdict_rx->umem->umem); - ifdict_tx->umem = ifdict_tx->umem_arr[1]; - ifdict_tx->xsk = ifdict_tx->xsk_arr[1]; - ifdict_rx->umem = ifdict_rx->umem_arr[1]; - ifdict_rx->xsk = ifdict_rx->xsk_arr[1]; + xsk_socket__delete(ifobj_tx->xsk->xsk); + xsk_umem__delete(ifobj_tx->umem->umem); + xsk_socket__delete(ifobj_rx->xsk->xsk); + xsk_umem__delete(ifobj_rx->umem->umem); + ifobj_tx->umem = &ifobj_tx->umem_arr[1]; + ifobj_tx->xsk = &ifobj_tx->xsk_arr[1]; + ifobj_rx->umem = &ifobj_rx->umem_arr[1]; + ifobj_rx->xsk = &ifobj_rx->xsk_arr[1]; } -static void testapp_bpf_res(void) +static void testapp_bpf_res(struct test_spec *test) { - int i; + test_spec_set_name(test, "BPF_RES"); + test->total_steps = 2; + test->nb_sockets = 2; + testapp_validate_traffic(test); - for (i = 0; i < MAX_BPF_ITER; i++) { - print_verbose("Creating socket\n"); - testapp_validate(); - if (!second_step) - swap_xsk_res(); - second_step = true; - } - - print_ksft_result(); + swap_xsk_resources(test->ifobj_tx, test->ifobj_rx); + testapp_validate_traffic(test); } -static void testapp_stats(void) +static void testapp_stats(struct test_spec *test) { - for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) { - stat_test_type = i; + int i; - /* reset defaults */ - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; + for (i = 0; i < STAT_TEST_TYPE_MAX; i++) { + test_spec_reset(test); + stat_test_type = i; switch (stat_test_type) { case STAT_TEST_RX_DROPPED: - frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE - - XDP_PACKET_HEADROOM - 1; + test_spec_set_name(test, "STAT_RX_DROPPED"); + test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size - + XDP_PACKET_HEADROOM - 1; + testapp_validate_traffic(test); break; case STAT_TEST_RX_FULL: - rxqsize = RX_FULL_RXQSIZE; + test_spec_set_name(test, "STAT_RX_FULL"); + test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE; + testapp_validate_traffic(test); break; case STAT_TEST_TX_INVALID: - continue; + test_spec_set_name(test, "STAT_TX_INVALID"); + pkt_stream_replace(test, DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case STAT_TEST_RX_FILL_EMPTY: + test_spec_set_name(test, "STAT_RX_FILL_EMPTY"); + test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, 0, + MIN_PKT_SIZE); + if (!test->ifobj_rx->pkt_stream) + exit_with_error(ENOMEM); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; default: break; } - testapp_validate(); } - print_ksft_result(); + /* To only see the whole stat set being completed unless an individual test fails. */ + test_spec_set_name(test, "STATS"); +} + +/* Simple test */ +static bool hugepages_present(struct ifobject *ifobject) +{ + const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size; + void *bufs; + + bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0); + if (bufs == MAP_FAILED) + return false; + + munmap(bufs, mmap_sz); + return true; +} + +static bool testapp_unaligned(struct test_spec *test) +{ + if (!hugepages_present(test->ifobj_tx)) { + ksft_test_result_skip("No 2M huge pages present.\n"); + return false; + } + + test_spec_set_name(test, "UNALIGNED_MODE"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + /* Let half of the packets straddle a buffer boundrary */ + pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32); + test->ifobj_rx->pkt_stream->use_addr_for_fill = true; + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + return true; +} + +static void testapp_invalid_desc(struct test_spec *test) +{ + struct pkt pkts[] = { + /* Zero packet length at address zero allowed */ + {0, 0, 0, true}, + /* Zero packet length allowed */ + {0x1000, 0, 0, true}, + /* Straddling the start of umem */ + {-2, PKT_SIZE, 0, false}, + /* Packet too large */ + {0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false}, + /* After umem ends */ + {UMEM_SIZE, PKT_SIZE, 0, false}, + /* Straddle the end of umem */ + {UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a page boundrary */ + {0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false}, + /* Straddle a 2K boundrary */ + {0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true}, + /* Valid packet for synch so that something is received */ + {0x4000, PKT_SIZE, 0, true}}; + + if (test->ifobj_tx->umem->unaligned_mode) { + /* Crossing a page boundrary allowed */ + pkts[6].valid = true; + } + if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) { + /* Crossing a 2K frame size boundrary not allowed */ + pkts[7].valid = false; + } + + pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts)); + testapp_validate_traffic(test); + pkt_stream_restore_default(test); } -static void init_iface(struct ifobject *ifobj, const char *dst_mac, - const char *src_mac, const char *dst_ip, - const char *src_ip, const u16 dst_port, - const u16 src_port, enum fvector vector) +static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac, + const char *dst_ip, const char *src_ip, const u16 dst_port, + const u16 src_port, thread_func_t func_ptr) { struct in_addr ip; @@ -1009,58 +1243,73 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, ifobj->dst_port = dst_port; ifobj->src_port = src_port; - if (vector == tx) { - ifobj->fv.vector = tx; - ifobj->func_ptr = worker_testapp_validate_tx; - ifdict_tx = ifobj; - } else { - ifobj->fv.vector = rx; - ifobj->func_ptr = worker_testapp_validate_rx; - ifdict_rx = ifobj; - } + ifobj->func_ptr = func_ptr; } -static void run_pkt_test(int mode, int type) +static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type) { test_type = type; /* reset defaults after potential previous test */ - xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; - second_step = 0; stat_test_type = -1; - rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS; - frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; - - configured_mode = mode; - - switch (mode) { - case (TEST_MODE_SKB): - xdp_flags |= XDP_FLAGS_SKB_MODE; - break; - case (TEST_MODE_DRV): - xdp_flags |= XDP_FLAGS_DRV_MODE; - break; - default: - break; - } switch (test_type) { case TEST_TYPE_STATS: - testapp_stats(); + testapp_stats(test); break; case TEST_TYPE_TEARDOWN: - testapp_teardown(); + testapp_teardown(test); break; case TEST_TYPE_BIDI: - testapp_bidi(); + testapp_bidi(test); break; case TEST_TYPE_BPF_RES: - testapp_bpf_res(); + testapp_bpf_res(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION: + test_spec_set_name(test, "RUN_TO_COMPLETION"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME: + test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE); + testapp_validate_traffic(test); + + pkt_stream_restore_default(test); + break; + case TEST_TYPE_POLL: + test->ifobj_tx->use_poll = true; + test->ifobj_rx->use_poll = true; + test_spec_set_name(test, "POLL"); + testapp_validate_traffic(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC: + test_spec_set_name(test, "ALIGNED_INV_DESC"); + testapp_invalid_desc(test); + break; + case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME: + test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE"); + test->ifobj_tx->umem->frame_size = 2048; + test->ifobj_rx->umem->frame_size = 2048; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED_INV_DESC: + test_spec_set_name(test, "UNALIGNED_INV_DESC"); + test->ifobj_tx->umem->unaligned_mode = true; + test->ifobj_rx->umem->unaligned_mode = true; + testapp_invalid_desc(test); + break; + case TEST_TYPE_UNALIGNED: + if (!testapp_unaligned(test)) + return; break; default: - testapp_validate(); break; } + + print_ksft_result(test); } static struct ifobject *ifobject_create(void) @@ -1071,11 +1320,11 @@ static struct ifobject *ifobject_create(void) if (!ifobj) return NULL; - ifobj->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *)); + ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr)); if (!ifobj->xsk_arr) goto out_xsk_arr; - ifobj->umem_arr = calloc(2, sizeof(struct xsk_umem_info *)); + ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr)); if (!ifobj->umem_arr) goto out_umem_arr; @@ -1098,34 +1347,53 @@ static void ifobject_delete(struct ifobject *ifobj) int main(int argc, char **argv) { struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY }; - int i, j; + struct pkt_stream *pkt_stream_default; + struct ifobject *ifobj_tx, *ifobj_rx; + struct test_spec test; + u32 i, j; if (setrlimit(RLIMIT_MEMLOCK, &_rlim)) exit_with_error(errno); - for (i = 0; i < MAX_INTERFACES; i++) { - ifdict[i] = ifobject_create(); - if (!ifdict[i]) - exit_with_error(ENOMEM); - } + ifobj_tx = ifobject_create(); + if (!ifobj_tx) + exit_with_error(ENOMEM); + ifobj_rx = ifobject_create(); + if (!ifobj_rx) + exit_with_error(ENOMEM); setlocale(LC_ALL, ""); - parse_command_line(argc, argv); + parse_command_line(ifobj_tx, ifobj_rx, argc, argv); - init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx); - init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx); + if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) { + usage(basename(argv[0])); + ksft_exit_xfail(); + } + + init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, + worker_testapp_validate_tx); + init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, + worker_testapp_validate_rx); + + test_spec_init(&test, ifobj_tx, ifobj_rx, 0); + pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE); + if (!pkt_stream_default) + exit_with_error(ENOMEM); + test.pkt_stream_default = pkt_stream_default; ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX); for (i = 0; i < TEST_MODE_MAX; i++) for (j = 0; j < TEST_TYPE_MAX; j++) { - run_pkt_test(i, j); + test_spec_init(&test, ifobj_tx, ifobj_rx, i); + run_pkt_test(&test, i, j); usleep(USLEEP_MAX); } - for (i = 0; i < MAX_INTERFACES; i++) - ifobject_delete(ifdict[i]); + pkt_stream_delete(pkt_stream_default); + ifobject_delete(ifobj_tx); + ifobject_delete(ifobj_rx); ksft_exit_pass(); return 0; diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h index 7e49b9fbe25e10..5ac4a5e6474451 100644 --- a/tools/testing/selftests/bpf/xdpxceiver.h +++ b/tools/testing/selftests/bpf/xdpxceiver.h @@ -20,10 +20,9 @@ #define MAX_INTERFACES 2 #define MAX_INTERFACE_NAME_CHARS 7 #define MAX_INTERFACES_NAMESPACE_CHARS 10 -#define MAX_SOCKS 1 +#define MAX_SOCKETS 2 +#define MAX_TEST_NAME_SIZE 32 #define MAX_TEARDOWN_ITER 10 -#define MAX_BIDI_ITER 2 -#define MAX_BPF_ITER 2 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ sizeof(struct udphdr)) #define MIN_PKT_SIZE 64 @@ -39,7 +38,10 @@ #define BATCH_SIZE 8 #define POLL_TMOUT 1000 #define DEFAULT_PKT_CNT (4 * 1024) +#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4) +#define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE) #define RX_FULL_RXQSIZE 32 +#define DEFAULT_OFFSET 256 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1) #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0) @@ -51,8 +53,13 @@ enum test_mode { }; enum test_type { - TEST_TYPE_NOPOLL, + TEST_TYPE_RUN_TO_COMPLETION, + TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME, TEST_TYPE_POLL, + TEST_TYPE_UNALIGNED, + TEST_TYPE_ALIGNED_INV_DESC, + TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME, + TEST_TYPE_UNALIGNED_INV_DESC, TEST_TYPE_TEARDOWN, TEST_TYPE_BIDI, TEST_TYPE_STATS, @@ -68,25 +75,21 @@ enum stat_test_type { STAT_TEST_TYPE_MAX }; -static int configured_mode; static bool opt_pkt_dump; -static u32 num_frames = DEFAULT_PKT_CNT / 4; -static bool second_step; static int test_type; static bool opt_verbose; - -static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; -static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY; static int stat_test_type; -static u32 rxqsize; -static u32 frame_headroom; struct xsk_umem_info { struct xsk_ring_prod fq; struct xsk_ring_cons cq; struct xsk_umem *umem; + u32 num_frames; + u32 frame_headroom; void *buffer; + u32 frame_size; + bool unaligned_mode; }; struct xsk_socket_info { @@ -95,51 +98,58 @@ struct xsk_socket_info { struct xsk_umem_info *umem; struct xsk_socket *xsk; u32 outstanding_tx; -}; - -struct flow_vector { - enum fvector { - tx, - rx, - } vector; + u32 rxqsize; }; struct pkt { u64 addr; u32 len; u32 payload; + bool valid; }; struct pkt_stream { u32 nb_pkts; + u32 rx_pkt_nb; struct pkt *pkts; + bool use_addr_for_fill; }; +typedef void *(*thread_func_t)(void *arg); + struct ifobject { char ifname[MAX_INTERFACE_NAME_CHARS]; char nsname[MAX_INTERFACES_NAMESPACE_CHARS]; struct xsk_socket_info *xsk; - struct xsk_socket_info **xsk_arr; - struct xsk_umem_info **umem_arr; + struct xsk_socket_info *xsk_arr; struct xsk_umem_info *umem; - void *(*func_ptr)(void *arg); - struct flow_vector fv; + struct xsk_umem_info *umem_arr; + thread_func_t func_ptr; struct pkt_stream *pkt_stream; int ns_fd; u32 dst_ip; u32 src_ip; + u32 xdp_flags; + u32 bind_flags; u16 src_port; u16 dst_port; + bool tx_on; + bool rx_on; + bool use_poll; u8 dst_mac[ETH_ALEN]; u8 src_mac[ETH_ALEN]; }; -static struct ifobject *ifdict[MAX_INTERFACES]; -static struct ifobject *ifdict_rx; -static struct ifobject *ifdict_tx; +struct test_spec { + struct ifobject *ifobj_tx; + struct ifobject *ifobj_rx; + struct pkt_stream *pkt_stream_default; + u16 total_steps; + u16 current_step; + u16 nb_sockets; + char name[MAX_TEST_NAME_SIZE]; +}; -/*threads*/ pthread_barrier_t barr; -pthread_t t0, t1; #endif /* XDPXCEIVER_H */ diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh index 7ca1f030d20990..922744059aaa24 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh @@ -50,7 +50,7 @@ function make_netdev { modprobe netdevsim fi - echo $NSIM_ID > /sys/bus/netdevsim/new_device + echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device # get new device name ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/ } diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh new file mode 100755 index 00000000000000..fd13c8cfb7a87a --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only + +source ethtool-common.sh + +set -o pipefail + +n_children() { + n=$(tc qdisc show dev $NDEV | grep '^qdisc' | wc -l) + echo $((n - 1)) +} + +tcq() { + tc qdisc $1 dev $NDEV ${@:2} +} + +n_child_assert() { + n=$(n_children) + if [ $n -ne $1 ]; then + echo "ERROR ($root): ${@:2}, expected $1 have $n" + ((num_errors++)) + else + ((num_passes++)) + fi +} + + +for root in mq mqprio; do + NDEV=$(make_netdev 1 4) + + opts= + [ $root == "mqprio" ] && opts='hw 0 num_tc 1 map 0 0 0 0 queues 1@0' + + tcq add root handle 100: $root $opts + n_child_assert 4 'Init' + + # All defaults + + for n in 3 2 1 2 3 4 1 4; do + ethtool -L $NDEV combined $n + n_child_assert $n "Change queues to $n while down" + done + + ip link set dev $NDEV up + + for n in 3 2 1 2 3 4 1 4; do + ethtool -L $NDEV combined $n + n_child_assert $n "Change queues to $n while up" + done + + # One real one + tcq replace parent 100:4 handle 204: pfifo_fast + n_child_assert 4 "One real queue" + + ethtool -L $NDEV combined 1 + n_child_assert 2 "One real queue, one default" + + ethtool -L $NDEV combined 4 + n_child_assert 4 "One real queue, rest default" + + # Graft some + tcq replace parent 100:1 handle 204: + n_child_assert 3 "Grafted" + + ethtool -L $NDEV combined 1 + n_child_assert 1 "Grafted, one" + + cleanup_nsim +done + +if [ $num_errors -eq 0 ]; then + echo "PASSED all $((num_passes)) checks" + exit 0 +else + echo "FAILED $num_errors/$((num_errors+num_passes)) checks" + exit 1 +fi diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 0d293391e9a449..b5a69ad191b078 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -2078,6 +2078,7 @@ basic_res() "id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1" log_test $? 0 "Dump all nexthop buckets in a group" + sleep 0.1 (( $($IP -j nexthop bucket list id 101 | jq '[.[] | select(.bucket.idle_time > 0 and .bucket.idle_time < 2)] | length') == 4 )) diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore index 260336d5f0b13f..7569d892967a99 100644 --- a/tools/testing/selftests/net/mptcp/.gitignore +++ b/tools/testing/selftests/net/mptcp/.gitignore @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only mptcp_connect +mptcp_sockopt pm_nl_ctl *.pcap diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index f1464f09b080fa..bbf4e448bad997 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -8,7 +8,7 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh -TEST_GEN_FILES = mptcp_connect pm_nl_ctl +TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt TEST_FILES := settings diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c new file mode 100644 index 00000000000000..417b11cafafe7a --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -0,0 +1,683 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <assert.h> +#include <errno.h> +#include <limits.h> +#include <string.h> +#include <stdarg.h> +#include <stdbool.h> +#include <stdint.h> +#include <inttypes.h> +#include <stdio.h> +#include <stdlib.h> +#include <strings.h> +#include <unistd.h> + +#include <sys/socket.h> +#include <sys/types.h> +#include <sys/wait.h> + +#include <netdb.h> +#include <netinet/in.h> + +#include <linux/tcp.h> + +static int pf = AF_INET; + +#ifndef IPPROTO_MPTCP +#define IPPROTO_MPTCP 262 +#endif +#ifndef SOL_MPTCP +#define SOL_MPTCP 284 +#endif + +#ifndef MPTCP_INFO +struct mptcp_info { + __u8 mptcpi_subflows; + __u8 mptcpi_add_addr_signal; + __u8 mptcpi_add_addr_accepted; + __u8 mptcpi_subflows_max; + __u8 mptcpi_add_addr_signal_max; + __u8 mptcpi_add_addr_accepted_max; + __u32 mptcpi_flags; + __u32 mptcpi_token; + __u64 mptcpi_write_seq; + __u64 mptcpi_snd_una; + __u64 mptcpi_rcv_nxt; + __u8 mptcpi_local_addr_used; + __u8 mptcpi_local_addr_max; + __u8 mptcpi_csum_enabled; +}; + +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 +#endif + +struct so_state { + struct mptcp_info mi; + uint64_t mptcpi_rcv_delta; + uint64_t tcpi_rcv_delta; +}; + +static void die_perror(const char *msg) +{ + perror(msg); + exit(1); +} + +static void die_usage(int r) +{ + fprintf(stderr, "Usage: mptcp_sockopt [-6]\n"); + exit(r); +} + +static void xerror(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + va_end(ap); + fputc('\n', stderr); + exit(1); +} + +static const char *getxinfo_strerr(int err) +{ + if (err == EAI_SYSTEM) + return strerror(errno); + + return gai_strerror(err); +} + +static void xgetaddrinfo(const char *node, const char *service, + const struct addrinfo *hints, + struct addrinfo **res) +{ + int err = getaddrinfo(node, service, hints, res); + + if (err) { + const char *errstr = getxinfo_strerr(err); + + fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n", + node ? node : "", service ? service : "", errstr); + exit(1); + } +} + +static int sock_listen_mptcp(const char * const listenaddr, + const char * const port) +{ + int sock; + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + .ai_flags = AI_PASSIVE | AI_NUMERICHOST + }; + + hints.ai_family = pf; + + struct addrinfo *a, *addr; + int one = 1; + + xgetaddrinfo(listenaddr, port, &hints, &addr); + hints.ai_family = pf; + + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP); + if (sock < 0) + continue; + + if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one, + sizeof(one))) + perror("setsockopt"); + + if (bind(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + perror("bind"); + close(sock); + sock = -1; + } + + freeaddrinfo(addr); + + if (sock < 0) + xerror("could not create listen socket"); + + if (listen(sock, 20)) + die_perror("listen"); + + return sock; +} + +static int sock_connect_mptcp(const char * const remoteaddr, + const char * const port, int proto) +{ + struct addrinfo hints = { + .ai_protocol = IPPROTO_TCP, + .ai_socktype = SOCK_STREAM, + }; + struct addrinfo *a, *addr; + int sock = -1; + + hints.ai_family = pf; + + xgetaddrinfo(remoteaddr, port, &hints, &addr); + for (a = addr; a; a = a->ai_next) { + sock = socket(a->ai_family, a->ai_socktype, proto); + if (sock < 0) + continue; + + if (connect(sock, a->ai_addr, a->ai_addrlen) == 0) + break; /* success */ + + die_perror("connect"); + } + + if (sock < 0) + xerror("could not create connect socket"); + + freeaddrinfo(addr); + return sock; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "h6")) != -1) { + switch (c) { + case 'h': + die_usage(0); + break; + case '6': + pf = AF_INET6; + break; + default: + die_usage(1); + break; + } + } +} + +static void do_getsockopt_bogus_sf_data(int fd, int optname) +{ + struct mptcp_subflow_data good_data; + struct bogus_data { + struct mptcp_subflow_data d; + char buf[2]; + } bd; + socklen_t olen, _olen; + int ret; + + memset(&bd, 0, sizeof(bd)); + memset(&good_data, 0, sizeof(good_data)); + + olen = sizeof(good_data); + good_data.size_subflow_data = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* 0 size_subflow_data */ + assert(olen == sizeof(good_data)); + + bd.d = good_data; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + assert(olen == sizeof(good_data)); + assert(bd.d.num_subflows == 1); + assert(bd.d.size_kernel > 0); + assert(bd.d.size_user == 0); + + bd.d = good_data; + _olen = rand() % olen; + olen = _olen; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* bogus olen */ + assert(olen == _olen); /* must be unchanged */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.size_kernel = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* size_kernel not 0 */ + + bd.d = good_data; + olen = sizeof(good_data); + bd.d.num_subflows = 1; + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret < 0); /* num_subflows not 0 */ + + /* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */ + bd.d = good_data; + olen = sizeof(bd); + bd.d.size_subflow_data = sizeof(bd); + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen); + assert(ret == 0); + + /* olen must be truncated to real data size filled by kernel: */ + assert(olen == sizeof(good_data)); + + assert(bd.d.size_subflow_data == sizeof(bd)); + + bd.d = good_data; + bd.d.size_subflow_data += 1; + bd.d.size_user = 1; + olen = bd.d.size_subflow_data + 1; + _olen = olen; + + ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen); + assert(ret == 0); + + /* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */ + assert(olen == _olen); + + assert(bd.d.size_subflow_data == sizeof(good_data) + 1); + assert(bd.buf[0] == 0); +} + +static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w) +{ + struct mptcp_info i; + socklen_t olen; + int ret; + + olen = sizeof(i); + ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen); + + if (ret < 0) + die_perror("getsockopt MPTCP_INFO"); + + assert(olen == sizeof(i)); + + if (s->mi.mptcpi_write_seq == 0) + s->mi = i; + + assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq); + + s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt; +} + +static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w) +{ + struct my_tcp_info { + struct mptcp_subflow_data d; + struct tcp_info ti[2]; + } ti; + int ret, tries = 5; + socklen_t olen; + + do { + memset(&ti, 0, sizeof(ti)); + + ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + ti.d.size_user = sizeof(struct tcp_info); + olen = sizeof(ti); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen); + if (ret < 0) + xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)"); + + assert(olen <= sizeof(ti)); + assert(ti.d.size_user == ti.d.size_kernel); + assert(ti.d.size_user == sizeof(struct tcp_info)); + assert(ti.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == sizeof(struct tcp_info)); + + if (ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received == r) + goto done; + + if (r == 0 && ti.ti[0].tcpi_bytes_sent == w && + ti.ti[0].tcpi_bytes_received) { + s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received; + goto done; + } + + /* wait and repeat, might be that tx is still ongoing */ + sleep(1); + } while (tries-- > 0); + + xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu", + ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r); + +done: + do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO); +} + +static void do_getsockopt_subflow_addrs(int fd) +{ + struct sockaddr_storage remote, local; + socklen_t olen, rlen, llen; + int ret; + struct my_addrs { + struct mptcp_subflow_data d; + struct mptcp_subflow_addrs addr[2]; + } addrs; + + memset(&addrs, 0, sizeof(addrs)); + memset(&local, 0, sizeof(local)); + memset(&remote, 0, sizeof(remote)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(struct mptcp_subflow_addrs); + olen = sizeof(addrs); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + if (ret < 0) + die_perror("getsockopt MPTCP_SUBFLOW_ADDRS"); + + assert(olen <= sizeof(addrs)); + assert(addrs.d.size_user == addrs.d.size_kernel); + assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs)); + assert(addrs.d.num_subflows == 1); + + assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data)); + olen -= sizeof(struct mptcp_subflow_data); + assert(olen == sizeof(struct mptcp_subflow_addrs)); + + llen = sizeof(local); + ret = getsockname(fd, (struct sockaddr *)&local, &llen); + if (ret < 0) + die_perror("getsockname"); + rlen = sizeof(remote); + ret = getpeername(fd, (struct sockaddr *)&remote, &rlen); + if (ret < 0) + die_perror("getpeername"); + + assert(rlen > 0); + assert(rlen == llen); + + assert(remote.ss_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0); + + memset(&addrs, 0, sizeof(addrs)); + + addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data); + addrs.d.size_user = sizeof(sa_family_t); + olen = sizeof(addrs.d) + sizeof(sa_family_t); + + ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen); + assert(ret == 0); + assert(olen == sizeof(addrs.d) + sizeof(sa_family_t)); + + assert(addrs.addr[0].sa_family == pf); + assert(addrs.addr[0].sa_family == local.ss_family); + + assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0); + assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0); + + do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS); +} + +static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w) +{ + do_getsockopt_mptcp_info(s, fd, w); + + do_getsockopt_tcp_info(s, fd, r, w); + + do_getsockopt_subflow_addrs(fd); +} + +static void connect_one_server(int fd, int pipefd) +{ + char buf[4096], buf2[4096]; + size_t len, i, total; + struct so_state s; + bool eof = false; + ssize_t ret; + + memset(&s, 0, sizeof(s)); + + len = rand() % (sizeof(buf) - 1); + + if (len < 128) + len = 128; + + for (i = 0; i < len ; i++) { + buf[i] = rand() % 26; + buf[i] += 'A'; + } + + buf[i] = '\n'; + + do_getsockopts(&s, fd, 0, 0); + + /* un-block server */ + ret = read(pipefd, buf2, 4); + assert(ret == 4); + close(pipefd); + + assert(strncmp(buf2, "xmit", 4) == 0); + + ret = write(fd, buf, len); + if (ret < 0) + die_perror("write"); + + if (ret != (ssize_t)len) + xerror("short write"); + + total = 0; + do { + ret = read(fd, buf2 + total, sizeof(buf2) - total); + if (ret < 0) + die_perror("read"); + if (ret == 0) { + eof = true; + break; + } + + total += ret; + } while (total < len); + + if (total != len) + xerror("total %lu, len %lu eof %d\n", total, len, eof); + + if (memcmp(buf, buf2, len)) + xerror("data corruption"); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta <= total); + + do_getsockopts(&s, fd, ret, ret); + + if (eof) + total += 1; /* sequence advances due to FIN */ + + assert(s.mptcpi_rcv_delta == (uint64_t)total); + close(fd); +} + +static void process_one_client(int fd, int pipefd) +{ + ssize_t ret, ret2, ret3; + struct so_state s; + char buf[4096]; + + memset(&s, 0, sizeof(s)); + do_getsockopts(&s, fd, 0, 0); + + ret = write(pipefd, "xmit", 4); + assert(ret == 4); + + ret = read(fd, buf, sizeof(buf)); + if (ret < 0) + die_perror("read"); + + assert(s.mptcpi_rcv_delta <= (uint64_t)ret); + + if (s.tcpi_rcv_delta) + assert(s.tcpi_rcv_delta == (uint64_t)ret); + + ret2 = write(fd, buf, ret); + if (ret2 < 0) + die_perror("write"); + + /* wait for hangup */ + ret3 = read(fd, buf, 1); + if (ret3 != 0) + xerror("expected EOF, got %lu", ret3); + + do_getsockopts(&s, fd, ret, ret2); + if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + close(fd); +} + +static int xaccept(int s) +{ + int fd = accept(s, NULL, 0); + + if (fd < 0) + die_perror("accept"); + + return fd; +} + +static int server(int pipefd) +{ + int fd = -1, r; + + switch (pf) { + case AF_INET: + fd = sock_listen_mptcp("127.0.0.1", "15432"); + break; + case AF_INET6: + fd = sock_listen_mptcp("::1", "15432"); + break; + default: + xerror("Unknown pf %d\n", pf); + break; + } + + r = write(pipefd, "conn", 4); + assert(r == 4); + + alarm(15); + r = xaccept(fd); + + process_one_client(r, pipefd); + + return 0; +} + +static int client(int pipefd) +{ + int fd = -1; + + alarm(15); + + switch (pf) { + case AF_INET: + fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP); + break; + case AF_INET6: + fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP); + break; + default: + xerror("Unknown pf %d\n", pf); + } + + connect_one_server(fd, pipefd); + + return 0; +} + +static pid_t xfork(void) +{ + pid_t p = fork(); + + if (p < 0) + die_perror("fork"); + + return p; +} + +static int rcheck(int wstatus, const char *what) +{ + if (WIFEXITED(wstatus)) { + if (WEXITSTATUS(wstatus) == 0) + return 0; + fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus)); + return WEXITSTATUS(wstatus); + } else if (WIFSIGNALED(wstatus)) { + xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus)); + } else if (WIFSTOPPED(wstatus)) { + xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus)); + } + + return 111; +} + +int main(int argc, char *argv[]) +{ + int e1, e2, wstatus; + pid_t s, c, ret; + int pipefds[2]; + + parse_opts(argc, argv); + + e1 = pipe(pipefds); + if (e1 < 0) + die_perror("pipe"); + + s = xfork(); + if (s == 0) + return server(pipefds[1]); + + close(pipefds[1]); + + /* wait until server bound a socket */ + e1 = read(pipefds[0], &e1, 4); + assert(e1 == 4); + + c = xfork(); + if (c == 0) + return client(pipefds[0]); + + close(pipefds[0]); + + ret = waitpid(s, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e1 = rcheck(wstatus, "server"); + ret = waitpid(c, &wstatus, 0); + if (ret == -1) + die_perror("waitpid"); + e2 = rcheck(wstatus, "client"); + + return e1 ? e1 : e2; +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 1579e471a5e7b8..41de643788b80e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -239,12 +239,35 @@ make_file() echo "Created $name (size $size KB) containing data sent by $who" } +do_mptcp_sockopt_tests() +{ + local lret=0 + + ./mptcp_sockopt + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt" 1>&2 + ret=$lret + return + fi + + ./mptcp_sockopt -6 + lret=$? + + if [ $lret -ne 0 ]; then + echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2 + ret=$lret + return + fi +} + run_tests() { listener_ns="$1" connector_ns="$2" connect_addr="$3" - lret=0 + local lret=0 do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} @@ -268,9 +291,13 @@ trap cleanup EXIT run_tests $ns1 $ns2 10.0.1.1 run_tests $ns1 $ns2 dead:beef:1::1 - if [ $ret -eq 0 ];then echo "PASS: all packets had packet mark set" fi +do_mptcp_sockopt_tests +if [ $ret -eq 0 ];then + echo "PASS: SOL_MPTCP getsockopt has expected information" +fi + exit $ret |