From 563fe939a81ab08198b78dc8451ef3090969f30b Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:54 -0800 Subject: [PATCH 01/16] netconsole: Helper to count number of used entries Add a helper function nr_extradata_entries() to count the number of used extradata entries in a netconsole target. This refactors the duplicate code for counting entries into a single function, which will be reused by upcoming CPU sysdata changes. The helper uses list_count_nodes() to count the number of children in the userdata group configfs hierarchy. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 7f05c7f74c31..15daaba65c88 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -662,6 +662,16 @@ out_unlock: return ret; } +/* Count number of entries we have in extradata. + * This is important because the extradata_complete only supports + * MAX_EXTRADATA_ITEMS entries. Before enabling any new {user,sys}data + * feature, number of entries needs to checked for available space. + */ +static size_t count_extradata_entries(struct netconsole_target *nt) +{ + return list_count_nodes(&nt->userdata_group.cg_children); +} + static ssize_t remote_mac_store(struct config_item *item, const char *buf, size_t count) { @@ -811,15 +821,13 @@ static struct config_item *userdatum_make_item(struct config_group *group, struct netconsole_target *nt; struct userdatum *udm; struct userdata *ud; - size_t child_count; if (strlen(name) > MAX_EXTRADATA_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); ud = to_userdata(&group->cg_item); nt = userdata_to_target(ud); - child_count = list_count_nodes(&nt->userdata_group.cg_children); - if (child_count >= MAX_EXTRADATA_ITEMS) + if (count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) return ERR_PTR(-ENOSPC); udm = kzalloc(sizeof(*udm), GFP_KERNEL); -- 2.50.1 From 364f67837e86cfd59ef8727dbf6db15594281d4d Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:55 -0800 Subject: [PATCH 02/16] netconsole: Introduce configfs helpers for sysdata features This patch introduces a bitfield to store sysdata features in the netconsole_target struct. It also adds configfs helpers to enable or disable the CPU_NR feature, which populates the CPU number in sysdata. The patch provides the necessary infrastructure to set or unset the CPU_NR feature, but does not modify the message itself. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 81 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 81 insertions(+) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 15daaba65c88..710330ae8ee4 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -97,6 +97,15 @@ struct netconsole_target_stats { struct u64_stats_sync syncp; }; +/* Features enabled in sysdata. Contrary to userdata, this data is populated by + * the kernel. The fields are designed as bitwise flags, allowing multiple + * features to be set in sysdata_fields. + */ +enum sysdata_feature { + /* Populate the CPU that sends the message */ + CPU_NR = BIT(0), +}; + /** * struct netconsole_target - Represents a configured netconsole target. * @list: Links this target into the target_list. @@ -104,6 +113,7 @@ struct netconsole_target_stats { * @userdata_group: Links to the userdata configfs hierarchy * @extradata_complete: Cached, formatted string of append * @userdata_length: String length of usedata in extradata_complete. + * @sysdata_fields: Sysdata features enabled. * @stats: Packet send stats for the target. Used for debugging. * @enabled: On / off knob to enable / disable target. * Visible from userspace (read-write). @@ -132,6 +142,8 @@ struct netconsole_target { struct config_group userdata_group; char extradata_complete[MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS]; size_t userdata_length; + /* bit-wise with sysdata_feature bits */ + u32 sysdata_fields; #endif struct netconsole_target_stats stats; bool enabled; @@ -399,6 +411,19 @@ static ssize_t transmit_errors_show(struct config_item *item, char *buf) return sysfs_emit(buf, "%llu\n", xmit_drop_count + enomem_count); } +/* configfs helper to display if cpu_nr sysdata feature is enabled */ +static ssize_t sysdata_cpu_nr_enabled_show(struct config_item *item, char *buf) +{ + struct netconsole_target *nt = to_target(item->ci_parent); + bool cpu_nr_enabled; + + mutex_lock(&dynamic_netconsole_mutex); + cpu_nr_enabled = !!(nt->sysdata_fields & CPU_NR); + mutex_unlock(&dynamic_netconsole_mutex); + + return sysfs_emit(buf, "%d\n", cpu_nr_enabled); +} + /* * This one is special -- targets created through the configfs interface * are not enabled (and the corresponding netpoll activated) by default. @@ -793,7 +818,62 @@ out_unlock: return ret; } +/* disable_sysdata_feature - Disable sysdata feature and clean sysdata + * @nt: target that is disabling the feature + * @feature: feature being disabled + */ +static void disable_sysdata_feature(struct netconsole_target *nt, + enum sysdata_feature feature) +{ + nt->sysdata_fields &= ~feature; + nt->extradata_complete[nt->userdata_length] = 0; +} + +/* configfs helper to sysdata cpu_nr feature */ +static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item, + const char *buf, size_t count) +{ + struct netconsole_target *nt = to_target(item->ci_parent); + bool cpu_nr_enabled, curr; + ssize_t ret; + + ret = kstrtobool(buf, &cpu_nr_enabled); + if (ret) + return ret; + + mutex_lock(&dynamic_netconsole_mutex); + curr = nt->sysdata_fields & CPU_NR; + if (cpu_nr_enabled == curr) + /* no change requested */ + goto unlock_ok; + + if (cpu_nr_enabled && + count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) { + /* user wants the new feature, but there is no space in the + * buffer. + */ + ret = -ENOSPC; + goto unlock; + } + + if (cpu_nr_enabled) + nt->sysdata_fields |= CPU_NR; + else + /* This is special because extradata_complete might have + * remaining data from previous sysdata, and it needs to be + * cleaned. + */ + disable_sysdata_feature(nt, CPU_NR); + +unlock_ok: + ret = strnlen(buf, count); +unlock: + mutex_unlock(&dynamic_netconsole_mutex); + return ret; +} + CONFIGFS_ATTR(userdatum_, value); +CONFIGFS_ATTR(sysdata_, cpu_nr_enabled); static struct configfs_attribute *userdatum_attrs[] = { &userdatum_attr_value, @@ -853,6 +933,7 @@ static void userdatum_drop(struct config_group *group, struct config_item *item) } static struct configfs_attribute *userdata_attrs[] = { + &sysdata_attr_cpu_nr_enabled, NULL, }; -- 2.50.1 From 2bae25b16aea249f0e96757b6cd28b03d2b4397f Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:56 -0800 Subject: [PATCH 03/16] netconsole: Include sysdata in extradata entry count Modify count_extradata_entries() to include sysdata fields when calculating the total number of extradata entries. This change ensures that the sysdata feature, specifically the CPU number field, is correctly counted against the MAX_EXTRADATA_ITEMS limit. The modification adds a simple check for the CPU_NR flag in the sysdata_fields, incrementing the entry count accordingly. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 710330ae8ee4..50739c7dbfb6 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -694,7 +694,15 @@ out_unlock: */ static size_t count_extradata_entries(struct netconsole_target *nt) { - return list_count_nodes(&nt->userdata_group.cg_children); + size_t entries; + + /* Userdata entries */ + entries = list_count_nodes(&nt->userdata_group.cg_children); + /* Plus sysdata entries */ + if (nt->sysdata_fields & CPU_NR) + entries += 1; + + return entries; } static ssize_t remote_mac_store(struct config_item *item, const char *buf, -- 2.50.1 From ec15bc46c63cc21bba4c4071060797a4b51f50de Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:57 -0800 Subject: [PATCH 04/16] netconsole: add support for sysdata and CPU population Add infrastructure to automatically append kernel-generated data (sysdata) to netconsole messages. As the first use case, implement CPU number population, which adds the CPU that sent the message. This change introduces three distinct data types: - extradata: The complete set of appended data (sysdata + userdata) - userdata: User-provided key-value pairs from userspace - sysdata: Kernel-populated data (e.g. cpu=XX) The implementation adds a new configfs attribute 'cpu_nr' to control CPU number population per target. When enabled, each message is tagged with its originating CPU. The sysdata is dynamically updated at message time and appended after any existing userdata. The CPU number is formatted as "cpu=XX" and is added to the extradata buffer, respecting the existing size limits. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/netconsole.c | 53 ++++++++++++++++++++++++++++++++-------- 1 file changed, 43 insertions(+), 10 deletions(-) diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 50739c7dbfb6..f77eddf22185 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -1117,6 +1117,40 @@ static void populate_configfs_item(struct netconsole_target *nt, init_target_config_group(nt, target_name); } +/* + * prepare_extradata - append sysdata at extradata_complete in runtime + * @nt: target to send message to + */ +static int prepare_extradata(struct netconsole_target *nt) +{ + int sysdata_len, extradata_len; + + /* userdata was appended when configfs write helper was called + * by update_userdata(). + */ + extradata_len = nt->userdata_length; + + if (!(nt->sysdata_fields & CPU_NR)) + goto out; + + /* Append cpu=%d at extradata_complete after userdata str */ + sysdata_len = scnprintf(&nt->extradata_complete[nt->userdata_length], + MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n", + raw_smp_processor_id()); + + extradata_len += sysdata_len; + + WARN_ON_ONCE(extradata_len > + MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS); + +out: + return extradata_len; +} +#else /* CONFIG_NETCONSOLE_DYNAMIC not set */ +static int prepare_extradata(struct netconsole_target *nt) +{ + return 0; +} #endif /* CONFIG_NETCONSOLE_DYNAMIC */ /* Handle network interface device notifications */ @@ -1251,16 +1285,14 @@ static void append_release(char *buf) static void send_fragmented_body(struct netconsole_target *nt, const char *msgbody, int header_len, - int msgbody_len) + int msgbody_len, int extradata_len) { int sent_extradata, preceding_bytes; const char *extradata = NULL; int body_len, offset = 0; - int extradata_len = 0; #ifdef CONFIG_NETCONSOLE_DYNAMIC extradata = nt->extradata_complete; - extradata_len = nt->userdata_length; #endif /* body_len represents the number of bytes that will be sent. This is @@ -1341,7 +1373,8 @@ static void send_fragmented_body(struct netconsole_target *nt, static void send_msg_fragmented(struct netconsole_target *nt, const char *msg, int msg_len, - int release_len) + int release_len, + int extradata_len) { int header_len, msgbody_len; const char *msgbody; @@ -1369,7 +1402,8 @@ static void send_msg_fragmented(struct netconsole_target *nt, /* for now on, the header will be persisted, and the msgbody * will be replaced */ - send_fragmented_body(nt, msgbody, header_len, msgbody_len); + send_fragmented_body(nt, msgbody, header_len, msgbody_len, + extradata_len); } /** @@ -1385,12 +1419,10 @@ static void send_msg_fragmented(struct netconsole_target *nt, static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, int msg_len) { - int extradata_len = 0; int release_len = 0; + int extradata_len; -#ifdef CONFIG_NETCONSOLE_DYNAMIC - extradata_len = nt->userdata_length; -#endif + extradata_len = prepare_extradata(nt); if (nt->release) release_len = strlen(init_utsname()->release) + 1; @@ -1398,7 +1430,8 @@ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg, if (msg_len + release_len + extradata_len <= MAX_PRINT_CHUNK) return send_msg_no_fragmentation(nt, msg, msg_len, release_len); - return send_msg_fragmented(nt, msg, msg_len, release_len); + return send_msg_fragmented(nt, msg, msg_len, release_len, + extradata_len); } static void write_ext_msg(struct console *con, const char *msg, -- 2.50.1 From 12fd83ca44d8c4b0a78beab8178a1a6754eae1b3 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:58 -0800 Subject: [PATCH 05/16] netconsole: selftest: test for sysdata CPU Add a new selftest to verify that the netconsole module correctly handles CPU runtime data in sysdata. The test validates three scenarios: 1. Basic CPU sysdata functionality - verifies that cpu=X is appended to messages 2. CPU sysdata with userdata - ensures CPU data works alongside userdata 3. Disabled CPU sysdata - confirms no CPU data is included when disabled The test uses taskset to control which CPU sends messages and verifies the reported CPU matches the one used. This helps ensure that netconsole accurately tracks and reports the originating CPU of messages. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- tools/testing/selftests/drivers/net/Makefile | 1 + .../drivers/net/lib/sh/lib_netcons.sh | 17 ++ .../selftests/drivers/net/netcons_sysdata.sh | 167 ++++++++++++++++++ 3 files changed, 185 insertions(+) create mode 100755 tools/testing/selftests/drivers/net/netcons_sysdata.sh diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index c7f1c443f2af..28b6d47f812d 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -9,6 +9,7 @@ TEST_PROGS := \ netcons_basic.sh \ netcons_fragmented_msg.sh \ netcons_overflow.sh \ + netcons_sysdata.sh \ ping.py \ queues.py \ stats.py \ diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh index 0c262b123fdd..3c96b022954d 100644 --- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh +++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh @@ -230,3 +230,20 @@ function check_for_dependencies() { exit "${ksft_skip}" fi } + +function check_for_taskset() { + if ! which taskset > /dev/null ; then + echo "SKIP: taskset(1) is not available" >&2 + exit "${ksft_skip}" + fi +} + +# This is necessary if running multiple tests in a row +function pkill_socat() { + PROCESS_NAME="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}" + # socat runs under timeout(1), kill it if it is still alive + # do not fail if socat doesn't exist anymore + set +e + pkill -f "${PROCESS_NAME}" + set -e +} diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh new file mode 100755 index 000000000000..2b78fd1f5982 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh @@ -0,0 +1,167 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 + +# A test that makes sure that sysdata runtime CPU data is properly set +# when a message is sent. +# +# There are 3 different tests, every time sent using a random CPU. +# - Test #1 +# * Only enable cpu_nr sysdata feature. +# - Test #2 +# * Keep cpu_nr sysdata feature enable and enable userdata. +# - Test #3 +# * keep userdata enabled, and disable sysdata cpu_nr feature. +# +# Author: Breno Leitao + +set -euo pipefail + +SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")") + +source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh + +# Enable the sysdata cpu_nr feature +function set_cpu_nr() { + if [[ ! -f "${NETCONS_PATH}/userdata/cpu_nr_enabled" ]] + then + echo "Populate CPU configfs path not available in ${NETCONS_PATH}/userdata/cpu_nr_enabled" >&2 + exit "${ksft_skip}" + fi + + echo 1 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" +} + +# Disable the sysdata cpu_nr feature +function unset_cpu_nr() { + echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled" +} + +# Test if MSG content and `cpu=${CPU}` exists in OUTPUT_FILE +function validate_sysdata_cpu_exists() { + # OUTPUT_FILE will contain something like: + # 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM + # userdatakey=userdatavalue + # cpu=X + + if [ ! -f "$OUTPUT_FILE" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then + echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + # Check if cpu=XX exists in the file and matches the one used + # in taskset(1) + if ! grep -q "cpu=${CPU}\+" "${OUTPUT_FILE}"; then + echo "FAIL: 'cpu=${CPU}' not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + rm "${OUTPUT_FILE}" + pkill_socat +} + +# Test if MSG content exists in OUTPUT_FILE but no `cpu=` string +function validate_sysdata_no_cpu() { + if [ ! -f "$OUTPUT_FILE" ]; then + echo "FAIL: File was not generated." >&2 + exit "${ksft_fail}" + fi + + if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then + echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + if grep -q "cpu=" "${OUTPUT_FILE}"; then + echo "FAIL: 'cpu= found in ${OUTPUT_FILE}" >&2 + cat "${OUTPUT_FILE}" >&2 + exit "${ksft_fail}" + fi + + rm "${OUTPUT_FILE}" +} + +# Start socat, send the message and wait for the file to show up in the file +# system +function runtest { + # Listen for netconsole port inside the namespace and destination + # interface + listen_port_and_save_to "${OUTPUT_FILE}" & + # Wait for socat to start and listen to the port. + wait_local_port_listen "${NAMESPACE}" "${PORT}" udp + # Send the message + taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg + # Wait until socat saves the file to disk + busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}" +} + +# ========== # +# Start here # +# ========== # + +modprobe netdevsim 2> /dev/null || true +modprobe netconsole 2> /dev/null || true + +# Check for basic system dependency and exit if not found +check_for_dependencies +# This test also depends on taskset(1). Check for it before starting the test +check_for_taskset + +# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5) +echo "6 5" > /proc/sys/kernel/printk +# Remove the namespace, interfaces and netconsole target on exit +trap cleanup EXIT +# Create one namespace and two interfaces +set_network +# Create a dynamic target for netconsole +create_dynamic_target + +#==================================================== +# TEST #1 +# Send message from a random CPU +#==================================================== +# Random CPU in the system +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_1" +MSG="Test #1 from CPU${CPU}" +# Enable the auto population of cpu_nr +set_cpu_nr +runtest +# Make sure the message was received in the dst part +# and exit +validate_sysdata_cpu_exists + +#==================================================== +# TEST #2 +# This test now adds userdata together with sysdata +# =================================================== +# Get a new random CPU +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_2" +MSG="Test #2 from CPU${CPU}" +set_user_data +runtest +validate_sysdata_cpu_exists + +# =================================================== +# TEST #3 +# Unset cpu_nr, so, no CPU should be appended. +# userdata is still set +# =================================================== +CPU=$((RANDOM % $(nproc))) +OUTPUT_FILE="/tmp/${TARGET}_3" +MSG="Test #3 from CPU${CPU}" +# Enable the auto population of cpu_nr +unset_cpu_nr +runtest +# At this time, cpu= shouldn't be present in the msg +validate_sysdata_no_cpu + +exit "${ksft_pass}" -- 2.50.1 From a7aec70a9092aec61a29ad1e1fc387ef888a6ad6 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Thu, 6 Feb 2025 03:05:59 -0800 Subject: [PATCH 06/16] netconsole: docs: Add documentation for CPU number auto-population Update the netconsole documentation to explain the new feature that allows automatic population of the CPU number. The key changes include introducing a new section titled "CPU number auto population in userdata", explaining how to enable the CPU number auto-population feature by writing to the "populate_cpu_nr" file in the netconsole configfs hierarchy. This documentation update ensures users are aware of the new CPU number auto-population functionality and how to leverage it for better demultiplexing and visibility of parallel netconsole output. Signed-off-by: Breno Leitao Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/networking/netconsole.rst | 45 +++++++++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 94c4680fdf3e..84803c59968a 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -17,6 +17,8 @@ Release prepend support by Breno Leitao , Jul 7 2023 Userdata append support by Matthew Wood , Jan 22 2024 +Sysdata append support by Breno Leitao , Jan 15 2025 + Please send bug reports to Matt Mackall Satyam Sharma , and Cong Wang @@ -238,6 +240,49 @@ Delete `userdata` entries with `rmdir`:: It is recommended to not write user data values with newlines. +CPU number auto population in userdata +-------------------------------------- + +Inside the netconsole configfs hierarchy, there is a file called +`cpu_nr` under the `userdata` directory. This file is used to enable or disable +the automatic CPU number population feature. This feature automatically +populates the CPU number that is sending the message. + +To enable the CPU number auto-population:: + + echo 1 > /sys/kernel/config/netconsole/target1/userdata/cpu_nr + +When this option is enabled, the netconsole messages will include an additional +line in the userdata field with the format `cpu=`. This allows the +receiver of the netconsole messages to easily differentiate and demultiplex +messages originating from different CPUs, which is particularly useful when +dealing with parallel log output. + +Example:: + + echo "This is a message" > /dev/kmsg + 12,607,22085407756,-;This is a message + cpu=42 + +In this example, the message was sent by CPU 42. + +.. note:: + + If the user has set a conflicting `cpu` key in the userdata dictionary, + both keys will be reported, with the kernel-populated entry appearing after + the user one. For example:: + + # User-defined CPU entry + mkdir -p /sys/kernel/config/netconsole/target1/userdata/cpu + echo "1" > /sys/kernel/config/netconsole/target1/userdata/cpu/value + + Output might look like:: + + 12,607,22085407756,-;This is a message + cpu=1 + cpu=42 # kernel-populated value + + Extended console: ================= -- 2.50.1 From de7f7582dff292832fbdeaeff34e6b2ee6f9f95f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 6 Feb 2025 15:53:28 -0800 Subject: [PATCH 07/16] net: ethtool: prevent flow steering to RSS contexts which don't exist Since commit 42dc431f5d0e ("ethtool: rss: prevent rss ctx deletion when in use") we prevent removal of RSS contexts pointed to by existing flow rules. Core should also prevent creation of rules which point to RSS context which don't exist in the first place. Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250206235334.1425329-2-kuba@kernel.org Signed-off-by: Jakub Kicinski --- net/ethtool/ioctl.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7609ce2b2c5e..98b7dcea207a 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -993,10 +993,14 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, return rc; /* Nonzero ring with RSS only makes sense if NIC adds them together */ - if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS && - !ops->cap_rss_rxnfc_adds && - ethtool_get_flow_spec_ring(info.fs.ring_cookie)) - return -EINVAL; + if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS) { + if (!ops->cap_rss_rxnfc_adds && + ethtool_get_flow_spec_ring(info.fs.ring_cookie)) + return -EINVAL; + + if (!xa_load(&dev->ethtool->rss_ctx, info.rss_context)) + return -EINVAL; + } if (cmd == ETHTOOL_SRXFH && ops->get_rxfh) { struct ethtool_rxfh_param rxfh = {}; -- 2.50.1 From 23bac399104c0f23df379a94fe325fef951c287b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 6 Feb 2025 15:53:29 -0800 Subject: [PATCH 08/16] selftests: net-drv: test adding flow rule to invalid RSS context Check that adding Rx flow steering rules pointing to an RSS context which does not exist is prevented. Reviewed-by: Willem de Bruijn Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250206235334.1425329-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../selftests/drivers/net/hw/rss_ctx.py | 27 ++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 319aaa004c40..7e5f4602e6b3 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -4,7 +4,8 @@ import datetime import random import re -from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true +from lib.py import ksft_run, ksft_pr, ksft_exit +from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises from lib.py import NetDrvEpEnv from lib.py import EthtoolFamily, NetdevFamily from lib.py import KsftSkipEx, KsftFailEx @@ -649,6 +650,29 @@ def test_rss_context_overlap2(cfg): test_rss_context_overlap(cfg, True) +def test_flow_add_context_missing(cfg): + """ + Test that we are not allowed to add a rule pointing to an RSS context + which was never created. + """ + + require_ntuple(cfg) + + # Find a context which doesn't exist + for ctx_id in range(1, 100): + try: + get_rss(cfg, context=ctx_id) + except CmdExitFailure: + break + + with ksft_raises(CmdExitFailure) as cm: + flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port 1234 context {ctx_id}" + ntuple_id = ethtool_create(cfg, "-N", flow) + ethtool(f"-N {cfg.ifname} delete {ntuple_id}") + if cm.exception: + ksft_in('Invalid argument', cm.exception.cmd.stderr) + + def test_delete_rss_context_busy(cfg): """ Test that deletion returns -EBUSY when an rss context is being used @@ -726,6 +750,7 @@ def main() -> None: test_rss_context_dump, test_rss_context_queue_reconfigure, test_rss_context_overlap, test_rss_context_overlap2, test_rss_context_out_of_order, test_rss_context4_create_with_cfg, + test_flow_add_context_missing, test_delete_rss_context_busy, test_rss_ntuple_addition], args=(cfg, )) ksft_exit() -- 2.50.1 From 260676ebb1f3b188796a045e0ecf79a699b8e857 Mon Sep 17 00:00:00 2001 From: Daniel Zahka Date: Thu, 6 Feb 2025 15:53:30 -0800 Subject: [PATCH 09/16] eth: fbnic: support an additional RSS context Add support for an extra RSS context. The device has a primary and a secondary context. Signed-off-by: Daniel Zahka Reviewed-by: Joe Damato Link: https://patch.msgid.link/20250206235334.1425329-4-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../net/ethernet/meta/fbnic/fbnic_ethtool.c | 59 +++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 20cd9f5f89e2..4d73b405c8b9 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -374,6 +374,61 @@ fbnic_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh, return 0; } +static int +fbnic_modify_rxfh_context(struct net_device *netdev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + const u32 *indir = rxfh->indir; + unsigned int changes; + + if (!indir) + indir = ethtool_rxfh_context_indir(ctx); + + changes = fbnic_set_indir(fbn, rxfh->rss_context, indir); + if (changes && netif_running(netdev)) + fbnic_rss_reinit_hw(fbn->fbd, fbn); + + return 0; +} + +static int +fbnic_create_rxfh_context(struct net_device *netdev, + struct ethtool_rxfh_context *ctx, + const struct ethtool_rxfh_param *rxfh, + struct netlink_ext_ack *extack) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) { + NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported"); + return -EOPNOTSUPP; + } + ctx->hfunc = ETH_RSS_HASH_TOP; + + if (!rxfh->indir) { + u32 *indir = ethtool_rxfh_context_indir(ctx); + unsigned int num_rx = fbn->num_rx_queues; + unsigned int i; + + for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++) + indir[i] = ethtool_rxfh_indir_default(i, num_rx); + } + + return fbnic_modify_rxfh_context(netdev, ctx, rxfh, extack); +} + +static int +fbnic_remove_rxfh_context(struct net_device *netdev, + struct ethtool_rxfh_context *ctx, u32 rss_context, + struct netlink_ext_ack *extack) +{ + /* Nothing to do, contexts are allocated statically */ + return 0; +} + static void fbnic_get_channels(struct net_device *netdev, struct ethtool_channels *ch) { @@ -586,6 +641,7 @@ fbnic_get_eth_mac_stats(struct net_device *netdev, } static const struct ethtool_ops fbnic_ethtool_ops = { + .rxfh_max_num_contexts = FBNIC_RPC_RSS_TBL_COUNT, .get_drvinfo = fbnic_get_drvinfo, .get_regs_len = fbnic_get_regs_len, .get_regs = fbnic_get_regs, @@ -598,6 +654,9 @@ static const struct ethtool_ops fbnic_ethtool_ops = { .get_rxfh_indir_size = fbnic_get_rxfh_indir_size, .get_rxfh = fbnic_get_rxfh, .set_rxfh = fbnic_set_rxfh, + .create_rxfh_context = fbnic_create_rxfh_context, + .modify_rxfh_context = fbnic_modify_rxfh_context, + .remove_rxfh_context = fbnic_remove_rxfh_context, .get_channels = fbnic_get_channels, .set_channels = fbnic_set_channels, .get_ts_info = fbnic_get_ts_info, -- 2.50.1 From 3a265bd6a3ba27ff56a686d845e959ce365edcaa Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 6 Feb 2025 15:53:31 -0800 Subject: [PATCH 10/16] eth: fbnic: add IP TCAM programming IPv6 addresses are huge so the device has 4 TCAMs used for narrowing them down to a smaller key before the main match / action engine. Add the tables in which we'll keep the IP addresses used by ethtool n-tuple rules. Add the code for programming them into the device, and code for allocating and freeing entries. A bit of copy / paste here as we need to support IPv4 and IPv6 in the same tables, and there is four of them. But it makes the code easier to match up with the device. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/20250206235334.1425329-5-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/meta/fbnic/fbnic.h | 6 + drivers/net/ethernet/meta/fbnic/fbnic_csr.h | 3 + drivers/net/ethernet/meta/fbnic/fbnic_rpc.c | 354 ++++++++++++++++++++ drivers/net/ethernet/meta/fbnic/fbnic_rpc.h | 26 ++ 4 files changed, 389 insertions(+) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index 14751f16e125..37f81db1fc30 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -60,6 +60,12 @@ struct fbnic_dev { u8 mac_addr_boundary; u8 tce_tcam_last; + /* IP TCAM */ + struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES]; + struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES]; + struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES]; + struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES]; + /* Number of TCQs/RCQs available on hardware */ u16 max_num_queues; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index 02bb81b3c506..d5e9b11ed2f8 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -677,6 +677,9 @@ enum { #define FBNIC_RPC_TCAM_OUTER_IPSRC(m, n)\ (0x08c00 + 0x08 * (n) + (m)) /* 0x023000 + 32*n + 4*m */ +#define FBNIC_RPC_TCAM_IP_ADDR_VALUE CSR_GENMASK(15, 0) +#define FBNIC_RPC_TCAM_IP_ADDR_MASK CSR_GENMASK(31, 16) + #define FBNIC_RPC_TCAM_OUTER_IPDST(m, n)\ (0x08c48 + 0x08 * (n) + (m)) /* 0x023120 + 32*n + 4*m */ #define FBNIC_RPC_TCAM_IPSRC(m, n)\ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index c25bd300b902..be06f43e51e4 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -3,6 +3,7 @@ #include #include +#include #include "fbnic.h" #include "fbnic_netdev.h" @@ -698,6 +699,359 @@ void fbnic_write_tce_tcam(struct fbnic_dev *fbd) __fbnic_write_tce_tcam(fbd); } +struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd, + struct fbnic_ip_addr *ip_addr, + const struct in_addr *addr, + const struct in_addr *mask) +{ + struct fbnic_ip_addr *avail_addr = NULL; + unsigned int i; + + /* Scan from top of list to bottom, filling bottom up. */ + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) { + struct in6_addr *m = &ip_addr->mask; + + if (ip_addr->state == FBNIC_TCAM_S_DISABLED) { + avail_addr = ip_addr; + continue; + } + + if (ip_addr->version != 4) + continue; + + /* Drop avail_addr if mask is a subset of our current mask, + * This prevents us from inserting a longer prefix behind a + * shorter one. + * + * The mask is stored inverted value so as an example: + * m ffff ffff ffff ffff ffff ffff ffff 0000 0000 + * mask 0000 0000 0000 0000 0000 0000 0000 ffff ffff + * + * "m" and "mask" represent typical IPv4 mask stored in + * the TCAM and those provided by the stack. The code below + * should return a non-zero result if there is a 0 stored + * anywhere in "m" where "mask" has a 0. + */ + if (~m->s6_addr32[3] & ~mask->s_addr) { + avail_addr = NULL; + continue; + } + + /* Check to see if the mask actually contains fewer bits than + * our new mask "m". The XOR below should only result in 0 if + * "m" is masking a bit that we are looking for in our new + * "mask", we eliminated the 0^0 case with the check above. + * + * If it contains fewer bits we need to stop here, otherwise + * we might be adding an unreachable rule. + */ + if (~(m->s6_addr32[3] ^ mask->s_addr)) + break; + + if (ip_addr->value.s6_addr32[3] == addr->s_addr) { + avail_addr = ip_addr; + break; + } + } + + if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) { + ipv6_addr_set(&avail_addr->value, 0, 0, 0, addr->s_addr); + ipv6_addr_set(&avail_addr->mask, htonl(~0), htonl(~0), + htonl(~0), ~mask->s_addr); + avail_addr->version = 4; + + avail_addr->state = FBNIC_TCAM_S_ADD; + } + + return avail_addr; +} + +struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd, + struct fbnic_ip_addr *ip_addr, + const struct in6_addr *addr, + const struct in6_addr *mask) +{ + struct fbnic_ip_addr *avail_addr = NULL; + unsigned int i; + + ip_addr = &ip_addr[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES - 1]; + + /* Scan from bottom of list to top, filling top down. */ + for (i = FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i--; ip_addr--) { + struct in6_addr *m = &ip_addr->mask; + + if (ip_addr->state == FBNIC_TCAM_S_DISABLED) { + avail_addr = ip_addr; + continue; + } + + if (ip_addr->version != 6) + continue; + + /* Drop avail_addr if mask is a superset of our current mask. + * This prevents us from inserting a longer prefix behind a + * shorter one. + * + * The mask is stored inverted value so as an example: + * m 0000 0000 0000 0000 0000 0000 0000 0000 0000 + * mask ffff ffff ffff ffff ffff ffff ffff ffff ffff + * + * "m" and "mask" represent typical IPv6 mask stored in + * the TCAM and those provided by the stack. The code below + * should return a non-zero result which will cause us + * to drop the avail_addr value that might be cached + * to prevent us from dropping a v6 address behind it. + */ + if ((m->s6_addr32[0] & mask->s6_addr32[0]) | + (m->s6_addr32[1] & mask->s6_addr32[1]) | + (m->s6_addr32[2] & mask->s6_addr32[2]) | + (m->s6_addr32[3] & mask->s6_addr32[3])) { + avail_addr = NULL; + continue; + } + + /* The previous test eliminated any overlap between the + * two values so now we need to check for gaps. + * + * If the mask is equal to our current mask then it should + * result with m ^ mask = ffff ffff, if however the value + * stored in m is bigger then we should see a 0 appear + * somewhere in the mask. + */ + if (~(m->s6_addr32[0] ^ mask->s6_addr32[0]) | + ~(m->s6_addr32[1] ^ mask->s6_addr32[1]) | + ~(m->s6_addr32[2] ^ mask->s6_addr32[2]) | + ~(m->s6_addr32[3] ^ mask->s6_addr32[3])) + break; + + if (ipv6_addr_cmp(&ip_addr->value, addr)) + continue; + + avail_addr = ip_addr; + break; + } + + if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) { + memcpy(&avail_addr->value, addr, sizeof(*addr)); + ipv6_addr_set(&avail_addr->mask, + ~mask->s6_addr32[0], ~mask->s6_addr32[1], + ~mask->s6_addr32[2], ~mask->s6_addr32[3]); + avail_addr->version = 6; + + avail_addr->state = FBNIC_TCAM_S_ADD; + } + + return avail_addr; +} + +int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx) +{ + if (!test_and_clear_bit(tcam_idx, ip_addr->act_tcam)) + return -ENOENT; + + if (bitmap_empty(ip_addr->act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES)) + ip_addr->state = FBNIC_TCAM_S_DELETE; + + return 0; +} + +static void fbnic_clear_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx) +{ + int i; + + /* Invalidate entry and clear addr state info */ + for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i), 0); +} + +static void fbnic_clear_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx) +{ + int i; + + /* Invalidate entry and clear addr state info */ + for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i), 0); +} + +static void fbnic_clear_ip_outer_src_entry(struct fbnic_dev *fbd, + unsigned int idx) +{ + int i; + + /* Invalidate entry and clear addr state info */ + for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), 0); +} + +static void fbnic_clear_ip_outer_dst_entry(struct fbnic_dev *fbd, + unsigned int idx) +{ + int i; + + /* Invalidate entry and clear addr state info */ + for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), 0); +} + +static void fbnic_write_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx, + struct fbnic_ip_addr *ip_addr) +{ + __be16 *mask, *value; + int i; + + mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i), + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) | + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--))); + wrfl(fbd); + + /* Bit 129 is used to flag for v4/v6 */ + wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i), + (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE); +} + +static void fbnic_write_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx, + struct fbnic_ip_addr *ip_addr) +{ + __be16 *mask, *value; + int i; + + mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i), + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) | + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--))); + wrfl(fbd); + + /* Bit 129 is used to flag for v4/v6 */ + wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i), + (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE); +} + +static void fbnic_write_ip_outer_src_entry(struct fbnic_dev *fbd, + unsigned int idx, + struct fbnic_ip_addr *ip_addr) +{ + __be16 *mask, *value; + int i; + + mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) | + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--))); + wrfl(fbd); + + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), FBNIC_RPC_TCAM_VALIDATE); +} + +static void fbnic_write_ip_outer_dst_entry(struct fbnic_dev *fbd, + unsigned int idx, + struct fbnic_ip_addr *ip_addr) +{ + __be16 *mask, *value; + int i; + + mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1]; + + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++) + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) | + FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--))); + wrfl(fbd); + + wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), FBNIC_RPC_TCAM_VALIDATE); +} + +void fbnic_write_ip_addr(struct fbnic_dev *fbd) +{ + int idx; + + for (idx = ARRAY_SIZE(fbd->ip_src); idx--;) { + struct fbnic_ip_addr *ip_addr = &fbd->ip_src[idx]; + + /* Check if update flag is set else skip. */ + if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE)) + continue; + + /* Clear by writing 0s. */ + if (ip_addr->state == FBNIC_TCAM_S_DELETE) { + /* Invalidate entry and clear addr state info */ + fbnic_clear_ip_src_entry(fbd, idx); + memset(ip_addr, 0, sizeof(*ip_addr)); + + continue; + } + + fbnic_write_ip_src_entry(fbd, idx, ip_addr); + + ip_addr->state = FBNIC_TCAM_S_VALID; + } + + /* Repeat process for other IP TCAMs */ + for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;) { + struct fbnic_ip_addr *ip_addr = &fbd->ip_dst[idx]; + + if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE)) + continue; + + if (ip_addr->state == FBNIC_TCAM_S_DELETE) { + fbnic_clear_ip_dst_entry(fbd, idx); + memset(ip_addr, 0, sizeof(*ip_addr)); + + continue; + } + + fbnic_write_ip_dst_entry(fbd, idx, ip_addr); + + ip_addr->state = FBNIC_TCAM_S_VALID; + } + + for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;) { + struct fbnic_ip_addr *ip_addr = &fbd->ipo_src[idx]; + + if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE)) + continue; + + if (ip_addr->state == FBNIC_TCAM_S_DELETE) { + fbnic_clear_ip_outer_src_entry(fbd, idx); + memset(ip_addr, 0, sizeof(*ip_addr)); + + continue; + } + + fbnic_write_ip_outer_src_entry(fbd, idx, ip_addr); + + ip_addr->state = FBNIC_TCAM_S_VALID; + } + + for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;) { + struct fbnic_ip_addr *ip_addr = &fbd->ipo_dst[idx]; + + if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE)) + continue; + + if (ip_addr->state == FBNIC_TCAM_S_DELETE) { + fbnic_clear_ip_outer_dst_entry(fbd, idx); + memset(ip_addr, 0, sizeof(*ip_addr)); + + continue; + } + + fbnic_write_ip_outer_dst_entry(fbd, idx, ip_addr); + + ip_addr->state = FBNIC_TCAM_S_VALID; + } +} + void fbnic_clear_rules(struct fbnic_dev *fbd) { u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h index 0d8285fa5b45..b3515f2f5f92 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h @@ -7,6 +7,8 @@ #include #include +struct in_addr; + /* The TCAM state definitions follow an expected ordering. * They start out disabled, then move through the following states: * Disabled 0 -> Add 2 @@ -32,6 +34,12 @@ enum { #define FBNIC_RPC_TCAM_MACDA_WORD_LEN 3 #define FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES 32 +/* 8 IPSRC and IPDST TCAM Entries each + * 8 registers, Validate each + */ +#define FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN 8 +#define FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES 8 + #define FBNIC_RPC_TCAM_ACT_WORD_LEN 11 #define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES 64 @@ -47,6 +55,13 @@ struct fbnic_mac_addr { DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES); }; +struct fbnic_ip_addr { + struct in6_addr mask, value; + unsigned char version; + unsigned char state; + DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES); +}; + struct fbnic_act_tcam { struct { u16 tcam[FBNIC_RPC_TCAM_ACT_WORD_LEN]; @@ -177,6 +192,17 @@ struct fbnic_mac_addr *__fbnic_mc_sync(struct fbnic_dev *fbd, void fbnic_sift_macda(struct fbnic_dev *fbd); void fbnic_write_macda(struct fbnic_dev *fbd); +struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd, + struct fbnic_ip_addr *ip_addr, + const struct in_addr *addr, + const struct in_addr *mask); +struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd, + struct fbnic_ip_addr *ip_addr, + const struct in6_addr *addr, + const struct in6_addr *mask); +int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx); +void fbnic_write_ip_addr(struct fbnic_dev *fbd); + static inline int __fbnic_uc_unsync(struct fbnic_mac_addr *mac_addr) { return __fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_UNICAST); -- 2.50.1 From 2230035439c8c666d1d010da1486b274a92e0075 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 6 Feb 2025 15:53:32 -0800 Subject: [PATCH 11/16] eth: fbnic: support n-tuple filters Add ethtool -n / -N support. Support only "un-ordered" rule sets (RX_CLS_LOC_ANY), just for simplicity of the code. It's unclear anyone actually cares about the rule ordering. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/20250206235334.1425329-6-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/meta/fbnic/fbnic_csr.h | 3 + .../net/ethernet/meta/fbnic/fbnic_ethtool.c | 646 ++++++++++++++++++ .../net/ethernet/meta/fbnic/fbnic_netdev.c | 1 + drivers/net/ethernet/meta/fbnic/fbnic_rpc.c | 2 +- drivers/net/ethernet/meta/fbnic/fbnic_rpc.h | 9 + 5 files changed, 660 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index d5e9b11ed2f8..6f24c5f2e175 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -605,8 +605,11 @@ enum { FBNIC_RPC_ACT_TBL0_DEST_EI = 4, }; +#define FBNIC_RPC_ACT_TBL0_Q_SEL CSR_BIT(4) +#define FBNIC_RPC_ACT_TBL0_Q_ID CSR_GENMASK(15, 8) #define FBNIC_RPC_ACT_TBL0_DMA_HINT CSR_GENMASK(24, 16) #define FBNIC_RPC_ACT_TBL0_TS_ENA CSR_BIT(28) +#define FBNIC_RPC_ACT_TBL0_ACT_TBL_IDX CSR_BIT(29) #define FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID CSR_BIT(30) #define FBNIC_RPC_ACT_TBL1_DEFAULT 0x0840b /* 0x2102c */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 4d73b405c8b9..9503c36620c6 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "fbnic.h" #include "fbnic_netdev.h" @@ -218,11 +219,234 @@ fbnic_get_rss_hash_opts(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd) return 0; } +static int fbnic_get_cls_rule_all(struct fbnic_net *fbn, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct fbnic_dev *fbd = fbn->fbd; + int i, cnt = 0; + + /* Report maximum rule count */ + cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; + + for (i = 0; i < FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i++) { + int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET; + struct fbnic_act_tcam *act_tcam; + + act_tcam = &fbd->act_tcam[idx]; + if (act_tcam->state != FBNIC_TCAM_S_VALID) + continue; + + if (rule_locs) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + + rule_locs[cnt] = i; + } + + cnt++; + } + + return cnt; +} + +static int fbnic_get_cls_rule(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp; + struct fbnic_dev *fbd = fbn->fbd; + struct fbnic_act_tcam *act_tcam; + int idx; + + fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + + if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES) + return -EINVAL; + + idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET; + act_tcam = &fbd->act_tcam[idx]; + + if (act_tcam->state != FBNIC_TCAM_S_VALID) + return -EINVAL; + + /* Report maximum rule count */ + cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; + + /* Set flow type field */ + if (!(act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_VALID)) { + fsp->flow_type = ETHER_FLOW; + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX, + act_tcam->mask.tcam[1])) { + struct fbnic_mac_addr *mac_addr; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX, + act_tcam->value.tcam[1]); + mac_addr = &fbd->mac_addr[idx]; + + ether_addr_copy(fsp->h_u.ether_spec.h_dest, + mac_addr->value.addr8); + eth_broadcast_addr(fsp->m_u.ether_spec.h_dest); + } + } else if (act_tcam->value.tcam[1] & + FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID) { + fsp->flow_type = IPV6_USER_FLOW; + fsp->h_u.usr_ip6_spec.l4_proto = IPPROTO_IPV6; + fsp->m_u.usr_ip6_spec.l4_proto = 0xff; + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + int i; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ipo_src[idx]; + + for (i = 0; i < 4; i++) { + fsp->h_u.usr_ip6_spec.ip6src[i] = + ip_addr->value.s6_addr32[i]; + fsp->m_u.usr_ip6_spec.ip6src[i] = + ~ip_addr->mask.s6_addr32[i]; + } + } + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + int i; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ipo_dst[idx]; + + for (i = 0; i < 4; i++) { + fsp->h_u.usr_ip6_spec.ip6dst[i] = + ip_addr->value.s6_addr32[i]; + fsp->m_u.usr_ip6_spec.ip6dst[i] = + ~ip_addr->mask.s6_addr32[i]; + } + } + } else if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_IS_V6)) { + if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) { + if (act_tcam->value.tcam[1] & + FBNIC_RPC_TCAM_ACT1_L4_IS_UDP) + fsp->flow_type = UDP_V6_FLOW; + else + fsp->flow_type = TCP_V6_FLOW; + fsp->h_u.tcp_ip6_spec.psrc = + cpu_to_be16(act_tcam->value.tcam[3]); + fsp->m_u.tcp_ip6_spec.psrc = + cpu_to_be16(~act_tcam->mask.tcam[3]); + fsp->h_u.tcp_ip6_spec.pdst = + cpu_to_be16(act_tcam->value.tcam[4]); + fsp->m_u.tcp_ip6_spec.pdst = + cpu_to_be16(~act_tcam->mask.tcam[4]); + } else { + fsp->flow_type = IPV6_USER_FLOW; + } + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + int i; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ip_src[idx]; + + for (i = 0; i < 4; i++) { + fsp->h_u.usr_ip6_spec.ip6src[i] = + ip_addr->value.s6_addr32[i]; + fsp->m_u.usr_ip6_spec.ip6src[i] = + ~ip_addr->mask.s6_addr32[i]; + } + } + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + int i; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ip_dst[idx]; + + for (i = 0; i < 4; i++) { + fsp->h_u.usr_ip6_spec.ip6dst[i] = + ip_addr->value.s6_addr32[i]; + fsp->m_u.usr_ip6_spec.ip6dst[i] = + ~ip_addr->mask.s6_addr32[i]; + } + } + } else { + if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) { + if (act_tcam->value.tcam[1] & + FBNIC_RPC_TCAM_ACT1_L4_IS_UDP) + fsp->flow_type = UDP_V4_FLOW; + else + fsp->flow_type = TCP_V4_FLOW; + fsp->h_u.tcp_ip4_spec.psrc = + cpu_to_be16(act_tcam->value.tcam[3]); + fsp->m_u.tcp_ip4_spec.psrc = + cpu_to_be16(~act_tcam->mask.tcam[3]); + fsp->h_u.tcp_ip4_spec.pdst = + cpu_to_be16(act_tcam->value.tcam[4]); + fsp->m_u.tcp_ip4_spec.pdst = + cpu_to_be16(~act_tcam->mask.tcam[4]); + } else { + fsp->flow_type = IPV4_USER_FLOW; + fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + } + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ip_src[idx]; + + fsp->h_u.usr_ip4_spec.ip4src = + ip_addr->value.s6_addr32[3]; + fsp->m_u.usr_ip4_spec.ip4src = + ~ip_addr->mask.s6_addr32[3]; + } + + if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + act_tcam->mask.tcam[0])) { + struct fbnic_ip_addr *ip_addr; + + idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + act_tcam->value.tcam[0]); + ip_addr = &fbd->ip_dst[idx]; + + fsp->h_u.usr_ip4_spec.ip4dst = + ip_addr->value.s6_addr32[3]; + fsp->m_u.usr_ip4_spec.ip4dst = + ~ip_addr->mask.s6_addr32[3]; + } + } + + /* Record action */ + if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_DROP) + fsp->ring_cookie = RX_CLS_FLOW_DISC; + else if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_Q_SEL) + fsp->ring_cookie = FIELD_GET(FBNIC_RPC_ACT_TBL0_Q_ID, + act_tcam->dest); + else + fsp->flow_type |= FLOW_RSS; + + cmd->rss_context = FIELD_GET(FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID, + act_tcam->dest); + + return 0; +} + static int fbnic_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { struct fbnic_net *fbn = netdev_priv(netdev); int ret = -EOPNOTSUPP; + u32 special = 0; switch (cmd->cmd) { case ETHTOOL_GRXRINGS: @@ -232,6 +456,22 @@ static int fbnic_get_rxnfc(struct net_device *netdev, case ETHTOOL_GRXFH: ret = fbnic_get_rss_hash_opts(fbn, cmd); break; + case ETHTOOL_GRXCLSRULE: + ret = fbnic_get_cls_rule(fbn, cmd); + break; + case ETHTOOL_GRXCLSRLCNT: + rule_locs = NULL; + special = RX_CLS_LOC_SPECIAL; + fallthrough; + case ETHTOOL_GRXCLSRLALL: + ret = fbnic_get_cls_rule_all(fbn, cmd, rule_locs); + if (ret < 0) + break; + + cmd->data |= special; + cmd->rule_cnt = ret; + ret = 0; + break; } return ret; @@ -272,6 +512,406 @@ fbnic_set_rss_hash_opts(struct fbnic_net *fbn, const struct ethtool_rxnfc *cmd) return 0; } +static int fbnic_cls_rule_any_loc(struct fbnic_dev *fbd) +{ + int i; + + for (i = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i--;) { + int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET; + + if (fbd->act_tcam[idx].state != FBNIC_TCAM_S_VALID) + return i; + } + + return -ENOSPC; +} + +static int fbnic_set_cls_rule_ins(struct fbnic_net *fbn, + const struct ethtool_rxnfc *cmd) +{ + u16 flow_value = 0, flow_mask = 0xffff, ip_value = 0, ip_mask = 0xffff; + u16 sport = 0, sport_mask = ~0, dport = 0, dport_mask = ~0; + u16 misc = 0, misc_mask = ~0; + u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK, + FBNIC_RPC_ACT_TBL0_DEST_HOST); + struct fbnic_ip_addr *ip_src = NULL, *ip_dst = NULL; + struct fbnic_mac_addr *mac_addr = NULL; + struct ethtool_rx_flow_spec *fsp; + struct fbnic_dev *fbd = fbn->fbd; + struct fbnic_act_tcam *act_tcam; + struct in6_addr *addr6, *mask6; + struct in_addr *addr4, *mask4; + int hash_idx, location; + u32 flow_type; + int idx, j; + + fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + + if (fsp->location != RX_CLS_LOC_ANY) + return -EINVAL; + location = fbnic_cls_rule_any_loc(fbd); + if (location < 0) + return location; + + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + dest = FBNIC_RPC_ACT_TBL0_DROP; + } else if (fsp->flow_type & FLOW_RSS) { + if (cmd->rss_context == 1) + dest |= FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID; + } else { + u32 ring_idx = ethtool_get_flow_spec_ring(fsp->ring_cookie); + + if (ring_idx >= fbn->num_rx_queues) + return -EINVAL; + + dest |= FBNIC_RPC_ACT_TBL0_Q_SEL | + FIELD_PREP(FBNIC_RPC_ACT_TBL0_Q_ID, ring_idx); + } + + idx = location + FBNIC_RPC_ACT_TBL_NFC_OFFSET; + act_tcam = &fbd->act_tcam[idx]; + + /* Do not allow overwriting for now. + * To support overwriting rules we will need to add logic to free + * any IP or MACDA TCAMs that may be associated with the old rule. + */ + if (act_tcam->state != FBNIC_TCAM_S_DISABLED) + return -EBUSY; + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_RSS); + hash_idx = fbnic_get_rss_hash_idx(flow_type); + + switch (flow_type) { + case UDP_V4_FLOW: +udp4_flow: + flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP; + fallthrough; + case TCP_V4_FLOW: +tcp4_flow: + flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID; + flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP | + FBNIC_RPC_TCAM_ACT1_L4_VALID); + + sport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.psrc); + sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.psrc); + dport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.pdst); + dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.pdst); + goto ip4_flow; + case IP_USER_FLOW: + if (!fsp->m_u.usr_ip4_spec.proto) + goto ip4_flow; + if (fsp->m_u.usr_ip4_spec.proto != 0xff) + return -EINVAL; + if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_UDP) + goto udp4_flow; + if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_TCP) + goto tcp4_flow; + return -EINVAL; +ip4_flow: + addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4src; + mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4src; + if (mask4->s_addr) { + ip_src = __fbnic_ip4_sync(fbd, fbd->ip_src, + addr4, mask4); + if (!ip_src) + return -ENOSPC; + + set_bit(idx, ip_src->act_tcam); + ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + ip_src - fbd->ip_src); + ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID | + FBNIC_RPC_TCAM_ACT0_IPSRC_IDX); + } + + addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4dst; + mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4dst; + if (mask4->s_addr) { + ip_dst = __fbnic_ip4_sync(fbd, fbd->ip_dst, + addr4, mask4); + if (!ip_dst) { + if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD) + memset(ip_src, 0, sizeof(*ip_src)); + return -ENOSPC; + } + + set_bit(idx, ip_dst->act_tcam); + ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + ip_dst - fbd->ip_dst); + ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID | + FBNIC_RPC_TCAM_ACT0_IPDST_IDX); + } + flow_value |= FBNIC_RPC_TCAM_ACT1_IP_VALID | + FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID; + flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 | + FBNIC_RPC_TCAM_ACT1_IP_VALID | + FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID); + break; + case UDP_V6_FLOW: +udp6_flow: + flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP; + fallthrough; + case TCP_V6_FLOW: +tcp6_flow: + flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID; + flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP | + FBNIC_RPC_TCAM_ACT1_L4_VALID); + + sport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.psrc); + sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.psrc); + dport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.pdst); + dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.pdst); + goto ipv6_flow; + case IPV6_USER_FLOW: + if (!fsp->m_u.usr_ip6_spec.l4_proto) + goto ipv6_flow; + + if (fsp->m_u.usr_ip6_spec.l4_proto != 0xff) + return -EINVAL; + if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_UDP) + goto udp6_flow; + if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_TCP) + goto tcp6_flow; + if (fsp->h_u.usr_ip6_spec.l4_proto != IPPROTO_IPV6) + return -EINVAL; + + addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src; + mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src; + if (!ipv6_addr_any(mask6)) { + ip_src = __fbnic_ip6_sync(fbd, fbd->ipo_src, + addr6, mask6); + if (!ip_src) + return -ENOSPC; + + set_bit(idx, ip_src->act_tcam); + ip_value |= + FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX, + ip_src - fbd->ipo_src); + ip_mask &= + ~(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID | + FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX); + } + + addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst; + mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst; + if (!ipv6_addr_any(mask6)) { + ip_dst = __fbnic_ip6_sync(fbd, fbd->ipo_dst, + addr6, mask6); + if (!ip_dst) { + if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD) + memset(ip_src, 0, sizeof(*ip_src)); + return -ENOSPC; + } + + set_bit(idx, ip_dst->act_tcam); + ip_value |= + FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX, + ip_dst - fbd->ipo_dst); + ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID | + FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX); + } + + flow_value |= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID; + flow_mask &= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID; +ipv6_flow: + addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src; + mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src; + if (!ip_src && !ipv6_addr_any(mask6)) { + ip_src = __fbnic_ip6_sync(fbd, fbd->ip_src, + addr6, mask6); + if (!ip_src) + return -ENOSPC; + + set_bit(idx, ip_src->act_tcam); + ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX, + ip_src - fbd->ip_src); + ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID | + FBNIC_RPC_TCAM_ACT0_IPSRC_IDX); + } + + addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst; + mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst; + if (!ip_dst && !ipv6_addr_any(mask6)) { + ip_dst = __fbnic_ip6_sync(fbd, fbd->ip_dst, + addr6, mask6); + if (!ip_dst) { + if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD) + memset(ip_src, 0, sizeof(*ip_src)); + return -ENOSPC; + } + + set_bit(idx, ip_dst->act_tcam); + ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID | + FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX, + ip_dst - fbd->ip_dst); + ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID | + FBNIC_RPC_TCAM_ACT0_IPDST_IDX); + } + + flow_value |= FBNIC_RPC_TCAM_ACT1_IP_IS_V6 | + FBNIC_RPC_TCAM_ACT1_IP_VALID | + FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID; + flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 | + FBNIC_RPC_TCAM_ACT1_IP_VALID | + FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID); + break; + case ETHER_FLOW: + if (!is_zero_ether_addr(fsp->m_u.ether_spec.h_dest)) { + u8 *addr = fsp->h_u.ether_spec.h_dest; + u8 *mask = fsp->m_u.ether_spec.h_dest; + + /* Do not allow MAC addr of 0 */ + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* Only support full MAC address to avoid + * conflicts with other MAC addresses. + */ + if (!is_broadcast_ether_addr(mask)) + return -EINVAL; + + if (is_multicast_ether_addr(addr)) + mac_addr = __fbnic_mc_sync(fbd, addr); + else + mac_addr = __fbnic_uc_sync(fbd, addr); + + if (!mac_addr) + return -ENOSPC; + + set_bit(idx, mac_addr->act_tcam); + flow_value |= + FIELD_PREP(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX, + mac_addr - fbd->mac_addr); + flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX; + } + + flow_value |= FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID; + flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID; + break; + default: + return -EINVAL; + } + + /* Write action table values */ + act_tcam->dest = dest; + act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx); + + /* Write IP Match value/mask to action_tcam[0] */ + act_tcam->value.tcam[0] = ip_value; + act_tcam->mask.tcam[0] = ip_mask; + + /* Write flow type value/mask to action_tcam[1] */ + act_tcam->value.tcam[1] = flow_value; + act_tcam->mask.tcam[1] = flow_mask; + + /* Write error, DSCP, extra L4 matches to action_tcam[2] */ + act_tcam->value.tcam[2] = misc; + act_tcam->mask.tcam[2] = misc_mask; + + /* Write source/destination port values */ + act_tcam->value.tcam[3] = sport; + act_tcam->mask.tcam[3] = sport_mask; + act_tcam->value.tcam[4] = dport; + act_tcam->mask.tcam[4] = dport_mask; + + for (j = 5; j < FBNIC_RPC_TCAM_ACT_WORD_LEN; j++) + act_tcam->mask.tcam[j] = 0xffff; + + act_tcam->state = FBNIC_TCAM_S_UPDATE; + fsp->location = location; + + if (netif_running(fbn->netdev)) { + fbnic_write_rules(fbd); + if (ip_src || ip_dst) + fbnic_write_ip_addr(fbd); + if (mac_addr) + fbnic_write_macda(fbd); + } + + return 0; +} + +static void fbnic_clear_nfc_macda(struct fbnic_net *fbn, + unsigned int tcam_idx) +{ + struct fbnic_dev *fbd = fbn->fbd; + int idx; + + for (idx = ARRAY_SIZE(fbd->mac_addr); idx--;) + __fbnic_xc_unsync(&fbd->mac_addr[idx], tcam_idx); + + /* Write updates to hardware */ + if (netif_running(fbn->netdev)) + fbnic_write_macda(fbd); +} + +static void fbnic_clear_nfc_ip_addr(struct fbnic_net *fbn, + unsigned int tcam_idx) +{ + struct fbnic_dev *fbd = fbn->fbd; + int idx; + + for (idx = ARRAY_SIZE(fbd->ip_src); idx--;) + __fbnic_ip_unsync(&fbd->ip_src[idx], tcam_idx); + for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;) + __fbnic_ip_unsync(&fbd->ip_dst[idx], tcam_idx); + for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;) + __fbnic_ip_unsync(&fbd->ipo_src[idx], tcam_idx); + for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;) + __fbnic_ip_unsync(&fbd->ipo_dst[idx], tcam_idx); + + /* Write updates to hardware */ + if (netif_running(fbn->netdev)) + fbnic_write_ip_addr(fbd); +} + +static int fbnic_set_cls_rule_del(struct fbnic_net *fbn, + const struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp; + struct fbnic_dev *fbd = fbn->fbd; + struct fbnic_act_tcam *act_tcam; + int idx; + + fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; + + if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES) + return -EINVAL; + + idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET; + act_tcam = &fbd->act_tcam[idx]; + + if (act_tcam->state != FBNIC_TCAM_S_VALID) + return -EINVAL; + + act_tcam->state = FBNIC_TCAM_S_DELETE; + + if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID) && + (~act_tcam->mask.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX)) + fbnic_clear_nfc_macda(fbn, idx); + + if ((act_tcam->value.tcam[0] & + (FBNIC_RPC_TCAM_ACT0_IPSRC_VALID | + FBNIC_RPC_TCAM_ACT0_IPDST_VALID | + FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID | + FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID)) && + (~act_tcam->mask.tcam[0] & + (FBNIC_RPC_TCAM_ACT0_IPSRC_IDX | + FBNIC_RPC_TCAM_ACT0_IPDST_IDX | + FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX | + FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX))) + fbnic_clear_nfc_ip_addr(fbn, idx); + + if (netif_running(fbn->netdev)) + fbnic_write_rules(fbd); + + return 0; +} + static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) { struct fbnic_net *fbn = netdev_priv(netdev); @@ -281,6 +921,12 @@ static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) case ETHTOOL_SRXFH: ret = fbnic_set_rss_hash_opts(fbn, cmd); break; + case ETHTOOL_SRXCLSRLINS: + ret = fbnic_set_cls_rule_ins(fbn, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = fbnic_set_cls_rule_del(fbn, cmd); + break; } return ret; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index 1db57c42333e..14e7a8384bce 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -639,6 +639,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netdev->hw_features |= netdev->features; netdev->vlan_features |= netdev->features; netdev->hw_enc_features |= netdev->features; + netdev->features |= NETIF_F_NTUPLE; netdev->min_mtu = IPV6_MIN_MTU; netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index be06f43e51e4..8ff07b5562e3 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -61,7 +61,7 @@ void fbnic_rss_disable_hw(struct fbnic_dev *fbd) #define FBNIC_FH_2_RSSEM_BIT(_fh, _rssem, _val) \ FIELD_PREP(FBNIC_RPC_ACT_TBL1_RSS_ENA_##_rssem, \ FIELD_GET(RXH_##_fh, _val)) -static u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type) +u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type) { u32 flow_hash = fbn->rss_flow_hash[flow_type]; u32 rss_en_mask = 0; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h index b3515f2f5f92..6892414195c3 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h @@ -96,6 +96,11 @@ enum { #define FBNIC_RPC_ACT_TBL_BMC_OFFSET 0 #define FBNIC_RPC_ACT_TBL_BMC_ALL_MULTI_OFFSET 1 +/* This should leave us with 48 total entries in the TCAM that can be used + * for NFC after also deducting the 14 needed for RSS table programming. + */ +#define FBNIC_RPC_ACT_TBL_NFC_OFFSET 2 + /* We reserve the last 14 entries for RSS rules on the host. The BMC * unicast rule will need to be populated above these and is expected to * use MACDA TCAM entry 23 to store the BMC MAC address. @@ -103,6 +108,9 @@ enum { #define FBNIC_RPC_ACT_TBL_RSS_OFFSET \ (FBNIC_RPC_ACT_TBL_NUM_ENTRIES - FBNIC_RSS_EN_NUM_ENTRIES) +#define FBNIC_RPC_ACT_TBL_NFC_ENTRIES \ + (FBNIC_RPC_ACT_TBL_RSS_OFFSET - FBNIC_RPC_ACT_TBL_NFC_OFFSET) + /* Flags used to identify the owner for this MAC filter. Note that any * flags set for Broadcast thru Promisc indicate that the rule belongs * to the RSS filters for the host. @@ -183,6 +191,7 @@ void fbnic_rss_init_en_mask(struct fbnic_net *fbn); void fbnic_rss_disable_hw(struct fbnic_dev *fbd); void fbnic_rss_reinit_hw(struct fbnic_dev *fbd, struct fbnic_net *fbn); void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn); +u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type); int __fbnic_xc_unsync(struct fbnic_mac_addr *mac_addr, unsigned int tcam_idx); struct fbnic_mac_addr *__fbnic_uc_sync(struct fbnic_dev *fbd, -- 2.50.1 From d2348b4bf748543172079eacb4dc0d40100fb443 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 6 Feb 2025 15:53:33 -0800 Subject: [PATCH 12/16] selftests: drv-net: rss_ctx: skip tests which need multiple contexts cleanly There's no good API to check how many contexts device supports. But initial tests sense the context count already, so just store that number and skip tests which we know need more. Link: https://patch.msgid.link/20250206235334.1425329-7-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../selftests/drivers/net/hw/rss_ctx.py | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 7e5f4602e6b3..d6e69d7d5e43 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -59,6 +59,14 @@ def require_ntuple(cfg): raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) +def require_context_cnt(cfg, need_cnt): + # There's no good API to get the context count, so the tests + # which try to add a lot opportunisitically set the count they + # discovered. Careful with test ordering! + if need_cnt and cfg.context_cnt and cfg.context_cnt < need_cnt: + raise KsftSkipEx(f"Test requires at least {need_cnt} contexts, but device only has {cfg.context_cnt}") + + # Get Rx packet counts for all queues, as a simple list of integers # if @prev is specified the prev counts will be subtracted def _get_rx_cnts(cfg, prev=None): @@ -457,6 +465,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None): raise ksft_pr(f"Failed to create context {i + 1}, trying to test what we got") ctx_cnt = i + if cfg.context_cnt is None: + cfg.context_cnt = ctx_cnt break _rss_key_check(cfg, context=ctx_id) @@ -512,8 +522,7 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4): """ require_ntuple(cfg) - - requested_ctx_cnt = ctx_cnt + require_context_cnt(cfg, 4) # Try to allocate more queues when necessary qcnt = len(_get_rx_cnts(cfg)) @@ -578,9 +587,6 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4): remove_ctx(-1) check_traffic() - if requested_ctx_cnt != ctx_cnt: - raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}") - def test_rss_context_overlap(cfg, other_ctx=0): """ @@ -589,6 +595,8 @@ def test_rss_context_overlap(cfg, other_ctx=0): """ require_ntuple(cfg) + if other_ctx: + require_context_cnt(cfg, 2) queue_cnt = len(_get_rx_cnts(cfg)) if queue_cnt < 4: @@ -741,6 +749,7 @@ def test_rss_ntuple_addition(cfg): def main() -> None: with NetDrvEpEnv(__file__, nsim_test=False) as cfg: + cfg.context_cnt = None cfg.ethnl = EthtoolFamily() cfg.netdevnl = NetdevFamily() -- 2.50.1 From 5797d3c62db81fd03ba7aeb36a83b44fb0ac2ecc Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 6 Feb 2025 15:53:34 -0800 Subject: [PATCH 13/16] eth: fbnic: support listing tcam content via debugfs The device has a handful of relatively small TCAM tables, support dumping the driver state via debugfs. # ethtool -N eth0 flow-type tcp6 \ dst-ip 1111::2222 dst-port $((0x1122)) \ src-ip 3333::4444 src-port $((0x3344)) \ action 2 Added rule with ID 47 # cd $dbgfs # cat ip_src Idx S TCAM Bitmap V Addr/Mask ------------------------------------ 00 1 00020000,00000000 6 33330000000000000000000000004444 00000000000000000000000000000000 ... # cat ip_dst Idx S TCAM Bitmap V Addr/Mask ------------------------------------ 00 1 00020000,00000000 6 11110000000000000000000000002222 00000000000000000000000000000000 ... # cat act_tcam Idx S Value/Mask RSS Dest ------------------------------------------------------------------------ ... 49 1 0000 0000 0000 0000 0000 0000 1122 3344 0000 9c00 0088 000f 00000212 ffff ffff ffff ffff ffff ffff 0000 0000 ffff 23ff ff00 ... The ipo_* tables are for outer IP addresses. The tce_* table is for directing/stealing traffic to NC-SI. Signed-off-by: Alexander Duyck Link: https://patch.msgid.link/20250206235334.1425329-8-kuba@kernel.org Signed-off-by: Jakub Kicinski --- .../net/ethernet/meta/fbnic/fbnic_debugfs.c | 138 ++++++++++++++++++ 1 file changed, 138 insertions(+) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c index ac80981f67c0..e8f2d7f2d962 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c @@ -44,6 +44,132 @@ static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v) } DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr); +static int fbnic_dbg_tce_tcam_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + int i, tcam_idx = 0; + char hdr[80]; + + /* Generate Header */ + snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n", + "Idx", "S", "TCAM Bitmap", "Addr/Mask"); + seq_puts(s, hdr); + fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr))); + + for (i = 0; i < ARRAY_SIZE(fbd->mac_addr); i++) { + struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i]; + + /* Verify BMC bit is set */ + if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam)) + continue; + + if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES) + break; + + seq_printf(s, "%02d %d %64pb %pm\n", + tcam_idx, mac_addr->state, mac_addr->act_tcam, + mac_addr->value.addr8); + seq_printf(s, " %pm\n", + mac_addr->mask.addr8); + tcam_idx++; + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_tce_tcam); + +static int fbnic_dbg_act_tcam_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + char hdr[80]; + int i; + + /* Generate Header */ + snprintf(hdr, sizeof(hdr), "%3s %s %-55s %-4s %s\n", + "Idx", "S", "Value/Mask", "RSS", "Dest"); + seq_puts(s, hdr); + fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr))); + + for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) { + struct fbnic_act_tcam *act_tcam = &fbd->act_tcam[i]; + + seq_printf(s, "%02d %d %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %08x\n", + i, act_tcam->state, + act_tcam->value.tcam[10], act_tcam->value.tcam[9], + act_tcam->value.tcam[8], act_tcam->value.tcam[7], + act_tcam->value.tcam[6], act_tcam->value.tcam[5], + act_tcam->value.tcam[4], act_tcam->value.tcam[3], + act_tcam->value.tcam[2], act_tcam->value.tcam[1], + act_tcam->value.tcam[0], act_tcam->rss_en_mask, + act_tcam->dest); + seq_printf(s, " %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x\n", + act_tcam->mask.tcam[10], act_tcam->mask.tcam[9], + act_tcam->mask.tcam[8], act_tcam->mask.tcam[7], + act_tcam->mask.tcam[6], act_tcam->mask.tcam[5], + act_tcam->mask.tcam[4], act_tcam->mask.tcam[3], + act_tcam->mask.tcam[2], act_tcam->mask.tcam[1], + act_tcam->mask.tcam[0]); + } + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_act_tcam); + +static int fbnic_dbg_ip_addr_show(struct seq_file *s, + struct fbnic_ip_addr *ip_addr) +{ + char hdr[80]; + int i; + + /* Generate Header */ + snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s %s\n", + "Idx", "S", "TCAM Bitmap", "V", "Addr/Mask"); + seq_puts(s, hdr); + fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr))); + + for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) { + seq_printf(s, "%02d %d %64pb %d %pi6\n", + i, ip_addr->state, ip_addr->act_tcam, + ip_addr->version, &ip_addr->value); + seq_printf(s, " %pi6\n", + &ip_addr->mask); + } + + return 0; +} + +static int fbnic_dbg_ip_src_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + + return fbnic_dbg_ip_addr_show(s, fbd->ip_src); +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_src); + +static int fbnic_dbg_ip_dst_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + + return fbnic_dbg_ip_addr_show(s, fbd->ip_dst); +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_dst); + +static int fbnic_dbg_ipo_src_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + + return fbnic_dbg_ip_addr_show(s, fbd->ipo_src); +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_src); + +static int fbnic_dbg_ipo_dst_show(struct seq_file *s, void *v) +{ + struct fbnic_dev *fbd = s->private; + + return fbnic_dbg_ip_addr_show(s, fbd->ipo_dst); +} +DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_dst); + static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v) { struct fbnic_dev *fbd = s->private; @@ -84,6 +210,18 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd) &fbnic_dbg_pcie_stats_fops); debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd, &fbnic_dbg_mac_addr_fops); + debugfs_create_file("tce_tcam", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_tce_tcam_fops); + debugfs_create_file("act_tcam", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_act_tcam_fops); + debugfs_create_file("ip_src", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_ip_src_fops); + debugfs_create_file("ip_dst", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_ip_dst_fops); + debugfs_create_file("ipo_src", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_ipo_src_fops); + debugfs_create_file("ipo_dst", 0400, fbd->dbg_fbd, fbd, + &fbnic_dbg_ipo_dst_fops); } void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd) -- 2.50.1 From e2c6737e6e82e9991646cd5389391bb6d3572a68 Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Mon, 30 Sep 2024 14:12:38 +0200 Subject: [PATCH 14/16] ice: Don't check device type when checking GNSS presence Don't check if the device type is E810T as non-E810T devices can support GNSS too and PCA9575 check is enough to determine if GNSS is present or not. Rename ice_gnss_is_gps_present() to ice_gnss_is_module_present() because GNSS module supports multiple GNSS providers, not only GPS. Move functions related to PCA9575 from ice_ptp_hw.c to ice_common.c to be able to access them when PTP is disabled in the kernel, but GNSS is enabled. Remove logical AND with ICE_AQC_LINK_TOPO_NODE_TYPE_M in ice_get_pca9575_handle(), which has no effect, and reorder device type checks to check the device_id first, then set other variables. Signed-off-by: Karol Kolacinski Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_common.c | 90 ++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_common.h | 2 + drivers/net/ethernet/intel/ice/ice_gnss.c | 29 +++---- drivers/net/ethernet/intel/ice/ice_gnss.h | 4 +- drivers/net/ethernet/intel/ice/ice_lib.c | 2 +- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 93 --------------------- drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 1 - 7 files changed, 105 insertions(+), 116 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 7a2a2e8da8fa..b61a50fda533 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -5764,6 +5764,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, return ice_aq_send_cmd(hw, &desc, NULL, 0, cd); } +/** + * ice_get_pca9575_handle - find and return the PCA9575 controller + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value. + * + * Return: 0 on success, -ENXIO when there's no PCA9575 present. + */ +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int err; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -ENXIO; + + /* If handle was not detected read it from the netlist */ + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + cmd = &desc.params.get_link_topo; + cmd->addr.topo_params.node_type_ctx = + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL; + cmd->addr.topo_params.index = idx; + + err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (err) + return -ENXIO; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -ENXIO; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_pca9575_reg - read the register from the PCA9575 controller + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + /** * ice_aq_set_gpio * @hw: pointer to the hw struct diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 15ba38543738..54a8692839dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -306,5 +306,7 @@ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle); +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index b2148dbe49b2..6b26290452d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf) } /** - * ice_gnss_is_gps_present - Check if GPS HW is present + * ice_gnss_is_module_present - Check if GNSS HW is present * @hw: pointer to HW struct + * + * Return: true when GNSS is present, false otherwise. */ -bool ice_gnss_is_gps_present(struct ice_hw *hw) +bool ice_gnss_is_module_present(struct ice_hw *hw) { - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return false; + int err; + u8 data; - if (!ice_is_gps_in_netlist(hw)) + if (!hw->func_caps.ts_func_info.src_tmr_owned || + !ice_is_gps_in_netlist(hw)) return false; -#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) - if (ice_is_e810t(hw)) { - int err; - u8 data; - - err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); - if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) - return false; - } else { - return false; - } -#else - if (!ice_is_e810t(hw)) + err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); + if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) return false; -#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 75e567ad7059..15daf603ed7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -37,11 +37,11 @@ struct gnss_serial { #if IS_ENABLED(CONFIG_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); -bool ice_gnss_is_gps_present(struct ice_hw *hw); +bool ice_gnss_is_module_present(struct ice_hw *hw); #else static inline void ice_gnss_init(struct ice_pf *pf) { } static inline void ice_gnss_exit(struct ice_pf *pf) { } -static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) +static inline bool ice_gnss_is_module_present(struct ice_hw *hw) { return false; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 16c419809849..978f308d3b1b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3893,7 +3893,7 @@ void ice_init_feature_support(struct ice_pf *pf) ice_set_feature_support(pf, ICE_F_CGU); if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) + if (ice_gnss_is_module_present(&pf->hw)) ice_set_feature_support(pf, ICE_F_GNSS); break; default: diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index ec91822e9280..53ce40fa2fe6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -5315,68 +5315,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) * to access the extended GPIOs available. */ -/** - * ice_get_pca9575_handle - * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value - */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) -{ - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; - int status; - u8 idx; - - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; - return 0; - } - - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); - -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 - - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; - else - return -EOPNOTSUPP; - - cmd->addr.topo_params.index = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; - - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; - - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; - - return 0; -} - /** * ice_read_sma_ctrl * @hw: pointer to the hw struct @@ -5441,37 +5379,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data) return status; } -/** - * ice_read_pca9575_reg - * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller - * - * Read the register from the GPIO controller - */ -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) -{ - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; - - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; - - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); -} - /** * ice_ptp_read_sdp_ac - read SDP available connections section from NVM * @hw: pointer to the HW struct diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 6779ce120515..15f048d9b582 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -395,7 +395,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold); /* E810 family functions */ int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries); int ice_cgu_get_num_pins(struct ice_hw *hw, bool input); enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); -- 2.50.1 From 9973ac9f23a79285d70365c72e98bffdb94a429d Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Mon, 30 Sep 2024 14:12:39 +0200 Subject: [PATCH 15/16] ice: Remove unnecessary ice_is_e8xx() functions Remove unnecessary ice_is_e8xx() functions and PHY model. Instead, use MAC type where applicable. Don't check device type in ice_ptp_maybe_trigger_tx_interrupt(), because in reality it depends on the ready bitmap, which only E810 does not have. Call ice_ptp_cfg_phy_interrupt() unconditionally, because all further function calls check the MAC type anyway and this allows simpler code in the future with addition of the new MAC types. Reorder ICE_MAC_* cases in switches in ice_ptp* as in enum ice_mac_type. Signed-off-by: Karol Kolacinski Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 5 - drivers/net/ethernet/intel/ice/ice_common.c | 118 +--------------- drivers/net/ethernet/intel/ice/ice_common.h | 5 - drivers/net/ethernet/intel/ice/ice_ddp.c | 4 +- drivers/net/ethernet/intel/ice/ice_ptp.c | 133 +++++++++--------- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 142 ++++++++++---------- drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 10 +- drivers/net/ethernet/intel/ice/ice_type.h | 9 -- 8 files changed, 147 insertions(+), 279 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2a6de2115193..c9104b13e1d2 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -1046,10 +1046,5 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } -static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw) -{ - return hw->ptp.phy_model; -} - extern const struct xdp_metadata_ops ice_xdp_md_ops; #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index b61a50fda533..aaa592ffd2d8 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -186,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw) * ice_is_generic_mac - check if device's mac_type is generic * @hw: pointer to the hardware structure * - * Return: true if mac_type is generic (with SBQ support), false if not + * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise. */ bool ice_is_generic_mac(struct ice_hw *hw) { @@ -194,120 +194,6 @@ bool ice_is_generic_mac(struct ice_hw *hw) hw->mac_type == ICE_MAC_GENERIC_3K_E825); } -/** - * ice_is_e810 - * @hw: pointer to the hardware structure - * - * returns true if the device is E810 based, false if not. - */ -bool ice_is_e810(struct ice_hw *hw) -{ - return hw->mac_type == ICE_MAC_E810; -} - -/** - * ice_is_e810t - * @hw: pointer to the hardware structure - * - * returns true if the device is E810T based, false if not. - */ -bool ice_is_e810t(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E810C_SFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T: - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T4: - case ICE_SUBDEV_ID_E810T6: - case ICE_SUBDEV_ID_E810T7: - return true; - } - break; - case ICE_DEV_ID_E810C_QSFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T5: - return true; - } - break; - default: - break; - } - - return false; -} - -/** - * ice_is_e822 - Check if a device is E822 family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E822 based, false if not. - */ -bool ice_is_e822(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E822C_BACKPLANE: - case ICE_DEV_ID_E822C_QSFP: - case ICE_DEV_ID_E822C_SFP: - case ICE_DEV_ID_E822C_10G_BASE_T: - case ICE_DEV_ID_E822C_SGMII: - case ICE_DEV_ID_E822L_BACKPLANE: - case ICE_DEV_ID_E822L_SFP: - case ICE_DEV_ID_E822L_10G_BASE_T: - case ICE_DEV_ID_E822L_SGMII: - return true; - default: - return false; - } -} - -/** - * ice_is_e823 - * @hw: pointer to the hardware structure - * - * returns true if the device is E823-L or E823-C based, false if not. - */ -bool ice_is_e823(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E823L_BACKPLANE: - case ICE_DEV_ID_E823L_SFP: - case ICE_DEV_ID_E823L_10G_BASE_T: - case ICE_DEV_ID_E823L_1GBE: - case ICE_DEV_ID_E823L_QSFP: - case ICE_DEV_ID_E823C_BACKPLANE: - case ICE_DEV_ID_E823C_QSFP: - case ICE_DEV_ID_E823C_SFP: - case ICE_DEV_ID_E823C_10G_BASE_T: - case ICE_DEV_ID_E823C_SGMII: - return true; - default: - return false; - } -} - -/** - * ice_is_e825c - Check if a device is E825C family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E825-C based, false if not. - */ -bool ice_is_e825c(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: - return true; - default: - return false; - } -} - /** * ice_is_pf_c827 - check if pf contains c827 phy * @hw: pointer to the hw struct @@ -2408,7 +2294,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); - if (!ice_is_e825c(hw)) { + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) { info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); } else { diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 54a8692839dd..9b00aa0ddf10 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -131,7 +131,6 @@ int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); bool ice_is_generic_mac(struct ice_hw *hw); -bool ice_is_e810(struct ice_hw *hw); int ice_clear_pf_cfg(struct ice_hw *hw); int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, @@ -276,10 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); -bool ice_is_e810t(struct ice_hw *hw); -bool ice_is_e822(struct ice_hw *hw); -bool ice_is_e823(struct ice_hw *hw); -bool ice_is_e825c(struct ice_hw *hw); int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 03988be03729..69d5b1a28491 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2345,14 +2345,14 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); } else { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo); cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM; } - if (!ice_is_e825c(hw)) + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e26320ce52ca..7bb4005a67f6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1318,20 +1318,20 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port) struct ice_hw *hw = &pf->hw; int err; - if (ice_is_e810(hw)) - return 0; - mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_stop_phy_timer_eth56g(hw, port, true); + switch (hw->mac_type) { + case ICE_MAC_E810: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: kthread_cancel_delayed_work_sync(&ptp_port->ov_work); err = ice_stop_phy_timer_e82x(hw, port, true); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_stop_phy_timer_eth56g(hw, port, true); + break; default: err = -ENODEV; } @@ -1361,19 +1361,16 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) unsigned long flags; int err; - if (ice_is_e810(hw)) - return 0; - if (!ptp_port->link_up) return ice_ptp_port_phy_stop(ptp_port); mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_start_phy_timer_eth56g(hw, port); + switch (hw->mac_type) { + case ICE_MAC_E810: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: /* Start the PHY timer in Vernier mode */ kthread_cancel_delayed_work_sync(&ptp_port->ov_work); @@ -1398,6 +1395,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_start_phy_timer_eth56g(hw, port); + break; default: err = -ENODEV; } @@ -1432,12 +1432,13 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Skip HW writes if reset is in progress */ if (pf->hw.reset_ongoing) return; - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + + switch (hw->mac_type) { + case ICE_MAC_E810: /* Do not reconfigure E810 PHY */ return; - case ICE_PHY_ETH56G: - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1465,46 +1466,44 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) ice_ptp_reset_ts_memory(hw); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: { - int port; + switch (hw->mac_type) { + case ICE_MAC_E810: + return 0; + case ICE_MAC_GENERIC: { + int quad; - for (port = 0; port < hw->ptp.num_lports; port++) { + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); + quad++) { int err; - err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); + err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", - port, err); + dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", + quad, err); return err; } } return 0; } - case ICE_PHY_E82X: { - int quad; + case ICE_MAC_GENERIC_3K_E825: { + int port; - for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); - quad++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; - err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); + err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", - quad, err); + dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", + port, err); return err; } } return 0; } - case ICE_PHY_E810: - return 0; - case ICE_PHY_UNSUP: + case ICE_MAC_UNKNOWN: default: - dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__, - ice_get_phy_model(hw)); return -EOPNOTSUPP; } } @@ -1740,7 +1739,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, /* 0. Reset mode & out_en in AUX_OUT */ wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); - if (ice_is_e825c(hw)) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) { int err; /* Enable/disable CGU 1PPS output for E825C */ @@ -1824,7 +1823,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0); if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 && - period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) { + period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) { dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n"); return -EOPNOTSUPP; } @@ -2078,7 +2077,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* For Vernier mode on E82X, we need to recalibrate after new settime. * Start with marking timestamps as invalid. */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) { + if (hw->mac_type == ICE_MAC_GENERIC) { err = ice_ptp_clear_phy_offset_ready_e82x(hw); if (err) dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n"); @@ -2102,7 +2101,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_enable_all_perout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) + if (hw->mac_type == ICE_MAC_GENERIC) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2556,7 +2555,7 @@ static void ice_ptp_set_funcs_e82x(struct ice_pf *pf) pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x; #endif /* CONFIG_ICE_HWTS */ - if (ice_is_e825c(&pf->hw)) { + if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) { pf->ptp.ice_pin_desc = ice_pin_desc_e825c; pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c); } else { @@ -2644,10 +2643,17 @@ static void ice_ptp_set_caps(struct ice_pf *pf) info->enable = ice_ptp_gpio_enable; info->verify = ice_verify_pin; - if (ice_is_e810(&pf->hw)) + switch (pf->hw.mac_type) { + case ICE_MAC_E810: ice_ptp_set_funcs_e810(pf); - else + return; + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_set_funcs_e82x(pf); + return; + default: + return; + } } /** @@ -2777,7 +2783,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) bool trigger_oicr = false; unsigned int i; - if (ice_is_e810(hw)) + if (!pf->ptp.port.tx.has_ready_bitmap) return; if (!ice_pf_src_tmr_owned(pf)) @@ -2912,14 +2918,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) */ ice_ptp_flush_all_tx_tracker(pf); - if (!ice_is_e810(hw)) { - /* Enable quad interrupts */ - err = ice_ptp_cfg_phy_interrupt(pf, true, 1); - if (err) - return err; + /* Enable quad interrupts */ + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); + if (err) + return err; - ice_ptp_restart_all_phy(pf); - } + ice_ptp_restart_all_phy(pf); /* Re-enable all periodic outputs and external timestamp events */ ice_ptp_enable_all_perout(pf); @@ -2971,8 +2975,9 @@ err: static bool ice_is_primary(struct ice_hw *hw) { - return ice_is_e825c(hw) && ice_is_dual(hw) ? - !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true; + return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) ? + !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : + true; } static int ice_ptp_setup_adapter(struct ice_pf *pf) @@ -2990,7 +2995,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf) struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf); struct ice_ptp *ptp = &pf->ptp; - if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP) + if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN) return -ENODEV; INIT_LIST_HEAD(&ptp->port.list_node); @@ -3007,7 +3012,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; - if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) { + if (pf->hw.mac_type != ICE_MAC_UNKNOWN) { mutex_lock(&pf->adapter->ports.lock); list_del(&ptp->port.list_node); mutex_unlock(&pf->adapter->ports.lock); @@ -3134,18 +3139,18 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) mutex_init(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx, - ptp_port->port_num); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_init_tx_e810(pf, &ptp_port->tx); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); return ice_ptp_init_tx_e82x(pf, &ptp_port->tx, ptp_port->port_num); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx, + ptp_port->port_num); default: return -ENODEV; } @@ -3162,8 +3167,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) */ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { - switch (ice_get_phy_model(&pf->hw)) { - case ICE_PHY_E82X: + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: /* E822 based PHY has the clock owner process the interrupt * for all ports. */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 53ce40fa2fe6..8475d422f1ec 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) int err; /* Disable sticky lock detection so lock err reported is accurate */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw); else err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw); @@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) /* Configure the CGU PLL using the parameters from the function * capabilities. */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref, (enum ice_clk_src)ts_info->clk_src); else @@ -827,8 +827,8 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, /* Certain hardware families share the same register values for the * port register and source timer register. */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810; default: break; @@ -2729,10 +2729,7 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u32 phy_rev; - int err; - ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; @@ -2742,9 +2739,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) ptp->num_lports = params->num_phys * ptp->ports_per_phy; ice_sb_access_ena_eth56g(hw, true); - err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) - ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -4792,7 +4786,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold) */ static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E82X; ptp->num_lports = 8; ptp->ports_per_phy = 8; } @@ -5445,7 +5438,6 @@ exit: */ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E810; ptp->num_lports = 8; ptp->ports_per_phy = 4; @@ -5454,9 +5446,8 @@ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) /* Device agnostic functions * - * The following functions implement shared behavior common to both E822 and - * E810 devices, possibly calling a device specific implementation where - * necessary. + * The following functions implement shared behavior common to all devices, + * possibly calling a device specific implementation where necessary. */ /** @@ -5519,14 +5510,19 @@ void ice_ptp_init_hw(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; - if (ice_is_e822(hw) || ice_is_e823(hw)) - ice_ptp_init_phy_e82x(ptp); - else if (ice_is_e810(hw)) + switch (hw->mac_type) { + case ICE_MAC_E810: ice_ptp_init_phy_e810(ptp); - else if (ice_is_e825c(hw)) + break; + case ICE_MAC_GENERIC: + ice_ptp_init_phy_e82x(ptp); + break; + case ICE_MAC_GENERIC_3K_E825: ice_ptp_init_phy_e825(hw); - else - ptp->phy_model = ICE_PHY_UNSUP; + break; + default: + return; + } } /** @@ -5547,11 +5543,11 @@ void ice_ptp_init_hw(struct ice_hw *hw) static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: return ice_ptp_write_port_cmd_e82x(hw, port, cmd); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); default: return -EOPNOTSUPP; } @@ -5612,8 +5608,8 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) u32 port; /* PHY models which can program all ports simultaneously */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_port_cmd_e810(hw, cmd); default: break; @@ -5691,17 +5687,17 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_time_eth56g(hw, - (u32)(time & 0xFFFFFFFF)); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_time_eth56g(hw, + (u32)(time & 0xFFFFFFFF)); + break; default: err = -EOPNOTSUPP; } @@ -5737,16 +5733,16 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_incval_eth56g(hw, incval); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_incval_e82x(hw, incval); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_incval_eth56g(hw, incval); + break; default: err = -EOPNOTSUPP; } @@ -5806,16 +5802,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_adj_eth56g(hw, adj); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_adj_eth56g(hw, adj); + break; default: err = -EOPNOTSUPP; } @@ -5839,13 +5835,13 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) */ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp); + case ICE_MAC_GENERIC_3K_E825: + return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); default: return -EOPNOTSUPP; } @@ -5869,13 +5865,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_clear_ptp_tstamp_eth56g(hw, block, idx); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_clear_phy_tstamp_e82x(hw, block, idx); + case ICE_MAC_GENERIC_3K_E825: + return ice_clear_ptp_tstamp_eth56g(hw, block, idx); default: return -EOPNOTSUPP; } @@ -5932,14 +5928,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) */ void ice_ptp_reset_ts_memory(struct ice_hw *hw) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - ice_ptp_reset_ts_memory_eth56g(hw); - break; - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: ice_ptp_reset_ts_memory_e82x(hw); break; - case ICE_PHY_E810: + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_reset_ts_memory_eth56g(hw); + break; + case ICE_MAC_E810: default: return; } @@ -5961,13 +5957,13 @@ int ice_ptp_init_phc(struct ice_hw *hw) /* Clear event err indications for auxiliary pins */ (void)rd32(hw, GLTSYN_STAT(src_idx)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_phc_eth56g(hw); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_init_phc_e810(hw); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_phc_eth56g(hw); default: return -EOPNOTSUPP; } @@ -5986,16 +5982,16 @@ int ice_ptp_init_phc(struct ice_hw *hw) */ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, - tstamp_ready); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_get_phy_tx_tstamp_ready_e810(hw, block, tstamp_ready); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_get_phy_tx_tstamp_ready_e82x(hw, block, tstamp_ready); + case ICE_MAC_GENERIC_3K_E825: + return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, + tstamp_ready); break; default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 15f048d9b582..6b4679407558 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -430,13 +430,13 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); */ static inline u64 ice_get_base_incval(struct ice_hw *hw) { - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_ETH56G_NOMINAL_INCVAL; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ICE_PTP_NOMINAL_INCVAL_E810; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); + case ICE_MAC_GENERIC_3K_E825: + return ICE_ETH56G_NOMINAL_INCVAL; default: return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 33a1a5934c0d..0aab21113cc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -871,14 +871,6 @@ union ice_phy_params { struct ice_eth56g_params eth56g; }; -/* PHY model */ -enum ice_phy_model { - ICE_PHY_UNSUP = -1, - ICE_PHY_E810 = 1, - ICE_PHY_E82X, - ICE_PHY_ETH56G, -}; - /* Global Link Topology */ enum ice_global_link_topo { ICE_LINK_TOPO_UP_TO_2_LINKS, @@ -888,7 +880,6 @@ enum ice_global_link_topo { }; struct ice_ptp_hw { - enum ice_phy_model phy_model; union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; -- 2.50.1 From ea7029fe10f46fd1ec0367b1b86bc744f9d9b34f Mon Sep 17 00:00:00 2001 From: Karol Kolacinski Date: Mon, 30 Sep 2024 14:12:40 +0200 Subject: [PATCH 16/16] ice: Use FIELD_PREP for timestamp values Instead of using shifts and casts, use FIELD_PREP after reading 40b timestamp values. Rename a couple defines for better clarity and consistency. Reviewed-by: Simon Horman Signed-off-by: Karol Kolacinski Tested-by: Pucha Himasekhar Reddy (A Contingent worker at Intel) Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 11 ++++++----- drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 9 +++++---- 2 files changed, 11 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 8475d422f1ec..a2a666e6df86 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -1576,9 +1576,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx, * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | - FIELD_PREP(TS_PHY_LOW_M, lo); - + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -3213,7 +3212,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo); + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -4979,7 +4979,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) /* For E810 devices, the timestamp is reported with the lower 32 bits * in the low register, and the upper 8 bits in the high register. */ - *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 6b4679407558..4381ef4a6c77 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -652,15 +652,16 @@ static inline bool ice_is_dual(struct ice_hw *hw) /* Source timer incval macros */ #define INCVAL_HIGH_M 0xFF -/* Timestamp block macros */ +/* PHY 40b registers macros */ +#define PHY_EXT_40B_LOW_M GENMASK(31, 0) +#define PHY_EXT_40B_HIGH_M GENMASK_ULL(39, 32) +#define PHY_40B_LOW_M GENMASK(7, 0) +#define PHY_40B_HIGH_M GENMASK_ULL(39, 8) #define TS_VALID BIT(0) #define TS_LOW_M 0xFFFFFFFF #define TS_HIGH_M 0xFF #define TS_HIGH_S 32 -#define TS_PHY_LOW_M GENMASK(7, 0) -#define TS_PHY_HIGH_M GENMASK_ULL(39, 8) - #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 -- 2.50.1