- 18 Jul, 2018 40 commits
-
-
David S. Miller authored
Ido Schimmel says: ==================== mlxsw: Introduce initial Spectrum-2 support This patch set adds initial support for the Spectrum-2 ASIC. The first two patches add Spectrum-2 specific KVD linear (KVDL) manager. Unlike the Spectrum ASIC, there is no linear memory and instead the type of the entry (e.g., nexthop) and its index are hashed and the entry is placed in the computed address in the hash-based KVD memory. The third patch adds Spectrum-2 stubs in the multicast routing code. Support for multicast routing will be added later on. Patches 4-15 add ACL support. The Spectrum-2 ASIC includes an algorithmic TCAM (A-TCAM) and a regular circuit TCAM (C-TCAM) for rules that can't be inserted into the A-TCAM. This set does not make use of the A-TCAM and only places rules in the C-TCAM. This provides equivalent scale and performance to the Spectrum ASIC. A follow-up patch set will introduce A-TCAM support. The last patch extends the main driver file to work with both ASICs. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Jiri Pirko authored
Extend existing driver for Spectrum ASIC to support Spectrum-2 ASIC. Signed-off-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
Ido Schimmel <idosch@mellanox.com> Signed-off-by:
-
Jiri Pirko authored
Utilize only C-TCAM for now. Do very minimal A-TCAM initialization in order to make C-TCAM work. Signed-off-by:
-
Ido Schimmel authored
In Spectrum-2, ACL regions that use 8 or 12 key blocks require several consecutive hardware regions. In order to allow defragmentation, the device stores a mapping from a logical region ID to an hardware region ID, which is similar to the page table that is used to translate virtual addresses to physical addresses. Add the region association callback to the region create sequence and implement it as a NOP in Spectrum which does not require it. Signed-off-by:
-
Ido Schimmel authored
Encode each flexible key block in the general block scheme according its block index. Signed-off-by:
-
Ido Schimmel authored
In Spectrum the key (and mask) block layout is very straight forward and every block is 16 bytes aligned. However, in Spectrum-2 the blocks are not even byte aligned, which makes it difficult to encode them using current method. Instead, first encode each block and then encode the block in the general blocks layout. Signed-off-by:
-
Ido Schimmel authored
The PGCR register configures general Policy-Engine settings. Specifically, we are going to use it in order to set the default action base pointer, which determines where the default action (when there is no hit) is located for each region. Signed-off-by:
-
Ido Schimmel authored
The PERERP register configures the region eRPs. It can be used, for example, to enable lookup in the C-TCAM in addition to the A-TCAM. To be able to perform a lookup in the C-TCAM we need to "use" the eRP table. This is done by marking the pointer as valid, but zeroing the eRP table vector. Signed-off-by:
-
Ido Schimmel authored
The PERCR register configures the region parameters such as whether to consult the bloom filter before performing a lookup using a specific eRP. For C-TCAM only usage we don't need to accurately set the master mask. Instead, we can set all of its bits to make sure all the extracted keys are actually used. Signed-off-by:
-
Jiri Pirko authored
The PERAR register is used to associate a hw region for region_id's. Signed-off-by:
-
Jiri Pirko authored
In Spectrum-2, activity cannot be find out by TCAM rule (PTCEv2 register), but rather by associated action set. For that purpose, extend action ops to allow query activity from PEFA register. Block activity is decided according to activity of the first set. Signed-off-by:
-
Jiri Pirko authored
In Spectrum-2, the PEFA register is extend to report if the action set was hit during processing of packets. Introduce this extension and adjust the code around this accordingly. Signed-off-by:
-
Jiri Pirko authored
Introduce key blocks for Spectrum-2 that contains the same elements used already for Spectrum1. Along with that, introduce encoder stub. Signed-off-by:
-
Jiri Pirko authored
In Spectrum-2, no action set is stored directly in TCAM, all are located in KVD linear. So ask core to treat the first set as dummy empty one, to be just used for PTCEV2 purposes. Signed-off-by:
-
Jiri Pirko authored
Add dummy ops for now. The ops are going to be implemented later on. Signed-off-by:
-
Jiri Pirko authored
In Spectrum-2, KVD linear indexes are hashed into KVD hash. Therefore it is possible for multiple resource types to use same indexes. There are multiple index spaces. Also, the index space is bigger than the actual KVD hash area, which allows to have holes in the index space without any penalization. The HW has to be told in case the index for particular resource type is no longer used so it can be freed from KVD hash. IEDR register is used for that. Signed-off-by:
-
Jiri Pirko authored
The IEDR register is used for deleting entries from the entry tables. Signed-off-by:
-
git://git.open-mesh.org/linux-mergeDavid S. Miller authored
Simon Wunderlich says: ==================== This feature/cleanup patchset includes the following patches: - Don't call BATMAN_V experimental in Kconfig anymore, by Sven Eckelmann - Enable DAT by default at compile time, by Antonio Quartulli - Remove obsolete default n in Kconfig, by Sven Eckelmann - Fix checkpatch spelling errors, by Sven Eckelmann - Unify header guards style, by Sven Eckelmann - Consolidate batadv_purge_orig functions, by Sven Eckelmann - Replace type define with proper typedef, by Sven Eckelmann ==================== Signed-off-by: -
Håkon Bugge authored
Signed-off-by:
Håkon Bugge <haakon.bugge@oracle.com> Signed-off-by:
-
Håkon Bugge authored
Commit b6fb0df1 ("RDS/IB: Make ib_recv_refill return void") did not change the comment accordingly. Fixes: b6fb0df1 ("RDS/IB: Make ib_recv_refill return void") Signed-off-by:
Santosh Shilimkar <santosh.shilimkar@oracle.ccom> Signed-off-by:
-
David S. Miller authored
drivers/net/dsa/rtl8366.c: In function ‘rtl8366_reset_vlan’: drivers/net/dsa/rtl8366.c:234:25: warning: unused variable ‘vlan4k’ [-Wunused-variable] Signed-off-by: -
David S. Miller authored
Niklas Söderlund says: ==================== ravb: small sparse fixes This are fixes that have bugged me whenever I run sparse to check my own changes to the driver. It's based on the latest net-next tree and tested on M3-N. ==================== Signed-off-by: -
Niklas Söderlund authored
The wrong helper is used to swap the bytes when adding the lower bits of the TX descriptors tag field in the shared ds_tagl variable. The variable contains the DS[11:0] field and then the TAG[3:0] bits. The mistake was highlighted by the sparse warning: ravb_main.c:1622:31: left side has type restricted __le16 ravb_main.c:1622:31: right side has type unsigned short ravb_main.c:1622:31: warning: invalid assignment: |= ravb_main.c:1622:34: warning: cast to restricted __le16 Signed-off-by:
Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se> Reviewed-by:
Geert Uytterhoeven <geert+renesas@glider.be> Acked-by:
Sergei Shtylyov <sergei.shtylyov@cogentembedded.com> Signed-off-by:
-
Niklas Söderlund authored
This fixes sparse warning: ravb_main.c:1257 ravb_get_strings() error: memcpy() '*ravb_gstrings_stats' too small (32 vs 960) Signed-off-by:
-
Niklas Söderlund authored
Inside a loop in ravb_get_ethtool_stats() a variable 'stats' is declared resulting in the argument also named 'stats' to be shadowed. Fix this warning by renaming the unused argument 'stats' to 'estats'. This fixes the sparse warning: ravb_main.c:1225:36: originally declared here ravb_main.c:1233:41: warning: symbol 'stats' shadows an earlier one Signed-off-by:
-
Linus Walleij authored
This adds the Ethernet and Realtek switch device to the D-Link DIR-685 Gemini-based device. Signed-off-by:
Linus Walleij <linus.walleij@linaro.org> Signed-off-by:
-
Linus Walleij authored
This adds a driver core for the Realtek SMI chips and a subdriver for the RTL8366RB. I just added this chip simply because it is all I can test. The code is a massaged variant of the code that has been sitting out-of-tree in OpenWRT for years in the absence of a proper switch subsystem. This creates a DSA driver for it. I have tried to credit the original authors wherever possible. The main changes I've done from the OpenWRT code: - Added an IRQ chip inside the RTL8366RB switch to demux and handle the line state IRQs. - Distributed the phy handling out to the PHY driver. - Added some RTL8366RB code that was missing in the driver at the time, such as setting up "green ethernet" with a funny jam table and forcing MAC5 (the CPU port) into 1 GBit. - Select jam table and add the default jam table from the vendor driver, also for ASIC "version 0" if need be. - Do not store jam tables in the device tree, store them in the driver. - Pick in the "initvals" jam tables from OpenWRT's driver and make those get selected per compatible for the whole system. It's apparently about electrical settings for this system and whatnot, not really configuration from device tree. - Implemented LED control: beware of bugs because there are no LEDs on the device I am using! We do not implement custom DSA tags. This is explained in a comment in the driver as well: this "tagging protocol" is not simply a few extra bytes tagged on to the ethernet frame as DSA is used to. Instead, enabling the CPU tags will make the switch start talking Realtek RRCP internally. For example a simple ping will make this kind of packets appear inside the switch: 0000 ff ff ff ff ff ff bc ae c5 6b a8 3d 88 99 a2 00 0010 08 06 00 01 08 00 06 04 00 01 bc ae c5 6b a8 3d 0020 a9 fe 01 01 00 00 00 00 00 00 a9 fe 01 02 00 00 0030 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 As you can see a custom "8899" tagged packet using the protocol 0xa2. Norm RRCP appears to always have this protocol set to 0x01 according to OpenRRCP. You can also see that this is not a ping packet at all, instead the switch is starting to talk network management issues with the CPU port. So for now custom "tagging" is disabled. This was tested on the D-Link DIR-685 with initramfs and OpenWRT userspaces and works fine on all the LAN ports (lan0 .. lan3). The WAN port is yet not working. Cc: Antti Seppälä <a.seppala@gmail.com> Cc: Roman Yeryomin <roman@advem.lv> Cc: Colin Leitner <colin.leitner@googlemail.com> Cc: Gabor Juhos <juhosg@openwrt.org> Cc: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Linus Walleij authored
The Realtek SMI family is a set of DSA chips that provide switching in routers. This binding just follows the pattern set by other switches but with the introduction of an embedded irqchip to demux and handle the interrupts fired by the single line from the chip. This interrupt construction is similar to how we handle interrupt controllers inside PCI bridges etc. Cc: Antti Seppälä <a.seppala@gmail.com> Cc: Roman Yeryomin <roman@advem.lv> Cc: Colin Leitner <colin.leitner@googlemail.com> Cc: Gabor Juhos <juhosg@openwrt.org> Cc: Florian Fainelli <f.fainelli@gmail.com> Cc: devicetree@vger.kernel.org Signed-off-by:
-
Linus Walleij authored
The RTL8366RB is an ASIC with five internal PHYs for LAN0..LAN3 and WAN. The PHYs are spawn off the main device so they can be handled in a distributed manner by the Realtek PHY driver. All that is really needed is the power save feature enablement and letting the PHY driver core pick up the IRQ from the switch chip. Cc: Antti Seppälä <a.seppala@gmail.com> Cc: Roman Yeryomin <roman@advem.lv> Cc: Colin Leitner <colin.leitner@googlemail.com> Cc: Gabor Juhos <juhosg@openwrt.org> Cc: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Heiner Kallweit authored
The removed code would be called in two situations: 1. interface is brought up never or >10s after driver load 2. after close() Case 1 we can handle cleaner by ensuring chip is powered down when leaving probe(). open() callback will power up the chip. In case 2 we call rtl_pll_power_down() twice currently, from the close() callback and 10s later when entering runtime-suspend. This is avoided by this patch. Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
-
David S. Miller authored
Andrew Lunn says: ==================== HWMON support for SFP modules This patchset adds HWMON support to SFP modules. The two patches add some attributes for temperature and power sensors which are currently missing from the hwmon core. The third patch adds a helper for filtering out characters in hwmon names which are invalid. The last patch then extends the core SFP code to export the sensors found in SFP modules. This code has been tested with two SFP modules: module OEM SFP-7000-85 rev 11.0 sn M1512220075 dc 160221 module FINISAR CORP. FTLF8524E2GNL rev A sn PW40MNN dc 160725 The anonymous module uses external calibration, while the FINISAR uses internal calibration. Thus both code paths have been tested. Due to the cross subsystem nature of these patches, as discussed with the RFC, it is hoped Guenter Roeck will ACK the patches, and then Dave Miller will merge them all via net-next. ==================== Signed-off-by: -
Andrew Lunn authored
SFP modules can contain a number of sensors. The EEPROM also contains recommended alarm and critical values for each sensor, and indications of if these have been exceeded. Export this information via HWMON. Currently temperature, VCC, bias current, transmit power, and possibly receiver power is supported. The sensors in the modules can either return calibrate or uncalibrated values. Uncalibrated values need to be manipulated, using coefficients provided in the SFP EEPROM. Uncalibrated receive power values require floating point maths in order to calibrate them. Performing this in the kernel is hard. So if the SFP module indicates it uses uncalibrated values, RX power is not made available. With this hwmon device, it is possible to view the sensor values using lm-sensors programs: in0: +3.29 V (crit min = +2.90 V, min = +3.00 V) (max = +3.60 V, crit max = +3.70 V) temp1: +33.0°C (low = -5.0°C, high = +80.0°C) (crit low = -10.0°C, crit = +85.0°C) power1: 1000.00 nW (max = 794.00 uW, min = 50.00 uW) ALARM (LCRIT) (lcrit = 40.00 uW, crit = 1000.00 uW) curr1: +0.00 A (crit min = +0.00 A, min = +0.00 A) ALARM (LCRIT, MIN) (max = +0.01 A, crit max = +0.01 A) The scaling sensors performs on the bias current is not particularly good. The raw values are more useful: curr1: curr1_input: 0.000 curr1_min: 0.002 curr1_max: 0.010 curr1_lcrit: 0.000 curr1_crit: 0.011 curr1_min_alarm: 1.000 curr1_max_alarm: 0.000 curr1_lcrit_alarm: 1.000 curr1_crit_alarm: 0.000 In order to keep the I2C overhead to a minimum, the constant values, such as limits and calibration coefficients are read once at module insertion time. Thus only reading *_input and *_alarm properties requires i2c read operations. Signed-off-by:Andrew Lunn <andrew@lunn.ch> Acked-by:
Guenter Roeck <linux@roeck-us.net> Signed-off-by:
-
Andrew Lunn authored
HWMON device names are not allowed to contain "-* \t\n". Add a helper which will return true if passed an invalid character. It can be used to massage a string into a hwmon compatible name by replacing invalid characters with '_'. Signed-off-by:
-
Andrew Lunn authored
Some sensors support reporting minimal and lower critical power, as well as alarms when these thresholds are reached. Add support for these attributes to the hwmon core. Signed-off-by:
-
Andrew Lunn authored
The enum hwmon_temp_lcrit_alarm exists, but the BIT definition is missing. Signed-off-by:
-
David S. Miller authored
Heiner Kallweit says: ==================== r8169: add phylib support Now that all the basic refactoring has been done we can add phylib support. This patch series was successfully tested on: RTL8168h RTL8168evl RTL8169sb Changes in v2: - return error in mdio ops if phyaddr > 0 - advertise pause modes - added reviewed-by for several patches Changes in v3: - return ENODEV for unused phy addresses in mdio ops - remove unneeded PHY suspend in patch 2 - use recently added phy_speed_down and phy_speed_up in patch 7 - other minor changes based on review comments ==================== Signed-off-by: -
Heiner Kallweit authored
Instead of accessing the PHYstatus register we can use the information phylib stores in the phy_device structure. Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Heiner Kallweit authored
The only remaining usage of the struct mii_if_info member is to store the information whether the chip is GMII-capable. So we can replace it with a simple flag. Signed-off-by:
-
Heiner Kallweit authored
We can remove rtl8169_set_speed_xmii() now that phylib handles all this. Signed-off-by:
-
Heiner Kallweit authored
Use new phylib functions phy_speed_down() and phy_speed_up(). Signed-off-by:
-
