- 03 Mar, 2009 5 commits
-
-
Eilon Greenstein authored
As noted by Ben Hutchings <bhutchings@solarflare.com>, these smb_mb are not needed Signed-off-by:
Eilon Greenstein <eilong@broadcom.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David Dillow authored
The conversion to avoid using pci_alloc_consistent() broke the firmware load process, as well as added an order-4 kmalloc and doubled the memory usage of the firmware image. Go back to loading a page at a time. Also, since the user can now give us utter garbage for firmware, do a cursory validation so we don't try to load just anything. Signed-off-by:
David Dillow <dave@thedillows.org> Signed-off-by:
-
Jesse Brandeburg authored
This is in reference to the issue shown in kerneloops (search e1000 unmap) The e1000 transmit code was calling pci_unmap_page on dma handles that it might have called pci_map_single on. Same bug as e1000e Signed-off-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Acked-by:
Bruce Allan <bruce.w.allan@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com> Signed-off-by:
-
Jesse Brandeburg authored
This is in reference to https://bugzilla.redhat.com/show_bug.cgi?id=484494 Also addresses issue show in kerneloops The e1000e transmit code was calling pci_unmap_page on dma handles that it might have called pci_map_single on. Signed-off-by:
-
Alexander Duyck authored
Remove skb_orphan call from igb driver as it can cause multiple issues due to the fact that it is calling the desctructor and removing the skb from the socket prior to transmission. The call was added to improve performance but did so by allowing the skb to be removed from the socket which gave the socket more window space to transmit. The performance gain is not worth the extra problems that this kind of workaround can introduce as this could lead to a potential DoS if a UDP stream decided to monopolize the transmit path. Signed-off-by:
Alexander Duyck <alexander.h.duyck@intel.com> Acked-by:
Mitch Williams <mitch.a.williams@intel.com> Signed-off-by:
-
- 02 Mar, 2009 35 commits
-
-
Randy Dunlap authored
Fix skbuff.h kernel-doc for timestamps: must include "struct" keyword, otherwise there are kernel-doc errors: Error(linux-next-20090227//include/linux/skbuff.h:161): cannot understand prototype: 'struct skb_shared_hwtstamps ' Error(linux-next-20090227//include/linux/skbuff.h:177): cannot understand prototype: 'union skb_shared_tx ' Signed-off-by:
Randy Dunlap <randy.dunlap@oracle.com> Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
Ben Hutchings <bhutchings@solarflare.com> Signed-off-by:
-
Ben Hutchings authored
Reinitialise LEDs after overriding them for identification. Rename set_fault_led method to set_id_led since we always use it for NIC identification and not faults. Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
-
Ben Hutchings authored
This is a new PHY supporting SFP+ modules, used in the SFN4112F reference design. It is similar to the QT2022C2 and shares much of its support code. Signed-off-by:
-
Ben Hutchings authored
Shuffle bits of the OUI into the conventional written order. Replace PHY id component macros with functions. Zero-pad PHY id components in log messages. Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
-
Ben Hutchings authored
During SFN4111T initialisation, check whether the PHY boot status indicates a bad firmware checksum. If so, prepare to reflash rather than continuing with normal initialisation. Remove redundant PHY boot status check from tenxpress_phy_init(). Signed-off-by:
-
Ben Hutchings authored
Commit 27dd2cac changed mdio_clause45_check_mmds() to read both DEVS0 and DEVS1 registers and to combine their values into an unsigned 32-bit mask. This made the following test for a negative (failure) value useless. Fix it to check whether either read failed. Signed-off-by:
-
Ben Hutchings authored
Signed-off-by:
-
Inaky Perez-Gonzalez authored
Allow the device to give the driver RX data with reorder information. When that is done, the device will indicate the driver if a packet has to be held in a (sorted) queue. It will also tell the driver when held packets have to be released to the OS. This is done to improve the WiMAX-protocol level retransmission support when missing frames are detected. The code docs provide details about the implementation. In general, this just hooks into the RX path in rx.c; if a packet with the reorder bit in the RX header is detected, the reorder information in the header is extracted and one of the four main reorder operations are executed. In one case (queue) no packet will be delivered to the networking stack, just queued, whereas in the others (reset, update_ws and queue_update_ws), queued packet might be delivered depending on the window start for the specific queue. The modifications to files other than rx.c are: - control.c: during device initialization, enable reordering support if the rx_reorder_disabled module parameter is not enabled - driver.c: expose a rx_reorder_disable module parameter and call i2400m_rx_setup/release() to initialize/shutdown RX reorder support. - i2400m.h: introduce members in 'struct i2400m' needed for implementing reorder support. - linux/i2400m.h: introduce TLVs, commands and constant definitions related to RX reorder Last but not least, the rx reorder code includes an small circular log where the last N reorder operations are recorded to be displayed in case of inconsistency. Otherwise diagnosing issues would be almost impossible. Signed-off-by:
Inaky Perez-Gonzalez <inaky@linux.intel.com> Signed-off-by:
-
Harvey Harrison authored
Base versions handle constant folding now. Edited by Inaky to fix conflicts due to changes in netdev.c Signed-off-by:
Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by:
-
Inaky Perez-Gonzalez authored
Newer i2400m firmwares (>= v1.4) extend the data RX protocol so that each packet has a 16 byte header. This header is mainly used to implement host reordeing (which is addressed in later commits). However, this header also allows us to overwrite it (once data has been extracted) with an Ethernet header and deliver to the networking stack without having to reallocate the skb (as it happened in fw <= v1.3) to make room for it. - control.c: indicate the device [dev_initialize()] that the driver wants to use the extended data RX protocol. Also involves adding the definition of the needed data types in include/linux/wimax/i2400m.h. - rx.c: handle the new payload type for the extended RX data protocol. Prepares the skb for delivery to netdev.c:i2400m_net_erx(). - netdev.c: Introduce i2400m_net_erx() that adds the fake ethernet address to a prepared skb and delivers it to the networking stack. - cleanup: in most instances in rx.c, the variable 'single' was renamed to 'single_last' for it better conveys its meaning. Signed-off-by:
-
Kay Sievers authored
Cc: inaky.perez-gonzalez@intel.com Cc: linux-wimax@intel.com Acked-by:
Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by:
Kay Sievers <kay.sievers@vrfy.org> Signed-off-by:
-
Inaky Perez-Gonzalez authored
For power saving reasons, WiMAX links can be put in idle mode while connected after a certain time of the link not being used for tx or rx. In this mode, the device pages the base-station regularly and when data is ready to be transmitted, the link is revived. This patch allows the user to control the time the device has to be idle before it decides to go to idle mode from a sysfs interace. It also updates the initialization code to acknowledge the module variable 'idle_mode_disabled' when the firmware is a newer version (upcoming 1.4 vs 2.6.29's v1.3). The method for setting the idle mode timeout in the older firmwares is much more limited and can be only done at initialization time. Thus, the sysfs file will return -ENOSYS on older ones. Signed-off-by:
-
Inaky Perez-Gonzalez authored
Upcoming modifications will need to test for the running firmware version before activating a feature or not. This is helpful to implement backward compatibility with older firmware versions. Modify i2400m_firmware_check() to encode in i2400m->fw_version the major and minor version numbers of the firmware interface. As well, move the call to be done as the very first operation once we have communication with the device during probe() [in __i2400m_dev_start()]. This is needed so any operation that is executed afterwards can determine which fw version it is talking to. Signed-off-by:
-
Inaky Perez-Gonzalez authored
Firmware interface version 8.x.x has long been deprecated and is no longer supported (nor available, as it is a preproduction firmware), so it can be safely dropped. Add support for firmware interface v9.2.x (current is 9.1.x). Firmware version 9.2.x is backwards compatible with 9.1.x; new features are enabled if switches are pressed to turn them on. Forthcoming commits to the driver will start pressing those switches when the firmware interface supports it. Signed-off-by:
-
Inaky Perez-Gonzalez authored
In order to support backwards compatibility with older firmwares when a driver is updated by a new kernel release, the i2400m bus drivers can declare a list of firmware files they can work with (in general these will be each a different version). The firmware loader will try them in sequence until one loads. Thus, if a user doesn't have the latest and greatest firmware that a newly installed kernel would require, the driver would fall back to the firmware from a previous release. To support this, the i2400m->bus_fw_name is changed to be a NULL terminated array firmware file names (and renamed to bus_fw_names) and we add a new entry (i2400m->fw_name) that points to the name of the firmware being currently used. All code that needs to print the firmware file name uses i2400m->fw_name instead of the old i2400m->bus_fw_name. The code in i2400m_dev_bootstrap() that loads the firmware is changed with an iterator over the firmware file name list that tries to load each form user space, using the first one that succeeds in request_firmware() (and thus stopping the iteration). The USB and SDIO bus drivers are updated to take advantage of this and reflect which firmwares they support. Signed-off-by:
-
Gerrit Renker authored
This fixes a problem caused by the overlap of the connection-setup and established-state phases of DCCP connections. During connection setup, the client retransmits Confirm Feature-Negotiation options until a response from the server signals that it can move from the half-established PARTOPEN into the OPEN state, whereupon the connection is fully established on both ends (RFC 4340, 8.1.5). However, since the client may already send data while it is in the PARTOPEN state, consequences arise for the Maximum Packet Size: the problem is that the initial option overhead is much higher than for the subsequent established phase, as it involves potentially many variable-length list-type options (server-priority options, RFC 4340, 6.4). Applying the standard MPS is insufficient here: especially with larger payloads this can lead to annoying, counter-intuitive EMSGSIZE errors. On the other hand, reducing the MPS available for the established phase by the added initial overhead is highly wasteful and inefficient. The solution chosen therefore is a two-phase strategy: If the payload length of the DataAck in PARTOPEN is too large, an Ack is sent to carry the options, and the feature-negotiation list is then flushed. This means that the server gets two Acks for one Response. If both Acks get lost, it is probably better to restart the connection anyway and devising yet another special-case does not seem worth the extra complexity. The result is a higher utilisation of the available packet space for the data transmission phase (established state) of a connection. The patch (over-)estimates the initial overhead to be 32*4 bytes -- commonly seen values were around 90 bytes for initial feature-negotiation options. It uses sizeof(u32) to mean "aligned units of 4 bytes". For consistency, another use of 4-byte alignment is adapted. Signed-off-by:
Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by:
-
Gerrit Renker authored
This patch resolves a long-standing FIXME to dynamically update the Maximum Packet Size depending on actual options usage. It uses the flags set by the feature-negotiation infrastructure to compute the required header option size. Most options are fixed-size, a notable exception are Ack Vectors (required currently only by CCID-2). These can have any length between 3 and 1020 bytes. As a result of testing, 16 bytes (2 bytes for type/length plus 14 Ack Vector cells) have been found to be sufficient for loss-free situations. There are currently no CCID-specific header options which may appear on data packets, thus it is not necessary to define a corresponding CCID field as suggested in the old comment. Further changes: ---------------- Adjusted the type of 'cur_mps' to match the unsigned return type of the function. Signed-off-by:
Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by:
-
Ilpo Järvinen authored
I guess these fields were one day 16-bit in the struct but nowadays they're just using 8 bits anyway. This is just a precaution, didn't result any change in my case but who knows what all those varying gcc versions & options do. I've been told that 16-bit is not so nice with some cpus. Signed-off-by:
Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by:
-
Ilpo Järvinen authored
copied was assigned zero right before the goto, so if (copied) cannot ever be true. Signed-off-by:
-
Ilpo Järvinen authored
Also fixes insignificant bug that would cause sending of stale SACK block (would occur in some corner cases). Signed-off-by:
-
Ilpo Järvinen authored
It seems that implementation in yeah was inconsistent to what other did as it would increase cwnd one ack earlier than the others do. Size benefits: bictcp_cong_avoid | -36 tcp_cong_avoid_ai | +52 bictcp_cong_avoid | -34 tcp_scalable_cong_avoid | -36 tcp_veno_cong_avoid | -12 tcp_yeah_cong_avoid | -38 = -104 bytes total Signed-off-by:
-
Ilpo Järvinen authored
Similar to what is done elsewhere in TCP code when double state checks are being done. Signed-off-by:
-
Ilpo Järvinen authored
Signed-off-by:
-
Ilpo Järvinen authored
Redundant checks made indentation impossible to follow. However, it might be useful to make this ca_state+is_sack indexed array. Signed-off-by:
-
Ilpo Järvinen authored
Some comment about its current state added. So far I have seen very few cases where the thing is actually useful, usually just marginally (though admittedly I don't usually see top of window losses where it seems possible that there could be some gain), instead, more often the cases suffer from L-marking spike which is certainly not desirable (I'll bury improving it to my todo list, but on a low prio position). Signed-off-by:
-
Ilpo Järvinen authored
Arnd Hannemann <hannemann@nets.rwth-aachen.de> noticed and was puzzled by the fact that !tcp_is_fack(tp) leads to early return near the beginning and the later on tcp_is_fack(tp) was still used in an if condition. The later check was a left-over from RFC3517 SACK stuff (== !tcp_is_fack(tp) behavior nowadays) as there wasn't clear way how to handle this particular check cheaply in the spirit of RFC3517 (using only SACK blocks, not holes + SACK blocks as with FACK). I sort of left it there as a reminder but since it's confusing other people just remove it and comment the missing-feature stuff instead. Signed-off-by:
-
Ilpo Järvinen authored
If cur_mss grew very recently so that the previously G/TSOed skb now fits well into a single segment it would get send up in parts unless we calculate # of segments again. This corner-case could happen eg. after mtu probe completes or less than previously sack blocks are required for the opposite direction. Signed-off-by:
-
Ilpo Järvinen authored
1) We didn't remove any skbs, so no need to handle stale refs. 2) scoreboard_skb_hint is trivial, no timestamps were changed so no need to clear that one 3) lost_skb_hint needs tweaking similar to that of tcp_sacktag_one(). Signed-off-by:
-
Ilpo Järvinen authored
If skb can be sent right away, we certainly should do that if it's in the middle of the queue because it won't get more data into it. Signed-off-by:
-
Ilpo Järvinen authored
It is possible that lost_cnt_hint gets underflow in tcp_clean_rtx_queue because the cumulative ACK can cover the segment where lost_skb_hint points to only partially, which means that the hint is not cleared, opposite to what my (earlier) comment claimed. Also I don't agree what I ended up writing about non-trivial case there to be what I intented to say. It was not supposed to happen that the hint won't get cleared and we underflow in any scenario. In general, this is quite hard to trigger in practice. Signed-off-by:
-
Ilpo Järvinen authored
Backtracking to sacked skbs is a horrible performance killer since the hint cannot be advanced successfully past them... ...And it's totally unnecessary too. In theory this is 2.6.27..28 regression but I doubt anybody can make .28 to have worse performance because of other TCP improvements. Signed-off-by:
-
Guo-Fu Tseng authored
From: Guo-Fu Tseng <cooldavid@cooldavid.org> Advance version number after previous changes. Sorry for not come along with previous patch series. Signed-off-by:
-
