From 1080d709fb9d8cd4392f93476ee46a9d6ea05a5b Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 27 Oct 2008 12:28:25 -0700 Subject: net: implement emergency route cache rebulds when gc_elasticity is exceeded This is a patch to provide on demand route cache rebuilding. Currently, our route cache is rebulid periodically regardless of need. This introduced unneeded periodic latency. This patch offers a better approach. Using code provided by Eric Dumazet, we compute the standard deviation of the average hash bucket chain length while running rt_check_expire. Should any given chain length grow to larger that average plus 4 standard deviations, we trigger an emergency hash table rebuild for that net namespace. This allows for the common case in which chains are well behaved and do not grow unevenly to not incur any latency at all, while those systems (which may be being maliciously attacked), only rebuild when the attack is detected. This patch take 2 other factors into account: 1) chains with multiple entries that differ by attributes that do not affect the hash value are only counted once, so as not to unduly bias system to rebuilding if features like QOS are heavily used 2) if rebuilding crosses a certain threshold (which is adjustable via the added sysctl in this patch), route caching is disabled entirely for that net namespace, since constant rebuilding is less efficient that no caching at all Tested successfully by me. Signed-off-by: Neil Horman Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index d84932650fd3..c7712787933c 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -27,6 +27,12 @@ min_adv_mss - INTEGER The advertised MSS depends on the first hop route MTU, but will never be lower than this setting. +rt_cache_rebuild_count - INTEGER + The per net-namespace route cache emergency rebuild threshold. + Any net-namespace having its route cache rebuilt due to + a hash bucket chain being too long more than this many times + will have its route caching disabled + IP Fragmentation: ipfrag_high_thresh - INTEGER -- cgit v1.2.3 From 6b1abbaefa31b84cc02bf4006ba8a63393de1136 Mon Sep 17 00:00:00 2001 From: Adrian Bunk Date: Wed, 29 Oct 2008 14:22:15 -0700 Subject: The overdue eepro100 removal. Signed-off-by: Adrian Bunk Cc: Jeff Garzik Signed-off-by: Andrew Morton Signed-off-by: Jeff Garzik --- Documentation/feature-removal-schedule.txt | 7 - MAINTAINERS | 5 - drivers/net/Kconfig | 13 - drivers/net/Makefile | 1 - drivers/net/eepro100.c | 2400 ---------------------------- 5 files changed, 2426 deletions(-) delete mode 100644 drivers/net/eepro100.c (limited to 'Documentation') diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 05d71b4b9430..6ecd4f0a24f0 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -144,13 +144,6 @@ Who: Christoph Hellwig --------------------------- -What: eepro100 network driver -When: January 2007 -Why: replaced by the e100 driver -Who: Adrian Bunk - ---------------------------- - What: Unused EXPORT_SYMBOL/EXPORT_SYMBOL_GPL exports (temporary transition config option provided until then) The transition config option will also be removed at the same time. diff --git a/MAINTAINERS b/MAINTAINERS index 16202c8ac68f..74e69ab8c132 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1599,11 +1599,6 @@ L: acpi4asus-user@lists.sourceforge.net W: http://sourceforge.net/projects/acpi4asus S: Maintained -EEPRO100 NETWORK DRIVER -P: Andrey V. Savochkin -M: saw@saw.sw.com.sg -S: Maintained - EFS FILESYSTEM W: http://aeschi.ch.eu.org/efs/ S: Orphan diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index f749b40f954e..0f3e6b2d2808 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -1414,19 +1414,6 @@ config TC35815 depends on NET_PCI && PCI && MIPS select PHYLIB -config EEPRO100 - tristate "EtherExpressPro/100 support (eepro100, original Becker driver)" - depends on NET_PCI && PCI - select MII - help - If you have an Intel EtherExpress PRO/100 PCI network (Ethernet) - card, say Y and read the Ethernet-HOWTO, available from - . - - To compile this driver as a module, choose M here. The module - will be called eepro100. - - config E100 tristate "Intel(R) PRO/100+ support" depends on NET_PCI && PCI diff --git a/drivers/net/Makefile b/drivers/net/Makefile index f19acf8b9220..657c47b1a6b6 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -53,7 +53,6 @@ obj-$(CONFIG_VORTEX) += 3c59x.o obj-$(CONFIG_TYPHOON) += typhoon.o obj-$(CONFIG_NE2K_PCI) += ne2k-pci.o 8390.o obj-$(CONFIG_PCNET32) += pcnet32.o -obj-$(CONFIG_EEPRO100) += eepro100.o obj-$(CONFIG_E100) += e100.o obj-$(CONFIG_TLAN) += tlan.o obj-$(CONFIG_EPIC100) += epic100.o diff --git a/drivers/net/eepro100.c b/drivers/net/eepro100.c deleted file mode 100644 index 81e84843c6a0..000000000000 --- a/drivers/net/eepro100.c +++ /dev/null @@ -1,2400 +0,0 @@ -/* drivers/net/eepro100.c: An Intel i82557-559 Ethernet driver for Linux. */ -/* - Written 1996-1999 by Donald Becker. - - The driver also contains updates by different kernel developers - (see incomplete list below). - Current maintainer is Andrey V. Savochkin . - Please use this email address and linux-kernel mailing list for bug reports. - - This software may be used and distributed according to the terms - of the GNU General Public License, incorporated herein by reference. - - This driver is for the Intel EtherExpress Pro100 (Speedo3) design. - It should work with all i82557/558/559 boards. - - Version history: - 1998 Apr - 2000 Feb Andrey V. Savochkin - Serious fixes for multicast filter list setting, TX timeout routine; - RX ring refilling logic; other stuff - 2000 Feb Jeff Garzik - Convert to new PCI driver interface - 2000 Mar 24 Dragan Stancevic - Disabled FC and ER, to avoid lockups when when we get FCP interrupts. - 2000 Jul 17 Goutham Rao - PCI DMA API fixes, adding pci_dma_sync_single calls where neccesary - 2000 Aug 31 David Mosberger - rx_align support: enables rx DMA without causing unaligned accesses. -*/ - -static const char * const version = -"eepro100.c:v1.09j-t 9/29/99 Donald Becker\n" -"eepro100.c: $Revision: 1.36 $ 2000/11/17 Modified by Andrey V. Savochkin and others\n"; - -/* A few user-configurable values that apply to all boards. - First set is undocumented and spelled per Intel recommendations. */ - -static int congenb /* = 0 */; /* Enable congestion control in the DP83840. */ -static int txfifo = 8; /* Tx FIFO threshold in 4 byte units, 0-15 */ -static int rxfifo = 8; /* Rx FIFO threshold, default 32 bytes. */ -/* Tx/Rx DMA burst length, 0-127, 0 == no preemption, tx==128 -> disabled. */ -static int txdmacount = 128; -static int rxdmacount /* = 0 */; - -#if defined(__ia64__) || defined(__alpha__) || defined(__sparc__) || defined(__mips__) || \ - defined(__arm__) - /* align rx buffers to 2 bytes so that IP header is aligned */ -# define rx_align(skb) skb_reserve((skb), 2) -# define RxFD_ALIGNMENT __attribute__ ((aligned (2), packed)) -#else -# define rx_align(skb) -# define RxFD_ALIGNMENT -#endif - -/* Set the copy breakpoint for the copy-only-tiny-buffer Rx method. - Lower values use more memory, but are faster. */ -static int rx_copybreak = 200; - -/* Maximum events (Rx packets, etc.) to handle at each interrupt. */ -static int max_interrupt_work = 20; - -/* Maximum number of multicast addresses to filter (vs. rx-all-multicast) */ -static int multicast_filter_limit = 64; - -/* 'options' is used to pass a transceiver override or full-duplex flag - e.g. "options=16" for FD, "options=32" for 100mbps-only. */ -static int full_duplex[] = {-1, -1, -1, -1, -1, -1, -1, -1}; -static int options[] = {-1, -1, -1, -1, -1, -1, -1, -1}; - -/* A few values that may be tweaked. */ -/* The ring sizes should be a power of two for efficiency. */ -#define TX_RING_SIZE 64 -#define RX_RING_SIZE 64 -/* How much slots multicast filter setup may take. - Do not descrease without changing set_rx_mode() implementaion. */ -#define TX_MULTICAST_SIZE 2 -#define TX_MULTICAST_RESERV (TX_MULTICAST_SIZE*2) -/* Actual number of TX packets queued, must be - <= TX_RING_SIZE-TX_MULTICAST_RESERV. */ -#define TX_QUEUE_LIMIT (TX_RING_SIZE-TX_MULTICAST_RESERV) -/* Hysteresis marking queue as no longer full. */ -#define TX_QUEUE_UNFULL (TX_QUEUE_LIMIT-4) - -/* Operational parameters that usually are not changed. */ - -/* Time in jiffies before concluding the transmitter is hung. */ -#define TX_TIMEOUT (2*HZ) -/* Size of an pre-allocated Rx buffer: + slack.*/ -#define PKT_BUF_SZ 1536 - -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -#include -#include -#include -#include -#include - -static int use_io; -static int debug = -1; -#define DEBUG_DEFAULT (NETIF_MSG_DRV | \ - NETIF_MSG_HW | \ - NETIF_MSG_RX_ERR | \ - NETIF_MSG_TX_ERR) -#define DEBUG ((debug >= 0) ? (1<"); -MODULE_DESCRIPTION("Intel i82557/i82558/i82559 PCI EtherExpressPro driver"); -MODULE_LICENSE("GPL"); -module_param(use_io, int, 0); -module_param(debug, int, 0); -module_param_array(options, int, NULL, 0); -module_param_array(full_duplex, int, NULL, 0); -module_param(congenb, int, 0); -module_param(txfifo, int, 0); -module_param(rxfifo, int, 0); -module_param(txdmacount, int, 0); -module_param(rxdmacount, int, 0); -module_param(rx_copybreak, int, 0); -module_param(max_interrupt_work, int, 0); -module_param(multicast_filter_limit, int, 0); -MODULE_PARM_DESC(debug, "debug level (0-6)"); -MODULE_PARM_DESC(options, "Bits 0-3: transceiver type, bit 4: full duplex, bit 5: 100Mbps"); -MODULE_PARM_DESC(full_duplex, "full duplex setting(s) (1)"); -MODULE_PARM_DESC(congenb, "Enable congestion control (1)"); -MODULE_PARM_DESC(txfifo, "Tx FIFO threshold in 4 byte units, (0-15)"); -MODULE_PARM_DESC(rxfifo, "Rx FIFO threshold in 4 byte units, (0-15)"); -MODULE_PARM_DESC(txdmacount, "Tx DMA burst length; 128 - disable (0-128)"); -MODULE_PARM_DESC(rxdmacount, "Rx DMA burst length; 128 - disable (0-128)"); -MODULE_PARM_DESC(rx_copybreak, "copy breakpoint for copy-only-tiny-frames"); -MODULE_PARM_DESC(max_interrupt_work, "maximum events handled per interrupt"); -MODULE_PARM_DESC(multicast_filter_limit, "maximum number of filtered multicast addresses"); - -#define RUN_AT(x) (jiffies + (x)) - -#define netdevice_start(dev) -#define netdevice_stop(dev) -#define netif_set_tx_timeout(dev, tf, tm) \ - do { \ - (dev)->tx_timeout = (tf); \ - (dev)->watchdog_timeo = (tm); \ - } while(0) - - - -/* - Theory of Operation - -I. Board Compatibility - -This device driver is designed for the Intel i82557 "Speedo3" chip, Intel's -single-chip fast Ethernet controller for PCI, as used on the Intel -EtherExpress Pro 100 adapter. - -II. Board-specific settings - -PCI bus devices are configured by the system at boot time, so no jumpers -need to be set on the board. The system BIOS should be set to assign the -PCI INTA signal to an otherwise unused system IRQ line. While it's -possible to share PCI interrupt lines, it negatively impacts performance and -only recent kernels support it. - -III. Driver operation - -IIIA. General -The Speedo3 is very similar to other Intel network chips, that is to say -"apparently designed on a different planet". This chips retains the complex -Rx and Tx descriptors and multiple buffers pointers as previous chips, but -also has simplified Tx and Rx buffer modes. This driver uses the "flexible" -Tx mode, but in a simplified lower-overhead manner: it associates only a -single buffer descriptor with each frame descriptor. - -Despite the extra space overhead in each receive skbuff, the driver must use -the simplified Rx buffer mode to assure that only a single data buffer is -associated with each RxFD. The driver implements this by reserving space -for the Rx descriptor at the head of each Rx skbuff. - -The Speedo-3 has receive and command unit base addresses that are added to -almost all descriptor pointers. The driver sets these to zero, so that all -pointer fields are absolute addresses. - -The System Control Block (SCB) of some previous Intel chips exists on the -chip in both PCI I/O and memory space. This driver uses the I/O space -registers, but might switch to memory mapped mode to better support non-x86 -processors. - -IIIB. Transmit structure - -The driver must use the complex Tx command+descriptor mode in order to -have a indirect pointer to the skbuff data section. Each Tx command block -(TxCB) is associated with two immediately appended Tx Buffer Descriptor -(TxBD). A fixed ring of these TxCB+TxBD pairs are kept as part of the -speedo_private data structure for each adapter instance. - -The newer i82558 explicitly supports this structure, and can read the two -TxBDs in the same PCI burst as the TxCB. - -This ring structure is used for all normal transmit packets, but the -transmit packet descriptors aren't long enough for most non-Tx commands such -as CmdConfigure. This is complicated by the possibility that the chip has -already loaded the link address in the previous descriptor. So for these -commands we convert the next free descriptor on the ring to a NoOp, and point -that descriptor's link to the complex command. - -An additional complexity of these non-transmit commands are that they may be -added asynchronous to the normal transmit queue, so we disable interrupts -whenever the Tx descriptor ring is manipulated. - -A notable aspect of these special configure commands is that they do -work with the normal Tx ring entry scavenge method. The Tx ring scavenge -is done at interrupt time using the 'dirty_tx' index, and checking for the -command-complete bit. While the setup frames may have the NoOp command on the -Tx ring marked as complete, but not have completed the setup command, this -is not a problem. The tx_ring entry can be still safely reused, as the -tx_skbuff[] entry is always empty for config_cmd and mc_setup frames. - -Commands may have bits set e.g. CmdSuspend in the command word to either -suspend or stop the transmit/command unit. This driver always flags the last -command with CmdSuspend, erases the CmdSuspend in the previous command, and -then issues a CU_RESUME. -Note: Watch out for the potential race condition here: imagine - erasing the previous suspend - the chip processes the previous command - the chip processes the final command, and suspends - doing the CU_RESUME - the chip processes the next-yet-valid post-final-command. -So blindly sending a CU_RESUME is only safe if we do it immediately after -after erasing the previous CmdSuspend, without the possibility of an -intervening delay. Thus the resume command is always within the -interrupts-disabled region. This is a timing dependence, but handling this -condition in a timing-independent way would considerably complicate the code. - -Note: In previous generation Intel chips, restarting the command unit was a -notoriously slow process. This is presumably no longer true. - -IIIC. Receive structure - -Because of the bus-master support on the Speedo3 this driver uses the new -SKBUFF_RX_COPYBREAK scheme, rather than a fixed intermediate receive buffer. -This scheme allocates full-sized skbuffs as receive buffers. The value -SKBUFF_RX_COPYBREAK is used as the copying breakpoint: it is chosen to -trade-off the memory wasted by passing the full-sized skbuff to the queue -layer for all frames vs. the copying cost of copying a frame to a -correctly-sized skbuff. - -For small frames the copying cost is negligible (esp. considering that we -are pre-loading the cache with immediately useful header information), so we -allocate a new, minimally-sized skbuff. For large frames the copying cost -is non-trivial, and the larger copy might flush the cache of useful data, so -we pass up the skbuff the packet was received into. - -IV. Notes - -Thanks to Steve Williams of Intel for arranging the non-disclosure agreement -that stated that I could disclose the information. But I still resent -having to sign an Intel NDA when I'm helping Intel sell their own product! - -*/ - -static int speedo_found1(struct pci_dev *pdev, void __iomem *ioaddr, int fnd_cnt, int acpi_idle_state); - -/* Offsets to the various registers. - All accesses need not be longword aligned. */ -enum speedo_offsets { - SCBStatus = 0, SCBCmd = 2, /* Rx/Command Unit command and status. */ - SCBIntmask = 3, - SCBPointer = 4, /* General purpose pointer. */ - SCBPort = 8, /* Misc. commands and operands. */ - SCBflash = 12, SCBeeprom = 14, /* EEPROM and flash memory control. */ - SCBCtrlMDI = 16, /* MDI interface control. */ - SCBEarlyRx = 20, /* Early receive byte count. */ -}; -/* Commands that can be put in a command list entry. */ -enum commands { - CmdNOp = 0, CmdIASetup = 0x10000, CmdConfigure = 0x20000, - CmdMulticastList = 0x30000, CmdTx = 0x40000, CmdTDR = 0x50000, - CmdDump = 0x60000, CmdDiagnose = 0x70000, - CmdSuspend = 0x40000000, /* Suspend after completion. */ - CmdIntr = 0x20000000, /* Interrupt after completion. */ - CmdTxFlex = 0x00080000, /* Use "Flexible mode" for CmdTx command. */ -}; -/* Clear CmdSuspend (1<<30) avoiding interference with the card access to the - status bits. Previous driver versions used separate 16 bit fields for - commands and statuses. --SAW - */ -#if defined(__alpha__) -# define clear_suspend(cmd) clear_bit(30, &(cmd)->cmd_status); -#else -# define clear_suspend(cmd) ((__le16 *)&(cmd)->cmd_status)[1] &= ~cpu_to_le16(1<<14) -#endif - -enum SCBCmdBits { - SCBMaskCmdDone=0x8000, SCBMaskRxDone=0x4000, SCBMaskCmdIdle=0x2000, - SCBMaskRxSuspend=0x1000, SCBMaskEarlyRx=0x0800, SCBMaskFlowCtl=0x0400, - SCBTriggerIntr=0x0200, SCBMaskAll=0x0100, - /* The rest are Rx and Tx commands. */ - CUStart=0x0010, CUResume=0x0020, CUStatsAddr=0x0040, CUShowStats=0x0050, - CUCmdBase=0x0060, /* CU Base address (set to zero) . */ - CUDumpStats=0x0070, /* Dump then reset stats counters. */ - RxStart=0x0001, RxResume=0x0002, RxAbort=0x0004, RxAddrLoad=0x0006, - RxResumeNoResources=0x0007, -}; - -enum SCBPort_cmds { - PortReset=0, PortSelfTest=1, PortPartialReset=2, PortDump=3, -}; - -/* The Speedo3 Rx and Tx frame/buffer descriptors. */ -struct descriptor { /* A generic descriptor. */ - volatile __le32 cmd_status; /* All command and status fields. */ - __le32 link; /* struct descriptor * */ - unsigned char params[0]; -}; - -/* The Speedo3 Rx and Tx buffer descriptors. */ -struct RxFD { /* Receive frame descriptor. */ - volatile __le32 status; - __le32 link; /* struct RxFD * */ - __le32 rx_buf_addr; /* void * */ - __le32 count; -} RxFD_ALIGNMENT; - -/* Selected elements of the Tx/RxFD.status word. */ -enum RxFD_bits { - RxComplete=0x8000, RxOK=0x2000, - RxErrCRC=0x0800, RxErrAlign=0x0400, RxErrTooBig=0x0200, RxErrSymbol=0x0010, - RxEth2Type=0x0020, RxNoMatch=0x0004, RxNoIAMatch=0x0002, - TxUnderrun=0x1000, StatusComplete=0x8000, -}; - -#define CONFIG_DATA_SIZE 22 -struct TxFD { /* Transmit frame descriptor set. */ - __le32 status; - __le32 link; /* void * */ - __le32 tx_desc_addr; /* Always points to the tx_buf_addr element. */ - __le32 count; /* # of TBD (=1), Tx start thresh., etc. */ - /* This constitutes two "TBD" entries -- we only use one. */ -#define TX_DESCR_BUF_OFFSET 16 - __le32 tx_buf_addr0; /* void *, frame to be transmitted. */ - __le32 tx_buf_size0; /* Length of Tx frame. */ - __le32 tx_buf_addr1; /* void *, frame to be transmitted. */ - __le32 tx_buf_size1; /* Length of Tx frame. */ - /* the structure must have space for at least CONFIG_DATA_SIZE starting - * from tx_desc_addr field */ -}; - -/* Multicast filter setting block. --SAW */ -struct speedo_mc_block { - struct speedo_mc_block *next; - unsigned int tx; - dma_addr_t frame_dma; - unsigned int len; - struct descriptor frame __attribute__ ((__aligned__(16))); -}; - -/* Elements of the dump_statistics block. This block must be lword aligned. */ -struct speedo_stats { - __le32 tx_good_frames; - __le32 tx_coll16_errs; - __le32 tx_late_colls; - __le32 tx_underruns; - __le32 tx_lost_carrier; - __le32 tx_deferred; - __le32 tx_one_colls; - __le32 tx_multi_colls; - __le32 tx_total_colls; - __le32 rx_good_frames; - __le32 rx_crc_errs; - __le32 rx_align_errs; - __le32 rx_resource_errs; - __le32 rx_overrun_errs; - __le32 rx_colls_errs; - __le32 rx_runt_errs; - __le32 done_marker; -}; - -enum Rx_ring_state_bits { - RrNoMem=1, RrPostponed=2, RrNoResources=4, RrOOMReported=8, -}; - -/* Do not change the position (alignment) of the first few elements! - The later elements are grouped for cache locality. - - Unfortunately, all the positions have been shifted since there. - A new re-alignment is required. 2000/03/06 SAW */ -struct speedo_private { - void __iomem *regs; - struct TxFD *tx_ring; /* Commands (usually CmdTxPacket). */ - struct RxFD *rx_ringp[RX_RING_SIZE]; /* Rx descriptor, used as ring. */ - /* The addresses of a Tx/Rx-in-place packets/buffers. */ - struct sk_buff *tx_skbuff[TX_RING_SIZE]; - struct sk_buff *rx_skbuff[RX_RING_SIZE]; - /* Mapped addresses of the rings. */ - dma_addr_t tx_ring_dma; -#define TX_RING_ELEM_DMA(sp, n) ((sp)->tx_ring_dma + (n)*sizeof(struct TxFD)) - dma_addr_t rx_ring_dma[RX_RING_SIZE]; - struct descriptor *last_cmd; /* Last command sent. */ - unsigned int cur_tx, dirty_tx; /* The ring entries to be free()ed. */ - spinlock_t lock; /* Group with Tx control cache line. */ - u32 tx_threshold; /* The value for txdesc.count. */ - struct RxFD *last_rxf; /* Last filled RX buffer. */ - dma_addr_t last_rxf_dma; - unsigned int cur_rx, dirty_rx; /* The next free ring entry */ - long last_rx_time; /* Last Rx, in jiffies, to handle Rx hang. */ - struct net_device_stats stats; - struct speedo_stats *lstats; - dma_addr_t lstats_dma; - int chip_id; - struct pci_dev *pdev; - struct timer_list timer; /* Media selection timer. */ - struct speedo_mc_block *mc_setup_head; /* Multicast setup frame list head. */ - struct speedo_mc_block *mc_setup_tail; /* Multicast setup frame list tail. */ - long in_interrupt; /* Word-aligned dev->interrupt */ - unsigned char acpi_pwr; - signed char rx_mode; /* Current PROMISC/ALLMULTI setting. */ - unsigned int tx_full:1; /* The Tx queue is full. */ - unsigned int flow_ctrl:1; /* Use 802.3x flow control. */ - unsigned int rx_bug:1; /* Work around receiver hang errata. */ - unsigned char default_port:8; /* Last dev->if_port value. */ - unsigned char rx_ring_state; /* RX ring status flags. */ - unsigned short phy[2]; /* PHY media interfaces available. */ - unsigned short partner; /* Link partner caps. */ - struct mii_if_info mii_if; /* MII API hooks, info */ - u32 msg_enable; /* debug message level */ -}; - -/* The parameters for a CmdConfigure operation. - There are so many options that it would be difficult to document each bit. - We mostly use the default or recommended settings. */ -static const char i82557_config_cmd[CONFIG_DATA_SIZE] = { - 22, 0x08, 0, 0, 0, 0, 0x32, 0x03, 1, /* 1=Use MII 0=Use AUI */ - 0, 0x2E, 0, 0x60, 0, - 0xf2, 0x48, 0, 0x40, 0xf2, 0x80, /* 0x40=Force full-duplex */ - 0x3f, 0x05, }; -static const char i82558_config_cmd[CONFIG_DATA_SIZE] = { - 22, 0x08, 0, 1, 0, 0, 0x22, 0x03, 1, /* 1=Use MII 0=Use AUI */ - 0, 0x2E, 0, 0x60, 0x08, 0x88, - 0x68, 0, 0x40, 0xf2, 0x84, /* Disable FC */ - 0x31, 0x05, }; - -/* PHY media interface chips. */ -static const char * const phys[] = { - "None", "i82553-A/B", "i82553-C", "i82503", - "DP83840", "80c240", "80c24", "i82555", - "unknown-8", "unknown-9", "DP83840A", "unknown-11", - "unknown-12", "unknown-13", "unknown-14", "unknown-15", }; -enum phy_chips { NonSuchPhy=0, I82553AB, I82553C, I82503, DP83840, S80C240, - S80C24, I82555, DP83840A=10, }; -static const char is_mii[] = { 0, 1, 1, 0, 1, 1, 0, 1 }; -#define EE_READ_CMD (6) - -static int eepro100_init_one(struct pci_dev *pdev, - const struct pci_device_id *ent); - -static int do_eeprom_cmd(void __iomem *ioaddr, int cmd, int cmd_len); -static int mdio_read(struct net_device *dev, int phy_id, int location); -static void mdio_write(struct net_device *dev, int phy_id, int location, int value); -static int speedo_open(struct net_device *dev); -static void speedo_resume(struct net_device *dev); -static void speedo_timer(unsigned long data); -static void speedo_init_rx_ring(struct net_device *dev); -static void speedo_tx_timeout(struct net_device *dev); -static int speedo_start_xmit(struct sk_buff *skb, struct net_device *dev); -static void speedo_refill_rx_buffers(struct net_device *dev, int force); -static int speedo_rx(struct net_device *dev); -static void speedo_tx_buffer_gc(struct net_device *dev); -static irqreturn_t speedo_interrupt(int irq, void *dev_instance); -static int speedo_close(struct net_device *dev); -static struct net_device_stats *speedo_get_stats(struct net_device *dev); -static int speedo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); -static void set_rx_mode(struct net_device *dev); -static void speedo_show_state(struct net_device *dev); -static const struct ethtool_ops ethtool_ops; - - - -#ifdef honor_default_port -/* Optional driver feature to allow forcing the transceiver setting. - Not recommended. */ -static int mii_ctrl[8] = { 0x3300, 0x3100, 0x0000, 0x0100, - 0x2000, 0x2100, 0x0400, 0x3100}; -#endif - -/* How to wait for the command unit to accept a command. - Typically this takes 0 ticks. */ -static inline unsigned char wait_for_cmd_done(struct net_device *dev, - struct speedo_private *sp) -{ - int wait = 1000; - void __iomem *cmd_ioaddr = sp->regs + SCBCmd; - unsigned char r; - - do { - udelay(1); - r = ioread8(cmd_ioaddr); - } while(r && --wait >= 0); - - if (wait < 0) - printk(KERN_ALERT "%s: wait_for_cmd_done timeout!\n", dev->name); - return r; -} - -static int __devinit eepro100_init_one (struct pci_dev *pdev, - const struct pci_device_id *ent) -{ - void __iomem *ioaddr; - int irq, pci_bar; - int acpi_idle_state = 0, pm; - static int cards_found /* = 0 */; - unsigned long pci_base; - -#ifndef MODULE - /* when built-in, we only print version if device is found */ - static int did_version; - if (did_version++ == 0) - printk(version); -#endif - - /* save power state before pci_enable_device overwrites it */ - pm = pci_find_capability(pdev, PCI_CAP_ID_PM); - if (pm) { - u16 pwr_command; - pci_read_config_word(pdev, pm + PCI_PM_CTRL, &pwr_command); - acpi_idle_state = pwr_command & PCI_PM_CTRL_STATE_MASK; - } - - if (pci_enable_device(pdev)) - goto err_out_free_mmio_region; - - pci_set_master(pdev); - - if (!request_region(pci_resource_start(pdev, 1), - pci_resource_len(pdev, 1), "eepro100")) { - dev_err(&pdev->dev, "eepro100: cannot reserve I/O ports\n"); - goto err_out_none; - } - if (!request_mem_region(pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0), "eepro100")) { - dev_err(&pdev->dev, "eepro100: cannot reserve MMIO region\n"); - goto err_out_free_pio_region; - } - - irq = pdev->irq; - pci_bar = use_io ? 1 : 0; - pci_base = pci_resource_start(pdev, pci_bar); - if (DEBUG & NETIF_MSG_PROBE) - printk("Found Intel i82557 PCI Speedo at %#lx, IRQ %d.\n", - pci_base, irq); - - ioaddr = pci_iomap(pdev, pci_bar, 0); - if (!ioaddr) { - dev_err(&pdev->dev, "eepro100: cannot remap IO\n"); - goto err_out_free_mmio_region; - } - - if (speedo_found1(pdev, ioaddr, cards_found, acpi_idle_state) == 0) - cards_found++; - else - goto err_out_iounmap; - - return 0; - -err_out_iounmap: ; - pci_iounmap(pdev, ioaddr); -err_out_free_mmio_region: - release_mem_region(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); -err_out_free_pio_region: - release_region(pci_resource_start(pdev, 1), pci_resource_len(pdev, 1)); -err_out_none: - return -ENODEV; -} - -#ifdef CONFIG_NET_POLL_CONTROLLER -/* - * Polling 'interrupt' - used by things like netconsole to send skbs - * without having to re-enable interrupts. It's not called while - * the interrupt routine is executing. - */ - -static void poll_speedo (struct net_device *dev) -{ - /* disable_irq is not very nice, but with the funny lockless design - we have no other choice. */ - disable_irq(dev->irq); - speedo_interrupt (dev->irq, dev); - enable_irq(dev->irq); -} -#endif - -static int __devinit speedo_found1(struct pci_dev *pdev, - void __iomem *ioaddr, int card_idx, int acpi_idle_state) -{ - struct net_device *dev; - struct speedo_private *sp; - const char *product; - int i, option; - u16 eeprom[0x100]; - int size; - void *tx_ring_space; - dma_addr_t tx_ring_dma; - - size = TX_RING_SIZE * sizeof(struct TxFD) + sizeof(struct speedo_stats); - tx_ring_space = pci_alloc_consistent(pdev, size, &tx_ring_dma); - if (tx_ring_space == NULL) - return -1; - - dev = alloc_etherdev(sizeof(struct speedo_private)); - if (dev == NULL) { - printk(KERN_ERR "eepro100: Could not allocate ethernet device.\n"); - pci_free_consistent(pdev, size, tx_ring_space, tx_ring_dma); - return -1; - } - - SET_NETDEV_DEV(dev, &pdev->dev); - - if (dev->mem_start > 0) - option = dev->mem_start; - else if (card_idx >= 0 && options[card_idx] >= 0) - option = options[card_idx]; - else - option = 0; - - rtnl_lock(); - if (dev_alloc_name(dev, dev->name) < 0) - goto err_free_unlock; - - /* Read the station address EEPROM before doing the reset. - Nominally his should even be done before accepting the device, but - then we wouldn't have a device name with which to report the error. - The size test is for 6 bit vs. 8 bit address serial EEPROMs. - */ - { - void __iomem *iobase; - int read_cmd, ee_size; - u16 sum; - int j; - - /* Use IO only to avoid postponed writes and satisfy EEPROM timing - requirements. */ - iobase = pci_iomap(pdev, 1, pci_resource_len(pdev, 1)); - if (!iobase) - goto err_free_unlock; - if ((do_eeprom_cmd(iobase, EE_READ_CMD << 24, 27) & 0xffe0000) - == 0xffe0000) { - ee_size = 0x100; - read_cmd = EE_READ_CMD << 24; - } else { - ee_size = 0x40; - read_cmd = EE_READ_CMD << 22; - } - - for (j = 0, i = 0, sum = 0; i < ee_size; i++) { - u16 value = do_eeprom_cmd(iobase, read_cmd | (i << 16), 27); - eeprom[i] = value; - sum += value; - if (i < 3) { - dev->dev_addr[j++] = value; - dev->dev_addr[j++] = value >> 8; - } - } - if (sum != 0xBABA) - printk(KERN_WARNING "%s: Invalid EEPROM checksum %#4.4x, " - "check settings before activating this device!\n", - dev->name, sum); - /* Don't unregister_netdev(dev); as the EEPro may actually be - usable, especially if the MAC address is set later. - On the other hand, it may be unusable if MDI data is corrupted. */ - - pci_iounmap(pdev, iobase); - } - - /* Reset the chip: stop Tx and Rx processes and clear counters. - This takes less than 10usec and will easily finish before the next - action. */ - iowrite32(PortReset, ioaddr + SCBPort); - ioread32(ioaddr + SCBPort); - udelay(10); - - if (eeprom[3] & 0x0100) - product = "OEM i82557/i82558 10/100 Ethernet"; - else - product = pci_name(pdev); - - printk(KERN_INFO "%s: %s, %pM, IRQ %d.\n", dev->name, product, - dev->dev_addr, pdev->irq); - - sp = netdev_priv(dev); - - /* we must initialize this early, for mdio_{read,write} */ - sp->regs = ioaddr; - -#if 1 || defined(kernel_bloat) - /* OK, this is pure kernel bloat. I don't like it when other drivers - waste non-pageable kernel space to emit similar messages, but I need - them for bug reports. */ - { - const char *connectors[] = {" RJ45", " BNC", " AUI", " MII"}; - /* The self-test results must be paragraph aligned. */ - volatile s32 *self_test_results; - int boguscnt = 16000; /* Timeout for set-test. */ - if ((eeprom[3] & 0x03) != 0x03) - printk(KERN_INFO " Receiver lock-up bug exists -- enabling" - " work-around.\n"); - printk(KERN_INFO " Board assembly %4.4x%2.2x-%3.3d, Physical" - " connectors present:", - eeprom[8], eeprom[9]>>8, eeprom[9] & 0xff); - for (i = 0; i < 4; i++) - if (eeprom[5] & (1<>8)&15], eeprom[6] & 0x1f); - if (eeprom[7] & 0x0700) - printk(KERN_INFO " Secondary interface chip %s.\n", - phys[(eeprom[7]>>8)&7]); - if (((eeprom[6]>>8) & 0x3f) == DP83840 - || ((eeprom[6]>>8) & 0x3f) == DP83840A) { - int mdi_reg23 = mdio_read(dev, eeprom[6] & 0x1f, 23) | 0x0422; - if (congenb) - mdi_reg23 |= 0x0100; - printk(KERN_INFO" DP83840 specific setup, setting register 23 to %4.4x.\n", - mdi_reg23); - mdio_write(dev, eeprom[6] & 0x1f, 23, mdi_reg23); - } - if ((option >= 0) && (option & 0x70)) { - printk(KERN_INFO " Forcing %dMbs %s-duplex operation.\n", - (option & 0x20 ? 100 : 10), - (option & 0x10 ? "full" : "half")); - mdio_write(dev, eeprom[6] & 0x1f, MII_BMCR, - ((option & 0x20) ? 0x2000 : 0) | /* 100mbps? */ - ((option & 0x10) ? 0x0100 : 0)); /* Full duplex? */ - } - - /* Perform a system self-test. */ - self_test_results = (s32*) ((((long) tx_ring_space) + 15) & ~0xf); - self_test_results[0] = 0; - self_test_results[1] = -1; - iowrite32(tx_ring_dma | PortSelfTest, ioaddr + SCBPort); - do { - udelay(10); - } while (self_test_results[1] == -1 && --boguscnt >= 0); - - if (boguscnt < 0) { /* Test optimized out. */ - printk(KERN_ERR "Self test failed, status %8.8x:\n" - KERN_ERR " Failure to initialize the i82557.\n" - KERN_ERR " Verify that the card is a bus-master" - " capable slot.\n", - self_test_results[1]); - } else - printk(KERN_INFO " General self-test: %s.\n" - KERN_INFO " Serial sub-system self-test: %s.\n" - KERN_INFO " Internal registers self-test: %s.\n" - KERN_INFO " ROM checksum self-test: %s (%#8.8x).\n", - self_test_results[1] & 0x1000 ? "failed" : "passed", - self_test_results[1] & 0x0020 ? "failed" : "passed", - self_test_results[1] & 0x0008 ? "failed" : "passed", - self_test_results[1] & 0x0004 ? "failed" : "passed", - self_test_results[0]); - } -#endif /* kernel_bloat */ - - iowrite32(PortReset, ioaddr + SCBPort); - ioread32(ioaddr + SCBPort); - udelay(10); - - /* Return the chip to its original power state. */ - pci_set_power_state(pdev, acpi_idle_state); - - pci_set_drvdata (pdev, dev); - SET_NETDEV_DEV(dev, &pdev->dev); - - dev->irq = pdev->irq; - - sp->pdev = pdev; - sp->msg_enable = DEBUG; - sp->acpi_pwr = acpi_idle_state; - sp->tx_ring = tx_ring_space; - sp->tx_ring_dma = tx_ring_dma; - sp->lstats = (struct speedo_stats *)(sp->tx_ring + TX_RING_SIZE); - sp->lstats_dma = TX_RING_ELEM_DMA(sp, TX_RING_SIZE); - init_timer(&sp->timer); /* used in ioctl() */ - spin_lock_init(&sp->lock); - - sp->mii_if.full_duplex = option >= 0 && (option & 0x10) ? 1 : 0; - if (card_idx >= 0) { - if (full_duplex[card_idx] >= 0) - sp->mii_if.full_duplex = full_duplex[card_idx]; - } - sp->default_port = option >= 0 ? (option & 0x0f) : 0; - - sp->phy[0] = eeprom[6]; - sp->phy[1] = eeprom[7]; - - sp->mii_if.phy_id = eeprom[6] & 0x1f; - sp->mii_if.phy_id_mask = 0x1f; - sp->mii_if.reg_num_mask = 0x1f; - sp->mii_if.dev = dev; - sp->mii_if.mdio_read = mdio_read; - sp->mii_if.mdio_write = mdio_write; - - sp->rx_bug = (eeprom[3] & 0x03) == 3 ? 0 : 1; - if (((pdev->device > 0x1030 && (pdev->device < 0x103F))) - || (pdev->device == 0x2449) || (pdev->device == 0x2459) - || (pdev->device == 0x245D)) { - sp->chip_id = 1; - } - - if (sp->rx_bug) - printk(KERN_INFO " Receiver lock-up workaround activated.\n"); - - /* The Speedo-specific entries in the device structure. */ - dev->open = &speedo_open; - dev->hard_start_xmit = &speedo_start_xmit; - netif_set_tx_timeout(dev, &speedo_tx_timeout, TX_TIMEOUT); - dev->stop = &speedo_close; - dev->get_stats = &speedo_get_stats; - dev->set_multicast_list = &set_rx_mode; - dev->do_ioctl = &speedo_ioctl; - SET_ETHTOOL_OPS(dev, ðtool_ops); -#ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = &poll_speedo; -#endif - - if (register_netdevice(dev)) - goto err_free_unlock; - rtnl_unlock(); - - return 0; - - err_free_unlock: - rtnl_unlock(); - free_netdev(dev); - return -1; -} - -static void do_slow_command(struct net_device *dev, struct speedo_private *sp, int cmd) -{ - void __iomem *cmd_ioaddr = sp->regs + SCBCmd; - int wait = 0; - do - if (ioread8(cmd_ioaddr) == 0) break; - while(++wait <= 200); - if (wait > 100) - printk(KERN_ERR "Command %4.4x never accepted (%d polls)!\n", - ioread8(cmd_ioaddr), wait); - - iowrite8(cmd, cmd_ioaddr); - - for (wait = 0; wait <= 100; wait++) - if (ioread8(cmd_ioaddr) == 0) return; - for (; wait <= 20000; wait++) - if (ioread8(cmd_ioaddr) == 0) return; - else udelay(1); - printk(KERN_ERR "Command %4.4x was not accepted after %d polls!" - " Current status %8.8x.\n", - cmd, wait, ioread32(sp->regs + SCBStatus)); -} - -/* Serial EEPROM section. - A "bit" grungy, but we work our way through bit-by-bit :->. */ -/* EEPROM_Ctrl bits. */ -#define EE_SHIFT_CLK 0x01 /* EEPROM shift clock. */ -#define EE_CS 0x02 /* EEPROM chip select. */ -#define EE_DATA_WRITE 0x04 /* EEPROM chip data in. */ -#define EE_DATA_READ 0x08 /* EEPROM chip data out. */ -#define EE_ENB (0x4800 | EE_CS) -#define EE_WRITE_0 0x4802 -#define EE_WRITE_1 0x4806 -#define EE_OFFSET SCBeeprom - -/* The fixes for the code were kindly provided by Dragan Stancevic - to strictly follow Intel specifications of EEPROM - access timing. - The publicly available sheet 64486302 (sec. 3.1) specifies 1us access - interval for serial EEPROM. However, it looks like that there is an - additional requirement dictating larger udelay's in the code below. - 2000/05/24 SAW */ -static int __devinit do_eeprom_cmd(void __iomem *ioaddr, int cmd, int cmd_len) -{ - unsigned retval = 0; - void __iomem *ee_addr = ioaddr + SCBeeprom; - - iowrite16(EE_ENB, ee_addr); udelay(2); - iowrite16(EE_ENB | EE_SHIFT_CLK, ee_addr); udelay(2); - - /* Shift the command bits out. */ - do { - short dataval = (cmd & (1 << cmd_len)) ? EE_WRITE_1 : EE_WRITE_0; - iowrite16(dataval, ee_addr); udelay(2); - iowrite16(dataval | EE_SHIFT_CLK, ee_addr); udelay(2); - retval = (retval << 1) | ((ioread16(ee_addr) & EE_DATA_READ) ? 1 : 0); - } while (--cmd_len >= 0); - iowrite16(EE_ENB, ee_addr); udelay(2); - - /* Terminate the EEPROM access. */ - iowrite16(EE_ENB & ~EE_CS, ee_addr); - return retval; -} - -static int mdio_read(struct net_device *dev, int phy_id, int location) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int val, boguscnt = 64*10; /* <64 usec. to complete, typ 27 ticks */ - iowrite32(0x08000000 | (location<<16) | (phy_id<<21), ioaddr + SCBCtrlMDI); - do { - val = ioread32(ioaddr + SCBCtrlMDI); - if (--boguscnt < 0) { - printk(KERN_ERR " mdio_read() timed out with val = %8.8x.\n", val); - break; - } - } while (! (val & 0x10000000)); - return val & 0xffff; -} - -static void mdio_write(struct net_device *dev, int phy_id, int location, int value) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int val, boguscnt = 64*10; /* <64 usec. to complete, typ 27 ticks */ - iowrite32(0x04000000 | (location<<16) | (phy_id<<21) | value, - ioaddr + SCBCtrlMDI); - do { - val = ioread32(ioaddr + SCBCtrlMDI); - if (--boguscnt < 0) { - printk(KERN_ERR" mdio_write() timed out with val = %8.8x.\n", val); - break; - } - } while (! (val & 0x10000000)); -} - -static int -speedo_open(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int retval; - - if (netif_msg_ifup(sp)) - printk(KERN_DEBUG "%s: speedo_open() irq %d.\n", dev->name, dev->irq); - - pci_set_power_state(sp->pdev, PCI_D0); - - /* Set up the Tx queue early.. */ - sp->cur_tx = 0; - sp->dirty_tx = 0; - sp->last_cmd = NULL; - sp->tx_full = 0; - sp->in_interrupt = 0; - - /* .. we can safely take handler calls during init. */ - retval = request_irq(dev->irq, &speedo_interrupt, IRQF_SHARED, dev->name, dev); - if (retval) { - return retval; - } - - dev->if_port = sp->default_port; - -#ifdef oh_no_you_dont_unless_you_honour_the_options_passed_in_to_us - /* Retrigger negotiation to reset previous errors. */ - if ((sp->phy[0] & 0x8000) == 0) { - int phy_addr = sp->phy[0] & 0x1f ; - /* Use 0x3300 for restarting NWay, other values to force xcvr: - 0x0000 10-HD - 0x0100 10-FD - 0x2000 100-HD - 0x2100 100-FD - */ -#ifdef honor_default_port - mdio_write(dev, phy_addr, MII_BMCR, mii_ctrl[dev->default_port & 7]); -#else - mdio_write(dev, phy_addr, MII_BMCR, 0x3300); -#endif - } -#endif - - speedo_init_rx_ring(dev); - - /* Fire up the hardware. */ - iowrite16(SCBMaskAll, ioaddr + SCBCmd); - speedo_resume(dev); - - netdevice_start(dev); - netif_start_queue(dev); - - /* Setup the chip and configure the multicast list. */ - sp->mc_setup_head = NULL; - sp->mc_setup_tail = NULL; - sp->flow_ctrl = sp->partner = 0; - sp->rx_mode = -1; /* Invalid -> always reset the mode. */ - set_rx_mode(dev); - if ((sp->phy[0] & 0x8000) == 0) - sp->mii_if.advertising = mdio_read(dev, sp->phy[0] & 0x1f, MII_ADVERTISE); - - mii_check_link(&sp->mii_if); - - if (netif_msg_ifup(sp)) { - printk(KERN_DEBUG "%s: Done speedo_open(), status %8.8x.\n", - dev->name, ioread16(ioaddr + SCBStatus)); - } - - /* Set the timer. The timer serves a dual purpose: - 1) to monitor the media interface (e.g. link beat) and perhaps switch - to an alternate media type - 2) to monitor Rx activity, and restart the Rx process if the receiver - hangs. */ - sp->timer.expires = RUN_AT((24*HZ)/10); /* 2.4 sec. */ - sp->timer.data = (unsigned long)dev; - sp->timer.function = &speedo_timer; /* timer handler */ - add_timer(&sp->timer); - - /* No need to wait for the command unit to accept here. */ - if ((sp->phy[0] & 0x8000) == 0) - mdio_read(dev, sp->phy[0] & 0x1f, MII_BMCR); - - return 0; -} - -/* Start the chip hardware after a full reset. */ -static void speedo_resume(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - - /* Start with a Tx threshold of 256 (0x..20.... 8 byte units). */ - sp->tx_threshold = 0x01208000; - - /* Set the segment registers to '0'. */ - if (wait_for_cmd_done(dev, sp) != 0) { - iowrite32(PortPartialReset, ioaddr + SCBPort); - udelay(10); - } - - iowrite32(0, ioaddr + SCBPointer); - ioread32(ioaddr + SCBPointer); /* Flush to PCI. */ - udelay(10); /* Bogus, but it avoids the bug. */ - - /* Note: these next two operations can take a while. */ - do_slow_command(dev, sp, RxAddrLoad); - do_slow_command(dev, sp, CUCmdBase); - - /* Load the statistics block and rx ring addresses. */ - iowrite32(sp->lstats_dma, ioaddr + SCBPointer); - ioread32(ioaddr + SCBPointer); /* Flush to PCI */ - - iowrite8(CUStatsAddr, ioaddr + SCBCmd); - sp->lstats->done_marker = 0; - wait_for_cmd_done(dev, sp); - - if (sp->rx_ringp[sp->cur_rx % RX_RING_SIZE] == NULL) { - if (netif_msg_rx_err(sp)) - printk(KERN_DEBUG "%s: NULL cur_rx in speedo_resume().\n", - dev->name); - } else { - iowrite32(sp->rx_ring_dma[sp->cur_rx % RX_RING_SIZE], - ioaddr + SCBPointer); - ioread32(ioaddr + SCBPointer); /* Flush to PCI */ - } - - /* Note: RxStart should complete instantly. */ - do_slow_command(dev, sp, RxStart); - do_slow_command(dev, sp, CUDumpStats); - - /* Fill the first command with our physical address. */ - { - struct descriptor *ias_cmd; - - ias_cmd = - (struct descriptor *)&sp->tx_ring[sp->cur_tx++ % TX_RING_SIZE]; - /* Avoid a bug(?!) here by marking the command already completed. */ - ias_cmd->cmd_status = cpu_to_le32((CmdSuspend | CmdIASetup) | 0xa000); - ias_cmd->link = - cpu_to_le32(TX_RING_ELEM_DMA(sp, sp->cur_tx % TX_RING_SIZE)); - memcpy(ias_cmd->params, dev->dev_addr, 6); - if (sp->last_cmd) - clear_suspend(sp->last_cmd); - sp->last_cmd = ias_cmd; - } - - /* Start the chip's Tx process and unmask interrupts. */ - iowrite32(TX_RING_ELEM_DMA(sp, sp->dirty_tx % TX_RING_SIZE), - ioaddr + SCBPointer); - /* We are not ACK-ing FCP and ER in the interrupt handler yet so they should - remain masked --Dragan */ - iowrite16(CUStart | SCBMaskEarlyRx | SCBMaskFlowCtl, ioaddr + SCBCmd); -} - -/* - * Sometimes the receiver stops making progress. This routine knows how to - * get it going again, without losing packets or being otherwise nasty like - * a chip reset would be. Previously the driver had a whole sequence - * of if RxSuspended, if it's no buffers do one thing, if it's no resources, - * do another, etc. But those things don't really matter. Separate logic - * in the ISR provides for allocating buffers--the other half of operation - * is just making sure the receiver is active. speedo_rx_soft_reset does that. - * This problem with the old, more involved algorithm is shown up under - * ping floods on the order of 60K packets/second on a 100Mbps fdx network. - */ -static void -speedo_rx_soft_reset(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - struct RxFD *rfd; - void __iomem *ioaddr; - - ioaddr = sp->regs; - if (wait_for_cmd_done(dev, sp) != 0) { - printk("%s: previous command stalled\n", dev->name); - return; - } - /* - * Put the hardware into a known state. - */ - iowrite8(RxAbort, ioaddr + SCBCmd); - - rfd = sp->rx_ringp[sp->cur_rx % RX_RING_SIZE]; - - rfd->rx_buf_addr = cpu_to_le32(0xffffffff); - - if (wait_for_cmd_done(dev, sp) != 0) { - printk("%s: RxAbort command stalled\n", dev->name); - return; - } - iowrite32(sp->rx_ring_dma[sp->cur_rx % RX_RING_SIZE], - ioaddr + SCBPointer); - iowrite8(RxStart, ioaddr + SCBCmd); -} - - -/* Media monitoring and control. */ -static void speedo_timer(unsigned long data) -{ - struct net_device *dev = (struct net_device *)data; - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int phy_num = sp->phy[0] & 0x1f; - - /* We have MII and lost link beat. */ - if ((sp->phy[0] & 0x8000) == 0) { - int partner = mdio_read(dev, phy_num, MII_LPA); - if (partner != sp->partner) { - int flow_ctrl = sp->mii_if.advertising & partner & 0x0400 ? 1 : 0; - if (netif_msg_link(sp)) { - printk(KERN_DEBUG "%s: Link status change.\n", dev->name); - printk(KERN_DEBUG "%s: Old partner %x, new %x, adv %x.\n", - dev->name, sp->partner, partner, sp->mii_if.advertising); - } - sp->partner = partner; - if (flow_ctrl != sp->flow_ctrl) { - sp->flow_ctrl = flow_ctrl; - sp->rx_mode = -1; /* Trigger a reload. */ - } - } - } - mii_check_link(&sp->mii_if); - if (netif_msg_timer(sp)) { - printk(KERN_DEBUG "%s: Media control tick, status %4.4x.\n", - dev->name, ioread16(ioaddr + SCBStatus)); - } - if (sp->rx_mode < 0 || - (sp->rx_bug && jiffies - sp->last_rx_time > 2*HZ)) { - /* We haven't received a packet in a Long Time. We might have been - bitten by the receiver hang bug. This can be cleared by sending - a set multicast list command. */ - if (netif_msg_timer(sp)) - printk(KERN_DEBUG "%s: Sending a multicast list set command" - " from a timer routine," - " m=%d, j=%ld, l=%ld.\n", - dev->name, sp->rx_mode, jiffies, sp->last_rx_time); - set_rx_mode(dev); - } - /* We must continue to monitor the media. */ - sp->timer.expires = RUN_AT(2*HZ); /* 2.0 sec. */ - add_timer(&sp->timer); -} - -static void speedo_show_state(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - int i; - - if (netif_msg_pktdata(sp)) { - printk(KERN_DEBUG "%s: Tx ring dump, Tx queue %u / %u:\n", - dev->name, sp->cur_tx, sp->dirty_tx); - for (i = 0; i < TX_RING_SIZE; i++) - printk(KERN_DEBUG "%s: %c%c%2d %8.8x.\n", dev->name, - i == sp->dirty_tx % TX_RING_SIZE ? '*' : ' ', - i == sp->cur_tx % TX_RING_SIZE ? '=' : ' ', - i, sp->tx_ring[i].status); - - printk(KERN_DEBUG "%s: Printing Rx ring" - " (next to receive into %u, dirty index %u).\n", - dev->name, sp->cur_rx, sp->dirty_rx); - for (i = 0; i < RX_RING_SIZE; i++) - printk(KERN_DEBUG "%s: %c%c%c%2d %8.8x.\n", dev->name, - sp->rx_ringp[i] == sp->last_rxf ? 'l' : ' ', - i == sp->dirty_rx % RX_RING_SIZE ? '*' : ' ', - i == sp->cur_rx % RX_RING_SIZE ? '=' : ' ', - i, (sp->rx_ringp[i] != NULL) ? - (unsigned)sp->rx_ringp[i]->status : 0); - } - -#if 0 - { - void __iomem *ioaddr = sp->regs; - int phy_num = sp->phy[0] & 0x1f; - for (i = 0; i < 16; i++) { - /* FIXME: what does it mean? --SAW */ - if (i == 6) i = 21; - printk(KERN_DEBUG "%s: PHY index %d register %d is %4.4x.\n", - dev->name, phy_num, i, mdio_read(dev, phy_num, i)); - } - } -#endif - -} - -/* Initialize the Rx and Tx rings, along with various 'dev' bits. */ -static void -speedo_init_rx_ring(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - struct RxFD *rxf, *last_rxf = NULL; - dma_addr_t last_rxf_dma = 0 /* to shut up the compiler */; - int i; - - sp->cur_rx = 0; - - for (i = 0; i < RX_RING_SIZE; i++) { - struct sk_buff *skb; - skb = dev_alloc_skb(PKT_BUF_SZ + sizeof(struct RxFD)); - if (skb) - rx_align(skb); /* Align IP on 16 byte boundary */ - sp->rx_skbuff[i] = skb; - if (skb == NULL) - break; /* OK. Just initially short of Rx bufs. */ - skb->dev = dev; /* Mark as being used by this device. */ - rxf = (struct RxFD *)skb->data; - sp->rx_ringp[i] = rxf; - sp->rx_ring_dma[i] = - pci_map_single(sp->pdev, rxf, - PKT_BUF_SZ + sizeof(struct RxFD), PCI_DMA_BIDIRECTIONAL); - skb_reserve(skb, sizeof(struct RxFD)); - if (last_rxf) { - last_rxf->link = cpu_to_le32(sp->rx_ring_dma[i]); - pci_dma_sync_single_for_device(sp->pdev, last_rxf_dma, - sizeof(struct RxFD), PCI_DMA_TODEVICE); - } - last_rxf = rxf; - last_rxf_dma = sp->rx_ring_dma[i]; - rxf->status = cpu_to_le32(0x00000001); /* '1' is flag value only. */ - rxf->link = 0; /* None yet. */ - /* This field unused by i82557. */ - rxf->rx_buf_addr = cpu_to_le32(0xffffffff); - rxf->count = cpu_to_le32(PKT_BUF_SZ << 16); - pci_dma_sync_single_for_device(sp->pdev, sp->rx_ring_dma[i], - sizeof(struct RxFD), PCI_DMA_TODEVICE); - } - sp->dirty_rx = (unsigned int)(i - RX_RING_SIZE); - /* Mark the last entry as end-of-list. */ - last_rxf->status = cpu_to_le32(0xC0000002); /* '2' is flag value only. */ - pci_dma_sync_single_for_device(sp->pdev, sp->rx_ring_dma[RX_RING_SIZE-1], - sizeof(struct RxFD), PCI_DMA_TODEVICE); - sp->last_rxf = last_rxf; - sp->last_rxf_dma = last_rxf_dma; -} - -static void speedo_purge_tx(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - int entry; - - while ((int)(sp->cur_tx - sp->dirty_tx) > 0) { - entry = sp->dirty_tx % TX_RING_SIZE; - if (sp->tx_skbuff[entry]) { - sp->stats.tx_errors++; - pci_unmap_single(sp->pdev, - le32_to_cpu(sp->tx_ring[entry].tx_buf_addr0), - sp->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(sp->tx_skbuff[entry]); - sp->tx_skbuff[entry] = NULL; - } - sp->dirty_tx++; - } - while (sp->mc_setup_head != NULL) { - struct speedo_mc_block *t; - if (netif_msg_tx_err(sp)) - printk(KERN_DEBUG "%s: freeing mc frame.\n", dev->name); - pci_unmap_single(sp->pdev, sp->mc_setup_head->frame_dma, - sp->mc_setup_head->len, PCI_DMA_TODEVICE); - t = sp->mc_setup_head->next; - kfree(sp->mc_setup_head); - sp->mc_setup_head = t; - } - sp->mc_setup_tail = NULL; - sp->tx_full = 0; - netif_wake_queue(dev); -} - -static void reset_mii(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - - /* Reset the MII transceiver, suggested by Fred Young @ scalable.com. */ - if ((sp->phy[0] & 0x8000) == 0) { - int phy_addr = sp->phy[0] & 0x1f; - int advertising = mdio_read(dev, phy_addr, MII_ADVERTISE); - int mii_bmcr = mdio_read(dev, phy_addr, MII_BMCR); - mdio_write(dev, phy_addr, MII_BMCR, 0x0400); - mdio_write(dev, phy_addr, MII_BMSR, 0x0000); - mdio_write(dev, phy_addr, MII_ADVERTISE, 0x0000); - mdio_write(dev, phy_addr, MII_BMCR, 0x8000); -#ifdef honor_default_port - mdio_write(dev, phy_addr, MII_BMCR, mii_ctrl[dev->default_port & 7]); -#else - mdio_read(dev, phy_addr, MII_BMCR); - mdio_write(dev, phy_addr, MII_BMCR, mii_bmcr); - mdio_write(dev, phy_addr, MII_ADVERTISE, advertising); -#endif - } -} - -static void speedo_tx_timeout(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int status = ioread16(ioaddr + SCBStatus); - unsigned long flags; - - if (netif_msg_tx_err(sp)) { - printk(KERN_WARNING "%s: Transmit timed out: status %4.4x " - " %4.4x at %d/%d command %8.8x.\n", - dev->name, status, ioread16(ioaddr + SCBCmd), - sp->dirty_tx, sp->cur_tx, - sp->tx_ring[sp->dirty_tx % TX_RING_SIZE].status); - - } - speedo_show_state(dev); -#if 0 - if ((status & 0x00C0) != 0x0080 - && (status & 0x003C) == 0x0010) { - /* Only the command unit has stopped. */ - printk(KERN_WARNING "%s: Trying to restart the transmitter...\n", - dev->name); - iowrite32(TX_RING_ELEM_DMA(sp, dirty_tx % TX_RING_SIZE]), - ioaddr + SCBPointer); - iowrite16(CUStart, ioaddr + SCBCmd); - reset_mii(dev); - } else { -#else - { -#endif - del_timer_sync(&sp->timer); - /* Reset the Tx and Rx units. */ - iowrite32(PortReset, ioaddr + SCBPort); - /* We may get spurious interrupts here. But I don't think that they - may do much harm. 1999/12/09 SAW */ - udelay(10); - /* Disable interrupts. */ - iowrite16(SCBMaskAll, ioaddr + SCBCmd); - synchronize_irq(dev->irq); - speedo_tx_buffer_gc(dev); - /* Free as much as possible. - It helps to recover from a hang because of out-of-memory. - It also simplifies speedo_resume() in case TX ring is full or - close-to-be full. */ - speedo_purge_tx(dev); - speedo_refill_rx_buffers(dev, 1); - spin_lock_irqsave(&sp->lock, flags); - speedo_resume(dev); - sp->rx_mode = -1; - dev->trans_start = jiffies; - spin_unlock_irqrestore(&sp->lock, flags); - set_rx_mode(dev); /* it takes the spinlock itself --SAW */ - /* Reset MII transceiver. Do it before starting the timer to serialize - mdio_xxx operations. Yes, it's a paranoya :-) 2000/05/09 SAW */ - reset_mii(dev); - sp->timer.expires = RUN_AT(2*HZ); - add_timer(&sp->timer); - } - return; -} - -static int -speedo_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int entry; - - /* Prevent interrupts from changing the Tx ring from underneath us. */ - unsigned long flags; - - spin_lock_irqsave(&sp->lock, flags); - - /* Check if there are enough space. */ - if ((int)(sp->cur_tx - sp->dirty_tx) >= TX_QUEUE_LIMIT) { - printk(KERN_ERR "%s: incorrect tbusy state, fixed.\n", dev->name); - netif_stop_queue(dev); - sp->tx_full = 1; - spin_unlock_irqrestore(&sp->lock, flags); - return 1; - } - - /* Calculate the Tx descriptor entry. */ - entry = sp->cur_tx++ % TX_RING_SIZE; - - sp->tx_skbuff[entry] = skb; - sp->tx_ring[entry].status = - cpu_to_le32(CmdSuspend | CmdTx | CmdTxFlex); - if (!(entry & ((TX_RING_SIZE>>2)-1))) - sp->tx_ring[entry].status |= cpu_to_le32(CmdIntr); - sp->tx_ring[entry].link = - cpu_to_le32(TX_RING_ELEM_DMA(sp, sp->cur_tx % TX_RING_SIZE)); - sp->tx_ring[entry].tx_desc_addr = - cpu_to_le32(TX_RING_ELEM_DMA(sp, entry) + TX_DESCR_BUF_OFFSET); - /* The data region is always in one buffer descriptor. */ - sp->tx_ring[entry].count = cpu_to_le32(sp->tx_threshold); - sp->tx_ring[entry].tx_buf_addr0 = - cpu_to_le32(pci_map_single(sp->pdev, skb->data, - skb->len, PCI_DMA_TODEVICE)); - sp->tx_ring[entry].tx_buf_size0 = cpu_to_le32(skb->len); - - /* workaround for hardware bug on 10 mbit half duplex */ - - if ((sp->partner == 0) && (sp->chip_id == 1)) { - wait_for_cmd_done(dev, sp); - iowrite8(0 , ioaddr + SCBCmd); - udelay(1); - } - - /* Trigger the command unit resume. */ - wait_for_cmd_done(dev, sp); - clear_suspend(sp->last_cmd); - /* We want the time window between clearing suspend flag on the previous - command and resuming CU to be as small as possible. - Interrupts in between are very undesired. --SAW */ - iowrite8(CUResume, ioaddr + SCBCmd); - sp->last_cmd = (struct descriptor *)&sp->tx_ring[entry]; - - /* Leave room for set_rx_mode(). If there is no more space than reserved - for multicast filter mark the ring as full. */ - if ((int)(sp->cur_tx - sp->dirty_tx) >= TX_QUEUE_LIMIT) { - netif_stop_queue(dev); - sp->tx_full = 1; - } - - spin_unlock_irqrestore(&sp->lock, flags); - - dev->trans_start = jiffies; - - return 0; -} - -static void speedo_tx_buffer_gc(struct net_device *dev) -{ - unsigned int dirty_tx; - struct speedo_private *sp = netdev_priv(dev); - - dirty_tx = sp->dirty_tx; - while ((int)(sp->cur_tx - dirty_tx) > 0) { - int entry = dirty_tx % TX_RING_SIZE; - int status = le32_to_cpu(sp->tx_ring[entry].status); - - if (netif_msg_tx_done(sp)) - printk(KERN_DEBUG " scavenge candidate %d status %4.4x.\n", - entry, status); - if ((status & StatusComplete) == 0) - break; /* It still hasn't been processed. */ - if (status & TxUnderrun) - if (sp->tx_threshold < 0x01e08000) { - if (netif_msg_tx_err(sp)) - printk(KERN_DEBUG "%s: TX underrun, threshold adjusted.\n", - dev->name); - sp->tx_threshold += 0x00040000; - } - /* Free the original skb. */ - if (sp->tx_skbuff[entry]) { - sp->stats.tx_packets++; /* Count only user packets. */ - sp->stats.tx_bytes += sp->tx_skbuff[entry]->len; - pci_unmap_single(sp->pdev, - le32_to_cpu(sp->tx_ring[entry].tx_buf_addr0), - sp->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(sp->tx_skbuff[entry]); - sp->tx_skbuff[entry] = NULL; - } - dirty_tx++; - } - - if (netif_msg_tx_err(sp) && (int)(sp->cur_tx - dirty_tx) > TX_RING_SIZE) { - printk(KERN_ERR "out-of-sync dirty pointer, %d vs. %d," - " full=%d.\n", - dirty_tx, sp->cur_tx, sp->tx_full); - dirty_tx += TX_RING_SIZE; - } - - while (sp->mc_setup_head != NULL - && (int)(dirty_tx - sp->mc_setup_head->tx - 1) > 0) { - struct speedo_mc_block *t; - if (netif_msg_tx_err(sp)) - printk(KERN_DEBUG "%s: freeing mc frame.\n", dev->name); - pci_unmap_single(sp->pdev, sp->mc_setup_head->frame_dma, - sp->mc_setup_head->len, PCI_DMA_TODEVICE); - t = sp->mc_setup_head->next; - kfree(sp->mc_setup_head); - sp->mc_setup_head = t; - } - if (sp->mc_setup_head == NULL) - sp->mc_setup_tail = NULL; - - sp->dirty_tx = dirty_tx; -} - -/* The interrupt handler does all of the Rx thread work and cleans up - after the Tx thread. */ -static irqreturn_t speedo_interrupt(int irq, void *dev_instance) -{ - struct net_device *dev = (struct net_device *)dev_instance; - struct speedo_private *sp; - void __iomem *ioaddr; - long boguscnt = max_interrupt_work; - unsigned short status; - unsigned int handled = 0; - - sp = netdev_priv(dev); - ioaddr = sp->regs; - -#ifndef final_version - /* A lock to prevent simultaneous entry on SMP machines. */ - if (test_and_set_bit(0, (void*)&sp->in_interrupt)) { - printk(KERN_ERR"%s: SMP simultaneous entry of an interrupt handler.\n", - dev->name); - sp->in_interrupt = 0; /* Avoid halting machine. */ - return IRQ_NONE; - } -#endif - - do { - status = ioread16(ioaddr + SCBStatus); - /* Acknowledge all of the current interrupt sources ASAP. */ - /* Will change from 0xfc00 to 0xff00 when we start handling - FCP and ER interrupts --Dragan */ - iowrite16(status & 0xfc00, ioaddr + SCBStatus); - - if (netif_msg_intr(sp)) - printk(KERN_DEBUG "%s: interrupt status=%#4.4x.\n", - dev->name, status); - - if ((status & 0xfc00) == 0) - break; - handled = 1; - - - if ((status & 0x5000) || /* Packet received, or Rx error. */ - (sp->rx_ring_state&(RrNoMem|RrPostponed)) == RrPostponed) - /* Need to gather the postponed packet. */ - speedo_rx(dev); - - /* Always check if all rx buffers are allocated. --SAW */ - speedo_refill_rx_buffers(dev, 0); - - spin_lock(&sp->lock); - /* - * The chip may have suspended reception for various reasons. - * Check for that, and re-prime it should this be the case. - */ - switch ((status >> 2) & 0xf) { - case 0: /* Idle */ - break; - case 1: /* Suspended */ - case 2: /* No resources (RxFDs) */ - case 9: /* Suspended with no more RBDs */ - case 10: /* No resources due to no RBDs */ - case 12: /* Ready with no RBDs */ - speedo_rx_soft_reset(dev); - break; - case 3: case 5: case 6: case 7: case 8: - case 11: case 13: case 14: case 15: - /* these are all reserved values */ - break; - } - - - /* User interrupt, Command/Tx unit interrupt or CU not active. */ - if (status & 0xA400) { - speedo_tx_buffer_gc(dev); - if (sp->tx_full - && (int)(sp->cur_tx - sp->dirty_tx) < TX_QUEUE_UNFULL) { - /* The ring is no longer full. */ - sp->tx_full = 0; - netif_wake_queue(dev); /* Attention: under a spinlock. --SAW */ - } - } - - spin_unlock(&sp->lock); - - if (--boguscnt < 0) { - printk(KERN_ERR "%s: Too much work at interrupt, status=0x%4.4x.\n", - dev->name, status); - /* Clear all interrupt sources. */ - /* Will change from 0xfc00 to 0xff00 when we start handling - FCP and ER interrupts --Dragan */ - iowrite16(0xfc00, ioaddr + SCBStatus); - break; - } - } while (1); - - if (netif_msg_intr(sp)) - printk(KERN_DEBUG "%s: exiting interrupt, status=%#4.4x.\n", - dev->name, ioread16(ioaddr + SCBStatus)); - - clear_bit(0, (void*)&sp->in_interrupt); - return IRQ_RETVAL(handled); -} - -static inline struct RxFD *speedo_rx_alloc(struct net_device *dev, int entry) -{ - struct speedo_private *sp = netdev_priv(dev); - struct RxFD *rxf; - struct sk_buff *skb; - /* Get a fresh skbuff to replace the consumed one. */ - skb = dev_alloc_skb(PKT_BUF_SZ + sizeof(struct RxFD)); - if (skb) - rx_align(skb); /* Align IP on 16 byte boundary */ - sp->rx_skbuff[entry] = skb; - if (skb == NULL) { - sp->rx_ringp[entry] = NULL; - return NULL; - } - rxf = sp->rx_ringp[entry] = (struct RxFD *)skb->data; - sp->rx_ring_dma[entry] = - pci_map_single(sp->pdev, rxf, - PKT_BUF_SZ + sizeof(struct RxFD), PCI_DMA_FROMDEVICE); - skb->dev = dev; - skb_reserve(skb, sizeof(struct RxFD)); - rxf->rx_buf_addr = cpu_to_le32(0xffffffff); - pci_dma_sync_single_for_device(sp->pdev, sp->rx_ring_dma[entry], - sizeof(struct RxFD), PCI_DMA_TODEVICE); - return rxf; -} - -static inline void speedo_rx_link(struct net_device *dev, int entry, - struct RxFD *rxf, dma_addr_t rxf_dma) -{ - struct speedo_private *sp = netdev_priv(dev); - rxf->status = cpu_to_le32(0xC0000001); /* '1' for driver use only. */ - rxf->link = 0; /* None yet. */ - rxf->count = cpu_to_le32(PKT_BUF_SZ << 16); - sp->last_rxf->link = cpu_to_le32(rxf_dma); - sp->last_rxf->status &= cpu_to_le32(~0xC0000000); - pci_dma_sync_single_for_device(sp->pdev, sp->last_rxf_dma, - sizeof(struct RxFD), PCI_DMA_TODEVICE); - sp->last_rxf = rxf; - sp->last_rxf_dma = rxf_dma; -} - -static int speedo_refill_rx_buf(struct net_device *dev, int force) -{ - struct speedo_private *sp = netdev_priv(dev); - int entry; - struct RxFD *rxf; - - entry = sp->dirty_rx % RX_RING_SIZE; - if (sp->rx_skbuff[entry] == NULL) { - rxf = speedo_rx_alloc(dev, entry); - if (rxf == NULL) { - unsigned int forw; - int forw_entry; - if (netif_msg_rx_err(sp) || !(sp->rx_ring_state & RrOOMReported)) { - printk(KERN_WARNING "%s: can't fill rx buffer (force %d)!\n", - dev->name, force); - sp->rx_ring_state |= RrOOMReported; - } - speedo_show_state(dev); - if (!force) - return -1; /* Better luck next time! */ - /* Borrow an skb from one of next entries. */ - for (forw = sp->dirty_rx + 1; forw != sp->cur_rx; forw++) - if (sp->rx_skbuff[forw % RX_RING_SIZE] != NULL) - break; - if (forw == sp->cur_rx) - return -1; - forw_entry = forw % RX_RING_SIZE; - sp->rx_skbuff[entry] = sp->rx_skbuff[forw_entry]; - sp->rx_skbuff[forw_entry] = NULL; - rxf = sp->rx_ringp[forw_entry]; - sp->rx_ringp[forw_entry] = NULL; - sp->rx_ringp[entry] = rxf; - } - } else { - rxf = sp->rx_ringp[entry]; - } - speedo_rx_link(dev, entry, rxf, sp->rx_ring_dma[entry]); - sp->dirty_rx++; - sp->rx_ring_state &= ~(RrNoMem|RrOOMReported); /* Mark the progress. */ - return 0; -} - -static void speedo_refill_rx_buffers(struct net_device *dev, int force) -{ - struct speedo_private *sp = netdev_priv(dev); - - /* Refill the RX ring. */ - while ((int)(sp->cur_rx - sp->dirty_rx) > 0 && - speedo_refill_rx_buf(dev, force) != -1); -} - -static int -speedo_rx(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - int entry = sp->cur_rx % RX_RING_SIZE; - int rx_work_limit = sp->dirty_rx + RX_RING_SIZE - sp->cur_rx; - int alloc_ok = 1; - int npkts = 0; - - if (netif_msg_intr(sp)) - printk(KERN_DEBUG " In speedo_rx().\n"); - /* If we own the next entry, it's a new packet. Send it up. */ - while (sp->rx_ringp[entry] != NULL) { - int status; - int pkt_len; - - pci_dma_sync_single_for_cpu(sp->pdev, sp->rx_ring_dma[entry], - sizeof(struct RxFD), PCI_DMA_FROMDEVICE); - status = le32_to_cpu(sp->rx_ringp[entry]->status); - pkt_len = le32_to_cpu(sp->rx_ringp[entry]->count) & 0x3fff; - - if (!(status & RxComplete)) - break; - - if (--rx_work_limit < 0) - break; - - /* Check for a rare out-of-memory case: the current buffer is - the last buffer allocated in the RX ring. --SAW */ - if (sp->last_rxf == sp->rx_ringp[entry]) { - /* Postpone the packet. It'll be reaped at an interrupt when this - packet is no longer the last packet in the ring. */ - if (netif_msg_rx_err(sp)) - printk(KERN_DEBUG "%s: RX packet postponed!\n", - dev->name); - sp->rx_ring_state |= RrPostponed; - break; - } - - if (netif_msg_rx_status(sp)) - printk(KERN_DEBUG " speedo_rx() status %8.8x len %d.\n", status, - pkt_len); - if ((status & (RxErrTooBig|RxOK|0x0f90)) != RxOK) { - if (status & RxErrTooBig) - printk(KERN_ERR "%s: Ethernet frame overran the Rx buffer, " - "status %8.8x!\n", dev->name, status); - else if (! (status & RxOK)) { - /* There was a fatal error. This *should* be impossible. */ - sp->stats.rx_errors++; - printk(KERN_ERR "%s: Anomalous event in speedo_rx(), " - "status %8.8x.\n", - dev->name, status); - } - } else { - struct sk_buff *skb; - - /* Check if the packet is long enough to just accept without - copying to a properly sized skbuff. */ - if (pkt_len < rx_copybreak - && (skb = dev_alloc_skb(pkt_len + 2)) != NULL) { - skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ - /* 'skb_put()' points to the start of sk_buff data area. */ - pci_dma_sync_single_for_cpu(sp->pdev, sp->rx_ring_dma[entry], - sizeof(struct RxFD) + pkt_len, - PCI_DMA_FROMDEVICE); - -#if 1 || USE_IP_CSUM - /* Packet is in one chunk -- we can copy + cksum. */ - skb_copy_to_linear_data(skb, sp->rx_skbuff[entry]->data, pkt_len); - skb_put(skb, pkt_len); -#else - skb_copy_from_linear_data(sp->rx_skbuff[entry], - skb_put(skb, pkt_len), - pkt_len); -#endif - pci_dma_sync_single_for_device(sp->pdev, sp->rx_ring_dma[entry], - sizeof(struct RxFD) + pkt_len, - PCI_DMA_FROMDEVICE); - npkts++; - } else { - /* Pass up the already-filled skbuff. */ - skb = sp->rx_skbuff[entry]; - if (skb == NULL) { - printk(KERN_ERR "%s: Inconsistent Rx descriptor chain.\n", - dev->name); - break; - } - sp->rx_skbuff[entry] = NULL; - skb_put(skb, pkt_len); - npkts++; - sp->rx_ringp[entry] = NULL; - pci_unmap_single(sp->pdev, sp->rx_ring_dma[entry], - PKT_BUF_SZ + sizeof(struct RxFD), - PCI_DMA_FROMDEVICE); - } - skb->protocol = eth_type_trans(skb, dev); - netif_rx(skb); - dev->last_rx = jiffies; - sp->stats.rx_packets++; - sp->stats.rx_bytes += pkt_len; - } - entry = (++sp->cur_rx) % RX_RING_SIZE; - sp->rx_ring_state &= ~RrPostponed; - /* Refill the recently taken buffers. - Do it one-by-one to handle traffic bursts better. */ - if (alloc_ok && speedo_refill_rx_buf(dev, 0) == -1) - alloc_ok = 0; - } - - /* Try hard to refill the recently taken buffers. */ - speedo_refill_rx_buffers(dev, 1); - - if (npkts) - sp->last_rx_time = jiffies; - - return 0; -} - -static int -speedo_close(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int i; - - netdevice_stop(dev); - netif_stop_queue(dev); - - if (netif_msg_ifdown(sp)) - printk(KERN_DEBUG "%s: Shutting down ethercard, status was %4.4x.\n", - dev->name, ioread16(ioaddr + SCBStatus)); - - /* Shut off the media monitoring timer. */ - del_timer_sync(&sp->timer); - - iowrite16(SCBMaskAll, ioaddr + SCBCmd); - - /* Shutting down the chip nicely fails to disable flow control. So.. */ - iowrite32(PortPartialReset, ioaddr + SCBPort); - ioread32(ioaddr + SCBPort); /* flush posted write */ - /* - * The chip requires a 10 microsecond quiet period. Wait here! - */ - udelay(10); - - free_irq(dev->irq, dev); - speedo_show_state(dev); - - /* Free all the skbuffs in the Rx and Tx queues. */ - for (i = 0; i < RX_RING_SIZE; i++) { - struct sk_buff *skb = sp->rx_skbuff[i]; - sp->rx_skbuff[i] = NULL; - /* Clear the Rx descriptors. */ - if (skb) { - pci_unmap_single(sp->pdev, - sp->rx_ring_dma[i], - PKT_BUF_SZ + sizeof(struct RxFD), PCI_DMA_FROMDEVICE); - dev_kfree_skb(skb); - } - } - - for (i = 0; i < TX_RING_SIZE; i++) { - struct sk_buff *skb = sp->tx_skbuff[i]; - sp->tx_skbuff[i] = NULL; - /* Clear the Tx descriptors. */ - if (skb) { - pci_unmap_single(sp->pdev, - le32_to_cpu(sp->tx_ring[i].tx_buf_addr0), - skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb(skb); - } - } - - /* Free multicast setting blocks. */ - for (i = 0; sp->mc_setup_head != NULL; i++) { - struct speedo_mc_block *t; - t = sp->mc_setup_head->next; - kfree(sp->mc_setup_head); - sp->mc_setup_head = t; - } - sp->mc_setup_tail = NULL; - if (netif_msg_ifdown(sp)) - printk(KERN_DEBUG "%s: %d multicast blocks dropped.\n", dev->name, i); - - pci_set_power_state(sp->pdev, PCI_D2); - - return 0; -} - -/* The Speedo-3 has an especially awkward and unusable method of getting - statistics out of the chip. It takes an unpredictable length of time - for the dump-stats command to complete. To avoid a busy-wait loop we - update the stats with the previous dump results, and then trigger a - new dump. - - Oh, and incoming frames are dropped while executing dump-stats! - */ -static struct net_device_stats * -speedo_get_stats(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - - /* Update only if the previous dump finished. */ - if (sp->lstats->done_marker == cpu_to_le32(0xA007)) { - sp->stats.tx_aborted_errors += le32_to_cpu(sp->lstats->tx_coll16_errs); - sp->stats.tx_window_errors += le32_to_cpu(sp->lstats->tx_late_colls); - sp->stats.tx_fifo_errors += le32_to_cpu(sp->lstats->tx_underruns); - sp->stats.tx_fifo_errors += le32_to_cpu(sp->lstats->tx_lost_carrier); - /*sp->stats.tx_deferred += le32_to_cpu(sp->lstats->tx_deferred);*/ - sp->stats.collisions += le32_to_cpu(sp->lstats->tx_total_colls); - sp->stats.rx_crc_errors += le32_to_cpu(sp->lstats->rx_crc_errs); - sp->stats.rx_frame_errors += le32_to_cpu(sp->lstats->rx_align_errs); - sp->stats.rx_over_errors += le32_to_cpu(sp->lstats->rx_resource_errs); - sp->stats.rx_fifo_errors += le32_to_cpu(sp->lstats->rx_overrun_errs); - sp->stats.rx_length_errors += le32_to_cpu(sp->lstats->rx_runt_errs); - sp->lstats->done_marker = 0x0000; - if (netif_running(dev)) { - unsigned long flags; - /* Take a spinlock to make wait_for_cmd_done and sending the - command atomic. --SAW */ - spin_lock_irqsave(&sp->lock, flags); - wait_for_cmd_done(dev, sp); - iowrite8(CUDumpStats, ioaddr + SCBCmd); - spin_unlock_irqrestore(&sp->lock, flags); - } - } - return &sp->stats; -} - -static void speedo_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) -{ - struct speedo_private *sp = netdev_priv(dev); - strncpy(info->driver, "eepro100", sizeof(info->driver)-1); - strncpy(info->version, version, sizeof(info->version)-1); - if (sp->pdev) - strcpy(info->bus_info, pci_name(sp->pdev)); -} - -static int speedo_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd) -{ - struct speedo_private *sp = netdev_priv(dev); - spin_lock_irq(&sp->lock); - mii_ethtool_gset(&sp->mii_if, ecmd); - spin_unlock_irq(&sp->lock); - return 0; -} - -static int speedo_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd) -{ - struct speedo_private *sp = netdev_priv(dev); - int res; - spin_lock_irq(&sp->lock); - res = mii_ethtool_sset(&sp->mii_if, ecmd); - spin_unlock_irq(&sp->lock); - return res; -} - -static int speedo_nway_reset(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - return mii_nway_restart(&sp->mii_if); -} - -static u32 speedo_get_link(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - return mii_link_ok(&sp->mii_if); -} - -static u32 speedo_get_msglevel(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - return sp->msg_enable; -} - -static void speedo_set_msglevel(struct net_device *dev, u32 v) -{ - struct speedo_private *sp = netdev_priv(dev); - sp->msg_enable = v; -} - -static const struct ethtool_ops ethtool_ops = { - .get_drvinfo = speedo_get_drvinfo, - .get_settings = speedo_get_settings, - .set_settings = speedo_set_settings, - .nway_reset = speedo_nway_reset, - .get_link = speedo_get_link, - .get_msglevel = speedo_get_msglevel, - .set_msglevel = speedo_set_msglevel, -}; - -static int speedo_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct speedo_private *sp = netdev_priv(dev); - struct mii_ioctl_data *data = if_mii(rq); - int phy = sp->phy[0] & 0x1f; - int saved_acpi; - int t; - - switch(cmd) { - case SIOCGMIIPHY: /* Get address of MII PHY in use. */ - data->phy_id = phy; - - case SIOCGMIIREG: /* Read MII PHY register. */ - /* FIXME: these operations need to be serialized with MDIO - access from the timeout handler. - They are currently serialized only with MDIO access from the - timer routine. 2000/05/09 SAW */ - saved_acpi = pci_set_power_state(sp->pdev, PCI_D0); - t = del_timer_sync(&sp->timer); - data->val_out = mdio_read(dev, data->phy_id & 0x1f, data->reg_num & 0x1f); - if (t) - add_timer(&sp->timer); /* may be set to the past --SAW */ - pci_set_power_state(sp->pdev, saved_acpi); - return 0; - - case SIOCSMIIREG: /* Write MII PHY register. */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - saved_acpi = pci_set_power_state(sp->pdev, PCI_D0); - t = del_timer_sync(&sp->timer); - mdio_write(dev, data->phy_id, data->reg_num, data->val_in); - if (t) - add_timer(&sp->timer); /* may be set to the past --SAW */ - pci_set_power_state(sp->pdev, saved_acpi); - return 0; - default: - return -EOPNOTSUPP; - } -} - -/* Set or clear the multicast filter for this adaptor. - This is very ugly with Intel chips -- we usually have to execute an - entire configuration command, plus process a multicast command. - This is complicated. We must put a large configuration command and - an arbitrarily-sized multicast command in the transmit list. - To minimize the disruption -- the previous command might have already - loaded the link -- we convert the current command block, normally a Tx - command, into a no-op and link it to the new command. -*/ -static void set_rx_mode(struct net_device *dev) -{ - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - struct descriptor *last_cmd; - char new_rx_mode; - unsigned long flags; - int entry, i; - - if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ - new_rx_mode = 3; - } else if ((dev->flags & IFF_ALLMULTI) || - dev->mc_count > multicast_filter_limit) { - new_rx_mode = 1; - } else - new_rx_mode = 0; - - if (netif_msg_rx_status(sp)) - printk(KERN_DEBUG "%s: set_rx_mode %d -> %d\n", dev->name, - sp->rx_mode, new_rx_mode); - - if ((int)(sp->cur_tx - sp->dirty_tx) > TX_RING_SIZE - TX_MULTICAST_SIZE) { - /* The Tx ring is full -- don't add anything! Hope the mode will be - * set again later. */ - sp->rx_mode = -1; - return; - } - - if (new_rx_mode != sp->rx_mode) { - u8 *config_cmd_data; - - spin_lock_irqsave(&sp->lock, flags); - entry = sp->cur_tx++ % TX_RING_SIZE; - last_cmd = sp->last_cmd; - sp->last_cmd = (struct descriptor *)&sp->tx_ring[entry]; - - sp->tx_skbuff[entry] = NULL; /* Redundant. */ - sp->tx_ring[entry].status = cpu_to_le32(CmdSuspend | CmdConfigure); - sp->tx_ring[entry].link = - cpu_to_le32(TX_RING_ELEM_DMA(sp, (entry + 1) % TX_RING_SIZE)); - config_cmd_data = (void *)&sp->tx_ring[entry].tx_desc_addr; - /* Construct a full CmdConfig frame. */ - memcpy(config_cmd_data, i82558_config_cmd, CONFIG_DATA_SIZE); - config_cmd_data[1] = (txfifo << 4) | rxfifo; - config_cmd_data[4] = rxdmacount; - config_cmd_data[5] = txdmacount + 0x80; - config_cmd_data[15] |= (new_rx_mode & 2) ? 1 : 0; - /* 0x80 doesn't disable FC 0x84 does. - Disable Flow control since we are not ACK-ing any FC interrupts - for now. --Dragan */ - config_cmd_data[19] = 0x84; - config_cmd_data[19] |= sp->mii_if.full_duplex ? 0x40 : 0; - config_cmd_data[21] = (new_rx_mode & 1) ? 0x0D : 0x05; - if (sp->phy[0] & 0x8000) { /* Use the AUI port instead. */ - config_cmd_data[15] |= 0x80; - config_cmd_data[8] = 0; - } - /* Trigger the command unit resume. */ - wait_for_cmd_done(dev, sp); - clear_suspend(last_cmd); - iowrite8(CUResume, ioaddr + SCBCmd); - if ((int)(sp->cur_tx - sp->dirty_tx) >= TX_QUEUE_LIMIT) { - netif_stop_queue(dev); - sp->tx_full = 1; - } - spin_unlock_irqrestore(&sp->lock, flags); - } - - if (new_rx_mode == 0 && dev->mc_count < 4) { - /* The simple case of 0-3 multicast list entries occurs often, and - fits within one tx_ring[] entry. */ - struct dev_mc_list *mclist; - __le16 *setup_params, *eaddrs; - - spin_lock_irqsave(&sp->lock, flags); - entry = sp->cur_tx++ % TX_RING_SIZE; - last_cmd = sp->last_cmd; - sp->last_cmd = (struct descriptor *)&sp->tx_ring[entry]; - - sp->tx_skbuff[entry] = NULL; - sp->tx_ring[entry].status = cpu_to_le32(CmdSuspend | CmdMulticastList); - sp->tx_ring[entry].link = - cpu_to_le32(TX_RING_ELEM_DMA(sp, (entry + 1) % TX_RING_SIZE)); - sp->tx_ring[entry].tx_desc_addr = 0; /* Really MC list count. */ - setup_params = (__le16 *)&sp->tx_ring[entry].tx_desc_addr; - *setup_params++ = cpu_to_le16(dev->mc_count*6); - /* Fill in the multicast addresses. */ - for (i = 0, mclist = dev->mc_list; i < dev->mc_count; - i++, mclist = mclist->next) { - eaddrs = (__le16 *)mclist->dmi_addr; - *setup_params++ = *eaddrs++; - *setup_params++ = *eaddrs++; - *setup_params++ = *eaddrs++; - } - - wait_for_cmd_done(dev, sp); - clear_suspend(last_cmd); - /* Immediately trigger the command unit resume. */ - iowrite8(CUResume, ioaddr + SCBCmd); - - if ((int)(sp->cur_tx - sp->dirty_tx) >= TX_QUEUE_LIMIT) { - netif_stop_queue(dev); - sp->tx_full = 1; - } - spin_unlock_irqrestore(&sp->lock, flags); - } else if (new_rx_mode == 0) { - struct dev_mc_list *mclist; - __le16 *setup_params, *eaddrs; - struct speedo_mc_block *mc_blk; - struct descriptor *mc_setup_frm; - int i; - - mc_blk = kmalloc(sizeof(*mc_blk) + 2 + multicast_filter_limit*6, - GFP_ATOMIC); - if (mc_blk == NULL) { - printk(KERN_ERR "%s: Failed to allocate a setup frame.\n", - dev->name); - sp->rx_mode = -1; /* We failed, try again. */ - return; - } - mc_blk->next = NULL; - mc_blk->len = 2 + multicast_filter_limit*6; - mc_blk->frame_dma = - pci_map_single(sp->pdev, &mc_blk->frame, mc_blk->len, - PCI_DMA_TODEVICE); - mc_setup_frm = &mc_blk->frame; - - /* Fill the setup frame. */ - if (netif_msg_ifup(sp)) - printk(KERN_DEBUG "%s: Constructing a setup frame at %p.\n", - dev->name, mc_setup_frm); - mc_setup_frm->cmd_status = - cpu_to_le32(CmdSuspend | CmdIntr | CmdMulticastList); - /* Link set below. */ - setup_params = (__le16 *)&mc_setup_frm->params; - *setup_params++ = cpu_to_le16(dev->mc_count*6); - /* Fill in the multicast addresses. */ - for (i = 0, mclist = dev->mc_list; i < dev->mc_count; - i++, mclist = mclist->next) { - eaddrs = (__le16 *)mclist->dmi_addr; - *setup_params++ = *eaddrs++; - *setup_params++ = *eaddrs++; - *setup_params++ = *eaddrs++; - } - - /* Disable interrupts while playing with the Tx Cmd list. */ - spin_lock_irqsave(&sp->lock, flags); - - if (sp->mc_setup_tail) - sp->mc_setup_tail->next = mc_blk; - else - sp->mc_setup_head = mc_blk; - sp->mc_setup_tail = mc_blk; - mc_blk->tx = sp->cur_tx; - - entry = sp->cur_tx++ % TX_RING_SIZE; - last_cmd = sp->last_cmd; - sp->last_cmd = mc_setup_frm; - - /* Change the command to a NoOp, pointing to the CmdMulti command. */ - sp->tx_skbuff[entry] = NULL; - sp->tx_ring[entry].status = cpu_to_le32(CmdNOp); - sp->tx_ring[entry].link = cpu_to_le32(mc_blk->frame_dma); - - /* Set the link in the setup frame. */ - mc_setup_frm->link = - cpu_to_le32(TX_RING_ELEM_DMA(sp, (entry + 1) % TX_RING_SIZE)); - - pci_dma_sync_single_for_device(sp->pdev, mc_blk->frame_dma, - mc_blk->len, PCI_DMA_TODEVICE); - - wait_for_cmd_done(dev, sp); - clear_suspend(last_cmd); - /* Immediately trigger the command unit resume. */ - iowrite8(CUResume, ioaddr + SCBCmd); - - if ((int)(sp->cur_tx - sp->dirty_tx) >= TX_QUEUE_LIMIT) { - netif_stop_queue(dev); - sp->tx_full = 1; - } - spin_unlock_irqrestore(&sp->lock, flags); - - if (netif_msg_rx_status(sp)) - printk(" CmdMCSetup frame length %d in entry %d.\n", - dev->mc_count, entry); - } - - sp->rx_mode = new_rx_mode; -} - -#ifdef CONFIG_PM -static int eepro100_suspend(struct pci_dev *pdev, pm_message_t state) -{ - struct net_device *dev = pci_get_drvdata (pdev); - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - - pci_save_state(pdev); - - if (!netif_running(dev)) - return 0; - - del_timer_sync(&sp->timer); - - netif_device_detach(dev); - iowrite32(PortPartialReset, ioaddr + SCBPort); - - /* XXX call pci_set_power_state ()? */ - pci_disable_device(pdev); - pci_set_power_state (pdev, PCI_D3hot); - return 0; -} - -static int eepro100_resume(struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata (pdev); - struct speedo_private *sp = netdev_priv(dev); - void __iomem *ioaddr = sp->regs; - int rc; - - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - - rc = pci_enable_device(pdev); - if (rc) - return rc; - - pci_set_master(pdev); - - if (!netif_running(dev)) - return 0; - - /* I'm absolutely uncertain if this part of code may work. - The problems are: - - correct hardware reinitialization; - - correct driver behavior between different steps of the - reinitialization; - - serialization with other driver calls. - 2000/03/08 SAW */ - iowrite16(SCBMaskAll, ioaddr + SCBCmd); - speedo_resume(dev); - netif_device_attach(dev); - sp->rx_mode = -1; - sp->flow_ctrl = sp->partner = 0; - set_rx_mode(dev); - sp->timer.expires = RUN_AT(2*HZ); - add_timer(&sp->timer); - return 0; -} -#endif /* CONFIG_PM */ - -static void __devexit eepro100_remove_one (struct pci_dev *pdev) -{ - struct net_device *dev = pci_get_drvdata (pdev); - struct speedo_private *sp = netdev_priv(dev); - - unregister_netdev(dev); - - release_region(pci_resource_start(pdev, 1), pci_resource_len(pdev, 1)); - release_mem_region(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); - - pci_iounmap(pdev, sp->regs); - pci_free_consistent(pdev, TX_RING_SIZE * sizeof(struct TxFD) - + sizeof(struct speedo_stats), - sp->tx_ring, sp->tx_ring_dma); - pci_disable_device(pdev); - free_netdev(dev); -} - -static struct pci_device_id eepro100_pci_tbl[] = { - { PCI_VENDOR_ID_INTEL, 0x1229, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1209, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1029, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1030, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1031, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1032, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1033, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1034, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1035, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1036, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1037, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1038, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1039, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x103A, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x103B, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x103C, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x103D, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x103E, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1050, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1059, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x1227, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x2449, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x2459, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x245D, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x5200, PCI_ANY_ID, PCI_ANY_ID, }, - { PCI_VENDOR_ID_INTEL, 0x5201, PCI_ANY_ID, PCI_ANY_ID, }, - { 0,} -}; -MODULE_DEVICE_TABLE(pci, eepro100_pci_tbl); - -static struct pci_driver eepro100_driver = { - .name = "eepro100", - .id_table = eepro100_pci_tbl, - .probe = eepro100_init_one, - .remove = __devexit_p(eepro100_remove_one), -#ifdef CONFIG_PM - .suspend = eepro100_suspend, - .resume = eepro100_resume, -#endif /* CONFIG_PM */ -}; - -static int __init eepro100_init_module(void) -{ -#ifdef MODULE - printk(version); -#endif - return pci_register_driver(&eepro100_driver); -} - -static void __exit eepro100_cleanup_module(void) -{ - pci_unregister_driver(&eepro100_driver); -} - -module_init(eepro100_init_module); -module_exit(eepro100_cleanup_module); - -/* - * Local variables: - * compile-command: "gcc -DMODULE -D__KERNEL__ -I/usr/src/linux/net/inet -Wall -Wstrict-prototypes -O6 -c eepro100.c `[ -f /usr/include/linux/modversions.h ] && echo -DMODVERSIONS`" - * c-indent-level: 4 - * c-basic-offset: 4 - * tab-width: 4 - * End: - */ -- cgit v1.2.3 From d003922dab6a66027344a787e9846ecf35a706a8 Mon Sep 17 00:00:00 2001 From: Henrique de Moraes Holschuh Date: Thu, 9 Oct 2008 21:49:33 -0300 Subject: rfkill: add master_switch_mode and EPO lock to rfkill and rfkill-input Add of software-based sanity to rfkill and rfkill-input so that it can reproduce what hardware-based EPO switches do, blocking all transmitters and locking down any further attempts to unblock them until the switch is deactivated. rfkill-input is responsible for issuing the EPO control requests, like before. While an rfkill EPO is active, all transmitters are locked to one of the BLOCKED states and all attempts to change that through the rfkill API (userspace and kernel) will be either ignored or return -EPERM errors. The lock will be released upon receipt of EV_SW SW_RFKILL_ALL ON by rfkill-input, or should modular rfkill-input be unloaded. This makes rfkill and rfkill-input extend the operation of an existing wireless master kill switch to all wireless devices in the system, even those that are not under hardware or firmware control. Since the above is the expected operational behavior for the master rfkill switch, the EPO lock functionality is not optional. Also, extend rfkill-input to allow for three different behaviors when it receives an EV_SW SW_RFKILL_ALL ON input event. The user can set which behavior he wants through the master_switch_mode parameter: master_switch_mode = 0: EV_SW SW_RFKILL_ALL ON just unlocks rfkill controller state changes (so that the rfkill userspace and kernel APIs can now be used to change rfkill controller states again), but doesn't change any of their states (so they will all remain blocked). This is the safest mode of operation, as it requires explicit operator action to re-enable a transmitter. master_switch_mode = 1: EV_SW SW_RFKILL_ALL ON causes rfkill-input to attempt to restore the system to the state before the last EV_SW SW_RFKILL_ALL OFF event, or to the default global states if no EV_SW SW_RFKILL_ALL OFF ever happened. This is the recommended mode of operation for laptops. master_switch_mode = 2: tries to unblock all rfkill controllers (i.e. enable all transmitters) when an EV_SW SW_RFKILL_ALL ON event is received. This is the default mode of operation, as it mimics the previous behavior of rfkill-input. In order to implement these features in a clean way, the entire event handling of rfkill-input was refactored into a single worker function. Protection against input event DoS (repeatedly firing rfkill events for rfkill-input to process) was removed during the code refactoring. It will be added back in a future patch. Note that with these changes, rfkill-input doesn't need to explicitly handle any radio types for which KEY_ or SW_ events do not exist yet. Code to handle EV_SW SW_{WLAN,WWAN,BLUETOOTH,WIMAX,...} was added as it might be needed in the future (and its implementation is not that obvious), but is currently #ifdef'd out to avoid wasting resources. Signed-off-by: Henrique de Moraes Holschuh Cc: Ivo van Doorn Cc: Dmitry Torokhov Signed-off-by: John W. Linville --- Documentation/rfkill.txt | 20 +-- net/rfkill/rfkill-input.c | 306 ++++++++++++++++++++++++++++++++++------------ net/rfkill/rfkill-input.h | 2 + net/rfkill/rfkill.c | 46 ++++++- 4 files changed, 287 insertions(+), 87 deletions(-) (limited to 'Documentation') diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt index b65f0799df48..4d3ee317a4a3 100644 --- a/Documentation/rfkill.txt +++ b/Documentation/rfkill.txt @@ -191,12 +191,20 @@ Userspace input handlers (uevents) or kernel input handlers (rfkill-input): to tell the devices registered with the rfkill class to change their state (i.e. translates the input layer event into real action). + * rfkill-input implements EPO by handling EV_SW SW_RFKILL_ALL 0 (power off all transmitters) in a special way: it ignores any overrides and local state cache and forces all transmitters to the RFKILL_STATE_SOFT_BLOCKED state (including those which are already - supposed to be BLOCKED). Note that the opposite event (power on all - transmitters) is handled normally. + supposed to be BLOCKED). + * rfkill EPO will remain active until rfkill-input receives an + EV_SW SW_RFKILL_ALL 1 event. While the EPO is active, transmitters + are locked in the blocked state (rfkill will refuse to unblock them). + * rfkill-input implements different policies that the user can + select for handling EV_SW SW_RFKILL_ALL 1. It will unlock rfkill, + and either do nothing (leave transmitters blocked, but now unlocked), + restore the transmitters to their state before the EPO, or unblock + them all. Userspace uevent handler or kernel platform-specific drivers hooked to the rfkill notifier chain: @@ -331,11 +339,9 @@ class to get a sysfs interface :-) correct event for your switch/button. These events are emergency power-off events when they are trying to turn the transmitters off. An example of an input device which SHOULD generate *_RFKILL_ALL events is the wireless-kill -switch in a laptop which is NOT a hotkey, but a real switch that kills radios -in hardware, even if the O.S. has gone to lunch. An example of an input device -which SHOULD NOT generate *_RFKILL_ALL events by default, is any sort of hot -key that does nothing by itself, as well as any hot key that is type-specific -(e.g. the one for WLAN). +switch in a laptop which is NOT a hotkey, but a real sliding/rocker switch. +An example of an input device which SHOULD NOT generate *_RFKILL_ALL events by +default, is any sort of hot key that is type-specific (e.g. the one for WLAN). 3.1 Guidelines for wireless device drivers diff --git a/net/rfkill/rfkill-input.c b/net/rfkill/rfkill-input.c index bfdade72e066..7706541f9f79 100644 --- a/net/rfkill/rfkill-input.c +++ b/net/rfkill/rfkill-input.c @@ -24,138 +24,291 @@ MODULE_AUTHOR("Dmitry Torokhov "); MODULE_DESCRIPTION("Input layer to RF switch connector"); MODULE_LICENSE("GPL"); +enum rfkill_input_master_mode { + RFKILL_INPUT_MASTER_DONOTHING = 0, + RFKILL_INPUT_MASTER_RESTORE = 1, + RFKILL_INPUT_MASTER_UNBLOCKALL = 2, + RFKILL_INPUT_MASTER_MAX, /* marker */ +}; + +static enum rfkill_input_master_mode rfkill_master_switch_mode = + RFKILL_INPUT_MASTER_UNBLOCKALL; +module_param_named(master_switch_mode, rfkill_master_switch_mode, uint, 0); +MODULE_PARM_DESC(master_switch_mode, + "SW_RFKILL_ALL ON should: 0=do nothing; 1=restore; 2=unblock all"); + +enum rfkill_global_sched_op { + RFKILL_GLOBAL_OP_EPO = 0, + RFKILL_GLOBAL_OP_RESTORE, + RFKILL_GLOBAL_OP_UNLOCK, + RFKILL_GLOBAL_OP_UNBLOCK, +}; + +/* + * Currently, the code marked with RFKILL_NEED_SWSET is inactive. + * If handling of EV_SW SW_WLAN/WWAN/BLUETOOTH/etc is needed in the + * future, when such events are added, that code will be necessary. + */ + struct rfkill_task { struct work_struct work; - enum rfkill_type type; - struct mutex mutex; /* ensures that task is serialized */ - spinlock_t lock; /* for accessing last and desired state */ - unsigned long last; /* last schedule */ - enum rfkill_state desired_state; /* on/off */ + + /* ensures that task is serialized */ + struct mutex mutex; + + /* protects everything below */ + spinlock_t lock; + + /* pending regular switch operations (1=pending) */ + unsigned long sw_pending[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; + +#ifdef RFKILL_NEED_SWSET + /* set operation pending (1=pending) */ + unsigned long sw_setpending[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; + + /* desired state for pending set operation (1=unblock) */ + unsigned long sw_newstate[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; +#endif + + /* should the state be complemented (1=yes) */ + unsigned long sw_togglestate[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; + + bool global_op_pending; + enum rfkill_global_sched_op op; }; -static void rfkill_task_handler(struct work_struct *work) +static void __rfkill_handle_global_op(enum rfkill_global_sched_op op) { - struct rfkill_task *task = container_of(work, struct rfkill_task, work); + unsigned int i; + + switch (op) { + case RFKILL_GLOBAL_OP_EPO: + rfkill_epo(); + break; + case RFKILL_GLOBAL_OP_RESTORE: + rfkill_restore_states(); + break; + case RFKILL_GLOBAL_OP_UNLOCK: + rfkill_remove_epo_lock(); + break; + case RFKILL_GLOBAL_OP_UNBLOCK: + rfkill_remove_epo_lock(); + for (i = 0; i < RFKILL_TYPE_MAX; i++) + rfkill_switch_all(i, RFKILL_STATE_UNBLOCKED); + break; + default: + /* memory corruption or bug, fail safely */ + rfkill_epo(); + WARN(1, "Unknown requested operation %d! " + "rfkill Emergency Power Off activated\n", + op); + } +} - mutex_lock(&task->mutex); +#ifdef RFKILL_NEED_SWSET +static void __rfkill_handle_normal_op(const enum rfkill_type type, + const bool sp, const bool s, const bool c) +{ + enum rfkill_state state; - rfkill_switch_all(task->type, task->desired_state); + if (sp) + state = (s) ? RFKILL_STATE_UNBLOCKED : + RFKILL_STATE_SOFT_BLOCKED; + else + state = rfkill_get_global_state(type); - mutex_unlock(&task->mutex); + if (c) + state = rfkill_state_complement(state); + + rfkill_switch_all(type, state); } +#else +static void __rfkill_handle_normal_op(const enum rfkill_type type, + const bool c) +{ + enum rfkill_state state; + + state = rfkill_get_global_state(type); + if (c) + state = rfkill_state_complement(state); + + rfkill_switch_all(type, state); +} +#endif -static void rfkill_task_epo_handler(struct work_struct *work) +static void rfkill_task_handler(struct work_struct *work) { - rfkill_epo(); + struct rfkill_task *task = + container_of(work, struct rfkill_task, work); + bool doit = true; + + mutex_lock(&task->mutex); + + spin_lock_irq(&task->lock); + while (doit) { + if (task->global_op_pending) { + enum rfkill_global_sched_op op = task->op; + task->global_op_pending = false; + memset(task->sw_pending, 0, sizeof(task->sw_pending)); + spin_unlock_irq(&task->lock); + + __rfkill_handle_global_op(op); + + /* make sure we do at least one pass with + * !task->global_op_pending */ + spin_lock_irq(&task->lock); + continue; + } else if (!rfkill_is_epo_lock_active()) { + unsigned int i = 0; + + while (!task->global_op_pending && + i < RFKILL_TYPE_MAX) { + if (test_and_clear_bit(i, task->sw_pending)) { + bool c; +#ifdef RFKILL_NEED_SWSET + bool sp, s; + sp = test_and_clear_bit(i, + task->sw_setpending); + s = test_bit(i, task->sw_newstate); +#endif + c = test_and_clear_bit(i, + task->sw_togglestate); + spin_unlock_irq(&task->lock); + +#ifdef RFKILL_NEED_SWSET + __rfkill_handle_normal_op(i, sp, s, c); +#else + __rfkill_handle_normal_op(i, c); +#endif + + spin_lock_irq(&task->lock); + } + i++; + } + } + doit = task->global_op_pending; + } + spin_unlock_irq(&task->lock); + + mutex_unlock(&task->mutex); } -static DECLARE_WORK(epo_work, rfkill_task_epo_handler); +static struct rfkill_task rfkill_task = { + .work = __WORK_INITIALIZER(rfkill_task.work, + rfkill_task_handler), + .mutex = __MUTEX_INITIALIZER(rfkill_task.mutex), + .lock = __SPIN_LOCK_UNLOCKED(rfkill_task.lock), +}; -static void rfkill_schedule_epo(void) +static void rfkill_schedule_global_op(enum rfkill_global_sched_op op) { - schedule_work(&epo_work); + unsigned long flags; + + spin_lock_irqsave(&rfkill_task.lock, flags); + rfkill_task.op = op; + rfkill_task.global_op_pending = true; + schedule_work(&rfkill_task.work); + spin_unlock_irqrestore(&rfkill_task.lock, flags); } -static void rfkill_schedule_set(struct rfkill_task *task, +#ifdef RFKILL_NEED_SWSET +/* Use this if you need to add EV_SW SW_WLAN/WWAN/BLUETOOTH/etc handling */ + +static void rfkill_schedule_set(enum rfkill_type type, enum rfkill_state desired_state) { unsigned long flags; - if (unlikely(work_pending(&epo_work))) + if (rfkill_is_epo_lock_active()) return; - spin_lock_irqsave(&task->lock, flags); - - if (time_after(jiffies, task->last + msecs_to_jiffies(200))) { - task->desired_state = desired_state; - task->last = jiffies; - schedule_work(&task->work); + spin_lock_irqsave(&rfkill_task.lock, flags); + if (!rfkill_task.global_op_pending) { + set_bit(type, rfkill_task.sw_pending); + set_bit(type, rfkill_task.sw_setpending); + clear_bit(type, rfkill_task.sw_togglestate); + if (desired_state) + set_bit(type, rfkill_task.sw_newstate); + else + clear_bit(type, rfkill_task.sw_newstate); + schedule_work(&rfkill_task.work); } - - spin_unlock_irqrestore(&task->lock, flags); + spin_unlock_irqrestore(&rfkill_task.lock, flags); } +#endif -static void rfkill_schedule_toggle(struct rfkill_task *task) +static void rfkill_schedule_toggle(enum rfkill_type type) { unsigned long flags; - if (unlikely(work_pending(&epo_work))) + if (rfkill_is_epo_lock_active()) return; - spin_lock_irqsave(&task->lock, flags); - - if (time_after(jiffies, task->last + msecs_to_jiffies(200))) { - task->desired_state = - rfkill_state_complement(task->desired_state); - task->last = jiffies; - schedule_work(&task->work); + spin_lock_irqsave(&rfkill_task.lock, flags); + if (!rfkill_task.global_op_pending) { + set_bit(type, rfkill_task.sw_pending); + change_bit(type, rfkill_task.sw_togglestate); + schedule_work(&rfkill_task.work); } - - spin_unlock_irqrestore(&task->lock, flags); + spin_unlock_irqrestore(&rfkill_task.lock, flags); } -#define DEFINE_RFKILL_TASK(n, t) \ - struct rfkill_task n = { \ - .work = __WORK_INITIALIZER(n.work, \ - rfkill_task_handler), \ - .type = t, \ - .mutex = __MUTEX_INITIALIZER(n.mutex), \ - .lock = __SPIN_LOCK_UNLOCKED(n.lock), \ - .desired_state = RFKILL_STATE_UNBLOCKED, \ - } - -static DEFINE_RFKILL_TASK(rfkill_wlan, RFKILL_TYPE_WLAN); -static DEFINE_RFKILL_TASK(rfkill_bt, RFKILL_TYPE_BLUETOOTH); -static DEFINE_RFKILL_TASK(rfkill_uwb, RFKILL_TYPE_UWB); -static DEFINE_RFKILL_TASK(rfkill_wimax, RFKILL_TYPE_WIMAX); -static DEFINE_RFKILL_TASK(rfkill_wwan, RFKILL_TYPE_WWAN); - static void rfkill_schedule_evsw_rfkillall(int state) { - /* EVERY radio type. state != 0 means radios ON */ - /* handle EPO (emergency power off) through shortcut */ if (state) { - rfkill_schedule_set(&rfkill_wwan, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_wimax, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_uwb, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_bt, - RFKILL_STATE_UNBLOCKED); - rfkill_schedule_set(&rfkill_wlan, - RFKILL_STATE_UNBLOCKED); + switch (rfkill_master_switch_mode) { + case RFKILL_INPUT_MASTER_UNBLOCKALL: + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_UNBLOCK); + break; + case RFKILL_INPUT_MASTER_RESTORE: + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_RESTORE); + break; + case RFKILL_INPUT_MASTER_DONOTHING: + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_UNLOCK); + break; + default: + /* memory corruption or driver bug! fail safely */ + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_EPO); + WARN(1, "Unknown rfkill_master_switch_mode (%d), " + "driver bug or memory corruption detected!\n", + rfkill_master_switch_mode); + break; + } } else - rfkill_schedule_epo(); + rfkill_schedule_global_op(RFKILL_GLOBAL_OP_EPO); } static void rfkill_event(struct input_handle *handle, unsigned int type, unsigned int code, int data) { if (type == EV_KEY && data == 1) { + enum rfkill_type t; + switch (code) { case KEY_WLAN: - rfkill_schedule_toggle(&rfkill_wlan); + t = RFKILL_TYPE_WLAN; break; case KEY_BLUETOOTH: - rfkill_schedule_toggle(&rfkill_bt); + t = RFKILL_TYPE_BLUETOOTH; break; case KEY_UWB: - rfkill_schedule_toggle(&rfkill_uwb); + t = RFKILL_TYPE_UWB; break; case KEY_WIMAX: - rfkill_schedule_toggle(&rfkill_wimax); + t = RFKILL_TYPE_WIMAX; break; default: - break; + return; } + rfkill_schedule_toggle(t); + return; } else if (type == EV_SW) { switch (code) { case SW_RFKILL_ALL: rfkill_schedule_evsw_rfkillall(data); - break; + return; default: - break; + return; } } } @@ -256,11 +409,9 @@ static struct input_handler rfkill_handler = { static int __init rfkill_handler_init(void) { - unsigned long last_run = jiffies - msecs_to_jiffies(500); - rfkill_wlan.last = last_run; - rfkill_bt.last = last_run; - rfkill_uwb.last = last_run; - rfkill_wimax.last = last_run; + if (rfkill_master_switch_mode >= RFKILL_INPUT_MASTER_MAX) + return -EINVAL; + return input_register_handler(&rfkill_handler); } @@ -268,6 +419,7 @@ static void __exit rfkill_handler_exit(void) { input_unregister_handler(&rfkill_handler); flush_scheduled_work(); + rfkill_remove_epo_lock(); } module_init(rfkill_handler_init); diff --git a/net/rfkill/rfkill-input.h b/net/rfkill/rfkill-input.h index d1e03e85cbed..fe8df6b5b935 100644 --- a/net/rfkill/rfkill-input.h +++ b/net/rfkill/rfkill-input.h @@ -14,6 +14,8 @@ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state); void rfkill_epo(void); void rfkill_restore_states(void); +void rfkill_remove_epo_lock(void); +bool rfkill_is_epo_lock_active(void); enum rfkill_state rfkill_get_global_state(const enum rfkill_type type); #endif /* __RFKILL_INPUT_H */ diff --git a/net/rfkill/rfkill.c b/net/rfkill/rfkill.c index fdf87d2ab25e..e348eab756f3 100644 --- a/net/rfkill/rfkill.c +++ b/net/rfkill/rfkill.c @@ -51,6 +51,7 @@ struct rfkill_gsw_state { static struct rfkill_gsw_state rfkill_global_states[RFKILL_TYPE_MAX]; static unsigned long rfkill_states_lockdflt[BITS_TO_LONGS(RFKILL_TYPE_MAX)]; +static bool rfkill_epo_lock_active; static BLOCKING_NOTIFIER_HEAD(rfkill_notifier_list); @@ -264,11 +265,14 @@ static void __rfkill_switch_all(const enum rfkill_type type, * * Acquires rfkill_global_mutex and calls __rfkill_switch_all(@type, @state). * Please refer to __rfkill_switch_all() for details. + * + * Does nothing if the EPO lock is active. */ void rfkill_switch_all(enum rfkill_type type, enum rfkill_state state) { mutex_lock(&rfkill_global_mutex); - __rfkill_switch_all(type, state); + if (!rfkill_epo_lock_active) + __rfkill_switch_all(type, state); mutex_unlock(&rfkill_global_mutex); } EXPORT_SYMBOL(rfkill_switch_all); @@ -289,6 +293,7 @@ void rfkill_epo(void) mutex_lock(&rfkill_global_mutex); + rfkill_epo_lock_active = true; list_for_each_entry(rfkill, &rfkill_list, node) { mutex_lock(&rfkill->mutex); rfkill_toggle_radio(rfkill, RFKILL_STATE_SOFT_BLOCKED, 1); @@ -317,12 +322,42 @@ void rfkill_restore_states(void) mutex_lock(&rfkill_global_mutex); + rfkill_epo_lock_active = false; for (i = 0; i < RFKILL_TYPE_MAX; i++) __rfkill_switch_all(i, rfkill_global_states[i].default_state); mutex_unlock(&rfkill_global_mutex); } EXPORT_SYMBOL_GPL(rfkill_restore_states); +/** + * rfkill_remove_epo_lock - unlock state changes + * + * Used by rfkill-input manually unlock state changes, when + * the EPO switch is deactivated. + */ +void rfkill_remove_epo_lock(void) +{ + mutex_lock(&rfkill_global_mutex); + rfkill_epo_lock_active = false; + mutex_unlock(&rfkill_global_mutex); +} +EXPORT_SYMBOL_GPL(rfkill_remove_epo_lock); + +/** + * rfkill_is_epo_lock_active - returns true EPO is active + * + * Returns 0 (false) if there is NOT an active EPO contidion, + * and 1 (true) if there is an active EPO contition, which + * locks all radios in one of the BLOCKED states. + * + * Can be called in atomic context. + */ +bool rfkill_is_epo_lock_active(void) +{ + return rfkill_epo_lock_active; +} +EXPORT_SYMBOL_GPL(rfkill_is_epo_lock_active); + /** * rfkill_get_global_state - returns global state for a type * @type: the type to get the global state of @@ -447,7 +482,12 @@ static ssize_t rfkill_state_store(struct device *dev, error = mutex_lock_killable(&rfkill->mutex); if (error) return error; - error = rfkill_toggle_radio(rfkill, state, 0); + + if (!rfkill_epo_lock_active) + error = rfkill_toggle_radio(rfkill, state, 0); + else + error = -EPERM; + mutex_unlock(&rfkill->mutex); return error ? error : count; @@ -491,7 +531,7 @@ static ssize_t rfkill_claim_store(struct device *dev, return error; if (rfkill->user_claim != claim) { - if (!claim) { + if (!claim && !rfkill_epo_lock_active) { mutex_lock(&rfkill->mutex); rfkill_toggle_radio(rfkill, rfkill_global_states[rfkill->type].current_state, -- cgit v1.2.3 From 5c7f9b7363bfd10e40cf1a28dfc9048417df7028 Mon Sep 17 00:00:00 2001 From: Tim Gardner Date: Tue, 14 Oct 2008 10:38:03 -0600 Subject: ipw2x00: change default policy for auto-associate Do not attempt association until directed to do so by a user space application. In particular, this avoids race conditions with NetworkManager association state. Signed-off-by: Tim Gardner Acked-by: Dan Williams Signed-off-by: John W. Linville --- Documentation/networking/README.ipw2200 | 2 +- drivers/net/wireless/ipw2100.c | 4 ++-- drivers/net/wireless/ipw2200.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/README.ipw2200 b/Documentation/networking/README.ipw2200 index 4f2a40f1dbc6..80c728522c4c 100644 --- a/Documentation/networking/README.ipw2200 +++ b/Documentation/networking/README.ipw2200 @@ -147,7 +147,7 @@ Where the supported parameter are: driver. If disabled, the driver will not attempt to scan for and associate to a network until it has been configured with one or more properties for the target network, for example configuring - the network SSID. Default is 1 (auto-associate) + the network SSID. Default is 0 (do not auto-associate) Example: % modprobe ipw2200 associate=0 diff --git a/drivers/net/wireless/ipw2100.c b/drivers/net/wireless/ipw2100.c index 6e988d2486a7..079dbd07e2f6 100644 --- a/drivers/net/wireless/ipw2100.c +++ b/drivers/net/wireless/ipw2100.c @@ -185,7 +185,7 @@ MODULE_LICENSE("GPL"); static int debug = 0; static int mode = 0; static int channel = 0; -static int associate = 1; +static int associate = 0; static int disable = 0; #ifdef CONFIG_PM static struct ipw2100_fw ipw2100_firmware; @@ -201,7 +201,7 @@ module_param(disable, int, 0444); MODULE_PARM_DESC(debug, "debug level"); MODULE_PARM_DESC(mode, "network mode (0=BSS,1=IBSS,2=Monitor)"); MODULE_PARM_DESC(channel, "channel"); -MODULE_PARM_DESC(associate, "auto associate when scanning (default on)"); +MODULE_PARM_DESC(associate, "auto associate when scanning (default off)"); MODULE_PARM_DESC(disable, "manually disable the radio (default 0 [radio on])"); static u32 ipw2100_debug_level = IPW_DL_NONE; diff --git a/drivers/net/wireless/ipw2200.c b/drivers/net/wireless/ipw2200.c index 13633d8274a3..6ec6de2960ee 100644 --- a/drivers/net/wireless/ipw2200.c +++ b/drivers/net/wireless/ipw2200.c @@ -87,7 +87,7 @@ static int channel = 0; static int mode = 0; static u32 ipw_debug_level; -static int associate = 1; +static int associate; static int auto_create = 1; static int led = 0; static int disable = 0; @@ -11913,7 +11913,7 @@ module_param(disable, int, 0444); MODULE_PARM_DESC(disable, "manually disable the radio (default 0 [radio on])"); module_param(associate, int, 0444); -MODULE_PARM_DESC(associate, "auto associate when scanning (default on)"); +MODULE_PARM_DESC(associate, "auto associate when scanning (default off)"); module_param(auto_create, int, 0444); MODULE_PARM_DESC(auto_create, "auto create adhoc network (default on)"); -- cgit v1.2.3 From d2372b315289aec9f565a855023c40654a5bff68 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 24 Oct 2008 20:32:20 +0200 Subject: wireless: make regdom passing semantics simpler The regdom struct is given to the core, so it might as well free it in error conditions. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- Documentation/networking/regulatory.txt | 13 +++---------- include/net/wireless.h | 3 +-- net/wireless/nl80211.c | 5 +---- net/wireless/reg.c | 9 +++++---- 4 files changed, 10 insertions(+), 20 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index a96989a8ff35..357d4ba4f135 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -167,7 +167,6 @@ struct ieee80211_regdomain mydriver_jp_regdom = { Then in some part of your code after your wiphy has been registered: - int r; struct ieee80211_regdomain *rd; int size_of_regd; int num_rules = mydriver_jp_regdom.n_reg_rules; @@ -178,17 +177,11 @@ Then in some part of your code after your wiphy has been registered: rd = kzalloc(size_of_regd, GFP_KERNEL); if (!rd) - return -ENOMEM; + return -ENOMEM; memcpy(rd, &mydriver_jp_regdom, sizeof(struct ieee80211_regdomain)); - for (i=0; i < num_rules; i++) { + for (i=0; i < num_rules; i++) memcpy(&rd->reg_rules[i], &mydriver_jp_regdom.reg_rules[i], sizeof(struct ieee80211_reg_rule)); - } - r = regulatory_hint(hw->wiphy, NULL, rd); - if (r) { - kfree(rd); - return r; - } - + return regulatory_hint(hw->wiphy, NULL, rd); diff --git a/include/net/wireless.h b/include/net/wireless.h index 061fe5017e5c..6e3ea0159045 100644 --- a/include/net/wireless.h +++ b/include/net/wireless.h @@ -358,8 +358,7 @@ ieee80211_get_channel(struct wiphy *wiphy, int freq) * for a regulatory domain structure for the respective country. If * a regulatory domain is build and passed you should set the alpha2 * if possible, otherwise set it to the special value of "99" which tells - * the wireless core it is unknown. If you pass a built regulatory domain - * and we return non zero you are in charge of kfree()'ing the structure. + * the wireless core it is unknown. * * Returns -EALREADY if *a regulatory domain* has already been set. Note that * this could be by another driver. It is safe for drivers to continue if diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 9a16e9e6c5ca..f82cc9aa6908 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1935,12 +1935,9 @@ static int nl80211_set_reg(struct sk_buff *skb, struct genl_info *info) mutex_lock(&cfg80211_drv_mutex); r = set_regdom(rd); mutex_unlock(&cfg80211_drv_mutex); - if (r) - goto bad_reg; - return r; -bad_reg: + bad_reg: kfree(rd); return -EINVAL; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 00c326b66c03..038f8f133c54 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -605,7 +605,6 @@ int __regulatory_hint(struct wiphy *wiphy, enum reg_set_by set_by, return r; } -/* If rd is not NULL and if this call fails the caller must free it */ int regulatory_hint(struct wiphy *wiphy, const char *alpha2, struct ieee80211_regdomain *rd) { @@ -690,6 +689,7 @@ void print_regdomain_info(const struct ieee80211_regdomain *rd) print_rd_rules(rd); } +/* Takes ownership of rd only if it doesn't fail */ static int __set_regdom(const struct ieee80211_regdomain *rd) { /* Some basic sanity checks first */ @@ -750,16 +750,17 @@ static int __set_regdom(const struct ieee80211_regdomain *rd) /* Use this call to set the current regulatory domain. Conflicts with * multiple drivers can be ironed out later. Caller must've already - * kmalloc'd the rd structure. If this calls fails you should kfree() - * the passed rd. Caller must hold cfg80211_drv_mutex */ + * kmalloc'd the rd structure. Caller must hold cfg80211_drv_mutex */ int set_regdom(const struct ieee80211_regdomain *rd) { int r; /* Note that this doesn't update the wiphys, this is done below */ r = __set_regdom(rd); - if (r) + if (r) { + kfree(rd); return r; + } /* This would make this whole thing pointless */ BUG_ON(rd != cfg80211_regdomain); -- cgit v1.2.3 From be3d48106c1e5d075784e5e67928a6b5ffc0f3b6 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 24 Oct 2008 20:32:21 +0200 Subject: wireless: remove struct regdom hinting The code needs to be split out and cleaned up, so as a first step remove the capability, to add it back in a subsequent patch as a separate function. Also remove the publically facing return value of the function and the wiphy argument. A number of internal functions go from being generic helpers to just being used for alpha2 setting. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville --- Documentation/networking/regulatory.txt | 11 +++--- drivers/net/wireless/zd1211rw/zd_mac.c | 2 +- include/net/wireless.h | 23 +++--------- net/wireless/nl80211.c | 2 +- net/wireless/reg.c | 63 +++++++++------------------------ net/wireless/reg.h | 23 ++++-------- 6 files changed, 36 insertions(+), 88 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/regulatory.txt b/Documentation/networking/regulatory.txt index 357d4ba4f135..dcf31648414a 100644 --- a/Documentation/networking/regulatory.txt +++ b/Documentation/networking/regulatory.txt @@ -131,11 +131,13 @@ are expected to do this during initialization. r = zd_reg2alpha2(mac->regdomain, alpha2); if (!r) - regulatory_hint(hw->wiphy, alpha2, NULL); + regulatory_hint(hw->wiphy, alpha2); Example code - drivers providing a built in regulatory domain: -------------------------------------------------------------- +[NOTE: This API is not currently available, it can be added when required] + If you have regulatory information you can obtain from your driver and you *need* to use this we let you build a regulatory domain structure and pass it to the wireless core. To do this you should @@ -182,6 +184,7 @@ Then in some part of your code after your wiphy has been registered: memcpy(rd, &mydriver_jp_regdom, sizeof(struct ieee80211_regdomain)); for (i=0; i < num_rules; i++) - memcpy(&rd->reg_rules[i], &mydriver_jp_regdom.reg_rules[i], - sizeof(struct ieee80211_reg_rule)); - return regulatory_hint(hw->wiphy, NULL, rd); + memcpy(&rd->reg_rules[i], + &mydriver_jp_regdom.reg_rules[i], + sizeof(struct ieee80211_reg_rule)); + regulatory_struct_hint(rd); diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c index 2f0802b29c4b..07513e48b8f2 100644 --- a/drivers/net/wireless/zd1211rw/zd_mac.c +++ b/drivers/net/wireless/zd1211rw/zd_mac.c @@ -171,7 +171,7 @@ int zd_mac_init_hw(struct ieee80211_hw *hw) r = zd_reg2alpha2(mac->regdomain, alpha2); if (!r) - regulatory_hint(hw->wiphy, alpha2, NULL); + regulatory_hint(hw->wiphy, alpha2); r = 0; disable_int: diff --git a/include/net/wireless.h b/include/net/wireless.h index 6e3ea0159045..41294c5f6f8f 100644 --- a/include/net/wireless.h +++ b/include/net/wireless.h @@ -342,34 +342,19 @@ ieee80211_get_channel(struct wiphy *wiphy, int freq) /** * regulatory_hint - driver hint to the wireless core a regulatory domain - * @wiphy: the driver's very own &struct wiphy + * @wiphy: the wireless device giving the hint (used only for reporting + * conflicts) * @alpha2: the ISO/IEC 3166 alpha2 the driver claims its regulatory domain * should be in. If @rd is set this should be NULL. Note that if you * set this to NULL you should still set rd->alpha2 to some accepted * alpha2. - * @rd: a complete regulatory domain provided by the driver. If passed - * the driver does not need to worry about freeing it. * * Wireless drivers can use this function to hint to the wireless core * what it believes should be the current regulatory domain by * giving it an ISO/IEC 3166 alpha2 country code it knows its regulatory * domain should be in or by providing a completely build regulatory domain. * If the driver provides an ISO/IEC 3166 alpha2 userspace will be queried - * for a regulatory domain structure for the respective country. If - * a regulatory domain is build and passed you should set the alpha2 - * if possible, otherwise set it to the special value of "99" which tells - * the wireless core it is unknown. - * - * Returns -EALREADY if *a regulatory domain* has already been set. Note that - * this could be by another driver. It is safe for drivers to continue if - * -EALREADY is returned, if drivers are not capable of world roaming they - * should not register more channels than they support. Right now we only - * support listening to the first driver hint. If the driver is capable - * of world roaming but wants to respect its own EEPROM mappings for - * specific regulatory domains it should register the @reg_notifier callback - * on the &struct wiphy. Returns 0 if the hint went through fine or through an - * intersection operation. Otherwise a standard error code is returned. + * for a regulatory domain structure for the respective country. */ -extern int regulatory_hint(struct wiphy *wiphy, - const char *alpha2, struct ieee80211_regdomain *rd); +extern void regulatory_hint(struct wiphy *wiphy, const char *alpha2); #endif /* __NET_WIRELESS_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f82cc9aa6908..5e1d658a8b5a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -1695,7 +1695,7 @@ static int nl80211_req_set_reg(struct sk_buff *skb, struct genl_info *info) return -EINVAL; #endif mutex_lock(&cfg80211_drv_mutex); - r = __regulatory_hint(NULL, REGDOM_SET_BY_USER, data, NULL); + r = __regulatory_hint(NULL, REGDOM_SET_BY_USER, data); mutex_unlock(&cfg80211_drv_mutex); return r; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 038f8f133c54..dc10071deaaa 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -42,7 +42,10 @@ #include "core.h" #include "reg.h" -/* wiphy is set if this request's initiator is REGDOM_SET_BY_DRIVER */ +/* + * wiphy is set if this request's initiator is + * REGDOM_SET_BY_COUNTRY_IE or _DRIVER + */ struct regulatory_request { struct wiphy *wiphy; enum reg_set_by initiator; @@ -298,7 +301,7 @@ static int call_crda(const char *alpha2) /* This has the logic which determines when a new request * should be ignored. */ static int ignore_request(struct wiphy *wiphy, enum reg_set_by set_by, - char *alpha2, struct ieee80211_regdomain *rd) + const char *alpha2) { /* All initial requests are respected */ if (!last_request) @@ -343,22 +346,8 @@ static int ignore_request(struct wiphy *wiphy, enum reg_set_by set_by, return 1; case REGDOM_SET_BY_DRIVER: BUG_ON(!wiphy); - if (last_request->initiator == REGDOM_SET_BY_DRIVER) { - /* Two separate drivers hinting different things, - * this is possible if you have two devices present - * on a system with different EEPROM regulatory - * readings. XXX: Do intersection, we support only - * the first regulatory hint for now */ - if (last_request->wiphy != wiphy) - return -EALREADY; - if (rd) - return -EALREADY; - /* Driver should not be trying to hint different - * regulatory domains! */ - BUG_ON(!alpha2_equal(alpha2, - cfg80211_regdomain->alpha2)); + if (last_request->initiator == REGDOM_SET_BY_DRIVER) return -EALREADY; - } if (last_request->initiator == REGDOM_SET_BY_CORE) return 0; /* XXX: Handle intersection, and add the @@ -557,40 +546,32 @@ void wiphy_update_regulatory(struct wiphy *wiphy, enum reg_set_by setby) /* Caller must hold &cfg80211_drv_mutex */ int __regulatory_hint(struct wiphy *wiphy, enum reg_set_by set_by, - const char *alpha2, struct ieee80211_regdomain *rd) + const char *alpha2) { struct regulatory_request *request; - char *rd_alpha2; int r = 0; - r = ignore_request(wiphy, set_by, (char *) alpha2, rd); + r = ignore_request(wiphy, set_by, alpha2); if (r) return r; - if (rd) - rd_alpha2 = rd->alpha2; - else - rd_alpha2 = (char *) alpha2; - switch (set_by) { case REGDOM_SET_BY_CORE: case REGDOM_SET_BY_COUNTRY_IE: case REGDOM_SET_BY_DRIVER: case REGDOM_SET_BY_USER: request = kzalloc(sizeof(struct regulatory_request), - GFP_KERNEL); + GFP_KERNEL); if (!request) return -ENOMEM; - request->alpha2[0] = rd_alpha2[0]; - request->alpha2[1] = rd_alpha2[1]; + request->alpha2[0] = alpha2[0]; + request->alpha2[1] = alpha2[1]; request->initiator = set_by; request->wiphy = wiphy; kfree(last_request); last_request = request; - if (rd) - break; r = call_crda(alpha2); #ifndef CONFIG_WIRELESS_OLD_REGULATORY if (r) @@ -605,25 +586,13 @@ int __regulatory_hint(struct wiphy *wiphy, enum reg_set_by set_by, return r; } -int regulatory_hint(struct wiphy *wiphy, const char *alpha2, - struct ieee80211_regdomain *rd) +void regulatory_hint(struct wiphy *wiphy, const char *alpha2) { - int r; - BUG_ON(!rd && !alpha2); + BUG_ON(!alpha2); mutex_lock(&cfg80211_drv_mutex); - - r = __regulatory_hint(wiphy, REGDOM_SET_BY_DRIVER, alpha2, rd); - if (r || !rd) - goto unlock_and_exit; - - /* If the driver passed a regulatory domain we skipped asking - * userspace for one so we can now go ahead and set it */ - r = set_regdom(rd); - -unlock_and_exit: + __regulatory_hint(wiphy, REGDOM_SET_BY_DRIVER, alpha2); mutex_unlock(&cfg80211_drv_mutex); - return r; } EXPORT_SYMBOL(regulatory_hint); @@ -792,11 +761,11 @@ int regulatory_init(void) * that is not a valid ISO / IEC 3166 alpha2 */ if (ieee80211_regdom[0] != 'E' || ieee80211_regdom[1] != 'U') err = __regulatory_hint(NULL, REGDOM_SET_BY_CORE, - ieee80211_regdom, NULL); + ieee80211_regdom); #else cfg80211_regdomain = cfg80211_world_regdom; - err = __regulatory_hint(NULL, REGDOM_SET_BY_CORE, "00", NULL); + err = __regulatory_hint(NULL, REGDOM_SET_BY_CORE, "00"); if (err) printk(KERN_ERR "cfg80211: calling CRDA failed - " "unable to update world regulatory domain, " diff --git a/net/wireless/reg.h b/net/wireless/reg.h index 0c1572b92fef..c9b6b6358bbe 100644 --- a/net/wireless/reg.h +++ b/net/wireless/reg.h @@ -11,30 +11,21 @@ int set_regdom(const struct ieee80211_regdomain *rd); /** * __regulatory_hint - hint to the wireless core a regulatory domain - * @wiphy: if a driver is providing the hint this is the driver's very - * own &struct wiphy + * @wiphy: if the hint comes from country information from an AP, this + * is required to be set to the wiphy that received the information * @alpha2: the ISO/IEC 3166 alpha2 being claimed the regulatory domain - * should be in. If @rd is set this should be NULL - * @rd: a complete regulatory domain, if passed the caller need not worry - * about freeing it + * should be in. * * The Wireless subsystem can use this function to hint to the wireless core * what it believes should be the current regulatory domain by * giving it an ISO/IEC 3166 alpha2 country code it knows its regulatory - * domain should be in or by providing a completely build regulatory domain. + * domain should be in. * - * Returns -EALREADY if *a regulatory domain* has already been set. Note that - * this could be by another driver. It is safe for drivers to continue if - * -EALREADY is returned, if drivers are not capable of world roaming they - * should not register more channels than they support. Right now we only - * support listening to the first driver hint. If the driver is capable - * of world roaming but wants to respect its own EEPROM mappings for - * specific regulatory domains it should register the @reg_notifier callback - * on the &struct wiphy. Returns 0 if the hint went through fine or through an - * intersection operation. Otherwise a standard error code is returned. + * Returns zero if all went fine, %-EALREADY if a regulatory domain had + * already been set or other standard error codes. * */ extern int __regulatory_hint(struct wiphy *wiphy, enum reg_set_by set_by, - const char *alpha2, struct ieee80211_regdomain *rd); + const char *alpha2); #endif /* __NET_WIRELESS_REG_H */ -- cgit v1.2.3 From 3f8b4b13785c2737413d3241c21c7c86a41535ef Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Wed, 22 Oct 2008 11:19:48 +0000 Subject: bonding: update docs to correctly reflect arp_ip_target behavior This documentation patch hopes to clarify that the '+' was only needed for Fedora 7 and Red Hat Enterprise Linux 5.0 and 5.1. After that the IP addreses could be added as a comma separated list just like the module option. Signed-off-by: Andy Gospodarek Signed-off-by: Jeff Garzik --- Documentation/networking/bonding.txt | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 688dfe1e6b70..d733a428eff6 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -922,17 +922,19 @@ USERCTL=no NETMASK, NETWORK and BROADCAST) to match your network configuration. For later versions of initscripts, such as that found with Fedora -7 and Red Hat Enterprise Linux version 5 (or later), it is possible, and, -indeed, preferable, to specify the bonding options in the ifcfg-bond0 +7 (or later) and Red Hat Enterprise Linux version 5 (or later), it is possible, +and, indeed, preferable, to specify the bonding options in the ifcfg-bond0 file, e.g. a line of the format: -BONDING_OPTS="mode=active-backup arp_interval=60 arp_ip_target=+192.168.1.254" +BONDING_OPTS="mode=active-backup arp_interval=60 arp_ip_target=192.168.1.254" will configure the bond with the specified options. The options specified in BONDING_OPTS are identical to the bonding module parameters -except for the arp_ip_target field. Each target should be included as a -separate option and should be preceded by a '+' to indicate it should be -added to the list of queried targets, e.g., +except for the arp_ip_target field when using versions of initscripts older +than and 8.57 (Fedora 8) and 8.45.19 (Red Hat Enterprise Linux 5.2). When +using older versions each target should be included as a separate option and +should be preceded by a '+' to indicate it should be added to the list of +queried targets, e.g., arp_ip_target=+192.168.1.1 arp_ip_target=+192.168.1.2 @@ -940,7 +942,7 @@ added to the list of queried targets, e.g., options via BONDING_OPTS, it is not necessary to edit /etc/modules.conf or /etc/modprobe.conf. - For older versions of initscripts that do not support + For even older versions of initscripts that do not support BONDING_OPTS, it is necessary to edit /etc/modules.conf (or /etc/modprobe.conf, depending upon your distro) to load the bonding module with your desired options when the bond0 interface is brought up. The -- cgit v1.2.3 From 305d552accae6afb859c493ebc7d98ca3371dae2 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Tue, 4 Nov 2008 17:51:14 -0800 Subject: bonding: send IPv6 neighbor advertisement on failover This patch adds better IPv6 failover support for bonding devices, especially when in active-backup mode and there are only IPv6 addresses configured, as reported by Alex Sidorenko. - Creates a new file, net/drivers/bonding/bond_ipv6.c, for the IPv6-specific routines. Both regular bonds and VLANs over bonds are supported. - Adds a new tunable, num_unsol_na, to limit the number of unsolicited IPv6 Neighbor Advertisements that are sent on a failover event. Default is 1. - Creates two new IPv6 neighbor discovery functions: ndisc_build_skb() ndisc_send_skb() These were required to support VLANs since we have to be able to add the VLAN id to the skb since ndisc_send_na() and friends shouldn't be asked to do this. These two routines are basically __ndisc_send() split into two pieces, in a slightly different order. - Updates Documentation/networking/bonding.txt and bumps the rev of bond support to 3.4.0. On failover, this new code will generate one packet: - An unsolicited IPv6 Neighbor Advertisement, which helps the switch learn that the address has moved to the new slave. Testing has shown that sending just the NA results in pretty good behavior when in active-back mode, I saw no lost ping packets for example. Signed-off-by: Brian Haley Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- Documentation/networking/bonding.txt | 10 ++ drivers/net/Kconfig | 1 + drivers/net/bonding/Makefile | 3 + drivers/net/bonding/bond_ipv6.c | 218 +++++++++++++++++++++++++++++++++++ drivers/net/bonding/bond_main.c | 33 +++++- drivers/net/bonding/bond_sysfs.c | 42 +++++++ drivers/net/bonding/bonding.h | 34 +++++- include/net/ndisc.h | 14 +++ net/ipv6/ndisc.c | 92 ++++++++++----- 9 files changed, 416 insertions(+), 31 deletions(-) create mode 100644 drivers/net/bonding/bond_ipv6.c (limited to 'Documentation') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index d733a428eff6..3f4d0fae7081 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -551,6 +551,16 @@ num_grat_arp affects only the active-backup mode. This option was added for bonding version 3.3.0. +num_unsol_na + + Specifies the number of unsolicited IPv6 Neighbor Advertisements + to be issued after a failover event. One unsolicited NA is issued + immediately after the failover. + + The valid range is 0 - 255; the default value is 1. This option + affects only the active-backup mode. This option was added for + bonding version 3.4.0. + primary A string (eth0, eth2, etc) specifying which slave is the diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 0f3e6b2d2808..f1d0a1371695 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -61,6 +61,7 @@ config DUMMY config BONDING tristate "Bonding driver support" depends on INET + depends on IPV6 || IPV6=n ---help--- Say 'Y' or 'M' if you wish to be able to 'bond' multiple Ethernet Channels together. This is called 'Etherchannel' by Cisco, diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile index 5cdae2bc055a..6f9c6faef24c 100644 --- a/drivers/net/bonding/Makefile +++ b/drivers/net/bonding/Makefile @@ -6,3 +6,6 @@ obj-$(CONFIG_BONDING) += bonding.o bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o +ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o +bonding-objs += $(ipv6-y) + diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c new file mode 100644 index 000000000000..7c78b7bf671c --- /dev/null +++ b/drivers/net/bonding/bond_ipv6.c @@ -0,0 +1,218 @@ +/* + * Copyright(c) 2008 Hewlett-Packard Development Company, L.P. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + */ + +//#define BONDING_DEBUG 1 + +#include +#include +#include +#include +#include +#include "bonding.h" + +/* + * Assign bond->master_ipv6 to the next IPv6 address in the list, or + * zero it out if there are none. + */ +static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + + if (!dev) + return; + + idev = in6_dev_get(dev); + if (!idev) + return; + + read_lock_bh(&idev->lock); + ifa = idev->addr_list; + if (ifa) + ipv6_addr_copy(addr, &ifa->addr); + else + ipv6_addr_set(addr, 0, 0, 0, 0); + + read_unlock_bh(&idev->lock); + + in6_dev_put(idev); +} + +static void bond_na_send(struct net_device *slave_dev, + struct in6_addr *daddr, + int router, + unsigned short vlan_id) +{ + struct in6_addr mcaddr; + struct icmp6hdr icmp6h = { + .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, + }; + struct sk_buff *skb; + + icmp6h.icmp6_router = router; + icmp6h.icmp6_solicited = 0; + icmp6h.icmp6_override = 1; + + addrconf_addr_solict_mult(daddr, &mcaddr); + + dprintk("ipv6 na on slave %s: dest %pI6, src %pI6\n", + slave->name, &mcaddr, daddr); + + skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr, + ND_OPT_TARGET_LL_ADDR); + + if (!skb) { + printk(KERN_ERR DRV_NAME ": NA packet allocation failed\n"); + return; + } + + if (vlan_id) { + skb = vlan_put_tag(skb, vlan_id); + if (!skb) { + printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n"); + return; + } + } + + ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h); +} + +/* + * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on + * the bonding master. This will help the switch learn our address + * if in active-backup mode. + * + * Caller must hold curr_slave_lock for read or better + */ +void bond_send_unsolicited_na(struct bonding *bond) +{ + struct slave *slave = bond->curr_active_slave; + struct vlan_entry *vlan; + struct inet6_dev *idev; + int is_router; + + dprintk("bond_send_unsol_na: bond %s slave %s\n", bond->dev->name, + slave ? slave->dev->name : "NULL"); + + if (!slave || !bond->send_unsol_na || + test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) + return; + + bond->send_unsol_na--; + + idev = in6_dev_get(bond->dev); + if (!idev) + return; + + is_router = !!idev->cnf.forwarding; + + in6_dev_put(idev); + + if (!ipv6_addr_any(&bond->master_ipv6)) + bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0); + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (!ipv6_addr_any(&vlan->vlan_ipv6)) { + bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router, + vlan->vlan_id); + } + } +} + +/* + * bond_inet6addr_event: handle inet6addr notifier chain events. + * + * We keep track of device IPv6 addresses primarily to use as source + * addresses in NS probes. + * + * We track one IPv6 for the main device (if it has one). + */ +static int bond_inet6addr_event(struct notifier_block *this, + unsigned long event, + void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + struct net_device *vlan_dev, *event_dev = ifa->idev->dev; + struct bonding *bond; + struct vlan_entry *vlan; + + if (dev_net(event_dev) != &init_net) + return NOTIFY_DONE; + + list_for_each_entry(bond, &bond_dev_list, bond_list) { + if (bond->dev == event_dev) { + switch (event) { + case NETDEV_UP: + if (ipv6_addr_any(&bond->master_ipv6)) + ipv6_addr_copy(&bond->master_ipv6, + &ifa->addr); + return NOTIFY_OK; + case NETDEV_DOWN: + if (ipv6_addr_equal(&bond->master_ipv6, + &ifa->addr)) + bond_glean_dev_ipv6(bond->dev, + &bond->master_ipv6); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } + } + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + vlan_dev = vlan_group_get_device(bond->vlgrp, + vlan->vlan_id); + if (vlan_dev == event_dev) { + switch (event) { + case NETDEV_UP: + if (ipv6_addr_any(&vlan->vlan_ipv6)) + ipv6_addr_copy(&vlan->vlan_ipv6, + &ifa->addr); + return NOTIFY_OK; + case NETDEV_DOWN: + if (ipv6_addr_equal(&vlan->vlan_ipv6, + &ifa->addr)) + bond_glean_dev_ipv6(vlan_dev, + &vlan->vlan_ipv6); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } + } + } + } + return NOTIFY_DONE; +} + +static struct notifier_block bond_inet6addr_notifier = { + .notifier_call = bond_inet6addr_event, +}; + +void bond_register_ipv6_notifier(void) +{ + register_inet6addr_notifier(&bond_inet6addr_notifier); +} + +void bond_unregister_ipv6_notifier(void) +{ + unregister_inet6addr_notifier(&bond_inet6addr_notifier); +} + diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 39575d764974..798d98ce2d97 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -89,6 +89,7 @@ static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int num_grat_arp = 1; +static int num_unsol_na = 1; static int miimon = BOND_LINK_MON_INTERV; static int updelay = 0; static int downdelay = 0; @@ -107,6 +108,8 @@ module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(num_grat_arp, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event"); +module_param(num_unsol_na, int, 0644); +MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); @@ -242,14 +245,13 @@ static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) dprintk("bond: %s, vlan id %d\n", (bond ? bond->dev->name: "None"), vlan_id); - vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL); + vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL); if (!vlan) { return -ENOMEM; } INIT_LIST_HEAD(&vlan->vlan_list); vlan->vlan_id = vlan_id; - vlan->vlan_ip = 0; write_lock_bh(&bond->lock); @@ -1208,6 +1210,9 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond->send_grat_arp = bond->params.num_grat_arp; bond_send_gratuitous_arp(bond); + bond->send_unsol_na = bond->params.num_unsol_na; + bond_send_unsolicited_na(bond); + write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); @@ -2463,6 +2468,12 @@ void bond_mii_monitor(struct work_struct *work) read_unlock(&bond->curr_slave_lock); } + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); + } + if (bond_miimon_inspect(bond)) { read_unlock(&bond->lock); rtnl_lock(); @@ -3158,6 +3169,12 @@ void bond_activebackup_arp_mon(struct work_struct *work) read_unlock(&bond->curr_slave_lock); } + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); + } + if (bond_ab_arp_inspect(bond, delta_in_ticks)) { read_unlock(&bond->lock); rtnl_lock(); @@ -3827,6 +3844,7 @@ static int bond_close(struct net_device *bond_dev) write_lock_bh(&bond->lock); bond->send_grat_arp = 0; + bond->send_unsol_na = 0; /* signal timers not to re-arm */ bond->kill_timers = 1; @@ -4542,6 +4560,7 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) bond->primary_slave = NULL; bond->dev = bond_dev; bond->send_grat_arp = 0; + bond->send_unsol_na = 0; bond->setup_by_slave = 0; INIT_LIST_HEAD(&bond->vlan_list); @@ -4791,6 +4810,13 @@ static int bond_check_params(struct bond_params *params) num_grat_arp = 1; } + if (num_unsol_na < 0 || num_unsol_na > 255) { + printk(KERN_WARNING DRV_NAME + ": Warning: num_unsol_na (%d) not in range 0-255 so it " + "was reset to 1 \n", num_unsol_na); + num_unsol_na = 1; + } + /* reset values for 802.3ad */ if (bond_mode == BOND_MODE_8023AD) { if (!miimon) { @@ -4992,6 +5018,7 @@ static int bond_check_params(struct bond_params *params) params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->num_grat_arp = num_grat_arp; + params->num_unsol_na = num_unsol_na; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->updelay = updelay; @@ -5144,6 +5171,7 @@ static int __init bonding_init(void) register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); + bond_register_ipv6_notifier(); goto out; err: @@ -5166,6 +5194,7 @@ static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); unregister_inetaddr_notifier(&bond_inetaddr_notifier); + bond_unregister_ipv6_notifier(); bond_destroy_sysfs(); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index e400d7dfdfc8..8788e3e33852 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -983,6 +983,47 @@ out: return ret; } static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR, bonding_show_n_grat_arp, bonding_store_n_grat_arp); + +/* + * Show and set the number of unsolicted NA's to send after a failover event. + */ +static ssize_t bonding_show_n_unsol_na(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.num_unsol_na); +} + +static ssize_t bonding_store_n_unsol_na(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value, ret = count; + struct bonding *bond = to_bond(d); + + if (sscanf(buf, "%d", &new_value) != 1) { + printk(KERN_ERR DRV_NAME + ": %s: no num_unsol_na value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0 || new_value > 255) { + printk(KERN_ERR DRV_NAME + ": %s: Invalid num_unsol_na value %d not in range 0-255; rejected.\n", + bond->dev->name, new_value); + ret = -EINVAL; + goto out; + } else { + bond->params.num_unsol_na = new_value; + } +out: + return ret; +} +static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR, bonding_show_n_unsol_na, bonding_store_n_unsol_na); + /* * Show and set the MII monitor interval. There are two tricky bits * here. First, if MII monitoring is activated, then we must disable @@ -1420,6 +1461,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_lacp_rate.attr, &dev_attr_xmit_hash_policy.attr, &dev_attr_num_grat_arp.attr, + &dev_attr_num_unsol_na.attr, &dev_attr_miimon.attr, &dev_attr_primary.attr, &dev_attr_use_carrier.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index ffb668dd6d3b..0491c7c2645b 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -19,16 +19,19 @@ #include #include #include +#include #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.3.0" -#define DRV_RELDATE "June 10, 2008" +#define DRV_VERSION "3.4.0" +#define DRV_RELDATE "October 7, 2008" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" #define BOND_MAX_ARP_TARGETS 16 +extern struct list_head bond_dev_list; + #ifdef BONDING_DEBUG #define dprintk(fmt, args...) \ printk(KERN_DEBUG \ @@ -126,6 +129,7 @@ struct bond_params { int xmit_policy; int miimon; int num_grat_arp; + int num_unsol_na; int arp_interval; int arp_validate; int use_carrier; @@ -148,6 +152,9 @@ struct vlan_entry { struct list_head vlan_list; __be32 vlan_ip; unsigned short vlan_id; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct in6_addr vlan_ipv6; +#endif }; struct slave { @@ -195,6 +202,7 @@ struct bonding { rwlock_t curr_slave_lock; s8 kill_timers; s8 send_grat_arp; + s8 send_unsol_na; s8 setup_by_slave; struct net_device_stats stats; #ifdef CONFIG_PROC_FS @@ -218,6 +226,9 @@ struct bonding { struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct in6_addr master_ipv6; +#endif }; /** @@ -341,5 +352,24 @@ extern struct bond_parm_tbl xmit_hashtype_tbl[]; extern struct bond_parm_tbl arp_validate_tbl[]; extern struct bond_parm_tbl fail_over_mac_tbl[]; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +void bond_send_unsolicited_na(struct bonding *bond); +void bond_register_ipv6_notifier(void); +void bond_unregister_ipv6_notifier(void); +#else +static inline void bond_send_unsolicited_na(struct bonding *bond) +{ + return; +} +static inline void bond_register_ipv6_notifier(void) +{ + return; +} +static inline void bond_unregister_ipv6_notifier(void) +{ + return; +} +#endif + #endif /* _LINUX_BONDING_H */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 11dd0137c6a5..ce532f2222ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -108,6 +108,20 @@ extern void ndisc_send_redirect(struct sk_buff *skb, extern int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir); +extern struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo); + +extern void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h); + /* diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2a6752dae09d..fbf451c0d77a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -437,38 +437,20 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -/* - * Send a Neighbour Advertisement - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) +struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { - struct flowi fl; - struct dst_entry *dst; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; - struct inet6_dev *idev; int len; int err; - u8 *opt, type; - - type = icmp6h->icmp6_type; - - icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); - - dst = icmp6_dst_alloc(dev, neigh, daddr); - if (!dst) - return; - - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) - return; + u8 *opt; if (!dev->addr_len) llinfo = 0; @@ -485,8 +467,7 @@ static void __ndisc_send(struct net_device *dev, ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __func__); - dst_release(dst); - return; + return NULL; } skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -513,6 +494,42 @@ static void __ndisc_send(struct net_device *dev, csum_partial((__u8 *) hdr, len, 0)); + return skb; +} + +EXPORT_SYMBOL(ndisc_build_skb); + +void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) +{ + struct flowi fl; + struct dst_entry *dst; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.ndisc_sk; + struct inet6_dev *idev; + int err; + u8 type; + + type = icmp6h->icmp6_type; + + icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); + + dst = icmp6_dst_alloc(dev, neigh, daddr); + if (!dst) { + kfree_skb(skb); + return; + } + + err = xfrm_lookup(&dst, &fl, NULL, 0); + if (err < 0) { + kfree_skb(skb); + return; + } + skb->dst = dst; idev = in6_dev_get(dst->dev); @@ -529,6 +546,27 @@ static void __ndisc_send(struct net_device *dev, in6_dev_put(idev); } +EXPORT_SYMBOL(ndisc_send_skb); + +/* + * Send a Neighbour Discover packet + */ +static void __ndisc_send(struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, const struct in6_addr *target, + int llinfo) +{ + struct sk_buff *skb; + + skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); + if (!skb) + return; + + ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); +} + static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, -- cgit v1.2.3 From fd989c83325cb34795bc4d4aa6b13c06f90eac99 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Tue, 4 Nov 2008 17:51:16 -0800 Subject: bonding: alternate agg selection policies for 802.3ad This patch implements alternative aggregator selection policies for 802.3ad. The existing policy, now termed "stable," selects the active aggregator by greatest bandwidth, and only reselects a new aggregator if the active aggregator is entirely disabled (no more ports or all ports down). This patch adds two new policies: bandwidth and count, selecting the active aggregator by total bandwidth (like the stable policy) or by the number of ports in the aggregator, respectively. These two policies also differ from the stable policy in that they will reselect the active aggregator when availability-related changes occur in the bond (e.g., link state change). This permits "gang failover" within 802.3ad, allowing redundant aggregators along parallel paths to always maintain the "best" aggregator as the active aggregator (rather than having to wait for the active to entirely fail). This patch also updates the driver version to 3.5.0. Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- Documentation/networking/bonding.txt | 42 +++++ drivers/net/bonding/bond_3ad.c | 326 ++++++++++++++++++++++------------- drivers/net/bonding/bond_3ad.h | 10 +- drivers/net/bonding/bond_main.c | 30 ++++ drivers/net/bonding/bond_sysfs.c | 49 ++++++ drivers/net/bonding/bonding.h | 5 +- 6 files changed, 333 insertions(+), 129 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 3f4d0fae7081..5ede7473b425 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -194,6 +194,48 @@ or, for backwards compatibility, the option value. E.g., The parameters are as follows: +ad_select + + Specifies the 802.3ad aggregation selection logic to use. The + possible values and their effects are: + + stable or 0 + + The active aggregator is chosen by largest aggregate + bandwidth. + + Reselection of the active aggregator occurs only when all + slaves of the active aggregator are down or the active + aggregator has no slaves. + + This is the default value. + + bandwidth or 1 + + The active aggregator is chosen by largest aggregate + bandwidth. Reselection occurs if: + + - A slave is added to or removed from the bond + + - Any slave's link state changes + + - Any slave's 802.3ad association state changes + + - The bond's adminstrative state changes to up + + count or 2 + + The active aggregator is chosen by the largest number of + ports (slaves). Reselection occurs as described under the + "bandwidth" setting, above. + + The bandwidth and count selection policies permit failover of + 802.3ad aggregations when partial failure of the active aggregator + occurs. This keeps the aggregator with the highest availability + (either in bandwidth or in number of ports) active at all times. + + This option was added in bonding version 3.4.0. + arp_interval Specifies the ARP link monitoring frequency in milliseconds. diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 6106660a4a44..ba1372f2f144 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -236,6 +237,17 @@ static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) return &(SLAVE_AD_INFO(slave->next).aggregator); } +/* + * __agg_has_partner + * + * Return nonzero if aggregator has a partner (denoted by a non-zero ether + * address for the partner). Return 0 if not. + */ +static inline int __agg_has_partner(struct aggregator *agg) +{ + return !is_zero_ether_addr(agg->partner_system.mac_addr_value); +} + /** * __disable_port - disable the port's slave * @port: the port we're looking at @@ -274,14 +286,14 @@ static inline int __port_is_enabled(struct port *port) * __get_agg_selection_mode - get the aggregator selection mode * @port: the port we're looking at * - * Get the aggregator selection mode. Can be %BANDWIDTH or %COUNT. + * Get the aggregator selection mode. Can be %STABLE, %BANDWIDTH or %COUNT. */ static inline u32 __get_agg_selection_mode(struct port *port) { struct bonding *bond = __get_bond_by_port(port); if (bond == NULL) { - return AD_BANDWIDTH; + return BOND_AD_STABLE; } return BOND_AD_INFO(bond).agg_select_mode; @@ -1414,9 +1426,82 @@ static void ad_port_selection_logic(struct port *port) // else set ready=FALSE in all aggregator's ports __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); - if (!__check_agg_selection_timer(port) && (aggregator = __get_first_agg(port))) { - ad_agg_selection_logic(aggregator); + aggregator = __get_first_agg(port); + ad_agg_selection_logic(aggregator); +} + +/* + * Decide if "agg" is a better choice for the new active aggregator that + * the current best, according to the ad_select policy. + */ +static struct aggregator *ad_agg_selection_test(struct aggregator *best, + struct aggregator *curr) +{ + /* + * 0. If no best, select current. + * + * 1. If the current agg is not individual, and the best is + * individual, select current. + * + * 2. If current agg is individual and the best is not, keep best. + * + * 3. Therefore, current and best are both individual or both not + * individual, so: + * + * 3a. If current agg partner replied, and best agg partner did not, + * select current. + * + * 3b. If current agg partner did not reply and best agg partner + * did reply, keep best. + * + * 4. Therefore, current and best both have partner replies or + * both do not, so perform selection policy: + * + * BOND_AD_COUNT: Select by count of ports. If count is equal, + * select by bandwidth. + * + * BOND_AD_STABLE, BOND_AD_BANDWIDTH: Select by bandwidth. + */ + if (!best) + return curr; + + if (!curr->is_individual && best->is_individual) + return curr; + + if (curr->is_individual && !best->is_individual) + return best; + + if (__agg_has_partner(curr) && !__agg_has_partner(best)) + return curr; + + if (!__agg_has_partner(curr) && __agg_has_partner(best)) + return best; + + switch (__get_agg_selection_mode(curr->lag_ports)) { + case BOND_AD_COUNT: + if (curr->num_of_ports > best->num_of_ports) + return curr; + + if (curr->num_of_ports < best->num_of_ports) + return best; + + /*FALLTHROUGH*/ + case BOND_AD_STABLE: + case BOND_AD_BANDWIDTH: + if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) + return curr; + + break; + + default: + printk(KERN_WARNING DRV_NAME + ": %s: Impossible agg select mode %d\n", + curr->slave->dev->master->name, + __get_agg_selection_mode(curr->lag_ports)); + break; } + + return best; } /** @@ -1424,156 +1509,138 @@ static void ad_port_selection_logic(struct port *port) * @aggregator: the aggregator we're looking at * * It is assumed that only one aggregator may be selected for a team. - * The logic of this function is to select (at first time) the aggregator with - * the most ports attached to it, and to reselect the active aggregator only if - * the previous aggregator has no more ports related to it. + * + * The logic of this function is to select the aggregator according to + * the ad_select policy: + * + * BOND_AD_STABLE: select the aggregator with the most ports attached to + * it, and to reselect the active aggregator only if the previous + * aggregator has no more ports related to it. + * + * BOND_AD_BANDWIDTH: select the aggregator with the highest total + * bandwidth, and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. + * + * BOND_AD_COUNT: select the aggregator with largest number of ports + * (slaves), and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. * * FIXME: this function MUST be called with the first agg in the bond, or * __get_active_agg() won't work correctly. This function should be better * called with the bond itself, and retrieve the first agg from it. */ -static void ad_agg_selection_logic(struct aggregator *aggregator) +static void ad_agg_selection_logic(struct aggregator *agg) { - struct aggregator *best_aggregator = NULL, *active_aggregator = NULL; - struct aggregator *last_active_aggregator = NULL, *origin_aggregator; + struct aggregator *best, *active, *origin; struct port *port; - u16 num_of_aggs=0; - origin_aggregator = aggregator; + origin = agg; - //get current active aggregator - last_active_aggregator = __get_active_agg(aggregator); + active = __get_active_agg(agg); + best = active; - // search for the aggregator with the most ports attached to it. do { - // count how many candidate lag's we have - if (aggregator->lag_ports) { - num_of_aggs++; - } - if (aggregator->is_active && !aggregator->is_individual && // if current aggregator is the active aggregator - MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr))) { // and partner answers to 802.3ad PDUs - if (aggregator->num_of_ports) { // if any ports attached to the current aggregator - best_aggregator=NULL; // disregard the best aggregator that was chosen by now - break; // stop the selection of other aggregator if there are any ports attached to this active aggregator - } else { // no ports attached to this active aggregator - aggregator->is_active = 0; // mark this aggregator as not active anymore + agg->is_active = 0; + + if (agg->num_of_ports) + best = ad_agg_selection_test(best, agg); + + } while ((agg = __get_next_agg(agg))); + + if (best && + __get_agg_selection_mode(best->lag_ports) == BOND_AD_STABLE) { + /* + * For the STABLE policy, don't replace the old active + * aggregator if it's still active (it has an answering + * partner) or if both the best and active don't have an + * answering partner. + */ + if (active && active->lag_ports && + active->lag_ports->is_enabled && + (__agg_has_partner(active) || + (!__agg_has_partner(active) && !__agg_has_partner(best)))) { + if (!(!active->actor_oper_aggregator_key && + best->actor_oper_aggregator_key)) { + best = NULL; + active->is_active = 1; } } - if (aggregator->num_of_ports) { // if any ports attached - if (best_aggregator) { // if there is a candidte aggregator - //The reasons for choosing new best aggregator: - // 1. if current agg is NOT individual and the best agg chosen so far is individual OR - // current and best aggs are both individual or both not individual, AND - // 2a. current agg partner reply but best agg partner do not reply OR - // 2b. current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply AND - // current has more ports/bandwidth, or same amount of ports but current has faster ports, THEN - // current agg become best agg so far - - //if current agg is NOT individual and the best agg chosen so far is individual change best_aggregator - if (!aggregator->is_individual && best_aggregator->is_individual) { - best_aggregator=aggregator; - } - // current and best aggs are both individual or both not individual - else if ((aggregator->is_individual && best_aggregator->is_individual) || - (!aggregator->is_individual && !best_aggregator->is_individual)) { - // current and best aggs are both individual or both not individual AND - // current agg partner reply but best agg partner do not reply - if ((MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - best_aggregator=aggregator; - } - // current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply - else if (! (!MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - if ((__get_agg_selection_mode(aggregator->lag_ports) == AD_BANDWIDTH)&& - (__get_agg_bandwidth(aggregator) > __get_agg_bandwidth(best_aggregator))) { - best_aggregator=aggregator; - } else if (__get_agg_selection_mode(aggregator->lag_ports) == AD_COUNT) { - if (((aggregator->num_of_ports > best_aggregator->num_of_ports) && - (aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS))|| - ((aggregator->num_of_ports == best_aggregator->num_of_ports) && - ((u16)(aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS) > - (u16)(best_aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS)))) { - best_aggregator=aggregator; - } - } - } - } - } else { - best_aggregator=aggregator; - } - } - aggregator->is_active = 0; // mark all aggregators as not active anymore - } while ((aggregator = __get_next_agg(aggregator))); - - // if we have new aggregator selected, don't replace the old aggregator if it has an answering partner, - // or if both old aggregator and new aggregator don't have answering partner - if (best_aggregator) { - if (last_active_aggregator && last_active_aggregator->lag_ports && last_active_aggregator->lag_ports->is_enabled && - (MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) || // partner answers OR - (!MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) && // both old and new - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) // partner do not answer - ) { - // if new aggregator has link, and old aggregator does not, replace old aggregator.(do nothing) - // -> don't replace otherwise. - if (!(!last_active_aggregator->actor_oper_aggregator_key && best_aggregator->actor_oper_aggregator_key)) { - best_aggregator=NULL; - last_active_aggregator->is_active = 1; // don't replace good old aggregator + } - } - } + if (best && (best == active)) { + best = NULL; + active->is_active = 1; } // if there is new best aggregator, activate it - if (best_aggregator) { - for (aggregator = __get_first_agg(best_aggregator->lag_ports); - aggregator; - aggregator = __get_next_agg(aggregator)) { - - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - aggregator->aggregator_identifier, aggregator->num_of_ports, - aggregator->actor_oper_aggregator_key, aggregator->partner_oper_aggregator_key, - aggregator->is_individual, aggregator->is_active); + if (best) { + dprintk("best Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); + dprintk("best ports %p slave %p %s\n", + best->lag_ports, best->slave, + best->slave ? best->slave->dev->name : "NULL"); + + for (agg = __get_first_agg(best->lag_ports); agg; + agg = __get_next_agg(agg)) { + + dprintk("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + agg->aggregator_identifier, agg->num_of_ports, + agg->actor_oper_aggregator_key, + agg->partner_oper_aggregator_key, + agg->is_individual, agg->is_active); } // check if any partner replys - if (best_aggregator->is_individual) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: No 802.3ad response from " - "the link partner for any adapters in the bond\n", - best_aggregator->slave->dev->master->name); - } - - // check if there are more than one aggregator - if (num_of_aggs > 1) { - dprintk("Warning: More than one Link Aggregation Group was " - "found in the bond. Only one group will function in the bond\n"); + if (best->is_individual) { + printk(KERN_WARNING DRV_NAME ": %s: Warning: No 802.3ad" + " response from the link partner for any" + " adapters in the bond\n", + best->slave->dev->master->name); } - best_aggregator->is_active = 1; - dprintk("LAG %d choosed as the active LAG\n", best_aggregator->aggregator_identifier); - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - best_aggregator->aggregator_identifier, best_aggregator->num_of_ports, - best_aggregator->actor_oper_aggregator_key, best_aggregator->partner_oper_aggregator_key, - best_aggregator->is_individual, best_aggregator->is_active); + best->is_active = 1; + dprintk("LAG %d chosen as the active LAG\n", + best->aggregator_identifier); + dprintk("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); // disable the ports that were related to the former active_aggregator - if (last_active_aggregator) { - for (port=last_active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + if (active) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { __disable_port(port); } } } - // if the selected aggregator is of join individuals(partner_system is NULL), enable their ports - active_aggregator = __get_active_agg(origin_aggregator); + /* + * if the selected aggregator is of join individuals + * (partner_system is NULL), enable their ports + */ + active = __get_active_agg(origin); - if (active_aggregator) { - if (!MAC_ADDRESS_COMPARE(&(active_aggregator->partner_system), &(null_mac_addr))) { - for (port=active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + if (active) { + if (!__agg_has_partner(active)) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { __enable_port(port); } } } + + if (origin->slave) { + struct bonding *bond; + + bond = bond_get_bond_by_slave(origin->slave); + if (bond) + bond_3ad_set_carrier(bond); + } } /** @@ -1830,6 +1897,19 @@ static void ad_initialize_lacpdu(struct lacpdu *lacpdu) // Check aggregators status in team every T seconds #define AD_AGGREGATOR_SELECTION_TIMER 8 +/* + * bond_3ad_initiate_agg_selection(struct bonding *bond) + * + * Set the aggregation selection timer, to initiate an agg selection in + * the very near future. Called during first initialization, and during + * any down to up transitions of the bond. + */ +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) +{ + BOND_AD_INFO(bond).agg_select_timer = timeout; + BOND_AD_INFO(bond).agg_select_mode = bond->params.ad_select; +} + static u16 aggregator_identifier; /** @@ -1854,9 +1934,9 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas // initialize how many times this module is called in one second(should be about every 100ms) ad_ticks_per_sec = tick_resolution; - // initialize the aggregator selection timer(to activate an aggregation selection after initialize) - BOND_AD_INFO(bond).agg_select_timer = (AD_AGGREGATOR_SELECTION_TIMER * ad_ticks_per_sec); - BOND_AD_INFO(bond).agg_select_mode = AD_BANDWIDTH; + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); } } diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index b5ee45f6d55a..a803fe05f63e 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -42,10 +42,11 @@ typedef struct mac_addr { u8 mac_addr_value[ETH_ALEN]; } mac_addr_t; -typedef enum { - AD_BANDWIDTH = 0, - AD_COUNT -} agg_selection_t; +enum { + BOND_AD_STABLE = 0, + BOND_AD_BANDWIDTH = 1, + BOND_AD_COUNT = 2, +}; // rx machine states(43.4.11 in the 802.3ad standard) typedef enum { @@ -277,6 +278,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas int bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); void bond_3ad_adapter_speed_changed(struct slave *slave); void bond_3ad_adapter_duplex_changed(struct slave *slave); void bond_3ad_handle_link_change(struct slave *slave, char link); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 798d98ce2d97..02de3e031237 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -97,6 +97,7 @@ static int use_carrier = 1; static char *mode = NULL; static char *primary = NULL; static char *lacp_rate = NULL; +static char *ad_select = NULL; static char *xmit_hash_policy = NULL; static int arp_interval = BOND_LINK_ARP_INTERV; static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, }; @@ -130,6 +131,8 @@ MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner " "(slow/fast)"); +module_param(ad_select, charp, 0); +MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)" ", 1 for layer 3+4"); @@ -200,6 +203,13 @@ struct bond_parm_tbl fail_over_mac_tbl[] = { { NULL, -1}, }; +struct bond_parm_tbl ad_select_tbl[] = { +{ "stable", BOND_AD_STABLE}, +{ "bandwidth", BOND_AD_BANDWIDTH}, +{ "count", BOND_AD_COUNT}, +{ NULL, -1}, +}; + /*-------------------------- Forward declarations ---------------------------*/ static void bond_send_gratuitous_arp(struct bonding *bond); @@ -3318,6 +3328,8 @@ static void bond_info_show_master(struct seq_file *seq) seq_puts(seq, "\n802.3ad info\n"); seq_printf(seq, "LACP rate: %s\n", (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + ad_select_tbl[bond->params.ad_select].modename); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { seq_printf(seq, "bond %s has no active aggregator\n", @@ -3824,6 +3836,7 @@ static int bond_open(struct net_device *bond_dev) queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond_register_lacpdu(bond); + bond_3ad_initiate_agg_selection(bond, 1); } return 0; @@ -4763,6 +4776,23 @@ static int bond_check_params(struct bond_params *params) } } + if (ad_select) { + params->ad_select = bond_parse_parm(ad_select, ad_select_tbl); + if (params->ad_select == -1) { + printk(KERN_ERR DRV_NAME + ": Error: Invalid ad_select \"%s\"\n", + ad_select == NULL ? "NULL" : ad_select); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_8023AD) { + printk(KERN_WARNING DRV_NAME + ": ad_select param only affects 802.3ad mode\n"); + } + } else { + params->ad_select = BOND_AD_STABLE; + } + if (max_bonds < 0 || max_bonds > INT_MAX) { printk(KERN_WARNING DRV_NAME ": Warning: max_bonds (%d) not in range %d-%d, so it " diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8788e3e33852..aaf2927b5c38 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -48,6 +48,7 @@ extern struct list_head bond_dev_list; extern struct bond_params bonding_defaults; extern struct bond_parm_tbl bond_mode_tbl[]; extern struct bond_parm_tbl bond_lacp_tbl[]; +extern struct bond_parm_tbl ad_select_tbl[]; extern struct bond_parm_tbl xmit_hashtype_tbl[]; extern struct bond_parm_tbl arp_validate_tbl[]; extern struct bond_parm_tbl fail_over_mac_tbl[]; @@ -944,6 +945,53 @@ out: } static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, bonding_show_lacp, bonding_store_lacp); +static ssize_t bonding_show_ad_select(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + ad_select_tbl[bond->params.ad_select].modename, + bond->params.ad_select); +} + + +static ssize_t bonding_store_ad_select(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value, ret = count; + struct bonding *bond = to_bond(d); + + if (bond->dev->flags & IFF_UP) { + printk(KERN_ERR DRV_NAME + ": %s: Unable to update ad_select because interface " + "is up.\n", bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, ad_select_tbl); + + if (new_value != -1) { + bond->params.ad_select = new_value; + printk(KERN_INFO DRV_NAME + ": %s: Setting ad_select to %s (%d).\n", + bond->dev->name, ad_select_tbl[new_value].modename, + new_value); + } else { + printk(KERN_ERR DRV_NAME + ": %s: Ignoring invalid ad_select value %.*s.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + ret = -EINVAL; + } +out: + return ret; +} + +static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, bonding_show_ad_select, bonding_store_ad_select); + /* * Show and set the number of grat ARP to send after a failover event. */ @@ -1459,6 +1507,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_downdelay.attr, &dev_attr_updelay.attr, &dev_attr_lacp_rate.attr, + &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, &dev_attr_num_grat_arp.attr, &dev_attr_num_unsol_na.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 0491c7c2645b..b5eb8e65b309 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -23,8 +23,8 @@ #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.4.0" -#define DRV_RELDATE "October 7, 2008" +#define DRV_VERSION "3.5.0" +#define DRV_RELDATE "November 4, 2008" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" @@ -137,6 +137,7 @@ struct bond_params { int updelay; int downdelay; int lacp_fast; + int ad_select; char primary[IFNAMSIZ]; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; }; -- cgit v1.2.3 From d90ebcbfa7f5a8b4e20518c9f94c5c4e4cd3c2e5 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Wed, 12 Nov 2008 00:47:26 -0800 Subject: dccp: Query supported CCIDs This provides a data structure to record which CCIDs are locally supported and three accessor functions: - a test function for internal use which is used to validate CCID requests made by the user; - a copy function so that the list can be used for feature-negotiation; - documented getsockopt() support so that the user can query capabilities. The data structure is a table which is filled in at compile-time with the list of available CCIDs (which in turn depends on the Kconfig choices). Using the copy function for cloning the list of supported CCIDs is useful for feature negotiation, since the negotiation is now with the full list of available CCIDs (e.g. {2, 3}) instead of the default value {2}. This means negotiation will not fail if the peer requests to use CCID3 instead of CCID2. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 4 ++++ include/linux/dccp.h | 1 + net/dccp/ccid.c | 48 +++++++++++++++++++++++++++++++++++++++ net/dccp/ccid.h | 5 ++++ net/dccp/feat.c | 4 ++++ net/dccp/proto.c | 2 ++ 6 files changed, 64 insertions(+) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 39131a3c78f8..f0aeb20fa63b 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -57,6 +57,10 @@ can be set before calling bind(). DCCP_SOCKOPT_GET_CUR_MPS is read-only and retrieves the current maximum packet size (application payload size) in bytes, see RFC 4340, section 14. +DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs +supported by the endpoint (see include/linux/dccp.h for symbolic constants). +The caller needs to provide a sufficiently large (> 2) array of type uint8_t. + DCCP_SOCKOPT_SERVER_TIMEWAIT enables the server (listening socket) to hold timewait state when closing the connection (RFC 4340, 8.3). The usual case is that the closing server sends a CloseReq, whereupon the client holds timewait diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 484b8a1fb023..d3ac1bde60b4 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -209,6 +209,7 @@ struct dccp_so_feat { #define DCCP_SOCKOPT_SERVER_TIMEWAIT 6 #define DCCP_SOCKOPT_SEND_CSCOV 10 #define DCCP_SOCKOPT_RECV_CSCOV 11 +#define DCCP_SOCKOPT_AVAILABLE_CCIDS 12 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 8fe931a3d7a1..647cb0614f84 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -13,6 +13,13 @@ #include "ccid.h" +static u8 builtin_ccids[] = { + DCCPC_CCID2, /* CCID2 is supported by default */ +#if defined(CONFIG_IP_DCCP_CCID3) || defined(CONFIG_IP_DCCP_CCID3_MODULE) + DCCPC_CCID3, +#endif +}; + static struct ccid_operations *ccids[CCID_MAX]; #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) static atomic_t ccids_lockct = ATOMIC_INIT(0); @@ -86,6 +93,47 @@ static void ccid_kmem_cache_destroy(struct kmem_cache *slab) } } +/* check that up to @array_len members in @ccid_array are supported */ +bool ccid_support_check(u8 const *ccid_array, u8 array_len) +{ + u8 i, j, found; + + for (i = 0, found = 0; i < array_len; i++, found = 0) { + for (j = 0; !found && j < ARRAY_SIZE(builtin_ccids); j++) + found = (ccid_array[i] == builtin_ccids[j]); + if (!found) + return false; + } + return true; +} + +/** + * ccid_get_builtin_ccids - Provide copy of `builtin' CCID array + * @ccid_array: pointer to copy into + * @array_len: value to return length into + * This function allocates memory - caller must see that it is freed after use. + */ +int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len) +{ + *ccid_array = kmemdup(builtin_ccids, sizeof(builtin_ccids), gfp_any()); + if (*ccid_array == NULL) + return -ENOBUFS; + *array_len = ARRAY_SIZE(builtin_ccids); + return 0; +} + +int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + if (len < sizeof(builtin_ccids)) + return -EINVAL; + + if (put_user(sizeof(builtin_ccids), optlen) || + copy_to_user(optval, builtin_ccids, sizeof(builtin_ccids))) + return -EFAULT; + return 0; +} + int ccid_register(struct ccid_operations *ccid_ops) { int err = -ENOBUFS; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index fdeae7b57319..259f5469d7d0 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -103,6 +103,11 @@ static inline void *ccid_priv(const struct ccid *ccid) return (void *)ccid->ccid_priv; } +extern bool ccid_support_check(u8 const *ccid_array, u8 array_len); +extern int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len); +extern int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, + char __user *, int __user *); + extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp); diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 192d494a3816..f79fb5e33f5e 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -342,6 +342,10 @@ static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local, !dccp_feat_sp_list_ok(feat, sp_val, sp_len)) return -EINVAL; + /* Avoid negotiating alien CCIDs by only advertising supported ones */ + if (feat == DCCPF_CCID && !ccid_support_check(sp_val, sp_len)) + return -EOPNOTSUPP; + if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len)) return -ENOMEM; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 01332fe7a99a..b4b10cbd8880 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -649,6 +649,8 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_GET_CUR_MPS: val = dp->dccps_mss_cache; break; + case DCCP_SOCKOPT_AVAILABLE_CCIDS: + return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); case DCCP_SOCKOPT_SERVER_TIMEWAIT: val = dp->dccps_server_timewait; break; -- cgit v1.2.3 From 536533e69e3e4a9f0174509813f8df28970d6ebe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 16 Nov 2008 19:41:14 -0800 Subject: rcu: documents rculist_nulls Adds Documentation/RCU/rculist_nulls.txt file to describe how 'nulls' end-of-list can help in some RCU algos. Signed-off-by: Eric Dumazet Acked-by: Peter Zijlstra Signed-off-by: David S. Miller --- Documentation/RCU/rculist_nulls.txt | 167 ++++++++++++++++++++++++++++++++++++ 1 file changed, 167 insertions(+) create mode 100644 Documentation/RCU/rculist_nulls.txt (limited to 'Documentation') diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt new file mode 100644 index 000000000000..239f542d48ba --- /dev/null +++ b/Documentation/RCU/rculist_nulls.txt @@ -0,0 +1,167 @@ +Using hlist_nulls to protect read-mostly linked lists and +objects using SLAB_DESTROY_BY_RCU allocations. + +Please read the basics in Documentation/RCU/listRCU.txt + +Using special makers (called 'nulls') is a convenient way +to solve following problem : + +A typical RCU linked list managing objects which are +allocated with SLAB_DESTROY_BY_RCU kmem_cache can +use following algos : + +1) Lookup algo +-------------- +rcu_read_lock() +begin: +obj = lockless_lookup(key); +if (obj) { + if (!try_get_ref(obj)) // might fail for free objects + goto begin; + /* + * Because a writer could delete object, and a writer could + * reuse these object before the RCU grace period, we + * must check key after geting the reference on object + */ + if (obj->key != key) { // not the object we expected + put_ref(obj); + goto begin; + } +} +rcu_read_unlock(); + +Beware that lockless_lookup(key) cannot use traditional hlist_for_each_entry_rcu() +but a version with an additional memory barrier (smp_rmb()) + +lockless_lookup(key) +{ + struct hlist_node *node, *next; + for (pos = rcu_dereference((head)->first); + pos && ({ next = pos->next; smp_rmb(); prefetch(next); 1; }) && + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); + pos = rcu_dereference(next)) + if (obj->key == key) + return obj; + return NULL; + +And note the traditional hlist_for_each_entry_rcu() misses this smp_rmb() : + + struct hlist_node *node; + for (pos = rcu_dereference((head)->first); + pos && ({ prefetch(pos->next); 1; }) && + ({ tpos = hlist_entry(pos, typeof(*tpos), member); 1; }); + pos = rcu_dereference(pos->next)) + if (obj->key == key) + return obj; + return NULL; +} + +Quoting Corey Minyard : + +"If the object is moved from one list to another list in-between the + time the hash is calculated and the next field is accessed, and the + object has moved to the end of a new list, the traversal will not + complete properly on the list it should have, since the object will + be on the end of the new list and there's not a way to tell it's on a + new list and restart the list traversal. I think that this can be + solved by pre-fetching the "next" field (with proper barriers) before + checking the key." + +2) Insert algo : +---------------- + +We need to make sure a reader cannot read the new 'obj->obj_next' value +and previous value of 'obj->key'. Or else, an item could be deleted +from a chain, and inserted into another chain. If new chain was empty +before the move, 'next' pointer is NULL, and lockless reader can +not detect it missed following items in original chain. + +/* + * Please note that new inserts are done at the head of list, + * not in the middle or end. + */ +obj = kmem_cache_alloc(...); +lock_chain(); // typically a spin_lock() +obj->key = key; +atomic_inc(&obj->refcnt); +/* + * we need to make sure obj->key is updated before obj->next + */ +smp_wmb(); +hlist_add_head_rcu(&obj->obj_node, list); +unlock_chain(); // typically a spin_unlock() + + +3) Remove algo +-------------- +Nothing special here, we can use a standard RCU hlist deletion. +But thanks to SLAB_DESTROY_BY_RCU, beware a deleted object can be reused +very very fast (before the end of RCU grace period) + +if (put_last_reference_on(obj) { + lock_chain(); // typically a spin_lock() + hlist_del_init_rcu(&obj->obj_node); + unlock_chain(); // typically a spin_unlock() + kmem_cache_free(cachep, obj); +} + + + +-------------------------------------------------------------------------- +With hlist_nulls we can avoid extra smp_rmb() in lockless_lookup() +and extra smp_wmb() in insert function. + +For example, if we choose to store the slot number as the 'nulls' +end-of-list marker for each slot of the hash table, we can detect +a race (some writer did a delete and/or a move of an object +to another chain) checking the final 'nulls' value if +the lookup met the end of chain. If final 'nulls' value +is not the slot number, then we must restart the lookup at +the begining. If the object was moved to same chain, +then the reader doesnt care : It might eventually +scan the list again without harm. + + +1) lookup algo + + head = &table[slot]; + rcu_read_lock(); +begin: + hlist_nulls_for_each_entry_rcu(obj, node, head, member) { + if (obj->key == key) { + if (!try_get_ref(obj)) // might fail for free objects + goto begin; + if (obj->key != key) { // not the object we expected + put_ref(obj); + goto begin; + } + goto out; + } +/* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; + obj = NULL; + +out: + rcu_read_unlock(); + +2) Insert function : +-------------------- + +/* + * Please note that new inserts are done at the head of list, + * not in the middle or end. + */ +obj = kmem_cache_alloc(cachep); +lock_chain(); // typically a spin_lock() +obj->key = key; +atomic_set(&obj->refcnt, 1); +/* + * insert obj in RCU way (readers might be traversing chain) + */ +hlist_nulls_add_head_rcu(&obj->obj_node, list); +unlock_chain(); // typically a spin_unlock() -- cgit v1.2.3 From dd9c0e363cef32b7d6f23d4c87e8dfe4f91fd1c5 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sun, 16 Nov 2008 22:55:08 -0800 Subject: dccp: Deprecate Ack Ratio sysctl This patch deprecates the Ack Ratio sysctl, since * Ack Ratio is entirely ignored by CCID-3 and CCID-4, * Ack Ratio currently doesn't work in CCID-2 (i.e. is always set to 1); * even if it would work in CCID-2, there is no point for a user to change it: - Ack Ratio is constrained by cwnd (RFC 4341, 6.1.2), - if Ack Ratio > cwnd, the system resorts to spurious RTO timeouts (since waiting for Acks which will never arrive in this window), - cwnd is not a user-configurable value. The only reasonable place for Ack Ratio is to print it for debugging. It is planned to do this later on, as part of e.g. dccp_probe. With this patch Ack Ratio is now under full control of feature negotiation: * Ack Ratio is resolved as a dependency of the selected CCID; * if the chosen CCID supports it (i.e. CCID == CCID-2), Ack Ratio is set to the default of 2, following RFC 4340, 11.3 - "New connections start with Ack Ratio 2 for both endpoints"; * what happens then is part of another patch set, since it concerns the dynamic update of Ack Ratio while the connection is in full flight. Thanks to Tomasz Grobelny for discussion leading up to this patch. Signed-off-by: Gerrit Renker Acked-by: Arnaldo Carvalho de Melo Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 3 --- include/linux/dccp.h | 2 -- net/dccp/dccp.h | 1 - net/dccp/minisocks.c | 1 - net/dccp/options.c | 1 - net/dccp/sysctl.c | 7 ------- 6 files changed, 15 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index f0aeb20fa63b..43df4487379b 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -125,9 +125,6 @@ send_ndp = 1 send_ackvec = 1 Whether or not to send Ack Vector options (sec. 11.5). -ack_ratio = 2 - The default Ack Ratio (sec. 11.3) to use. - tx_ccid = 2 Default CCID for the sender-receiver half-connection. diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 5a5a89935dbc..eda389ce04f4 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -368,7 +368,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * @dccpms_ccid - Congestion Control Id (CCID) (section 10) * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2) - * @dccpms_ack_ratio - Ack Ratio Feature (section 11.3) * @dccpms_pending - List of features being negotiated * @dccpms_conf - */ @@ -378,7 +377,6 @@ struct dccp_minisock { __u8 dccpms_tx_ccid; __u8 dccpms_send_ack_vector; __u8 dccpms_send_ndp_count; - __u8 dccpms_ack_ratio; struct list_head dccpms_pending; struct list_head dccpms_conf; }; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index e656dafb5d96..031ce350d3c1 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -98,7 +98,6 @@ extern int sysctl_dccp_retries2; extern int sysctl_dccp_feat_sequence_window; extern int sysctl_dccp_feat_rx_ccid; extern int sysctl_dccp_feat_tx_ccid; -extern int sysctl_dccp_feat_ack_ratio; extern int sysctl_dccp_feat_send_ack_vector; extern int sysctl_dccp_feat_send_ndp_count; extern int sysctl_dccp_tx_qlen; diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index afdacbb94d75..ed61bc58e41e 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -47,7 +47,6 @@ void dccp_minisock_init(struct dccp_minisock *dmsk) dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window; dmsk->dccpms_rx_ccid = sysctl_dccp_feat_rx_ccid; dmsk->dccpms_tx_ccid = sysctl_dccp_feat_tx_ccid; - dmsk->dccpms_ack_ratio = sysctl_dccp_feat_ack_ratio; dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; dmsk->dccpms_send_ndp_count = sysctl_dccp_feat_send_ndp_count; } diff --git a/net/dccp/options.c b/net/dccp/options.c index 67a171a1268c..515ad45013ad 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -26,7 +26,6 @@ int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID; int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID; -int sysctl_dccp_feat_ack_ratio = DCCPF_INITIAL_ACK_RATIO; int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; int sysctl_dccp_feat_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT; diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 21295993fdb8..f6e54f433e29 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -40,13 +40,6 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "ack_ratio", - .data = &sysctl_dccp_feat_ack_ratio, - .maxlen = sizeof(sysctl_dccp_feat_ack_ratio), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "send_ackvec", .data = &sysctl_dccp_feat_send_ack_vector, -- cgit v1.2.3 From f9f88fed3433139b58962011c81597b44fd48458 Mon Sep 17 00:00:00 2001 From: Jouni Malinen Date: Sun, 9 Nov 2008 18:38:51 +0200 Subject: mac80211_hwsim: Update documentation (AP mode enabled) AP mode is now enabled in mac80211, so there is no need to point users to an additional patch to enable the mode. In addition, add a pointer to more hwsim test cases in hostap.git. Signed-off-by: Jouni Malinen Signed-off-by: John W. Linville --- Documentation/networking/mac80211_hwsim/README | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/mac80211_hwsim/README b/Documentation/networking/mac80211_hwsim/README index 2ff8ccb8dc37..24ac91d56698 100644 --- a/Documentation/networking/mac80211_hwsim/README +++ b/Documentation/networking/mac80211_hwsim/README @@ -50,10 +50,6 @@ associates with the AP. hostapd and wpa_supplicant are used to take care of WPA2-PSK authentication. In addition, hostapd is also processing access point side of association. -Please note that the current Linux kernel does not enable AP mode, so a -simple patch is needed to enable AP mode selection: -http://johannes.sipsolutions.net/patches/kernel/all/LATEST/006-allow-ap-vlan-modes.patch - # Build mac80211_hwsim as part of kernel configuration @@ -65,3 +61,8 @@ hostapd hostapd.conf # Run wpa_supplicant (station) for wlan1 wpa_supplicant -Dwext -iwlan1 -c wpa_supplicant.conf + + +More test cases are available in hostap.git: +git://w1.fi/srv/git/hostap.git and mac80211_hwsim/tests subdirectory +(http://w1.fi/gitweb/gitweb.cgi?p=hostap.git;a=tree;f=mac80211_hwsim/tests) -- cgit v1.2.3 From e022c2f07ae52bfbd92faa273db0db2f34eb28e8 Mon Sep 17 00:00:00 2001 From: Krzysztof HaÅ‚asa Date: Thu, 14 Aug 2008 19:17:38 +0200 Subject: WAN: new synchronous PPP implementation for generic HDLC. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Krzysztof HaÅ‚asa --- Documentation/networking/generic-hdlc.txt | 8 +- drivers/net/wan/Makefile | 2 +- drivers/net/wan/hdlc_ppp.c | 648 +++++++++++++++++++++++++++--- 3 files changed, 606 insertions(+), 52 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/generic-hdlc.txt b/Documentation/networking/generic-hdlc.txt index 31bc8b759b75..4eb3cc40b702 100644 --- a/Documentation/networking/generic-hdlc.txt +++ b/Documentation/networking/generic-hdlc.txt @@ -3,15 +3,15 @@ Krzysztof Halasa Generic HDLC layer currently supports: -1. Frame Relay (ANSI, CCITT, Cisco and no LMI). +1. Frame Relay (ANSI, CCITT, Cisco and no LMI) - Normal (routed) and Ethernet-bridged (Ethernet device emulation) interfaces can share a single PVC. - ARP support (no InARP support in the kernel - there is an experimental InARP user-space daemon available on: http://www.kernel.org/pub/linux/utils/net/hdlc/). -2. raw HDLC - either IP (IPv4) interface or Ethernet device emulation. -3. Cisco HDLC. -4. PPP (uses syncppp.c). +2. raw HDLC - either IP (IPv4) interface or Ethernet device emulation +3. Cisco HDLC +4. PPP 5. X.25 (uses X.25 routines). Generic HDLC is a protocol driver only - it needs a low-level driver diff --git a/drivers/net/wan/Makefile b/drivers/net/wan/Makefile index 102549605d09..cec16818a130 100644 --- a/drivers/net/wan/Makefile +++ b/drivers/net/wan/Makefile @@ -14,7 +14,7 @@ obj-$(CONFIG_HDLC_RAW) += hdlc_raw.o obj-$(CONFIG_HDLC_RAW_ETH) += hdlc_raw_eth.o obj-$(CONFIG_HDLC_CISCO) += hdlc_cisco.o obj-$(CONFIG_HDLC_FR) += hdlc_fr.o -obj-$(CONFIG_HDLC_PPP) += hdlc_ppp.o syncppp.o +obj-$(CONFIG_HDLC_PPP) += hdlc_ppp.o obj-$(CONFIG_HDLC_X25) += hdlc_x25.o pc300-y := pc300_drv.o diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 4efe9e6d32d5..72fae217f1c4 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -2,7 +2,7 @@ * Generic HDLC support routines for Linux * Point-to-point protocol support * - * Copyright (C) 1999 - 2006 Krzysztof Halasa + * Copyright (C) 1999 - 2008 Krzysztof Halasa * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License @@ -18,87 +18,632 @@ #include #include #include -#include #include #include -#include +#include + +#define DEBUG_CP 0 /* also bytes# to dump */ +#define DEBUG_STATE 0 +#define DEBUG_HARD_HEADER 0 + +#define HDLC_ADDR_ALLSTATIONS 0xFF +#define HDLC_CTRL_UI 0x03 + +#define PID_LCP 0xC021 +#define PID_IP 0x0021 +#define PID_IPCP 0x8021 +#define PID_IPV6 0x0057 +#define PID_IPV6CP 0x8057 + +enum {IDX_LCP = 0, IDX_IPCP, IDX_IPV6CP, IDX_COUNT}; +enum {CP_CONF_REQ = 1, CP_CONF_ACK, CP_CONF_NAK, CP_CONF_REJ, CP_TERM_REQ, + CP_TERM_ACK, CP_CODE_REJ, LCP_PROTO_REJ, LCP_ECHO_REQ, LCP_ECHO_REPLY, + LCP_DISC_REQ, CP_CODES}; +#if DEBUG_CP +static const char *const code_names[CP_CODES] = { + "0", "ConfReq", "ConfAck", "ConfNak", "ConfRej", "TermReq", + "TermAck", "CodeRej", "ProtoRej", "EchoReq", "EchoReply", "Discard" +}; +static char debug_buffer[64 + 3 * DEBUG_CP]; +#endif + +enum {LCP_OPTION_MRU = 1, LCP_OPTION_ACCM, LCP_OPTION_MAGIC = 5}; + +struct hdlc_header { + u8 address; + u8 control; + __be16 protocol; +}; + +struct cp_header { + u8 code; + u8 id; + __be16 len; +}; + -struct ppp_state { - struct ppp_device pppdev; - struct ppp_device *syncppp_ptr; - int (*old_change_mtu)(struct net_device *dev, int new_mtu); +struct proto { + struct net_device *dev; + struct timer_list timer; + unsigned long timeout; + u16 pid; /* protocol ID */ + u8 state; + u8 cr_id; /* ID of last Configuration-Request */ + u8 restart_counter; }; +struct ppp { + struct proto protos[IDX_COUNT]; + spinlock_t lock; + unsigned long last_pong; + unsigned int req_timeout, cr_retries, term_retries; + unsigned int keepalive_interval, keepalive_timeout; + u8 seq; /* local sequence number for requests */ + u8 echo_id; /* ID of last Echo-Request (LCP) */ +}; + +enum {CLOSED = 0, STOPPED, STOPPING, REQ_SENT, ACK_RECV, ACK_SENT, OPENED, + STATES, STATE_MASK = 0xF}; +enum {START = 0, STOP, TO_GOOD, TO_BAD, RCR_GOOD, RCR_BAD, RCA, RCN, RTR, RTA, + RUC, RXJ_GOOD, RXJ_BAD, EVENTS}; +enum {INV = 0x10, IRC = 0x20, ZRC = 0x40, SCR = 0x80, SCA = 0x100, + SCN = 0x200, STR = 0x400, STA = 0x800, SCJ = 0x1000}; + +#if DEBUG_STATE +static const char *const state_names[STATES] = { + "Closed", "Stopped", "Stopping", "ReqSent", "AckRecv", "AckSent", + "Opened" +}; +static const char *const event_names[EVENTS] = { + "Start", "Stop", "TO+", "TO-", "RCR+", "RCR-", "RCA", "RCN", + "RTR", "RTA", "RUC", "RXJ+", "RXJ-" +}; +#endif + +static struct sk_buff_head tx_queue; /* used when holding the spin lock */ + static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr); +static inline struct ppp* get_ppp(struct net_device *dev) +{ + return (struct ppp *)dev_to_hdlc(dev)->state; +} -static inline struct ppp_state* state(hdlc_device *hdlc) +static inline struct proto* get_proto(struct net_device *dev, u16 pid) { - return(struct ppp_state *)(hdlc->state); + struct ppp *ppp = get_ppp(dev); + + switch (pid) { + case PID_LCP: + return &ppp->protos[IDX_LCP]; + case PID_IPCP: + return &ppp->protos[IDX_IPCP]; + case PID_IPV6CP: + return &ppp->protos[IDX_IPV6CP]; + default: + return NULL; + } } +static inline const char* proto_name(u16 pid) +{ + switch (pid) { + case PID_LCP: + return "LCP"; + case PID_IPCP: + return "IPCP"; + case PID_IPV6CP: + return "IPV6CP"; + default: + return NULL; + } +} -static int ppp_open(struct net_device *dev) +static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev) { - hdlc_device *hdlc = dev_to_hdlc(dev); - int (*old_ioctl)(struct net_device *, struct ifreq *, int); - int result; + struct hdlc_header *data = (struct hdlc_header*)skb->data; + + if (skb->len < sizeof(struct hdlc_header)) + return htons(ETH_P_HDLC); + if (data->address != HDLC_ADDR_ALLSTATIONS || + data->control != HDLC_CTRL_UI) + return htons(ETH_P_HDLC); + + switch (data->protocol) { + case __constant_htons(PID_IP): + skb_pull(skb, sizeof(struct hdlc_header)); + return htons(ETH_P_IP); - dev->ml_priv = &state(hdlc)->syncppp_ptr; - state(hdlc)->syncppp_ptr = &state(hdlc)->pppdev; - state(hdlc)->pppdev.dev = dev; + case __constant_htons(PID_IPV6): + skb_pull(skb, sizeof(struct hdlc_header)); + return htons(ETH_P_IPV6); - old_ioctl = dev->do_ioctl; - state(hdlc)->old_change_mtu = dev->change_mtu; - sppp_attach(&state(hdlc)->pppdev); - /* sppp_attach nukes them. We don't need syncppp's ioctl */ - dev->do_ioctl = old_ioctl; - state(hdlc)->pppdev.sppp.pp_flags &= ~PP_CISCO; - dev->type = ARPHRD_PPP; - result = sppp_open(dev); - if (result) { - sppp_detach(dev); - return result; + default: + return htons(ETH_P_HDLC); } +} - return 0; + +static int ppp_hard_header(struct sk_buff *skb, struct net_device *dev, + u16 type, const void *daddr, const void *saddr, + unsigned int len) +{ + struct hdlc_header *data; +#if DEBUG_HARD_HEADER + printk(KERN_DEBUG "%s: ppp_hard_header() called\n", dev->name); +#endif + + skb_push(skb, sizeof(struct hdlc_header)); + data = (struct hdlc_header*)skb->data; + + data->address = HDLC_ADDR_ALLSTATIONS; + data->control = HDLC_CTRL_UI; + switch (type) { + case ETH_P_IP: + data->protocol = htons(PID_IP); + break; + case ETH_P_IPV6: + data->protocol = htons(PID_IPV6); + break; + case PID_LCP: + case PID_IPCP: + case PID_IPV6CP: + data->protocol = htons(type); + break; + default: /* unknown protocol */ + data->protocol = 0; + } + return sizeof(struct hdlc_header); } +static void ppp_tx_flush(void) +{ + struct sk_buff *skb; + while ((skb = skb_dequeue(&tx_queue)) != NULL) + dev_queue_xmit(skb); +} -static void ppp_close(struct net_device *dev) +static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code, + u8 id, unsigned int len, const void *data) { - hdlc_device *hdlc = dev_to_hdlc(dev); + struct sk_buff *skb; + struct cp_header *cp; + unsigned int magic_len = 0; + static u32 magic; + +#if DEBUG_CP + int i; + char *ptr; +#endif + + if (pid == PID_LCP && (code == LCP_ECHO_REQ || code == LCP_ECHO_REPLY)) + magic_len = sizeof(magic); + + skb = dev_alloc_skb(sizeof(struct hdlc_header) + + sizeof(struct cp_header) + magic_len + len); + if (!skb) { + printk(KERN_WARNING "%s: out of memory in ppp_tx_cp()\n", + dev->name); + return; + } + skb_reserve(skb, sizeof(struct hdlc_header)); + + cp = (struct cp_header *)skb_put(skb, sizeof(struct cp_header)); + cp->code = code; + cp->id = id; + cp->len = htons(sizeof(struct cp_header) + magic_len + len); + + if (magic_len) + memcpy(skb_put(skb, magic_len), &magic, magic_len); + if (len) + memcpy(skb_put(skb, len), data, len); + +#if DEBUG_CP + BUG_ON(code >= CP_CODES); + ptr = debug_buffer; + *ptr = '\x0'; + for (i = 0; i < min_t(unsigned int, magic_len + len, DEBUG_CP); i++) { + sprintf(ptr, " %02X", skb->data[sizeof(struct cp_header) + i]); + ptr += strlen(ptr); + } + printk(KERN_DEBUG "%s: TX %s [%s id 0x%X]%s\n", dev->name, + proto_name(pid), code_names[code], id, debug_buffer); +#endif - sppp_close(dev); - sppp_detach(dev); + ppp_hard_header(skb, dev, pid, NULL, NULL, 0); - dev->change_mtu = state(hdlc)->old_change_mtu; - dev->mtu = HDLC_MAX_MTU; - dev->hard_header_len = 16; + skb->priority = TC_PRIO_CONTROL; + skb->dev = dev; + skb_reset_network_header(skb); + skb_queue_tail(&tx_queue, skb); } +/* State transition table (compare STD-51) + Events Actions + TO+ = Timeout with counter > 0 irc = Initialize-Restart-Count + TO- = Timeout with counter expired zrc = Zero-Restart-Count + + RCR+ = Receive-Configure-Request (Good) scr = Send-Configure-Request + RCR- = Receive-Configure-Request (Bad) + RCA = Receive-Configure-Ack sca = Send-Configure-Ack + RCN = Receive-Configure-Nak/Rej scn = Send-Configure-Nak/Rej + + RTR = Receive-Terminate-Request str = Send-Terminate-Request + RTA = Receive-Terminate-Ack sta = Send-Terminate-Ack + + RUC = Receive-Unknown-Code scj = Send-Code-Reject + RXJ+ = Receive-Code-Reject (permitted) + or Receive-Protocol-Reject + RXJ- = Receive-Code-Reject (catastrophic) + or Receive-Protocol-Reject +*/ +static int cp_table[EVENTS][STATES] = { + /* CLOSED STOPPED STOPPING REQ_SENT ACK_RECV ACK_SENT OPENED + 0 1 2 3 4 5 6 */ + {IRC|SCR|3, INV , INV , INV , INV , INV , INV }, /* START */ + { INV , 0 , 0 , 0 , 0 , 0 , 0 }, /* STOP */ + { INV , INV ,STR|2, SCR|3 ,SCR|3, SCR|5 , INV }, /* TO+ */ + { INV , INV , 1 , 1 , 1 , 1 , INV }, /* TO- */ + { STA|0 ,IRC|SCR|SCA|5, 2 , SCA|5 ,SCA|6, SCA|5 ,SCR|SCA|5}, /* RCR+ */ + { STA|0 ,IRC|SCR|SCN|3, 2 , SCN|3 ,SCN|4, SCN|3 ,SCR|SCN|3}, /* RCR- */ + { STA|0 , STA|1 , 2 , IRC|4 ,SCR|3, 6 , SCR|3 }, /* RCA */ + { STA|0 , STA|1 , 2 ,IRC|SCR|3,SCR|3,IRC|SCR|5, SCR|3 }, /* RCN */ + { STA|0 , STA|1 ,STA|2, STA|3 ,STA|3, STA|3 ,ZRC|STA|2}, /* RTR */ + { 0 , 1 , 1 , 3 , 3 , 5 , SCR|3 }, /* RTA */ + { SCJ|0 , SCJ|1 ,SCJ|2, SCJ|3 ,SCJ|4, SCJ|5 , SCJ|6 }, /* RUC */ + { 0 , 1 , 2 , 3 , 3 , 5 , 6 }, /* RXJ+ */ + { 0 , 1 , 1 , 1 , 1 , 1 ,IRC|STR|2}, /* RXJ- */ +}; + -static __be16 ppp_type_trans(struct sk_buff *skb, struct net_device *dev) +/* SCA: RCR+ must supply id, len and data + SCN: RCR- must supply code, id, len and data + STA: RTR must supply id + SCJ: RUC must supply CP packet len and data */ +static void ppp_cp_event(struct net_device *dev, u16 pid, u16 event, u8 code, + u8 id, unsigned int len, void *data) { - return __constant_htons(ETH_P_WAN_PPP); + int old_state, action; + struct ppp *ppp = get_ppp(dev); + struct proto *proto = get_proto(dev, pid); + + old_state = proto->state; + BUG_ON(old_state >= STATES); + BUG_ON(event >= EVENTS); + +#if DEBUG_STATE + printk(KERN_DEBUG "%s: %s ppp_cp_event(%s) %s ...\n", dev->name, + proto_name(pid), event_names[event], state_names[proto->state]); +#endif + + action = cp_table[event][old_state]; + + proto->state = action & STATE_MASK; + if (action & (SCR | STR)) /* set Configure-Req/Terminate-Req timer */ + mod_timer(&proto->timer, proto->timeout = + jiffies + ppp->req_timeout * HZ); + if (action & ZRC) + proto->restart_counter = 0; + if (action & IRC) + proto->restart_counter = (proto->state == STOPPING) ? + ppp->term_retries : ppp->cr_retries; + + if (action & SCR) /* send Configure-Request */ + ppp_tx_cp(dev, pid, CP_CONF_REQ, proto->cr_id = ++ppp->seq, + 0, NULL); + if (action & SCA) /* send Configure-Ack */ + ppp_tx_cp(dev, pid, CP_CONF_ACK, id, len, data); + if (action & SCN) /* send Configure-Nak/Reject */ + ppp_tx_cp(dev, pid, code, id, len, data); + if (action & STR) /* send Terminate-Request */ + ppp_tx_cp(dev, pid, CP_TERM_REQ, ++ppp->seq, 0, NULL); + if (action & STA) /* send Terminate-Ack */ + ppp_tx_cp(dev, pid, CP_TERM_ACK, id, 0, NULL); + if (action & SCJ) /* send Code-Reject */ + ppp_tx_cp(dev, pid, CP_CODE_REJ, ++ppp->seq, len, data); + + if (old_state != OPENED && proto->state == OPENED) { + printk(KERN_INFO "%s: %s up\n", dev->name, proto_name(pid)); + if (pid == PID_LCP) { + netif_dormant_off(dev); + ppp_cp_event(dev, PID_IPCP, START, 0, 0, 0, NULL); + ppp_cp_event(dev, PID_IPV6CP, START, 0, 0, 0, NULL); + ppp->last_pong = jiffies; + mod_timer(&proto->timer, proto->timeout = + jiffies + ppp->keepalive_interval * HZ); + } + } + if (old_state == OPENED && proto->state != OPENED) { + printk(KERN_INFO "%s: %s down\n", dev->name, proto_name(pid)); + if (pid == PID_LCP) { + netif_dormant_on(dev); + ppp_cp_event(dev, PID_IPCP, STOP, 0, 0, 0, NULL); + ppp_cp_event(dev, PID_IPV6CP, STOP, 0, 0, 0, NULL); + } + } + if (old_state != CLOSED && proto->state == CLOSED) + del_timer(&proto->timer); + +#if DEBUG_STATE + printk(KERN_DEBUG "%s: %s ppp_cp_event(%s) ... %s\n", dev->name, + proto_name(pid), event_names[event], state_names[proto->state]); +#endif } +static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, + unsigned int len, u8 *data) +{ + static u8 const valid_accm[6] = { LCP_OPTION_ACCM, 6, 0, 0, 0, 0 }; + u8 *opt, *out; + unsigned int nak_len = 0, rej_len = 0; + + if (!(out = kmalloc(len, GFP_ATOMIC))) { + dev->stats.rx_dropped++; + return; /* out of memory, ignore CR packet */ + } + + for (opt = data; len; len -= opt[1], opt += opt[1]) { + if (len < 2 || len < opt[1]) { + dev->stats.rx_errors++; + return; /* bad packet, drop silently */ + } + + if (pid == PID_LCP) + switch (opt[0]) { + case LCP_OPTION_MRU: + continue; /* MRU always OK and > 1500 bytes? */ + + case LCP_OPTION_ACCM: /* async control character map */ + if (!memcmp(opt, valid_accm, + sizeof(valid_accm))) + continue; + if (!rej_len) { /* NAK it */ + memcpy(out + nak_len, valid_accm, + sizeof(valid_accm)); + nak_len += sizeof(valid_accm); + continue; + } + break; + case LCP_OPTION_MAGIC: + if (opt[1] != 6 || (!opt[2] && !opt[3] && + !opt[4] && !opt[5])) + break; /* reject invalid magic number */ + continue; + } + /* reject this option */ + memcpy(out + rej_len, opt, opt[1]); + rej_len += opt[1]; + } + + if (rej_len) + ppp_cp_event(dev, pid, RCR_BAD, CP_CONF_REJ, id, rej_len, out); + else if (nak_len) + ppp_cp_event(dev, pid, RCR_BAD, CP_CONF_NAK, id, nak_len, out); + else + ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, len, data); + + kfree(out); +} + +static int ppp_rx(struct sk_buff *skb) +{ + struct hdlc_header *hdr = (struct hdlc_header*)skb->data; + struct net_device *dev = skb->dev; + struct ppp *ppp = get_ppp(dev); + struct proto *proto; + struct cp_header *cp; + unsigned long flags; + unsigned int len; + u16 pid; +#if DEBUG_CP + int i; + char *ptr; +#endif + + spin_lock_irqsave(&ppp->lock, flags); + /* Check HDLC header */ + if (skb->len < sizeof(struct hdlc_header)) + goto rx_error; + cp = (struct cp_header*)skb_pull(skb, sizeof(struct hdlc_header)); + if (hdr->address != HDLC_ADDR_ALLSTATIONS || + hdr->control != HDLC_CTRL_UI) + goto rx_error; + + pid = ntohs(hdr->protocol); + proto = get_proto(dev, pid); + if (!proto) { + if (ppp->protos[IDX_LCP].state == OPENED) + ppp_tx_cp(dev, PID_LCP, LCP_PROTO_REJ, + ++ppp->seq, skb->len + 2, &hdr->protocol); + goto rx_error; + } + + len = ntohs(cp->len); + if (len < sizeof(struct cp_header) /* no complete CP header? */ || + skb->len < len /* truncated packet? */) + goto rx_error; + skb_pull(skb, sizeof(struct cp_header)); + len -= sizeof(struct cp_header); + + /* HDLC and CP headers stripped from skb */ +#if DEBUG_CP + if (cp->code < CP_CODES) + sprintf(debug_buffer, "[%s id 0x%X]", code_names[cp->code], + cp->id); + else + sprintf(debug_buffer, "[code %u id 0x%X]", cp->code, cp->id); + ptr = debug_buffer + strlen(debug_buffer); + for (i = 0; i < min_t(unsigned int, len, DEBUG_CP); i++) { + sprintf(ptr, " %02X", skb->data[i]); + ptr += strlen(ptr); + } + printk(KERN_DEBUG "%s: RX %s %s\n", dev->name, proto_name(pid), + debug_buffer); +#endif + + /* LCP only */ + if (pid == PID_LCP) + switch (cp->code) { + case LCP_PROTO_REJ: + pid = ntohs(*(__be16*)skb->data); + if (pid == PID_LCP || pid == PID_IPCP || + pid == PID_IPV6CP) + ppp_cp_event(dev, pid, RXJ_BAD, 0, 0, + 0, NULL); + goto out; + + case LCP_ECHO_REQ: /* send Echo-Reply */ + if (len >= 4 && proto->state == OPENED) + ppp_tx_cp(dev, PID_LCP, LCP_ECHO_REPLY, + cp->id, len - 4, skb->data + 4); + goto out; + + case LCP_ECHO_REPLY: + if (cp->id == ppp->echo_id) + ppp->last_pong = jiffies; + goto out; + + case LCP_DISC_REQ: /* discard */ + goto out; + } + + /* LCP, IPCP and IPV6CP */ + switch (cp->code) { + case CP_CONF_REQ: + ppp_cp_parse_cr(dev, pid, cp->id, len, skb->data); + goto out; + + case CP_CONF_ACK: + if (cp->id == proto->cr_id) + ppp_cp_event(dev, pid, RCA, 0, 0, 0, NULL); + goto out; + + case CP_CONF_REJ: + case CP_CONF_NAK: + if (cp->id == proto->cr_id) + ppp_cp_event(dev, pid, RCN, 0, 0, 0, NULL); + goto out; + + case CP_TERM_REQ: + ppp_cp_event(dev, pid, RTR, 0, cp->id, 0, NULL); + goto out; + + case CP_TERM_ACK: + ppp_cp_event(dev, pid, RTA, 0, 0, 0, NULL); + goto out; + + case CP_CODE_REJ: + ppp_cp_event(dev, pid, RXJ_BAD, 0, 0, 0, NULL); + goto out; + + default: + len += sizeof(struct cp_header); + if (len > dev->mtu) + len = dev->mtu; + ppp_cp_event(dev, pid, RUC, 0, 0, len, cp); + goto out; + } + goto out; + +rx_error: + dev->stats.rx_errors++; +out: + spin_unlock_irqrestore(&ppp->lock, flags); + dev_kfree_skb_any(skb); + ppp_tx_flush(); + return NET_RX_DROP; +} + + +static void ppp_timer(unsigned long arg) +{ + struct proto *proto = (struct proto *)arg; + struct ppp *ppp = get_ppp(proto->dev); + unsigned long flags; + + spin_lock_irqsave(&ppp->lock, flags); + switch (proto->state) { + case STOPPING: + case REQ_SENT: + case ACK_RECV: + case ACK_SENT: + if (proto->restart_counter) { + ppp_cp_event(proto->dev, proto->pid, TO_GOOD, 0, 0, + 0, NULL); + proto->restart_counter--; + } else + ppp_cp_event(proto->dev, proto->pid, TO_BAD, 0, 0, + 0, NULL); + break; + + case OPENED: + if (proto->pid != PID_LCP) + break; + if (time_after(jiffies, ppp->last_pong + + ppp->keepalive_timeout * HZ)) { + printk(KERN_INFO "%s: Link down\n", proto->dev->name); + ppp_cp_event(proto->dev, PID_LCP, STOP, 0, 0, 0, NULL); + ppp_cp_event(proto->dev, PID_LCP, START, 0, 0, 0, NULL); + } else { /* send keep-alive packet */ + ppp->echo_id = ++ppp->seq; + ppp_tx_cp(proto->dev, PID_LCP, LCP_ECHO_REQ, + ppp->echo_id, 0, NULL); + proto->timer.expires = jiffies + + ppp->keepalive_interval * HZ; + add_timer(&proto->timer); + } + break; + } + spin_unlock_irqrestore(&ppp->lock, flags); + ppp_tx_flush(); +} + + +static void ppp_start(struct net_device *dev) +{ + struct ppp *ppp = get_ppp(dev); + int i; + + for (i = 0; i < IDX_COUNT; i++) { + struct proto *proto = &ppp->protos[i]; + proto->dev = dev; + init_timer(&proto->timer); + proto->timer.function = ppp_timer; + proto->timer.data = (unsigned long)proto; + proto->state = CLOSED; + } + ppp->protos[IDX_LCP].pid = PID_LCP; + ppp->protos[IDX_IPCP].pid = PID_IPCP; + ppp->protos[IDX_IPV6CP].pid = PID_IPV6CP; + + ppp_cp_event(dev, PID_LCP, START, 0, 0, 0, NULL); +} + +static void ppp_stop(struct net_device *dev) +{ + ppp_cp_event(dev, PID_LCP, STOP, 0, 0, 0, NULL); +} static struct hdlc_proto proto = { - .open = ppp_open, - .close = ppp_close, + .start = ppp_start, + .stop = ppp_stop, .type_trans = ppp_type_trans, .ioctl = ppp_ioctl, + .netif_rx = ppp_rx, .module = THIS_MODULE, }; +static const struct header_ops ppp_header_ops = { + .create = ppp_hard_header, +}; static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) { hdlc_device *hdlc = dev_to_hdlc(dev); + struct ppp *ppp; int result; switch (ifr->ifr_settings.type) { @@ -109,25 +654,35 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) return 0; /* return protocol only, no settable parameters */ case IF_PROTO_PPP: - if(!capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) return -EPERM; - if(dev->flags & IFF_UP) + if (dev->flags & IFF_UP) return -EBUSY; /* no settable parameters */ - result=hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); + result = hdlc->attach(dev, ENCODING_NRZ,PARITY_CRC16_PR1_CCITT); if (result) return result; - result = attach_hdlc_protocol(dev, &proto, - sizeof(struct ppp_state)); + result = attach_hdlc_protocol(dev, &proto, sizeof(struct ppp)); if (result) return result; + + ppp = get_ppp(dev); + spin_lock_init(&ppp->lock); + ppp->req_timeout = 2; + ppp->cr_retries = 10; + ppp->term_retries = 2; + ppp->keepalive_interval = 10; + ppp->keepalive_timeout = 60; + dev->hard_start_xmit = hdlc->xmit; + dev->hard_header_len = sizeof(struct hdlc_header); + dev->header_ops = &ppp_header_ops; dev->type = ARPHRD_PPP; - netif_dormant_off(dev); + netif_dormant_on(dev); return 0; } @@ -137,12 +692,11 @@ static int ppp_ioctl(struct net_device *dev, struct ifreq *ifr) static int __init mod_init(void) { + skb_queue_head_init(&tx_queue); register_hdlc_protocol(&proto); return 0; } - - static void __exit mod_exit(void) { unregister_hdlc_protocol(&proto); -- cgit v1.2.3 From 72364706c3b7c09a658e356218a918c5f92dcad0 Mon Sep 17 00:00:00 2001 From: Krzysztof HaÅ‚asa Date: Thu, 14 Aug 2008 19:18:17 +0200 Subject: WAN: syncppp.c is no longer used by any kernel code. Remove it. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Krzysztof HaÅ‚asa --- Documentation/DocBook/Makefile | 2 +- Documentation/DocBook/networking.tmpl | 3 - Documentation/DocBook/wanbook.tmpl | 99 --- drivers/net/wan/syncppp.c | 1476 --------------------------------- include/net/syncppp.h | 102 --- 5 files changed, 1 insertion(+), 1681 deletions(-) delete mode 100644 Documentation/DocBook/wanbook.tmpl delete mode 100644 drivers/net/wan/syncppp.c delete mode 100644 include/net/syncppp.h (limited to 'Documentation') diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile index 9b1f6ca100d1..0a08126d3094 100644 --- a/Documentation/DocBook/Makefile +++ b/Documentation/DocBook/Makefile @@ -6,7 +6,7 @@ # To add a new book the only step required is to add the book to the # list of DOCBOOKS. -DOCBOOKS := wanbook.xml z8530book.xml mcabook.xml \ +DOCBOOKS := z8530book.xml mcabook.xml \ kernel-hacking.xml kernel-locking.xml deviceiobook.xml \ procfs-guide.xml writing_usb_driver.xml networking.xml \ kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \ diff --git a/Documentation/DocBook/networking.tmpl b/Documentation/DocBook/networking.tmpl index f24f9e85e4ae..627707a3cb9d 100644 --- a/Documentation/DocBook/networking.tmpl +++ b/Documentation/DocBook/networking.tmpl @@ -98,9 +98,6 @@ X!Enet/core/wireless.c --> - Synchronous PPP -!Edrivers/net/wan/syncppp.c - diff --git a/Documentation/DocBook/wanbook.tmpl b/Documentation/DocBook/wanbook.tmpl deleted file mode 100644 index 8c93db122f04..000000000000 --- a/Documentation/DocBook/wanbook.tmpl +++ /dev/null @@ -1,99 +0,0 @@ - - - - - - Synchronous PPP and Cisco HDLC Programming Guide - - - - Alan - Cox - -
- alan@lxorguk.ukuu.org.uk -
- - - - - - 2000 - Alan Cox - - - - - This documentation is free software; you can redistribute - it and/or modify it under the terms of the GNU General Public - License as published by the Free Software Foundation; either - version 2 of the License, or (at your option) any later - version. - - - - This program is distributed in the hope that it will be - useful, but WITHOUT ANY WARRANTY; without even the implied - warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - See the GNU General Public License for more details. - - - - You should have received a copy of the GNU General Public - License along with this program; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, - MA 02111-1307 USA - - - - For more details see the file COPYING in the source - distribution of Linux. - - - - - - - - Introduction - - The syncppp drivers in Linux provide a fairly complete - implementation of Cisco HDLC and a minimal implementation of - PPP. The longer term goal is to switch the PPP layer to the - generic PPP interface that is new in Linux 2.3.x. The API should - remain unchanged when this is done, but support will then be - available for IPX, compression and other PPP features - - - - Known Bugs And Assumptions - - - PPP is minimal - - - The current PPP implementation is very basic, although sufficient - for most wan usages. - - - - Cisco HDLC Quirks - - - Currently we do not end all packets with the correct Cisco multicast - or unicast flags. Nothing appears to mind too much but this should - be corrected. - - - - - - - - - Public Functions Provided -!Edrivers/net/wan/syncppp.c - - - diff --git a/drivers/net/wan/syncppp.c b/drivers/net/wan/syncppp.c deleted file mode 100644 index 58ae8a2223af..000000000000 --- a/drivers/net/wan/syncppp.c +++ /dev/null @@ -1,1476 +0,0 @@ -/* - * NET3: A (fairly minimal) implementation of synchronous PPP for Linux - * as well as a CISCO HDLC implementation. See the copyright - * message below for the original source. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the license, or (at your option) any later version. - * - * Note however. This code is also used in a different form by FreeBSD. - * Therefore when making any non OS specific change please consider - * contributing it back to the original author under the terms - * below in addition. - * -- Alan - * - * Port for Linux-2.1 by Jan "Yenya" Kasprzak - */ - -/* - * Synchronous PPP/Cisco link level subroutines. - * Keepalive protocol implemented in both Cisco and PPP modes. - * - * Copyright (C) 1994 Cronyx Ltd. - * Author: Serge Vakulenko, - * - * This software is distributed with NO WARRANTIES, not even the implied - * warranties for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * - * Authors grant any other persons or organisations permission to use - * or modify this software as long as this message is kept with the software, - * all derivative works or modified versions. - * - * Version 1.9, Wed Oct 4 18:58:15 MSK 1995 - * - * $Id: syncppp.c,v 1.18 2000/04/11 05:25:31 asj Exp $ - */ -#undef DEBUG - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include -#include - -#define MAXALIVECNT 6 /* max. alive packets */ - -#define PPP_ALLSTATIONS 0xff /* All-Stations broadcast address */ -#define PPP_UI 0x03 /* Unnumbered Information */ -#define PPP_IP 0x0021 /* Internet Protocol */ -#define PPP_ISO 0x0023 /* ISO OSI Protocol */ -#define PPP_XNS 0x0025 /* Xerox NS Protocol */ -#define PPP_IPX 0x002b /* Novell IPX Protocol */ -#define PPP_LCP 0xc021 /* Link Control Protocol */ -#define PPP_IPCP 0x8021 /* Internet Protocol Control Protocol */ - -#define LCP_CONF_REQ 1 /* PPP LCP configure request */ -#define LCP_CONF_ACK 2 /* PPP LCP configure acknowledge */ -#define LCP_CONF_NAK 3 /* PPP LCP configure negative ack */ -#define LCP_CONF_REJ 4 /* PPP LCP configure reject */ -#define LCP_TERM_REQ 5 /* PPP LCP terminate request */ -#define LCP_TERM_ACK 6 /* PPP LCP terminate acknowledge */ -#define LCP_CODE_REJ 7 /* PPP LCP code reject */ -#define LCP_PROTO_REJ 8 /* PPP LCP protocol reject */ -#define LCP_ECHO_REQ 9 /* PPP LCP echo request */ -#define LCP_ECHO_REPLY 10 /* PPP LCP echo reply */ -#define LCP_DISC_REQ 11 /* PPP LCP discard request */ - -#define LCP_OPT_MRU 1 /* maximum receive unit */ -#define LCP_OPT_ASYNC_MAP 2 /* async control character map */ -#define LCP_OPT_AUTH_PROTO 3 /* authentication protocol */ -#define LCP_OPT_QUAL_PROTO 4 /* quality protocol */ -#define LCP_OPT_MAGIC 5 /* magic number */ -#define LCP_OPT_RESERVED 6 /* reserved */ -#define LCP_OPT_PROTO_COMP 7 /* protocol field compression */ -#define LCP_OPT_ADDR_COMP 8 /* address/control field compression */ - -#define IPCP_CONF_REQ LCP_CONF_REQ /* PPP IPCP configure request */ -#define IPCP_CONF_ACK LCP_CONF_ACK /* PPP IPCP configure acknowledge */ -#define IPCP_CONF_NAK LCP_CONF_NAK /* PPP IPCP configure negative ack */ -#define IPCP_CONF_REJ LCP_CONF_REJ /* PPP IPCP configure reject */ -#define IPCP_TERM_REQ LCP_TERM_REQ /* PPP IPCP terminate request */ -#define IPCP_TERM_ACK LCP_TERM_ACK /* PPP IPCP terminate acknowledge */ -#define IPCP_CODE_REJ LCP_CODE_REJ /* PPP IPCP code reject */ - -#define CISCO_MULTICAST 0x8f /* Cisco multicast address */ -#define CISCO_UNICAST 0x0f /* Cisco unicast address */ -#define CISCO_KEEPALIVE 0x8035 /* Cisco keepalive protocol */ -#define CISCO_ADDR_REQ 0 /* Cisco address request */ -#define CISCO_ADDR_REPLY 1 /* Cisco address reply */ -#define CISCO_KEEPALIVE_REQ 2 /* Cisco keepalive request */ - -struct ppp_header { - u8 address; - u8 control; - __be16 protocol; -}; -#define PPP_HEADER_LEN sizeof (struct ppp_header) - -struct lcp_header { - u8 type; - u8 ident; - __be16 len; -}; -#define LCP_HEADER_LEN sizeof (struct lcp_header) - -struct cisco_packet { - __be32 type; - __be32 par1; - __be32 par2; - __be16 rel; - __be16 time0; - __be16 time1; -}; -#define CISCO_PACKET_LEN 18 -#define CISCO_BIG_PACKET_LEN 20 - -static struct sppp *spppq; -static struct timer_list sppp_keepalive_timer; -static DEFINE_SPINLOCK(spppq_lock); - -/* global xmit queue for sending packets while spinlock is held */ -static struct sk_buff_head tx_queue; - -static void sppp_keepalive (unsigned long dummy); -static void sppp_cp_send (struct sppp *sp, u16 proto, u8 type, - u8 ident, u16 len, void *data); -static void sppp_cisco_send (struct sppp *sp, int type, u32 par1, u32 par2); -static void sppp_lcp_input (struct sppp *sp, struct sk_buff *m); -static void sppp_cisco_input (struct sppp *sp, struct sk_buff *m); -static void sppp_ipcp_input (struct sppp *sp, struct sk_buff *m); -static void sppp_lcp_open (struct sppp *sp); -static void sppp_ipcp_open (struct sppp *sp); -static int sppp_lcp_conf_parse_options (struct sppp *sp, struct lcp_header *h, - int len, u32 *magic); -static void sppp_cp_timeout (unsigned long arg); -static char *sppp_lcp_type_name (u8 type); -static char *sppp_ipcp_type_name (u8 type); -static void sppp_print_bytes (u8 *p, u16 len); - -static int debug; - -/* Flush global outgoing packet queue to dev_queue_xmit(). - * - * dev_queue_xmit() must be called with interrupts enabled - * which means it can't be called with spinlocks held. - * If a packet needs to be sent while a spinlock is held, - * then put the packet into tx_queue, and call sppp_flush_xmit() - * after spinlock is released. - */ -static void sppp_flush_xmit(void) -{ - struct sk_buff *skb; - while ((skb = skb_dequeue(&tx_queue)) != NULL) - dev_queue_xmit(skb); -} - -/* - * Interface down stub - */ - -static void if_down(struct net_device *dev) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - - sp->pp_link_state=SPPP_LINK_DOWN; -} - -/* - * Timeout routine activations. - */ - -static void sppp_set_timeout(struct sppp *p,int s) -{ - if (! (p->pp_flags & PP_TIMO)) - { - init_timer(&p->pp_timer); - p->pp_timer.function=sppp_cp_timeout; - p->pp_timer.expires=jiffies+s*HZ; - p->pp_timer.data=(unsigned long)p; - p->pp_flags |= PP_TIMO; - add_timer(&p->pp_timer); - } -} - -static void sppp_clear_timeout(struct sppp *p) -{ - if (p->pp_flags & PP_TIMO) - { - del_timer(&p->pp_timer); - p->pp_flags &= ~PP_TIMO; - } -} - -/** - * sppp_input - receive and process a WAN PPP frame - * @skb: The buffer to process - * @dev: The device it arrived on - * - * This can be called directly by cards that do not have - * timing constraints but is normally called from the network layer - * after interrupt servicing to process frames queued via netif_rx(). - * - * We process the options in the card. If the frame is destined for - * the protocol stacks then it requeues the frame for the upper level - * protocol. If it is a control from it is processed and discarded - * here. - */ - -static void sppp_input (struct net_device *dev, struct sk_buff *skb) -{ - struct ppp_header *h; - struct sppp *sp = (struct sppp *)sppp_of(dev); - unsigned long flags; - - skb->dev=dev; - skb_reset_mac_header(skb); - - if (!pskb_may_pull(skb, PPP_HEADER_LEN)) { - /* Too small packet, drop it. */ - if (sp->pp_flags & PP_DEBUG) - printk (KERN_DEBUG "%s: input packet is too small, %d bytes\n", - dev->name, skb->len); - kfree_skb(skb); - return; - } - - /* Get PPP header. */ - h = (struct ppp_header *)skb->data; - skb_pull(skb,sizeof(struct ppp_header)); - - spin_lock_irqsave(&sp->lock, flags); - - switch (h->address) { - default: /* Invalid PPP packet. */ - goto invalid; - case PPP_ALLSTATIONS: - if (h->control != PPP_UI) - goto invalid; - if (sp->pp_flags & PP_CISCO) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: PPP packet in Cisco mode <0x%x 0x%x 0x%x>\n", - dev->name, - h->address, h->control, ntohs (h->protocol)); - goto drop; - } - switch (ntohs (h->protocol)) { - default: - if (sp->lcp.state == LCP_STATE_OPENED) - sppp_cp_send (sp, PPP_LCP, LCP_PROTO_REJ, - ++sp->pp_seq, skb->len + 2, - &h->protocol); - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid input protocol <0x%x 0x%x 0x%x>\n", - dev->name, - h->address, h->control, ntohs (h->protocol)); - goto drop; - case PPP_LCP: - sppp_lcp_input (sp, skb); - goto drop; - case PPP_IPCP: - if (sp->lcp.state == LCP_STATE_OPENED) - sppp_ipcp_input (sp, skb); - else - printk(KERN_DEBUG "IPCP when still waiting LCP finish.\n"); - goto drop; - case PPP_IP: - if (sp->ipcp.state == IPCP_STATE_OPENED) { - if(sp->pp_flags&PP_DEBUG) - printk(KERN_DEBUG "Yow an IP frame.\n"); - skb->protocol=htons(ETH_P_IP); - netif_rx(skb); - goto done; - } - break; -#ifdef IPX - case PPP_IPX: - /* IPX IPXCP not implemented yet */ - if (sp->lcp.state == LCP_STATE_OPENED) { - skb->protocol=htons(ETH_P_IPX); - netif_rx(skb); - goto done; - } - break; -#endif - } - break; - case CISCO_MULTICAST: - case CISCO_UNICAST: - /* Don't check the control field here (RFC 1547). */ - if (! (sp->pp_flags & PP_CISCO)) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: Cisco packet in PPP mode <0x%x 0x%x 0x%x>\n", - dev->name, - h->address, h->control, ntohs (h->protocol)); - goto drop; - } - switch (ntohs (h->protocol)) { - default: - goto invalid; - case CISCO_KEEPALIVE: - sppp_cisco_input (sp, skb); - goto drop; -#ifdef CONFIG_INET - case ETH_P_IP: - skb->protocol=htons(ETH_P_IP); - netif_rx(skb); - goto done; -#endif -#ifdef CONFIG_IPX - case ETH_P_IPX: - skb->protocol=htons(ETH_P_IPX); - netif_rx(skb); - goto done; -#endif - } - break; - } - goto drop; - -invalid: - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid input packet <0x%x 0x%x 0x%x>\n", - dev->name, h->address, h->control, ntohs (h->protocol)); -drop: - kfree_skb(skb); -done: - spin_unlock_irqrestore(&sp->lock, flags); - sppp_flush_xmit(); - return; -} - -/* - * Handle transmit packets. - */ - -static int sppp_hard_header(struct sk_buff *skb, - struct net_device *dev, __u16 type, - const void *daddr, const void *saddr, - unsigned int len) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - struct ppp_header *h; - skb_push(skb,sizeof(struct ppp_header)); - h=(struct ppp_header *)skb->data; - if(sp->pp_flags&PP_CISCO) - { - h->address = CISCO_UNICAST; - h->control = 0; - } - else - { - h->address = PPP_ALLSTATIONS; - h->control = PPP_UI; - } - if(sp->pp_flags & PP_CISCO) - { - h->protocol = htons(type); - } - else switch(type) - { - case ETH_P_IP: - h->protocol = htons(PPP_IP); - break; - case ETH_P_IPX: - h->protocol = htons(PPP_IPX); - break; - } - return sizeof(struct ppp_header); -} - -static const struct header_ops sppp_header_ops = { - .create = sppp_hard_header, -}; - -/* - * Send keepalive packets, every 10 seconds. - */ - -static void sppp_keepalive (unsigned long dummy) -{ - struct sppp *sp; - unsigned long flags; - - spin_lock_irqsave(&spppq_lock, flags); - - for (sp=spppq; sp; sp=sp->pp_next) - { - struct net_device *dev = sp->pp_if; - - /* Keepalive mode disabled or channel down? */ - if (! (sp->pp_flags & PP_KEEPALIVE) || - ! (dev->flags & IFF_UP)) - continue; - - spin_lock(&sp->lock); - - /* No keepalive in PPP mode if LCP not opened yet. */ - if (! (sp->pp_flags & PP_CISCO) && - sp->lcp.state != LCP_STATE_OPENED) { - spin_unlock(&sp->lock); - continue; - } - - if (sp->pp_alivecnt == MAXALIVECNT) { - /* No keepalive packets got. Stop the interface. */ - printk (KERN_WARNING "%s: protocol down\n", dev->name); - if_down (dev); - if (! (sp->pp_flags & PP_CISCO)) { - /* Shut down the PPP link. */ - sp->lcp.magic = jiffies; - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - sppp_clear_timeout (sp); - /* Initiate negotiation. */ - sppp_lcp_open (sp); - } - } - if (sp->pp_alivecnt <= MAXALIVECNT) - ++sp->pp_alivecnt; - if (sp->pp_flags & PP_CISCO) - sppp_cisco_send (sp, CISCO_KEEPALIVE_REQ, ++sp->pp_seq, - sp->pp_rseq); - else if (sp->lcp.state == LCP_STATE_OPENED) { - __be32 nmagic = htonl (sp->lcp.magic); - sp->lcp.echoid = ++sp->pp_seq; - sppp_cp_send (sp, PPP_LCP, LCP_ECHO_REQ, - sp->lcp.echoid, 4, &nmagic); - } - - spin_unlock(&sp->lock); - } - spin_unlock_irqrestore(&spppq_lock, flags); - sppp_flush_xmit(); - sppp_keepalive_timer.expires=jiffies+10*HZ; - add_timer(&sppp_keepalive_timer); -} - -/* - * Handle incoming PPP Link Control Protocol packets. - */ - -static void sppp_lcp_input (struct sppp *sp, struct sk_buff *skb) -{ - struct lcp_header *h; - struct net_device *dev = sp->pp_if; - int len = skb->len; - u8 *p, opt[6]; - u32 rmagic = 0; - - if (!pskb_may_pull(skb, sizeof(struct lcp_header))) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid lcp packet length: %d bytes\n", - dev->name, len); - return; - } - h = (struct lcp_header *)skb->data; - skb_pull(skb,sizeof(struct lcp_header *)); - - if (sp->pp_flags & PP_DEBUG) - { - char state = '?'; - switch (sp->lcp.state) { - case LCP_STATE_CLOSED: state = 'C'; break; - case LCP_STATE_ACK_RCVD: state = 'R'; break; - case LCP_STATE_ACK_SENT: state = 'S'; break; - case LCP_STATE_OPENED: state = 'O'; break; - } - printk (KERN_WARNING "%s: lcp input(%c): %d bytes <%s id=%xh len=%xh", - dev->name, state, len, - sppp_lcp_type_name (h->type), h->ident, ntohs (h->len)); - if (len > 4) - sppp_print_bytes ((u8*) (h+1), len-4); - printk (">\n"); - } - if (len > ntohs (h->len)) - len = ntohs (h->len); - switch (h->type) { - default: - /* Unknown packet type -- send Code-Reject packet. */ - sppp_cp_send (sp, PPP_LCP, LCP_CODE_REJ, ++sp->pp_seq, - skb->len, h); - break; - case LCP_CONF_REQ: - if (len < 4) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_DEBUG"%s: invalid lcp configure request packet length: %d bytes\n", - dev->name, len); - break; - } - if (len>4 && !sppp_lcp_conf_parse_options (sp, h, len, &rmagic)) - goto badreq; - if (rmagic == sp->lcp.magic) { - /* Local and remote magics equal -- loopback? */ - if (sp->pp_loopcnt >= MAXALIVECNT*5) { - printk (KERN_WARNING "%s: loopback\n", - dev->name); - sp->pp_loopcnt = 0; - if (dev->flags & IFF_UP) { - if_down (dev); - } - } else if (sp->pp_flags & PP_DEBUG) - printk (KERN_DEBUG "%s: conf req: magic glitch\n", - dev->name); - ++sp->pp_loopcnt; - - /* MUST send Conf-Nack packet. */ - rmagic = ~sp->lcp.magic; - opt[0] = LCP_OPT_MAGIC; - opt[1] = sizeof (opt); - opt[2] = rmagic >> 24; - opt[3] = rmagic >> 16; - opt[4] = rmagic >> 8; - opt[5] = rmagic; - sppp_cp_send (sp, PPP_LCP, LCP_CONF_NAK, - h->ident, sizeof (opt), &opt); -badreq: - switch (sp->lcp.state) { - case LCP_STATE_OPENED: - /* Initiate renegotiation. */ - sppp_lcp_open (sp); - /* fall through... */ - case LCP_STATE_ACK_SENT: - /* Go to closed state. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - } - break; - } - /* Send Configure-Ack packet. */ - sp->pp_loopcnt = 0; - if (sp->lcp.state != LCP_STATE_OPENED) { - sppp_cp_send (sp, PPP_LCP, LCP_CONF_ACK, - h->ident, len-4, h+1); - } - /* Change the state. */ - switch (sp->lcp.state) { - case LCP_STATE_CLOSED: - sp->lcp.state = LCP_STATE_ACK_SENT; - break; - case LCP_STATE_ACK_RCVD: - sp->lcp.state = LCP_STATE_OPENED; - sppp_ipcp_open (sp); - break; - case LCP_STATE_OPENED: - /* Remote magic changed -- close session. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - /* Initiate renegotiation. */ - sppp_lcp_open (sp); - /* Send ACK after our REQ in attempt to break loop */ - sppp_cp_send (sp, PPP_LCP, LCP_CONF_ACK, - h->ident, len-4, h+1); - sp->lcp.state = LCP_STATE_ACK_SENT; - break; - } - break; - case LCP_CONF_ACK: - if (h->ident != sp->lcp.confid) - break; - sppp_clear_timeout (sp); - if ((sp->pp_link_state != SPPP_LINK_UP) && - (dev->flags & IFF_UP)) { - /* Coming out of loopback mode. */ - sp->pp_link_state=SPPP_LINK_UP; - printk (KERN_INFO "%s: protocol up\n", dev->name); - } - switch (sp->lcp.state) { - case LCP_STATE_CLOSED: - sp->lcp.state = LCP_STATE_ACK_RCVD; - sppp_set_timeout (sp, 5); - break; - case LCP_STATE_ACK_SENT: - sp->lcp.state = LCP_STATE_OPENED; - sppp_ipcp_open (sp); - break; - } - break; - case LCP_CONF_NAK: - if (h->ident != sp->lcp.confid) - break; - p = (u8*) (h+1); - if (len>=10 && p[0] == LCP_OPT_MAGIC && p[1] >= 4) { - rmagic = (u32)p[2] << 24 | - (u32)p[3] << 16 | p[4] << 8 | p[5]; - if (rmagic == ~sp->lcp.magic) { - int newmagic; - if (sp->pp_flags & PP_DEBUG) - printk (KERN_DEBUG "%s: conf nak: magic glitch\n", - dev->name); - get_random_bytes(&newmagic, sizeof(newmagic)); - sp->lcp.magic += newmagic; - } else - sp->lcp.magic = rmagic; - } - if (sp->lcp.state != LCP_STATE_ACK_SENT) { - /* Go to closed state. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - } - /* The link will be renegotiated after timeout, - * to avoid endless req-nack loop. */ - sppp_clear_timeout (sp); - sppp_set_timeout (sp, 2); - break; - case LCP_CONF_REJ: - if (h->ident != sp->lcp.confid) - break; - sppp_clear_timeout (sp); - /* Initiate renegotiation. */ - sppp_lcp_open (sp); - if (sp->lcp.state != LCP_STATE_ACK_SENT) { - /* Go to closed state. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - } - break; - case LCP_TERM_REQ: - sppp_clear_timeout (sp); - /* Send Terminate-Ack packet. */ - sppp_cp_send (sp, PPP_LCP, LCP_TERM_ACK, h->ident, 0, NULL); - /* Go to closed state. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - /* Initiate renegotiation. */ - sppp_lcp_open (sp); - break; - case LCP_TERM_ACK: - case LCP_CODE_REJ: - case LCP_PROTO_REJ: - /* Ignore for now. */ - break; - case LCP_DISC_REQ: - /* Discard the packet. */ - break; - case LCP_ECHO_REQ: - if (sp->lcp.state != LCP_STATE_OPENED) - break; - if (len < 8) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid lcp echo request packet length: %d bytes\n", - dev->name, len); - break; - } - if (ntohl (*(__be32*)(h+1)) == sp->lcp.magic) { - /* Line loopback mode detected. */ - printk (KERN_WARNING "%s: loopback\n", dev->name); - if_down (dev); - - /* Shut down the PPP link. */ - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - sppp_clear_timeout (sp); - /* Initiate negotiation. */ - sppp_lcp_open (sp); - break; - } - *(__be32 *)(h+1) = htonl (sp->lcp.magic); - sppp_cp_send (sp, PPP_LCP, LCP_ECHO_REPLY, h->ident, len-4, h+1); - break; - case LCP_ECHO_REPLY: - if (h->ident != sp->lcp.echoid) - break; - if (len < 8) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid lcp echo reply packet length: %d bytes\n", - dev->name, len); - break; - } - if (ntohl(*(__be32 *)(h+1)) != sp->lcp.magic) - sp->pp_alivecnt = 0; - break; - } -} - -/* - * Handle incoming Cisco keepalive protocol packets. - */ - -static void sppp_cisco_input (struct sppp *sp, struct sk_buff *skb) -{ - struct cisco_packet *h; - struct net_device *dev = sp->pp_if; - - if (!pskb_may_pull(skb, sizeof(struct cisco_packet)) - || (skb->len != CISCO_PACKET_LEN - && skb->len != CISCO_BIG_PACKET_LEN)) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid cisco packet length: %d bytes\n", - dev->name, skb->len); - return; - } - h = (struct cisco_packet *)skb->data; - skb_pull(skb, sizeof(struct cisco_packet*)); - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: cisco input: %d bytes <%xh %xh %xh %xh %xh-%xh>\n", - dev->name, skb->len, - ntohl (h->type), h->par1, h->par2, h->rel, - h->time0, h->time1); - switch (ntohl (h->type)) { - default: - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: unknown cisco packet type: 0x%x\n", - dev->name, ntohl (h->type)); - break; - case CISCO_ADDR_REPLY: - /* Reply on address request, ignore */ - break; - case CISCO_KEEPALIVE_REQ: - sp->pp_alivecnt = 0; - sp->pp_rseq = ntohl (h->par1); - if (sp->pp_seq == sp->pp_rseq) { - /* Local and remote sequence numbers are equal. - * Probably, the line is in loopback mode. */ - int newseq; - if (sp->pp_loopcnt >= MAXALIVECNT) { - printk (KERN_WARNING "%s: loopback\n", - dev->name); - sp->pp_loopcnt = 0; - if (dev->flags & IFF_UP) { - if_down (dev); - } - } - ++sp->pp_loopcnt; - - /* Generate new local sequence number */ - get_random_bytes(&newseq, sizeof(newseq)); - sp->pp_seq ^= newseq; - break; - } - sp->pp_loopcnt = 0; - if (sp->pp_link_state==SPPP_LINK_DOWN && - (dev->flags & IFF_UP)) { - sp->pp_link_state=SPPP_LINK_UP; - printk (KERN_INFO "%s: protocol up\n", dev->name); - } - break; - case CISCO_ADDR_REQ: - /* Stolen from net/ipv4/devinet.c -- SIOCGIFADDR ioctl */ - { - __be32 addr = 0, mask = htonl(~0U); /* FIXME: is the mask correct? */ -#ifdef CONFIG_INET - struct in_device *in_dev; - struct in_ifaddr *ifa; - - rcu_read_lock(); - if ((in_dev = __in_dev_get_rcu(dev)) != NULL) - { - for (ifa=in_dev->ifa_list; ifa != NULL; - ifa=ifa->ifa_next) { - if (strcmp(dev->name, ifa->ifa_label) == 0) - { - addr = ifa->ifa_local; - mask = ifa->ifa_mask; - break; - } - } - } - rcu_read_unlock(); -#endif - sppp_cisco_send (sp, CISCO_ADDR_REPLY, ntohl(addr), ntohl(mask)); - break; - } - } -} - - -/* - * Send PPP LCP packet. - */ - -static void sppp_cp_send (struct sppp *sp, u16 proto, u8 type, - u8 ident, u16 len, void *data) -{ - struct ppp_header *h; - struct lcp_header *lh; - struct sk_buff *skb; - struct net_device *dev = sp->pp_if; - - skb=alloc_skb(dev->hard_header_len+PPP_HEADER_LEN+LCP_HEADER_LEN+len, - GFP_ATOMIC); - if (skb==NULL) - return; - - skb_reserve(skb,dev->hard_header_len); - - h = (struct ppp_header *)skb_put(skb, sizeof(struct ppp_header)); - h->address = PPP_ALLSTATIONS; /* broadcast address */ - h->control = PPP_UI; /* Unnumbered Info */ - h->protocol = htons (proto); /* Link Control Protocol */ - - lh = (struct lcp_header *)skb_put(skb, sizeof(struct lcp_header)); - lh->type = type; - lh->ident = ident; - lh->len = htons (LCP_HEADER_LEN + len); - - if (len) - memcpy(skb_put(skb,len),data, len); - - if (sp->pp_flags & PP_DEBUG) { - printk (KERN_WARNING "%s: %s output <%s id=%xh len=%xh", - dev->name, - proto==PPP_LCP ? "lcp" : "ipcp", - proto==PPP_LCP ? sppp_lcp_type_name (lh->type) : - sppp_ipcp_type_name (lh->type), lh->ident, - ntohs (lh->len)); - if (len) - sppp_print_bytes ((u8*) (lh+1), len); - printk (">\n"); - } - /* Control is high priority so it doesn't get queued behind data */ - skb->priority=TC_PRIO_CONTROL; - skb->dev = dev; - skb_queue_tail(&tx_queue, skb); -} - -/* - * Send Cisco keepalive packet. - */ - -static void sppp_cisco_send (struct sppp *sp, int type, u32 par1, u32 par2) -{ - struct ppp_header *h; - struct cisco_packet *ch; - struct sk_buff *skb; - struct net_device *dev = sp->pp_if; - u32 t = jiffies * 1000/HZ; - - skb=alloc_skb(dev->hard_header_len+PPP_HEADER_LEN+CISCO_PACKET_LEN, - GFP_ATOMIC); - - if(skb==NULL) - return; - - skb_reserve(skb, dev->hard_header_len); - h = (struct ppp_header *)skb_put (skb, sizeof(struct ppp_header)); - h->address = CISCO_MULTICAST; - h->control = 0; - h->protocol = htons (CISCO_KEEPALIVE); - - ch = (struct cisco_packet*)skb_put(skb, CISCO_PACKET_LEN); - ch->type = htonl (type); - ch->par1 = htonl (par1); - ch->par2 = htonl (par2); - ch->rel = htons(0xffff); - ch->time0 = htons ((u16) (t >> 16)); - ch->time1 = htons ((u16) t); - - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: cisco output: <%xh %xh %xh %xh %xh-%xh>\n", - dev->name, ntohl (ch->type), ch->par1, - ch->par2, ch->rel, ch->time0, ch->time1); - skb->priority=TC_PRIO_CONTROL; - skb->dev = dev; - skb_queue_tail(&tx_queue, skb); -} - -/** - * sppp_close - close down a synchronous PPP or Cisco HDLC link - * @dev: The network device to drop the link of - * - * This drops the logical interface to the channel. It is not - * done politely as we assume we will also be dropping DTR. Any - * timeouts are killed. - */ - -int sppp_close (struct net_device *dev) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - unsigned long flags; - - spin_lock_irqsave(&sp->lock, flags); - sp->pp_link_state = SPPP_LINK_DOWN; - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - sppp_clear_timeout (sp); - spin_unlock_irqrestore(&sp->lock, flags); - - return 0; -} - -EXPORT_SYMBOL(sppp_close); - -/** - * sppp_open - open a synchronous PPP or Cisco HDLC link - * @dev: Network device to activate - * - * Close down any existing synchronous session and commence - * from scratch. In the PPP case this means negotiating LCP/IPCP - * and friends, while for Cisco HDLC we simply need to start sending - * keepalives - */ - -int sppp_open (struct net_device *dev) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - unsigned long flags; - - sppp_close(dev); - - spin_lock_irqsave(&sp->lock, flags); - if (!(sp->pp_flags & PP_CISCO)) { - sppp_lcp_open (sp); - } - sp->pp_link_state = SPPP_LINK_DOWN; - spin_unlock_irqrestore(&sp->lock, flags); - sppp_flush_xmit(); - - return 0; -} - -EXPORT_SYMBOL(sppp_open); - -/** - * sppp_reopen - notify of physical link loss - * @dev: Device that lost the link - * - * This function informs the synchronous protocol code that - * the underlying link died (for example a carrier drop on X.21) - * - * We increment the magic numbers to ensure that if the other end - * failed to notice we will correctly start a new session. It happens - * do to the nature of telco circuits is that you can lose carrier on - * one endonly. - * - * Having done this we go back to negotiating. This function may - * be called from an interrupt context. - */ - -int sppp_reopen (struct net_device *dev) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - unsigned long flags; - - sppp_close(dev); - - spin_lock_irqsave(&sp->lock, flags); - if (!(sp->pp_flags & PP_CISCO)) - { - sp->lcp.magic = jiffies; - ++sp->pp_seq; - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - /* Give it a moment for the line to settle then go */ - sppp_set_timeout (sp, 1); - } - sp->pp_link_state=SPPP_LINK_DOWN; - spin_unlock_irqrestore(&sp->lock, flags); - - return 0; -} - -EXPORT_SYMBOL(sppp_reopen); - -/** - * sppp_change_mtu - Change the link MTU - * @dev: Device to change MTU on - * @new_mtu: New MTU - * - * Change the MTU on the link. This can only be called with - * the link down. It returns an error if the link is up or - * the mtu is out of range. - */ - -static int sppp_change_mtu(struct net_device *dev, int new_mtu) -{ - if(new_mtu<128||new_mtu>PPP_MTU||(dev->flags&IFF_UP)) - return -EINVAL; - dev->mtu=new_mtu; - return 0; -} - -/** - * sppp_do_ioctl - Ioctl handler for ppp/hdlc - * @dev: Device subject to ioctl - * @ifr: Interface request block from the user - * @cmd: Command that is being issued - * - * This function handles the ioctls that may be issued by the user - * to control the settings of a PPP/HDLC link. It does both busy - * and security checks. This function is intended to be wrapped by - * callers who wish to add additional ioctl calls of their own. - */ - -int sppp_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct sppp *sp = (struct sppp *)sppp_of(dev); - - if(dev->flags&IFF_UP) - return -EBUSY; - - if(!capable(CAP_NET_ADMIN)) - return -EPERM; - - switch(cmd) - { - case SPPPIOCCISCO: - sp->pp_flags|=PP_CISCO; - dev->type = ARPHRD_HDLC; - break; - case SPPPIOCPPP: - sp->pp_flags&=~PP_CISCO; - dev->type = ARPHRD_PPP; - break; - case SPPPIOCDEBUG: - sp->pp_flags&=~PP_DEBUG; - if(ifr->ifr_flags) - sp->pp_flags|=PP_DEBUG; - break; - case SPPPIOCGFLAGS: - if(copy_to_user(ifr->ifr_data, &sp->pp_flags, sizeof(sp->pp_flags))) - return -EFAULT; - break; - case SPPPIOCSFLAGS: - if(copy_from_user(&sp->pp_flags, ifr->ifr_data, sizeof(sp->pp_flags))) - return -EFAULT; - break; - default: - return -EINVAL; - } - return 0; -} - -EXPORT_SYMBOL(sppp_do_ioctl); - -/** - * sppp_attach - attach synchronous PPP/HDLC to a device - * @pd: PPP device to initialise - * - * This initialises the PPP/HDLC support on an interface. At the - * time of calling the dev element must point to the network device - * that this interface is attached to. The interface should not yet - * be registered. - */ - -void sppp_attach(struct ppp_device *pd) -{ - struct net_device *dev = pd->dev; - struct sppp *sp = &pd->sppp; - unsigned long flags; - - /* Make sure embedding is safe for sppp_of */ - BUG_ON(sppp_of(dev) != sp); - - spin_lock_irqsave(&spppq_lock, flags); - /* Initialize keepalive handler. */ - if (! spppq) - { - init_timer(&sppp_keepalive_timer); - sppp_keepalive_timer.expires=jiffies+10*HZ; - sppp_keepalive_timer.function=sppp_keepalive; - add_timer(&sppp_keepalive_timer); - } - /* Insert new entry into the keepalive list. */ - sp->pp_next = spppq; - spppq = sp; - spin_unlock_irqrestore(&spppq_lock, flags); - - sp->pp_loopcnt = 0; - sp->pp_alivecnt = 0; - sp->pp_seq = 0; - sp->pp_rseq = 0; - sp->pp_flags = PP_KEEPALIVE|PP_CISCO|debug;/*PP_DEBUG;*/ - sp->lcp.magic = 0; - sp->lcp.state = LCP_STATE_CLOSED; - sp->ipcp.state = IPCP_STATE_CLOSED; - sp->pp_if = dev; - spin_lock_init(&sp->lock); - - /* - * Device specific setup. All but interrupt handler and - * hard_start_xmit. - */ - - dev->header_ops = &sppp_header_ops; - - dev->tx_queue_len = 10; - dev->type = ARPHRD_HDLC; - dev->addr_len = 0; - dev->hard_header_len = sizeof(struct ppp_header); - dev->mtu = PPP_MTU; - /* - * These 4 are callers but MUST also call sppp_ functions - */ - dev->do_ioctl = sppp_do_ioctl; -#if 0 - dev->get_stats = NULL; /* Let the driver override these */ - dev->open = sppp_open; - dev->stop = sppp_close; -#endif - dev->change_mtu = sppp_change_mtu; - dev->flags = IFF_MULTICAST|IFF_POINTOPOINT|IFF_NOARP; -} - -EXPORT_SYMBOL(sppp_attach); - -/** - * sppp_detach - release PPP resources from a device - * @dev: Network device to release - * - * Stop and free up any PPP/HDLC resources used by this - * interface. This must be called before the device is - * freed. - */ - -void sppp_detach (struct net_device *dev) -{ - struct sppp **q, *p, *sp = (struct sppp *)sppp_of(dev); - unsigned long flags; - - spin_lock_irqsave(&spppq_lock, flags); - /* Remove the entry from the keepalive list. */ - for (q = &spppq; (p = *q); q = &p->pp_next) - if (p == sp) { - *q = p->pp_next; - break; - } - - /* Stop keepalive handler. */ - if (! spppq) - del_timer(&sppp_keepalive_timer); - sppp_clear_timeout (sp); - spin_unlock_irqrestore(&spppq_lock, flags); -} - -EXPORT_SYMBOL(sppp_detach); - -/* - * Analyze the LCP Configure-Request options list - * for the presence of unknown options. - * If the request contains unknown options, build and - * send Configure-reject packet, containing only unknown options. - */ -static int -sppp_lcp_conf_parse_options (struct sppp *sp, struct lcp_header *h, - int len, u32 *magic) -{ - u8 *buf, *r, *p; - int rlen; - - len -= 4; - buf = r = kmalloc (len, GFP_ATOMIC); - if (! buf) - return (0); - - p = (void*) (h+1); - for (rlen=0; len>1 && p[1]; len-=p[1], p+=p[1]) { - switch (*p) { - case LCP_OPT_MAGIC: - /* Magic number -- extract. */ - if (len >= 6 && p[1] == 6) { - *magic = (u32)p[2] << 24 | - (u32)p[3] << 16 | p[4] << 8 | p[5]; - continue; - } - break; - case LCP_OPT_ASYNC_MAP: - /* Async control character map -- check to be zero. */ - if (len >= 6 && p[1] == 6 && ! p[2] && ! p[3] && - ! p[4] && ! p[5]) - continue; - break; - case LCP_OPT_MRU: - /* Maximum receive unit -- always OK. */ - continue; - default: - /* Others not supported. */ - break; - } - /* Add the option to rejected list. */ - memcpy(r, p, p[1]); - r += p[1]; - rlen += p[1]; - } - if (rlen) - sppp_cp_send (sp, PPP_LCP, LCP_CONF_REJ, h->ident, rlen, buf); - kfree(buf); - return (rlen == 0); -} - -static void sppp_ipcp_input (struct sppp *sp, struct sk_buff *skb) -{ - struct lcp_header *h; - struct net_device *dev = sp->pp_if; - int len = skb->len; - - if (!pskb_may_pull(skb, sizeof(struct lcp_header))) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid ipcp packet length: %d bytes\n", - dev->name, len); - return; - } - h = (struct lcp_header *)skb->data; - skb_pull(skb,sizeof(struct lcp_header)); - if (sp->pp_flags & PP_DEBUG) { - printk (KERN_WARNING "%s: ipcp input: %d bytes <%s id=%xh len=%xh", - dev->name, len, - sppp_ipcp_type_name (h->type), h->ident, ntohs (h->len)); - if (len > 4) - sppp_print_bytes ((u8*) (h+1), len-4); - printk (">\n"); - } - if (len > ntohs (h->len)) - len = ntohs (h->len); - switch (h->type) { - default: - /* Unknown packet type -- send Code-Reject packet. */ - sppp_cp_send (sp, PPP_IPCP, IPCP_CODE_REJ, ++sp->pp_seq, len, h); - break; - case IPCP_CONF_REQ: - if (len < 4) { - if (sp->pp_flags & PP_DEBUG) - printk (KERN_WARNING "%s: invalid ipcp configure request packet length: %d bytes\n", - dev->name, len); - return; - } - if (len > 4) { - sppp_cp_send (sp, PPP_IPCP, LCP_CONF_REJ, h->ident, - len-4, h+1); - - switch (sp->ipcp.state) { - case IPCP_STATE_OPENED: - /* Initiate renegotiation. */ - sppp_ipcp_open (sp); - /* fall through... */ - case IPCP_STATE_ACK_SENT: - /* Go to closed state. */ - sp->ipcp.state = IPCP_STATE_CLOSED; - } - } else { - /* Send Configure-Ack packet. */ - sppp_cp_send (sp, PPP_IPCP, IPCP_CONF_ACK, h->ident, - 0, NULL); - /* Change the state. */ - if (sp->ipcp.state == IPCP_STATE_ACK_RCVD) - sp->ipcp.state = IPCP_STATE_OPENED; - else - sp->ipcp.state = IPCP_STATE_ACK_SENT; - } - break; - case IPCP_CONF_ACK: - if (h->ident != sp->ipcp.confid) - break; - sppp_clear_timeout (sp); - switch (sp->ipcp.state) { - case IPCP_STATE_CLOSED: - sp->ipcp.state = IPCP_STATE_ACK_RCVD; - sppp_set_timeout (sp, 5); - break; - case IPCP_STATE_ACK_SENT: - sp->ipcp.state = IPCP_STATE_OPENED; - break; - } - break; - case IPCP_CONF_NAK: - case IPCP_CONF_REJ: - if (h->ident != sp->ipcp.confid) - break; - sppp_clear_timeout (sp); - /* Initiate renegotiation. */ - sppp_ipcp_open (sp); - if (sp->ipcp.state != IPCP_STATE_ACK_SENT) - /* Go to closed state. */ - sp->ipcp.state = IPCP_STATE_CLOSED; - break; - case IPCP_TERM_REQ: - /* Send Terminate-Ack packet. */ - sppp_cp_send (sp, PPP_IPCP, IPCP_TERM_ACK, h->ident, 0, NULL); - /* Go to closed state. */ - sp->ipcp.state = IPCP_STATE_CLOSED; - /* Initiate renegotiation. */ - sppp_ipcp_open (sp); - break; - case IPCP_TERM_ACK: - /* Ignore for now. */ - case IPCP_CODE_REJ: - /* Ignore for now. */ - break; - } -} - -static void sppp_lcp_open (struct sppp *sp) -{ - char opt[6]; - - if (! sp->lcp.magic) - sp->lcp.magic = jiffies; - opt[0] = LCP_OPT_MAGIC; - opt[1] = sizeof (opt); - opt[2] = sp->lcp.magic >> 24; - opt[3] = sp->lcp.magic >> 16; - opt[4] = sp->lcp.magic >> 8; - opt[5] = sp->lcp.magic; - sp->lcp.confid = ++sp->pp_seq; - sppp_cp_send (sp, PPP_LCP, LCP_CONF_REQ, sp->lcp.confid, - sizeof (opt), &opt); - sppp_set_timeout (sp, 2); -} - -static void sppp_ipcp_open (struct sppp *sp) -{ - sp->ipcp.confid = ++sp->pp_seq; - sppp_cp_send (sp, PPP_IPCP, IPCP_CONF_REQ, sp->ipcp.confid, 0, NULL); - sppp_set_timeout (sp, 2); -} - -/* - * Process PPP control protocol timeouts. - */ - -static void sppp_cp_timeout (unsigned long arg) -{ - struct sppp *sp = (struct sppp*) arg; - unsigned long flags; - - spin_lock_irqsave(&sp->lock, flags); - - sp->pp_flags &= ~PP_TIMO; - if (! (sp->pp_if->flags & IFF_UP) || (sp->pp_flags & PP_CISCO)) { - spin_unlock_irqrestore(&sp->lock, flags); - return; - } - switch (sp->lcp.state) { - case LCP_STATE_CLOSED: - /* No ACK for Configure-Request, retry. */ - sppp_lcp_open (sp); - break; - case LCP_STATE_ACK_RCVD: - /* ACK got, but no Configure-Request for peer, retry. */ - sppp_lcp_open (sp); - sp->lcp.state = LCP_STATE_CLOSED; - break; - case LCP_STATE_ACK_SENT: - /* ACK sent but no ACK for Configure-Request, retry. */ - sppp_lcp_open (sp); - break; - case LCP_STATE_OPENED: - /* LCP is already OK, try IPCP. */ - switch (sp->ipcp.state) { - case IPCP_STATE_CLOSED: - /* No ACK for Configure-Request, retry. */ - sppp_ipcp_open (sp); - break; - case IPCP_STATE_ACK_RCVD: - /* ACK got, but no Configure-Request for peer, retry. */ - sppp_ipcp_open (sp); - sp->ipcp.state = IPCP_STATE_CLOSED; - break; - case IPCP_STATE_ACK_SENT: - /* ACK sent but no ACK for Configure-Request, retry. */ - sppp_ipcp_open (sp); - break; - case IPCP_STATE_OPENED: - /* IPCP is OK. */ - break; - } - break; - } - spin_unlock_irqrestore(&sp->lock, flags); - sppp_flush_xmit(); -} - -static char *sppp_lcp_type_name (u8 type) -{ - static char buf [8]; - switch (type) { - case LCP_CONF_REQ: return ("conf-req"); - case LCP_CONF_ACK: return ("conf-ack"); - case LCP_CONF_NAK: return ("conf-nack"); - case LCP_CONF_REJ: return ("conf-rej"); - case LCP_TERM_REQ: return ("term-req"); - case LCP_TERM_ACK: return ("term-ack"); - case LCP_CODE_REJ: return ("code-rej"); - case LCP_PROTO_REJ: return ("proto-rej"); - case LCP_ECHO_REQ: return ("echo-req"); - case LCP_ECHO_REPLY: return ("echo-reply"); - case LCP_DISC_REQ: return ("discard-req"); - } - sprintf (buf, "%xh", type); - return (buf); -} - -static char *sppp_ipcp_type_name (u8 type) -{ - static char buf [8]; - switch (type) { - case IPCP_CONF_REQ: return ("conf-req"); - case IPCP_CONF_ACK: return ("conf-ack"); - case IPCP_CONF_NAK: return ("conf-nack"); - case IPCP_CONF_REJ: return ("conf-rej"); - case IPCP_TERM_REQ: return ("term-req"); - case IPCP_TERM_ACK: return ("term-ack"); - case IPCP_CODE_REJ: return ("code-rej"); - } - sprintf (buf, "%xh", type); - return (buf); -} - -static void sppp_print_bytes (u_char *p, u16 len) -{ - printk (" %x", *p++); - while (--len > 0) - printk ("-%x", *p++); -} - -/** - * sppp_rcv - receive and process a WAN PPP frame - * @skb: The buffer to process - * @dev: The device it arrived on - * @p: Unused - * @orig_dev: Unused - * - * Protocol glue. This drives the deferred processing mode the poorer - * cards use. This can be called directly by cards that do not have - * timing constraints but is normally called from the network layer - * after interrupt servicing to process frames queued via netif_rx. - */ - -static int sppp_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *p, struct net_device *orig_dev) -{ - if (dev_net(dev) != &init_net) { - kfree_skb(skb); - return 0; - } - - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) - return NET_RX_DROP; - sppp_input(dev,skb); - return 0; -} - -static struct packet_type sppp_packet_type = { - .type = __constant_htons(ETH_P_WAN_PPP), - .func = sppp_rcv, -}; - -static char banner[] __initdata = - KERN_INFO "Cronyx Ltd, Synchronous PPP and CISCO HDLC (c) 1994\n" - KERN_INFO "Linux port (c) 1998 Building Number Three Ltd & " - "Jan \"Yenya\" Kasprzak.\n"; - -static int __init sync_ppp_init(void) -{ - if(debug) - debug=PP_DEBUG; - printk(banner); - skb_queue_head_init(&tx_queue); - dev_add_pack(&sppp_packet_type); - return 0; -} - - -static void __exit sync_ppp_cleanup(void) -{ - dev_remove_pack(&sppp_packet_type); -} - -module_init(sync_ppp_init); -module_exit(sync_ppp_cleanup); -module_param(debug, int, 0); -MODULE_LICENSE("GPL"); - diff --git a/include/net/syncppp.h b/include/net/syncppp.h deleted file mode 100644 index 9e306f7f579a..000000000000 --- a/include/net/syncppp.h +++ /dev/null @@ -1,102 +0,0 @@ -/* - * Defines for synchronous PPP/Cisco link level subroutines. - * - * Copyright (C) 1994 Cronyx Ltd. - * Author: Serge Vakulenko, - * - * This software is distributed with NO WARRANTIES, not even the implied - * warranties for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. - * - * Authors grant any other persons or organizations permission to use - * or modify this software as long as this message is kept with the software, - * all derivative works or modified versions. - * - * Version 1.7, Wed Jun 7 22:12:02 MSD 1995 - * - * - * - */ - -#ifndef _SYNCPPP_H_ -#define _SYNCPPP_H_ 1 - -#ifdef __KERNEL__ -struct slcp { - u16 state; /* state machine */ - u32 magic; /* local magic number */ - u_char echoid; /* id of last keepalive echo request */ - u_char confid; /* id of last configuration request */ -}; - -struct sipcp { - u16 state; /* state machine */ - u_char confid; /* id of last configuration request */ -}; - -struct sppp -{ - struct sppp * pp_next; /* next interface in keepalive list */ - u32 pp_flags; /* use Cisco protocol instead of PPP */ - u16 pp_alivecnt; /* keepalive packets counter */ - u16 pp_loopcnt; /* loopback detection counter */ - u32 pp_seq; /* local sequence number */ - u32 pp_rseq; /* remote sequence number */ - struct slcp lcp; /* LCP params */ - struct sipcp ipcp; /* IPCP params */ - struct timer_list pp_timer; - struct net_device *pp_if; - char pp_link_state; /* Link status */ - spinlock_t lock; -}; - -struct ppp_device -{ - struct net_device *dev; /* Network device pointer */ - struct sppp sppp; /* Synchronous PPP */ -}; - -static inline struct sppp *sppp_of(struct net_device *dev) -{ - struct ppp_device **ppp = dev->ml_priv; - BUG_ON((*ppp)->dev != dev); - return &(*ppp)->sppp; -} - -#define PP_KEEPALIVE 0x01 /* use keepalive protocol */ -#define PP_CISCO 0x02 /* use Cisco protocol instead of PPP */ -#define PP_TIMO 0x04 /* cp_timeout routine active */ -#define PP_DEBUG 0x08 - -#define PPP_MTU 1500 /* max. transmit unit */ - -#define LCP_STATE_CLOSED 0 /* LCP state: closed (conf-req sent) */ -#define LCP_STATE_ACK_RCVD 1 /* LCP state: conf-ack received */ -#define LCP_STATE_ACK_SENT 2 /* LCP state: conf-ack sent */ -#define LCP_STATE_OPENED 3 /* LCP state: opened */ - -#define IPCP_STATE_CLOSED 0 /* IPCP state: closed (conf-req sent) */ -#define IPCP_STATE_ACK_RCVD 1 /* IPCP state: conf-ack received */ -#define IPCP_STATE_ACK_SENT 2 /* IPCP state: conf-ack sent */ -#define IPCP_STATE_OPENED 3 /* IPCP state: opened */ - -#define SPPP_LINK_DOWN 0 /* link down - no keepalive */ -#define SPPP_LINK_UP 1 /* link is up - keepalive ok */ - -void sppp_attach (struct ppp_device *pd); -void sppp_detach (struct net_device *dev); -int sppp_do_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd); -struct sk_buff *sppp_dequeue (struct net_device *dev); -int sppp_isempty (struct net_device *dev); -void sppp_flush (struct net_device *dev); -int sppp_open (struct net_device *dev); -int sppp_reopen (struct net_device *dev); -int sppp_close (struct net_device *dev); -#endif - -#define SPPPIOCCISCO (SIOCDEVPRIVATE) -#define SPPPIOCPPP (SIOCDEVPRIVATE+1) -#define SPPPIOCDEBUG (SIOCDEVPRIVATE+2) -#define SPPPIOCSFLAGS (SIOCDEVPRIVATE+3) -#define SPPPIOCGFLAGS (SIOCDEVPRIVATE+4) - -#endif /* _SYNCPPP_H_ */ -- cgit v1.2.3 From b20a9c24d5c5d466d7e4a25c6f1bedbd2d16ad4f Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Sun, 23 Nov 2008 16:02:31 -0800 Subject: dccp: Set per-connection CCIDs via socket options With this patch, TX/RX CCIDs can now be changed on a per-connection basis, which overrides the defaults set by the global sysctl variables for TX/RX CCIDs. To make full use of this facility, the remaining patches of this patch set are needed, which track dependencies and activate negotiated feature values. Signed-off-by: Gerrit Renker Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 14 ++++++++++++++ include/linux/dccp.h | 5 +++++ net/dccp/ackvec.c | 9 ++++----- net/dccp/ackvec.h | 5 ++--- net/dccp/feat.h | 2 ++ net/dccp/proto.c | 34 ++++++++++++++++++++++++++++++++++ 6 files changed, 61 insertions(+), 8 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 43df4487379b..610083ff73f6 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -61,6 +61,20 @@ DCCP_SOCKOPT_AVAILABLE_CCIDS is also read-only and returns the list of CCIDs supported by the endpoint (see include/linux/dccp.h for symbolic constants). The caller needs to provide a sufficiently large (> 2) array of type uint8_t. +DCCP_SOCKOPT_CCID is write-only and sets both the TX and RX CCIDs at the same +time, combining the operation of the next two socket options. This option is +preferrable over the latter two, since often applications will use the same +type of CCID for both directions; and mixed use of CCIDs is not currently well +understood. This socket option takes as argument at least one uint8_t value, or +an array of uint8_t values, which must match available CCIDS (see above). CCIDs +must be registered on the socket before calling connect() or listen(). + +DCCP_SOCKOPT_TX_CCID is read/write. It returns the current CCID (if set) or sets +the preference list for the TX CCID, using the same format as DCCP_SOCKOPT_CCID. +Please note that the getsockopt argument type here is `int', not uint8_t. + +DCCP_SOCKOPT_RX_CCID is analogous to DCCP_SOCKOPT_TX_CCID, but for the RX CCID. + DCCP_SOCKOPT_SERVER_TIMEWAIT enables the server (listening socket) to hold timewait state when closing the connection (RFC 4340, 8.3). The usual case is that the closing server sends a CloseReq, whereupon the client holds timewait diff --git a/include/linux/dccp.h b/include/linux/dccp.h index eda389ce04f4..6a72ff52a8a4 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -168,6 +168,8 @@ enum { DCCPO_MIN_CCID_SPECIFIC = 128, DCCPO_MAX_CCID_SPECIFIC = 255, }; +/* maximum size of a single TLV-encoded DCCP option (sans type/len bytes) */ +#define DCCP_SINGLE_OPT_MAXLEN 253 /* DCCP CCIDS */ enum { @@ -203,6 +205,9 @@ enum dccp_feature_numbers { #define DCCP_SOCKOPT_SEND_CSCOV 10 #define DCCP_SOCKOPT_RECV_CSCOV 11 #define DCCP_SOCKOPT_AVAILABLE_CCIDS 12 +#define DCCP_SOCKOPT_CCID 13 +#define DCCP_SOCKOPT_TX_CCID 14 +#define DCCP_SOCKOPT_RX_CCID 15 #define DCCP_SOCKOPT_CCID_RX_INFO 128 #define DCCP_SOCKOPT_CCID_TX_INFO 192 diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 1e8be246ad15..01e4d39fa232 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -12,7 +12,6 @@ #include "ackvec.h" #include "dccp.h" -#include #include #include #include @@ -68,7 +67,7 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) struct dccp_sock *dp = dccp_sk(sk); struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; /* Figure out how many options do we need to represent the ackvec */ - const u16 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_MAX_ACKVEC_OPT_LEN); + const u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN); u16 len = av->av_vec_len + 2 * nr_opts, i; u32 elapsed_time; const unsigned char *tail, *from; @@ -100,8 +99,8 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) for (i = 0; i < nr_opts; ++i) { int copylen = len; - if (len > DCCP_MAX_ACKVEC_OPT_LEN) - copylen = DCCP_MAX_ACKVEC_OPT_LEN; + if (len > DCCP_SINGLE_OPT_MAXLEN) + copylen = DCCP_SINGLE_OPT_MAXLEN; *to++ = DCCPO_ACK_VECTOR_0; *to++ = copylen + 2; @@ -432,7 +431,7 @@ found: int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, u64 *ackno, const u8 opt, const u8 *value, const u8 len) { - if (len > DCCP_MAX_ACKVEC_OPT_LEN) + if (len > DCCP_SINGLE_OPT_MAXLEN) return -1; /* dccp_ackvector_print(DCCP_SKB_CB(skb)->dccpd_ack_seq, value, len); */ diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index bcb64fb4acef..4ccee030524e 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -11,15 +11,14 @@ * published by the Free Software Foundation. */ +#include #include #include #include #include -/* Read about the ECN nonce to see why it is 253 */ -#define DCCP_MAX_ACKVEC_OPT_LEN 253 /* We can spread an ack vector across multiple options */ -#define DCCP_MAX_ACKVEC_LEN (DCCP_MAX_ACKVEC_OPT_LEN * 2) +#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2) #define DCCP_ACKVEC_STATE_RECEIVED 0 #define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) diff --git a/net/dccp/feat.h b/net/dccp/feat.h index 4d172822df17..093af1610d11 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -22,6 +22,8 @@ /* Wmin=32 and Wmax=2^46-1 from 7.5.2 */ #define DCCPF_SEQ_WMIN 32 #define DCCPF_SEQ_WMAX 0x3FFFFFFFFFFFull +/* Maximum number of SP values that fit in a single (Confirm) option */ +#define DCCP_FEAT_MAX_SP_VALS (DCCP_SINGLE_OPT_MAXLEN - 2) enum dccp_feat_type { FEAT_AT_RX = 1, /* located at RX side of half-connection */ diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 8b63394ec24c..445884cf1c29 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -501,6 +501,36 @@ static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) return rc; } +static int dccp_setsockopt_ccid(struct sock *sk, int type, + char __user *optval, int optlen) +{ + u8 *val; + int rc = 0; + + if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) + return -EINVAL; + + val = kmalloc(optlen, GFP_KERNEL); + if (val == NULL) + return -ENOMEM; + + if (copy_from_user(val, optval, optlen)) { + kfree(val); + return -EFAULT; + } + + lock_sock(sk); + if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID) + rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen); + + if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID)) + rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen); + release_sock(sk); + + kfree(val); + return rc; +} + static int do_dccp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { @@ -515,6 +545,10 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_CHANGE_R: DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n"); return 0; + case DCCP_SOCKOPT_CCID: + case DCCP_SOCKOPT_RX_CCID: + case DCCP_SOCKOPT_TX_CCID: + return dccp_setsockopt_ccid(sk, optname, optval, optlen); } if (optlen < (int)sizeof(int)) -- cgit v1.2.3 From b74ca3a896b9ab5f952bc440154758e708c48884 Mon Sep 17 00:00:00 2001 From: Wang Chen Date: Mon, 8 Dec 2008 01:14:16 -0800 Subject: netdevice: Kill netdev->priv This is the last shoot of this series. After I removing all directly reference of netdev->priv, I am killing "priv" of "struct net_device" and fixing relative comments/docs. Anyone will not be allowed to reference netdev->priv directly. If you want to reference the memory of private data, use netdev_priv() instead. If the private data is not allocted when alloc_netdev(), use netdev->ml_priv to point that memory after you creating that private data. Signed-off-by: Wang Chen Signed-off-by: David S. Miller --- Documentation/networking/driver.txt | 2 +- Documentation/networking/netdevices.txt | 2 +- drivers/net/3c501.h | 2 +- drivers/net/atp.c | 2 +- drivers/net/eexpress.c | 2 +- drivers/net/forcedeth.c | 4 ++-- drivers/net/lance.c | 2 +- drivers/net/myri_sbus.c | 2 +- drivers/net/pci-skeleton.c | 2 +- drivers/net/sun3_82586.c | 2 +- drivers/net/sunbmac.c | 2 +- drivers/net/tokenring/3c359.c | 5 +++-- drivers/net/via-rhine.c | 9 +++++---- drivers/net/wireless/strip.c | 2 +- include/linux/hdlc.h | 2 +- include/linux/netdevice.h | 1 - net/atm/mpc.c | 4 ++-- net/core/dev.c | 6 ------ 18 files changed, 24 insertions(+), 29 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/driver.txt b/Documentation/networking/driver.txt index ea72d2e66ca8..03283daa64fe 100644 --- a/Documentation/networking/driver.txt +++ b/Documentation/networking/driver.txt @@ -13,7 +13,7 @@ Transmit path guidelines: static int drv_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { - struct drv *dp = dev->priv; + struct drv *dp = netdev_priv(dev); lock_tx(dp); ... diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt index d0f71fc7f782..a2ab6a0b116d 100644 --- a/Documentation/networking/netdevices.txt +++ b/Documentation/networking/netdevices.txt @@ -18,7 +18,7 @@ There are routines in net_init.c to handle the common cases of alloc_etherdev, alloc_netdev. These reserve extra space for driver private data which gets freed when the network device is freed. If separately allocated data is attached to the network device -(dev->priv) then it is up to the module exit handler to free that. +(netdev_priv(dev)) then it is up to the module exit handler to free that. MTU === diff --git a/drivers/net/3c501.h b/drivers/net/3c501.h index cfec64efff78..f40b0493337a 100644 --- a/drivers/net/3c501.h +++ b/drivers/net/3c501.h @@ -23,7 +23,7 @@ static const struct ethtool_ops netdev_ethtool_ops; static int el_debug = EL_DEBUG; /* - * Board-specific info in dev->priv. + * Board-specific info in netdev_priv(dev). */ struct net_local diff --git a/drivers/net/atp.c b/drivers/net/atp.c index 7028b276dfd3..1d6b74c5d6c9 100644 --- a/drivers/net/atp.c +++ b/drivers/net/atp.c @@ -420,7 +420,7 @@ static unsigned short __init eeprom_op(long ioaddr, u32 cmd) registers that "should" only need to be set once at boot, so that there is non-reboot way to recover if something goes wrong. - This is an attachable device: if there is no dev->priv entry then it wasn't + This is an attachable device: if there is no private entry then it wasn't probed for at boot-time, and we need to probe for it again. */ static int net_open(struct net_device *dev) diff --git a/drivers/net/eexpress.c b/drivers/net/eexpress.c index a125e41240f5..9ff3f2f5e382 100644 --- a/drivers/net/eexpress.c +++ b/drivers/net/eexpress.c @@ -1046,7 +1046,7 @@ static void eexp_hw_tx_pio(struct net_device *dev, unsigned short *buf, /* * Sanity check the suspected EtherExpress card * Read hardware address, reset card, size memory and initialize buffer - * memory pointers. These are held in dev->priv, in case someone has more + * memory pointers. These are held in netdev_priv(), in case someone has more * than one card in a machine. */ diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 12384df8cb2b..1f2b24743ee9 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -712,12 +712,12 @@ struct nv_skb_map { /* * SMP locking: - * All hardware access under dev->priv->lock, except the performance + * All hardware access under netdev_priv(dev)->lock, except the performance * critical parts: * - rx is (pseudo-) lockless: it relies on the single-threading provided * by the arch code for interrupts. * - tx setup is lockless: it relies on netif_tx_lock. Actual submission - * needs dev->priv->lock :-( + * needs netdev_priv(dev)->lock :-( * - set_multicast_list: preparation lockless, relies on netif_tx_lock. */ diff --git a/drivers/net/lance.c b/drivers/net/lance.c index e81b6113ed94..d7afb938ea62 100644 --- a/drivers/net/lance.c +++ b/drivers/net/lance.c @@ -519,7 +519,7 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int } } - /* We can't allocate dev->priv from alloc_etherdev() because it must + /* We can't allocate private data from alloc_etherdev() because it must a ISA DMA-able region. */ chipname = chip_table[lance_version].name; printk("%s: %s at %#3x, ", dev->name, chipname, ioaddr); diff --git a/drivers/net/myri_sbus.c b/drivers/net/myri_sbus.c index 6833f65f8aec..899ed065a147 100644 --- a/drivers/net/myri_sbus.c +++ b/drivers/net/myri_sbus.c @@ -1091,7 +1091,7 @@ static int __devinit myri_sbus_probe(struct of_device *op, const struct of_devic err_free_irq: free_irq(dev->irq, dev); err: - /* This will also free the co-allocated 'dev->priv' */ + /* This will also free the co-allocated private data*/ free_netdev(dev); return -ENODEV; } diff --git a/drivers/net/pci-skeleton.c b/drivers/net/pci-skeleton.c index b23b5c397b1d..c95fd72c3bb9 100644 --- a/drivers/net/pci-skeleton.c +++ b/drivers/net/pci-skeleton.c @@ -781,7 +781,7 @@ static int __devinit netdrv_init_one (struct pci_dev *pdev, dev->irq = pdev->irq; dev->base_addr = (unsigned long) ioaddr; - /* dev->priv/tp zeroed and aligned in alloc_etherdev */ + /* netdev_priv()/tp zeroed and aligned in alloc_etherdev */ tp = netdev_priv(dev); /* note: tp->chipset set in netdrv_init_board */ diff --git a/drivers/net/sun3_82586.c b/drivers/net/sun3_82586.c index e8f97d5c9c23..e0d84772771c 100644 --- a/drivers/net/sun3_82586.c +++ b/drivers/net/sun3_82586.c @@ -209,7 +209,7 @@ static int sun3_82586_open(struct net_device *dev) static int check586(struct net_device *dev,char *where,unsigned size) { struct priv pb; - struct priv *p = /* (struct priv *) dev->priv*/ &pb; + struct priv *p = &pb; char *iscp_addr; int i; diff --git a/drivers/net/sunbmac.c b/drivers/net/sunbmac.c index 977b3e08bbfc..7f69c7f176c4 100644 --- a/drivers/net/sunbmac.c +++ b/drivers/net/sunbmac.c @@ -1233,7 +1233,7 @@ fail_and_cleanup: bp->bmac_block, bp->bblock_dvma); - /* This also frees the co-located 'dev->priv' */ + /* This also frees the co-located private data */ free_netdev(dev); return -ENODEV; } diff --git a/drivers/net/tokenring/3c359.c b/drivers/net/tokenring/3c359.c index e7a944657cf8..43853e3b210e 100644 --- a/drivers/net/tokenring/3c359.c +++ b/drivers/net/tokenring/3c359.c @@ -296,8 +296,9 @@ static int __devinit xl_probe(struct pci_dev *pdev, } ; /* - * Allowing init_trdev to allocate the dev->priv structure will align xl_private - * on a 32 bytes boundary which we need for the rx/tx descriptors + * Allowing init_trdev to allocate the private data will align + * xl_private on a 32 bytes boundary which we need for the rx/tx + * descriptors */ dev = alloc_trdev(sizeof(struct xl_private)) ; diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index 93b74b7b7077..8d405c83df8b 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -191,12 +191,13 @@ IIId. Synchronization The driver runs as two independent, single-threaded flows of control. One is the send-packet routine, which enforces single-threaded use by the -dev->priv->lock spinlock. The other thread is the interrupt handler, which -is single threaded by the hardware and interrupt handling software. +netdev_priv(dev)->lock spinlock. The other thread is the interrupt handler, +which is single threaded by the hardware and interrupt handling software. The send packet thread has partial control over the Tx ring. It locks the -dev->priv->lock whenever it's queuing a Tx packet. If the next slot in the ring -is not available it stops the transmit queue by calling netif_stop_queue. +netdev_priv(dev)->lock whenever it's queuing a Tx packet. If the next slot in +the ring is not available it stops the transmit queue by +calling netif_stop_queue. The interrupt handler has exclusive control over the Rx ring and records stats from the Tx ring. After reaping the stats, it marks the Tx queue entry as diff --git a/drivers/net/wireless/strip.c b/drivers/net/wireless/strip.c index 692e6c5e009a..dd0de3a9ed4e 100644 --- a/drivers/net/wireless/strip.c +++ b/drivers/net/wireless/strip.c @@ -2494,7 +2494,7 @@ static void strip_dev_setup(struct net_device *dev) dev->type = ARPHRD_METRICOM; /* dtang */ dev->hard_header_len = sizeof(STRIP_Header); /* - * dev->priv Already holds a pointer to our struct strip + * netdev_priv(dev) Already holds a pointer to our struct strip */ *(MetricomAddress *) & dev->broadcast = broadcast_address; diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index e960faac609d..fd47a151665e 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -43,7 +43,7 @@ struct hdlc_proto { }; -/* Pointed to by dev->priv */ +/* Pointed to by netdev_priv(dev) */ typedef struct hdlc_device { /* used by HDLC layer to take control over HDLC device from hw driver*/ int (*attach)(struct net_device *dev, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0df0db068ac3..47e731528315 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -785,7 +785,6 @@ struct net_device /* * One part is mostly used on xmit path (device) */ - void *priv; /* pointer to private data */ /* These may be needed for future network-power-down code. */ unsigned long trans_start; /* Time (in jiffies) of last Tx */ diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 12e9ea371db1..039d5cc72c3d 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -341,8 +341,8 @@ static const char *mpoa_device_type_string(char type) } /* - * lec device calls this via its dev->priv->lane2_ops->associate_indicator() - * when it sees a TLV in LE_ARP packet. + * lec device calls this via its netdev_priv(dev)->lane2_ops + * ->associate_indicator() when it sees a TLV in LE_ARP packet. * We fill in the pointer above when we see a LANE2 lec initializing * See LANE2 spec 3.1.5 * diff --git a/net/core/dev.c b/net/core/dev.c index 4615e9a443aa..f54cac76438a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4378,12 +4378,6 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev->num_tx_queues = queue_count; dev->real_num_tx_queues = queue_count; - if (sizeof_priv) { - dev->priv = ((char *)dev + - ((sizeof(struct net_device) + NETDEV_ALIGN_CONST) - & ~NETDEV_ALIGN_CONST)); - } - dev->gso_max_size = GSO_MAX_SIZE; netdev_init_queues(dev); -- cgit v1.2.3 From 0049bab5e765aa74cf767a834fa336e19453fc5e Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 8 Dec 2008 01:18:05 -0800 Subject: dccp: Remove obsolete parts of the old CCID interface The TX/RX CCIDs of the minisock are now redundant: similar to the Ack Vector case, their value equals initially that of the sysctl, but at the end of feature negotiation may be something different. The old interface removed by this patch thus has been replaced by the newer interface to dynamically query the currently loaded CCIDs. Also removed are the constructors for the TX CCID and the RX CCID, since the switch "rx <-> non-rx" is done by the handler in minisocks.c (and the handler is the only place in the code where CCIDs are loaded). Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 5 +++-- include/linux/dccp.h | 3 --- net/dccp/ccid.c | 14 -------------- net/dccp/ccid.h | 5 ----- net/dccp/feat.c | 13 ------------- net/dccp/minisocks.c | 2 -- 6 files changed, 3 insertions(+), 39 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 610083ff73f6..a203d132dbef 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -140,10 +140,11 @@ send_ackvec = 1 Whether or not to send Ack Vector options (sec. 11.5). tx_ccid = 2 - Default CCID for the sender-receiver half-connection. + Default CCID for the sender-receiver half-connection. Depending on the + choice of CCID, the Send Ack Vector feature is enabled automatically. rx_ccid = 2 - Default CCID for the receiver-sender half-connection. + Default CCID for the receiver-sender half-connection; see tx_ccid. seq_window = 100 The initial sequence window (sec. 7.5.2). diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 6a72ff52a8a4..46daea312d92 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -370,7 +370,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * Will be used to pass the state from dccp_request_sock to dccp_sock. * * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) - * @dccpms_ccid - Congestion Control Id (CCID) (section 10) * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2) * @dccpms_pending - List of features being negotiated @@ -378,8 +377,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) */ struct dccp_minisock { __u64 dccpms_sequence_window; - __u8 dccpms_rx_ccid; - __u8 dccpms_tx_ccid; __u8 dccpms_send_ack_vector; __u8 dccpms_send_ndp_count; struct list_head dccpms_pending; diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 647cb0614f84..bcc643f992ae 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -253,20 +253,6 @@ out_module_put: EXPORT_SYMBOL_GPL(ccid_new); -struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, gfp_t gfp) -{ - return ccid_new(id, sk, 1, gfp); -} - -EXPORT_SYMBOL_GPL(ccid_hc_rx_new); - -struct ccid *ccid_hc_tx_new(unsigned char id,struct sock *sk, gfp_t gfp) -{ - return ccid_new(id, sk, 0, gfp); -} - -EXPORT_SYMBOL_GPL(ccid_hc_tx_new); - static void ccid_delete(struct ccid *ccid, struct sock *sk, int rx) { struct ccid_operations *ccid_ops; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 803343aed004..18f69423a708 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -111,11 +111,6 @@ extern int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp); -extern struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, - gfp_t gfp); -extern struct ccid *ccid_hc_tx_new(unsigned char id, struct sock *sk, - gfp_t gfp); - static inline int ccid_get_current_rx_ccid(struct dccp_sock *dp) { struct ccid *ccid = dp->dccps_hc_rx_ccid; diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 077f78d579c4..a0d5891a37bf 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1124,22 +1124,9 @@ int dccp_feat_init(struct sock *sk) INIT_LIST_HEAD(&dmsk->dccpms_pending); /* XXX no longer used */ INIT_LIST_HEAD(&dmsk->dccpms_conf); /* XXX no longer used */ - /* CCID L */ - rc = __feat_register_sp(&dp->dccps_featneg, DCCPF_CCID, 1, 0, - &dmsk->dccpms_tx_ccid, 1); - if (rc) - goto out; - - /* CCID R */ - rc = __feat_register_sp(&dp->dccps_featneg, DCCPF_CCID, 0, 0, - &dmsk->dccpms_rx_ccid, 1); - if (rc) - goto out; - /* Ack ratio */ rc = __feat_register_nn(&dp->dccps_featneg, DCCPF_ACK_RATIO, 0, dp->dccps_l_ack_ratio); -out: return rc; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 308b6b928c3d..210c346899ba 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -45,8 +45,6 @@ EXPORT_SYMBOL_GPL(dccp_death_row); void dccp_minisock_init(struct dccp_minisock *dmsk) { dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window; - dmsk->dccpms_rx_ccid = sysctl_dccp_feat_rx_ccid; - dmsk->dccpms_tx_ccid = sysctl_dccp_feat_tx_ccid; dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; dmsk->dccpms_send_ndp_count = sysctl_dccp_feat_send_ndp_count; } -- cgit v1.2.3 From 4098dce5be537a157eed4a326efd464109825b8b Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 8 Dec 2008 01:18:37 -0800 Subject: dccp: Remove manual influence on NDP Count feature Updating the NDP count feature is handled automatically now: * for CCID-2 it is disabled, since the code does not use NDP counts; * for CCID-3 it is enabled, as NDP counts are used to determine loss lengths. Allowing the user to change NDP values leads to unpredictable and failing behaviour, since it is then possible to disable NDP counts even when they are needed (e.g. in CCID-3). This means that only those user settings are sensible that agree with the values for Send NDP Count implied by the choice of CCID. But those settings are already activated by the feature negotiation (CCID dependency tracking), hence this form of support is redundant. At startup the initialisation of the NDP count feature uses the default value of 0, which is done implicitly by the zeroing-out of the socket when it is allocated. If the choice of CCID or feature negotiation enables NDP count, this will then be updated via the NDP activation handler. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 3 --- include/linux/dccp.h | 4 ++-- net/dccp/dccp.h | 1 - net/dccp/feat.c | 2 +- net/dccp/minisocks.c | 1 - net/dccp/options.c | 4 +--- net/dccp/sysctl.c | 7 ------- 7 files changed, 4 insertions(+), 18 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index a203d132dbef..1403745ab406 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -133,9 +133,6 @@ retries2 importance for retransmitted acknowledgments and feature negotiation, data packets are never retransmitted. Analogue of tcp_retries2. -send_ndp = 1 - Whether or not to send NDP count options (sec. 7.7.2). - send_ackvec = 1 Whether or not to send Ack Vector options (sec. 11.5). diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 46daea312d92..60e94438eadd 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -371,14 +371,12 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) - * @dccpms_send_ndp_count - Send NDP Count Feature (7.7.2) * @dccpms_pending - List of features being negotiated * @dccpms_conf - */ struct dccp_minisock { __u64 dccpms_sequence_window; __u8 dccpms_send_ack_vector; - __u8 dccpms_send_ndp_count; struct list_head dccpms_pending; struct list_head dccpms_conf; }; @@ -490,6 +488,7 @@ struct dccp_ackvec; * @dccps_r_ack_ratio - feature-remote Ack Ratio * @dccps_pcslen - sender partial checksum coverage (via sockopt) * @dccps_pcrlen - receiver partial checksum coverage (via sockopt) + * @dccps_send_ndp_count - local Send NDP Count feature (7.7.2) * @dccps_ndp_count - number of Non Data Packets since last data packet * @dccps_mss_cache - current value of MSS (path MTU minus header sizes) * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4) @@ -529,6 +528,7 @@ struct dccp_sock { __u16 dccps_r_ack_ratio; __u8 dccps_pcslen:4; __u8 dccps_pcrlen:4; + __u8 dccps_send_ndp_count:1; __u64 dccps_ndp_count:48; unsigned long dccps_rate_last; struct dccp_minisock dccps_minisock; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 94f6785f81ec..e0759d098b9a 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -99,7 +99,6 @@ extern int sysctl_dccp_feat_sequence_window; extern int sysctl_dccp_feat_rx_ccid; extern int sysctl_dccp_feat_tx_ccid; extern int sysctl_dccp_feat_send_ack_vector; -extern int sysctl_dccp_feat_send_ndp_count; extern int sysctl_dccp_tx_qlen; extern int sysctl_dccp_sync_ratelimit; diff --git a/net/dccp/feat.c b/net/dccp/feat.c index a0d5891a37bf..30f9fb76b921 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -85,7 +85,7 @@ static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx) static int dccp_hdlr_ndp(struct sock *sk, u64 enable, bool rx) { if (!rx) - dccp_msk(sk)->dccpms_send_ndp_count = (enable > 0); + dccp_sk(sk)->dccps_send_ndp_count = (enable > 0); return 0; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 210c346899ba..02b14812464a 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -46,7 +46,6 @@ void dccp_minisock_init(struct dccp_minisock *dmsk) { dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window; dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; - dmsk->dccpms_send_ndp_count = sysctl_dccp_feat_send_ndp_count; } void dccp_time_wait(struct sock *sk, int state, int timeo) diff --git a/net/dccp/options.c b/net/dccp/options.c index debb1008c7ad..e9d674874b4e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -27,7 +27,6 @@ int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID; int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID; int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; -int sysctl_dccp_feat_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT; u64 dccp_decode_value_var(const u8 *bf, const u8 len) { @@ -531,8 +530,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_opt_len = 0; - if (dmsk->dccpms_send_ndp_count && - dccp_insert_option_ndp(sk, skb)) + if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb)) return -1; if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) { diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index f6e54f433e29..587c12f915c1 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -47,13 +47,6 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "send_ndp", - .data = &sysctl_dccp_feat_send_ndp_count, - .maxlen = sizeof(sysctl_dccp_feat_send_ndp_count), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "request_retries", .data = &sysctl_dccp_request_retries, -- cgit v1.2.3 From 6fdd34d43bff8be9bb925b49d87a0ee144d2ab07 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Mon, 8 Dec 2008 01:19:06 -0800 Subject: dccp ccid-2: Phase out the use of boolean Ack Vector sysctl This removes the use of the sysctl and the minisock variable for the Send Ack Vector feature, as it now is handled fully dynamically via feature negotiation (i.e. when CCID-2 is enabled, Ack Vectors are automatically enabled as per RFC 4341, 4.). Using a sysctl in parallel to this implementation would open the door to crashes, since much of the code relies on tests of the boolean minisock / sysctl variable. Thus, this patch replaces all tests of type if (dccp_msk(sk)->dccpms_send_ack_vector) /* ... */ with if (dp->dccps_hc_rx_ackvec != NULL) /* ... */ The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature negotiation concluded that Ack Vectors are to be used on the half-connection. Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child), so that the test is a valid one. The activation handler for Ack Vectors is called as soon as the feature negotiation has concluded at the * server when the Ack marking the transition RESPOND => OPEN arrives; * client after it has sent its ACK, marking the transition REQUEST => PARTOPEN. Adding the sequence number of the Response packet to the Ack Vector has been removed, since (a) connection establishment implies that the Response has been received; (b) the CCIDs only look at packets received in the (PART)OPEN state, i.e. this entry will always be ignored; (c) it can not be used for anything useful - to detect loss for instance, only packets received after the loss can serve as pseudo-dupacks. There was a FIXME to change the error code when dccp_ackvec_add() fails. I removed this after finding out that: * the check whether ackno < ISN is already made earlier, * this Response is likely the 1st packet with an Ackno that the client gets, * so when dccp_ackvec_add() fails, the reason is likely not a packet error. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald Signed-off-by: David S. Miller --- Documentation/networking/dccp.txt | 3 --- include/linux/dccp.h | 3 --- net/dccp/dccp.h | 3 +-- net/dccp/diag.c | 2 +- net/dccp/input.c | 12 +++--------- net/dccp/minisocks.c | 1 - net/dccp/options.c | 7 ++----- net/dccp/proto.c | 3 +-- net/dccp/sysctl.c | 7 ------- 9 files changed, 8 insertions(+), 33 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 1403745ab406..7a3bb1abb830 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -133,9 +133,6 @@ retries2 importance for retransmitted acknowledgments and feature negotiation, data packets are never retransmitted. Analogue of tcp_retries2. -send_ackvec = 1 - Whether or not to send Ack Vector options (sec. 11.5). - tx_ccid = 2 Default CCID for the sender-receiver half-connection. Depending on the choice of CCID, the Send Ack Vector feature is enabled automatically. diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 60e94438eadd..61734e27abb7 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -360,7 +360,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 #define DCCPF_INITIAL_ACK_RATIO 2 #define DCCPF_INITIAL_CCID DCCPC_CCID2 -#define DCCPF_INITIAL_SEND_ACK_VECTOR 1 /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 @@ -370,13 +369,11 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * Will be used to pass the state from dccp_request_sock to dccp_sock. * * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) - * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) * @dccpms_pending - List of features being negotiated * @dccpms_conf - */ struct dccp_minisock { __u64 dccpms_sequence_window; - __u8 dccpms_send_ack_vector; struct list_head dccpms_pending; struct list_head dccpms_conf; }; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index e0759d098b9a..0bc4c9a02e19 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -98,7 +98,6 @@ extern int sysctl_dccp_retries2; extern int sysctl_dccp_feat_sequence_window; extern int sysctl_dccp_feat_rx_ccid; extern int sysctl_dccp_feat_tx_ccid; -extern int sysctl_dccp_feat_send_ack_vector; extern int sysctl_dccp_tx_qlen; extern int sysctl_dccp_sync_ratelimit; @@ -434,7 +433,7 @@ static inline int dccp_ack_pending(const struct sock *sk) const struct dccp_sock *dp = dccp_sk(sk); return dp->dccps_timestamp_echo != 0 || #ifdef CONFIG_IP_DCCP_ACKVEC - (dccp_msk(sk)->dccpms_send_ack_vector && + (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || #endif inet_csk_ack_scheduled(sk); diff --git a/net/dccp/diag.c b/net/dccp/diag.c index d1e100395efb..652a1b67f727 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -29,7 +29,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_backoff = icsk->icsk_backoff; info->tcpi_pmtu = icsk->icsk_pmtu_cookie; - if (dccp_msk(sk)->dccpms_send_ack_vector) + if (dp->dccps_hc_rx_ackvec != NULL) info->tcpi_options |= TCPI_OPT_SACK; ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); diff --git a/net/dccp/input.c b/net/dccp/input.c index 0672b7e1763e..5eb443f656c1 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -163,7 +163,7 @@ static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - if (dccp_msk(sk)->dccpms_send_ack_vector) + if (dp->dccps_hc_rx_ackvec != NULL) dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_ack_seq); } @@ -375,7 +375,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -434,12 +434,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp - dp->dccps_options_received.dccpor_timestamp_echo)); - if (dccp_msk(sk)->dccpms_send_ack_vector && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) - goto out_invalid_packet; /* FIXME: change error code */ - /* Stop the REQUEST timer */ inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); WARN_ON(sk->sk_send_head == NULL); @@ -637,7 +631,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 02b14812464a..6821ae33dd37 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -45,7 +45,6 @@ EXPORT_SYMBOL_GPL(dccp_death_row); void dccp_minisock_init(struct dccp_minisock *dmsk) { dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window; - dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; } void dccp_time_wait(struct sock *sk, int state, int timeo) diff --git a/net/dccp/options.c b/net/dccp/options.c index e9d674874b4e..7b1165c21f51 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -26,7 +26,6 @@ int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID; int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID; -int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; u64 dccp_decode_value_var(const u8 *bf, const u8 len) { @@ -145,8 +144,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; - - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_parse(sk, skb, &ackno, opt, value, len)) goto out_invalid_option; break; @@ -526,7 +524,6 @@ static void dccp_insert_option_padding(struct sk_buff *skb) int dccp_insert_options(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; @@ -547,7 +544,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) if (dccp_insert_option_timestamp(sk, skb)) return -1; - } else if (dmsk->dccpms_send_ack_vector && + } else if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && dccp_insert_option_ackvec(sk, skb)) { return -1; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 0941f8fe1675..d5c2bacb713c 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -201,7 +201,6 @@ EXPORT_SYMBOL_GPL(dccp_init_sock); void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); /* * DCCP doesn't use sk_write_queue, just sk_send_head @@ -219,7 +218,7 @@ void dccp_destroy_sock(struct sock *sk) kfree(dp->dccps_service_list); dp->dccps_service_list = NULL; - if (dmsk->dccpms_send_ack_vector) { + if (dp->dccps_hc_rx_ackvec != NULL) { dccp_ackvec_free(dp->dccps_hc_rx_ackvec); dp->dccps_hc_rx_ackvec = NULL; } diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 587c12f915c1..018e210875e1 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -40,13 +40,6 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "send_ackvec", - .data = &sysctl_dccp_feat_send_ack_vector, - .maxlen = sizeof(sysctl_dccp_feat_send_ack_vector), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "request_retries", .data = &sysctl_dccp_request_retries, -- cgit v1.2.3 From b31a1d8b41513b96e9c7ec2f68c5734cef0b26a4 Mon Sep 17 00:00:00 2001 From: Andy Fleming Date: Tue, 16 Dec 2008 15:29:15 -0800 Subject: gianfar: Convert gianfar to an of_platform_driver Does the same for the accompanying MDIO driver, and then modifies the TBI configuration method. The old way used fields in einfo, which no longer exists. The new way is to create an MDIO device-tree node for each instance of gianfar, and create a tbi-handle property to associate ethernet controllers with the TBI PHYs they are connected to. Signed-off-by: Andy Fleming Signed-off-by: David S. Miller --- Documentation/powerpc/dts-bindings/fsl/tsec.txt | 12 +- arch/powerpc/boot/dts/asp834x-redboot.dts | 20 ++ arch/powerpc/boot/dts/ksi8560.dts | 20 ++ arch/powerpc/boot/dts/mpc8313erdb.dts | 20 ++ arch/powerpc/boot/dts/mpc8315erdb.dts | 19 ++ arch/powerpc/boot/dts/mpc8349emitx.dts | 18 ++ arch/powerpc/boot/dts/mpc8349emitxgp.dts | 5 + arch/powerpc/boot/dts/mpc834x_mds.dts | 19 ++ arch/powerpc/boot/dts/mpc8377_mds.dts | 19 ++ arch/powerpc/boot/dts/mpc8377_rdb.dts | 19 ++ arch/powerpc/boot/dts/mpc8378_mds.dts | 19 ++ arch/powerpc/boot/dts/mpc8378_rdb.dts | 17 ++ arch/powerpc/boot/dts/mpc8379_mds.dts | 18 ++ arch/powerpc/boot/dts/mpc8379_rdb.dts | 18 ++ arch/powerpc/boot/dts/mpc8536ds.dts | 18 ++ arch/powerpc/boot/dts/mpc8540ads.dts | 31 +++ arch/powerpc/boot/dts/mpc8541cds.dts | 18 ++ arch/powerpc/boot/dts/mpc8544ds.dts | 20 ++ arch/powerpc/boot/dts/mpc8548cds.dts | 44 ++++ arch/powerpc/boot/dts/mpc8555cds.dts | 18 ++ arch/powerpc/boot/dts/mpc8560ads.dts | 18 ++ arch/powerpc/boot/dts/mpc8568mds.dts | 18 ++ arch/powerpc/boot/dts/mpc8572ds.dts | 45 ++++ arch/powerpc/boot/dts/mpc8641_hpcn.dts | 45 ++++ arch/powerpc/boot/dts/sbc8349.dts | 18 ++ arch/powerpc/boot/dts/sbc8548.dts | 18 ++ arch/powerpc/boot/dts/sbc8560.dts | 18 ++ arch/powerpc/boot/dts/sbc8641d.dts | 44 ++++ arch/powerpc/boot/dts/stx_gp3_8560.dts | 18 ++ arch/powerpc/boot/dts/tqm8540.dts | 28 +++ arch/powerpc/boot/dts/tqm8541.dts | 18 ++ arch/powerpc/boot/dts/tqm8548-bigflash.dts | 44 ++++ arch/powerpc/boot/dts/tqm8548.dts | 44 ++++ arch/powerpc/boot/dts/tqm8555.dts | 18 ++ arch/powerpc/boot/dts/tqm8560.dts | 18 ++ arch/powerpc/sysdev/fsl_soc.c | 241 +++--------------- drivers/net/gianfar.c | 321 ++++++++++++++++-------- drivers/net/gianfar.h | 21 +- drivers/net/gianfar_ethtool.c | 22 +- drivers/net/gianfar_mii.c | 212 +++++++++++----- drivers/net/gianfar_mii.h | 2 + include/linux/fsl_devices.h | 18 +- 42 files changed, 1217 insertions(+), 424 deletions(-) (limited to 'Documentation') diff --git a/Documentation/powerpc/dts-bindings/fsl/tsec.txt b/Documentation/powerpc/dts-bindings/fsl/tsec.txt index cf55fa4112d2..7fa4b27574b5 100644 --- a/Documentation/powerpc/dts-bindings/fsl/tsec.txt +++ b/Documentation/powerpc/dts-bindings/fsl/tsec.txt @@ -2,8 +2,8 @@ The MDIO is a bus to which the PHY devices are connected. For each device that exists on this bus, a child node should be created. See -the definition of the PHY node below for an example of how to define -a PHY. +the definition of the PHY node in booting-without-of.txt for an example +of how to define a PHY. Required properties: - reg : Offset and length of the register set for the device @@ -21,6 +21,14 @@ Example: }; }; +* TBI Internal MDIO bus + +As of this writing, every tsec is associated with an internal TBI PHY. +This PHY is accessed through the local MDIO bus. These buses are defined +similarly to the mdio buses, except they are compatible with "fsl,gianfar-tbi". +The TBI PHYs underneath them are similar to normal PHYs, but the reg property +is considered instructive, rather than descriptive. The reg property should +be chosen so it doesn't interfere with other PHYs on the bus. * Gianfar-compatible ethernet nodes diff --git a/arch/powerpc/boot/dts/asp834x-redboot.dts b/arch/powerpc/boot/dts/asp834x-redboot.dts index 6235fca445de..524af7ef9f26 100644 --- a/arch/powerpc/boot/dts/asp834x-redboot.dts +++ b/arch/powerpc/boot/dts/asp834x-redboot.dts @@ -199,8 +199,26 @@ reg = <0x2>; device_type = "ethernet-phy"; }; + + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -210,6 +228,7 @@ local-mac-address = [ 00 08 e5 11 32 33 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; linux,network-index = <0>; }; @@ -223,6 +242,7 @@ local-mac-address = [ 00 08 e5 11 32 34 ]; interrupts = <35 0x8 36 0x8 37 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; linux,network-index = <1>; }; diff --git a/arch/powerpc/boot/dts/ksi8560.dts b/arch/powerpc/boot/dts/ksi8560.dts index 49737589ffc8..3bfff47418db 100644 --- a/arch/powerpc/boot/dts/ksi8560.dts +++ b/arch/powerpc/boot/dts/ksi8560.dts @@ -141,8 +141,26 @@ reg = <0x2>; device_type = "ethernet-phy"; }; + + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + enet0: ethernet@24000 { device_type = "network"; model = "TSEC"; @@ -152,6 +170,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&PHY1>; }; @@ -164,6 +183,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&PHY2>; }; diff --git a/arch/powerpc/boot/dts/mpc8313erdb.dts b/arch/powerpc/boot/dts/mpc8313erdb.dts index 503031766825..d4df8b6857a4 100644 --- a/arch/powerpc/boot/dts/mpc8313erdb.dts +++ b/arch/powerpc/boot/dts/mpc8313erdb.dts @@ -190,6 +190,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 0x8 36 0x8 35 0x8>; interrupt-parent = <&ipic>; + tbi-handle = < &tbi0 >; phy-handle = < &phy1 >; fsl,magic-packet; @@ -210,6 +211,10 @@ reg = <0x4>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; }; @@ -222,9 +227,24 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <34 0x8 33 0x8 32 0x8>; interrupt-parent = <&ipic>; + tbi-handle = < &tbi1 >; phy-handle = < &phy4 >; sleep = <&pmc 0x10000000>; fsl,magic-packet; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + }; serial0: serial@4500 { diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts index 6b850670de1d..d2cdd47a246d 100644 --- a/arch/powerpc/boot/dts/mpc8315erdb.dts +++ b/arch/powerpc/boot/dts/mpc8315erdb.dts @@ -206,8 +206,25 @@ reg = <0x1>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -217,6 +234,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = < &phy0 >; }; @@ -229,6 +247,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 0x8 36 0x8 37 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = < &phy1 >; }; diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts index 4bdbaf4993a1..712783d0707e 100644 --- a/arch/powerpc/boot/dts/mpc8349emitx.dts +++ b/arch/powerpc/boot/dts/mpc8349emitx.dts @@ -184,6 +184,22 @@ reg = <0x1c>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -195,6 +211,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy1c>; linux,network-index = <0>; }; @@ -211,6 +228,7 @@ /* Vitesse 7385 isn't on the MDIO bus */ fixed-link = <1 1 1000 0 0>; linux,network-index = <1>; + tbi-handle = <&tbi1>; }; serial0: serial@4500 { diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts index fa40647ee62e..3e918af41fb1 100644 --- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts +++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts @@ -163,6 +163,10 @@ reg = <0x1c>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -174,6 +178,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy1c>; linux,network-index = <0>; }; diff --git a/arch/powerpc/boot/dts/mpc834x_mds.dts b/arch/powerpc/boot/dts/mpc834x_mds.dts index c986c541e9bb..d9adba01c09c 100644 --- a/arch/powerpc/boot/dts/mpc834x_mds.dts +++ b/arch/powerpc/boot/dts/mpc834x_mds.dts @@ -185,8 +185,25 @@ reg = <0x1>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -196,6 +213,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; linux,network-index = <0>; }; @@ -209,6 +227,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 0x8 36 0x8 37 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; linux,network-index = <1>; }; diff --git a/arch/powerpc/boot/dts/mpc8377_mds.dts b/arch/powerpc/boot/dts/mpc8377_mds.dts index 0484561bd2c0..1d14d7052e6d 100644 --- a/arch/powerpc/boot/dts/mpc8377_mds.dts +++ b/arch/powerpc/boot/dts/mpc8377_mds.dts @@ -193,8 +193,25 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -205,6 +222,7 @@ interrupts = <32 0x8 33 0x8 34 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -218,6 +236,7 @@ interrupts = <35 0x8 36 0x8 37 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy3>; }; diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts index 435ef3dd022d..31f348fdfe14 100644 --- a/arch/powerpc/boot/dts/mpc8377_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts @@ -211,8 +211,25 @@ reg = <0x2>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -223,6 +240,7 @@ interrupts = <32 0x8 33 0x8 34 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -237,6 +255,7 @@ phy-connection-type = "mii"; interrupt-parent = <&ipic>; fixed-link = <1 1 1000 0 0>; + tbi-handle = <&tbi1>; }; serial0: serial@4500 { diff --git a/arch/powerpc/boot/dts/mpc8378_mds.dts b/arch/powerpc/boot/dts/mpc8378_mds.dts index 67a08d2e2ff2..b85fc02682d2 100644 --- a/arch/powerpc/boot/dts/mpc8378_mds.dts +++ b/arch/powerpc/boot/dts/mpc8378_mds.dts @@ -232,8 +232,25 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -244,6 +261,7 @@ interrupts = <32 0x8 33 0x8 34 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -257,6 +275,7 @@ interrupts = <35 0x8 36 0x8 37 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy3>; }; diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts index b11e68f56a06..7a2bad038bd6 100644 --- a/arch/powerpc/boot/dts/mpc8378_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts @@ -211,8 +211,25 @@ reg = <0x2>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; diff --git a/arch/powerpc/boot/dts/mpc8379_mds.dts b/arch/powerpc/boot/dts/mpc8379_mds.dts index 323370a2b5ff..acf06c438dbf 100644 --- a/arch/powerpc/boot/dts/mpc8379_mds.dts +++ b/arch/powerpc/boot/dts/mpc8379_mds.dts @@ -232,6 +232,22 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -244,6 +260,7 @@ interrupts = <32 0x8 33 0x8 34 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -257,6 +274,7 @@ interrupts = <35 0x8 36 0x8 37 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy3>; }; diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts index 337af6ea26d3..e067616f3f42 100644 --- a/arch/powerpc/boot/dts/mpc8379_rdb.dts +++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts @@ -211,6 +211,22 @@ reg = <0x2>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -223,6 +239,7 @@ interrupts = <32 0x8 33 0x8 34 0x8>; phy-connection-type = "mii"; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -237,6 +254,7 @@ phy-connection-type = "mii"; interrupt-parent = <&ipic>; fixed-link = <1 1 1000 0 0>; + tbi-handle = <&tbi1>; }; serial0: serial@4500 { diff --git a/arch/powerpc/boot/dts/mpc8536ds.dts b/arch/powerpc/boot/dts/mpc8536ds.dts index 35db1e5440c7..3c905df1812c 100644 --- a/arch/powerpc/boot/dts/mpc8536ds.dts +++ b/arch/powerpc/boot/dts/mpc8536ds.dts @@ -155,6 +155,22 @@ reg = <1>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; usb@22000 { @@ -186,6 +202,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy1>; phy-connection-type = "rgmii-id"; }; @@ -199,6 +216,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy0>; phy-connection-type = "rgmii-id"; }; diff --git a/arch/powerpc/boot/dts/mpc8540ads.dts b/arch/powerpc/boot/dts/mpc8540ads.dts index 9568bfaff8f7..79570ffe41b9 100644 --- a/arch/powerpc/boot/dts/mpc8540ads.dts +++ b/arch/powerpc/boot/dts/mpc8540ads.dts @@ -150,6 +150,34 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -161,6 +189,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -173,6 +202,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; @@ -185,6 +215,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <41 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy3>; }; diff --git a/arch/powerpc/boot/dts/mpc8541cds.dts b/arch/powerpc/boot/dts/mpc8541cds.dts index 6480f4fd96e0..221036a8ce23 100644 --- a/arch/powerpc/boot/dts/mpc8541cds.dts +++ b/arch/powerpc/boot/dts/mpc8541cds.dts @@ -144,6 +144,22 @@ reg = <0x1>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -155,6 +171,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -167,6 +184,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/mpc8544ds.dts b/arch/powerpc/boot/dts/mpc8544ds.dts index f1fb20737e3e..b9da42105066 100644 --- a/arch/powerpc/boot/dts/mpc8544ds.dts +++ b/arch/powerpc/boot/dts/mpc8544ds.dts @@ -116,8 +116,26 @@ reg = <0x1>; device_type = "ethernet-phy"; }; + + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + dma@21300 { #address-cells = <1>; #size-cells = <1>; @@ -169,6 +187,7 @@ interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; phy-handle = <&phy0>; + tbi-handle = <&tbi0>; phy-connection-type = "rgmii-id"; }; @@ -182,6 +201,7 @@ interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; phy-handle = <&phy1>; + tbi-handle = <&tbi1>; phy-connection-type = "rgmii-id"; }; diff --git a/arch/powerpc/boot/dts/mpc8548cds.dts b/arch/powerpc/boot/dts/mpc8548cds.dts index 431b496270dc..df774a7088ff 100644 --- a/arch/powerpc/boot/dts/mpc8548cds.dts +++ b/arch/powerpc/boot/dts/mpc8548cds.dts @@ -172,6 +172,46 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -183,6 +223,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -195,6 +236,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; @@ -208,6 +250,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy2>; }; @@ -220,6 +263,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy3>; }; */ diff --git a/arch/powerpc/boot/dts/mpc8555cds.dts b/arch/powerpc/boot/dts/mpc8555cds.dts index d833a5c4f476..053b01e1c93b 100644 --- a/arch/powerpc/boot/dts/mpc8555cds.dts +++ b/arch/powerpc/boot/dts/mpc8555cds.dts @@ -144,6 +144,22 @@ reg = <0x1>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -155,6 +171,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -167,6 +184,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/mpc8560ads.dts b/arch/powerpc/boot/dts/mpc8560ads.dts index 4d1f2f284094..11b1bcbe14ce 100644 --- a/arch/powerpc/boot/dts/mpc8560ads.dts +++ b/arch/powerpc/boot/dts/mpc8560ads.dts @@ -145,6 +145,22 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -156,6 +172,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -168,6 +185,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/mpc8568mds.dts b/arch/powerpc/boot/dts/mpc8568mds.dts index c80158f7741d..1955bd9e113d 100644 --- a/arch/powerpc/boot/dts/mpc8568mds.dts +++ b/arch/powerpc/boot/dts/mpc8568mds.dts @@ -179,6 +179,22 @@ reg = <0x3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -190,6 +206,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -202,6 +219,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy3>; }; diff --git a/arch/powerpc/boot/dts/mpc8572ds.dts b/arch/powerpc/boot/dts/mpc8572ds.dts index 5c69b2fafd32..05f67253b49f 100644 --- a/arch/powerpc/boot/dts/mpc8572ds.dts +++ b/arch/powerpc/boot/dts/mpc8572ds.dts @@ -225,6 +225,47 @@ interrupts = <10 1>; reg = <0x3>; }; + + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -236,6 +277,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; phy-connection-type = "rgmii-id"; }; @@ -249,6 +291,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; phy-connection-type = "rgmii-id"; }; @@ -262,6 +305,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy2>; phy-connection-type = "rgmii-id"; }; @@ -275,6 +319,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy3>; phy-connection-type = "rgmii-id"; }; diff --git a/arch/powerpc/boot/dts/mpc8641_hpcn.dts b/arch/powerpc/boot/dts/mpc8641_hpcn.dts index d665e767822a..35d5e248ccd7 100644 --- a/arch/powerpc/boot/dts/mpc8641_hpcn.dts +++ b/arch/powerpc/boot/dts/mpc8641_hpcn.dts @@ -205,8 +205,49 @@ reg = <3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; + enet0: ethernet@24000 { cell-index = <0>; device_type = "network"; @@ -216,6 +257,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; phy-connection-type = "rgmii-id"; }; @@ -229,6 +271,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; phy-connection-type = "rgmii-id"; }; @@ -242,6 +285,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy2>; phy-connection-type = "rgmii-id"; }; @@ -255,6 +299,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy3>; phy-connection-type = "rgmii-id"; }; diff --git a/arch/powerpc/boot/dts/sbc8349.dts b/arch/powerpc/boot/dts/sbc8349.dts index 0f941f310e44..8d365a57ebc1 100644 --- a/arch/powerpc/boot/dts/sbc8349.dts +++ b/arch/powerpc/boot/dts/sbc8349.dts @@ -177,6 +177,22 @@ reg = <0x1a>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -188,6 +204,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <32 0x8 33 0x8 34 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; linux,network-index = <0>; }; @@ -201,6 +218,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 0x8 36 0x8 37 0x8>; interrupt-parent = <&ipic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; linux,network-index = <1>; }; diff --git a/arch/powerpc/boot/dts/sbc8548.dts b/arch/powerpc/boot/dts/sbc8548.dts index 333552b4e90d..2baf4a51f224 100644 --- a/arch/powerpc/boot/dts/sbc8548.dts +++ b/arch/powerpc/boot/dts/sbc8548.dts @@ -252,6 +252,22 @@ reg = <0x1a>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -263,6 +279,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -275,6 +292,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/sbc8560.dts b/arch/powerpc/boot/dts/sbc8560.dts index db3632ef9888..01542f7062ab 100644 --- a/arch/powerpc/boot/dts/sbc8560.dts +++ b/arch/powerpc/boot/dts/sbc8560.dts @@ -168,6 +168,22 @@ reg = <0x1c>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -179,6 +195,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x1d 0x2 0x1e 0x2 0x22 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; }; @@ -191,6 +208,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <0x23 0x2 0x24 0x2 0x28 0x2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/sbc8641d.dts b/arch/powerpc/boot/dts/sbc8641d.dts index 9652456158fb..36db981548e4 100644 --- a/arch/powerpc/boot/dts/sbc8641d.dts +++ b/arch/powerpc/boot/dts/sbc8641d.dts @@ -222,6 +222,46 @@ reg = <2>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -233,6 +273,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy0>; phy-connection-type = "rgmii-id"; }; @@ -246,6 +287,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; phy-connection-type = "rgmii-id"; }; @@ -259,6 +301,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy2>; phy-connection-type = "rgmii-id"; }; @@ -272,6 +315,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy3>; phy-connection-type = "rgmii-id"; }; diff --git a/arch/powerpc/boot/dts/stx_gp3_8560.dts b/arch/powerpc/boot/dts/stx_gp3_8560.dts index fcd1db6ca0a8..fff33fe6efc6 100644 --- a/arch/powerpc/boot/dts/stx_gp3_8560.dts +++ b/arch/powerpc/boot/dts/stx_gp3_8560.dts @@ -142,6 +142,22 @@ reg = <4>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -153,6 +169,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -165,6 +182,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy4>; }; diff --git a/arch/powerpc/boot/dts/tqm8540.dts b/arch/powerpc/boot/dts/tqm8540.dts index e1d260b9085e..a693f01c21aa 100644 --- a/arch/powerpc/boot/dts/tqm8540.dts +++ b/arch/powerpc/boot/dts/tqm8540.dts @@ -155,6 +155,34 @@ reg = <3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { diff --git a/arch/powerpc/boot/dts/tqm8541.dts b/arch/powerpc/boot/dts/tqm8541.dts index d76441ec5dc7..9e3f5f0dde20 100644 --- a/arch/powerpc/boot/dts/tqm8541.dts +++ b/arch/powerpc/boot/dts/tqm8541.dts @@ -154,6 +154,22 @@ reg = <3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -165,6 +181,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -177,6 +194,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/tqm8548-bigflash.dts b/arch/powerpc/boot/dts/tqm8548-bigflash.dts index 4199e89b4e50..15086eb65c50 100644 --- a/arch/powerpc/boot/dts/tqm8548-bigflash.dts +++ b/arch/powerpc/boot/dts/tqm8548-bigflash.dts @@ -179,6 +179,46 @@ reg = <5>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -190,6 +230,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -202,6 +243,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; @@ -214,6 +256,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy3>; }; @@ -226,6 +269,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy4>; }; diff --git a/arch/powerpc/boot/dts/tqm8548.dts b/arch/powerpc/boot/dts/tqm8548.dts index 58ee4185454b..b7b65f5e79b6 100644 --- a/arch/powerpc/boot/dts/tqm8548.dts +++ b/arch/powerpc/boot/dts/tqm8548.dts @@ -179,6 +179,46 @@ reg = <5>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@26520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x26520 0x20>; + + tbi2: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@27520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x27520 0x20>; + + tbi3: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -190,6 +230,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -202,6 +243,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; @@ -214,6 +256,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <31 2 32 2 33 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi2>; phy-handle = <&phy3>; }; @@ -226,6 +269,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <37 2 38 2 39 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi3>; phy-handle = <&phy4>; }; diff --git a/arch/powerpc/boot/dts/tqm8555.dts b/arch/powerpc/boot/dts/tqm8555.dts index 6f7ea59c4846..cf92b4e7945e 100644 --- a/arch/powerpc/boot/dts/tqm8555.dts +++ b/arch/powerpc/boot/dts/tqm8555.dts @@ -154,6 +154,22 @@ reg = <3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -165,6 +181,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -177,6 +194,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/boot/dts/tqm8560.dts b/arch/powerpc/boot/dts/tqm8560.dts index 3fe35208907b..9e1ab2d2f669 100644 --- a/arch/powerpc/boot/dts/tqm8560.dts +++ b/arch/powerpc/boot/dts/tqm8560.dts @@ -156,6 +156,22 @@ reg = <3>; device_type = "ethernet-phy"; }; + tbi0: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; + }; + + mdio@25520 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "fsl,gianfar-tbi"; + reg = <0x25520 0x20>; + + tbi1: tbi-phy@11 { + reg = <0x11>; + device_type = "tbi-phy"; + }; }; enet0: ethernet@24000 { @@ -167,6 +183,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <29 2 30 2 34 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi0>; phy-handle = <&phy2>; }; @@ -179,6 +196,7 @@ local-mac-address = [ 00 00 00 00 00 00 ]; interrupts = <35 2 36 2 40 2>; interrupt-parent = <&mpic>; + tbi-handle = <&tbi1>; phy-handle = <&phy1>; }; diff --git a/arch/powerpc/sysdev/fsl_soc.c b/arch/powerpc/sysdev/fsl_soc.c index 26ecb96f9731..115cb16351fd 100644 --- a/arch/powerpc/sysdev/fsl_soc.c +++ b/arch/powerpc/sysdev/fsl_soc.c @@ -207,236 +207,51 @@ static int __init of_add_fixed_phys(void) arch_initcall(of_add_fixed_phys); #endif /* CONFIG_FIXED_PHY */ -static int gfar_mdio_of_init_one(struct device_node *np) -{ - int k; - struct device_node *child = NULL; - struct gianfar_mdio_data mdio_data; - struct platform_device *mdio_dev; - struct resource res; - int ret; - - memset(&res, 0, sizeof(res)); - memset(&mdio_data, 0, sizeof(mdio_data)); - - ret = of_address_to_resource(np, 0, &res); - if (ret) - return ret; - - /* The gianfar device will try to use the same ID created below to find - * this bus, to coordinate register access (since they share). */ - mdio_dev = platform_device_register_simple("fsl-gianfar_mdio", - res.start&0xfffff, &res, 1); - if (IS_ERR(mdio_dev)) - return PTR_ERR(mdio_dev); - - for (k = 0; k < 32; k++) - mdio_data.irq[k] = PHY_POLL; - - while ((child = of_get_next_child(np, child)) != NULL) { - int irq = irq_of_parse_and_map(child, 0); - if (irq != NO_IRQ) { - const u32 *id = of_get_property(child, "reg", NULL); - mdio_data.irq[*id] = irq; - } - } - - ret = platform_device_add_data(mdio_dev, &mdio_data, - sizeof(struct gianfar_mdio_data)); - if (ret) - platform_device_unregister(mdio_dev); - - return ret; -} - -static int __init gfar_mdio_of_init(void) -{ - struct device_node *np = NULL; - - for_each_compatible_node(np, NULL, "fsl,gianfar-mdio") - gfar_mdio_of_init_one(np); - - /* try the deprecated version */ - for_each_compatible_node(np, "mdio", "gianfar"); - gfar_mdio_of_init_one(np); - - return 0; -} - -arch_initcall(gfar_mdio_of_init); - -static const char *gfar_tx_intr = "tx"; -static const char *gfar_rx_intr = "rx"; -static const char *gfar_err_intr = "error"; - -static int __init gfar_of_init(void) +#ifdef CONFIG_PPC_83xx +static int __init mpc83xx_wdt_init(void) { + struct resource r; struct device_node *np; - unsigned int i; - struct platform_device *gfar_dev; - struct resource res; + struct platform_device *dev; + u32 freq = fsl_get_sys_freq(); int ret; - for (np = NULL, i = 0; - (np = of_find_compatible_node(np, "network", "gianfar")) != NULL; - i++) { - struct resource r[4]; - struct device_node *phy, *mdio; - struct gianfar_platform_data gfar_data; - const unsigned int *id; - const char *model; - const char *ctype; - const void *mac_addr; - const phandle *ph; - int n_res = 2; - - if (!of_device_is_available(np)) - continue; - - memset(r, 0, sizeof(r)); - memset(&gfar_data, 0, sizeof(gfar_data)); - - ret = of_address_to_resource(np, 0, &r[0]); - if (ret) - goto err; - - of_irq_to_resource(np, 0, &r[1]); - - model = of_get_property(np, "model", NULL); - - /* If we aren't the FEC we have multiple interrupts */ - if (model && strcasecmp(model, "FEC")) { - r[1].name = gfar_tx_intr; - - r[2].name = gfar_rx_intr; - of_irq_to_resource(np, 1, &r[2]); + np = of_find_compatible_node(NULL, "watchdog", "mpc83xx_wdt"); - r[3].name = gfar_err_intr; - of_irq_to_resource(np, 2, &r[3]); - - n_res += 2; - } - - gfar_dev = - platform_device_register_simple("fsl-gianfar", i, &r[0], - n_res); - - if (IS_ERR(gfar_dev)) { - ret = PTR_ERR(gfar_dev); - goto err; - } - - mac_addr = of_get_mac_address(np); - if (mac_addr) - memcpy(gfar_data.mac_addr, mac_addr, 6); - - if (model && !strcasecmp(model, "TSEC")) - gfar_data.device_flags = - FSL_GIANFAR_DEV_HAS_GIGABIT | - FSL_GIANFAR_DEV_HAS_COALESCE | - FSL_GIANFAR_DEV_HAS_RMON | - FSL_GIANFAR_DEV_HAS_MULTI_INTR; - if (model && !strcasecmp(model, "eTSEC")) - gfar_data.device_flags = - FSL_GIANFAR_DEV_HAS_GIGABIT | - FSL_GIANFAR_DEV_HAS_COALESCE | - FSL_GIANFAR_DEV_HAS_RMON | - FSL_GIANFAR_DEV_HAS_MULTI_INTR | - FSL_GIANFAR_DEV_HAS_CSUM | - FSL_GIANFAR_DEV_HAS_VLAN | - FSL_GIANFAR_DEV_HAS_EXTENDED_HASH; - - ctype = of_get_property(np, "phy-connection-type", NULL); - - /* We only care about rgmii-id. The rest are autodetected */ - if (ctype && !strcmp(ctype, "rgmii-id")) - gfar_data.interface = PHY_INTERFACE_MODE_RGMII_ID; - else - gfar_data.interface = PHY_INTERFACE_MODE_MII; - - if (of_get_property(np, "fsl,magic-packet", NULL)) - gfar_data.device_flags |= FSL_GIANFAR_DEV_HAS_MAGIC_PACKET; - - ph = of_get_property(np, "phy-handle", NULL); - if (ph == NULL) { - u32 *fixed_link; - - fixed_link = (u32 *)of_get_property(np, "fixed-link", - NULL); - if (!fixed_link) { - ret = -ENODEV; - goto unreg; - } - - snprintf(gfar_data.bus_id, MII_BUS_ID_SIZE, "0"); - gfar_data.phy_id = fixed_link[0]; - } else { - phy = of_find_node_by_phandle(*ph); - - if (phy == NULL) { - ret = -ENODEV; - goto unreg; - } - - mdio = of_get_parent(phy); - - id = of_get_property(phy, "reg", NULL); - ret = of_address_to_resource(mdio, 0, &res); - if (ret) { - of_node_put(phy); - of_node_put(mdio); - goto unreg; - } - - gfar_data.phy_id = *id; - snprintf(gfar_data.bus_id, MII_BUS_ID_SIZE, "%llx", - (unsigned long long)res.start&0xfffff); + if (!np) { + ret = -ENODEV; + goto nodev; + } - of_node_put(phy); - of_node_put(mdio); - } + memset(&r, 0, sizeof(r)); - /* Get MDIO bus controlled by this eTSEC, if any. Normally only - * eTSEC 1 will control an MDIO bus, not necessarily the same - * bus that its PHY is on ('mdio' above), so we can't just use - * that. What we do is look for a gianfar mdio device that has - * overlapping registers with this device. That's really the - * whole point, to find the device sharing our registers to - * coordinate access with it. - */ - for_each_compatible_node(mdio, NULL, "fsl,gianfar-mdio") { - if (of_address_to_resource(mdio, 0, &res)) - continue; - - if (res.start >= r[0].start && res.end <= r[0].end) { - /* Get the ID the mdio bus platform device was - * registered with. gfar_data.bus_id is - * different because it's for finding a PHY, - * while this is for finding a MII bus. - */ - gfar_data.mdio_bus = res.start&0xfffff; - of_node_put(mdio); - break; - } - } + ret = of_address_to_resource(np, 0, &r); + if (ret) + goto err; - ret = - platform_device_add_data(gfar_dev, &gfar_data, - sizeof(struct - gianfar_platform_data)); - if (ret) - goto unreg; + dev = platform_device_register_simple("mpc83xx_wdt", 0, &r, 1); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto err; } + ret = platform_device_add_data(dev, &freq, sizeof(freq)); + if (ret) + goto unreg; + + of_node_put(np); return 0; unreg: - platform_device_unregister(gfar_dev); + platform_device_unregister(dev); err: + of_node_put(np); +nodev: return ret; } -arch_initcall(gfar_of_init); +arch_initcall(mpc83xx_wdt_init); +#endif static enum fsl_usb2_phy_modes determine_usb_phy(const char *phy_type) { diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c index 55e319fa7fe6..7398704c4b55 100644 --- a/drivers/net/gianfar.c +++ b/drivers/net/gianfar.c @@ -25,11 +25,8 @@ * * Theory of operation * - * The driver is initialized through platform_device. Structures which - * define the configuration needed by the board are defined in a - * board structure in arch/ppc/platforms (though I do not - * discount the possibility that other architectures could one - * day be supported. + * The driver is initialized through of_device. Configuration information + * is therefore conveyed through an OF-style device tree. * * The Gianfar Ethernet Controller uses a ring of buffer * descriptors. The beginning is indicated by a register @@ -78,7 +75,7 @@ #include #include #include -#include +#include #include #include #include @@ -92,6 +89,8 @@ #include #include #include +#include +#include #include "gianfar.h" #include "gianfar_mii.h" @@ -119,8 +118,9 @@ static irqreturn_t gfar_interrupt(int irq, void *dev_id); static void adjust_link(struct net_device *dev); static void init_registers(struct net_device *dev); static int init_phy(struct net_device *dev); -static int gfar_probe(struct platform_device *pdev); -static int gfar_remove(struct platform_device *pdev); +static int gfar_probe(struct of_device *ofdev, + const struct of_device_id *match); +static int gfar_remove(struct of_device *ofdev); static void free_skb_resources(struct gfar_private *priv); static void gfar_set_multi(struct net_device *dev); static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr); @@ -152,25 +152,158 @@ static inline int gfar_uses_fcb(struct gfar_private *priv) return (priv->vlan_enable || priv->rx_csum_enable); } +static int gfar_of_init(struct net_device *dev) +{ + struct device_node *phy, *mdio; + const unsigned int *id; + const char *model; + const char *ctype; + const void *mac_addr; + const phandle *ph; + u64 addr, size; + int err = 0; + struct gfar_private *priv = netdev_priv(dev); + struct device_node *np = priv->node; + char bus_name[MII_BUS_ID_SIZE]; + + if (!np || !of_device_is_available(np)) + return -ENODEV; + + /* get a pointer to the register memory */ + addr = of_translate_address(np, of_get_address(np, 0, &size, NULL)); + priv->regs = ioremap(addr, size); + + if (priv->regs == NULL) + return -ENOMEM; + + priv->interruptTransmit = irq_of_parse_and_map(np, 0); + + model = of_get_property(np, "model", NULL); + + /* If we aren't the FEC we have multiple interrupts */ + if (model && strcasecmp(model, "FEC")) { + priv->interruptReceive = irq_of_parse_and_map(np, 1); + + priv->interruptError = irq_of_parse_and_map(np, 2); + + if (priv->interruptTransmit < 0 || + priv->interruptReceive < 0 || + priv->interruptError < 0) { + err = -EINVAL; + goto err_out; + } + } + + mac_addr = of_get_mac_address(np); + if (mac_addr) + memcpy(dev->dev_addr, mac_addr, MAC_ADDR_LEN); + + if (model && !strcasecmp(model, "TSEC")) + priv->device_flags = + FSL_GIANFAR_DEV_HAS_GIGABIT | + FSL_GIANFAR_DEV_HAS_COALESCE | + FSL_GIANFAR_DEV_HAS_RMON | + FSL_GIANFAR_DEV_HAS_MULTI_INTR; + if (model && !strcasecmp(model, "eTSEC")) + priv->device_flags = + FSL_GIANFAR_DEV_HAS_GIGABIT | + FSL_GIANFAR_DEV_HAS_COALESCE | + FSL_GIANFAR_DEV_HAS_RMON | + FSL_GIANFAR_DEV_HAS_MULTI_INTR | + FSL_GIANFAR_DEV_HAS_CSUM | + FSL_GIANFAR_DEV_HAS_VLAN | + FSL_GIANFAR_DEV_HAS_MAGIC_PACKET | + FSL_GIANFAR_DEV_HAS_EXTENDED_HASH; + + ctype = of_get_property(np, "phy-connection-type", NULL); + + /* We only care about rgmii-id. The rest are autodetected */ + if (ctype && !strcmp(ctype, "rgmii-id")) + priv->interface = PHY_INTERFACE_MODE_RGMII_ID; + else + priv->interface = PHY_INTERFACE_MODE_MII; + + if (of_get_property(np, "fsl,magic-packet", NULL)) + priv->device_flags |= FSL_GIANFAR_DEV_HAS_MAGIC_PACKET; + + ph = of_get_property(np, "phy-handle", NULL); + if (ph == NULL) { + u32 *fixed_link; + + fixed_link = (u32 *)of_get_property(np, "fixed-link", NULL); + if (!fixed_link) { + err = -ENODEV; + goto err_out; + } + + snprintf(priv->phy_bus_id, BUS_ID_SIZE, PHY_ID_FMT, "0", + fixed_link[0]); + } else { + phy = of_find_node_by_phandle(*ph); + + if (phy == NULL) { + err = -ENODEV; + goto err_out; + } + + mdio = of_get_parent(phy); + + id = of_get_property(phy, "reg", NULL); + + of_node_put(phy); + of_node_put(mdio); + + gfar_mdio_bus_name(bus_name, mdio); + snprintf(priv->phy_bus_id, BUS_ID_SIZE, "%s:%02x", + bus_name, *id); + } + + /* Find the TBI PHY. If it's not there, we don't support SGMII */ + ph = of_get_property(np, "tbi-handle", NULL); + if (ph) { + struct device_node *tbi = of_find_node_by_phandle(*ph); + struct of_device *ofdev; + struct mii_bus *bus; + + if (!tbi) + return 0; + + mdio = of_get_parent(tbi); + if (!mdio) + return 0; + + ofdev = of_find_device_by_node(mdio); + + of_node_put(mdio); + + id = of_get_property(tbi, "reg", NULL); + if (!id) + return 0; + + of_node_put(tbi); + + bus = dev_get_drvdata(&ofdev->dev); + + priv->tbiphy = bus->phy_map[*id]; + } + + return 0; + +err_out: + iounmap(priv->regs); + return err; +} + /* Set up the ethernet device structure, private data, * and anything else we need before we start */ -static int gfar_probe(struct platform_device *pdev) +static int gfar_probe(struct of_device *ofdev, + const struct of_device_id *match) { u32 tempval; struct net_device *dev = NULL; struct gfar_private *priv = NULL; - struct gianfar_platform_data *einfo; - struct resource *r; - int err = 0, irq; - - einfo = (struct gianfar_platform_data *) pdev->dev.platform_data; - - if (NULL == einfo) { - printk(KERN_ERR "gfar %d: Missing additional data!\n", - pdev->id); - - return -ENODEV; - } + int err = 0; + DECLARE_MAC_BUF(mac); /* Create an ethernet device instance */ dev = alloc_etherdev(sizeof (*priv)); @@ -180,48 +313,19 @@ static int gfar_probe(struct platform_device *pdev) priv = netdev_priv(dev); priv->dev = dev; + priv->node = ofdev->node; - /* Set the info in the priv to the current info */ - priv->einfo = einfo; - - /* fill out IRQ fields */ - if (einfo->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { - irq = platform_get_irq_byname(pdev, "tx"); - if (irq < 0) - goto regs_fail; - priv->interruptTransmit = irq; - - irq = platform_get_irq_byname(pdev, "rx"); - if (irq < 0) - goto regs_fail; - priv->interruptReceive = irq; - - irq = platform_get_irq_byname(pdev, "error"); - if (irq < 0) - goto regs_fail; - priv->interruptError = irq; - } else { - irq = platform_get_irq(pdev, 0); - if (irq < 0) - goto regs_fail; - priv->interruptTransmit = irq; - } - - /* get a pointer to the register memory */ - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs = ioremap(r->start, sizeof (struct gfar)); + err = gfar_of_init(dev); - if (NULL == priv->regs) { - err = -ENOMEM; + if (err) goto regs_fail; - } spin_lock_init(&priv->txlock); spin_lock_init(&priv->rxlock); spin_lock_init(&priv->bflock); INIT_WORK(&priv->reset_task, gfar_reset_task); - platform_set_drvdata(pdev, dev); + dev_set_drvdata(&ofdev->dev, priv); /* Stop the DMA engine now, in case it was running before */ /* (The firmware could have used it, and left it running). */ @@ -239,13 +343,10 @@ static int gfar_probe(struct platform_device *pdev) /* Initialize ECNTRL */ gfar_write(&priv->regs->ecntrl, ECNTRL_INIT_SETTINGS); - /* Copy the station address into the dev structure, */ - memcpy(dev->dev_addr, einfo->mac_addr, MAC_ADDR_LEN); - /* Set the dev->base_addr to the gfar reg region */ dev->base_addr = (unsigned long) (priv->regs); - SET_NETDEV_DEV(dev, &pdev->dev); + SET_NETDEV_DEV(dev, &ofdev->dev); /* Fill in the dev structure */ dev->open = gfar_enet_open; @@ -263,7 +364,7 @@ static int gfar_probe(struct platform_device *pdev) dev->ethtool_ops = &gfar_ethtool_ops; - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { priv->rx_csum_enable = 1; dev->features |= NETIF_F_IP_CSUM; } else @@ -271,7 +372,7 @@ static int gfar_probe(struct platform_device *pdev) priv->vlgrp = NULL; - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { dev->vlan_rx_register = gfar_vlan_rx_register; dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX; @@ -279,7 +380,7 @@ static int gfar_probe(struct platform_device *pdev) priv->vlan_enable = 1; } - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_EXTENDED_HASH) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_EXTENDED_HASH) { priv->extended_hash = 1; priv->hash_width = 9; @@ -314,7 +415,7 @@ static int gfar_probe(struct platform_device *pdev) priv->hash_regs[7] = &priv->regs->gaddr7; } - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_PADDING) + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_PADDING) priv->padding = DEFAULT_PADDING; else priv->padding = 0; @@ -368,29 +469,28 @@ regs_fail: return err; } -static int gfar_remove(struct platform_device *pdev) +static int gfar_remove(struct of_device *ofdev) { - struct net_device *dev = platform_get_drvdata(pdev); - struct gfar_private *priv = netdev_priv(dev); + struct gfar_private *priv = dev_get_drvdata(&ofdev->dev); - platform_set_drvdata(pdev, NULL); + dev_set_drvdata(&ofdev->dev, NULL); iounmap(priv->regs); - free_netdev(dev); + free_netdev(priv->dev); return 0; } #ifdef CONFIG_PM -static int gfar_suspend(struct platform_device *pdev, pm_message_t state) +static int gfar_suspend(struct of_device *ofdev, pm_message_t state) { - struct net_device *dev = platform_get_drvdata(pdev); - struct gfar_private *priv = netdev_priv(dev); + struct gfar_private *priv = dev_get_drvdata(&ofdev->dev); + struct net_device *dev = priv->dev; unsigned long flags; u32 tempval; int magic_packet = priv->wol_en && - (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); netif_device_detach(dev); @@ -431,14 +531,14 @@ static int gfar_suspend(struct platform_device *pdev, pm_message_t state) return 0; } -static int gfar_resume(struct platform_device *pdev) +static int gfar_resume(struct of_device *ofdev) { - struct net_device *dev = platform_get_drvdata(pdev); - struct gfar_private *priv = netdev_priv(dev); + struct gfar_private *priv = dev_get_drvdata(&ofdev->dev); + struct net_device *dev = priv->dev; unsigned long flags; u32 tempval; int magic_packet = priv->wol_en && - (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); + (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET); if (!netif_running(dev)) { netif_device_attach(dev); @@ -497,7 +597,7 @@ static phy_interface_t gfar_get_interface(struct net_device *dev) if (ecntrl & ECNTRL_REDUCED_MII_MODE) return PHY_INTERFACE_MODE_RMII; else { - phy_interface_t interface = priv->einfo->interface; + phy_interface_t interface = priv->interface; /* * This isn't autodetected right now, so it must @@ -510,7 +610,7 @@ static phy_interface_t gfar_get_interface(struct net_device *dev) } } - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) return PHY_INTERFACE_MODE_GMII; return PHY_INTERFACE_MODE_MII; @@ -524,21 +624,18 @@ static int init_phy(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); uint gigabit_support = - priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT ? + priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT ? SUPPORTED_1000baseT_Full : 0; struct phy_device *phydev; - char phy_id[BUS_ID_SIZE]; phy_interface_t interface; priv->oldlink = 0; priv->oldspeed = 0; priv->oldduplex = -1; - snprintf(phy_id, sizeof(phy_id), PHY_ID_FMT, priv->einfo->bus_id, priv->einfo->phy_id); - interface = gfar_get_interface(dev); - phydev = phy_connect(dev, phy_id, &adjust_link, 0, interface); + phydev = phy_connect(dev, priv->phy_bus_id, &adjust_link, 0, interface); if (interface == PHY_INTERFACE_MODE_SGMII) gfar_configure_serdes(dev); @@ -569,35 +666,31 @@ static int init_phy(struct net_device *dev) static void gfar_configure_serdes(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - struct gfar_mii __iomem *regs = - (void __iomem *)&priv->regs->gfar_mii_regs; - int tbipa = gfar_read(&priv->regs->tbipa); - struct mii_bus *bus = gfar_get_miibus(priv); - if (bus) - mutex_lock(&bus->mdio_lock); + if (!priv->tbiphy) { + printk(KERN_WARNING "SGMII mode requires that the device " + "tree specify a tbi-handle\n"); + return; + } - /* If the link is already up, we must already be ok, and don't need to + /* + * If the link is already up, we must already be ok, and don't need to * configure and reset the TBI<->SerDes link. Maybe U-Boot configured * everything for us? Resetting it takes the link down and requires * several seconds for it to come back. */ - if (gfar_local_mdio_read(regs, tbipa, MII_BMSR) & BMSR_LSTATUS) - goto done; + if (phy_read(priv->tbiphy, MII_BMSR) & BMSR_LSTATUS) + return; /* Single clk mode, mii mode off(for serdes communication) */ - gfar_local_mdio_write(regs, tbipa, MII_TBICON, TBICON_CLK_SELECT); + phy_write(priv->tbiphy, MII_TBICON, TBICON_CLK_SELECT); - gfar_local_mdio_write(regs, tbipa, MII_ADVERTISE, + phy_write(priv->tbiphy, MII_ADVERTISE, ADVERTISE_1000XFULL | ADVERTISE_1000XPAUSE | ADVERTISE_1000XPSE_ASYM); - gfar_local_mdio_write(regs, tbipa, MII_BMCR, BMCR_ANENABLE | + phy_write(priv->tbiphy, MII_BMCR, BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX | BMCR_SPEED1000); - - done: - if (bus) - mutex_unlock(&bus->mdio_lock); } static void init_registers(struct net_device *dev) @@ -630,7 +723,7 @@ static void init_registers(struct net_device *dev) gfar_write(&priv->regs->gaddr7, 0); /* Zero out the rmon mib registers if it has them */ - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { memset_io(&(priv->regs->rmon), 0, sizeof (struct rmon_mib)); /* Mask off the CAM interrupts */ @@ -705,7 +798,7 @@ void stop_gfar(struct net_device *dev) spin_unlock_irqrestore(&priv->txlock, flags); /* Free the IRQs */ - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { free_irq(priv->interruptError, dev); free_irq(priv->interruptTransmit, dev); free_irq(priv->interruptReceive, dev); @@ -919,7 +1012,7 @@ int startup_gfar(struct net_device *dev) /* If the device has multiple interrupts, register for * them. Otherwise, only register for the one */ - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { /* Install our interrupt handlers for Error, * Transmit, and Receive */ if (request_irq(priv->interruptError, gfar_error, @@ -1751,7 +1844,7 @@ static void gfar_netpoll(struct net_device *dev) struct gfar_private *priv = netdev_priv(dev); /* If the device has multiple interrupts, run tx/rx */ - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { disable_irq(priv->interruptTransmit); disable_irq(priv->interruptReceive); disable_irq(priv->interruptError); @@ -2045,7 +2138,7 @@ static irqreturn_t gfar_error(int irq, void *dev_id) gfar_write(&priv->regs->ievent, events & IEVENT_ERR_MASK); /* Magic Packet is not an error. */ - if ((priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && + if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && (events & IEVENT_MAG)) events &= ~IEVENT_MAG; @@ -2111,16 +2204,24 @@ static irqreturn_t gfar_error(int irq, void *dev_id) /* work with hotplug and coldplug */ MODULE_ALIAS("platform:fsl-gianfar"); +static struct of_device_id gfar_match[] = +{ + { + .type = "network", + .compatible = "gianfar", + }, + {}, +}; + /* Structure for a device driver */ -static struct platform_driver gfar_driver = { +static struct of_platform_driver gfar_driver = { + .name = "fsl-gianfar", + .match_table = gfar_match, + .probe = gfar_probe, .remove = gfar_remove, .suspend = gfar_suspend, .resume = gfar_resume, - .driver = { - .name = "fsl-gianfar", - .owner = THIS_MODULE, - }, }; static int __init gfar_init(void) @@ -2130,7 +2231,7 @@ static int __init gfar_init(void) if (err) return err; - err = platform_driver_register(&gfar_driver); + err = of_register_platform_driver(&gfar_driver); if (err) gfar_mdio_exit(); @@ -2140,7 +2241,7 @@ static int __init gfar_init(void) static void __exit gfar_exit(void) { - platform_driver_unregister(&gfar_driver); + of_unregister_platform_driver(&gfar_driver); gfar_mdio_exit(); } diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h index f46e9b63af13..ca7f0a6a68c5 100644 --- a/drivers/net/gianfar.h +++ b/drivers/net/gianfar.h @@ -657,6 +657,19 @@ struct gfar { }; +/* Flags related to gianfar device features */ +#define FSL_GIANFAR_DEV_HAS_GIGABIT 0x00000001 +#define FSL_GIANFAR_DEV_HAS_COALESCE 0x00000002 +#define FSL_GIANFAR_DEV_HAS_RMON 0x00000004 +#define FSL_GIANFAR_DEV_HAS_MULTI_INTR 0x00000008 +#define FSL_GIANFAR_DEV_HAS_CSUM 0x00000010 +#define FSL_GIANFAR_DEV_HAS_VLAN 0x00000020 +#define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH 0x00000040 +#define FSL_GIANFAR_DEV_HAS_PADDING 0x00000080 +#define FSL_GIANFAR_DEV_HAS_MAGIC_PACKET 0x00000100 +#define FSL_GIANFAR_DEV_HAS_BD_STASHING 0x00000200 +#define FSL_GIANFAR_DEV_HAS_BUF_STASHING 0x00000400 + /* Struct stolen almost completely (and shamelessly) from the FCC enet source * (Ok, that's not so true anymore, but there is a family resemblence) * The GFAR buffer descriptors track the ring buffers. The rx_bd_base @@ -694,6 +707,7 @@ struct gfar_private { /* RX Locked fields */ spinlock_t rxlock; + struct device_node *node; struct net_device *dev; struct napi_struct napi; @@ -733,6 +747,9 @@ struct gfar_private { /* Bitfield update lock */ spinlock_t bflock; + phy_interface_t interface; + char phy_bus_id[BUS_ID_SIZE]; + u32 device_flags; unsigned char vlan_enable:1, rx_csum_enable:1, extended_hash:1, @@ -744,11 +761,9 @@ struct gfar_private { unsigned int interruptReceive; unsigned int interruptError; - /* info structure initialized by platform code */ - struct gianfar_platform_data *einfo; - /* PHY stuff */ struct phy_device *phydev; + struct phy_device *tbiphy; struct mii_bus *mii_bus; int oldspeed; int oldduplex; diff --git a/drivers/net/gianfar_ethtool.c b/drivers/net/gianfar_ethtool.c index fb7d3ccc0fdc..53944b120a3d 100644 --- a/drivers/net/gianfar_ethtool.c +++ b/drivers/net/gianfar_ethtool.c @@ -121,7 +121,7 @@ static void gfar_gstrings(struct net_device *dev, u32 stringset, u8 * buf) { struct gfar_private *priv = netdev_priv(dev); - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_RMON) + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) memcpy(buf, stat_gstrings, GFAR_STATS_LEN * ETH_GSTRING_LEN); else memcpy(buf, stat_gstrings, @@ -138,7 +138,7 @@ static void gfar_fill_stats(struct net_device *dev, struct ethtool_stats *dummy, struct gfar_private *priv = netdev_priv(dev); u64 *extra = (u64 *) & priv->extra_stats; - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { u32 __iomem *rmon = (u32 __iomem *) & priv->regs->rmon; struct gfar_stats *stats = (struct gfar_stats *) buf; @@ -158,7 +158,7 @@ static int gfar_sset_count(struct net_device *dev, int sset) switch (sset) { case ETH_SS_STATS: - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_RMON) + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) return GFAR_STATS_LEN; else return GFAR_EXTRA_STATS_LEN; @@ -280,7 +280,7 @@ static int gfar_gcoalesce(struct net_device *dev, struct ethtool_coalesce *cvals { struct gfar_private *priv = netdev_priv(dev); - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE)) return -EOPNOTSUPP; if (NULL == priv->phydev) @@ -332,7 +332,7 @@ static int gfar_scoalesce(struct net_device *dev, struct ethtool_coalesce *cvals { struct gfar_private *priv = netdev_priv(dev); - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_COALESCE)) return -EOPNOTSUPP; /* Set up rx coalescing */ @@ -482,7 +482,7 @@ static int gfar_set_rx_csum(struct net_device *dev, uint32_t data) unsigned long flags; int err = 0; - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) return -EOPNOTSUPP; if (dev->flags & IFF_UP) { @@ -515,7 +515,7 @@ static uint32_t gfar_get_rx_csum(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) return 0; return priv->rx_csum_enable; @@ -526,7 +526,7 @@ static int gfar_set_tx_csum(struct net_device *dev, uint32_t data) unsigned long flags; struct gfar_private *priv = netdev_priv(dev); - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) return -EOPNOTSUPP; spin_lock_irqsave(&priv->txlock, flags); @@ -547,7 +547,7 @@ static uint32_t gfar_get_tx_csum(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM)) return 0; return (dev->features & NETIF_F_IP_CSUM) != 0; @@ -570,7 +570,7 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct gfar_private *priv = netdev_priv(dev); - if (priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) { + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) { wol->supported = WAKE_MAGIC; wol->wolopts = priv->wol_en ? WAKE_MAGIC : 0; } else { @@ -583,7 +583,7 @@ static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct gfar_private *priv = netdev_priv(dev); unsigned long flags; - if (!(priv->einfo->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && wol->wolopts != 0) return -EINVAL; diff --git a/drivers/net/gianfar_mii.c b/drivers/net/gianfar_mii.c index 0e2595d24933..f3706e415b45 100644 --- a/drivers/net/gianfar_mii.c +++ b/drivers/net/gianfar_mii.c @@ -34,6 +34,8 @@ #include #include #include +#include +#include #include #include @@ -150,19 +152,83 @@ static int gfar_mdio_reset(struct mii_bus *bus) return 0; } +/* Allocate an array which provides irq #s for each PHY on the given bus */ +static int *create_irq_map(struct device_node *np) +{ + int *irqs; + int i; + struct device_node *child = NULL; + + irqs = kcalloc(PHY_MAX_ADDR, sizeof(int), GFP_KERNEL); + + if (!irqs) + return NULL; + + for (i = 0; i < PHY_MAX_ADDR; i++) + irqs[i] = PHY_POLL; + + while ((child = of_get_next_child(np, child)) != NULL) { + int irq = irq_of_parse_and_map(child, 0); + const u32 *id; + + if (irq == NO_IRQ) + continue; + + id = of_get_property(child, "reg", NULL); + + if (!id) + continue; + + if (*id < PHY_MAX_ADDR && *id >= 0) + irqs[*id] = irq; + else + printk(KERN_WARNING "%s: " + "%d is not a valid PHY address\n", + np->full_name, *id); + } + + return irqs; +} + + +void gfar_mdio_bus_name(char *name, struct device_node *np) +{ + const u32 *reg; + + reg = of_get_property(np, "reg", NULL); -static int gfar_mdio_probe(struct device *dev) + snprintf(name, MII_BUS_ID_SIZE, "%s@%x", np->name, reg ? *reg : 0); +} + +/* Scan the bus in reverse, looking for an empty spot */ +static int gfar_mdio_find_free(struct mii_bus *new_bus) +{ + int i; + + for (i = PHY_MAX_ADDR; i > 0; i--) { + u32 phy_id; + + if (get_phy_id(new_bus, i, &phy_id)) + return -1; + + if (phy_id == 0xffffffff) + break; + } + + return i; +} + +static int gfar_mdio_probe(struct of_device *ofdev, + const struct of_device_id *match) { - struct platform_device *pdev = to_platform_device(dev); - struct gianfar_mdio_data *pdata; struct gfar_mii __iomem *regs; struct gfar __iomem *enet_regs; struct mii_bus *new_bus; - struct resource *r; - int i, err = 0; - - if (NULL == dev) - return -EINVAL; + int err = 0; + u64 addr, size; + struct device_node *np = ofdev->node; + struct device_node *tbi; + int tbiaddr = -1; new_bus = mdiobus_alloc(); if (NULL == new_bus) @@ -172,31 +238,28 @@ static int gfar_mdio_probe(struct device *dev) new_bus->read = &gfar_mdio_read, new_bus->write = &gfar_mdio_write, new_bus->reset = &gfar_mdio_reset, - snprintf(new_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id); - - pdata = (struct gianfar_mdio_data *)pdev->dev.platform_data; - - if (NULL == pdata) { - printk(KERN_ERR "gfar mdio %d: Missing platform data!\n", pdev->id); - return -ENODEV; - } - - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); + gfar_mdio_bus_name(new_bus->id, np); /* Set the PHY base address */ - regs = ioremap(r->start, sizeof (struct gfar_mii)); + addr = of_translate_address(np, of_get_address(np, 0, &size, NULL)); + regs = ioremap(addr, size); if (NULL == regs) { err = -ENOMEM; - goto reg_map_fail; + goto err_free_bus; } new_bus->priv = (void __force *)regs; - new_bus->irq = pdata->irq; + new_bus->irq = create_irq_map(np); + + if (new_bus->irq == NULL) { + err = -ENOMEM; + goto err_unmap_regs; + } - new_bus->parent = dev; - dev_set_drvdata(dev, new_bus); + new_bus->parent = &ofdev->dev; + dev_set_drvdata(&ofdev->dev, new_bus); /* * This is mildly evil, but so is our hardware for doing this. @@ -206,96 +269,109 @@ static int gfar_mdio_probe(struct device *dev) enet_regs = (struct gfar __iomem *) ((char *)regs - offsetof(struct gfar, gfar_mii_regs)); - /* Scan the bus, looking for an empty spot for TBIPA */ - gfar_write(&enet_regs->tbipa, 0); - for (i = PHY_MAX_ADDR; i > 0; i--) { - u32 phy_id; + for_each_child_of_node(np, tbi) { + if (!strncmp(tbi->type, "tbi-phy", 8)) + break; + } - err = get_phy_id(new_bus, i, &phy_id); - if (err) - goto bus_register_fail; + if (tbi) { + const u32 *prop = of_get_property(tbi, "reg", NULL); - if (phy_id == 0xffffffff) - break; + if (prop) + tbiaddr = *prop; } - /* The bus is full. We don't support using 31 PHYs, sorry */ - if (i == 0) { + if (tbiaddr == -1) { + gfar_write(&enet_regs->tbipa, 0); + + tbiaddr = gfar_mdio_find_free(new_bus); + } + + /* + * We define TBIPA at 0 to be illegal, opting to fail for boards that + * have PHYs at 1-31, rather than change tbipa and rescan. + */ + if (tbiaddr == 0) { err = -EBUSY; - goto bus_register_fail; + goto err_free_irqs; } - gfar_write(&enet_regs->tbipa, i); + gfar_write(&enet_regs->tbipa, tbiaddr); + + /* + * The TBIPHY-only buses will find PHYs at every address, + * so we mask them all but the TBI + */ + if (!of_device_is_compatible(np, "fsl,gianfar-mdio")) + new_bus->phy_mask = ~(1 << tbiaddr); err = mdiobus_register(new_bus); - if (0 != err) { + if (err != 0) { printk (KERN_ERR "%s: Cannot register as MDIO bus\n", new_bus->name); - goto bus_register_fail; + goto err_free_irqs; } return 0; -bus_register_fail: +err_free_irqs: + kfree(new_bus->irq); +err_unmap_regs: iounmap(regs); -reg_map_fail: +err_free_bus: mdiobus_free(new_bus); return err; } -static int gfar_mdio_remove(struct device *dev) +static int gfar_mdio_remove(struct of_device *ofdev) { - struct mii_bus *bus = dev_get_drvdata(dev); + struct mii_bus *bus = dev_get_drvdata(&ofdev->dev); mdiobus_unregister(bus); - dev_set_drvdata(dev, NULL); + dev_set_drvdata(&ofdev->dev, NULL); iounmap((void __iomem *)bus->priv); bus->priv = NULL; + kfree(bus->irq); mdiobus_free(bus); return 0; } -static struct device_driver gianfar_mdio_driver = { +static struct of_device_id gfar_mdio_match[] = +{ + { + .compatible = "fsl,gianfar-mdio", + }, + { + .compatible = "fsl,gianfar-tbi", + }, + { + .type = "mdio", + .compatible = "gianfar", + }, + {}, +}; + +static struct of_platform_driver gianfar_mdio_driver = { .name = "fsl-gianfar_mdio", - .bus = &platform_bus_type, + .match_table = gfar_mdio_match, + .probe = gfar_mdio_probe, .remove = gfar_mdio_remove, }; -static int match_mdio_bus(struct device *dev, void *data) -{ - const struct gfar_private *priv = data; - const struct platform_device *pdev = to_platform_device(dev); - - return !strcmp(pdev->name, gianfar_mdio_driver.name) && - pdev->id == priv->einfo->mdio_bus; -} - -/* Given a gfar_priv structure, find the mii_bus controlled by this device (not - * necessarily the same as the bus the gfar's PHY is on), if one exists. - * Normally only the first gianfar controls a mii_bus. */ -struct mii_bus *gfar_get_miibus(const struct gfar_private *priv) -{ - /*const*/ struct device *d; - - d = bus_find_device(gianfar_mdio_driver.bus, NULL, (void *)priv, - match_mdio_bus); - return d ? dev_get_drvdata(d) : NULL; -} - int __init gfar_mdio_init(void) { - return driver_register(&gianfar_mdio_driver); + return of_register_platform_driver(&gianfar_mdio_driver); } void gfar_mdio_exit(void) { - driver_unregister(&gianfar_mdio_driver); + of_unregister_platform_driver(&gianfar_mdio_driver); } diff --git a/drivers/net/gianfar_mii.h b/drivers/net/gianfar_mii.h index 02dc970ca1ff..65c242cd468a 100644 --- a/drivers/net/gianfar_mii.h +++ b/drivers/net/gianfar_mii.h @@ -49,4 +49,6 @@ int gfar_local_mdio_read(struct gfar_mii __iomem *regs, int mii_id, int regnum); struct mii_bus *gfar_get_miibus(const struct gfar_private *priv); int __init gfar_mdio_init(void); void gfar_mdio_exit(void); + +void gfar_mdio_bus_name(char *name, struct device_node *np); #endif /* GIANFAR_PHY_H */ diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h index 708bab58d8d0..d9051d717d27 100644 --- a/include/linux/fsl_devices.h +++ b/include/linux/fsl_devices.h @@ -47,12 +47,7 @@ struct gianfar_platform_data { /* device specific information */ u32 device_flags; - /* board specific information */ - u32 board_flags; - int mdio_bus; /* Bus controlled by us */ - char bus_id[MII_BUS_ID_SIZE]; /* Bus PHY is on */ - u32 phy_id; - u8 mac_addr[6]; + char bus_id[BUS_ID_SIZE]; phy_interface_t interface; }; @@ -61,17 +56,6 @@ struct gianfar_mdio_data { int irq[32]; }; -/* Flags related to gianfar device features */ -#define FSL_GIANFAR_DEV_HAS_GIGABIT 0x00000001 -#define FSL_GIANFAR_DEV_HAS_COALESCE 0x00000002 -#define FSL_GIANFAR_DEV_HAS_RMON 0x00000004 -#define FSL_GIANFAR_DEV_HAS_MULTI_INTR 0x00000008 -#define FSL_GIANFAR_DEV_HAS_CSUM 0x00000010 -#define FSL_GIANFAR_DEV_HAS_VLAN 0x00000020 -#define FSL_GIANFAR_DEV_HAS_EXTENDED_HASH 0x00000040 -#define FSL_GIANFAR_DEV_HAS_PADDING 0x00000080 -#define FSL_GIANFAR_DEV_HAS_MAGIC_PACKET 0x00000100 - /* Flags in gianfar_platform_data */ #define FSL_GIANFAR_BRD_HAS_PHY_INTR 0x00000001 /* set or use a timer */ #define FSL_GIANFAR_BRD_IS_REDUCED 0x00000002 /* Set if RGMII, RMII */ -- cgit v1.2.3