---------------------------
+ What: PRISM54
+ When: 2.6.34
+
+ Why: prism54 FullMAC PCI / Cardbus devices used to be supported only by the
+ prism54 wireless driver. After Intersil stopped selling these
+ devices in preference for the newer more flexible SoftMAC devices
+ a SoftMAC device driver was required and prism54 did not support
+ them. The p54pci driver now exists and has been present in the kernel for
+ a while. This driver supports both SoftMAC devices and FullMAC devices.
+ The main difference between these devices was the amount of memory which
+ could be used for the firmware. The SoftMAC devices support a smaller
+ amount of memory. Because of this the SoftMAC firmware fits into FullMAC
+ devices's memory. p54pci supports not only PCI / Cardbus but also USB
+ and SPI. Since p54pci supports all devices prism54 supports
+ you will have a conflict. I'm not quite sure how distributions are
+ handling this conflict right now. prism54 was kept around due to
+ claims users may experience issues when using the SoftMAC driver.
+ Time has passed users have not reported issues. If you use prism54
+ and for whatever reason you cannot use p54pci please let us know!
+ E-mail us at: linux-wireless@vger.kernel.org
+
+ For more information see the p54 wiki page:
+
+ http://wireless.kernel.org/en/users/Drivers/p54
+
+ Who: Luis R. Rodriguez <lrodriguez@atheros.com>
+
+ ---------------------------
+
What: IRQF_SAMPLE_RANDOM
Check: IRQF_SAMPLE_RANDOM
When: July 2009
---------------------------
-What: libata spindown skipping and warning
-When: Dec 2008
-Why: Some halt(8) implementations synchronize caches for and spin
- down libata disks because libata didn't use to spin down disk on
- system halt (only synchronized caches).
- Spin down on system halt is now implemented. sysfs node
- /sys/class/scsi_disk/h:c:i:l/manage_start_stop is present if
- spin down support is available.
- Because issuing spin down command to an already spun down disk
- makes some disks spin up just to spin down again, libata tracks
- device spindown status to skip the extra spindown command and
- warn about it.
- This is to give userspace tools the time to get updated and will
- be removed after userspace is reasonably updated.
-Who: Tejun Heo <htejun@gmail.com>
-
----------------------------
-
What: i386/x86_64 bzImage symlinks
When: April 2010
---------------------------
What (Why):
- - include/linux/netfilter_ipv4/ipt_TOS.h ipt_tos.h header files
- (superseded by xt_TOS/xt_tos target & match)
-
- - "forwarding" header files like ipt_mac.h in
- include/linux/netfilter_ipv4/ and include/linux/netfilter_ipv6/
-
- - xt_CONNMARK match revision 0
- (superseded by xt_CONNMARK match revision 1)
-
- - xt_MARK target revisions 0 and 1
- (superseded by xt_MARK match revision 2)
-
- - xt_connmark match revision 0
- (superseded by xt_connmark match revision 1)
-
- - xt_conntrack match revision 0
- (superseded by xt_conntrack match revision 1)
-
- - xt_iprange match revision 0,
- include/linux/netfilter_ipv4/ipt_iprange.h
- (superseded by xt_iprange match revision 1)
-
- - xt_mark match revision 0
- (superseded by xt_mark match revision 1)
-
- xt_recent: the old ipt_recent proc dir
(superseded by /proc/net/xt_recent)
-----------------------------
-What: obsolete generic irq defines and typedefs
-When: 2.6.30
-Why: The defines and typedefs (hw_interrupt_type, no_irq_type, irq_desc_t)
- have been kept around for migration reasons. After more than two years
- it's time to remove them finally
-Who: Thomas Gleixner <tglx@linutronix.de>
-
----------------------------
-
What: fakephp and associated sysfs files in /sys/bus/pci/slots/
When: 2011
Why: In 2.6.27, the semantics of /sys/bus/pci/slots was redefined to
cpufreq core and contained inside cpufreq.c. Other dependent
drivers should not use it in order to safely avoid lockdep issues.
Who: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+
+----------------------------
+
+What: sound-slot/service-* module aliases and related clutters in
+ sound/sound_core.c
+When: August 2010
+Why: OSS sound_core grabs all legacy minors (0-255) of SOUND_MAJOR
+ (14) and requests modules using custom sound-slot/service-*
+ module aliases. The only benefit of doing this is allowing
+ use of custom module aliases which might as well be considered
+ a bug at this point. This preemptive claiming prevents
+ alternative OSS implementations.
+
+ Till the feature is removed, the kernel will be requesting
+ both sound-slot/service-* and the standard char-major-* module
+ aliases and allow turning off the pre-claiming selectively via
+ CONFIG_SOUND_OSS_CORE_PRECLAIM and soundcore.preclaim_oss
+ kernel parameter.
+
+ After the transition phase is complete, both the custom module
+ aliases and switches to disable it will go away. This removal
+ will also allow making ALSA OSS emulation independent of
+ sound_core. The dependency will be broken then too.
+Who: Tejun Heo <tj@kernel.org>
libata.dma=4 Compact Flash DMA only
Combinations also work, so libata.dma=3 enables DMA
for disks and CDROMs, but not CFs.
+
+ libata.ignore_hpa= [LIBATA] Ignore HPA limit
+ libata.ignore_hpa=0 keep BIOS limits (default)
+ libata.ignore_hpa=1 ignore limits, using full disk
libata.noacpi [LIBATA] Disables use of ACPI in libata suspend/resume
when set.
[NFS] set the TCP port on which the NFSv4 callback
channel should listen.
+ nfs.cache_getent=
+ [NFS] sets the pathname to the program which is used
+ to update the NFS client cache entries.
+
+ nfs.cache_getent_timeout=
+ [NFS] sets the timeout after which an attempt to
+ update a cache entry is deemed to have failed.
+
nfs.idmap_cache_timeout=
[NFS] set the maximum lifetime for idmapper cache
entries.
symbolic names: lapic and ioapic
Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
+ netpoll.carrier_timeout=
+ [NET] Specifies amount of time (in seconds) that
+ netpoll should wait for a carrier. By default netpoll
+ waits 4 seconds.
+
no387 [BUGS=X86-32] Tells the kernel to use the 387 maths
emulation library even if a 387 maths coprocessor
is present.
stifb= [HW]
Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
+ sunrpc.min_resvport=
+ sunrpc.max_resvport=
+ [NFS,SUNRPC]
+ SunRPC servers often require that client requests
+ originate from a privileged port (i.e. a port in the
+ range 0 < portnr < 1024).
+ An administrator who wishes to reserve some of these
+ ports for other uses may adjust the range that the
+ kernel's sunrpc client considers to be privileged
+ using these two parameters to set the minimum and
+ maximum port values.
+
sunrpc.pool_mode=
[NFS]
Control how the NFS server code allocates CPUs to
pernode one pool for each NUMA node (equivalent
to global on non-NUMA machines)
+ sunrpc.tcp_slot_table_entries=
+ sunrpc.udp_slot_table_entries=
+ [NFS,SUNRPC]
+ Sets the upper limit on the number of simultaneous
+ RPC calls that can be sent from the client to a
+ server. Increasing these values may allow you to
+ improve throughput, but will also increase the
+ amount of memory reserved for use by the client.
+
swiotlb= [IA-64] Number of I/O TLB slabs
switches= [HW,M68k]
trace_buf_size=nn[KMG]
[FTRACE] will set tracing buffer size.
+ trace_event=[event-list]
+ [FTRACE] Set and start specified trace events in order
+ to facilitate early boot debugging.
+ See also Documentation/trace/events.txt
+
trix= [HW,OSS] MediaTrix AudioTrix Pro
Format:
<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
AMSO1100 RNIC DRIVER
M: Tom Tucker <tom@opengridcomputing.com>
M: Steve Wise <swise@opengridcomputing.com>
-L: general@lists.openfabrics.org
+L: linux-rdma@vger.kernel.org
S: Maintained
F: drivers/infiniband/hw/amso1100/
M: Bob Copeland <me@bobcopeland.com>
L: linux-wireless@vger.kernel.org
L: ath5k-devel@lists.ath5k.org
+ W: http://wireless.kernel.org/en/users/Drivers/ath5k
S: Maintained
F: drivers/net/wireless/ath/ath5k/
M: Senthil Balasubramanian <senthilkumar@atheros.com>
L: linux-wireless@vger.kernel.org
L: ath9k-devel@lists.ath9k.org
+ W: http://wireless.kernel.org/en/users/Drivers/ath9k
S: Supported
F: drivers/net/wireless/ath/ath9k/
CXGB3 IWARP RNIC DRIVER (IW_CXGB3)
M: Steve Wise <swise@chelsio.com>
-L: general@lists.openfabrics.org
+L: linux-rdma@vger.kernel.org
W: http://www.openfabrics.org
S: Supported
F: drivers/infiniband/hw/cxgb3/
EHCA (IBM GX bus InfiniBand adapter) DRIVER
M: Hoang-Nam Nguyen <hnguyen@de.ibm.com>
M: Christoph Raisch <raisch@de.ibm.com>
-L: general@lists.openfabrics.org
+L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/infiniband/hw/ehca/
S: Maintained
F: drivers/media/video/gspca/pac207.c
+GSPCA SN9C20X SUBDRIVER
+M: Brian Johnson <brijohn@gmail.com>
+L: linux-media@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git
+S: Maintained
+F: drivers/media/video/gspca/sn9c20x.c
+
GSPCA T613 SUBDRIVER
M: Leandro Costantino <lcostantino@gmail.com>
L: linux-media@vger.kernel.org
M: Roland Dreier <rolandd@cisco.com>
M: Sean Hefty <sean.hefty@intel.com>
M: Hal Rosenstock <hal.rosenstock@gmail.com>
-L: general@lists.openfabrics.org (moderated for non-subscribers)
+L: linux-rdma@vger.kernel.org
W: http://www.openib.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
S: Supported
INTEL PRO/WIRELESS 2100 NETWORK CONNECTION SUPPORT
M: Zhu Yi <yi.zhu@intel.com>
- M: James Ketrenos <jketreno@linux.intel.com>
M: Reinette Chatre <reinette.chatre@intel.com>
+ M: Intel Linux Wireless <ilw@linux.intel.com>
L: linux-wireless@vger.kernel.org
- L: ipw2100-devel@lists.sourceforge.net
- W: http://lists.sourceforge.net/mailman/listinfo/ipw2100-devel
W: http://ipw2100.sourceforge.net
- S: Supported
+ S: Odd Fixes
F: Documentation/networking/README.ipw2100
F: drivers/net/wireless/ipw2x00/ipw2100.*
INTEL PRO/WIRELESS 2915ABG NETWORK CONNECTION SUPPORT
M: Zhu Yi <yi.zhu@intel.com>
- M: James Ketrenos <jketreno@linux.intel.com>
M: Reinette Chatre <reinette.chatre@intel.com>
+ M: Intel Linux Wireless <ilw@linux.intel.com>
L: linux-wireless@vger.kernel.org
- L: ipw2100-devel@lists.sourceforge.net
- W: http://lists.sourceforge.net/mailman/listinfo/ipw2100-devel
W: http://ipw2200.sourceforge.net
- S: Supported
+ S: Odd Fixes
F: Documentation/networking/README.ipw2200
F: drivers/net/wireless/ipw2x00/ipw2200.*
INTEL WIRELESS WIFI LINK (iwlwifi)
M: Zhu Yi <yi.zhu@intel.com>
M: Reinette Chatre <reinette.chatre@intel.com>
+ M: Intel Linux Wireless <ilw@linux.intel.com>
L: linux-wireless@vger.kernel.org
- L: ipw3945-devel@lists.sourceforge.net
W: http://intellinuxwireless.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi-2.6.git
S: Supported
IPATH DRIVER
M: Ralph Campbell <infinipath@qlogic.com>
-L: general@lists.openfabrics.org
+L: linux-rdma@vger.kernel.org
T: git git://git.qlogic.com/ipath-linux-2.6
S: Supported
F: drivers/infiniband/hw/ipath/
F: drivers/net/mv643xx_eth.*
F: include/linux/mv643xx.h
+ MARVELL MWL8K WIRELESS DRIVER
+ M: Lennert Buytenhek <buytenh@marvell.com>
+ L: linux-wireless@vger.kernel.org
+ S: Supported
+ F: drivers/net/wireless/mwl8k.c
+
MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER
M: Nicolas Pitre <nico@cam.org>
S: Maintained
MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
S: Orphan
+L: linux-mmc@vger.kernel.org
F: drivers/mmc/
F: include/linux/mmc/
NETEFFECT IWARP RNIC DRIVER (IW_NES)
M: Faisal Latif <faisal.latif@intel.com>
M: Chien Tung <chien.tin.tung@intel.com>
-L: general@lists.openfabrics.org
+L: linux-rdma@vger.kernel.org
W: http://www.neteffect.com
S: Supported
F: drivers/infiniband/hw/nes/
L: linux-wireless@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-2.6.git
S: Maintained
+ F: net/mac80211/
+ F: net/rfkill/
F: net/wireless/
F: include/net/ieee80211*
F: include/linux/wireless.h
+ F: drivers/net/wireless/
NETWORKING DRIVERS
L: netdev@vger.kernel.org
T: git git://git.open-osd.org/open-osd.git
S: Maintained
F: drivers/scsi/osd/
-F: drivers/include/scsi/osd_*
+F: include/scsi/osd_*
F: fs/exofs/
P54 WIRELESS DRIVER
W: http://linuxwireless.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
S: Maintained
- F: drivers/net/wireless/rtl818*
+ F: drivers/net/wireless/rtl818x/rtl8180*
RTL8187 WIRELESS DRIVER
M: Herton Ronaldo Krzesinski <herton@mandriva.com.br>
F: drivers/net/benet/
SFC NETWORK DRIVER
- P: Steve Hodgson
- P: Ben Hutchings
- M: Robert Stonehouse <linux-net-drivers@solarflare.com>
+ M: Solarflare linux maintainers <linux-net-drivers@solarflare.com>
+ M: Steve Hodgson <shodgson@solarflare.com>
+ M: Ben Hutchings <bhutchings@solarflare.com>
+ L: netdev@vger.kernel.org
S: Supported
F: drivers/net/sfc/
S: Maintained
F: drivers/input/misc/wistron_btns.c
+ WL1251 WIRELESS DRIVER
+ P: Kalle Valo
+ M: kalle.valo@nokia.com
+ L: linux-wireless@vger.kernel.org
+ W: http://wireless.kernel.org
+ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
+ S: Maintained
+ F: drivers/net/wireless/wl12xx/*
+ X: drivers/net/wireless/wl12xx/wl1271*
+
+ WL1271 WIRELESS DRIVER
+ M: Luciano Coelho <luciano.coelho@nokia.com>
+ L: linux-wireless@vger.kernel.org
+ W: http://wireless.kernel.org
+ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
+ S: Maintained
+ F: drivers/net/wireless/wl12xx/wl1271*
+
WL3501 WIRELESS PCMCIA CARD DRIVER
M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
L: linux-wireless@vger.kernel.org
SIGN1(sys32_umask, sys_umask, %o0)
SIGN3(sys32_tgkill, sys_tgkill, %o0, %o1, %o2)
SIGN1(sys32_sendto, sys_sendto, %o0)
- SIGN1(sys32_recvfrom, sys_recvfrom, %o0)
+ SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
SIGN3(sys32_socket, sys_socket, %o0, %o1, %o2)
SIGN2(sys32_connect, sys_connect, %o0, %o2)
SIGN2(sys32_bind, sys_bind, %o0, %o2)
SIGN1(sys32_getsockname, sys_getsockname, %o0)
SIGN2(sys32_ioprio_get, sys_ioprio_get, %o0, %o1)
SIGN3(sys32_ioprio_set, sys_ioprio_set, %o0, %o1, %o2)
-SIGN2(sys32_splice, sys_splice, %o0, %o1)
+SIGN2(sys32_splice, sys_splice, %o0, %o2)
SIGN2(sys32_sync_file_range, compat_sync_file_range, %o0, %o5)
SIGN2(sys32_tee, sys_tee, %o0, %o1)
SIGN1(sys32_vmsplice, compat_sys_vmsplice, %o0)
+SIGN1(sys32_truncate, sys_truncate, %o1)
+SIGN1(sys32_ftruncate, sys_ftruncate, %o1)
.globl sys32_mmap2
sys32_mmap2:
static void c2_print_macaddr(struct net_device *netdev)
{
- pr_debug("%s: MAC %02X:%02X:%02X:%02X:%02X:%02X, "
- "IRQ %u\n", netdev->name,
- netdev->dev_addr[0], netdev->dev_addr[1], netdev->dev_addr[2],
- netdev->dev_addr[3], netdev->dev_addr[4], netdev->dev_addr[5],
- netdev->irq);
+ pr_debug("%s: MAC %pM, IRQ %u\n", netdev->name, netdev->dev_addr, netdev->irq);
}
static void c2_set_rxbufsize(struct c2_port *c2_port)
netif_rx(skb);
- netdev->last_rx = jiffies;
netdev->stats.rx_packets++;
netdev->stats.rx_bytes += buflen;
}
static void process_critical_error(struct nes_device *nesdev);
static void nes_process_mac_intr(struct nes_device *nesdev, u32 mac_number);
static unsigned int nes_reset_adapter_ne020(struct nes_device *nesdev, u8 *OneG_Mode);
+static void nes_terminate_timeout(unsigned long context);
+static void nes_terminate_start_timer(struct nes_qp *nesqp);
#ifdef CONFIG_INFINIBAND_NES_DEBUG
static unsigned char *nes_iwarp_state_str[] = {
}
skip_rx_indicate0:
- nesvnic->netdev->last_rx = jiffies;
+ ;
/* nesvnic->netstats.rx_packets++; */
/* nesvnic->netstats.rx_bytes += rx_pkt_size; */
}
}
+static u8 *locate_mpa(u8 *pkt, u32 aeq_info)
+{
+ u16 pkt_len;
+
+ if (aeq_info & NES_AEQE_Q2_DATA_ETHERNET) {
+ /* skip over ethernet header */
+ pkt_len = be16_to_cpu(*(u16 *)(pkt + ETH_HLEN - 2));
+ pkt += ETH_HLEN;
+
+ /* Skip over IP and TCP headers */
+ pkt += 4 * (pkt[0] & 0x0f);
+ pkt += 4 * ((pkt[12] >> 4) & 0x0f);
+ }
+ return pkt;
+}
+
+/* Determine if incoming error pkt is rdma layer */
+static u32 iwarp_opcode(struct nes_qp *nesqp, u32 aeq_info)
+{
+ u8 *pkt;
+ u16 *mpa;
+ u32 opcode = 0xffffffff;
+
+ if (aeq_info & NES_AEQE_Q2_DATA_WRITTEN) {
+ pkt = nesqp->hwqp.q2_vbase + BAD_FRAME_OFFSET;
+ mpa = (u16 *)locate_mpa(pkt, aeq_info);
+ opcode = be16_to_cpu(mpa[1]) & 0xf;
+ }
+
+ return opcode;
+}
+
+/* Build iWARP terminate header */
+static int nes_bld_terminate_hdr(struct nes_qp *nesqp, u16 async_event_id, u32 aeq_info)
+{
+ u8 *pkt = nesqp->hwqp.q2_vbase + BAD_FRAME_OFFSET;
+ u16 ddp_seg_len;
+ int copy_len = 0;
+ u8 is_tagged = 0;
+ u8 flush_code = 0;
+ struct nes_terminate_hdr *termhdr;
+
+ termhdr = (struct nes_terminate_hdr *)nesqp->hwqp.q2_vbase;
+ memset(termhdr, 0, 64);
+
+ if (aeq_info & NES_AEQE_Q2_DATA_WRITTEN) {
+
+ /* Use data from offending packet to fill in ddp & rdma hdrs */
+ pkt = locate_mpa(pkt, aeq_info);
+ ddp_seg_len = be16_to_cpu(*(u16 *)pkt);
+ if (ddp_seg_len) {
+ copy_len = 2;
+ termhdr->hdrct = DDP_LEN_FLAG;
+ if (pkt[2] & 0x80) {
+ is_tagged = 1;
+ if (ddp_seg_len >= TERM_DDP_LEN_TAGGED) {
+ copy_len += TERM_DDP_LEN_TAGGED;
+ termhdr->hdrct |= DDP_HDR_FLAG;
+ }
+ } else {
+ if (ddp_seg_len >= TERM_DDP_LEN_UNTAGGED) {
+ copy_len += TERM_DDP_LEN_UNTAGGED;
+ termhdr->hdrct |= DDP_HDR_FLAG;
+ }
+
+ if (ddp_seg_len >= (TERM_DDP_LEN_UNTAGGED + TERM_RDMA_LEN)) {
+ if ((pkt[3] & RDMA_OPCODE_MASK) == RDMA_READ_REQ_OPCODE) {
+ copy_len += TERM_RDMA_LEN;
+ termhdr->hdrct |= RDMA_HDR_FLAG;
+ }
+ }
+ }
+ }
+ }
+
+ switch (async_event_id) {
+ case NES_AEQE_AEID_AMP_UNALLOCATED_STAG:
+ switch (iwarp_opcode(nesqp, aeq_info)) {
+ case IWARP_OPCODE_WRITE:
+ flush_code = IB_WC_LOC_PROT_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_TAGGED_BUFFER;
+ termhdr->error_code = DDP_TAGGED_INV_STAG;
+ break;
+ default:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_INV_STAG;
+ }
+ break;
+ case NES_AEQE_AEID_AMP_INVALID_STAG:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_INV_STAG;
+ break;
+ case NES_AEQE_AEID_AMP_BAD_QP:
+ flush_code = IB_WC_LOC_QP_OP_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_QN;
+ break;
+ case NES_AEQE_AEID_AMP_BAD_STAG_KEY:
+ case NES_AEQE_AEID_AMP_BAD_STAG_INDEX:
+ switch (iwarp_opcode(nesqp, aeq_info)) {
+ case IWARP_OPCODE_SEND_INV:
+ case IWARP_OPCODE_SEND_SE_INV:
+ flush_code = IB_WC_REM_OP_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_OP;
+ termhdr->error_code = RDMAP_CANT_INV_STAG;
+ break;
+ default:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_INV_STAG;
+ }
+ break;
+ case NES_AEQE_AEID_AMP_BOUNDS_VIOLATION:
+ if (aeq_info & (NES_AEQE_Q2_DATA_ETHERNET | NES_AEQE_Q2_DATA_MPA)) {
+ flush_code = IB_WC_LOC_PROT_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_TAGGED_BUFFER;
+ termhdr->error_code = DDP_TAGGED_BOUNDS;
+ } else {
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_INV_BOUNDS;
+ }
+ break;
+ case NES_AEQE_AEID_AMP_RIGHTS_VIOLATION:
+ case NES_AEQE_AEID_AMP_INVALIDATE_NO_REMOTE_ACCESS_RIGHTS:
+ case NES_AEQE_AEID_PRIV_OPERATION_DENIED:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_ACCESS;
+ break;
+ case NES_AEQE_AEID_AMP_TO_WRAP:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_TO_WRAP;
+ break;
+ case NES_AEQE_AEID_AMP_BAD_PD:
+ switch (iwarp_opcode(nesqp, aeq_info)) {
+ case IWARP_OPCODE_WRITE:
+ flush_code = IB_WC_LOC_PROT_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_TAGGED_BUFFER;
+ termhdr->error_code = DDP_TAGGED_UNASSOC_STAG;
+ break;
+ case IWARP_OPCODE_SEND_INV:
+ case IWARP_OPCODE_SEND_SE_INV:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_CANT_INV_STAG;
+ break;
+ default:
+ flush_code = IB_WC_REM_ACCESS_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_PROT;
+ termhdr->error_code = RDMAP_UNASSOC_STAG;
+ }
+ break;
+ case NES_AEQE_AEID_LLP_RECEIVED_MARKER_AND_LENGTH_FIELDS_DONT_MATCH:
+ flush_code = IB_WC_LOC_LEN_ERR;
+ termhdr->layer_etype = (LAYER_MPA << 4) | DDP_LLP;
+ termhdr->error_code = MPA_MARKER;
+ break;
+ case NES_AEQE_AEID_LLP_RECEIVED_MPA_CRC_ERROR:
+ flush_code = IB_WC_GENERAL_ERR;
+ termhdr->layer_etype = (LAYER_MPA << 4) | DDP_LLP;
+ termhdr->error_code = MPA_CRC;
+ break;
+ case NES_AEQE_AEID_LLP_SEGMENT_TOO_LARGE:
+ case NES_AEQE_AEID_LLP_SEGMENT_TOO_SMALL:
+ flush_code = IB_WC_LOC_LEN_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_CATASTROPHIC;
+ termhdr->error_code = DDP_CATASTROPHIC_LOCAL;
+ break;
+ case NES_AEQE_AEID_DDP_LCE_LOCAL_CATASTROPHIC:
+ case NES_AEQE_AEID_DDP_NO_L_BIT:
+ flush_code = IB_WC_FATAL_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_CATASTROPHIC;
+ termhdr->error_code = DDP_CATASTROPHIC_LOCAL;
+ break;
+ case NES_AEQE_AEID_DDP_INVALID_MSN_GAP_IN_MSN:
+ case NES_AEQE_AEID_DDP_INVALID_MSN_RANGE_IS_NOT_VALID:
+ flush_code = IB_WC_GENERAL_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_MSN_RANGE;
+ break;
+ case NES_AEQE_AEID_DDP_UBE_DDP_MESSAGE_TOO_LONG_FOR_AVAILABLE_BUFFER:
+ flush_code = IB_WC_LOC_LEN_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_TOO_LONG;
+ break;
+ case NES_AEQE_AEID_DDP_UBE_INVALID_DDP_VERSION:
+ flush_code = IB_WC_GENERAL_ERR;
+ if (is_tagged) {
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_TAGGED_BUFFER;
+ termhdr->error_code = DDP_TAGGED_INV_DDP_VER;
+ } else {
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_DDP_VER;
+ }
+ break;
+ case NES_AEQE_AEID_DDP_UBE_INVALID_MO:
+ flush_code = IB_WC_GENERAL_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_MO;
+ break;
+ case NES_AEQE_AEID_DDP_UBE_INVALID_MSN_NO_BUFFER_AVAILABLE:
+ flush_code = IB_WC_REM_OP_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_MSN_NO_BUF;
+ break;
+ case NES_AEQE_AEID_DDP_UBE_INVALID_QN:
+ flush_code = IB_WC_GENERAL_ERR;
+ termhdr->layer_etype = (LAYER_DDP << 4) | DDP_UNTAGGED_BUFFER;
+ termhdr->error_code = DDP_UNTAGGED_INV_QN;
+ break;
+ case NES_AEQE_AEID_RDMAP_ROE_INVALID_RDMAP_VERSION:
+ flush_code = IB_WC_GENERAL_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_OP;
+ termhdr->error_code = RDMAP_INV_RDMAP_VER;
+ break;
+ case NES_AEQE_AEID_RDMAP_ROE_UNEXPECTED_OPCODE:
+ flush_code = IB_WC_LOC_QP_OP_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_OP;
+ termhdr->error_code = RDMAP_UNEXPECTED_OP;
+ break;
+ default:
+ flush_code = IB_WC_FATAL_ERR;
+ termhdr->layer_etype = (LAYER_RDMA << 4) | RDMAP_REMOTE_OP;
+ termhdr->error_code = RDMAP_UNSPECIFIED;
+ break;
+ }
+
+ if (copy_len)
+ memcpy(termhdr + 1, pkt, copy_len);
+
+ if ((flush_code) && ((NES_AEQE_INBOUND_RDMA & aeq_info) == 0)) {
+ if (aeq_info & NES_AEQE_SQ)
+ nesqp->term_sq_flush_code = flush_code;
+ else
+ nesqp->term_rq_flush_code = flush_code;
+ }
+
+ return sizeof(struct nes_terminate_hdr) + copy_len;
+}
+
+static void nes_terminate_connection(struct nes_device *nesdev, struct nes_qp *nesqp,
+ struct nes_hw_aeqe *aeqe, enum ib_event_type eventtype)
+{
+ u64 context;
+ unsigned long flags;
+ u32 aeq_info;
+ u16 async_event_id;
+ u8 tcp_state;
+ u8 iwarp_state;
+ u32 termlen = 0;
+ u32 mod_qp_flags = NES_CQP_QP_IWARP_STATE_TERMINATE |
+ NES_CQP_QP_TERM_DONT_SEND_FIN;
+ struct nes_adapter *nesadapter = nesdev->nesadapter;
+
+ if (nesqp->term_flags & NES_TERM_SENT)
+ return; /* Sanity check */
+
+ aeq_info = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_MISC_IDX]);
+ tcp_state = (aeq_info & NES_AEQE_TCP_STATE_MASK) >> NES_AEQE_TCP_STATE_SHIFT;
+ iwarp_state = (aeq_info & NES_AEQE_IWARP_STATE_MASK) >> NES_AEQE_IWARP_STATE_SHIFT;
+ async_event_id = (u16)aeq_info;
+
+ context = (unsigned long)nesadapter->qp_table[le32_to_cpu(
+ aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]) - NES_FIRST_QPN];
+ if (!context) {
+ WARN_ON(!context);
+ return;
+ }
+
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ spin_lock_irqsave(&nesqp->lock, flags);
+ nesqp->hw_iwarp_state = iwarp_state;
+ nesqp->hw_tcp_state = tcp_state;
+ nesqp->last_aeq = async_event_id;
+ nesqp->terminate_eventtype = eventtype;
+ spin_unlock_irqrestore(&nesqp->lock, flags);
+
+ if (nesadapter->send_term_ok)
+ termlen = nes_bld_terminate_hdr(nesqp, async_event_id, aeq_info);
+ else
+ mod_qp_flags |= NES_CQP_QP_TERM_DONT_SEND_TERM_MSG;
+
+ nes_terminate_start_timer(nesqp);
+ nesqp->term_flags |= NES_TERM_SENT;
+ nes_hw_modify_qp(nesdev, nesqp, mod_qp_flags, termlen, 0);
+}
+
+static void nes_terminate_send_fin(struct nes_device *nesdev,
+ struct nes_qp *nesqp, struct nes_hw_aeqe *aeqe)
+{
+ u32 aeq_info;
+ u16 async_event_id;
+ u8 tcp_state;
+ u8 iwarp_state;
+ unsigned long flags;
+
+ aeq_info = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_MISC_IDX]);
+ tcp_state = (aeq_info & NES_AEQE_TCP_STATE_MASK) >> NES_AEQE_TCP_STATE_SHIFT;
+ iwarp_state = (aeq_info & NES_AEQE_IWARP_STATE_MASK) >> NES_AEQE_IWARP_STATE_SHIFT;
+ async_event_id = (u16)aeq_info;
+
+ spin_lock_irqsave(&nesqp->lock, flags);
+ nesqp->hw_iwarp_state = iwarp_state;
+ nesqp->hw_tcp_state = tcp_state;
+ nesqp->last_aeq = async_event_id;
+ spin_unlock_irqrestore(&nesqp->lock, flags);
+
+ /* Send the fin only */
+ nes_hw_modify_qp(nesdev, nesqp, NES_CQP_QP_IWARP_STATE_TERMINATE |
+ NES_CQP_QP_TERM_DONT_SEND_TERM_MSG, 0, 0);
+}
+
+/* Cleanup after a terminate sent or received */
+static void nes_terminate_done(struct nes_qp *nesqp, int timeout_occurred)
+{
+ u32 next_iwarp_state = NES_CQP_QP_IWARP_STATE_ERROR;
+ unsigned long flags;
+ struct nes_vnic *nesvnic = to_nesvnic(nesqp->ibqp.device);
+ struct nes_device *nesdev = nesvnic->nesdev;
+ u8 first_time = 0;
+
+ spin_lock_irqsave(&nesqp->lock, flags);
+ if (nesqp->hte_added) {
+ nesqp->hte_added = 0;
+ next_iwarp_state |= NES_CQP_QP_DEL_HTE;
+ }
+
+ first_time = (nesqp->term_flags & NES_TERM_DONE) == 0;
+ nesqp->term_flags |= NES_TERM_DONE;
+ spin_unlock_irqrestore(&nesqp->lock, flags);
+
+ /* Make sure we go through this only once */
+ if (first_time) {
+ if (timeout_occurred == 0)
+ del_timer(&nesqp->terminate_timer);
+ else
+ next_iwarp_state |= NES_CQP_QP_RESET;
+
+ nes_hw_modify_qp(nesdev, nesqp, next_iwarp_state, 0, 0);
+ nes_cm_disconn(nesqp);
+ }
+}
+
+static void nes_terminate_received(struct nes_device *nesdev,
+ struct nes_qp *nesqp, struct nes_hw_aeqe *aeqe)
+{
+ u32 aeq_info;
+ u8 *pkt;
+ u32 *mpa;
+ u8 ddp_ctl;
+ u8 rdma_ctl;
+ u16 aeq_id = 0;
+
+ aeq_info = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_MISC_IDX]);
+ if (aeq_info & NES_AEQE_Q2_DATA_WRITTEN) {
+ /* Terminate is not a performance path so the silicon */
+ /* did not validate the frame - do it now */
+ pkt = nesqp->hwqp.q2_vbase + BAD_FRAME_OFFSET;
+ mpa = (u32 *)locate_mpa(pkt, aeq_info);
+ ddp_ctl = (be32_to_cpu(mpa[0]) >> 8) & 0xff;
+ rdma_ctl = be32_to_cpu(mpa[0]) & 0xff;
+ if ((ddp_ctl & 0xc0) != 0x40)
+ aeq_id = NES_AEQE_AEID_DDP_LCE_LOCAL_CATASTROPHIC;
+ else if ((ddp_ctl & 0x03) != 1)
+ aeq_id = NES_AEQE_AEID_DDP_UBE_INVALID_DDP_VERSION;
+ else if (be32_to_cpu(mpa[2]) != 2)
+ aeq_id = NES_AEQE_AEID_DDP_UBE_INVALID_QN;
+ else if (be32_to_cpu(mpa[3]) != 1)
+ aeq_id = NES_AEQE_AEID_DDP_INVALID_MSN_GAP_IN_MSN;
+ else if (be32_to_cpu(mpa[4]) != 0)
+ aeq_id = NES_AEQE_AEID_DDP_UBE_INVALID_MO;
+ else if ((rdma_ctl & 0xc0) != 0x40)
+ aeq_id = NES_AEQE_AEID_RDMAP_ROE_INVALID_RDMAP_VERSION;
+
+ if (aeq_id) {
+ /* Bad terminate recvd - send back a terminate */
+ aeq_info = (aeq_info & 0xffff0000) | aeq_id;
+ aeqe->aeqe_words[NES_AEQE_MISC_IDX] = cpu_to_le32(aeq_info);
+ nes_terminate_connection(nesdev, nesqp, aeqe, IB_EVENT_QP_FATAL);
+ return;
+ }
+ }
+
+ nesqp->term_flags |= NES_TERM_RCVD;
+ nesqp->terminate_eventtype = IB_EVENT_QP_FATAL;
+ nes_terminate_start_timer(nesqp);
+ nes_terminate_send_fin(nesdev, nesqp, aeqe);
+}
+
+/* Timeout routine in case terminate fails to complete */
+static void nes_terminate_timeout(unsigned long context)
+{
+ struct nes_qp *nesqp = (struct nes_qp *)(unsigned long)context;
+
+ nes_terminate_done(nesqp, 1);
+}
+
+/* Set a timer in case hw cannot complete the terminate sequence */
+static void nes_terminate_start_timer(struct nes_qp *nesqp)
+{
+ init_timer(&nesqp->terminate_timer);
+ nesqp->terminate_timer.function = nes_terminate_timeout;
+ nesqp->terminate_timer.expires = jiffies + HZ;
+ nesqp->terminate_timer.data = (unsigned long)nesqp;
+ add_timer(&nesqp->terminate_timer);
+}
+
/**
* nes_process_iwarp_aeqe
*/
struct nes_hw_aeqe *aeqe)
{
u64 context;
- u64 aeqe_context = 0;
unsigned long flags;
struct nes_qp *nesqp;
+ struct nes_hw_cq *hw_cq;
+ struct nes_cq *nescq;
int resource_allocated;
- /* struct iw_cm_id *cm_id; */
struct nes_adapter *nesadapter = nesdev->nesadapter;
- struct ib_event ibevent;
- /* struct iw_cm_event cm_event; */
u32 aeq_info;
u32 next_iwarp_state = 0;
u16 async_event_id;
u8 tcp_state;
u8 iwarp_state;
+ int must_disconn = 1;
+ int must_terminate = 0;
+ struct ib_event ibevent;
nes_debug(NES_DBG_AEQ, "\n");
aeq_info = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_MISC_IDX]);
- if ((NES_AEQE_INBOUND_RDMA&aeq_info) || (!(NES_AEQE_QP&aeq_info))) {
+ if ((NES_AEQE_INBOUND_RDMA & aeq_info) || (!(NES_AEQE_QP & aeq_info))) {
context = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_CTXT_LOW_IDX]);
context += ((u64)le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_CTXT_HIGH_IDX])) << 32;
} else {
- aeqe_context = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_CTXT_LOW_IDX]);
- aeqe_context += ((u64)le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_CTXT_HIGH_IDX])) << 32;
context = (unsigned long)nesadapter->qp_table[le32_to_cpu(
aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]) - NES_FIRST_QPN];
BUG_ON(!context);
switch (async_event_id) {
case NES_AEQE_AEID_LLP_FIN_RECEIVED:
- nesqp = *((struct nes_qp **)&context);
+ nesqp = (struct nes_qp *)(unsigned long)context;
+
+ if (nesqp->term_flags)
+ return; /* Ignore it, wait for close complete */
+
if (atomic_inc_return(&nesqp->close_timer_started) == 1) {
nesqp->cm_id->add_ref(nesqp->cm_id);
schedule_nes_timer(nesqp->cm_node, (struct sk_buff *)nesqp,
nesqp->hwqp.qp_id, atomic_read(&nesqp->refcount),
async_event_id, nesqp->last_aeq, tcp_state);
}
+
if ((tcp_state != NES_AEQE_TCP_STATE_CLOSE_WAIT) ||
(nesqp->ibqp_state != IB_QPS_RTS)) {
/* FIN Received but tcp state or IB state moved on,
should expect a close complete */
return;
}
+
case NES_AEQE_AEID_LLP_CLOSE_COMPLETE:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ if (nesqp->term_flags) {
+ nes_terminate_done(nesqp, 0);
+ return;
+ }
+
case NES_AEQE_AEID_LLP_CONNECTION_RESET:
- case NES_AEQE_AEID_TERMINATE_SENT:
- case NES_AEQE_AEID_RDMAP_ROE_BAD_LLP_CLOSE:
case NES_AEQE_AEID_RESET_SENT:
- nesqp = *((struct nes_qp **)&context);
+ nesqp = (struct nes_qp *)(unsigned long)context;
if (async_event_id == NES_AEQE_AEID_RESET_SENT) {
tcp_state = NES_AEQE_TCP_STATE_CLOSED;
}
if ((tcp_state == NES_AEQE_TCP_STATE_CLOSED) ||
(tcp_state == NES_AEQE_TCP_STATE_TIME_WAIT)) {
nesqp->hte_added = 0;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "issuing hw modifyqp for QP%u to remove hte\n",
- nesqp->hwqp.qp_id);
- nes_hw_modify_qp(nesdev, nesqp,
- NES_CQP_QP_IWARP_STATE_ERROR | NES_CQP_QP_DEL_HTE, 0);
- spin_lock_irqsave(&nesqp->lock, flags);
+ next_iwarp_state = NES_CQP_QP_IWARP_STATE_ERROR | NES_CQP_QP_DEL_HTE;
}
if ((nesqp->ibqp_state == IB_QPS_RTS) &&
nesqp->hw_iwarp_state = NES_AEQE_IWARP_STATE_CLOSING;
break;
case NES_AEQE_IWARP_STATE_TERMINATE:
- next_iwarp_state = NES_CQP_QP_IWARP_STATE_TERMINATE;
- nesqp->hw_iwarp_state = NES_AEQE_IWARP_STATE_TERMINATE;
- if (async_event_id == NES_AEQE_AEID_RDMAP_ROE_BAD_LLP_CLOSE) {
- next_iwarp_state |= 0x02000000;
- nesqp->hw_tcp_state = NES_AEQE_TCP_STATE_CLOSED;
- }
+ must_disconn = 0; /* terminate path takes care of disconn */
+ if (nesqp->term_flags == 0)
+ must_terminate = 1;
break;
- default:
- next_iwarp_state = 0;
- }
- spin_unlock_irqrestore(&nesqp->lock, flags);
- if (next_iwarp_state) {
- nes_debug(NES_DBG_AEQ, "issuing hw modifyqp for QP%u. next state = 0x%08X,"
- " also added another reference\n",
- nesqp->hwqp.qp_id, next_iwarp_state);
- nes_hw_modify_qp(nesdev, nesqp, next_iwarp_state, 0);
}
- nes_cm_disconn(nesqp);
} else {
if (async_event_id == NES_AEQE_AEID_LLP_FIN_RECEIVED) {
/* FIN Received but ib state not RTS,
close complete will be on its way */
- spin_unlock_irqrestore(&nesqp->lock, flags);
- return;
- }
- spin_unlock_irqrestore(&nesqp->lock, flags);
- if (async_event_id == NES_AEQE_AEID_RDMAP_ROE_BAD_LLP_CLOSE) {
- next_iwarp_state = NES_CQP_QP_IWARP_STATE_TERMINATE | 0x02000000;
- nesqp->hw_tcp_state = NES_AEQE_TCP_STATE_CLOSED;
- nes_debug(NES_DBG_AEQ, "issuing hw modifyqp for QP%u. next state = 0x%08X,"
- " also added another reference\n",
- nesqp->hwqp.qp_id, next_iwarp_state);
- nes_hw_modify_qp(nesdev, nesqp, next_iwarp_state, 0);
+ must_disconn = 0;
}
- nes_cm_disconn(nesqp);
}
- break;
- case NES_AEQE_AEID_LLP_TERMINATE_RECEIVED:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_LLP_TERMINATE_RECEIVED"
- " event on QP%u \n Q2 Data:\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_FATAL;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
- if ((tcp_state == NES_AEQE_TCP_STATE_CLOSE_WAIT) ||
- ((nesqp->ibqp_state == IB_QPS_RTS)&&
- (async_event_id == NES_AEQE_AEID_LLP_CONNECTION_RESET))) {
+
+ if (must_terminate)
+ nes_terminate_connection(nesdev, nesqp, aeqe, IB_EVENT_QP_FATAL);
+ else if (must_disconn) {
+ if (next_iwarp_state) {
+ nes_debug(NES_DBG_AEQ, "issuing hw modifyqp for QP%u. next state = 0x%08X\n",
+ nesqp->hwqp.qp_id, next_iwarp_state);
+ nes_hw_modify_qp(nesdev, nesqp, next_iwarp_state, 0, 0);
+ }
nes_cm_disconn(nesqp);
- } else {
- nesqp->in_disconnect = 0;
- wake_up(&nesqp->kick_waitq);
}
break;
- case NES_AEQE_AEID_LLP_TOO_MANY_RETRIES:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = NES_AEQE_IWARP_STATE_ERROR;
- nesqp->hw_tcp_state = NES_AEQE_TCP_STATE_CLOSED;
- nesqp->last_aeq = async_event_id;
- if (nesqp->cm_id) {
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_LLP_TOO_MANY_RETRIES"
- " event on QP%u, remote IP = 0x%08X \n",
- nesqp->hwqp.qp_id,
- ntohl(nesqp->cm_id->remote_addr.sin_addr.s_addr));
- } else {
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_LLP_TOO_MANY_RETRIES"
- " event on QP%u \n",
- nesqp->hwqp.qp_id);
- }
- spin_unlock_irqrestore(&nesqp->lock, flags);
- next_iwarp_state = NES_CQP_QP_IWARP_STATE_ERROR | NES_CQP_QP_RESET;
- nes_hw_modify_qp(nesdev, nesqp, next_iwarp_state, 0);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_FATAL;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
+
+ case NES_AEQE_AEID_TERMINATE_SENT:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ nes_terminate_send_fin(nesdev, nesqp, aeqe);
break;
- case NES_AEQE_AEID_AMP_BAD_STAG_INDEX:
- if (NES_AEQE_INBOUND_RDMA&aeq_info) {
- nesqp = nesadapter->qp_table[le32_to_cpu(
- aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX])-NES_FIRST_QPN];
- } else {
- /* TODO: get the actual WQE and mask off wqe index */
- context &= ~((u64)511);
- nesqp = *((struct nes_qp **)&context);
- }
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_AMP_BAD_STAG_INDEX event on QP%u\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_ACCESS_ERR;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
+
+ case NES_AEQE_AEID_LLP_TERMINATE_RECEIVED:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ nes_terminate_received(nesdev, nesqp, aeqe);
break;
+
+ case NES_AEQE_AEID_AMP_BAD_STAG_KEY:
+ case NES_AEQE_AEID_AMP_BAD_STAG_INDEX:
case NES_AEQE_AEID_AMP_UNALLOCATED_STAG:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_AMP_UNALLOCATED_STAG event on QP%u\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_ACCESS_ERR;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
- break;
+ case NES_AEQE_AEID_AMP_INVALID_STAG:
+ case NES_AEQE_AEID_AMP_RIGHTS_VIOLATION:
+ case NES_AEQE_AEID_AMP_INVALIDATE_NO_REMOTE_ACCESS_RIGHTS:
case NES_AEQE_AEID_PRIV_OPERATION_DENIED:
- nesqp = nesadapter->qp_table[le32_to_cpu(aeqe->aeqe_words
- [NES_AEQE_COMP_QP_CQ_ID_IDX])-NES_FIRST_QPN];
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_PRIV_OPERATION_DENIED event on QP%u,"
- " nesqp = %p, AE reported %p\n",
- nesqp->hwqp.qp_id, nesqp, *((struct nes_qp **)&context));
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_ACCESS_ERR;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
+ case NES_AEQE_AEID_DDP_UBE_DDP_MESSAGE_TOO_LONG_FOR_AVAILABLE_BUFFER:
+ case NES_AEQE_AEID_AMP_BOUNDS_VIOLATION:
+ case NES_AEQE_AEID_AMP_TO_WRAP:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ nes_terminate_connection(nesdev, nesqp, aeqe, IB_EVENT_QP_ACCESS_ERR);
+ break;
+
+ case NES_AEQE_AEID_LLP_SEGMENT_TOO_LARGE:
+ case NES_AEQE_AEID_LLP_SEGMENT_TOO_SMALL:
+ case NES_AEQE_AEID_DDP_UBE_INVALID_MO:
+ case NES_AEQE_AEID_DDP_UBE_INVALID_QN:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ if (iwarp_opcode(nesqp, aeq_info) > IWARP_OPCODE_TERM) {
+ aeq_info &= 0xffff0000;
+ aeq_info |= NES_AEQE_AEID_RDMAP_ROE_UNEXPECTED_OPCODE;
+ aeqe->aeqe_words[NES_AEQE_MISC_IDX] = cpu_to_le32(aeq_info);
}
+
+ case NES_AEQE_AEID_RDMAP_ROE_BAD_LLP_CLOSE:
+ case NES_AEQE_AEID_LLP_TOO_MANY_RETRIES:
+ case NES_AEQE_AEID_DDP_UBE_INVALID_MSN_NO_BUFFER_AVAILABLE:
+ case NES_AEQE_AEID_LLP_RECEIVED_MPA_CRC_ERROR:
+ case NES_AEQE_AEID_AMP_BAD_QP:
+ case NES_AEQE_AEID_LLP_RECEIVED_MARKER_AND_LENGTH_FIELDS_DONT_MATCH:
+ case NES_AEQE_AEID_DDP_LCE_LOCAL_CATASTROPHIC:
+ case NES_AEQE_AEID_DDP_NO_L_BIT:
+ case NES_AEQE_AEID_DDP_INVALID_MSN_GAP_IN_MSN:
+ case NES_AEQE_AEID_DDP_INVALID_MSN_RANGE_IS_NOT_VALID:
+ case NES_AEQE_AEID_DDP_UBE_INVALID_DDP_VERSION:
+ case NES_AEQE_AEID_RDMAP_ROE_INVALID_RDMAP_VERSION:
+ case NES_AEQE_AEID_RDMAP_ROE_UNEXPECTED_OPCODE:
+ case NES_AEQE_AEID_AMP_BAD_PD:
+ case NES_AEQE_AEID_AMP_FASTREG_SHARED:
+ case NES_AEQE_AEID_AMP_FASTREG_VALID_STAG:
+ case NES_AEQE_AEID_AMP_FASTREG_MW_STAG:
+ case NES_AEQE_AEID_AMP_FASTREG_INVALID_RIGHTS:
+ case NES_AEQE_AEID_AMP_FASTREG_PBL_TABLE_OVERFLOW:
+ case NES_AEQE_AEID_AMP_FASTREG_INVALID_LENGTH:
+ case NES_AEQE_AEID_AMP_INVALIDATE_SHARED:
+ case NES_AEQE_AEID_AMP_INVALIDATE_MR_WITH_BOUND_WINDOWS:
+ case NES_AEQE_AEID_AMP_MWBIND_VALID_STAG:
+ case NES_AEQE_AEID_AMP_MWBIND_OF_MR_STAG:
+ case NES_AEQE_AEID_AMP_MWBIND_TO_ZERO_BASED_STAG:
+ case NES_AEQE_AEID_AMP_MWBIND_TO_MW_STAG:
+ case NES_AEQE_AEID_AMP_MWBIND_INVALID_RIGHTS:
+ case NES_AEQE_AEID_AMP_MWBIND_INVALID_BOUNDS:
+ case NES_AEQE_AEID_AMP_MWBIND_TO_INVALID_PARENT:
+ case NES_AEQE_AEID_AMP_MWBIND_BIND_DISABLED:
+ case NES_AEQE_AEID_BAD_CLOSE:
+ case NES_AEQE_AEID_RDMA_READ_WHILE_ORD_ZERO:
+ case NES_AEQE_AEID_STAG_ZERO_INVALID:
+ case NES_AEQE_AEID_ROE_INVALID_RDMA_READ_REQUEST:
+ case NES_AEQE_AEID_ROE_INVALID_RDMA_WRITE_OR_READ_RESP:
+ nesqp = (struct nes_qp *)(unsigned long)context;
+ nes_terminate_connection(nesdev, nesqp, aeqe, IB_EVENT_QP_FATAL);
break;
+
case NES_AEQE_AEID_CQ_OPERATION_ERROR:
context <<= 1;
nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_CQ_OPERATION_ERROR event on CQ%u, %p\n",
if (resource_allocated) {
printk(KERN_ERR PFX "%s: Processing an NES_AEQE_AEID_CQ_OPERATION_ERROR event on CQ%u\n",
__func__, le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]));
+ hw_cq = (struct nes_hw_cq *)(unsigned long)context;
+ if (hw_cq) {
+ nescq = container_of(hw_cq, struct nes_cq, hw_cq);
+ if (nescq->ibcq.event_handler) {
+ ibevent.device = nescq->ibcq.device;
+ ibevent.event = IB_EVENT_CQ_ERR;
+ ibevent.element.cq = &nescq->ibcq;
+ nescq->ibcq.event_handler(&ibevent, nescq->ibcq.cq_context);
+ }
+ }
}
break;
- case NES_AEQE_AEID_DDP_UBE_DDP_MESSAGE_TOO_LONG_FOR_AVAILABLE_BUFFER:
- nesqp = nesadapter->qp_table[le32_to_cpu(
- aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX])-NES_FIRST_QPN];
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_DDP_UBE_DDP_MESSAGE_TOO_LONG"
- "_FOR_AVAILABLE_BUFFER event on QP%u\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_ACCESS_ERR;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
- /* tell cm to disconnect, cm will queue work to thread */
- nes_cm_disconn(nesqp);
- break;
- case NES_AEQE_AEID_DDP_UBE_INVALID_MSN_NO_BUFFER_AVAILABLE:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_DDP_UBE_INVALID_MSN"
- "_NO_BUFFER_AVAILABLE event on QP%u\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_FATAL;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
- /* tell cm to disconnect, cm will queue work to thread */
- nes_cm_disconn(nesqp);
- break;
- case NES_AEQE_AEID_LLP_RECEIVED_MPA_CRC_ERROR:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- nes_debug(NES_DBG_AEQ, "Processing an NES_AEQE_AEID_LLP_RECEIVED_MPA_CRC_ERROR"
- " event on QP%u \n Q2 Data:\n",
- nesqp->hwqp.qp_id);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_FATAL;
- nesqp->ibqp.event_handler(&ibevent, nesqp->ibqp.qp_context);
- }
- /* tell cm to disconnect, cm will queue work to thread */
- nes_cm_disconn(nesqp);
- break;
- /* TODO: additional AEs need to be here */
- case NES_AEQE_AEID_AMP_BOUNDS_VIOLATION:
- nesqp = *((struct nes_qp **)&context);
- spin_lock_irqsave(&nesqp->lock, flags);
- nesqp->hw_iwarp_state = iwarp_state;
- nesqp->hw_tcp_state = tcp_state;
- nesqp->last_aeq = async_event_id;
- spin_unlock_irqrestore(&nesqp->lock, flags);
- if (nesqp->ibqp.event_handler) {
- ibevent.device = nesqp->ibqp.device;
- ibevent.element.qp = &nesqp->ibqp;
- ibevent.event = IB_EVENT_QP_ACCESS_ERR;
- nesqp->ibqp.event_handler(&ibevent,
- nesqp->ibqp.qp_context);
- }
- nes_cm_disconn(nesqp);
- break;
+
default:
nes_debug(NES_DBG_AEQ, "Processing an iWARP related AE for QP, misc = 0x%04X\n",
async_event_id);
}
-
/**
* nes_iwarp_ce_handler
*/
{
struct nes_cqp_request *cqp_request;
struct nes_hw_cqp_wqe *cqp_wqe;
+ u32 sq_code = (NES_IWARP_CQE_MAJOR_FLUSH << 16) | NES_IWARP_CQE_MINOR_FLUSH;
+ u32 rq_code = (NES_IWARP_CQE_MAJOR_FLUSH << 16) | NES_IWARP_CQE_MINOR_FLUSH;
int ret;
cqp_request = nes_get_cqp_request(nesdev);
cqp_wqe = &cqp_request->cqp_wqe;
nes_fill_init_cqp_wqe(cqp_wqe, nesdev);
+ /* If wqe in error was identified, set code to be put into cqe */
+ if ((nesqp->term_sq_flush_code) && (which_wq & NES_CQP_FLUSH_SQ)) {
+ which_wq |= NES_CQP_FLUSH_MAJ_MIN;
+ sq_code = (CQE_MAJOR_DRV << 16) | nesqp->term_sq_flush_code;
+ nesqp->term_sq_flush_code = 0;
+ }
+
+ if ((nesqp->term_rq_flush_code) && (which_wq & NES_CQP_FLUSH_RQ)) {
+ which_wq |= NES_CQP_FLUSH_MAJ_MIN;
+ rq_code = (CQE_MAJOR_DRV << 16) | nesqp->term_rq_flush_code;
+ nesqp->term_rq_flush_code = 0;
+ }
+
+ if (which_wq & NES_CQP_FLUSH_MAJ_MIN) {
+ cqp_wqe->wqe_words[NES_CQP_QP_WQE_FLUSH_SQ_CODE] = cpu_to_le32(sq_code);
+ cqp_wqe->wqe_words[NES_CQP_QP_WQE_FLUSH_RQ_CODE] = cpu_to_le32(rq_code);
+ }
+
cqp_wqe->wqe_words[NES_CQP_WQE_OPCODE_IDX] =
cpu_to_le32(NES_CQP_FLUSH_WQES | which_wq);
cqp_wqe->wqe_words[NES_CQP_WQE_ID_IDX] = cpu_to_le32(nesqp->hwqp.qp_id);
*/
#include <rdma/ib_cm.h>
-#include <rdma/ib_cache.h>
#include <net/dst.h>
#include <net/icmp.h>
#include <linux/icmpv6.h>
skb_reset_mac_header(skb);
skb_pull(skb, IPOIB_ENCAP_LEN);
- dev->last_rx = jiffies;
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
#include <linux/delay.h>
#include <linux/dma-mapping.h>
-#include <rdma/ib_cache.h>
#include <linux/ip.h>
#include <linux/tcp.h>
skb_reset_mac_header(skb);
skb_pull(skb, IPOIB_ENCAP_LEN);
- dev->last_rx = jiffies;
++dev->stats.rx_packets;
dev->stats.rx_bytes += skb->len;
}
}
+ static void enable_tx_fifo_drain(struct adapter *adapter,
+ struct port_info *pi)
+ {
+ t3_set_reg_field(adapter, A_XGM_TXFIFO_CFG + pi->mac.offset, 0,
+ F_ENDROPPKT);
+ t3_write_reg(adapter, A_XGM_RX_CTRL + pi->mac.offset, 0);
+ t3_write_reg(adapter, A_XGM_TX_CTRL + pi->mac.offset, F_TXEN);
+ t3_write_reg(adapter, A_XGM_RX_CTRL + pi->mac.offset, F_RXEN);
+ }
+
+ static void disable_tx_fifo_drain(struct adapter *adapter,
+ struct port_info *pi)
+ {
+ t3_set_reg_field(adapter, A_XGM_TXFIFO_CFG + pi->mac.offset,
+ F_ENDROPPKT, 0);
+ }
+
void t3_os_link_fault(struct adapter *adap, int port_id, int state)
{
struct net_device *dev = adap->port[port_id];
netif_carrier_on(dev);
+ disable_tx_fifo_drain(adap, pi);
+
/* Clear local faults */
t3_xgm_intr_disable(adap, pi->port_id);
t3_read_reg(adap, A_XGM_INT_STATUS +
t3_xgm_intr_enable(adap, pi->port_id);
t3_mac_enable(mac, MAC_DIRECTION_TX);
- } else
+ } else {
netif_carrier_off(dev);
+ /* Flush TX FIFO */
+ enable_tx_fifo_drain(adap, pi);
+ }
link_report(dev);
}
if (link_stat != netif_carrier_ok(dev)) {
if (link_stat) {
+ disable_tx_fifo_drain(adapter, pi);
+
t3_mac_enable(mac, MAC_DIRECTION_RX);
/* Clear local faults */
t3_read_reg(adapter, A_XGM_INT_STATUS + pi->mac.offset);
t3_mac_disable(mac, MAC_DIRECTION_RX);
t3_link_start(&pi->phy, mac, &pi->link_config);
+
+ /* Flush TX FIFO */
+ enable_tx_fifo_drain(adapter, pi);
}
link_report(dev);
memset(req, 0, sizeof(*req));
req->wr.wr_hi = htonl(V_WR_OP(FW_WROPCODE_FORWARD));
OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SMT_WRITE_REQ, i));
+ req->mtu_idx = NMTUS - 1;
req->iff = i;
t3_mgmt_tx(adap, skb);
if (skb == adap->nofail_skb) {
#define FW_FNAME "cxgb3/t3fw-%d.%d.%d.bin"
#define TPSRAM_NAME "cxgb3/t3%c_psram-%d.%d.%d.bin"
+ #define AEL2005_OPT_EDC_NAME "cxgb3/ael2005_opt_edc.bin"
+ #define AEL2005_TWX_EDC_NAME "cxgb3/ael2005_twx_edc.bin"
+ #define AEL2020_TWX_EDC_NAME "cxgb3/ael2020_twx_edc.bin"
+
+ static inline const char *get_edc_fw_name(int edc_idx)
+ {
+ const char *fw_name = NULL;
+
+ switch (edc_idx) {
+ case EDC_OPT_AEL2005:
+ fw_name = AEL2005_OPT_EDC_NAME;
+ break;
+ case EDC_TWX_AEL2005:
+ fw_name = AEL2005_TWX_EDC_NAME;
+ break;
+ case EDC_TWX_AEL2020:
+ fw_name = AEL2020_TWX_EDC_NAME;
+ break;
+ }
+ return fw_name;
+ }
+
+ int t3_get_edc_fw(struct cphy *phy, int edc_idx, int size)
+ {
+ struct adapter *adapter = phy->adapter;
+ const struct firmware *fw;
+ char buf[64];
+ u32 csum;
+ const __be32 *p;
+ u16 *cache = phy->phy_cache;
+ int i, ret;
+
+ snprintf(buf, sizeof(buf), get_edc_fw_name(edc_idx));
+
+ ret = request_firmware(&fw, buf, &adapter->pdev->dev);
+ if (ret < 0) {
+ dev_err(&adapter->pdev->dev,
+ "could not upgrade firmware: unable to load %s\n",
+ buf);
+ return ret;
+ }
+
+ /* check size, take checksum in account */
+ if (fw->size > size + 4) {
+ CH_ERR(adapter, "firmware image too large %u, expected %d\n",
+ (unsigned int)fw->size, size + 4);
+ ret = -EINVAL;
+ }
+
+ /* compute checksum */
+ p = (const __be32 *)fw->data;
+ for (csum = 0, i = 0; i < fw->size / sizeof(csum); i++)
+ csum += ntohl(p[i]);
+
+ if (csum != 0xffffffff) {
+ CH_ERR(adapter, "corrupted firmware image, checksum %u\n",
+ csum);
+ ret = -EINVAL;
+ }
+
+ for (i = 0; i < size / 4 ; i++) {
+ *cache++ = (be32_to_cpu(p[i]) & 0xffff0000) >> 16;
+ *cache++ = be32_to_cpu(p[i]) & 0xffff;
+ }
+
+ release_firmware(fw);
+
+ return ret;
+ }
static int upgrade_fw(struct adapter *adap)
{
if (!other_ports)
schedule_chk_task(adapter);
+ cxgb3_event_notify(&adapter->tdev, OFFLOAD_PORT_UP, pi->port_id);
return 0;
}
if (!adapter->open_device_map)
cxgb_down(adapter);
+ cxgb3_event_notify(&adapter->tdev, OFFLOAD_PORT_DOWN, pi->port_id);
return 0;
}
if (is_offload(adapter) &&
test_bit(OFFLOAD_DEVMAP_BIT, &adapter->open_device_map)) {
- cxgb3_err_notify(&adapter->tdev, OFFLOAD_STATUS_DOWN, 0);
+ cxgb3_event_notify(&adapter->tdev, OFFLOAD_STATUS_DOWN, 0);
offload_close(&adapter->tdev);
}
}
if (is_offload(adapter) && !ofld_disable)
- cxgb3_err_notify(&adapter->tdev, OFFLOAD_STATUS_UP, 0);
+ cxgb3_event_notify(&adapter->tdev, OFFLOAD_STATUS_UP, 0);
}
/*
u32 tempval;
struct net_device *dev = NULL;
struct gfar_private *priv = NULL;
- DECLARE_MAC_BUF(mac);
int err = 0;
int len_devname;
dev_set_drvdata(&ofdev->dev, NULL);
- unregister_netdev(dev);
+ unregister_netdev(priv->ndev);
iounmap(priv->regs);
free_netdev(priv->ndev);
uid_t owner;
gid_t group;
- struct sk_buff_head readq;
-
struct net_device *dev;
struct fasync_struct *fasync;
struct tap_filter txflt;
- struct sock *sk;
struct socket socket;
#ifdef TUN_DEBUG
static int tun_attach(struct tun_struct *tun, struct file *file)
{
struct tun_file *tfile = file->private_data;
- const struct cred *cred = current_cred();
int err;
ASSERT_RTNL();
- /* Check permissions */
- if (((tun->owner != -1 && cred->euid != tun->owner) ||
- (tun->group != -1 && !in_egroup_p(tun->group))) &&
- !capable(CAP_NET_ADMIN))
- return -EPERM;
-
netif_tx_lock_bh(tun->dev);
err = -EINVAL;
tfile->tun = tun;
tun->tfile = tfile;
dev_hold(tun->dev);
- sock_hold(tun->sk);
+ sock_hold(tun->socket.sk);
atomic_inc(&tfile->count);
out:
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
- skb_queue_purge(&tun->readq);
+ skb_queue_purge(&tun->socket.sk->sk_receive_queue);
/* Drop the extra count on the net device */
dev_put(tun->dev);
{
struct tun_struct *tun = netdev_priv(dev);
- sock_put(tun->sk);
+ sock_put(tun->socket.sk);
}
/* Net device open. */
}
/* Net device start xmit */
- static int tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
+ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
if (!check_filter(&tun->txflt, skb))
goto drop;
- if (skb_queue_len(&tun->readq) >= dev->tx_queue_len) {
+ if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
}
/* Enqueue packet */
- skb_queue_tail(&tun->readq, skb);
+ skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
dev->trans_start = jiffies;
/* Notify and wake up reader process */
if (tun->flags & TUN_FASYNC)
kill_fasync(&tun->fasync, SIGIO, POLL_IN);
wake_up_interruptible(&tun->socket.wait);
- return 0;
+ return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
kfree_skb(skb);
- return 0;
+ return NETDEV_TX_OK;
}
static void tun_net_mclist(struct net_device *dev)
if (!tun)
return POLLERR;
- sk = tun->sk;
+ sk = tun->socket.sk;
DBG(KERN_INFO "%s: tun_chr_poll\n", tun->dev->name);
poll_wait(file, &tun->socket.wait, wait);
- if (!skb_queue_empty(&tun->readq))
+ if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
if (sock_writeable(sk) ||
size_t prepad, size_t len,
size_t linear, int noblock)
{
- struct sock *sk = tun->sk;
+ struct sock *sk = tun->socket.sk;
struct sk_buff *skb;
int err;
case VIRTIO_NET_HDR_GSO_TCPV6:
skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+ break;
default:
tun->dev->stats.rx_frame_errors++;
kfree_skb(skb);
gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
else if (sinfo->gso_type & SKB_GSO_TCPV6)
gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ else if (sinfo->gso_type & SKB_GSO_UDP)
+ gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
else
BUG();
if (sinfo->gso_type & SKB_GSO_TCP_ECN)
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->readq))) {
+ if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
if (file->f_flags & O_NONBLOCK) {
ret = -EAGAIN;
break;
{
struct tun_struct *tun = netdev_priv(dev);
- skb_queue_head_init(&tun->readq);
-
tun->owner = -1;
tun->group = -1;
dev = __dev_get_by_name(net, ifr->ifr_name);
if (dev) {
+ const struct cred *cred = current_cred();
+
if (ifr->ifr_flags & IFF_TUN_EXCL)
return -EBUSY;
if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
else
return -EINVAL;
- err = security_tun_dev_attach(tun->sk);
+ if (((tun->owner != -1 && cred->euid != tun->owner) ||
+ (tun->group != -1 && !in_egroup_p(tun->group))) &&
+ !capable(CAP_NET_ADMIN))
+ return -EPERM;
++ err = security_tun_dev_attach(tun->socket.sk);
+ if (err < 0)
+ return err;
+
err = tun_attach(tun, file);
if (err < 0)
return err;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
+ err = security_tun_dev_create();
+ if (err < 0)
+ return err;
/* Set dev type */
if (ifr->ifr_flags & IFF_TUN) {
sk->sk_write_space = tun_sock_write_space;
sk->sk_sndbuf = INT_MAX;
- tun->sk = sk;
container_of(sk, struct tun_sock, sk)->tun = tun;
+ security_tun_dev_post_create(sk);
+
tun_net_init(dev);
if (strchr(dev->name, '%')) {
goto err_free_sk;
}
- err = -EINVAL;
err = register_netdevice(tun->dev);
if (err < 0)
goto err_free_sk;
old_features = dev->features;
/* Unset features, set them as we chew on the arg. */
features = (old_features & ~(NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST
- |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6));
+ |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6
+ |NETIF_F_UFO));
if (arg & TUN_F_CSUM) {
features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
features |= NETIF_F_TSO6;
arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
}
+
+ if (arg & TUN_F_UFO) {
+ features |= NETIF_F_UFO;
+ arg &= ~TUN_F_UFO;
+ }
}
/* This gives the user a way to test for new features in future by
break;
case TUNGETSNDBUF:
- sndbuf = tun->sk->sk_sndbuf;
+ sndbuf = tun->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
ret = -EFAULT;
break;
break;
}
- tun->sk->sk_sndbuf = sndbuf;
+ tun->socket.sk->sk_sndbuf = sndbuf;
break;
default:
tun = tfile->tun;
if (tun)
- sock_put(tun->sk);
+ sock_put(tun->socket.sk);
put_net(tfile->net);
kfree(tfile);
* we must use netif_rx_ni() instead of netif_rx()
*/
netif_rx_ni(skb);
- dev->last_rx = jiffies;
skb_pull(pskb, header->next);
skb_put(pskb, NETIUCV_HDRLEN);
}
if (skb == NULL) {
IUCV_DBF_TEXT(data, 2, "netiucv_tx: skb is NULL\n");
privptr->stats.tx_dropped++;
- return 0;
+ return NETDEV_TX_OK;
}
if (skb_headroom(skb) < NETIUCV_HDRLEN) {
IUCV_DBF_TEXT(data, 2,
"netiucv_tx: skb_headroom < NETIUCV_HDRLEN\n");
dev_kfree_skb(skb);
privptr->stats.tx_dropped++;
- return 0;
+ return NETDEV_TX_OK;
}
/**
privptr->stats.tx_dropped++;
privptr->stats.tx_errors++;
privptr->stats.tx_carrier_errors++;
- return 0;
+ return NETDEV_TX_OK;
}
if (netiucv_test_and_set_busy(dev)) {
return -ENOMEM;
ret = device_register(dev);
-
- if (ret)
+ if (ret) {
+ put_device(dev);
return ret;
+ }
ret = netiucv_add_files(dev);
if (ret)
goto out_unreg;
netiucv_dev->release = (void (*)(struct device *))kfree;
netiucv_dev->driver = &netiucv_driver;
rc = device_register(netiucv_dev);
- if (rc)
+ if (rc) {
+ put_device(netiucv_dev);
goto out_driver;
+ }
netiucv_banner();
return rc;
#define PCI_DEVICE_ID_ATI_IXP600_IDE 0x438c
#define PCI_DEVICE_ID_ATI_IXP700_SATA 0x4390
#define PCI_DEVICE_ID_ATI_IXP700_IDE 0x439c
+/* AMD SB Chipset */
+#define PCI_DEVICE_ID_AMD_SB900_IDE 0x780c
+#define PCI_DEVICE_ID_AMD_SB900_SATA_IDE 0x7800
#define PCI_VENDOR_ID_VLSI 0x1004
#define PCI_DEVICE_ID_VLSI_82C592 0x0005
#define PCI_DEVICE_ID_AMD_8131_BRIDGE 0x7450
#define PCI_DEVICE_ID_AMD_8131_APIC 0x7451
#define PCI_DEVICE_ID_AMD_8132_BRIDGE 0x7458
+#define PCI_DEVICE_ID_AMD_CS5535_IDE 0x208F
#define PCI_DEVICE_ID_AMD_CS5536_ISA 0x2090
#define PCI_DEVICE_ID_AMD_CS5536_FLASH 0x2091
#define PCI_DEVICE_ID_AMD_CS5536_AUDIO 0x2093
#define PCI_VENDOR_ID_SAMSUNG 0x144d
+ #define PCI_VENDOR_ID_GIGABYTE 0x1458
+
#define PCI_VENDOR_ID_AMBIT 0x1468
#define PCI_VENDOR_ID_MYRICOM 0x14c1
#define PCI_DEVICE_ID_TIGON3_5787M 0x1693
#define PCI_DEVICE_ID_TIGON3_5782 0x1696
#define PCI_DEVICE_ID_TIGON3_5784 0x1698
- #define PCI_DEVICE_ID_TIGON3_5785 0x1699
#define PCI_DEVICE_ID_TIGON3_5786 0x169a
#define PCI_DEVICE_ID_TIGON3_5787 0x169b
#define PCI_DEVICE_ID_TIGON3_5788 0x169c
* semaphore held.
*/
DEFINE_RWLOCK(dev_base_lock);
-
EXPORT_SYMBOL(dev_base_lock);
#define NETDEV_HASHBITS 8
*/
DEFINE_PER_CPU(struct softnet_data, softnet_data);
+ EXPORT_PER_CPU_SYMBOL(softnet_data);
#ifdef CONFIG_LOCKDEP
/*
ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211,
ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET,
- ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY,
+ ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154,
ARPHRD_VOID, ARPHRD_NONE};
- static const char *netdev_lock_name[] =
+ static const char *const netdev_lock_name[] =
{"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
"_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211",
"_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET",
- "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY",
+ "_xmit_PHONET_PIPE", "_xmit_IEEE802154",
"_xmit_VOID", "_xmit_NONE"};
static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
}
spin_unlock_bh(&ptype_lock);
}
+ EXPORT_SYMBOL(dev_add_pack);
/**
* __dev_remove_pack - remove packet handler
out:
spin_unlock_bh(&ptype_lock);
}
+ EXPORT_SYMBOL(__dev_remove_pack);
+
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
synchronize_net();
}
+ EXPORT_SYMBOL(dev_remove_pack);
/******************************************************************************
}
return 0;
}
+ EXPORT_SYMBOL(netdev_boot_setup_check);
/**
}
return NULL;
}
+ EXPORT_SYMBOL(__dev_get_by_name);
/**
* dev_get_by_name - find a device by its name
read_unlock(&dev_base_lock);
return dev;
}
+ EXPORT_SYMBOL(dev_get_by_name);
/**
* __dev_get_by_index - find a device by its ifindex
}
return NULL;
}
+ EXPORT_SYMBOL(__dev_get_by_index);
/**
read_unlock(&dev_base_lock);
return dev;
}
+ EXPORT_SYMBOL(dev_get_by_index);
/**
* dev_getbyhwaddr - find a device by its hardware address
return NULL;
}
-
EXPORT_SYMBOL(dev_getbyhwaddr);
struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
return NULL;
}
-
EXPORT_SYMBOL(__dev_getfirstbyhwtype);
struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
rtnl_unlock();
return dev;
}
-
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
* dev_put to indicate they have finished with it.
*/
- struct net_device * dev_get_by_flags(struct net *net, unsigned short if_flags, unsigned short mask)
+ struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags,
+ unsigned short mask)
{
struct net_device *dev, *ret;
read_unlock(&dev_base_lock);
return ret;
}
+ EXPORT_SYMBOL(dev_get_by_flags);
/**
* dev_valid_name - check if name is okay for network device
}
return 1;
}
+ EXPORT_SYMBOL(dev_valid_name);
/**
* __dev_alloc_name - allocate a name for a device
strlcpy(dev->name, buf, IFNAMSIZ);
return ret;
}
+ EXPORT_SYMBOL(dev_alloc_name);
/**
err = dev_alloc_name(dev, newname);
if (err < 0)
return err;
- }
- else if (__dev_get_by_name(net, newname))
+ } else if (__dev_get_by_name(net, newname))
return -EEXIST;
else
strlcpy(dev->name, newname, IFNAMSIZ);
return 0;
}
- dev->ifalias = krealloc(dev->ifalias, len+1, GFP_KERNEL);
+ dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL);
if (!dev->ifalias)
return -ENOMEM;
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
+ EXPORT_SYMBOL(netdev_state_change);
void netdev_bonding_change(struct net_device *dev)
{
dev = __dev_get_by_name(net, name);
read_unlock(&dev_base_lock);
- if (!dev && capable(CAP_SYS_MODULE))
+ if (!dev && capable(CAP_NET_ADMIN))
request_module("%s", name);
}
+ EXPORT_SYMBOL(dev_load);
/**
* dev_open - prepare an interface for use.
return ret;
}
+ EXPORT_SYMBOL(dev_open);
/**
* dev_close - shutdown an interface.
return 0;
}
+ EXPORT_SYMBOL(dev_close);
/**
raw_notifier_chain_unregister(&netdev_chain, nb);
goto unlock;
}
+ EXPORT_SYMBOL(register_netdevice_notifier);
/**
* unregister_netdevice_notifier - unregister a network notifier block
rtnl_unlock();
return err;
}
+ EXPORT_SYMBOL(unregister_netdevice_notifier);
/**
* call_netdevice_notifiers - call all network notifier blocks
{
atomic_inc(&netstamp_needed);
}
+ EXPORT_SYMBOL(net_enable_timestamp);
void net_disable_timestamp(void)
{
atomic_dec(&netstamp_needed);
}
+ EXPORT_SYMBOL(net_disable_timestamp);
static inline void net_timestamp(struct sk_buff *skb)
{
if ((ptype->dev == dev || !ptype->dev) &&
(ptype->af_packet_priv == NULL ||
(struct sock *)ptype->af_packet_priv != skb->sk)) {
- struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
+ struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
break;
out:
return ret;
}
+ EXPORT_SYMBOL(skb_checksum_help);
/**
* skb_gso_segment - Perform segmentation on skb.
return segs;
}
-
EXPORT_SYMBOL(skb_gso_segment);
/* Take action when hardware reception checksum errors are detected. */
skb_dst_drop(skb);
rc = ops->ndo_start_xmit(skb, dev);
- if (rc == 0)
+ if (rc == NETDEV_TX_OK)
txq_trans_update(txq);
/*
* TODO: if skb_orphan() was called by
skb->next = nskb->next;
nskb->next = NULL;
rc = ops->ndo_start_xmit(nskb, dev);
- if (unlikely(rc)) {
+ if (unlikely(rc != NETDEV_TX_OK)) {
nskb->next = skb->next;
skb->next = nskb;
return rc;
out_kfree_skb:
kfree_skb(skb);
- return 0;
+ return NETDEV_TX_OK;
}
static u32 skb_tx_hashrnd;
if (skb_rx_queue_recorded(skb)) {
hash = skb_get_rx_queue(skb);
- while (unlikely (hash >= dev->real_num_tx_queues))
+ while (unlikely(hash >= dev->real_num_tx_queues))
hash -= dev->real_num_tx_queues;
return hash;
}
return netdev_get_tx_queue(dev, queue_index);
}
+ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
+ struct net_device *dev,
+ struct netdev_queue *txq)
+ {
+ spinlock_t *root_lock = qdisc_lock(q);
+ int rc;
+
+ spin_lock(root_lock);
+ if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
+ kfree_skb(skb);
+ rc = NET_XMIT_DROP;
+ } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) &&
+ !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) {
+ /*
+ * This is a work-conserving queue; there are no old skbs
+ * waiting to be sent out; and the qdisc is not running -
+ * xmit the skb directly.
+ */
+ __qdisc_update_bstats(q, skb->len);
+ if (sch_direct_xmit(skb, q, dev, txq, root_lock))
+ __qdisc_run(q);
+ else
+ clear_bit(__QDISC_STATE_RUNNING, &q->state);
+
+ rc = NET_XMIT_SUCCESS;
+ } else {
+ rc = qdisc_enqueue_root(skb, q);
+ qdisc_run(q);
+ }
+ spin_unlock(root_lock);
+
+ return rc;
+ }
+
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
q = rcu_dereference(txq->qdisc);
#ifdef CONFIG_NET_CLS_ACT
- skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
+ skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS);
#endif
if (q->enqueue) {
- spinlock_t *root_lock = qdisc_lock(q);
-
- spin_lock(root_lock);
-
- if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) {
- kfree_skb(skb);
- rc = NET_XMIT_DROP;
- } else {
- rc = qdisc_enqueue_root(skb, q);
- qdisc_run(q);
- }
- spin_unlock(root_lock);
-
+ rc = __dev_xmit_skb(skb, q, dev, txq);
goto out;
}
HARD_TX_LOCK(dev, txq, cpu);
if (!netif_tx_queue_stopped(txq)) {
- rc = 0;
+ rc = NET_XMIT_SUCCESS;
if (!dev_hard_start_xmit(skb, dev, txq)) {
HARD_TX_UNLOCK(dev, txq);
goto out;
rcu_read_unlock_bh();
return rc;
}
+ EXPORT_SYMBOL(dev_queue_xmit);
/*=======================================================================
kfree_skb(skb);
return NET_RX_DROP;
}
+ EXPORT_SYMBOL(netif_rx);
int netif_rx_ni(struct sk_buff *skb)
{
return err;
}
-
EXPORT_SYMBOL(netif_rx_ni);
static void net_tx_action(struct softirq_action *h)
/* This hook is defined here for ATM LANE */
int (*br_fdb_test_addr_hook)(struct net_device *dev,
unsigned char *addr) __read_mostly;
- EXPORT_SYMBOL(br_fdb_test_addr_hook);
+ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
#endif
/*
*/
struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
struct sk_buff *skb) __read_mostly;
- EXPORT_SYMBOL(br_handle_frame_hook);
+ EXPORT_SYMBOL_GPL(br_handle_frame_hook);
static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
struct packet_type **pt_prev, int *ret,
rcu_read_unlock();
return ret;
}
+ EXPORT_SYMBOL(netif_receive_skb);
/* Network device is going away, flush any packets still pending */
static void flush_backlog(void *arg)
goto out;
}
- static gifconf_func_t * gifconf_list [NPROTO];
+ static gifconf_func_t *gifconf_list[NPROTO];
/**
* register_gifconf - register a SIOCGIF handler
* that is passed must not be freed or reused until it has been replaced
* by another handler.
*/
- int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
+ int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
{
if (family >= NPROTO)
return -EINVAL;
gifconf_list[family] = gifconf;
return 0;
}
+ EXPORT_SYMBOL(register_gifconf);
/*
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
- s->cpu_collision );
+ s->cpu_collision);
return 0;
}
rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
return 0;
}
+ EXPORT_SYMBOL(netdev_set_master);
static void dev_change_rx_flags(struct net_device *dev, int flags)
{
dev_set_rx_mode(dev);
return err;
}
+ EXPORT_SYMBOL(dev_set_promiscuity);
/**
* dev_set_allmulti - update allmulti count on a device
}
return 0;
}
+ EXPORT_SYMBOL(dev_set_allmulti);
/*
* Upload unicast and multicast address lists to device and
}
return err;
}
+ EXPORT_SYMBOL_GPL(__dev_addr_sync);
void __dev_addr_unsync(struct dev_addr_list **to, int *to_count,
struct dev_addr_list **from, int *from_count)
da = next;
}
}
+ EXPORT_SYMBOL_GPL(__dev_addr_unsync);
/**
* dev_unicast_sync - Synchronize device's unicast list to another device
return flags;
}
+ EXPORT_SYMBOL(dev_get_flags);
/**
* dev_change_flags - change device settings
}
if (dev->flags & IFF_UP &&
- ((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
+ ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
IFF_VOLATILE)))
call_netdevice_notifiers(NETDEV_CHANGE, dev);
if ((flags ^ dev->gflags) & IFF_PROMISC) {
- int inc = (flags & IFF_PROMISC) ? +1 : -1;
+ int inc = (flags & IFF_PROMISC) ? 1 : -1;
+
dev->gflags ^= IFF_PROMISC;
dev_set_promiscuity(dev, inc);
}
IFF_ALLMULTI is requested not asking us and not reporting.
*/
if ((flags ^ dev->gflags) & IFF_ALLMULTI) {
- int inc = (flags & IFF_ALLMULTI) ? +1 : -1;
+ int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
+
dev->gflags ^= IFF_ALLMULTI;
dev_set_allmulti(dev, inc);
}
return ret;
}
+ EXPORT_SYMBOL(dev_change_flags);
/**
* dev_set_mtu - Change maximum transfer unit
call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
}
+ EXPORT_SYMBOL(dev_set_mtu);
/**
* dev_set_mac_address - Change Media Access Control Address
call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
return err;
}
+ EXPORT_SYMBOL(dev_set_mac_address);
/*
* Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock)
return -ENODEV;
switch (cmd) {
- case SIOCGIFFLAGS: /* Get interface flags */
- ifr->ifr_flags = (short) dev_get_flags(dev);
- return 0;
+ case SIOCGIFFLAGS: /* Get interface flags */
+ ifr->ifr_flags = (short) dev_get_flags(dev);
+ return 0;
- case SIOCGIFMETRIC: /* Get the metric on the interface
- (currently unused) */
- ifr->ifr_metric = 0;
- return 0;
+ case SIOCGIFMETRIC: /* Get the metric on the interface
+ (currently unused) */
+ ifr->ifr_metric = 0;
+ return 0;
- case SIOCGIFMTU: /* Get the MTU of a device */
- ifr->ifr_mtu = dev->mtu;
- return 0;
+ case SIOCGIFMTU: /* Get the MTU of a device */
+ ifr->ifr_mtu = dev->mtu;
+ return 0;
- case SIOCGIFHWADDR:
- if (!dev->addr_len)
- memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
- else
- memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- ifr->ifr_hwaddr.sa_family = dev->type;
- return 0;
+ case SIOCGIFHWADDR:
+ if (!dev->addr_len)
+ memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+ else
+ memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ ifr->ifr_hwaddr.sa_family = dev->type;
+ return 0;
- case SIOCGIFSLAVE:
- err = -EINVAL;
- break;
+ case SIOCGIFSLAVE:
+ err = -EINVAL;
+ break;
- case SIOCGIFMAP:
- ifr->ifr_map.mem_start = dev->mem_start;
- ifr->ifr_map.mem_end = dev->mem_end;
- ifr->ifr_map.base_addr = dev->base_addr;
- ifr->ifr_map.irq = dev->irq;
- ifr->ifr_map.dma = dev->dma;
- ifr->ifr_map.port = dev->if_port;
- return 0;
+ case SIOCGIFMAP:
+ ifr->ifr_map.mem_start = dev->mem_start;
+ ifr->ifr_map.mem_end = dev->mem_end;
+ ifr->ifr_map.base_addr = dev->base_addr;
+ ifr->ifr_map.irq = dev->irq;
+ ifr->ifr_map.dma = dev->dma;
+ ifr->ifr_map.port = dev->if_port;
+ return 0;
- case SIOCGIFINDEX:
- ifr->ifr_ifindex = dev->ifindex;
- return 0;
+ case SIOCGIFINDEX:
+ ifr->ifr_ifindex = dev->ifindex;
+ return 0;
- case SIOCGIFTXQLEN:
- ifr->ifr_qlen = dev->tx_queue_len;
- return 0;
+ case SIOCGIFTXQLEN:
+ ifr->ifr_qlen = dev->tx_queue_len;
+ return 0;
- default:
- /* dev_ioctl() should ensure this case
- * is never reached
- */
- WARN_ON(1);
- err = -EINVAL;
- break;
+ default:
+ /* dev_ioctl() should ensure this case
+ * is never reached
+ */
+ WARN_ON(1);
+ err = -EINVAL;
+ break;
}
return err;
ops = dev->netdev_ops;
switch (cmd) {
- case SIOCSIFFLAGS: /* Set interface flags */
- return dev_change_flags(dev, ifr->ifr_flags);
-
- case SIOCSIFMETRIC: /* Set the metric on the interface
- (currently unused) */
- return -EOPNOTSUPP;
+ case SIOCSIFFLAGS: /* Set interface flags */
+ return dev_change_flags(dev, ifr->ifr_flags);
- case SIOCSIFMTU: /* Set the MTU of a device */
- return dev_set_mtu(dev, ifr->ifr_mtu);
+ case SIOCSIFMETRIC: /* Set the metric on the interface
+ (currently unused) */
+ return -EOPNOTSUPP;
- case SIOCSIFHWADDR:
- return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+ case SIOCSIFMTU: /* Set the MTU of a device */
+ return dev_set_mtu(dev, ifr->ifr_mtu);
- case SIOCSIFHWBROADCAST:
- if (ifr->ifr_hwaddr.sa_family != dev->type)
- return -EINVAL;
- memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
- min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
- call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
- return 0;
+ case SIOCSIFHWADDR:
+ return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
- case SIOCSIFMAP:
- if (ops->ndo_set_config) {
- if (!netif_device_present(dev))
- return -ENODEV;
- return ops->ndo_set_config(dev, &ifr->ifr_map);
- }
- return -EOPNOTSUPP;
-
- case SIOCADDMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
- if (!netif_device_present(dev))
- return -ENODEV;
- return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ case SIOCSIFHWBROADCAST:
+ if (ifr->ifr_hwaddr.sa_family != dev->type)
+ return -EINVAL;
+ memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+ min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+ call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+ return 0;
- case SIOCDELMULTI:
- if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
- ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
- return -EINVAL;
+ case SIOCSIFMAP:
+ if (ops->ndo_set_config) {
if (!netif_device_present(dev))
return -ENODEV;
- return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
- dev->addr_len, 1);
+ return ops->ndo_set_config(dev, &ifr->ifr_map);
+ }
+ return -EOPNOTSUPP;
- case SIOCSIFTXQLEN:
- if (ifr->ifr_qlen < 0)
- return -EINVAL;
- dev->tx_queue_len = ifr->ifr_qlen;
- return 0;
+ case SIOCADDMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_add(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
+
+ case SIOCDELMULTI:
+ if ((!ops->ndo_set_multicast_list && !ops->ndo_set_rx_mode) ||
+ ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+ return -EINVAL;
+ if (!netif_device_present(dev))
+ return -ENODEV;
+ return dev_mc_delete(dev, ifr->ifr_hwaddr.sa_data,
+ dev->addr_len, 1);
- case SIOCSIFNAME:
- ifr->ifr_newname[IFNAMSIZ-1] = '\0';
- return dev_change_name(dev, ifr->ifr_newname);
+ case SIOCSIFTXQLEN:
+ if (ifr->ifr_qlen < 0)
+ return -EINVAL;
+ dev->tx_queue_len = ifr->ifr_qlen;
+ return 0;
- /*
- * Unknown or private ioctl
- */
+ case SIOCSIFNAME:
+ ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+ return dev_change_name(dev, ifr->ifr_newname);
- default:
- if ((cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15) ||
- cmd == SIOCBONDENSLAVE ||
- cmd == SIOCBONDRELEASE ||
- cmd == SIOCBONDSETHWADDR ||
- cmd == SIOCBONDSLAVEINFOQUERY ||
- cmd == SIOCBONDINFOQUERY ||
- cmd == SIOCBONDCHANGEACTIVE ||
- cmd == SIOCGMIIPHY ||
- cmd == SIOCGMIIREG ||
- cmd == SIOCSMIIREG ||
- cmd == SIOCBRADDIF ||
- cmd == SIOCBRDELIF ||
- cmd == SIOCSHWTSTAMP ||
- cmd == SIOCWANDEV) {
- err = -EOPNOTSUPP;
- if (ops->ndo_do_ioctl) {
- if (netif_device_present(dev))
- err = ops->ndo_do_ioctl(dev, ifr, cmd);
- else
- err = -ENODEV;
- }
- } else
- err = -EINVAL;
+ /*
+ * Unknown or private ioctl
+ */
+ default:
+ if ((cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15) ||
+ cmd == SIOCBONDENSLAVE ||
+ cmd == SIOCBONDRELEASE ||
+ cmd == SIOCBONDSETHWADDR ||
+ cmd == SIOCBONDSLAVEINFOQUERY ||
+ cmd == SIOCBONDINFOQUERY ||
+ cmd == SIOCBONDCHANGEACTIVE ||
+ cmd == SIOCGMIIPHY ||
+ cmd == SIOCGMIIREG ||
+ cmd == SIOCSMIIREG ||
+ cmd == SIOCBRADDIF ||
+ cmd == SIOCBRDELIF ||
+ cmd == SIOCSHWTSTAMP ||
+ cmd == SIOCWANDEV) {
+ err = -EOPNOTSUPP;
+ if (ops->ndo_do_ioctl) {
+ if (netif_device_present(dev))
+ err = ops->ndo_do_ioctl(dev, ifr, cmd);
+ else
+ err = -ENODEV;
+ }
+ } else
+ err = -EINVAL;
}
return err;
*/
switch (cmd) {
- /*
- * These ioctl calls:
- * - can be done by all.
- * - atomic and do not require locking.
- * - return a value
- */
- case SIOCGIFFLAGS:
- case SIOCGIFMETRIC:
- case SIOCGIFMTU:
- case SIOCGIFHWADDR:
- case SIOCGIFSLAVE:
- case SIOCGIFMAP:
- case SIOCGIFINDEX:
- case SIOCGIFTXQLEN:
- dev_load(net, ifr.ifr_name);
- read_lock(&dev_base_lock);
- ret = dev_ifsioc_locked(net, &ifr, cmd);
- read_unlock(&dev_base_lock);
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - can be done by all.
+ * - atomic and do not require locking.
+ * - return a value
+ */
+ case SIOCGIFFLAGS:
+ case SIOCGIFMETRIC:
+ case SIOCGIFMTU:
+ case SIOCGIFHWADDR:
+ case SIOCGIFSLAVE:
+ case SIOCGIFMAP:
+ case SIOCGIFINDEX:
+ case SIOCGIFTXQLEN:
+ dev_load(net, ifr.ifr_name);
+ read_lock(&dev_base_lock);
+ ret = dev_ifsioc_locked(net, &ifr, cmd);
+ read_unlock(&dev_base_lock);
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- case SIOCETHTOOL:
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ethtool(net, &ifr);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ case SIOCETHTOOL:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ethtool(net, &ifr);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - return a value
- */
- case SIOCGMIIPHY:
- case SIOCGMIIREG:
- case SIOCSIFNAME:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret) {
- if (colon)
- *colon = ':';
- if (copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- }
- return ret;
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - return a value
+ */
+ case SIOCGMIIPHY:
+ case SIOCGMIIREG:
+ case SIOCSIFNAME:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ if (!ret) {
+ if (colon)
+ *colon = ':';
+ if (copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
+ }
+ return ret;
- /*
- * These ioctl calls:
- * - require superuser power.
- * - require strict serialization.
- * - do not return a value
- */
- case SIOCSIFFLAGS:
- case SIOCSIFMETRIC:
- case SIOCSIFMTU:
- case SIOCSIFMAP:
- case SIOCSIFHWADDR:
- case SIOCSIFSLAVE:
- case SIOCADDMULTI:
- case SIOCDELMULTI:
- case SIOCSIFHWBROADCAST:
- case SIOCSIFTXQLEN:
- case SIOCSMIIREG:
- case SIOCBONDENSLAVE:
- case SIOCBONDRELEASE:
- case SIOCBONDSETHWADDR:
- case SIOCBONDCHANGEACTIVE:
- case SIOCBRADDIF:
- case SIOCBRDELIF:
- case SIOCSHWTSTAMP:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- /* fall through */
- case SIOCBONDSLAVEINFOQUERY:
- case SIOCBONDINFOQUERY:
+ /*
+ * These ioctl calls:
+ * - require superuser power.
+ * - require strict serialization.
+ * - do not return a value
+ */
+ case SIOCSIFFLAGS:
+ case SIOCSIFMETRIC:
+ case SIOCSIFMTU:
+ case SIOCSIFMAP:
+ case SIOCSIFHWADDR:
+ case SIOCSIFSLAVE:
+ case SIOCADDMULTI:
+ case SIOCDELMULTI:
+ case SIOCSIFHWBROADCAST:
+ case SIOCSIFTXQLEN:
+ case SIOCSMIIREG:
+ case SIOCBONDENSLAVE:
+ case SIOCBONDRELEASE:
+ case SIOCBONDSETHWADDR:
+ case SIOCBONDCHANGEACTIVE:
+ case SIOCBRADDIF:
+ case SIOCBRDELIF:
+ case SIOCSHWTSTAMP:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ /* fall through */
+ case SIOCBONDSLAVEINFOQUERY:
+ case SIOCBONDINFOQUERY:
+ dev_load(net, ifr.ifr_name);
+ rtnl_lock();
+ ret = dev_ifsioc(net, &ifr, cmd);
+ rtnl_unlock();
+ return ret;
+
+ case SIOCGIFMEM:
+ /* Get the per device memory space. We can add this but
+ * currently do not support it */
+ case SIOCSIFMEM:
+ /* Set the per device memory buffer space.
+ * Not applicable in our case */
+ case SIOCSIFLINK:
+ return -EINVAL;
+
+ /*
+ * Unknown or private ioctl.
+ */
+ default:
+ if (cmd == SIOCWANDEV ||
+ (cmd >= SIOCDEVPRIVATE &&
+ cmd <= SIOCDEVPRIVATE + 15)) {
dev_load(net, ifr.ifr_name);
rtnl_lock();
ret = dev_ifsioc(net, &ifr, cmd);
rtnl_unlock();
+ if (!ret && copy_to_user(arg, &ifr,
+ sizeof(struct ifreq)))
+ ret = -EFAULT;
return ret;
-
- case SIOCGIFMEM:
- /* Get the per device memory space. We can add this but
- * currently do not support it */
- case SIOCSIFMEM:
- /* Set the per device memory buffer space.
- * Not applicable in our case */
- case SIOCSIFLINK:
- return -EINVAL;
-
- /*
- * Unknown or private ioctl.
- */
- default:
- if (cmd == SIOCWANDEV ||
- (cmd >= SIOCDEVPRIVATE &&
- cmd <= SIOCDEVPRIVATE + 15)) {
- dev_load(net, ifr.ifr_name);
- rtnl_lock();
- ret = dev_ifsioc(net, &ifr, cmd);
- rtnl_unlock();
- if (!ret && copy_to_user(arg, &ifr,
- sizeof(struct ifreq)))
- ret = -EFAULT;
- return ret;
- }
- /* Take care of Wireless Extensions */
- if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
- return wext_handle_ioctl(net, &ifr, cmd, arg);
- return -EINVAL;
+ }
+ /* Take care of Wireless Extensions */
+ if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
+ return wext_handle_ioctl(net, &ifr, cmd, arg);
+ return -EINVAL;
}
}
dev->netdev_ops->ndo_uninit(dev);
goto out;
}
+ EXPORT_SYMBOL(register_netdevice);
/**
* init_dummy_netdev - init a dummy network device for NAPI
/* will free via device release */
put_device(&dev->dev);
}
+ EXPORT_SYMBOL(free_netdev);
/**
* synchronize_net - Synchronize with packet receive processing
might_sleep();
synchronize_rcu();
}
+ EXPORT_SYMBOL(synchronize_net);
/**
* unregister_netdevice - remove device from the kernel
/* Finish processing unregister after unlock */
net_set_todo(dev);
}
+ EXPORT_SYMBOL(unregister_netdevice);
/**
* unregister_netdev - remove device from the kernel
unregister_netdevice(dev);
rtnl_unlock();
}
-
EXPORT_SYMBOL(unregister_netdev);
/**
out:
return err;
}
+ EXPORT_SYMBOL_GPL(dev_change_net_namespace);
static int dev_cpu_callback(struct notifier_block *nfb,
unsigned long action,
unsigned long mask)
{
/* If device needs checksumming, downgrade to it. */
- if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM);
else if (mask & NETIF_F_ALL_CSUM) {
/* If one device supports v4/v6 checksumming, set for all. */
late_initcall_sync(initialize_hashrnd);
- EXPORT_SYMBOL(__dev_get_by_index);
- EXPORT_SYMBOL(__dev_get_by_name);
- EXPORT_SYMBOL(__dev_remove_pack);
- EXPORT_SYMBOL(dev_valid_name);
- EXPORT_SYMBOL(dev_add_pack);
- EXPORT_SYMBOL(dev_alloc_name);
- EXPORT_SYMBOL(dev_close);
- EXPORT_SYMBOL(dev_get_by_flags);
- EXPORT_SYMBOL(dev_get_by_index);
- EXPORT_SYMBOL(dev_get_by_name);
- EXPORT_SYMBOL(dev_open);
- EXPORT_SYMBOL(dev_queue_xmit);
- EXPORT_SYMBOL(dev_remove_pack);
- EXPORT_SYMBOL(dev_set_allmulti);
- EXPORT_SYMBOL(dev_set_promiscuity);
- EXPORT_SYMBOL(dev_change_flags);
- EXPORT_SYMBOL(dev_set_mtu);
- EXPORT_SYMBOL(dev_set_mac_address);
- EXPORT_SYMBOL(free_netdev);
- EXPORT_SYMBOL(netdev_boot_setup_check);
- EXPORT_SYMBOL(netdev_set_master);
- EXPORT_SYMBOL(netdev_state_change);
- EXPORT_SYMBOL(netif_receive_skb);
- EXPORT_SYMBOL(netif_rx);
- EXPORT_SYMBOL(register_gifconf);
- EXPORT_SYMBOL(register_netdevice);
- EXPORT_SYMBOL(register_netdevice_notifier);
- EXPORT_SYMBOL(skb_checksum_help);
- EXPORT_SYMBOL(synchronize_net);
- EXPORT_SYMBOL(unregister_netdevice);
- EXPORT_SYMBOL(unregister_netdevice_notifier);
- EXPORT_SYMBOL(net_enable_timestamp);
- EXPORT_SYMBOL(net_disable_timestamp);
- EXPORT_SYMBOL(dev_get_flags);
-
- EXPORT_SYMBOL(dev_load);
-
- EXPORT_PER_CPU_SYMBOL(softnet_data);
inet->cork.addr = ipc->addr;
}
rt = *rtp;
+ if (unlikely(!rt))
+ return -EFAULT;
/*
* We steal reference to this route, caller should not release it
*/
err = ip_local_out(skb);
if (err) {
if (err > 0)
- err = inet->recverr ? net_xmit_errno(err) : 0;
+ err = net_xmit_errno(err);
if (err)
goto error;
}
static void qdisc_list_add(struct Qdisc *q)
{
if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS))
- list_add_tail(&q->list, &qdisc_root_sleeping(q)->list);
+ list_add_tail(&q->list, &qdisc_dev(q)->qdisc->list);
}
void qdisc_list_del(struct Qdisc *q)
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
{
- unsigned int i;
struct Qdisc *q;
- for (i = 0; i < dev->num_tx_queues; i++) {
- struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
- struct Qdisc *txq_root = txq->qdisc_sleeping;
-
- q = qdisc_match_from_root(txq_root, handle);
- if (q)
- goto out;
- }
+ q = qdisc_match_from_root(dev->qdisc, handle);
+ if (q)
+ goto out;
q = qdisc_match_from_root(dev->rx_queue.qdisc_sleeping, handle);
out:
return i>0 ? autohandle : 0;
}
- /* Attach toplevel qdisc to device queue. */
-
- static struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
- struct Qdisc *qdisc)
- {
- struct Qdisc *oqdisc = dev_queue->qdisc_sleeping;
- spinlock_t *root_lock;
-
- root_lock = qdisc_lock(oqdisc);
- spin_lock_bh(root_lock);
-
- /* Prune old scheduler */
- if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1)
- qdisc_reset(oqdisc);
-
- /* ... and graft new one */
- if (qdisc == NULL)
- qdisc = &noop_qdisc;
- dev_queue->qdisc_sleeping = qdisc;
- rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc);
-
- spin_unlock_bh(root_lock);
-
- return oqdisc;
- }
-
void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n)
{
const struct Qdisc_class_ops *cops;
if (dev->flags & IFF_UP)
dev_deactivate(dev);
+ if (new && new->ops->attach) {
+ new->ops->attach(new);
+ num_q = 0;
+ }
+
for (i = 0; i < num_q; i++) {
struct netdev_queue *dev_queue = &dev->rx_queue;
if (new && i > 0)
atomic_inc(&new->refcnt);
- notify_and_destroy(skb, n, classid, old, new);
+ qdisc_destroy(old);
}
+ notify_and_destroy(skb, n, classid, dev->qdisc, new);
+ if (new && !new->ops->attach)
+ atomic_inc(&new->refcnt);
+ dev->qdisc = new ? : &noop_qdisc;
+
if (dev->flags & IFF_UP)
dev_activate(dev);
} else {
const struct Qdisc_class_ops *cops = parent->ops->cl_ops;
- err = -EINVAL;
-
- if (cops) {
+ err = -EOPNOTSUPP;
+ if (cops && cops->graft) {
unsigned long cl = cops->get(parent, classid);
if (cl) {
err = cops->graft(parent, cl, new, &old);
cops->put(parent, cl);
- }
+ } else
+ err = -ENOENT;
}
if (!err)
notify_and_destroy(skb, n, classid, old, new);
static struct Qdisc *
qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
- u32 parent, u32 handle, struct nlattr **tca, int *errp)
+ struct Qdisc *p, u32 parent, u32 handle,
+ struct nlattr **tca, int *errp)
{
int err;
struct nlattr *kind = tca[TCA_KIND];
if (tca[TCA_RATE]) {
spinlock_t *root_lock;
+ err = -EOPNOTSUPP;
+ if (sch->flags & TCQ_F_MQROOT)
+ goto err_out4;
+
if ((sch->parent != TC_H_ROOT) &&
- !(sch->flags & TCQ_F_INGRESS))
+ !(sch->flags & TCQ_F_INGRESS) &&
+ (!p || !(p->flags & TCQ_F_MQROOT)))
root_lock = qdisc_root_sleeping_lock(sch);
else
root_lock = qdisc_lock(sch);
err = gen_new_estimator(&sch->bstats, &sch->rate_est,
root_lock, tca[TCA_RATE]);
- if (err) {
- /*
- * Any broken qdiscs that would require
- * a ops->reset() here? The qdisc was never
- * in action so it shouldn't be necessary.
- */
- if (ops->destroy)
- ops->destroy(sch);
- goto err_out3;
- }
+ if (err)
+ goto err_out4;
}
qdisc_list_add(sch);
err_out:
*errp = err;
return NULL;
+
+ err_out4:
+ /*
+ * Any broken qdiscs that would require a ops->reset() here?
+ * The qdisc was never in action so it shouldn't be necessary.
+ */
+ if (ops->destroy)
+ ops->destroy(sch);
+ goto err_out3;
}
static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
qdisc_put_stab(sch->stab);
sch->stab = stab;
- if (tca[TCA_RATE])
+ if (tca[TCA_RATE]) {
/* NB: ignores errors from replace_estimator
because change can't be undone. */
+ if (sch->flags & TCQ_F_MQROOT)
+ goto out;
gen_replace_estimator(&sch->bstats, &sch->rate_est,
qdisc_root_sleeping_lock(sch),
tca[TCA_RATE]);
-
+ }
+ out:
return 0;
}
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
if (!q)
return -ENOENT;
q = dev->rx_queue.qdisc_sleeping;
}
} else {
- struct netdev_queue *dev_queue;
- dev_queue = netdev_get_tx_queue(dev, 0);
- q = dev_queue->qdisc_sleeping;
+ q = dev->qdisc;
}
/* It may be default qdisc, ignore it */
if (!(n->nlmsg_flags&NLM_F_CREATE))
return -ENOENT;
if (clid == TC_H_INGRESS)
- q = qdisc_create(dev, &dev->rx_queue,
+ q = qdisc_create(dev, &dev->rx_queue, p,
tcm->tcm_parent, tcm->tcm_parent,
tca, &err);
- else
- q = qdisc_create(dev, netdev_get_tx_queue(dev, 0),
+ else {
+ unsigned int ntx = 0;
+
+ if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue)
+ ntx = p->ops->cl_ops->select_queue(p, tcm);
+
+ q = qdisc_create(dev, netdev_get_tx_queue(dev, ntx), p,
tcm->tcm_parent, tcm->tcm_handle,
tca, &err);
+ }
if (q == NULL) {
if (err == -EAGAIN)
goto replay;
s_q_idx = 0;
q_idx = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_qdisc_root(dev_queue->qdisc_sleeping, skb, cb, &q_idx, s_q_idx) < 0)
+ if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx) < 0)
goto done;
dev_queue = &dev->rx_queue;
static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg)
{
struct net *net = sock_net(skb->sk);
- struct netdev_queue *dev_queue;
struct tcmsg *tcm = NLMSG_DATA(n);
struct nlattr *tca[TCA_MAX + 1];
struct net_device *dev;
/* Step 1. Determine qdisc handle X:0 */
- dev_queue = netdev_get_tx_queue(dev, 0);
if (pid != TC_H_ROOT) {
u32 qid1 = TC_H_MAJ(pid);
} else if (qid1) {
qid = qid1;
} else if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
/* Now qid is genuine qdisc handle consistent
both with parent and child.
pid = TC_H_MAKE(qid, pid);
} else {
if (qid == 0)
- qid = dev_queue->qdisc_sleeping->handle;
+ qid = dev->qdisc->handle;
}
/* OK. Locate qdisc */
goto out;
break;
case RTM_DELTCLASS:
- err = cops->delete(q, cl);
+ err = -EOPNOTSUPP;
+ if (cops->delete)
+ err = cops->delete(q, cl);
if (err == 0)
tclass_notify(skb, n, q, cl, RTM_DELTCLASS);
goto out;
}
new_cl = cl;
- err = cops->change(q, clid, pid, tca, &new_cl);
+ err = -EOPNOTSUPP;
+ if (cops->change)
+ err = cops->change(q, clid, pid, tca, &new_cl);
if (err == 0)
tclass_notify(skb, n, q, new_cl, RTM_NEWTCLASS);
nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags);
tcm = NLMSG_DATA(nlh);
tcm->tcm_family = AF_UNSPEC;
+ tcm->tcm__pad1 = 0;
+ tcm->tcm__pad2 = 0;
tcm->tcm_ifindex = qdisc_dev(q)->ifindex;
tcm->tcm_parent = q->handle;
tcm->tcm_handle = q->handle;
s_t = cb->args[0];
t = 0;
- dev_queue = netdev_get_tx_queue(dev, 0);
- if (tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb, &t, s_t) < 0)
+ if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0)
goto done;
dev_queue = &dev->rx_queue;
{
register_qdisc(&pfifo_qdisc_ops);
register_qdisc(&bfifo_qdisc_ops);
+ register_qdisc(&mq_qdisc_ops);
proc_net_fops_create(&init_net, "psched", 0, &psched_fops);
rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL);
git://bbs.cooldavid.org / net-next-2.6.git / commitdiff