* [PATCH nf-next-2.6 2/2] conntrack: per_cpu untracking
From: Eric Dumazet @ 2010-06-04 20:15 UTC (permalink / raw)
To: Patrick McHardy; +Cc: Changli Gao, Netfilter Developers, netdev
In-Reply-To: <1275668732.2482.201.camel@edumazet-laptop>
NOTRACK makes all cpus share a cache line on nf_conntrack_untracked
twice per packet, slowing down performance.
This patch converts it to a per_cpu variable.
We assume same cpu is used for a given packet, entering and exiting the
NOTRACK state.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/net/netfilter/nf_conntrack.h | 5 +--
net/netfilter/nf_conntrack_core.c | 36 ++++++++++++++++++-------
2 files changed, 28 insertions(+), 13 deletions(-)
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 3bc38c7..84a4b6f 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -261,11 +261,10 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
u32 seq);
/* Fake conntrack entry for untracked connections */
+DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
static inline struct nf_conn *nf_ct_untracked_get(void)
{
- extern struct nf_conn nf_conntrack_untracked;
-
- return &nf_conntrack_untracked;
+ return &__raw_get_cpu_var(nf_conntrack_untracked);
}
extern void nf_ct_untracked_status_or(unsigned long bits);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 6c1da21..9c66141 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -62,8 +62,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_max);
-struct nf_conn nf_conntrack_untracked;
-EXPORT_SYMBOL_GPL(nf_conntrack_untracked);
+DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
static int nf_conntrack_hash_rnd_initted;
static unsigned int nf_conntrack_hash_rnd;
@@ -1183,10 +1183,21 @@ static void nf_ct_release_dying_list(struct net *net)
spin_unlock_bh(&nf_conntrack_lock);
}
+static int untrack_refs(void)
+{
+ int cnt = 0, cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
+
+ cnt += atomic_read(&ct->ct_general.use) - 1;
+ }
+ return cnt;
+}
+
static void nf_conntrack_cleanup_init_net(void)
{
- /* wait until all references to nf_conntrack_untracked are dropped */
- while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1)
+ while (untrack_refs() > 0)
schedule();
nf_conntrack_helper_fini();
@@ -1323,14 +1334,17 @@ module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
void nf_ct_untracked_status_or(unsigned long bits)
{
- nf_conntrack_untracked.status |= bits;
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(nf_conntrack_untracked, cpu).status |= bits;
}
EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
static int nf_conntrack_init_init_net(void)
{
int max_factor = 8;
- int ret;
+ int ret, cpu;
/* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB
* machine has 512 buckets. >= 1GB machines have 16384 buckets. */
@@ -1369,10 +1383,12 @@ static int nf_conntrack_init_init_net(void)
goto err_extend;
#endif
/* Set up fake conntrack: to never be deleted, not in any hashes */
-#ifdef CONFIG_NET_NS
- nf_conntrack_untracked.ct_net = &init_net;
-#endif
- atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
+ for_each_possible_cpu(cpu) {
+ struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
+
+ write_pnet(&ct->ct_net, &init_net);
+ atomic_set(&ct->ct_general.use, 1);
+ }
/* - and look it like as a confirmed connection */
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
return 0;
^ permalink raw reply related
* Re: still having r8169 woes with XID 18000000
From: Timo Teräs @ 2010-06-04 20:24 UTC (permalink / raw)
To: Phil Sutter; +Cc: françois romieu, netdev
In-Reply-To: <4C09387F.1050403@iki.fi>
On 06/04/2010 08:31 PM, Timo Teräs wrote:
> On 06/04/2010 04:43 PM, Phil Sutter wrote:
>> On Fri, Jun 04, 2010 at 04:02:11PM +0300, Timo Teräs wrote:
>>>> Comparing r8169-6.013 with it's predecessor 6.012, you'll find a newly
>>>> enabled function rtl8169_phy_power_up() as well as some more invocations
>>>> of rtl8169_phy_power_down().
>>>>
>>>> This is probably the solution to these (at least in our case) very
>>>> sporadic, but highly annoying, problems. In fact, when our NIC didn't
>>>> detect any link, it needed a full power-cycle (no success with
>>>> reset-button), so almost not workaroundable.
>>>
> However, removing the specific phy config code
> (rtl8169scd_hw_phy_config) which was introduced by commit 2e955856ff
> seems to solve it. At least I was not able to reproduce the failure with
> 20-30 module reloads.
Ok, I figured that either the data the phy config writes is bad, or mdio
io is failing, so I added some additional checks to mdio_write and
mdio_read. More loops (upto 2000 iterations) and debug print if it
ultimately failed. And it did!
At bootup I got this:
r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
r8169 0000:00:09.0: PCI->APIC IRQ transform: INT A -> IRQ 18
r8169 0000:00:09.0: no PCI Express capability
eth0: RTL8169sc/8110sc at 0xf835c000, 00:30:18:a6:2b:6c, XID 18000000 IRQ 18
r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
r8169 0000:00:0b.0: PCI->APIC IRQ transform: INT A -> IRQ 19
r8169 0000:00:0b.0: no PCI Express capability
eth1: RTL8169sc/8110sc at 0xf8360000, 00:30:18:a6:2b:6d, XID 18000000 IRQ 19
r8169 Gigabit Ethernet driver 2.3LK-NAPI loaded
r8169 0000:00:0c.0: PCI->APIC IRQ transform: INT A -> IRQ 16
r8169 0000:00:0c.0: no PCI Express capability
eth2: RTL8169sc/8110sc at 0xf8364000, 00:30:18:a6:2b:6e, XID 18000000 IRQ 16
r8169: mdio_write(f8364000, 0x00000003, 0000000a1) required 2000 cycles
r8169: mdio_write(f8364000, 0x00000000, 000001000) required 2000 cycles
r8169: mdio_write(f8364000, 0x00000000, 00000a0ff) required 2000 cycles
r8169: mdio_write(f8364000, 0x00000014, 00000fb54) required 2000 cycles
And eth2 was not working. Reloading the module gave a lot of other
mdio_write and mdio_read errors.
It seems to be pretty random when the errors occur, but that's the
reason why the NIC stops working: mdio_write() fails (one or more times)
at some crucial point of the board specific phy config code resulting in
bad state.
Any ideas how to debug this further?
I guess next step is to compile the Realtek driver and see if that works
right.
> One more curiosity: if i do a hard power reset, the NIC has green link
> indicator led after power up. When loading the kernel module it goes to
> orange/red. I wonder why the difference.
Figured this. At startup it goes to 100mbit/s fixed mode. After module
load it gets 1gb/s. Setting it manually to 100mbit/s changes the color
back to green. So it's just a speed indicator.
^ permalink raw reply
* RE: [PATCH V2 1/2] Export firmware assigned labels of network devices to sysfs
From: Narendra_K @ 2010-06-04 20:31 UTC (permalink / raw)
To: Narendra_K, greg; +Cc: netdev, linux-hotplug, linux-pci, Matt_Domsch
In-Reply-To: <20100603210715.GA18025@auslistsprd01.us.dell.com>
With regards,
Narendra K
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of Narendra K
> Sent: Friday, June 04, 2010 2:37 AM
> To: greg@kroah.com
> Cc: netdev@vger.kernel.org; linux-hotplug@vger.kernel.org; linux-
> pci@vger.kernel.org; Domsch, Matt
> Subject: Re: [PATCH V2 1/2] Export firmware assigned labels of network
> devices to sysfs
>
> > -----Original Message-----
> > From: Greg KH [mailto:greg@kroah.com]
> > Sent: Friday, May 28, 2010 9:11 PM
> > To: K, Narendra
> > Cc: netdev@vger.kernel.org; linux-hotplug@vger.kernel.org;
> > linux-pci@vger.kernel.org; Domsch, Matt; Hargrave, Jordan; Rose,
> > Charles; Nijhawan, Vijay
> > Subject: Re: [PATCH 1/2] Export firmware assigned labels of network
> > devices to sysfs
> >
> Thanks for the comments.
>
> > On Fri, May 28, 2010 at 06:55:21AM -0500, K, Narendra wrote:
> > > Please refer to the PCI-SIG Draft ECN
> > > "PCIe Device Labeling under Operating Systems Draft ECN" at this
> link
> > -
> > > http://www.pcisig.com/specifications/pciexpress/review_zone/.
> > >
> > > It would be great to know your views on this ECN. Please let us
> know
> > if you have
> > > have any suggestions or changes.
> >
> > Note that only members of the PCI-SIG can do this, which pretty much
> > rules out any "normal" Linux kernel developer :(
> >
> > Care to post a public version of this for us to review?
> > > --- /dev/null
> > > +++ b/drivers/pci/pci-label.c
> > > @@ -0,0 +1,242 @@
> > > +/*
> > > + * File: drivers/pci/pci-label.c
> >
> > This line is not needed, we know the file name :)
> >
> > > + * Purpose: Export the firmware label associated with a pci
> > network interface
> > > + * device to sysfs
> > > + * Copyright (C) 2010 Dell Inc.
> > > + * by Narendra K <Narendra_K@dell.com>, Jordan Hargrave
> > <Jordan_Hargrave@dell.com>
> > > + *
> > > + * This code checks if the pci network device has a related ACPI
> > _DSM. If
> > > + * available, the code calls the _DSM to retrieve the index and
> > string and
> > > + * exports them to sysfs. If the ACPI _DSM is not available, it
> falls
> > back on
> > > + * SMBIOS. SMBIOS defines type 41 for onboard pci devices. This
> code
> > retrieves
> > > + * strings associated with the type 41 and exports it to sysfs.
> > > + *
> > > + * Please see
> http://linux.dell.com/wiki/index.php/Oss/libnetdevname
> > for more
> > > + * information.
> > > + */
> > > +
> > > +#include <linux/pci-label.h>
> >
> > Why is this file in include/linux/ ? Who needs it there? Can't it
> just
> > be in in the drivers/pci/ directory? Actually all you need is 2
> > functions in there, so it could go into the internal pci.h file in
> that
> > directory without a problem, right?
> >
>
> This file is removed and functions are moved to the internal pci.h
>
> > > +
> > > +static ssize_t
> > > +smbiosname_string_exists(struct device *dev, char *buf)
> > > +{
> > > + struct pci_dev *pdev = to_pci_dev(dev);
> > > + const struct dmi_device *dmi;
> > > + struct dmi_devslot *dslot;
> > > + int bus;
> > > + int devfn;
> > > +
> > > + bus = pdev->bus->number;
> > > + devfn = pdev->devfn;
> > > +
> > > + dmi = NULL;
> > > + while ((dmi = dmi_find_device(DMI_DEV_TYPE_DEVSLOT, NULL,
> > dmi)) != NULL) {
> > > + dslot = dmi->device_data;
> > > + if (dslot && dslot->bus == bus && dslot->devfn ==
> > devfn) {
> > > + if (buf)
> > > + return scnprintf(buf, PAGE_SIZE,
> > "%s\n", dmi->name);
> > > + return strlen(dmi->name);
> > > + }
> > > + }
> > > +
> > > + return 0;
> > > +}
> > > +
> > > +static ssize_t
> > > +smbiosname_show(struct device *dev, struct device_attribute *attr,
> > char *buf)
> > > +{
> > > + return smbiosname_string_exists(dev, buf);
> > > +}
> > > +
> > > +struct smbios_attribute smbios_attr_label = {
> > > + .attr = {.name = __stringify(label), .mode = 0444, .owner =
> > THIS_MODULE},
> >
> > Can't you just put "label" as the name?
> >
>
> This is fixed.
>
> > > + .show = smbiosname_show,
> > > + .test = smbiosname_string_exists,
> > > +};
> > > +
> > > +static int
> > > +pci_create_smbiosname_file(struct pci_dev *pdev)
> > > +{
> > > + if (smbios_attr_label.test &&
> > smbios_attr_label.test(&pdev->dev, NULL)) {
> > > + sysfs_create_file(&pdev->dev.kobj,
> > &smbios_attr_label.attr);
> > > + return 0;
> > > + }
> > > + return -1;
> > > +}
> > > +
> > > +static int
> > > +pci_remove_smbiosname_file(struct pci_dev *pdev)
> > > +{
> > > + if (smbios_attr_label.test &&
> > smbios_attr_label.test(&pdev->dev, NULL)) {
> > > + sysfs_remove_file(&pdev->dev.kobj,
> > &smbios_attr_label.attr);
> > > + return 0;
> > > + }
> > > + return -1;
> > > +}
> > > +
> > > +static const char dell_dsm_uuid[] = {
> >
> > Um, a dell specific uuid in a generic file? What happens when we
> need
> > to support another manufacturer?
> >
>
> My understanding of uuid was incorrect. I have renamed it to a more
> generic
> device_label_dsm_uuid and ACPI_DSM_FUNCTION to DEVICE_LABEL_DSM
>
> > > + 0xD0, 0x37, 0xC9, 0xE5, 0x53, 0x35, 0x7A, 0x4D,
> > > + 0x91, 0x17, 0xEA, 0x4D, 0x19, 0xC3, 0x43, 0x4D
> > > +};
> > > +
> > > +
> > > +static int
> > > +dsm_get_label(acpi_handle handle, int func,
> > > + struct acpi_buffer *output,
> > > + char *buf, char *attribute)
> > > +{
> > > + struct acpi_object_list input;
> > > + union acpi_object params[4];
> > > + union acpi_object *obj;
> > > + int len = 0;
> > > +
> > > + int err;
> > > +
> > > + input.count = 4;
> > > + input.pointer = params;
> > > + params[0].type = ACPI_TYPE_BUFFER;
> > > + params[0].buffer.length = sizeof(dell_dsm_uuid);
> > > + params[0].buffer.pointer = (char *)dell_dsm_uuid;
> > > + params[1].type = ACPI_TYPE_INTEGER;
> > > + params[1].integer.value = 0x02;
> > > + params[2].type = ACPI_TYPE_INTEGER;
> > > + params[2].integer.value = func;
> > > + params[3].type = ACPI_TYPE_PACKAGE;
> > > + params[3].package.count = 0;
> > > + params[3].package.elements = NULL;
> > > +
> > > + err = acpi_evaluate_object(handle, "_DSM", &input, output);
> > > + if (err) {
> > > + printk(KERN_INFO "failed to evaulate _DSM\n");
> > > + return -1;
> > > + }
> > > +
> > > + obj = (union acpi_object *)output->pointer;
> > > +
> > > + switch (obj->type) {
> > > + case ACPI_TYPE_PACKAGE:
> > > + if (obj->package.count == 2) {
> > > + len = obj-
> >package.elements[0].integer.value;
> > > + if (buf) {
> > > + if (!strncmp(attribute, "index",
> > strlen(attribute)))
> > > + scnprintf(buf, PAGE_SIZE,
> > "%lu\n",
> > > +
> > obj->package.elements[0].integer.value);
> > > + else
> > > + scnprintf(buf, PAGE_SIZE,
> > "%s\n",
> > > +
> > obj->package.elements[1].string.pointer);
> > > + kfree(output->pointer);
> > > + return strlen(buf);
> > > + }
> > > + }
> > > + kfree(output->pointer);
> > > + return len;
> > > + break;
> > > + default:
> > > + return -1;
> > > + }
> > > +}
> > > +
> > > +static ssize_t
> > > +acpi_index_string_exist(struct device *dev, char *buf, char
> > *attribute)
> > > +{
> > > + struct pci_dev *pdev = to_pci_dev(dev);
> > > +
> > > + struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
> > > + acpi_handle handle;
> > > + int length;
> > > + int is_addin_card = 0;
> > > +
> > > + if ((pdev->class >> 16) != PCI_BASE_CLASS_NETWORK)
> > > + return -1;
> > > +
> > > + handle = DEVICE_ACPI_HANDLE(dev);
> > > +
> > > + if (!handle) {
> > > + /*
> > > + * The device is an add-in network controller and
> does
> > have
> > > + * a valid handle. Try until we get the handle for
> the
> > parent
> > > + * bridge
> > > + */
> > > + struct pci_bus *pbus;
> > > + for (pbus = pdev->bus; pbus; pbus = pbus->parent) {
> > > + handle =
> > DEVICE_ACPI_HANDLE(&(pbus->self->dev));
> > > + if (handle)
> > > + break;
> > > +
> > > + }
> > > + }
> > > +
> > > + if ((length = dsm_get_label(handle, DELL_DSM_NETWORK,
> > > + &output, buf, attribute)) < 0)
> > > + return -1;
> > > +
> > > + return length;
> > > +}
> > > +
> > > +static ssize_t
> > > +acpilabel_show(struct device *dev, struct device_attribute *attr,
> > char *buf)
> > > +{
> > > + return acpi_index_string_exist(dev, buf, "label");
> > > +}
> > > +
> > > +static ssize_t
> > > +acpiindex_show(struct device *dev, struct device_attribute *attr,
> > char *buf)
> > > +{
> > > + return acpi_index_string_exist(dev, buf, "index");
> > > +}
> > > +
> > > +struct acpi_attribute acpi_attr_label = {
> > > + .attr = {.name = __stringify(label), .mode = 0444, .owner =
> > THIS_MODULE},
> > > + .show = acpilabel_show,
> > > + .test = acpi_index_string_exist,
> > > +};
> > > +
> > > +struct acpi_attribute acpi_attr_index = {
> > > + .attr = {.name = __stringify(index), .mode = 0444, .owner =
> > THIS_MODULE},
> > > + .show = acpiindex_show,
> > > + .test = acpi_index_string_exist,
> > > +};
> > > +
> > > +static int
> > > +pci_create_acpi_index_label_files(struct pci_dev *pdev)
> > > +{
> > > + if (acpi_attr_label.test && acpi_attr_label.test(&pdev-
> >dev,
> > NULL) > 0) {
> > > + sysfs_create_file(&pdev->dev.kobj,
> > &acpi_attr_label.attr);
> > > + sysfs_create_file(&pdev->dev.kobj,
> > &acpi_attr_index.attr);
> > > + return 0;
> > > + }
> > > + return -1;
> > > +}
> > > +
> > > +static int
> > > +pci_remove_acpi_index_label_files(struct pci_dev *pdev)
> > > +{
> > > + if (acpi_attr_label.test && acpi_attr_label.test(&pdev-
> >dev,
> > NULL) > 0) {
> > > + sysfs_remove_file(&pdev->dev.kobj,
> > &acpi_attr_label.attr);
> > > + sysfs_remove_file(&pdev->dev.kobj,
> > &acpi_attr_index.attr);
> > > + return 0;
> > > + }
> > > + return -1;
> > > +}
> > > +
> > > +int pci_create_acpi_attr_files(struct pci_dev *pdev)
> > > +{
> > > + if (!pci_create_acpi_index_label_files(pdev))
> > > + return 0;
> > > + if (!pci_create_smbiosname_file(pdev))
> > > + return 0;
> > > + return -ENODEV;
> > > +}
> > > +EXPORT_SYMBOL(pci_create_acpi_attr_files);
> >
> > EXPORT_SYMBOL_GPL?
> >
> > Wait, why does this need to be exported at all? What module is ever
> > going to call this function?
> >
> > > +int pci_remove_acpi_attr_files(struct pci_dev *pdev)
> > > +{
> > > + if (!pci_remove_acpi_index_label_files(pdev))
> > > + return 0;
> > > + if (!pci_remove_smbiosname_file(pdev))
> > > + return 0;
> > > + return -ENODEV;
> > > +
> > > +}
> > > +EXPORT_SYMBOL(pci_remove_acpi_attr_files);
> >
> > Same here, what module will call this?
> >
>
> These functions need not be exported as they are not called by any
> module.
>
> > > +++ b/include/linux/pci-label.h
> >
> > As discussed above, this whole file does not need to exist.
> >
> > > +extern int pci_create_acpi_attr_files(struct pci_dev *pdev);
> > > +extern int pci_remove_acpi_attr_files(struct pci_dev *pdev);
> >
> > Just put these two functions in the drivers/pci/pci.h file.
> >
> Fixed.
>
> In addition to these changes there are a coulple of changes i have done
> -
>
> 1.Removed the check for network devices and evaulate _DSM for any pci
> device
> that has _DSM defined in adherence to the spec.
>
> 2.Renamed the functions pci_create,remove-acpi_attr_files to
> pci_create,remove_firmware_label_files.
>
> 3.Added checks for conditional compilation of if CONFIG_ACPI ||
> CONFIG_DMI
>
> Note: While testing the patch with CONFIG_ACPI set to no, the
> compilation
> would fail with the below message.
>
> CC drivers/pci/pci-label.o
> In file included from drivers/pci/pci-label.c:24:
> include/linux/pci-acpi.h:39: error: expected ‘=’, ‘,’, ‘;’, ‘asm’ or
> ‘__attribute__’
> before ‘acpi_find_root_bridge_handle’
>
> I had to add make this change to proceed with the compilation. It would
> be
> great to know if i am missing something in the way conditional
> compilation
> is implemented or is it a issue.
>
> ---
> include/linux/pci-acpi.h | 4 ++--
> 1 files changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
> index c8b6473..bc40827 100644
> --- a/include/linux/pci-acpi.h
> +++ b/include/linux/pci-acpi.h
> @@ -36,8 +36,8 @@ static inline acpi_handle
> acpi_pci_get_bridge_handle(struct pci_bus *pbus)
> pbus->number);
> }
> #else
> -static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev
> *pdev)
> -{ return NULL; }
> +static inline void acpi_find_root_bridge_handle(struct pci_dev *pdev)
> +{ }
> #endif
>
> #endif /* _PCI_ACPI_H_ */
>
>
> Please find the patch with above suggestions and changes -
>
>
> From: Narendra K <narendra_k@dell.com>
> Subject: [PATCH V2 1/2] Export firmware assigned labels of pci devices
> to sysfs
>
> This patch exports the firmware assigned labels of pci devices to
> sysfs which could be used by user space.
>
> Signed-off-by: Jordan Hargrave <jordan_hargrave@dell.com>
> Signed-off-by: Narendra K <narendra_k@dell.com>
> ---
> drivers/firmware/dmi_scan.c | 24 ++++
> drivers/pci/Makefile | 2 +-
> drivers/pci/pci-label.c | 273
> +++++++++++++++++++++++++++++++++++++++++++
> drivers/pci/pci-sysfs.c | 5 +
> drivers/pci/pci.h | 2 +
> include/linux/dmi.h | 9 ++
> 6 files changed, 314 insertions(+), 1 deletions(-)
> create mode 100644 drivers/pci/pci-label.c
>
> diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
> index d464672..7d8439b 100644
> --- a/drivers/firmware/dmi_scan.c
> +++ b/drivers/firmware/dmi_scan.c
> @@ -277,6 +277,28 @@ static void __init dmi_save_ipmi_device(const
> struct dmi_header *dm)
> list_add_tail(&dev->list, &dmi_devices);
> }
>
> +static void __init dmi_save_devslot(int id, int seg, int bus, int
> devfn, const char *name)
> +{
> + struct dmi_devslot *slot;
> +
> + slot = dmi_alloc(sizeof(*slot) + strlen(name) + 1);
> + if (!slot) {
> + printk(KERN_ERR "dmi_save_devslot: out of memory.\n");
> + return;
> + }
> + slot->id = id;
> + slot->seg = seg;
> + slot->bus = bus;
> + slot->devfn = devfn;
> +
> + strcpy((char *)&slot[1], name);
> + slot->dev.type = DMI_DEV_TYPE_DEVSLOT;
> + slot->dev.name = (char *)&slot[1];
> + slot->dev.device_data = slot;
> +
> + list_add(&slot->dev.list, &dmi_devices);
> +}
> +
> static void __init dmi_save_extended_devices(const struct dmi_header
> *dm)
> {
> const u8 *d = (u8*) dm + 5;
> @@ -285,6 +307,7 @@ static void __init dmi_save_extended_devices(const
> struct dmi_header *dm)
> if ((*d & 0x80) == 0)
> return;
>
> + dmi_save_devslot(-1, *(u16 *)(d+2), *(d+4), *(d+5),
> dmi_string_nosave(dm, *(d-1)));
> dmi_save_one_device(*d & 0x7f, dmi_string_nosave(dm, *(d - 1)));
> }
>
> @@ -333,6 +356,7 @@ static void __init dmi_decode(const struct
> dmi_header *dm, void *dummy)
> break;
> case 41: /* Onboard Devices Extended Information */
> dmi_save_extended_devices(dm);
> + break;
> }
> }
>
> diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
> index 0b51857..69c503a 100644
> --- a/drivers/pci/Makefile
> +++ b/drivers/pci/Makefile
> @@ -4,7 +4,7 @@
>
> obj-y += access.o bus.o probe.o remove.o pci.o \
> pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
> - irq.o vpd.o
> + irq.o vpd.o pci-label.o
> obj-$(CONFIG_PROC_FS) += proc.o
> obj-$(CONFIG_SYSFS) += slot.o
>
> diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
> new file mode 100644
> index 0000000..b35d48c
> --- /dev/null
> +++ b/drivers/pci/pci-label.c
> @@ -0,0 +1,273 @@
> +/*
> + * Purpose: Export the firmware label associated with a pci network
> interface
> + * device to sysfs
> + * Copyright (C) 2010 Dell Inc.
> + * by Narendra K <Narendra_K@dell.com>, Jordan Hargrave
> <Jordan_Hargrave@dell.com>
> + *
> + * This code checks if the pci network device has a related ACPI _DSM.
> If
> + * available, the code calls the _DSM to retrieve the index and string
> and
> + * exports them to sysfs. If the ACPI _DSM is not available, it falls
> back on
> + * SMBIOS. SMBIOS defines type 41 for onboard pci devices. This code
> retrieves
> + * strings associated with the type 41 and exports it to sysfs.
> + *
> + * Please see http://linux.dell.com/wiki/index.php/Oss/libnetdevname
> for more
> + * information.
> + */
> +
> +#include <linux/dmi.h>
> +#include <linux/sysfs.h>
> +#include <linux/pci.h>
> +#include <linux/pci_ids.h>
> +#include <linux/module.h>
> +#include <linux/acpi.h>
> +#include <linux/pci-acpi.h>
> +#include <acpi/acpi_drivers.h>
> +#include <acpi/acpi_bus.h>
> +#include "pci.h"
> +
> +#define DEVICE_LABEL_DSM 0x07
> +
> +#if defined CONFIG_DMI
> +
> +struct smbios_attribute {
> + struct attribute attr;
> + ssize_t (*show) (struct device *dev, char *buf);
> + ssize_t (*test) (struct device *dev, char *buf);
> +};
> +
> +static ssize_t
> +smbiosname_string_exists(struct device *dev, char *buf)
> +{
> + struct pci_dev *pdev = to_pci_dev(dev);
> + const struct dmi_device *dmi;
> + struct dmi_devslot *dslot;
> + int bus;
> + int devfn;
> +
> + bus = pdev->bus->number;
> + devfn = pdev->devfn;
> +
> + dmi = NULL;
> + while ((dmi = dmi_find_device(DMI_DEV_TYPE_DEVSLOT, NULL, dmi))
> != NULL) {
> + dslot = dmi->device_data;
> + if (dslot && dslot->bus == bus && dslot->devfn == devfn) {
> + if (buf)
> + return scnprintf(buf, PAGE_SIZE, "%s\n",
> dmi->name);
> + return strlen(dmi->name);
> + }
> + }
> +
> + return 0;
> +}
> +
> +static ssize_t
> +smbiosname_show(struct device *dev, struct device_attribute *attr,
> char *buf)
> +{
> + return smbiosname_string_exists(dev, buf);
> +}
> +
> +struct smbios_attribute smbios_attr_label = {
> + .attr = {.name = "label", .mode = 0444, .owner = THIS_MODULE},
> + .show = smbiosname_show,
> + .test = smbiosname_string_exists,
> +};
> +
> +static int
> +pci_create_smbiosname_file(struct pci_dev *pdev)
> +{
> + if (smbios_attr_label.test && smbios_attr_label.test(&pdev->dev,
> NULL)) {
> + sysfs_create_file(&pdev->dev.kobj,
> &smbios_attr_label.attr);
> + return 0;
> + }
> + return -1;
> +}
> +
> +static int
> +pci_remove_smbiosname_file(struct pci_dev *pdev)
> +{
> + if (smbios_attr_label.test && smbios_attr_label.test(&pdev->dev,
> NULL)) {
> + sysfs_remove_file(&pdev->dev.kobj,
> &smbios_attr_label.attr);
> + return 0;
> + }
> + return -1;
> +}
> +#else
> +static inline int
> +pci_create_smbiosname_file(struct pci_dev *pdev)
> +{
> + return -1;
> +}
> +
> +static inline int
> +pci_remove_smbiosname_file(struct pci_dev *pdev)
> +{
> + return -1;
> +}
> +#endif
> +
> +#if defined CONFIG_ACPI
> +
> +static const char device_label_dsm_uuid[] = {
> + 0xD0, 0x37, 0xC9, 0xE5, 0x53, 0x35, 0x7A, 0x4D,
> + 0x91, 0x17, 0xEA, 0x4D, 0x19, 0xC3, 0x43, 0x4D
> +};
> +
> +struct acpi_attribute {
> + struct attribute attr;
> + ssize_t (*show) (struct device *dev, char *buf);
> + ssize_t (*test) (struct device *dev, char *buf);
> +};
> +
> +static int
> +dsm_get_label(acpi_handle handle, int func,
> + struct acpi_buffer *output,
> + char *buf, char *attribute)
> +{
> + struct acpi_object_list input;
> + union acpi_object params[4];
> + union acpi_object *obj;
> + int len = 0;
> +
> + int err;
> +
> + input.count = 4;
> + input.pointer = params;
> + params[0].type = ACPI_TYPE_BUFFER;
> + params[0].buffer.length = sizeof(device_label_dsm_uuid);
> + params[0].buffer.pointer = (char *)device_label_dsm_uuid;
> + params[1].type = ACPI_TYPE_INTEGER;
> + params[1].integer.value = 0x02;
> + params[2].type = ACPI_TYPE_INTEGER;
> + params[2].integer.value = func;
> + params[3].type = ACPI_TYPE_PACKAGE;
> + params[3].package.count = 0;
> + params[3].package.elements = NULL;
> +
> + err = acpi_evaluate_object(handle, "_DSM", &input, output);
> + if (err)
> + return -1;
> +
> +
> + obj = (union acpi_object *)output->pointer;
> +
> + switch (obj->type) {
> + case ACPI_TYPE_PACKAGE:
> + if (obj->package.count != 2)
> + break;
> + len = obj->package.elements[0].integer.value;
> + if (buf) {
> + if (!strncmp(attribute, "index", strlen(attribute)))
> + scnprintf(buf, PAGE_SIZE, "%lu\n",
> + obj->package.elements[0].integer.value);
> + else
> + scnprintf(buf, PAGE_SIZE, "%s\n",
> + obj->package.elements[1].string.pointer);
> + kfree(output->pointer);
> + return strlen(buf);
> + }
> + kfree(output->pointer);
> + return len;
> + break;
> + default:
> + kfree(output->pointer);
> + return -1;
> + }
> +}
> +
> +static ssize_t
> +acpi_index_string_exist(struct device *dev, char *buf, char
> *attribute)
> +{
> + struct pci_dev *pdev = to_pci_dev(dev);
> +
> + struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
> + acpi_handle handle;
> + int length;
> +
> + handle = DEVICE_ACPI_HANDLE(dev);
> +
> + if (!handle)
> + return -1;
> +
> + if ((length = dsm_get_label(handle, DEVICE_LABEL_DSM,
> + &output, buf, attribute)) < 0)
> + return -1;
> +
> + return length;
> +}
> +
> +static ssize_t
> +acpilabel_show(struct device *dev, struct device_attribute *attr, char
> *buf)
> +{
> + return acpi_index_string_exist(dev, buf, "label");
> +}
> +
> +static ssize_t
> +acpiindex_show(struct device *dev, struct device_attribute *attr, char
> *buf)
> +{
> + return acpi_index_string_exist(dev, buf, "index");
> +}
> +
> +struct acpi_attribute acpi_attr_label = {
> + .attr = {.name = "label", .mode = 0444, .owner = THIS_MODULE},
> + .show = acpilabel_show,
> + .test = acpi_index_string_exist,
> +};
> +
> +struct acpi_attribute acpi_attr_index = {
> + .attr = {.name = "index", .mode = 0444, .owner = THIS_MODULE},
> + .show = acpiindex_show,
> + .test = acpi_index_string_exist,
> +};
> +
> +static int
> +pci_create_acpi_index_label_files(struct pci_dev *pdev)
> +{
> + if (acpi_attr_label.test && acpi_attr_label.test(&pdev->dev,
> NULL) > 0) {
> + sysfs_create_file(&pdev->dev.kobj, &acpi_attr_label.attr);
> + sysfs_create_file(&pdev->dev.kobj, &acpi_attr_index.attr);
> + return 0;
> + }
> + return -1;
> +}
> +
> +static int
> +pci_remove_acpi_index_label_files(struct pci_dev *pdev)
> +{
> + if (acpi_attr_label.test && acpi_attr_label.test(&pdev->dev,
> NULL) > 0) {
> + sysfs_remove_file(&pdev->dev.kobj, &acpi_attr_label.attr);
> + sysfs_remove_file(&pdev->dev.kobj, &acpi_attr_index.attr);
> + return 0;
> + }
> + return -1;
> +}
> +#else
> +static inline int
> +pci_create_acpi_index_label_files(struct pci_dev *pdev)
> +{
> + return -1;
> +}
> +
> +static inline int
> +pci_remove_acpi_index_label_files(struct pci_dev *pdev)
> +{
> + return -1;
> +}
> +#endif
> +
> +int pci_create_firmware_label_files(struct pci_dev *pdev)
> +{
> + if (!pci_create_acpi_index_label_files(pdev))
> + return 0;
> + if (!pci_create_smbiosname_file(pdev))
> + return 0;
> + return -ENODEV;
> +}
> +
> +int pci_remove_firmware_label_files(struct pci_dev *pdev)
> +{
> + if (!pci_remove_acpi_index_label_files(pdev))
> + return 0;
> + if (!pci_remove_smbiosname_file(pdev))
> + return 0;
> + return -ENODEV;
> +}
> diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
> index fad9398..4ed517f 100644
> --- a/drivers/pci/pci-sysfs.c
> +++ b/drivers/pci/pci-sysfs.c
> @@ -1073,6 +1073,8 @@ int __must_check pci_create_sysfs_dev_files
> (struct pci_dev *pdev)
> if (retval)
> goto err_vga_file;
>
> + pci_create_firmware_label_files(pdev);
> +
> return 0;
>
> err_vga_file:
> @@ -1140,6 +1142,9 @@ void pci_remove_sysfs_dev_files(struct pci_dev
> *pdev)
> sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
> kfree(pdev->rom_attr);
> }
> +
> + pci_remove_firmware_label_files(pdev);
> +
> }
>
> static int __init pci_sysfs_init(void)
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index 4eb10f4..f223283 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -11,6 +11,8 @@
> extern int pci_uevent(struct device *dev, struct kobj_uevent_env
> *env);
> extern int pci_create_sysfs_dev_files(struct pci_dev *pdev);
> extern void pci_remove_sysfs_dev_files(struct pci_dev *pdev);
> +extern int pci_create_firmware_label_files(struct pci_dev *pdev);
> +extern int pci_remove_firmware_label_files(struct pci_dev *pdev);
> extern void pci_cleanup_rom(struct pci_dev *dev);
> #ifdef HAVE_PCI_MMAP
> extern int pci_mmap_fits(struct pci_dev *pdev, int resno,
> diff --git a/include/linux/dmi.h b/include/linux/dmi.h
> index a8a3e1a..cc57c3a 100644
> --- a/include/linux/dmi.h
> +++ b/include/linux/dmi.h
> @@ -20,6 +20,7 @@ enum dmi_device_type {
> DMI_DEV_TYPE_SAS,
> DMI_DEV_TYPE_IPMI = -1,
> DMI_DEV_TYPE_OEM_STRING = -2,
> + DMI_DEV_TYPE_DEVSLOT = -3,
> };
>
> struct dmi_header {
> @@ -37,6 +38,14 @@ struct dmi_device {
>
> #ifdef CONFIG_DMI
>
> +struct dmi_devslot {
> + struct dmi_device dev;
> + int id;
> + int seg;
> + int bus;
> + int devfn;
> +};
> +
> extern int dmi_check_system(const struct dmi_system_id *list);
> const struct dmi_system_id *dmi_first_match(const struct dmi_system_id
> *list);
> extern const char * dmi_get_system_info(int field);
> --
> 1.6.5.2
>
> With regards,
> Narendra K
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 1/2] net: Enable 64-bit net device statistics on 32-bit architectures
From: Stephen Hemminger @ 2010-06-04 20:39 UTC (permalink / raw)
To: Ben Hutchings; +Cc: David Miller, Arnd Bergmann, netdev, linux-net-drivers
In-Reply-To: <1275675318.2095.30.camel@achroite.uk.solarflarecom.com>
On Fri, 04 Jun 2010 19:15:18 +0100
Ben Hutchings <bhutchings@solarflare.com> wrote:
> On Fri, 2010-06-04 at 10:28 -0700, Stephen Hemminger wrote:
> > On Thu, 03 Jun 2010 20:11:38 +0100
> > Ben Hutchings <bhutchings@solarflare.com> wrote:
> >
> > > static inline u64 rtnl_link_stats64_read(const u64 *field)
> > > {
> > > return ACCESS_ONCE(*field);
> > > }
> > > static inline u32 rtnl_link_stats64_read32(const u64 *field)
> > > {
> > > return ACCESS_ONCE(*field);
> > > }
> >
> > Do we really care if compiler reorders access. I think not.
> > There was no order guarantee in the past.
>
> Since these reads are potentially racing with writes, we want to ensure
> that they are atomic. Without the volatile-qualification, the compiler
> can legitimately split or repeat the reads, though I don't see any
> particular reason why this is a likely optimisation.
>
> Ben.
>
But this part of the code is only being run on on 64 bit machines.
Updates of basic types for the CPU are atomic, lots of other code
already assumes this.
Take off your tin hat, this is excessive paranoia.
--
^ permalink raw reply
* Re: [PATCH 1/2] net: Enable 64-bit net device statistics on 32-bit architectures
From: Ben Hutchings @ 2010-06-04 20:47 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: David Miller, Arnd Bergmann, netdev, linux-net-drivers
In-Reply-To: <20100604133930.34e2d53b@nehalam>
On Fri, 2010-06-04 at 13:39 -0700, Stephen Hemminger wrote:
> On Fri, 04 Jun 2010 19:15:18 +0100
> Ben Hutchings <bhutchings@solarflare.com> wrote:
>
> > On Fri, 2010-06-04 at 10:28 -0700, Stephen Hemminger wrote:
> > > On Thu, 03 Jun 2010 20:11:38 +0100
> > > Ben Hutchings <bhutchings@solarflare.com> wrote:
> > >
> > > > static inline u64 rtnl_link_stats64_read(const u64 *field)
> > > > {
> > > > return ACCESS_ONCE(*field);
> > > > }
> > > > static inline u32 rtnl_link_stats64_read32(const u64 *field)
> > > > {
> > > > return ACCESS_ONCE(*field);
> > > > }
> > >
> > > Do we really care if compiler reorders access. I think not.
> > > There was no order guarantee in the past.
> >
> > Since these reads are potentially racing with writes, we want to ensure
> > that they are atomic. Without the volatile-qualification, the compiler
> > can legitimately split or repeat the reads, though I don't see any
> > particular reason why this is a likely optimisation.
> >
> > Ben.
> >
>
> But this part of the code is only being run on on 64 bit machines.
> Updates of basic types for the CPU are atomic, lots of other code
> already assumes this.
> Take off your tin hat, this is excessive paranoia.
I like my tin hat, I'm sure I saw more oopses before I put it on. ;-)
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: [PATCH V2 1/2] Export firmware assigned labels of network devices to sysfs
From: Greg KH @ 2010-06-04 20:49 UTC (permalink / raw)
To: Narendra_K; +Cc: netdev, linux-hotplug, linux-pci, Matt_Domsch
In-Reply-To: <EDA0A4495861324DA2618B4C45DCB3EE612913@blrx3m08.blr.amer.dell.com>
On Sat, Jun 05, 2010 at 02:01:35AM +0530, Narendra_K@Dell.com wrote:
>
>
> With regards,
Um, what?
Why are you resending this over and over with no additional content
added?
If you have a new patch, send it. Don't bury it at the bottom of
another message, and then linewrap the thing...
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH 2/2] pktgen: receive packets and process incoming rate
From: Eric Dumazet @ 2010-06-02 13:00 UTC (permalink / raw)
To: Daniel Turull; +Cc: netdev, robert, jens.laas
In-Reply-To: <4C06453B.1080801@gmail.com>
Le mercredi 02 juin 2010 à 13:49 +0200, Daniel Turull a écrit :
> This patch adds receiver part to pktgen taking advantages of SMP systems
> with multiple rx queues:
> - Creation of new proc file /proc/net/pktgen/pgrx to control and display the receiver.
> - It uses PER-CPU variable to store the results per each CPU.
> - Results displayed per CPU and aggregated.
> - The packet handler is add in the protocols handlers (dev_Add_pack())
> - Available statistics: packets and bytes received, work time and rate
> - Only process pktgen packets
> - It is possible to select the incoming interface
> - Documentation updated with the new commands to control the receiver part.
>
Interesting, but does it belongs to pktgen ?
other comments included :)
> Signed-off-by: Daniel Turull <daniel.turull@gmail.com>
>
>
> +/*Recevier parameters per cpu*/
> +struct pktgen_rx {
> + u64 rx_packets; /*packets arrived*/
unsigned long rx_packets ?
> + u64 rx_bytes; /*bytes arrived*/
> +
> + ktime_t start_time; /*first time stamp of a packet*/
> + ktime_t last_time; /*last packet arrival */
> +};
> +int pktgen_rcv_basic(struct sk_buff *skb, struct net_device *dev,
> + struct packet_type *pt, struct net_device *orig_dev)
> +{
> + /* Check magic*/
> + struct iphdr *iph = ip_hdr(skb);
> + struct pktgen_hdr *pgh;
> + void *vaddr;
Following code is ... well ... interesting... But ...
1) Is it IPV6 compatable ? pktgen can be ipv6 or ipv4
2) Is it resistant to malicious packets ? (very small ones)
3) No checksum ?
I think you should use standard mechanisms... (pskb_may_pull(), ...)
Take a look at __netpoll_rx() for an example.
> + if (skb_is_nonlinear(skb)) {
> + vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[0]);
> + pgh = (struct pktgen_hdr *)
> + (vaddr+skb_shinfo(skb)->frags[0].page_offset);
> + } else {
> + pgh = (struct pktgen_hdr *)(((char *)(iph)) + 28);
> + }
> +
> + if (unlikely(pgh->pgh_magic != PKTGEN_MAGIC_NET))
> + goto end;
> +
> + if (unlikely(!__get_cpu_var(pktgen_rx_data).rx_packets))
> + __get_cpu_var(pktgen_rx_data).start_time = ktime_now();
> +
> + __get_cpu_var(pktgen_rx_data).last_time = ktime_now();
> +
Its a bit suboptimal to use __get_cpu_var several time. Take a look at
disassembly code :)
Use a pointer instead
> + /* Update counter of packets*/
> + __get_cpu_var(pktgen_rx_data).rx_packets++;
> + __get_cpu_var(pktgen_rx_data).rx_bytes += skb->len+14;
This +14 seems suspect (what about vlan tags ?)
Use ETH_HLEN instead at a very minimum?
> +end:
> + if (skb_is_nonlinear(skb))
> + kunmap_skb_frag(vaddr);
Should not recognised packets be allowed to flight in other parts of
kernel stack ? This way, we could use ssh to remotely control this
pktgen session ;)
> + kfree_skb(skb);
> + return 0;
> +}
> +
^ permalink raw reply
* Re: [PATCH V2 1/2] Export firmware assigned labels of network devices to sysfs
From: Greg KH @ 2010-06-04 21:01 UTC (permalink / raw)
To: Narendra_K; +Cc: netdev, linux-hotplug, linux-pci, Matt_Domsch
In-Reply-To: <20100604204955.GA20329@kroah.com>
On Fri, Jun 04, 2010 at 01:49:55PM -0700, Greg KH wrote:
> On Sat, Jun 05, 2010 at 02:01:35AM +0530, Narendra_K@Dell.com wrote:
> >
> >
> > With regards,
>
> Um, what?
>
> Why are you resending this over and over with no additional content
> added?
And you have an out-of-office autoreply.
I give up...
^ permalink raw reply
* Re: [PATCH V3 1/2] Export firmware assigned labels of network devices to sysfs
From: Narendra K @ 2010-06-04 21:07 UTC (permalink / raw)
To: greg
Cc: netdev, linux-hotplug, linux-pci, matt_domsch, jordan_hargrave,
charles_rose
In-Reply-To: <EDA0A4495861324DA2618B4C45DCB3EE612918@blrx3m08.blr.amer.dell.com>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-owner@vger.kernel.org] On Behalf Of Narendra K
> Sent: Friday, June 04, 2010 2:37 AM
> To: greg@kroah.com
> Cc: netdev@vger.kernel.org; linux-hotplug@vger.kernel.org; linux-pci@vger.kernel.org; Domsch, Matt
> Subject: Re: [PATCH V2 1/2] Export firmware assigned labels of network devices to sysfs
>
> In addition to these changes there are a coulple of changes i have done -
>
> 1.Removed the check for network devices and evaulate _DSM for any pci device
> that has _DSM defined in adherence to the spec.
>
> 2.Renamed the functions pci_create,remove-acpi_attr_files to
> pci_create,remove_firmware_label_files.
>
> 3.Added checks for conditional compilation of if CONFIG_ACPI || CONFIG_DMI
>
V2 -> V3: I had missed fixing warnings in the patch. Please find the V3
of the patch with the warnings fixed -
From: Narendra K <narendra_k@dell.com>
Subject: [PATCH V3 1/2] Export firmware assigned labels of pci devices to sysfs
This patch exports the firmware assigned labels of pci devices to
sysfs which could be used by user space.
Signed-off-by: Jordan Hargrave <jordan_hargrave@dell.com>
Signed-off-by: Narendra K <narendra_k@dell.com>
---
drivers/firmware/dmi_scan.c | 24 ++++
drivers/pci/Makefile | 2 +-
drivers/pci/pci-label.c | 274 +++++++++++++++++++++++++++++++++++++++++++
drivers/pci/pci-sysfs.c | 5 +
drivers/pci/pci.h | 2 +
include/linux/dmi.h | 9 ++
6 files changed, 315 insertions(+), 1 deletions(-)
create mode 100644 drivers/pci/pci-label.c
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index d464672..7d8439b 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -277,6 +277,28 @@ static void __init dmi_save_ipmi_device(const struct dmi_header *dm)
list_add_tail(&dev->list, &dmi_devices);
}
+static void __init dmi_save_devslot(int id, int seg, int bus, int devfn, const char *name)
+{
+ struct dmi_devslot *slot;
+
+ slot = dmi_alloc(sizeof(*slot) + strlen(name) + 1);
+ if (!slot) {
+ printk(KERN_ERR "dmi_save_devslot: out of memory.\n");
+ return;
+ }
+ slot->id = id;
+ slot->seg = seg;
+ slot->bus = bus;
+ slot->devfn = devfn;
+
+ strcpy((char *)&slot[1], name);
+ slot->dev.type = DMI_DEV_TYPE_DEVSLOT;
+ slot->dev.name = (char *)&slot[1];
+ slot->dev.device_data = slot;
+
+ list_add(&slot->dev.list, &dmi_devices);
+}
+
static void __init dmi_save_extended_devices(const struct dmi_header *dm)
{
const u8 *d = (u8*) dm + 5;
@@ -285,6 +307,7 @@ static void __init dmi_save_extended_devices(const struct dmi_header *dm)
if ((*d & 0x80) == 0)
return;
+ dmi_save_devslot(-1, *(u16 *)(d+2), *(d+4), *(d+5), dmi_string_nosave(dm, *(d-1)));
dmi_save_one_device(*d & 0x7f, dmi_string_nosave(dm, *(d - 1)));
}
@@ -333,6 +356,7 @@ static void __init dmi_decode(const struct dmi_header *dm, void *dummy)
break;
case 41: /* Onboard Devices Extended Information */
dmi_save_extended_devices(dm);
+ break;
}
}
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 0b51857..69c503a 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -4,7 +4,7 @@
obj-y += access.o bus.o probe.o remove.o pci.o \
pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
- irq.o vpd.o
+ irq.o vpd.o pci-label.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_SYSFS) += slot.o
diff --git a/drivers/pci/pci-label.c b/drivers/pci/pci-label.c
new file mode 100644
index 0000000..d6e0e9b
--- /dev/null
+++ b/drivers/pci/pci-label.c
@@ -0,0 +1,274 @@
+/*
+ * Purpose: Export the firmware label associated with a pci network interface
+ * device to sysfs
+ * Copyright (C) 2010 Dell Inc.
+ * by Narendra K <Narendra_K@dell.com>, Jordan Hargrave <Jordan_Hargrave@dell.com>
+ *
+ * This code checks if the pci network device has a related ACPI _DSM. If
+ * available, the code calls the _DSM to retrieve the index and string and
+ * exports them to sysfs. If the ACPI _DSM is not available, it falls back on
+ * SMBIOS. SMBIOS defines type 41 for onboard pci devices. This code retrieves
+ * strings associated with the type 41 and exports it to sysfs.
+ *
+ * Please see http://linux.dell.com/wiki/index.php/Oss/libnetdevname for more
+ * information.
+ */
+
+#include <linux/dmi.h>
+#include <linux/sysfs.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/pci-acpi.h>
+#include <acpi/acpi_drivers.h>
+#include <acpi/acpi_bus.h>
+#include "pci.h"
+
+#define DEVICE_LABEL_DSM 0x07
+
+#if defined CONFIG_DMI
+
+struct smbios_attribute {
+ struct attribute attr;
+ ssize_t (*show) (struct device *dev, struct device_attribute *, char *buf);
+ ssize_t (*test) (struct device *dev, char *buf);
+};
+
+static ssize_t
+smbiosname_string_exists(struct device *dev, char *buf)
+{
+ struct pci_dev *pdev = to_pci_dev(dev);
+ const struct dmi_device *dmi;
+ struct dmi_devslot *dslot;
+ int bus;
+ int devfn;
+
+ bus = pdev->bus->number;
+ devfn = pdev->devfn;
+
+ dmi = NULL;
+ while ((dmi = dmi_find_device(DMI_DEV_TYPE_DEVSLOT, NULL, dmi)) != NULL) {
+ dslot = dmi->device_data;
+ if (dslot && dslot->bus == bus && dslot->devfn == devfn) {
+ if (buf)
+ return scnprintf(buf, PAGE_SIZE, "%s\n", dmi->name);
+ return strlen(dmi->name);
+ }
+ }
+
+ return 0;
+}
+
+static ssize_t
+smbiosname_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return smbiosname_string_exists(dev, buf);
+}
+
+struct smbios_attribute smbios_attr_label = {
+ .attr = {.name = "label", .mode = 0444, .owner = THIS_MODULE},
+ .show = smbiosname_show,
+ .test = smbiosname_string_exists,
+};
+
+static int
+pci_create_smbiosname_file(struct pci_dev *pdev)
+{
+ if (smbios_attr_label.test && smbios_attr_label.test(&pdev->dev, NULL)) {
+ if (sysfs_create_file(&pdev->dev.kobj, &smbios_attr_label.attr))
+ return -1;
+ return 0;
+ }
+ return -1;
+}
+
+static int
+pci_remove_smbiosname_file(struct pci_dev *pdev)
+{
+ if (smbios_attr_label.test && smbios_attr_label.test(&pdev->dev, NULL)) {
+ sysfs_remove_file(&pdev->dev.kobj, &smbios_attr_label.attr);
+ return 0;
+ }
+ return -1;
+}
+#else
+static inline int
+pci_create_smbiosname_file(struct pci_dev *pdev)
+{
+ return -1;
+}
+
+static inline int
+pci_remove_smbiosname_file(struct pci_dev *pdev)
+{
+ return -1;
+}
+#endif
+
+#if defined CONFIG_ACPI
+
+static const char device_label_dsm_uuid[] = {
+ 0xD0, 0x37, 0xC9, 0xE5, 0x53, 0x35, 0x7A, 0x4D,
+ 0x91, 0x17, 0xEA, 0x4D, 0x19, 0xC3, 0x43, 0x4D
+};
+
+struct acpi_attribute {
+ struct attribute attr;
+ ssize_t (*show) (struct device *dev, struct device_attribute *attr, char *buf);
+ ssize_t (*test) (struct device *dev, char *buf, char *attribute);
+};
+
+static int
+dsm_get_label(acpi_handle handle, int func,
+ struct acpi_buffer *output,
+ char *buf, char *attribute)
+{
+ struct acpi_object_list input;
+ union acpi_object params[4];
+ union acpi_object *obj;
+ int len = 0;
+
+ int err;
+
+ input.count = 4;
+ input.pointer = params;
+ params[0].type = ACPI_TYPE_BUFFER;
+ params[0].buffer.length = sizeof(device_label_dsm_uuid);
+ params[0].buffer.pointer = (char *)device_label_dsm_uuid;
+ params[1].type = ACPI_TYPE_INTEGER;
+ params[1].integer.value = 0x02;
+ params[2].type = ACPI_TYPE_INTEGER;
+ params[2].integer.value = func;
+ params[3].type = ACPI_TYPE_PACKAGE;
+ params[3].package.count = 0;
+ params[3].package.elements = NULL;
+
+ err = acpi_evaluate_object(handle, "_DSM", &input, output);
+ if (err)
+ return -1;
+
+
+ obj = (union acpi_object *)output->pointer;
+
+ switch (obj->type) {
+ case ACPI_TYPE_PACKAGE:
+ if (obj->package.count != 2)
+ break;
+ len = obj->package.elements[0].integer.value;
+ if (buf) {
+ if (!strncmp(attribute, "index", strlen(attribute)))
+ scnprintf(buf, PAGE_SIZE, "%llu\n",
+ obj->package.elements[0].integer.value);
+ else
+ scnprintf(buf, PAGE_SIZE, "%s\n",
+ obj->package.elements[1].string.pointer);
+ kfree(output->pointer);
+ return strlen(buf);
+ }
+ kfree(output->pointer);
+ return len;
+ break;
+ default:
+ kfree(output->pointer);
+ }
+ return -1;
+}
+
+static ssize_t
+acpi_index_string_exist(struct device *dev, char *buf, char *attribute)
+{
+ struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
+ acpi_handle handle;
+ int length;
+
+ handle = DEVICE_ACPI_HANDLE(dev);
+
+ if (!handle)
+ return -1;
+
+ if ((length = dsm_get_label(handle, DEVICE_LABEL_DSM,
+ &output, buf, attribute)) < 0)
+ return -1;
+
+ return length;
+}
+
+static ssize_t
+acpilabel_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return acpi_index_string_exist(dev, buf, "label");
+}
+
+static ssize_t
+acpiindex_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return acpi_index_string_exist(dev, buf, "index");
+}
+
+struct acpi_attribute acpi_attr_label = {
+ .attr = {.name = "label", .mode = 0444, .owner = THIS_MODULE},
+ .show = acpilabel_show,
+ .test = acpi_index_string_exist,
+};
+
+struct acpi_attribute acpi_attr_index = {
+ .attr = {.name = "index", .mode = 0444, .owner = THIS_MODULE},
+ .show = acpiindex_show,
+ .test = acpi_index_string_exist,
+};
+
+static int
+pci_create_acpi_index_label_files(struct pci_dev *pdev)
+{
+ if (acpi_attr_label.test && acpi_attr_label.test(&pdev->dev, NULL, NULL) > 0) {
+ if (sysfs_create_file(&pdev->dev.kobj, &acpi_attr_label.attr))
+ return -1;
+ if (sysfs_create_file(&pdev->dev.kobj, &acpi_attr_index.attr))
+ return -1;
+ return 0;
+ }
+ return -1;
+}
+
+static int
+pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+{
+ if (acpi_attr_label.test && acpi_attr_label.test(&pdev->dev, NULL, NULL) > 0) {
+ sysfs_remove_file(&pdev->dev.kobj, &acpi_attr_label.attr);
+ sysfs_remove_file(&pdev->dev.kobj, &acpi_attr_index.attr);
+ return 0;
+ }
+ return -1;
+}
+#else
+static inline int
+pci_create_acpi_index_label_files(struct pci_dev *pdev)
+{
+ return -1;
+}
+
+static inline int
+pci_remove_acpi_index_label_files(struct pci_dev *pdev)
+{
+ return -1;
+}
+#endif
+
+int pci_create_firmware_label_files(struct pci_dev *pdev)
+{
+ if (!pci_create_acpi_index_label_files(pdev))
+ return 0;
+ if (!pci_create_smbiosname_file(pdev))
+ return 0;
+ return -ENODEV;
+}
+
+int pci_remove_firmware_label_files(struct pci_dev *pdev)
+{
+ if (!pci_remove_acpi_index_label_files(pdev))
+ return 0;
+ if (!pci_remove_smbiosname_file(pdev))
+ return 0;
+ return -ENODEV;
+}
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index fad9398..4ed517f 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1073,6 +1073,8 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev)
if (retval)
goto err_vga_file;
+ pci_create_firmware_label_files(pdev);
+
return 0;
err_vga_file:
@@ -1140,6 +1142,9 @@ void pci_remove_sysfs_dev_files(struct pci_dev *pdev)
sysfs_remove_bin_file(&pdev->dev.kobj, pdev->rom_attr);
kfree(pdev->rom_attr);
}
+
+ pci_remove_firmware_label_files(pdev);
+
}
static int __init pci_sysfs_init(void)
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4eb10f4..f223283 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -11,6 +11,8 @@
extern int pci_uevent(struct device *dev, struct kobj_uevent_env *env);
extern int pci_create_sysfs_dev_files(struct pci_dev *pdev);
extern void pci_remove_sysfs_dev_files(struct pci_dev *pdev);
+extern int pci_create_firmware_label_files(struct pci_dev *pdev);
+extern int pci_remove_firmware_label_files(struct pci_dev *pdev);
extern void pci_cleanup_rom(struct pci_dev *dev);
#ifdef HAVE_PCI_MMAP
extern int pci_mmap_fits(struct pci_dev *pdev, int resno,
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index a8a3e1a..cc57c3a 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -20,6 +20,7 @@ enum dmi_device_type {
DMI_DEV_TYPE_SAS,
DMI_DEV_TYPE_IPMI = -1,
DMI_DEV_TYPE_OEM_STRING = -2,
+ DMI_DEV_TYPE_DEVSLOT = -3,
};
struct dmi_header {
@@ -37,6 +38,14 @@ struct dmi_device {
#ifdef CONFIG_DMI
+struct dmi_devslot {
+ struct dmi_device dev;
+ int id;
+ int seg;
+ int bus;
+ int devfn;
+};
+
extern int dmi_check_system(const struct dmi_system_id *list);
const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list);
extern const char * dmi_get_system_info(int field);
--
1.6.5.2
With regards,
Narendra K
^ permalink raw reply related
* RE: [PATCH V2 1/2] Export firmware assigned labels of network devices to sysfs
From: Narendra_K @ 2010-06-04 21:15 UTC (permalink / raw)
To: greg; +Cc: netdev, linux-hotplug, linux-pci, Matt_Domsch
In-Reply-To: <20100604204955.GA20329@kroah.com>
>
> Um, what?
>
> Why are you resending this over and over with no additional content
> added?
>
> If you have a new patch, send it. Don't bury it at the bottom of
> another message, and then linewrap the thing...
>
Greg, Sorry for the inconvenience caused. I have sent the V3 patch with
changes mentioned.
With regards,
Narendra K
^ permalink raw reply
* Ethernet drivers wiki page
From: Luis R. Rodriguez @ 2010-06-04 21:52 UTC (permalink / raw)
To: netdev; +Cc: H. Peter Anvin, Stephen Hemminger, Johannes Berg
Where can I start adding documentation for our Ethernet drivers
upstream? I was hoping for a wiki but I don't think we have a netdev
one yet. Shall we create one or piggy back on something else? I'm
reviewing:
https://wiki.kernel.org/
FWIW, I want to see something like this:
http://wireless.kernel.org/en/users/Drivers
But for ethernet.
Luis
^ permalink raw reply
* Re: Ethernet drivers wiki page
From: Ben Hutchings @ 2010-06-04 22:01 UTC (permalink / raw)
To: Luis R. Rodriguez
Cc: netdev, H. Peter Anvin, Stephen Hemminger, Johannes Berg
In-Reply-To: <AANLkTinSjJsqNvEhJZIE6cJxEkBtg-DO2dqZWMczUy2i@mail.gmail.com>
On Fri, 2010-06-04 at 14:52 -0700, Luis R. Rodriguez wrote:
> Where can I start adding documentation for our Ethernet drivers
> upstream? I was hoping for a wiki but I don't think we have a netdev
> one yet. Shall we create one or piggy back on something else? I'm
> reviewing:
>
> https://wiki.kernel.org/
>
> FWIW, I want to see something like this:
>
> http://wireless.kernel.org/en/users/Drivers
>
> But for ethernet.
Wherever you put it, it should probably be linked from:
http://www.linuxfoundation.org/collaborate/workgroups/networking/
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* Re: Ethernet drivers wiki page
From: Luis R. Rodriguez @ 2010-06-04 22:04 UTC (permalink / raw)
To: netdev; +Cc: H. Peter Anvin, Stephen Hemminger, Johannes Berg, linux-kernel
In-Reply-To: <AANLkTinSjJsqNvEhJZIE6cJxEkBtg-DO2dqZWMczUy2i@mail.gmail.com>
On Fri, Jun 4, 2010 at 2:52 PM, Luis R. Rodriguez <mcgrof@gmail.com> wrote:
> Where can I start adding documentation for our Ethernet drivers
> upstream? I was hoping for a wiki but I don't think we have a netdev
> one yet. Shall we create one or piggy back on something else? I'm
> reviewing:
>
> https://wiki.kernel.org/
>
> FWIW, I want to see something like this:
>
> http://wireless.kernel.org/en/users/Drivers
>
> But for ethernet.
Since I've stuffed a few ethernet drivers on compat-wireless I might
as well start carrying more. So now we'd have 802.11, Bluetooth and
Ethernet all backported using the same framework, automatically, down
to at least the oldest stable kernel supported listed on kernel.org
and using all a generic compat module.
I want to document all this crap.
Luis
^ permalink raw reply
* [PATCHv2 1/2] net: Enable 64-bit net device statistics on 32-bit architectures
From: Ben Hutchings @ 2010-06-04 22:04 UTC (permalink / raw)
To: David Miller; +Cc: Stephen Hemminger, Arnd Bergmann, netdev, linux-net-drivers
Use struct rtnl_link_stats64 as the statistics structure.
On 32-bit architectures, insert 32 bits of padding after/before each
field of struct net_device_stats to make its layout compatible with
struct rtnl_link_stats64. Add an anonymous union in net_device; move
stats into the union and add struct rtnl_link_stats64 stats64.
Add net_device_ops::ndo_get_stats64, implementations of which will
return a pointer to struct rtnl_link_stats64. Drivers that implement
this operation must not update the structure asynchronously.
Change dev_get_stats() to call ndo_get_stats64 if available, and to
return a pointer to struct rtnl_link_stats64. Change callers of
dev_get_stats() accordingly.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
This time without the horrible accessor macros.
Ben.
include/linux/if_link.h | 3 +-
include/linux/netdevice.h | 91 ++++++++++++++++++++++++++------------------
net/8021q/vlanproc.c | 13 +++---
net/core/dev.c | 19 +++++----
net/core/net-sysfs.c | 12 +++---
net/core/rtnetlink.c | 6 +-
6 files changed, 83 insertions(+), 61 deletions(-)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 85c812d..7fcad2e 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -4,7 +4,7 @@
#include <linux/types.h>
#include <linux/netlink.h>
-/* The struct should be in sync with struct net_device_stats */
+/* This struct should be in sync with struct rtnl_link_stats64 */
struct rtnl_link_stats {
__u32 rx_packets; /* total packets received */
__u32 tx_packets; /* total packets transmitted */
@@ -37,6 +37,7 @@ struct rtnl_link_stats {
__u32 tx_compressed;
};
+/* The main device statistics structure */
struct rtnl_link_stats64 {
__u64 rx_packets; /* total packets received */
__u64 tx_packets; /* total packets transmitted */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a249161..dceacc2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -159,45 +159,49 @@ static inline bool dev_xmit_complete(int rc)
#define MAX_HEADER (LL_MAX_HEADER + 48)
#endif
-#endif /* __KERNEL__ */
-
/*
- * Network device statistics. Akin to the 2.0 ether stats but
- * with byte counters.
+ * Old network device statistics. Fields are native words
+ * (unsigned long) so they can be read and written atomically.
+ * Each field is padded to 64 bits for compatibility with
+ * rtnl_link_stats64.
*/
+#if BITS_PER_LONG == 64
+#define NET_DEVICE_STATS_DEFINE(name) u64 name
+#elif defined(__LITTLE_ENDIAN)
+#define NET_DEVICE_STATS_DEFINE(name) u32 name, pad_ ## name
+#else
+#define NET_DEVICE_STATS_DEFINE(name) u32 pad_ ## name, name
+#endif
+
struct net_device_stats {
- unsigned long rx_packets; /* total packets received */
- unsigned long tx_packets; /* total packets transmitted */
- unsigned long rx_bytes; /* total bytes received */
- unsigned long tx_bytes; /* total bytes transmitted */
- unsigned long rx_errors; /* bad packets received */
- unsigned long tx_errors; /* packet transmit problems */
- unsigned long rx_dropped; /* no space in linux buffers */
- unsigned long tx_dropped; /* no space available in linux */
- unsigned long multicast; /* multicast packets received */
- unsigned long collisions;
-
- /* detailed rx_errors: */
- unsigned long rx_length_errors;
- unsigned long rx_over_errors; /* receiver ring buff overflow */
- unsigned long rx_crc_errors; /* recved pkt with crc error */
- unsigned long rx_frame_errors; /* recv'd frame alignment error */
- unsigned long rx_fifo_errors; /* recv'r fifo overrun */
- unsigned long rx_missed_errors; /* receiver missed packet */
-
- /* detailed tx_errors */
- unsigned long tx_aborted_errors;
- unsigned long tx_carrier_errors;
- unsigned long tx_fifo_errors;
- unsigned long tx_heartbeat_errors;
- unsigned long tx_window_errors;
-
- /* for cslip etc */
- unsigned long rx_compressed;
- unsigned long tx_compressed;
+ NET_DEVICE_STATS_DEFINE(rx_packets);
+ NET_DEVICE_STATS_DEFINE(tx_packets);
+ NET_DEVICE_STATS_DEFINE(rx_bytes);
+ NET_DEVICE_STATS_DEFINE(tx_bytes);
+ NET_DEVICE_STATS_DEFINE(rx_errors);
+ NET_DEVICE_STATS_DEFINE(tx_errors);
+ NET_DEVICE_STATS_DEFINE(rx_dropped);
+ NET_DEVICE_STATS_DEFINE(tx_dropped);
+ NET_DEVICE_STATS_DEFINE(multicast);
+ NET_DEVICE_STATS_DEFINE(collisions);
+ NET_DEVICE_STATS_DEFINE(rx_length_errors);
+ NET_DEVICE_STATS_DEFINE(rx_over_errors);
+ NET_DEVICE_STATS_DEFINE(rx_crc_errors);
+ NET_DEVICE_STATS_DEFINE(rx_frame_errors);
+ NET_DEVICE_STATS_DEFINE(rx_fifo_errors);
+ NET_DEVICE_STATS_DEFINE(rx_missed_errors);
+ NET_DEVICE_STATS_DEFINE(tx_aborted_errors);
+ NET_DEVICE_STATS_DEFINE(tx_carrier_errors);
+ NET_DEVICE_STATS_DEFINE(tx_fifo_errors);
+ NET_DEVICE_STATS_DEFINE(tx_heartbeat_errors);
+ NET_DEVICE_STATS_DEFINE(tx_window_errors);
+ NET_DEVICE_STATS_DEFINE(rx_compressed);
+ NET_DEVICE_STATS_DEFINE(tx_compressed);
};
+#endif /* __KERNEL__ */
+
/* Media selection options. */
enum {
@@ -660,10 +664,19 @@ struct netdev_rx_queue {
* Callback uses when the transmitter has not made any progress
* for dev->watchdog ticks.
*
+ * struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev);
* struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
* Called when a user wants to get the network device usage
- * statistics. If not defined, the counters in dev->stats will
- * be used.
+ * statistics. Drivers must do one of the following:
+ * 1. Define @ndo_get_stats64 to update a rtnl_link_stats64 structure
+ * (which should normally be dev->stats64) and return a ponter to
+ * it. The structure must not be changed asynchronously.
+ * 2. Define @ndo_get_stats to update a net_device_stats64 structure
+ * (which should normally be dev->stats) and return a pointer to
+ * it. The structure may be changed asynchronously only if each
+ * field is written atomically.
+ * 3. Update dev->stats asynchronously and atomically, and define
+ * neither operation.
*
* void (*ndo_vlan_rx_register)(struct net_device *dev, struct vlan_group *grp);
* If device support VLAN receive accleration
@@ -718,6 +731,7 @@ struct net_device_ops {
struct neigh_parms *);
void (*ndo_tx_timeout) (struct net_device *dev);
+ struct rtnl_link_stats64* (*ndo_get_stats64)(struct net_device *dev);
struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
void (*ndo_vlan_rx_register)(struct net_device *dev,
@@ -867,7 +881,10 @@ struct net_device {
int ifindex;
int iflink;
- struct net_device_stats stats;
+ union {
+ struct rtnl_link_stats64 stats64;
+ struct net_device_stats stats;
+ };
#ifdef CONFIG_WIRELESS_EXT
/* List of functions to handle Wireless Extensions (instead of ioctl).
@@ -2118,7 +2135,7 @@ extern void netdev_features_change(struct net_device *dev);
/* Load a device via the kmod */
extern void dev_load(struct net *net, const char *name);
extern void dev_mcast_init(void);
-extern const struct net_device_stats *dev_get_stats(struct net_device *dev);
+extern const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev);
extern void dev_txq_stats_fold(const struct net_device *dev, struct net_device_stats *stats);
extern int netdev_max_backlog;
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index afead35..df56f5c 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -278,8 +278,9 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
{
struct net_device *vlandev = (struct net_device *) seq->private;
const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
- const struct net_device_stats *stats;
+ const struct rtnl_link_stats64 *stats;
static const char fmt[] = "%30s %12lu\n";
+ static const char fmt64[] = "%30s %12llu\n";
int i;
if (!is_vlan_dev(vlandev))
@@ -291,12 +292,12 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
vlandev->name, dev_info->vlan_id,
(int)(dev_info->flags & 1), vlandev->priv_flags);
- seq_printf(seq, fmt, "total frames received", stats->rx_packets);
- seq_printf(seq, fmt, "total bytes received", stats->rx_bytes);
- seq_printf(seq, fmt, "Broadcast/Multicast Rcvd", stats->multicast);
+ seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
+ seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
+ seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast);
seq_puts(seq, "\n");
- seq_printf(seq, fmt, "total frames transmitted", stats->tx_packets);
- seq_printf(seq, fmt, "total bytes transmitted", stats->tx_bytes);
+ seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
+ seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
seq_printf(seq, fmt, "total headroom inc",
dev_info->cnt_inc_headroom_on_tx);
seq_printf(seq, fmt, "total encap on xmit",
diff --git a/net/core/dev.c b/net/core/dev.c
index 983a3c1..71a6fd8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3686,10 +3686,10 @@ void dev_seq_stop(struct seq_file *seq, void *v)
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
- const struct net_device_stats *stats = dev_get_stats(dev);
+ const struct rtnl_link_stats64 *stats = dev_get_stats(dev);
- seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
- "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
+ seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
+ "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
dev->name, stats->rx_bytes, stats->rx_packets,
stats->rx_errors,
stats->rx_dropped + stats->rx_missed_errors,
@@ -5266,18 +5266,21 @@ EXPORT_SYMBOL(dev_txq_stats_fold);
* @dev: device to get statistics from
*
* Get network statistics from device. The device driver may provide
- * its own method by setting dev->netdev_ops->get_stats; otherwise
- * the internal statistics structure is used.
+ * its own method by setting dev->netdev_ops->get_stats64 or
+ * dev->netdev_ops->get_stats; otherwise the internal statistics
+ * structure is used.
*/
-const struct net_device_stats *dev_get_stats(struct net_device *dev)
+const struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev)
{
const struct net_device_ops *ops = dev->netdev_ops;
+ if (ops->ndo_get_stats64)
+ return ops->ndo_get_stats64(dev);
if (ops->ndo_get_stats)
- return ops->ndo_get_stats(dev);
+ return (struct rtnl_link_stats64 *)ops->ndo_get_stats(dev);
dev_txq_stats_fold(dev, &dev->stats);
- return &dev->stats;
+ return &dev->stats64;
}
EXPORT_SYMBOL(dev_get_stats);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 99e7052..ea3bb4c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -29,6 +29,7 @@ static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
static const char fmt_ulong[] = "%lu\n";
+static const char fmt_u64[] = "%llu\n";
static inline int dev_isalive(const struct net_device *dev)
{
@@ -324,14 +325,13 @@ static ssize_t netstat_show(const struct device *d,
struct net_device *dev = to_net_dev(d);
ssize_t ret = -EINVAL;
- WARN_ON(offset > sizeof(struct net_device_stats) ||
- offset % sizeof(unsigned long) != 0);
+ WARN_ON(offset > sizeof(struct rtnl_link_stats64) ||
+ offset % sizeof(u64) != 0);
read_lock(&dev_base_lock);
if (dev_isalive(dev)) {
- const struct net_device_stats *stats = dev_get_stats(dev);
- ret = sprintf(buf, fmt_ulong,
- *(unsigned long *)(((u8 *) stats) + offset));
+ const struct rtnl_link_stats64 *stats = dev_get_stats(dev);
+ ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset));
}
read_unlock(&dev_base_lock);
return ret;
@@ -343,7 +343,7 @@ static ssize_t show_##name(struct device *d, \
struct device_attribute *attr, char *buf) \
{ \
return netstat_show(d, attr, buf, \
- offsetof(struct net_device_stats, name)); \
+ offsetof(struct rtnl_link_stats64, name)); \
} \
static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1a2af24..e645778 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -579,7 +579,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev,
}
static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
- const struct net_device_stats *b)
+ const struct rtnl_link_stats64 *b)
{
a->rx_packets = b->rx_packets;
a->tx_packets = b->tx_packets;
@@ -610,7 +610,7 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
a->tx_compressed = b->tx_compressed;
}
-static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b)
+static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b)
{
struct rtnl_link_stats64 a;
@@ -791,7 +791,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
- const struct net_device_stats *stats;
+ const struct rtnl_link_stats64 *stats;
struct nlattr *attr;
nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags);
--
1.6.2.5
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCHv2 2/2] sfc: Implement 64-bit net device statistics on all architectures
From: Ben Hutchings @ 2010-06-04 22:06 UTC (permalink / raw)
To: David Miller; +Cc: Stephen Hemminger, Arnd Bergmann, netdev, linux-net-drivers
In-Reply-To: <1275689093.2095.36.camel@achroite.uk.solarflarecom.com>
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
This is unchanged from v1.
Ben.
drivers/net/sfc/efx.c | 6 +++---
1 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 26b0cc2..8ad476a 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -1492,11 +1492,11 @@ static int efx_net_stop(struct net_device *net_dev)
}
/* Context: process, dev_base_lock or RTNL held, non-blocking. */
-static struct net_device_stats *efx_net_stats(struct net_device *net_dev)
+static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_mac_stats *mac_stats = &efx->mac_stats;
- struct net_device_stats *stats = &net_dev->stats;
+ struct rtnl_link_stats64 *stats = &net_dev->stats64;
spin_lock_bh(&efx->stats_lock);
efx->type->update_stats(efx);
@@ -1630,7 +1630,7 @@ static void efx_set_multicast_list(struct net_device *net_dev)
static const struct net_device_ops efx_netdev_ops = {
.ndo_open = efx_net_open,
.ndo_stop = efx_net_stop,
- .ndo_get_stats = efx_net_stats,
+ .ndo_get_stats64 = efx_net_stats,
.ndo_tx_timeout = efx_watchdog,
.ndo_start_xmit = efx_hard_start_xmit,
.ndo_validate_addr = eth_validate_addr,
--
1.6.2.5
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* Re: Is CONFIG_IP_VS_IPV6 still/really dangerous?
From: Ferenc Wagner @ 2010-06-04 22:21 UTC (permalink / raw)
To: lvs-users; +Cc: netdev, robert.gallagher, Julius Volz
In-Reply-To: <AANLkTikQPaHYuOOAiJtIft9NnOZ2S1LXTVMi_BLD8gau@mail.gmail.com>
Julius Volz <juliusv@google.com> writes:
> On Fri, Jun 4, 2010 at 3:56 PM, Ferenc Wagner <wferi@niif.hu> wrote:
>
>> In commit fab0de02fb0da83b90cec7fce4294747d86d5c6f CONFIG_IP_VS_IPV6 is
>> described as:
>>
>> Add IPv6 support to IPVS. This is incomplete and might be dangerous.
>>
>> I agree its implementation is incomplete. But I wonder if it's really
>> dangerous in the sense that generic distribution kernels shouldn't
>> enable it, because it can break unrelated (eg. IPv4 IPVS) functionality.
>>
>> What does that warning mean today? Isn't it out of date?
>
> I wrote the IPv6 support back in the day, but never used it
> large-scale. Rob Gallagher from HEAnet was doing some bigger
> experiments with it, but I'm not sure how far it went. CCing him.
>
> There are probably some other people out there that have tested it
> extensively. Maybe try the lvs-users and lvs-devel mailing lists?
Sounds like a good idea! So:
Dear lvs-users,
did you experience any breakage as a result of switching on
CONFIG_IP_VS_IPV6? I mean apart from it having incomplete
functionality. The gist of the question is whether this option
is suitable for generic distro kernels or not, cf. above.
--
Thanks for your time,
Feri.
^ permalink raw reply
* Re: Ethernet drivers wiki page
From: Stephen Hemminger @ 2010-06-04 22:23 UTC (permalink / raw)
To: Luis R. Rodriguez; +Cc: netdev, H. Peter Anvin, Johannes Berg, linux-kernel
In-Reply-To: <AANLkTik1isTBolg4IDchOlmKqXOLjQoobZrJ-9bb8ZL5@mail.gmail.com>
On Fri, 4 Jun 2010 15:04:17 -0700
"Luis R. Rodriguez" <mcgrof@gmail.com> wrote:
> On Fri, Jun 4, 2010 at 2:52 PM, Luis R. Rodriguez <mcgrof@gmail.com> wrote:
> > Where can I start adding documentation for our Ethernet drivers
> > upstream? I was hoping for a wiki but I don't think we have a netdev
> > one yet. Shall we create one or piggy back on something else? I'm
> > reviewing:
> >
> > https://wiki.kernel.org/
> >
> > FWIW, I want to see something like this:
> >
> > http://wireless.kernel.org/en/users/Drivers
> >
> > But for ethernet.
>
> Since I've stuffed a few ethernet drivers on compat-wireless I might
> as well start carrying more. So now we'd have 802.11, Bluetooth and
> Ethernet all backported using the same framework, automatically, down
> to at least the oldest stable kernel supported listed on kernel.org
> and using all a generic compat module.
>
> I want to document all this crap.
Why not Documentation/networking in kernel source? There is already
documentation there though much of it is out of date.
This has the advantage of having change log and matching kernel version.
^ permalink raw reply
* Re: 200 millisecond timeouts in TCP
From: Ryousei Takano @ 2010-06-04 22:55 UTC (permalink / raw)
To: Satoru SATOH; +Cc: Ivan Novick, netdev
In-Reply-To: <20100604150202.GA8268@localhost.localdomain>
Hi satoru,
On Sat, Jun 5, 2010 at 12:02 AM, Satoru SATOH <satoru.satoh@gmail.com> wrote:
> It's possible to tune the RTO min value (rto_min) per route since
> 2.6.23+. (see also the manual of iproute2, ip(8) )
>
Yeah, I forgot it. Per route configuration is a nice idea compared
with global sysctls.
Thanks!
Ryousei
> - satoru
>
> On Fri, Jun 04, 2010 at 03:58:57PM +0900, Ryousei Takano wrote:
>> On Fri, Jun 4, 2010 at 7:37 AM, Ivan Novick <novickivan@gmail.com> wrote:
>> > Hello,
>> >
>> > Using tcpdump and systemtap I am seeing that sometimes retransmission
>> > of data is sent after waiting 200 milliseconds. However sometimes
>> > retransmissions happen quicker.
>> >
>> > Is there a specifc event that causes these 200 milisec delays to kick
>> > in? Are those events identifiable in netstat -s output?
>> >
>> > Also do you know if the timeout numbers for TCP are configurable parameters?
>> >
>> The minimum RTO value is fixed to 200 ms. It is useful to make the min/max
>> RTO values tunable. For example, reducing the minimum RTO value is effective
>> for TCP incast problem [1]. Of course, it may occur spurious retransmissions.
>>
>> [1] Vijay Vasudevan, et al, Safe and Effective Fine-grained TCP Retransmissions
>> for Datacenter Communication, SIGCOMM2009
>>
>> In Solaris, there are two tunable parameters: tcp_rexmit_interval_min/max.
>>
>> Do you have plan to introduce sysctl parameters like these to the Linux.
>>
>> Thanks,
>> Ryousei
>
^ permalink raw reply
* Re: [PATCH] syncookies: remove Kconfig text line about disabled-by-default
From: David Miller @ 2010-06-04 22:57 UTC (permalink / raw)
To: fw; +Cc: netdev
In-Reply-To: <1275561750-24111-1-git-send-email-fw@strlen.de>
From: Florian Westphal <fw@strlen.de>
Date: Thu, 3 Jun 2010 12:42:30 +0200
> syncookies default to on since
> e994b7c901ded7200b525a707c6da71f2cf6d4bb
> (tcp: Don't make syn cookies initial setting depend on CONFIG_SYSCTL).
>
> Signed-off-by: Florian Westphal <fw@strlen.de>
Applied, thanks Florian.
^ permalink raw reply
* Re: [PATCH] tcp: use correct net ns in cookie_v4_check()
From: David Miller @ 2010-06-04 22:57 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1275579947.2456.80.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 03 Jun 2010 17:45:47 +0200
> [PATCH] tcp: use correct net ns in cookie_v4_check()
>
> Its better to make a route lookup in appropriate namespace.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied and queued up for -stable, thanks Eric!
^ permalink raw reply
* Re: [PATCH] rps: tcp: fix rps_sock_flow_table table updates
From: David Miller @ 2010-06-04 22:57 UTC (permalink / raw)
To: eric.dumazet; +Cc: therbert, netdev
In-Reply-To: <1275591838.2533.37.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Thu, 03 Jun 2010 21:03:58 +0200
> I believe a moderate SYN flood attack can corrupt RFS flow table
> (rps_sock_flow_table), making RPS/RFS much less effective.
>
> Even in a normal situation, server handling short lived sessions suffer
> from bad steering for the first data packet of a session, if another SYN
> packet is received for another session.
>
> We do following action in tcp_v4_rcv() :
>
> sock_rps_save_rxhash(sk, skb->rxhash);
>
> We should _not_ do this if sk is a LISTEN socket, as about each
> packet received on a LISTEN socket has a different rxhash than
> previous one.
> -> RPS_NO_CPU markers are spread all over rps_sock_flow_table.
>
> Also, it makes sense to protect sk->rxhash field changes with socket
> lock (We currently can change it even if user thread owns the lock
> and might use rxhash)
>
> This patch moves sock_rps_save_rxhash() to a sock locked section,
> and only for non LISTEN sockets.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [net-2.6 PATCH] ixgbe: only check pfc bits in hang logic if pfc is enabled
From: David Miller @ 2010-06-04 22:58 UTC (permalink / raw)
To: jeffrey.t.kirsher; +Cc: netdev, gospo, john.r.fastabend, donald.c.skidmore
In-Reply-To: <20100604030314.16356.79492.stgit@localhost.localdomain>
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Thu, 03 Jun 2010 20:03:45 -0700
> From: John Fastabend <john.r.fastabend@intel.com>
>
> Only check pfc bits in hang logic if PFC is enabled. Previously,
> if DCB was enabled but PFC was disabled the incorrect pause
> bits would be checked.
>
> Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
> Acked-by: Don Skidmore <donald.c.skidmore@intel.com>
> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Applied.
^ permalink raw reply
* Re: [PATCH v2] net: check for refcount if pop a stacked dst_entry
From: David Miller @ 2010-06-04 22:58 UTC (permalink / raw)
To: eric.dumazet; +Cc: steffen.klassert, netdev
In-Reply-To: <1275653207.2482.120.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 04 Jun 2010 14:06:47 +0200
> Le vendredi 04 juin 2010 à 13:57 +0200, Steffen Klassert a écrit :
>> xfrm triggers a warning if dst_pop() drops a refcount
>> on a noref dst. This patch changes dst_pop() to
>> skb_dst_pop(). skb_dst_pop() drops the refcnt only
>> on a refcounted dst. Also we don't clone the child
>> dst_entry, so it is not refcounted and we can use
>> skb_dst_set_noref() in xfrm_output_one().
>>
>> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
>> ---
>
> Thanks a lot Steffen !
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied, thanks guys!
^ permalink raw reply
* cxgb4i_v4 submission
From: Rakesh Ranjan @ 2010-06-04 22:58 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt
The following 3 patches add a new iscsi LLD driver cxgb4i to enable iscsi offload
support on Chelsio's new 1G and 10G cards. This is updated version of previous cxgb4i
patch. Please share you commnets after review.
Changes since cxgb4i_v3.1
1. Fixed issues reported by mike.
2. Made libcxgbi more generic.
[PATCH 1/3] cxgb4i_v4: add build support
[PATCH 2/3] cxgb4i_v4: libcxgbi library for handling common part in cxgb4i/cxgb3i
[PATCH 3/3] cxgb4i_v4: main driver files
Regards
Rakesh Ranjan
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply
* [PATCH 2/3] cxgb4i_v4: libcxgbi library for handling common part in cxgb4i/cxgb3i
From: Rakesh Ranjan @ 2010-06-04 22:58 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt, Rakesh Ranjan
In-Reply-To: <1275692327-21502-1-git-send-email-rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
From: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/scsi/cxgbi/libcxgbi.c | 1529 +++++++++++++++++++++++++++++++++++++++++
drivers/scsi/cxgbi/libcxgbi.h | 577 ++++++++++++++++
2 files changed, 2106 insertions(+), 0 deletions(-)
create mode 100644 drivers/scsi/cxgbi/libcxgbi.c
create mode 100644 drivers/scsi/cxgbi/libcxgbi.h
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
new file mode 100644
index 0000000..3c2e621
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -0,0 +1,1529 @@
+/*
+ * libcxgbi.c: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * 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.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <linux/pci.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/if_vlan.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <net/tcp.h>
+
+#include "libcxgbi.h"
+
+MODULE_AUTHOR("Chelsio Communications");
+MODULE_DESCRIPTION("Chelsio libcxgbi common library");
+MODULE_LICENSE("GPL");
+
+static LIST_HEAD(cdev_list);
+static DEFINE_MUTEX(cdev_rwlock);
+
+struct cxgbi_device *cxgbi_device_register(unsigned int dd_size,
+ unsigned int nports)
+{
+ struct cxgbi_device *cdev;
+
+ cdev = kzalloc(sizeof(*cdev) + dd_size, GFP_KERNEL);
+ if (!cdev)
+ return NULL;
+
+ cdev->hbas = kzalloc(sizeof(struct cxgbi_hba **) * nports, GFP_KERNEL);
+ if (!cdev->hbas) {
+ kfree(cdev);
+ return NULL;
+ }
+
+ mutex_lock(&cdev_rwlock);
+ list_add_tail(&cdev->list_head, &cdev_list);
+ mutex_unlock(&cdev_rwlock);
+ return cdev;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_register);
+
+void cxgbi_device_unregister(struct cxgbi_device *cdev)
+{
+ mutex_lock(&cdev_rwlock);
+ list_del(&cdev->list_head);
+ mutex_unlock(&cdev_rwlock);
+
+ kfree(cdev->hbas);
+ kfree(cdev);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister);
+
+struct cxgbi_hba *cxgbi_hba_find_by_netdev(struct net_device *dev,
+ struct cxgbi_device *cdev)
+{
+ int i;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN)
+ dev = vlan_dev_real_dev(dev);
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (cdev->hbas[i]->ndev == dev)
+ return cdev->hbas[i];
+ }
+
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_hba_find_by_netdev);
+
+static struct rtable *find_route(struct net_device *dev,
+ __be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport,
+ u8 tos)
+{
+ struct rtable *rt;
+ struct flowi fl = {
+ .oif = dev ? dev->ifindex : 0,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = daddr,
+ .saddr = saddr,
+ .tos = tos }
+ },
+ .proto = IPPROTO_TCP,
+ .uli_u = {
+ .ports = {
+ .sport = sport,
+ .dport = dport }
+ }
+ };
+
+ if (ip_route_output_flow(dev ? dev_net(dev) : &init_net,
+ &rt, &fl, NULL, 0))
+ return NULL;
+
+ return rt;
+}
+
+static struct net_device *cxgbi_find_dev(struct net_device *dev,
+ __be32 ipaddr)
+{
+ struct flowi fl;
+ struct rtable *rt;
+ int err;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.nl_u.ip4_u.daddr = ipaddr;
+
+ err = ip_route_output_key(dev ? dev_net(dev) : &init_net, &rt, &fl);
+ if (!err)
+ return (&rt->u.dst)->dev;
+
+ return NULL;
+}
+
+static int is_cxgbi_dev(struct net_device *dev, struct cxgbi_device *cdev)
+{
+ struct net_device *ndev = dev;
+ int i;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN)
+ ndev = vlan_dev_real_dev(dev);
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (ndev == cdev->ports[i])
+ return 1;
+ }
+ return 0;
+}
+
+static struct net_device *cxgbi_find_egress_dev(struct net_device *root_dev,
+ struct cxgbi_device *cdev)
+{
+ while (root_dev) {
+ if (root_dev->priv_flags & IFF_802_1Q_VLAN)
+ root_dev = vlan_dev_real_dev(root_dev);
+ else if (is_cxgbi_dev(root_dev, cdev))
+ return root_dev;
+ else
+ return NULL;
+ }
+
+ return NULL;
+}
+
+struct cxgbi_device *cxgbi_find_cdev(struct net_device *dev, __be32 ipaddr)
+{
+ struct flowi fl;
+ struct rtable *rt;
+ struct net_device *sdev = NULL;
+ struct cxgbi_device *cdev = NULL, *tmp;
+ int err, i;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.nl_u.ip4_u.daddr = ipaddr;
+
+ err = ip_route_output_key(dev ? dev_net(dev) : &init_net, &rt, &fl);
+ if (err)
+ goto out;
+
+ sdev = (&rt->u.dst)->dev;
+ mutex_lock(&cdev_rwlock);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+ if (cdev) {
+ for (i = 0; i < cdev->nports; i++) {
+ if (sdev == cdev->ports[i]) {
+ mutex_unlock(&cdev_rwlock);
+ return cdev;
+ }
+ }
+ }
+ }
+ mutex_unlock(&cdev_rwlock);
+out: return cdev;
+}
+
+/*
+ * pdu receive, interact with libiscsi_tcp
+ */
+static inline int read_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb,
+ unsigned int offset,
+ int offloaded)
+{
+ int status = 0;
+ int bytes_read;
+
+ bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status);
+ switch (status) {
+ case ISCSI_TCP_CONN_ERR:
+ return -EIO;
+ case ISCSI_TCP_SUSPENDED:
+ /* no transfer - just have caller flush queue */
+ return bytes_read;
+ case ISCSI_TCP_SKB_DONE:
+ /*
+ * pdus should always fit in the skb and we should get
+ * segment done notifcation.
+ */
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb.");
+ return -EFAULT;
+ case ISCSI_TCP_SEGMENT_DONE:
+ return bytes_read;
+ default:
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid iscsi_tcp_recv_skb "
+ "status %d\n", status);
+ return -EINVAL;
+ }
+}
+
+static int cxgbi_conn_read_bhs_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ int rc;
+
+ cxgbi_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n",
+ conn, skb, skb->len, cdev->get_skb_ulp_mode(skb));
+
+ if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_PROTO);
+ return -EIO;
+ }
+
+ if (conn->hdrdgst_en && (cdev->get_skb_ulp_mode(skb)
+ & ULP2_FLAG_HCRC_ERROR)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST);
+ return -EIO;
+ }
+
+ rc = read_pdu_skb(conn, skb, 0, 0);
+ if (rc <= 0)
+ return rc;
+
+ return 0;
+}
+
+static int cxgbi_conn_read_data_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ bool offloaded = 0;
+ unsigned int offset = 0;
+ int rc;
+
+ cxgbi_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n",
+ conn, skb, skb->len, cdev->get_skb_ulp_mode(skb));
+
+ if (conn->datadgst_en &&
+ (cdev->get_skb_ulp_mode(skb) & ULP2_FLAG_DCRC_ERROR)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+ return -EIO;
+ }
+
+ if (iscsi_tcp_recv_segment_is_hdr(tcp_conn))
+ return 0;
+
+ if (conn->hdrdgst_en)
+ offset = ISCSI_DIGEST_SIZE;
+
+ if (cdev->get_skb_ulp_mode(skb) & ULP2_FLAG_DATA_DDPED) {
+ cxgbi_rx_debug("skb 0x%p, opcode 0x%x, data %u, ddp'ed, "
+ "itt 0x%x.\n",
+ skb,
+ tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+ tcp_conn->in.datalen,
+ ntohl(tcp_conn->in.hdr->itt));
+ offloaded = 1;
+ } else {
+ cxgbi_rx_debug("skb 0x%p, opcode 0x%x, data %u, NOT ddp'ed, "
+ "itt 0x%x.\n",
+ skb,
+ tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+ tcp_conn->in.datalen,
+ ntohl(tcp_conn->in.hdr->itt));
+ }
+
+ rc = read_pdu_skb(conn, skb, 0, offloaded);
+ if (rc < 0)
+ return rc;
+
+ return 0;
+}
+
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+ unsigned int read = 0;
+ struct iscsi_conn *conn = csk->user_data;
+ int err = 0;
+
+ cxgbi_rx_debug("csk 0x%p.\n", csk);
+
+ read_lock(&csk->callback_lock);
+ if (unlikely(!conn || conn->suspend_rx)) {
+ cxgbi_rx_debug("conn 0x%p, id %d, suspend_rx %lu!\n",
+ conn, conn ? conn->id : 0xFF,
+ conn ? conn->suspend_rx : 0xFF);
+ read_unlock(&csk->callback_lock);
+ return;
+ }
+
+ skb = skb_peek(&csk->receive_queue);
+ while (!err && skb) {
+ __skb_unlink(skb, &csk->receive_queue);
+ read += csk->cdev->get_skb_rx_pdulen(skb);
+ cxgbi_rx_debug("conn 0x%p, csk 0x%p, rx skb 0x%p, pdulen %u\n",
+ conn, csk, skb,
+ csk->cdev->get_skb_rx_pdulen(skb));
+ if (csk->flags & CTPF_MSG_COALESCED) {
+ err = cxgbi_conn_read_bhs_pdu_skb(conn, skb);
+ err = cxgbi_conn_read_data_pdu_skb(conn, skb);
+ } else {
+ if (csk->cdev->get_skb_flags(skb) & CTP_SKCBF_HDR_RCVD)
+ err = cxgbi_conn_read_bhs_pdu_skb(conn, skb);
+ else if (csk->cdev->get_skb_flags(skb) ==
+ CTP_SKCBF_DATA_RCVD)
+ err = cxgbi_conn_read_data_pdu_skb(conn, skb);
+ }
+ __kfree_skb(skb);
+ skb = skb_peek(&csk->receive_queue);
+ }
+ cxgbi_log_debug("read %d\n", read);
+ read_unlock(&csk->callback_lock);
+ csk->copied_seq += read;
+ csk->cdev->sock_rx_credits(csk, read);
+ conn->rxdata_octets += read;
+
+ if (err) {
+ cxgbi_log_info("conn 0x%p rx failed err %d.\n", conn, err);
+ iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_pdu_ready);
+
+static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt,
+ unsigned int offset, unsigned int *off,
+ struct scatterlist **sgp)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, sgcnt, i) {
+ if (offset < sg->length) {
+ *off = offset;
+ *sgp = sg;
+ return 0;
+ }
+ offset -= sg->length;
+ }
+ return -EFAULT;
+}
+
+static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset,
+ unsigned int dlen, skb_frag_t *frags,
+ int frag_max)
+{
+ unsigned int datalen = dlen;
+ unsigned int sglen = sg->length - sgoffset;
+ struct page *page = sg_page(sg);
+ int i;
+
+ i = 0;
+ do {
+ unsigned int copy;
+
+ if (!sglen) {
+ sg = sg_next(sg);
+ if (!sg) {
+ cxgbi_log_error("sg NULL, len %u/%u.\n",
+ datalen, dlen);
+ return -EINVAL;
+ }
+ sgoffset = 0;
+ sglen = sg->length;
+ page = sg_page(sg);
+
+ }
+ copy = min(datalen, sglen);
+ if (i && page == frags[i - 1].page &&
+ sgoffset + sg->offset ==
+ frags[i - 1].page_offset + frags[i - 1].size) {
+ frags[i - 1].size += copy;
+ } else {
+ if (i >= frag_max) {
+ cxgbi_log_error("too many pages %u, "
+ "dlen %u.\n", frag_max, dlen);
+ return -EINVAL;
+ }
+
+ frags[i].page = page;
+ frags[i].page_offset = sg->offset + sgoffset;
+ frags[i].size = copy;
+ i++;
+ }
+ datalen -= copy;
+ sgoffset += copy;
+ sglen -= copy;
+ } while (datalen);
+
+ return i;
+}
+
+int cxgbi_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = task->dd_data + sizeof(*tcp_task);
+ struct scsi_cmnd *sc = task->sc;
+ int headroom = SKB_TX_PDU_HEADER_LEN;
+
+ tcp_task->dd_data = tdata;
+ task->hdr = NULL;
+
+ /* write command, need to send data pdus */
+ if (cdev->skb_extra_headroom && (opcode == ISCSI_OP_SCSI_DATA_OUT ||
+ (opcode == ISCSI_OP_SCSI_CMD &&
+ (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE))))
+ headroom += min(cdev->skb_extra_headroom,
+ conn->max_xmit_dlength);
+
+ tdata->skb = alloc_skb(cdev->skb_tx_headroom + headroom, GFP_ATOMIC);
+ if (!tdata->skb)
+ return -ENOMEM;
+
+ skb_reserve(tdata->skb, cdev->skb_tx_headroom);
+ cxgbi_tx_debug("task 0x%p, opcode 0x%x, skb 0x%p.\n",
+ task, opcode, tdata->skb);
+ task->hdr = (struct iscsi_hdr *)tdata->skb->data;
+ task->hdr_max = SKB_TX_PDU_HEADER_LEN;
+
+ /* data_out uses scsi_cmd's itt */
+ if (opcode != ISCSI_OP_SCSI_DATA_OUT)
+ cxgbi_reserve_itt(task, &task->hdr->itt);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_alloc_pdu);
+
+int cxgbi_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
+ unsigned int count)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen = count;
+ int i, padlen = iscsi_padding(count);
+ struct page *pg;
+
+ cxgbi_tx_debug("task 0x%p,0x%p, offset %u, count %u, skb 0x%p.\n",
+ task, task->sc, offset, count, skb);
+
+ skb_put(skb, task->hdr_len);
+ cdev->set_skb_txmode(skb, conn->hdrdgst_en,
+ datalen ? conn->datadgst_en : 0);
+ if (!count)
+ return 0;
+
+ if (task->sc) {
+ struct scsi_data_buffer *sdb = scsi_out(task->sc);
+ struct scatterlist *sg = NULL;
+ int err;
+
+ tdata->offset = offset;
+ tdata->count = count;
+ err = sgl_seek_offset(sdb->table.sgl, sdb->table.nents,
+ tdata->offset, &tdata->sgoffset, &sg);
+ if (err < 0) {
+ cxgbi_log_warn("tpdu, sgl %u, bad offset %u/%u.\n",
+ sdb->table.nents, tdata->offset,
+ sdb->length);
+ return err;
+ }
+ err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count,
+ tdata->frags, MAX_PDU_FRAGS);
+ if (err < 0) {
+ cxgbi_log_warn("tpdu, sgl %u, bad offset %u + %u.\n",
+ sdb->table.nents, tdata->offset,
+ tdata->count);
+ return err;
+ }
+ tdata->nr_frags = err;
+
+ if (tdata->nr_frags > MAX_SKB_FRAGS ||
+ (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) {
+ char *dst = skb->data + task->hdr_len;
+ skb_frag_t *frag = tdata->frags;
+
+ /* data fits in the skb's headroom */
+ for (i = 0; i < tdata->nr_frags; i++, frag++) {
+ char *src = kmap_atomic(frag->page,
+ KM_SOFTIRQ0);
+
+ memcpy(dst, src+frag->page_offset, frag->size);
+ dst += frag->size;
+ kunmap_atomic(src, KM_SOFTIRQ0);
+ }
+ if (padlen) {
+ memset(dst, 0, padlen);
+ padlen = 0;
+ }
+ skb_put(skb, count + padlen);
+ } else {
+ /* data fit into frag_list */
+ for (i = 0; i < tdata->nr_frags; i++)
+ get_page(tdata->frags[i].page);
+
+ memcpy(skb_shinfo(skb)->frags, tdata->frags,
+ sizeof(skb_frag_t) * tdata->nr_frags);
+ skb_shinfo(skb)->nr_frags = tdata->nr_frags;
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ } else {
+ pg = virt_to_page(task->data);
+
+ get_page(pg);
+ skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data),
+ count);
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ if (padlen) {
+ i = skb_shinfo(skb)->nr_frags;
+ get_page(cdev->pad_page);
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ cdev->pad_page, 0, padlen);
+
+ skb->data_len += padlen;
+ skb->truesize += padlen;
+ skb->len += padlen;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_init_pdu);
+
+int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen;
+ int err;
+
+ if (!skb)
+ return 0;
+
+ datalen = skb->data_len;
+ tdata->skb = NULL;
+ err = cdev->sock_send_pdus(cconn->cep->csk, skb);
+ if (err > 0) {
+ int pdulen = err;
+
+ cxgbi_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n",
+ task, skb, skb->len, skb->data_len, err);
+
+ if (task->conn->hdrdgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ if (datalen && task->conn->datadgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ task->conn->txdata_octets += pdulen;
+ return 0;
+ }
+
+ if (err == -EAGAIN || err == -ENOBUFS) {
+ /* reset skb to send when we are called again */
+ tdata->skb = skb;
+ return err;
+ }
+
+ kfree_skb(skb);
+ cxgbi_tx_debug("itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
+ task->itt, skb, skb->len, skb->data_len, err);
+ iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
+ iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_xmit_pdu);
+
+int cxgbi_pdu_init(struct cxgbi_device *cdev)
+{
+ cdev->pad_page = alloc_page(GFP_KERNEL);
+ if (!cdev->pad_page)
+ return -ENOMEM;
+
+ memset(page_address(cdev->pad_page), 0, PAGE_SIZE);
+
+ if (cdev->skb_tx_headroom > (512 * MAX_SKB_FRAGS))
+ cdev->skb_extra_headroom = cdev->skb_tx_headroom;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_pdu_init);
+
+void cxgbi_pdu_cleanup(struct cxgbi_device *cdev)
+{
+ if (cdev->pad_page) {
+ __free_page(cdev->pad_page);
+ cdev->pad_page = NULL;
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_pdu_cleanup);
+
+void cxgbi_conn_tx_open(struct cxgbi_sock *csk)
+{
+ struct iscsi_conn *conn = csk->user_data;
+
+ if (conn) {
+ cxgbi_tx_debug("cn 0x%p, cid %d.\n", csk, conn->id);
+ iscsi_conn_queue_work(conn);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_tx_open);
+
+struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev)
+{
+ struct cxgbi_sock *csk = NULL;
+
+ csk = kzalloc(sizeof(*csk), GFP_NOIO);
+ if (!csk)
+ return NULL;
+
+ if (cdev->alloc_cpl_skbs(csk) < 0)
+ goto free_csk;
+
+ cxgbi_conn_debug("alloc csk: 0x%p\n", csk);
+
+ csk->flags = 0;
+ spin_lock_init(&csk->lock);
+ kref_init(&csk->refcnt);
+ skb_queue_head_init(&csk->receive_queue);
+ skb_queue_head_init(&csk->write_queue);
+ setup_timer(&csk->retry_timer, NULL, (unsigned long)csk);
+ rwlock_init(&csk->callback_lock);
+ csk->cdev = cdev;
+ return csk;
+free_csk:
+ cxgbi_api_debug("csk alloc failed %p, baling out\n", csk);
+ kfree(csk);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_create);
+
+int cxgbi_sock_connect(struct net_device *dev, struct cxgbi_sock *csk,
+ struct sockaddr_in *sin)
+{
+ struct rtable *rt;
+ __be32 sipv4 = 0;
+ struct net_device *dstdev;
+ struct cxgbi_hba *chba = NULL;
+ int err;
+
+ cxgbi_conn_debug("csk 0x%p, dev 0x%p\n", csk, dev);
+
+ if (sin->sin_family != AF_INET)
+ return -EAFNOSUPPORT;
+
+ csk->daddr.sin_port = sin->sin_port;
+ csk->daddr.sin_addr.s_addr = sin->sin_addr.s_addr;
+
+ dstdev = cxgbi_find_dev(dev, sin->sin_addr.s_addr);
+ if (!dstdev || !is_cxgbi_dev(dstdev, csk->cdev))
+ return -ENETUNREACH;
+
+ if (dstdev->priv_flags & IFF_802_1Q_VLAN)
+ dev = dstdev;
+
+ rt = find_route(dev, csk->saddr.sin_addr.s_addr,
+ csk->daddr.sin_addr.s_addr,
+ csk->saddr.sin_port,
+ csk->daddr.sin_port,
+ 0);
+ if (rt == NULL) {
+ cxgbi_conn_debug("no route to %pI4, port %u, dev %s, "
+ "snic 0x%p\n",
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port),
+ dev ? dev->name : "any",
+ csk->dd_data);
+ return -ENETUNREACH;
+ }
+
+ if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
+ cxgbi_conn_debug("multi-cast route to %pI4, port %u, "
+ "dev %s, snic 0x%p\n",
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port),
+ dev ? dev->name : "any",
+ csk->dd_data);
+ ip_rt_put(rt);
+ return -ENETUNREACH;
+ }
+
+ if (!csk->saddr.sin_addr.s_addr)
+ csk->saddr.sin_addr.s_addr = rt->rt_src;
+
+ csk->dst = &rt->u.dst;
+
+ dev = cxgbi_find_egress_dev(csk->dst->dev, csk->cdev);
+ if (dev == NULL) {
+ cxgbi_conn_debug("csk: 0x%p, egress dev NULL\n", csk);
+ return -ENETUNREACH;
+ }
+
+ csk->egdev = dev;
+
+ err = cxgbi_sock_get_port(csk);
+ if (err)
+ return err;
+
+ cxgbi_conn_debug("csk: 0x%p get port: %u\n",
+ csk, ntohs(csk->saddr.sin_port));
+
+ chba = cxgbi_hba_find_by_netdev(csk->dst->dev, csk->cdev);
+
+ sipv4 = cxgbi_get_iscsi_ipv4(chba);
+ if (!sipv4) {
+ cxgbi_conn_debug("csk: 0x%p, iscsi is not configured\n", csk);
+ sipv4 = csk->saddr.sin_addr.s_addr;
+ cxgbi_set_iscsi_ipv4(chba, sipv4);
+ } else
+ csk->saddr.sin_addr.s_addr = sipv4;
+
+ cxgbi_conn_debug("csk: 0x%p, %pI4:[%u], %pI4:[%u] SYN_SENT\n",
+ csk,
+ &csk->saddr.sin_addr.s_addr,
+ ntohs(csk->saddr.sin_port),
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port));
+
+ cxgbi_sock_set_state(csk, CTP_CONNECTING);
+
+ if (!csk->cdev->init_act_open(csk, dev))
+ return 0;
+
+ err = -ENOTSUPP;
+ cxgbi_conn_debug("csk 0x%p -> closed\n", csk);
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+ ip_rt_put(rt);
+ cxgbi_sock_put_port(csk);
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_connect);
+
+int cxgbi_sock_get_port(struct cxgbi_sock *csk)
+{
+ unsigned int start;
+ int idx;
+
+ if (!csk->cdev->pmap)
+ goto error_out;
+
+ if (csk->saddr.sin_port) {
+ cxgbi_log_error("connect, sin_port none ZERO %u\n",
+ ntohs(csk->saddr.sin_port));
+ return -EADDRINUSE;
+ }
+
+ spin_lock_bh(&csk->cdev->pmap->lock);
+ start = idx = csk->cdev->pmap->next;
+
+ do {
+ if (++idx >= csk->cdev->pmap->max_connect)
+ idx = 0;
+ if (!csk->cdev->pmap->port_csk[idx]) {
+ csk->saddr.sin_port =
+ htons(csk->cdev->pmap->sport_base + idx);
+ csk->cdev->pmap->next = idx;
+ csk->cdev->pmap->port_csk[idx] = csk;
+ spin_unlock_bh(&csk->cdev->pmap->lock);
+ cxgbi_conn_debug("reserved port %u\n",
+ csk->cdev->pmap->sport_base + idx);
+ return 0;
+ }
+ } while (idx != start);
+ spin_unlock_bh(&csk->cdev->pmap->lock);
+error_out:
+ return -EADDRNOTAVAIL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_get_port);
+
+void cxgbi_sock_put_port(struct cxgbi_sock *csk)
+{
+ if (csk->saddr.sin_port) {
+ int idx = ntohs(csk->saddr.sin_port) -
+ csk->cdev->pmap->sport_base;
+
+ csk->saddr.sin_port = 0;
+ if (idx < 0 || idx >= csk->cdev->pmap->max_connect)
+ return;
+
+ spin_lock_bh(&csk->cdev->pmap->lock);
+ csk->cdev->pmap->port_csk[idx] = NULL;
+ spin_unlock_bh(&csk->cdev->pmap->lock);
+ cxgbi_conn_debug("released port %u\n",
+ csk->cdev->pmap->sport_base + idx);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_put_port);
+
+void cxgbi_sock_conn_closing(struct cxgbi_sock *csk)
+{
+ struct iscsi_conn *conn = csk->user_data;
+
+ read_lock(&csk->callback_lock);
+ if (conn && csk->state != CTP_ESTABLISHED)
+ iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+ read_unlock(&csk->callback_lock);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_conn_closing);
+
+void cxgbi_sock_closed(struct cxgbi_sock *csk)
+{
+ cxgbi_conn_debug("csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+
+ cxgbi_sock_put_port(csk);
+ csk->cdev->release_offload_resources(csk);
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+ cxgbi_sock_conn_closing(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_closed);
+
+static void cxgbi_sock_active_close(struct cxgbi_sock *csk)
+{
+ int data_lost;
+ int close_req = 0;
+
+ cxgbi_conn_debug("csk 0x%p, state %u, flags %lu\n",
+ csk, csk->state, csk->flags);
+
+ dst_confirm(csk->dst);
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ data_lost = skb_queue_len(&csk->receive_queue);
+ __skb_queue_purge(&csk->receive_queue);
+
+ switch (csk->state) {
+ case CTP_CLOSED:
+ case CTP_ACTIVE_CLOSE:
+ case CTP_CLOSE_WAIT_1:
+ case CTP_CLOSE_WAIT_2:
+ case CTP_ABORTING:
+ break;
+ case CTP_CONNECTING:
+ cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ break;
+ case CTP_ESTABLISHED:
+ close_req = 1;
+ cxgbi_sock_set_flag(csk, CTP_ACTIVE_CLOSE);
+ break;
+ case CTP_PASSIVE_CLOSE:
+ close_req = 1;
+ cxgbi_sock_set_flag(csk, CTP_CLOSE_WAIT_2);
+ break;
+ }
+
+ if (close_req) {
+ if (data_lost)
+ csk->cdev->send_abort_req(csk);
+ else
+ csk->cdev->send_close_req(csk);
+ }
+
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+
+void cxgbi_sock_release(struct cxgbi_sock *csk)
+{
+ cxgbi_conn_debug("csk 0x%p, state %u, flags %lu\n",
+ csk, csk->state, csk->flags);
+
+ if (unlikely(csk->state == CTP_CONNECTING))
+ cxgbi_sock_set_state(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ else if (likely(csk->state != CTP_CLOSED))
+ cxgbi_sock_active_close(csk);
+
+ cxgbi_sock_put(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_release);
+
+unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *csk,
+ unsigned short mtu)
+{
+ int i = 0;
+
+ while (i < csk->cdev->nmtus - 1 && csk->cdev->mtus[i + 1] <= mtu)
+ ++i;
+
+ return i;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_find_best_mtu);
+
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *csk, unsigned int pmtu)
+{
+ unsigned int idx;
+ struct dst_entry *dst = csk->dst;
+ u16 advmss = dst_metric(dst, RTAX_ADVMSS);
+
+ if (advmss > pmtu - 40)
+ advmss = pmtu - 40;
+ if (advmss < csk->cdev->mtus[0] - 40)
+ advmss = csk->cdev->mtus[0] - 40;
+ idx = cxgbi_sock_find_best_mtu(csk, advmss + 40);
+
+ return idx;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_select_mss);
+
+void cxgbi_release_itt(struct iscsi_task *task, itt_t hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ struct cxgbi_tag_format *tformat = &csk->cdev->tag_format;
+ u32 tag = ntohl((__force u32)hdr_itt);
+
+ cxgbi_tag_debug("release tag 0x%x.\n", tag);
+
+ if (sc && (scsi_bidi_cmnd(sc) ||
+ sc->sc_data_direction == DMA_FROM_DEVICE) &&
+ cxgbi_is_ddp_tag(tformat, tag))
+ csk->cdev->ddp_tag_release(csk, tag);
+}
+EXPORT_SYMBOL_GPL(cxgbi_release_itt);
+
+int cxgbi_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_session *sess = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct cxgbi_tag_format *tformat = &cdev->tag_format;
+ u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt;
+ u32 tag;
+ int err = -EINVAL;
+
+ if (sc && (scsi_bidi_cmnd(sc) ||
+ sc->sc_data_direction == DMA_FROM_DEVICE) &&
+ cxgbi_sw_tag_usable(tformat, sw_tag)) {
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ struct cxgbi_gather_list *gl;
+
+ gl = cdev->ddp_make_gl(scsi_in(sc)->length,
+ scsi_in(sc)->table.sgl,
+ scsi_in(sc)->table.nents,
+ cdev->pdev, GFP_ATOMIC);
+ if (gl) {
+ tag = sw_tag;
+ err = cdev->ddp_tag_reserve(csk, csk->hwtid,
+ tformat, &tag,
+ gl, GFP_ATOMIC);
+ if (err < 0)
+ cdev->ddp_release_gl(gl, cdev->pdev);
+ }
+ }
+ if (err < 0)
+ tag = cxgbi_set_non_ddp_tag(tformat, sw_tag);
+ /* the itt need to sent in big-endian order */
+ *hdr_itt = (__force itt_t)htonl(tag);
+
+ cxgbi_tag_debug("new sc 0x%p tag 0x%x/0x%x (itt 0x%x, age 0x%x).\n",
+ sc, tag, *hdr_itt, task->itt, sess->age);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_reserve_itt);
+
+void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt,
+ int *idx, int *age)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ u32 tag = ntohl((__force u32) itt);
+ u32 sw_bits;
+
+ sw_bits = cxgbi_tag_nonrsvd_bits(&cdev->tag_format, tag);
+ if (idx)
+ *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1);
+ if (age)
+ *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK;
+
+ cxgbi_tag_debug("parse tag 0x%x/0x%x, sw 0x%x, itt 0x%x, age 0x%x.\n",
+ tag, itt, sw_bits, idx ? *idx : 0xFFFFF,
+ age ? *age : 0xFF);
+}
+EXPORT_SYMBOL_GPL(cxgbi_parse_pdu_itt);
+
+void cxgbi_cleanup_task(struct iscsi_task *task)
+{
+ struct cxgbi_task_data *tdata = task->dd_data +
+ sizeof(struct iscsi_tcp_task);
+
+ /* never reached the xmit task callout */
+ if (tdata->skb)
+ __kfree_skb(tdata->skb);
+ memset(tdata, 0, sizeof(*tdata));
+
+ cxgbi_release_itt(task, task->hdr_itt);
+ iscsi_tcp_cleanup_task(task);
+}
+EXPORT_SYMBOL_GPL(cxgbi_cleanup_task);
+
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *cls_conn,
+ struct iscsi_stats *stats)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+
+ stats->txdata_octets = conn->txdata_octets;
+ stats->rxdata_octets = conn->rxdata_octets;
+ stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
+ stats->dataout_pdus = conn->dataout_pdus_cnt;
+ stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
+ stats->datain_pdus = conn->datain_pdus_cnt;
+ stats->r2t_pdus = conn->r2t_pdus_cnt;
+ stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
+ stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
+ stats->digest_err = 0;
+ stats->timeout_err = 0;
+ stats->custom_length = 1;
+ strcpy(stats->custom[0].desc, "eh_abort_cnt");
+ stats->custom[0].value = conn->eh_abort_cnt;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_stats);
+
+int cxgbi_conn_max_xmit_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ unsigned int skb_tx_headroom = cdev->skb_tx_headroom;
+ unsigned int max_def = 512 * MAX_SKB_FRAGS;
+ unsigned int max = max(max_def, skb_tx_headroom);
+
+ max = min(cconn->chba->cdev->tx_max_size, max);
+ if (conn->max_xmit_dlength)
+ conn->max_xmit_dlength = min(conn->max_xmit_dlength, max);
+ else
+ conn->max_xmit_dlength = max;
+ cxgbi_align_pdu_size(conn->max_xmit_dlength);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_max_xmit_dlength);
+
+int cxgbi_conn_max_recv_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ unsigned int max = cconn->chba->cdev->rx_max_size;
+
+ cxgbi_align_pdu_size(max);
+
+ if (conn->max_recv_dlength) {
+ if (conn->max_recv_dlength > max) {
+ cxgbi_log_error("MaxRecvDataSegmentLength %u too big."
+ " Need to be <= %u.\n",
+ conn->max_recv_dlength, max);
+ return -EINVAL;
+ }
+ conn->max_recv_dlength = min(conn->max_recv_dlength, max);
+ cxgbi_align_pdu_size(conn->max_recv_dlength);
+ } else
+ conn->max_recv_dlength = max;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_max_recv_dlength);
+
+int cxgbi_set_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buf, int buflen)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_session *session = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ int value, err = 0;
+
+ switch (param) {
+ case ISCSI_PARAM_HDRDGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->hdrdgst_en)
+ err = csk->cdev->ddp_setup_conn_digest(csk, csk->hwtid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_DATADGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->datadgst_en)
+ err = csk->cdev->ddp_setup_conn_digest(csk, csk->hwtid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_MAX_R2T:
+ sscanf(buf, "%d", &value);
+ if (value <= 0 || !is_power_of_2(value))
+ return -EINVAL;
+ if (session->max_r2t == value)
+ break;
+ iscsi_tcp_r2tpool_free(session);
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && iscsi_tcp_r2tpool_alloc(session))
+ return -ENOMEM;
+ case ISCSI_PARAM_MAX_RECV_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_recv_dlength(conn);
+ break;
+ case ISCSI_PARAM_MAX_XMIT_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_xmit_dlength(conn);
+ break;
+ default:
+ return iscsi_set_param(cls_conn, param, buf, buflen);
+ }
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_conn_param);
+
+int cxgbi_get_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buff)
+{
+ struct iscsi_conn *iconn = cls_conn->dd_data;
+ int len;
+
+ switch (param) {
+ case ISCSI_PARAM_CONN_PORT:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buff, "%hu\n", iconn->portal_port);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ case ISCSI_PARAM_CONN_ADDRESS:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buff, "%s\n", iconn->portal_address);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ default:
+ return iscsi_conn_get_param(cls_conn, param, buff);
+ }
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_param);
+
+struct iscsi_cls_conn *
+cxgbi_create_conn(struct iscsi_cls_session *cls_session, u32 cid)
+{
+ struct iscsi_cls_conn *cls_conn;
+ struct iscsi_conn *conn;
+ struct iscsi_tcp_conn *tcp_conn;
+ struct cxgbi_conn *cconn;
+
+ cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*cconn), cid);
+ if (!cls_conn)
+ return NULL;
+
+ conn = cls_conn->dd_data;
+ tcp_conn = conn->dd_data;
+ cconn = tcp_conn->dd_data;
+
+ cconn->iconn = conn;
+ return cls_conn;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_conn);
+
+int cxgbi_bind_conn(struct iscsi_cls_session *cls_session,
+ struct iscsi_cls_conn *cls_conn,
+ u64 transport_eph, int is_leading)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct iscsi_endpoint *ep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_sock *csk;
+ int err;
+
+ ep = iscsi_lookup_endpoint(transport_eph);
+ if (!ep)
+ return -EINVAL;
+
+ /* setup ddp pagesize */
+ cep = ep->dd_data;
+ csk = cep->csk;
+ err = csk->cdev->ddp_setup_conn_host_pgsz(csk, csk->hwtid, 0);
+ if (err < 0)
+ return err;
+
+ err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
+ if (err)
+ return -EINVAL;
+
+ /* calculate the tag idx bits needed for this conn based on cmds_max */
+ cconn->task_idx_bits = (__ilog2_u32(conn->session->cmds_max - 1)) + 1;
+
+ read_lock(&csk->callback_lock);
+ csk->user_data = conn;
+ cconn->chba = cep->chba;
+ cconn->cep = cep;
+ cep->cconn = cconn;
+ read_unlock(&csk->callback_lock);
+
+ cxgbi_conn_max_xmit_dlength(conn);
+ cxgbi_conn_max_recv_dlength(conn);
+
+ spin_lock_bh(&conn->session->lock);
+ sprintf(conn->portal_address, "%pI4", &csk->daddr.sin_addr.s_addr);
+ conn->portal_port = ntohs(csk->daddr.sin_port);
+ spin_unlock_bh(&conn->session->lock);
+
+ /* init recv engine */
+ iscsi_tcp_hdr_recv_prep(tcp_conn);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_bind_conn);
+
+struct iscsi_cls_session *
+cxgbi_create_session(struct iscsi_endpoint *ep, u16 cmds_max, u16 qdepth,
+ u32 initial_cmdsn)
+{
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ struct iscsi_cls_session *cls_session;
+ struct iscsi_session *session;
+
+ if (!ep) {
+ cxgbi_log_error("missing endpoint\n");
+ return NULL;
+ }
+
+ cep = ep->dd_data;
+ chba = cep->chba;
+ shost = chba->shost;
+
+ BUG_ON(chba != iscsi_host_priv(shost));
+
+ cls_session = iscsi_session_setup(chba->cdev->itp, shost,
+ cmds_max, 0,
+ sizeof(struct iscsi_tcp_task) +
+ sizeof(struct cxgbi_task_data),
+ initial_cmdsn, ISCSI_MAX_TARGET);
+ if (!cls_session)
+ return NULL;
+
+ session = cls_session->dd_data;
+ if (iscsi_tcp_r2tpool_alloc(session))
+ goto remove_session;
+
+ return cls_session;
+
+remove_session:
+ iscsi_session_teardown(cls_session);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_session);
+
+void cxgbi_destroy_session(struct iscsi_cls_session *cls_session)
+{
+ iscsi_tcp_r2tpool_free(cls_session->dd_data);
+ iscsi_session_teardown(cls_session);
+}
+EXPORT_SYMBOL_GPL(cxgbi_destroy_session);
+
+int cxgbi_set_host_param(struct Scsi_Host *shost,
+ enum iscsi_host_param param, char *buff, int buflen)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not set host param. "
+ "Netdev for host not set\n");
+ return -ENODEV;
+ }
+
+ cxgbi_api_debug("param %d, buff %s\n", param, buff);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr = in_aton(buff);
+ cxgbi_set_iscsi_ipv4(chba, addr);
+ return 0;
+ }
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ return 0;
+ default:
+ return iscsi_host_set_param(shost, param, buff, buflen);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_host_param);
+
+int cxgbi_get_host_param(struct Scsi_Host *shost,
+ enum iscsi_host_param param, char *buff)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+ int len = 0;
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not set host param. "
+ "Netdev for host not set\n");
+ return -ENODEV;
+ }
+
+ cxgbi_api_debug("hba %s, param %d\n", chba->ndev->name, param);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ len = sysfs_format_mac(buff, chba->ndev->dev_addr, 6);
+ break;
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ len = sprintf(buff, "%s\n", chba->ndev->name);
+ break;
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr;
+
+ addr = cxgbi_get_iscsi_ipv4(chba);
+ len = sprintf(buff, "%pI4", &addr);
+ break;
+ }
+ default:
+ return iscsi_host_get_param(shost, param, buff);
+ }
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_host_param);
+
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *shost,
+ struct sockaddr *dst_addr,
+ int non_blocking)
+{
+ struct iscsi_endpoint *iep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *hba = NULL;
+ struct cxgbi_sock *csk = NULL;
+ struct cxgbi_device *cdev;
+ int err = 0;
+
+ if (shost)
+ hba = iscsi_host_priv(shost);
+
+ cdev = cxgbi_find_cdev(hba ? hba->ndev : NULL,
+ ((struct sockaddr_in *)dst_addr)->sin_addr.s_addr);
+ if (!cdev) {
+ cxgbi_log_info("ep connect no cdev\n");
+ err = -ENOSPC;
+ goto release_conn;
+ }
+
+ csk = cxgbi_sock_create(cdev);
+ if (!csk) {
+ cxgbi_log_info("ep connect OOM\n");
+ err = -ENOMEM;
+ goto release_conn;
+ }
+ err = cxgbi_sock_connect(hba ? hba->ndev : NULL, csk,
+ (struct sockaddr_in *)dst_addr);
+ if (err < 0) {
+ cxgbi_log_info("ep connect failed\n");
+ goto release_conn;
+ }
+
+ hba = cxgbi_hba_find_by_netdev(csk->dst->dev, cdev);
+ if (!hba) {
+ err = -ENOSPC;
+ cxgbi_log_info("Not going through cxgb4i device\n");
+ goto release_conn;
+ }
+
+ if (shost && hba != iscsi_host_priv(shost)) {
+ err = -ENOSPC;
+ cxgbi_log_info("Could not connect through request host %u\n",
+ shost->host_no);
+ goto release_conn;
+ }
+
+ if (cxgbi_sock_is_closing(csk)) {
+ err = -ENOSPC;
+ cxgbi_log_info("ep connect unable to connect\n");
+ goto release_conn;
+ }
+
+ iep = iscsi_create_endpoint(sizeof(*cep));
+ if (!iep) {
+ err = -ENOMEM;
+ cxgbi_log_info("iscsi alloc ep, OOM\n");
+ goto release_conn;
+ }
+
+ cep = iep->dd_data;
+ cep->csk = csk;
+ cep->chba = hba;
+ cxgbi_api_debug("iep 0x%p, cep 0x%p, csk 0x%p, hba 0x%p\n",
+ iep, cep, csk, hba);
+ return iep;
+release_conn:
+ cxgbi_api_debug("conn 0x%p failed, release\n", csk);
+ if (csk)
+ cxgbi_sock_release(csk);
+
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_connect);
+
+int cxgbi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_sock *csk = cep->csk;
+
+ if (!cxgbi_sock_is_established(csk))
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_poll);
+
+void cxgbi_ep_disconnect(struct iscsi_endpoint *ep)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_conn *cconn = cep->cconn;
+
+ if (cconn && cconn->iconn) {
+ iscsi_suspend_tx(cconn->iconn);
+
+ write_lock_bh(&cep->csk->callback_lock);
+ cep->csk->user_data = NULL;
+ cconn->cep = NULL;
+ write_unlock_bh(&cep->csk->callback_lock);
+ }
+
+ cxgbi_sock_release(cep->csk);
+ iscsi_destroy_endpoint(ep);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_disconnect);
+
+struct cxgbi_hba *cxgbi_hba_add(struct cxgbi_device *cdev,
+ unsigned int max_lun,
+ unsigned int max_id,
+ struct scsi_transport_template *stt,
+ struct scsi_host_template *sht,
+ struct net_device *dev)
+{
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ int err;
+
+ shost = iscsi_host_alloc(sht, sizeof(*chba), 1);
+
+ if (!shost) {
+ cxgbi_log_info("cdev 0x%p, ndev 0x%p, host alloc failed\n",
+ cdev, dev);
+ return NULL;
+ }
+
+ shost->transportt = stt;
+ shost->max_lun = max_lun;
+ shost->max_id = max_id;
+ shost->max_channel = 0;
+ shost->max_cmd_len = 16;
+ chba = iscsi_host_priv(shost);
+ cxgbi_log_debug("cdev %p\n", cdev);
+ chba->cdev = cdev;
+ chba->ndev = dev;
+ chba->shost = shost;
+ pci_dev_get(cdev->pdev);
+ err = iscsi_host_add(shost, &cdev->pdev->dev);
+ if (err) {
+ cxgbi_log_info("cdev 0x%p, dev 0x%p, host add failed\n",
+ cdev, dev);
+ goto pci_dev_put;
+ }
+
+ return chba;
+pci_dev_put:
+ pci_dev_put(cdev->pdev);
+ scsi_host_put(shost);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_hba_add);
+
+void cxgbi_hba_remove(struct cxgbi_hba *chba)
+{
+ iscsi_host_remove(chba->shost);
+ pci_dev_put(chba->cdev->pdev);
+ iscsi_host_free(chba->shost);
+}
+EXPORT_SYMBOL_GPL(cxgbi_hba_remove);
+
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
new file mode 100644
index 0000000..880eb9e
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -0,0 +1,577 @@
+/*
+ * libcxgbi.h: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * 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.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#ifndef __LIBCXGBI_H__
+#define __LIBCXGBI_H__
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <scsi/libiscsi_tcp.h>
+
+
+#define cxgbi_log_error(fmt...) printk(KERN_ERR "cxgbi: ERR! " fmt)
+#define cxgbi_log_warn(fmt...) printk(KERN_WARNING "cxgbi: WARN! " fmt)
+#define cxgbi_log_info(fmt...) printk(KERN_INFO "cxgbi: " fmt)
+#define cxgbi_debug_log(fmt, args...) \
+ printk(KERN_INFO "cxgbi: %s - " fmt, __func__ , ## args)
+
+
+#ifdef __DEBUG_CXGBI__
+#define cxgbi_log_debug cxgbi_debug_log
+#else
+#define cxgbi_log_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_TAG__
+#define cxgbi_tag_debug cxgbi_log_debug
+#else
+#define cxgbi_tag_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_API__
+#define cxgbi_api_debug cxgbi_log_debug
+#else
+#define cxgbi_api_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_CONN__
+#define cxgbi_conn_debug cxgbi_log_debug
+#else
+#define cxgbi_conn_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_TX__
+#define cxgbi_tx_debug cxgbi_log_debug
+#else
+#define cxgbi_tx_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_RX__
+#define cxgbi_rx_debug cxgbi_log_debug
+#else
+#define cxgbi_rx_debug(fmt...)
+#endif
+
+/* always allocate rooms for AHS */
+#define SKB_TX_PDU_HEADER_LEN \
+ (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE)
+
+#define ISCSI_PDU_NONPAYLOAD_LEN 312 /* bhs(48) + ahs(256) + digest(8)*/
+#define ULP2_MAX_PKT_SIZE 16224
+#define ULP2_MAX_PDU_PAYLOAD \
+ (ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN)
+
+#define PPOD_PAGES_MAX 4
+#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */
+
+/*
+ * align pdu size to multiple of 512 for better performance
+ */
+#define cxgbi_align_pdu_size(n) do { n = (n) & (~511); } while (0)
+
+/*
+ * struct pagepod_hdr, pagepod - pagepod format
+ */
+struct pagepod_hdr {
+ unsigned int vld_tid;
+ unsigned int pgsz_tag_clr;
+ unsigned int max_offset;
+ unsigned int page_offset;
+ unsigned long long rsvd;
+};
+
+struct pagepod {
+ struct pagepod_hdr hdr;
+ unsigned long long addr[PPOD_PAGES_MAX + 1];
+};
+
+struct cxgbi_tag_format {
+ unsigned char sw_bits;
+ unsigned char rsvd_bits;
+ unsigned char rsvd_shift;
+ unsigned char filler[1];
+ unsigned int rsvd_mask;
+};
+
+struct cxgbi_gather_list {
+ unsigned int tag;
+ unsigned int length;
+ unsigned int offset;
+ unsigned int nelem;
+ struct page **pages;
+ dma_addr_t phys_addr[0];
+};
+
+/*
+ * sge_opaque_hdr -
+ * Opaque version of structure the SGE stores at skb->head of TX_DATA packets
+ * and for which we must reserve space.
+ */
+struct sge_opaque_hdr {
+ void *dev;
+ dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+struct cxgbi_sock {
+ struct net_device *egdev;
+ struct cxgbi_device *cdev;
+
+ unsigned long flags;
+ unsigned short rss_qid;
+ unsigned short txq_idx;
+
+ unsigned int hwtid;
+ unsigned int atid;
+
+ unsigned int tx_chan;
+ unsigned int rx_chan;
+ unsigned int mss_idx;
+ unsigned int smac_idx;
+ unsigned char port_id;
+
+ unsigned char hcrc_len;
+ unsigned char dcrc_len;
+
+ void *l2t;
+
+ int wr_max_cred;
+ int wr_cred;
+ int wr_una_cred;
+
+ struct sk_buff *wr_pending_head;
+ struct sk_buff *wr_pending_tail;
+ struct sk_buff *cpl_close;
+ struct sk_buff *cpl_abort_req;
+ struct sk_buff *cpl_abort_rpl;
+ struct sk_buff *skb_ulp_lhdr;
+ spinlock_t lock;
+ struct kref refcnt;
+ unsigned int state;
+ struct sockaddr_in saddr;
+ struct sockaddr_in daddr;
+ struct dst_entry *dst;
+ struct sk_buff_head receive_queue;
+ struct sk_buff_head write_queue;
+ struct timer_list retry_timer;
+ int err;
+ rwlock_t callback_lock;
+ void *user_data;
+
+ u32 rcv_nxt;
+ u32 copied_seq;
+ u32 rcv_wup;
+ u32 snd_nxt;
+ u32 snd_una;
+ u32 write_seq;
+};
+
+enum cxgbi_sock_states{
+ CTP_CONNECTING = 1,
+ CTP_ESTABLISHED,
+ CTP_ACTIVE_CLOSE,
+ CTP_PASSIVE_CLOSE,
+ CTP_CLOSE_WAIT_1,
+ CTP_CLOSE_WAIT_2,
+ CTP_ABORTING,
+ CTP_CLOSED,
+};
+
+enum cxgbi_sock_flags {
+ CTPF_ABORT_RPL_RCVD = 1,/*received one ABORT_RPL_RSS message */
+ CTPF_ABORT_REQ_RCVD, /*received one ABORT_REQ_RSS message */
+ CTPF_ABORT_RPL_PENDING, /* expecting an abort reply */
+ CTPF_TX_DATA_SENT, /* already sent a TX_DATA WR */
+ CTPF_ACTIVE_CLOSE_NEEDED, /* need to be closed */
+ CTPF_MSG_COALESCED,
+ CTPF_OFFLOAD_DOWN, /* offload function off */
+};
+
+enum cxgbi_skcb_flags {
+ CTP_SKCBF_NEED_HDR = 1 << 0, /* packet needs a header */
+ CTP_SKCBF_NO_APPEND = 1 << 1, /* don't grow this skb */
+ CTP_SKCBF_COMPL = 1 << 2, /* request WR completion */
+ CTP_SKCBF_HDR_RCVD = 1 << 3, /* recieved header pdu */
+ CTP_SKCBF_DATA_RCVD = 1 << 4, /* recieved data pdu */
+ CTP_SKCBF_STATUS_RCVD = 1 << 5, /* recieved ddp status */
+};
+
+static inline void cxgbi_sock_set_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __set_bit(flag, &csk->flags);
+ cxgbi_conn_debug("csk 0x%p, set %d, state %u, flags 0x%lu\n",
+ csk, flag, csk->state, csk->flags);
+}
+
+static inline void cxgbi_sock_clear_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __clear_bit(flag, &csk->flags);
+ cxgbi_conn_debug("csk 0x%p, clear %d, state %u, flags 0x%lu\n",
+ csk, flag, csk->state, csk->flags);
+}
+
+static inline int cxgbi_sock_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ if (csk == NULL)
+ return 0;
+
+ return test_bit(flag, &csk->flags);
+}
+
+static inline void cxgbi_sock_set_state(struct cxgbi_sock *csk, int state)
+{
+ csk->state = state;
+}
+
+static inline void cxgbi_sock_hold(struct cxgbi_sock *csk)
+{
+ kref_get(&csk->refcnt);
+}
+
+static inline void cxgbi_clean_sock(struct kref *kref)
+{
+ struct cxgbi_sock *csk = container_of(kref,
+ struct cxgbi_sock,
+ refcnt);
+ if (csk) {
+ cxgbi_log_debug("free csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+ kfree(csk);
+ }
+}
+
+static inline void cxgbi_sock_put(struct cxgbi_sock *csk)
+{
+ if (csk)
+ kref_put(&csk->refcnt, cxgbi_clean_sock);
+}
+
+static inline unsigned int cxgbi_sock_is_closing(const struct cxgbi_sock *csk)
+{
+ return csk->state >= CTP_ACTIVE_CLOSE;
+}
+
+static inline unsigned int cxgbi_sock_is_established(
+ const struct cxgbi_sock *csk)
+{
+ return csk->state == CTP_ESTABLISHED;
+}
+
+static inline void cxgbi_sock_purge_write_queue(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(&csk->write_queue)))
+ __kfree_skb(skb);
+}
+
+static inline int cxgbi_sock_compute_wscale(int win)
+{
+ int wscale = 0;
+ while (wscale < 14 && (65535 << wscale) < win)
+ wscale++;
+ return wscale;
+}
+
+
+struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *);
+int cxgbi_sock_connect(struct net_device *, struct cxgbi_sock *,
+ struct sockaddr_in *);
+int cxgbi_sock_get_port(struct cxgbi_sock *);
+void cxgbi_sock_put_port(struct cxgbi_sock *);
+void cxgbi_sock_conn_closing(struct cxgbi_sock *);
+void cxgbi_sock_closed(struct cxgbi_sock *);
+void cxgbi_sock_release(struct cxgbi_sock *);
+unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *, unsigned short);
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *, unsigned int);
+
+struct cxgbi_hba {
+ struct net_device *ndev;
+ struct Scsi_Host *shost;
+ struct cxgbi_device *cdev;
+ __be32 ipv4addr;
+};
+
+struct cxgbi_ports_map {
+ unsigned int max_connect;
+ unsigned short sport_base;
+ spinlock_t lock;
+ unsigned int next;
+ struct cxgbi_sock *port_csk[0];
+};
+
+struct cxgbi_device {
+ struct list_head list_head;
+ char *name;
+ struct net_device **ports;
+ struct cxgbi_hba **hbas;
+ const unsigned short *mtus;
+ unsigned char nmtus;
+ unsigned char nports;
+ struct pci_dev *pdev;
+
+ unsigned int skb_tx_headroom;
+ unsigned int skb_extra_headroom;
+ unsigned int tx_max_size;
+ unsigned int rx_max_size;
+ struct page *pad_page;
+ struct cxgbi_ports_map *pmap;
+ struct iscsi_transport *itp;
+ struct cxgbi_tag_format tag_format;
+
+ int (*ddp_tag_reserve)(struct cxgbi_sock *, unsigned int,
+ struct cxgbi_tag_format *, u32 *,
+ struct cxgbi_gather_list *, gfp_t);
+ void (*ddp_tag_release)(struct cxgbi_sock *, u32);
+ struct cxgbi_gather_list* (*ddp_make_gl)(unsigned int,
+ struct scatterlist *,
+ unsigned int,
+ struct pci_dev *,
+ gfp_t);
+ void (*ddp_release_gl)(struct cxgbi_gather_list *, struct pci_dev *);
+ int (*ddp_setup_conn_digest)(struct cxgbi_sock *,
+ unsigned int, int, int, int);
+ int (*ddp_setup_conn_host_pgsz)(struct cxgbi_sock *,
+ unsigned int, int);
+ __u16 (*get_skb_ulp_mode)(struct sk_buff *);
+ __u16 (*get_skb_flags)(struct sk_buff *);
+ __u32 (*get_skb_tcp_seq)(struct sk_buff *);
+ __u32 (*get_skb_rx_pdulen)(struct sk_buff *);
+ void (*set_skb_txmode)(struct sk_buff *, int, int);
+
+ void (*release_offload_resources)(struct cxgbi_sock *);
+ int (*sock_send_pdus)(struct cxgbi_sock *, struct sk_buff *);
+ void (*sock_rx_credits)(struct cxgbi_sock *, int);
+ void (*send_abort_req)(struct cxgbi_sock *);
+ void (*send_close_req)(struct cxgbi_sock *);
+ int (*alloc_cpl_skbs)(struct cxgbi_sock *);
+ int (*init_act_open)(struct cxgbi_sock *, struct net_device *);
+
+ unsigned long dd_data[0];
+};
+
+static inline void *cxgbi_cdev_priv(struct cxgbi_device *cdev)
+{
+ return (void *)cdev->dd_data;
+}
+
+struct cxgbi_device *cxgbi_device_register(unsigned int, unsigned int);
+void cxgbi_device_unregister(struct cxgbi_device *);
+
+struct cxgbi_conn {
+ struct list_head list_head;
+ struct cxgbi_endpoint *cep;
+ struct iscsi_conn *iconn;
+ struct cxgbi_hba *chba;
+ u32 task_idx_bits;
+};
+
+struct cxgbi_endpoint {
+ struct cxgbi_conn *cconn;
+ struct cxgbi_hba *chba;
+ struct cxgbi_sock *csk;
+};
+
+#define MAX_PDU_FRAGS ((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512)
+struct cxgbi_task_data {
+ unsigned short nr_frags;
+ skb_frag_t frags[MAX_PDU_FRAGS];
+ struct sk_buff *skb;
+ unsigned int offset;
+ unsigned int count;
+ unsigned int sgoffset;
+};
+
+static inline int cxgbi_is_ddp_tag(struct cxgbi_tag_format *tformat, u32 tag)
+{
+ return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1)));
+}
+
+static inline int cxgbi_sw_tag_usable(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ sw_tag >>= (32 - tformat->rsvd_bits);
+ return !sw_tag;
+}
+
+static inline u32 cxgbi_set_non_ddp_tag(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+
+ u32 mask = (1 << shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & ((1 << shift) - 1);
+ u32 v2 = (sw_tag >> (shift - 1)) << shift;
+
+ return v2 | v1 | 1 << shift;
+ }
+
+ return sw_tag | 1 << shift;
+}
+
+static inline u32 cxgbi_ddp_tag_base(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ u32 mask = (1 << tformat->rsvd_shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & mask;
+ u32 v2 = sw_tag >> tformat->rsvd_shift;
+
+ v2 <<= tformat->rsvd_bits + tformat->rsvd_shift;
+
+ return v2 | v1;
+ }
+
+ return sw_tag;
+}
+
+static inline u32 cxgbi_tag_rsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ if (cxgbi_is_ddp_tag(tformat, tag))
+ return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask;
+
+ return 0;
+}
+
+static inline u32 cxgbi_tag_nonrsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+ u32 v1, v2;
+
+ if (cxgbi_is_ddp_tag(tformat, tag)) {
+ v1 = tag & ((1 << tformat->rsvd_shift) - 1);
+ v2 = (tag >> (shift + 1)) << tformat->rsvd_shift;
+ } else {
+ u32 mask = (1 << shift) - 1;
+ tag &= ~(1 << shift);
+ v1 = tag & mask;
+ v2 = (tag >> 1) & ~mask;
+ }
+ return v1 | v2;
+}
+
+static inline void *cxgbi_alloc_big_mem(unsigned int size,
+ gfp_t gfp)
+{
+ void *p = kmalloc(size, gfp);
+ if (!p)
+ p = vmalloc(size);
+ if (p)
+ memset(p, 0, size);
+ return p;
+}
+
+static inline void cxgbi_free_big_mem(void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+
+#define RX_DDP_STATUS_IPP_SHIFT 27 /* invalid pagepod */
+#define RX_DDP_STATUS_TID_SHIFT 26 /* tid mismatch */
+#define RX_DDP_STATUS_COLOR_SHIFT 25 /* color mismatch */
+#define RX_DDP_STATUS_OFFSET_SHIFT 24 /* offset mismatch */
+#define RX_DDP_STATUS_ULIMIT_SHIFT 23 /* ulimit error */
+#define RX_DDP_STATUS_TAG_SHIFT 22 /* tag mismatch */
+#define RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */
+#define RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */
+#define RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */
+#define RX_DDP_STATUS_PPP_SHIFT 18 /* pagepod parity error */
+#define RX_DDP_STATUS_LLIMIT_SHIFT 17 /* llimit error */
+#define RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */
+#define RX_DDP_STATUS_PMM_SHIFT 15 /* pagepod mismatch */
+
+
+#define ULP2_FLAG_DATA_READY 0x1
+#define ULP2_FLAG_DATA_DDPED 0x2
+#define ULP2_FLAG_HCRC_ERROR 0x4
+#define ULP2_FLAG_DCRC_ERROR 0x8
+#define ULP2_FLAG_PAD_ERROR 0x10
+
+struct cxgbi_hba *cxgbi_hba_find_by_netdev(struct net_device *dev,
+ struct cxgbi_device *cdev);
+struct cxgbi_hba *cxgbi_hba_add(struct cxgbi_device *,
+ unsigned int, unsigned int,
+ struct scsi_transport_template *,
+ struct scsi_host_template *,
+ struct net_device *);
+void cxgbi_hba_remove(struct cxgbi_hba *);
+
+
+int cxgbi_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt);
+void cxgbi_release_itt(struct iscsi_task *task, itt_t hdr_itt);
+void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt,
+ int *idx, int *age);
+void cxgbi_cleanup_task(struct iscsi_task *task);
+
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *);
+void cxgbi_conn_tx_open(struct cxgbi_sock *);
+int cxgbi_conn_init_pdu(struct iscsi_task *, unsigned int , unsigned int);
+int cxgbi_conn_alloc_pdu(struct iscsi_task *, u8);
+int cxgbi_conn_xmit_pdu(struct iscsi_task *);
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *, struct iscsi_stats *);
+int cxgbi_conn_max_xmit_dlength(struct iscsi_conn *);
+int cxgbi_conn_max_recv_dlength(struct iscsi_conn *);
+int cxgbi_set_conn_param(struct iscsi_cls_conn *,
+ enum iscsi_param, char *, int);
+int cxgbi_get_conn_param(struct iscsi_cls_conn *, enum iscsi_param, char *);
+struct iscsi_cls_conn *cxgbi_create_conn(struct iscsi_cls_session *, u32);
+int cxgbi_bind_conn(struct iscsi_cls_session *,
+ struct iscsi_cls_conn *, u64, int);
+void cxgbi_destroy_session(struct iscsi_cls_session *);
+struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *,
+ u16, u16, u32);
+int cxgbi_set_host_param(struct Scsi_Host *,
+ enum iscsi_host_param, char *, int);
+int cxgbi_get_host_param(struct Scsi_Host *, enum iscsi_host_param, char *);
+
+
+int cxgbi_pdu_init(struct cxgbi_device *);
+void cxgbi_pdu_cleanup(struct cxgbi_device *);
+
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *,
+ struct sockaddr *, int);
+int cxgbi_ep_poll(struct iscsi_endpoint *, int);
+void cxgbi_ep_disconnect(struct iscsi_endpoint *);
+
+static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr)
+{
+ chba->ipv4addr = ipaddr;
+}
+
+static inline __be32 cxgbi_get_iscsi_ipv4(struct cxgbi_hba *chba)
+{
+ return chba->ipv4addr;
+}
+
+struct cxgbi_device *cxgbi_device_alloc(unsigned int dd_size);
+void cxgbi_device_free(struct cxgbi_device *cdev);
+void cxgbi_device_add(struct list_head *list_head);
+void cxgbi_device_remove(struct cxgbi_device *cdev);
+
+#endif /*__LIBCXGBI_H__*/
+
--
1.6.6.1
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox