Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 758 insertions, 0 deletions

diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
new file mode 100644
index 000000000..c7891cc84
--- /dev/null
+++ b/drivers/ata/sata_via.c
@@ -0,0 +1,758 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  sata_via.c - VIA Serial ATA controllers
+ *
+ *  Maintained by:  Tejun Heo <tj@kernel.org>
+ * 		   Please ALWAYS copy linux-ide@vger.kernel.org
+ *		   on emails.
+ *
+ *  Copyright 2003-2004 Red Hat, Inc.  All rights reserved.
+ *  Copyright 2003-2004 Jeff Garzik
+ *
+ *  libata documentation is available via 'make {ps|pdf}docs',
+ *  as Documentation/driver-api/libata.rst
+ *
+ *  Hardware documentation available under NDA.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <scsi/scsi.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/libata.h>
+
+#define DRV_NAME	"sata_via"
+#define DRV_VERSION	"2.6"
+
+/*
+ * vt8251 is different from other sata controllers of VIA.  It has two
+ * channels, each channel has both Master and Slave slot.
+ */
+enum board_ids_enum {
+	vt6420,
+	vt6421,
+	vt8251,
+};
+
+enum {
+	SATA_CHAN_ENAB		= 0x40, /* SATA channel enable */
+	SATA_INT_GATE		= 0x41, /* SATA interrupt gating */
+	SATA_NATIVE_MODE	= 0x42, /* Native mode enable */
+	SVIA_MISC_3		= 0x46,	/* Miscellaneous Control III */
+	PATA_UDMA_TIMING	= 0xB3, /* PATA timing for DMA/ cable detect */
+	PATA_PIO_TIMING		= 0xAB, /* PATA timing register */
+
+	PORT0			= (1 << 1),
+	PORT1			= (1 << 0),
+	ALL_PORTS		= PORT0 | PORT1,
+
+	NATIVE_MODE_ALL		= (1 << 7) | (1 << 6) | (1 << 5) | (1 << 4),
+
+	SATA_EXT_PHY		= (1 << 6), /* 0==use PATA, 1==ext phy */
+
+	SATA_HOTPLUG		= (1 << 5), /* enable IRQ on hotplug */
+};
+
+struct svia_priv {
+	bool			wd_workaround;
+};
+
+static int vt6420_hotplug;
+module_param_named(vt6420_hotplug, vt6420_hotplug, int, 0644);
+MODULE_PARM_DESC(vt6420_hotplug, "Enable hot-plug support for VT6420 (0=Don't support, 1=support)");
+
+static int svia_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
+#ifdef CONFIG_PM_SLEEP
+static int svia_pci_device_resume(struct pci_dev *pdev);
+#endif
+static int svia_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val);
+static int svia_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val);
+static int vt8251_scr_read(struct ata_link *link, unsigned int scr, u32 *val);
+static int vt8251_scr_write(struct ata_link *link, unsigned int scr, u32 val);
+static void svia_tf_load(struct ata_port *ap, const struct ata_taskfile *tf);
+static void svia_noop_freeze(struct ata_port *ap);
+static int vt6420_prereset(struct ata_link *link, unsigned long deadline);
+static void vt6420_bmdma_start(struct ata_queued_cmd *qc);
+static int vt6421_pata_cable_detect(struct ata_port *ap);
+static void vt6421_set_pio_mode(struct ata_port *ap, struct ata_device *adev);
+static void vt6421_set_dma_mode(struct ata_port *ap, struct ata_device *adev);
+static void vt6421_error_handler(struct ata_port *ap);
+
+static const struct pci_device_id svia_pci_tbl[] = {
+	{ PCI_VDEVICE(VIA, 0x5337), vt6420 },
+	{ PCI_VDEVICE(VIA, 0x0591), vt6420 }, /* 2 sata chnls (Master) */
+	{ PCI_VDEVICE(VIA, 0x3149), vt6420 }, /* 2 sata chnls (Master) */
+	{ PCI_VDEVICE(VIA, 0x3249), vt6421 }, /* 2 sata chnls, 1 pata chnl */
+	{ PCI_VDEVICE(VIA, 0x5372), vt6420 },
+	{ PCI_VDEVICE(VIA, 0x7372), vt6420 },
+	{ PCI_VDEVICE(VIA, 0x5287), vt8251 }, /* 2 sata chnls (Master/Slave) */
+	{ PCI_VDEVICE(VIA, 0x9000), vt8251 },
+
+	{ }	/* terminate list */
+};
+
+static struct pci_driver svia_pci_driver = {
+	.name			= DRV_NAME,
+	.id_table		= svia_pci_tbl,
+	.probe			= svia_init_one,
+#ifdef CONFIG_PM_SLEEP
+	.suspend		= ata_pci_device_suspend,
+	.resume			= svia_pci_device_resume,
+#endif
+	.remove			= ata_pci_remove_one,
+};
+
+static struct scsi_host_template svia_sht = {
+	ATA_BMDMA_SHT(DRV_NAME),
+};
+
+static struct ata_port_operations svia_base_ops = {
+	.inherits		= &ata_bmdma_port_ops,
+	.sff_tf_load		= svia_tf_load,
+};
+
+static struct ata_port_operations vt6420_sata_ops = {
+	.inherits		= &svia_base_ops,
+	.freeze			= svia_noop_freeze,
+	.prereset		= vt6420_prereset,
+	.bmdma_start		= vt6420_bmdma_start,
+};
+
+static struct ata_port_operations vt6421_pata_ops = {
+	.inherits		= &svia_base_ops,
+	.cable_detect		= vt6421_pata_cable_detect,
+	.set_piomode		= vt6421_set_pio_mode,
+	.set_dmamode		= vt6421_set_dma_mode,
+};
+
+static struct ata_port_operations vt6421_sata_ops = {
+	.inherits		= &svia_base_ops,
+	.scr_read		= svia_scr_read,
+	.scr_write		= svia_scr_write,
+	.error_handler		= vt6421_error_handler,
+};
+
+static struct ata_port_operations vt8251_ops = {
+	.inherits		= &svia_base_ops,
+	.hardreset		= sata_std_hardreset,
+	.scr_read		= vt8251_scr_read,
+	.scr_write		= vt8251_scr_write,
+};
+
+static const struct ata_port_info vt6420_port_info = {
+	.flags		= ATA_FLAG_SATA,
+	.pio_mask	= ATA_PIO4,
+	.mwdma_mask	= ATA_MWDMA2,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &vt6420_sata_ops,
+};
+
+static const struct ata_port_info vt6421_sport_info = {
+	.flags		= ATA_FLAG_SATA,
+	.pio_mask	= ATA_PIO4,
+	.mwdma_mask	= ATA_MWDMA2,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &vt6421_sata_ops,
+};
+
+static const struct ata_port_info vt6421_pport_info = {
+	.flags		= ATA_FLAG_SLAVE_POSS,
+	.pio_mask	= ATA_PIO4,
+	/* No MWDMA */
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &vt6421_pata_ops,
+};
+
+static const struct ata_port_info vt8251_port_info = {
+	.flags		= ATA_FLAG_SATA | ATA_FLAG_SLAVE_POSS,
+	.pio_mask	= ATA_PIO4,
+	.mwdma_mask	= ATA_MWDMA2,
+	.udma_mask	= ATA_UDMA6,
+	.port_ops	= &vt8251_ops,
+};
+
+MODULE_AUTHOR("Jeff Garzik");
+MODULE_DESCRIPTION("SCSI low-level driver for VIA SATA controllers");
+MODULE_LICENSE("GPL");
+MODULE_DEVICE_TABLE(pci, svia_pci_tbl);
+MODULE_VERSION(DRV_VERSION);
+
+static int svia_scr_read(struct ata_link *link, unsigned int sc_reg, u32 *val)
+{
+	if (sc_reg > SCR_CONTROL)
+		return -EINVAL;
+	*val = ioread32(link->ap->ioaddr.scr_addr + (4 * sc_reg));
+	return 0;
+}
+
+static int svia_scr_write(struct ata_link *link, unsigned int sc_reg, u32 val)
+{
+	if (sc_reg > SCR_CONTROL)
+		return -EINVAL;
+	iowrite32(val, link->ap->ioaddr.scr_addr + (4 * sc_reg));
+	return 0;
+}
+
+static int vt8251_scr_read(struct ata_link *link, unsigned int scr, u32 *val)
+{
+	static const u8 ipm_tbl[] = { 1, 2, 6, 0 };
+	struct pci_dev *pdev = to_pci_dev(link->ap->host->dev);
+	int slot = 2 * link->ap->port_no + link->pmp;
+	u32 v = 0;
+	u8 raw;
+
+	switch (scr) {
+	case SCR_STATUS:
+		pci_read_config_byte(pdev, 0xA0 + slot, &raw);
+
+		/* read the DET field, bit0 and 1 of the config byte */
+		v |= raw & 0x03;
+
+		/* read the SPD field, bit4 of the configure byte */
+		if (raw & (1 << 4))
+			v |= 0x02 << 4;
+		else
+			v |= 0x01 << 4;
+
+		/* read the IPM field, bit2 and 3 of the config byte */
+		v |= ipm_tbl[(raw >> 2) & 0x3];
+		break;
+
+	case SCR_ERROR:
+		/* devices other than 5287 uses 0xA8 as base */
+		WARN_ON(pdev->device != 0x5287);
+		pci_read_config_dword(pdev, 0xB0 + slot * 4, &v);
+		break;
+
+	case SCR_CONTROL:
+		pci_read_config_byte(pdev, 0xA4 + slot, &raw);
+
+		/* read the DET field, bit0 and bit1 */
+		v |= ((raw & 0x02) << 1) | (raw & 0x01);
+
+		/* read the IPM field, bit2 and bit3 */
+		v |= ((raw >> 2) & 0x03) << 8;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	*val = v;
+	return 0;
+}
+
+static int vt8251_scr_write(struct ata_link *link, unsigned int scr, u32 val)
+{
+	struct pci_dev *pdev = to_pci_dev(link->ap->host->dev);
+	int slot = 2 * link->ap->port_no + link->pmp;
+	u32 v = 0;
+
+	switch (scr) {
+	case SCR_ERROR:
+		/* devices other than 5287 uses 0xA8 as base */
+		WARN_ON(pdev->device != 0x5287);
+		pci_write_config_dword(pdev, 0xB0 + slot * 4, val);
+		return 0;
+
+	case SCR_CONTROL:
+		/* set the DET field */
+		v |= ((val & 0x4) >> 1) | (val & 0x1);
+
+		/* set the IPM field */
+		v |= ((val >> 8) & 0x3) << 2;
+
+		pci_write_config_byte(pdev, 0xA4 + slot, v);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+/**
+ *	svia_tf_load - send taskfile registers to host controller
+ *	@ap: Port to which output is sent
+ *	@tf: ATA taskfile register set
+ *
+ *	Outputs ATA taskfile to standard ATA host controller.
+ *
+ *	This is to fix the internal bug of via chipsets, which will
+ *	reset the device register after changing the IEN bit on ctl
+ *	register.
+ */
+static void svia_tf_load(struct ata_port *ap, const struct ata_taskfile *tf)
+{
+	struct ata_taskfile ttf;
+
+	if (tf->ctl != ap->last_ctl)  {
+		ttf = *tf;
+		ttf.flags |= ATA_TFLAG_DEVICE;
+		tf = &ttf;
+	}
+	ata_sff_tf_load(ap, tf);
+}
+
+static void svia_noop_freeze(struct ata_port *ap)
+{
+	/* Some VIA controllers choke if ATA_NIEN is manipulated in
+	 * certain way.  Leave it alone and just clear pending IRQ.
+	 */
+	ap->ops->sff_check_status(ap);
+	ata_bmdma_irq_clear(ap);
+}
+
+/**
+ *	vt6420_prereset - prereset for vt6420
+ *	@link: target ATA link
+ *	@deadline: deadline jiffies for the operation
+ *
+ *	SCR registers on vt6420 are pieces of shit and may hang the
+ *	whole machine completely if accessed with the wrong timing.
+ *	To avoid such catastrophe, vt6420 doesn't provide generic SCR
+ *	access operations, but uses SStatus and SControl only during
+ *	boot probing in controlled way.
+ *
+ *	As the old (pre EH update) probing code is proven to work, we
+ *	strictly follow the access pattern.
+ *
+ *	LOCKING:
+ *	Kernel thread context (may sleep)
+ *
+ *	RETURNS:
+ *	0 on success, -errno otherwise.
+ */
+static int vt6420_prereset(struct ata_link *link, unsigned long deadline)
+{
+	struct ata_port *ap = link->ap;
+	struct ata_eh_context *ehc = &ap->link.eh_context;
+	unsigned long timeout = jiffies + (HZ * 5);
+	u32 sstatus, scontrol;
+	int online;
+
+	/* don't do any SCR stuff if we're not loading */
+	if (!(ap->pflags & ATA_PFLAG_LOADING))
+		goto skip_scr;
+
+	/* Resume phy.  This is the old SATA resume sequence */
+	svia_scr_write(link, SCR_CONTROL, 0x300);
+	svia_scr_read(link, SCR_CONTROL, &scontrol); /* flush */
+
+	/* wait for phy to become ready, if necessary */
+	do {
+		ata_msleep(link->ap, 200);
+		svia_scr_read(link, SCR_STATUS, &sstatus);
+		if ((sstatus & 0xf) != 1)
+			break;
+	} while (time_before(jiffies, timeout));
+
+	/* open code sata_print_link_status() */
+	svia_scr_read(link, SCR_STATUS, &sstatus);
+	svia_scr_read(link, SCR_CONTROL, &scontrol);
+
+	online = (sstatus & 0xf) == 0x3;
+
+	ata_port_info(ap,
+		      "SATA link %s 1.5 Gbps (SStatus %X SControl %X)\n",
+		      online ? "up" : "down", sstatus, scontrol);
+
+	/* SStatus is read one more time */
+	svia_scr_read(link, SCR_STATUS, &sstatus);
+
+	if (!online) {
+		/* tell EH to bail */
+		ehc->i.action &= ~ATA_EH_RESET;
+		return 0;
+	}
+
+ skip_scr:
+	/* wait for !BSY */
+	ata_sff_wait_ready(link, deadline);
+
+	return 0;
+}
+
+static void vt6420_bmdma_start(struct ata_queued_cmd *qc)
+{
+	struct ata_port *ap = qc->ap;
+	if ((qc->tf.command == ATA_CMD_PACKET) &&
+	    (qc->scsicmd->sc_data_direction == DMA_TO_DEVICE)) {
+		/* Prevents corruption on some ATAPI burners */
+		ata_sff_pause(ap);
+	}
+	ata_bmdma_start(qc);
+}
+
+static int vt6421_pata_cable_detect(struct ata_port *ap)
+{
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u8 tmp;
+
+	pci_read_config_byte(pdev, PATA_UDMA_TIMING, &tmp);
+	if (tmp & 0x10)
+		return ATA_CBL_PATA40;
+	return ATA_CBL_PATA80;
+}
+
+static void vt6421_set_pio_mode(struct ata_port *ap, struct ata_device *adev)
+{
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	static const u8 pio_bits[] = { 0xA8, 0x65, 0x65, 0x31, 0x20 };
+	pci_write_config_byte(pdev, PATA_PIO_TIMING - adev->devno,
+			      pio_bits[adev->pio_mode - XFER_PIO_0]);
+}
+
+static void vt6421_set_dma_mode(struct ata_port *ap, struct ata_device *adev)
+{
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	static const u8 udma_bits[] = { 0xEE, 0xE8, 0xE6, 0xE4, 0xE2, 0xE1, 0xE0, 0xE0 };
+	pci_write_config_byte(pdev, PATA_UDMA_TIMING - adev->devno,
+			      udma_bits[adev->dma_mode - XFER_UDMA_0]);
+}
+
+static const unsigned int svia_bar_sizes[] = {
+	8, 4, 8, 4, 16, 256
+};
+
+static const unsigned int vt6421_bar_sizes[] = {
+	16, 16, 16, 16, 32, 128
+};
+
+static void __iomem *svia_scr_addr(void __iomem *addr, unsigned int port)
+{
+	return addr + (port * 128);
+}
+
+static void __iomem *vt6421_scr_addr(void __iomem *addr, unsigned int port)
+{
+	return addr + (port * 64);
+}
+
+static void vt6421_init_addrs(struct ata_port *ap)
+{
+	void __iomem * const * iomap = ap->host->iomap;
+	void __iomem *reg_addr = iomap[ap->port_no];
+	void __iomem *bmdma_addr = iomap[4] + (ap->port_no * 8);
+	struct ata_ioports *ioaddr = &ap->ioaddr;
+
+	ioaddr->cmd_addr = reg_addr;
+	ioaddr->altstatus_addr =
+	ioaddr->ctl_addr = (void __iomem *)
+		((unsigned long)(reg_addr + 8) | ATA_PCI_CTL_OFS);
+	ioaddr->bmdma_addr = bmdma_addr;
+	ioaddr->scr_addr = vt6421_scr_addr(iomap[5], ap->port_no);
+
+	ata_sff_std_ports(ioaddr);
+
+	ata_port_pbar_desc(ap, ap->port_no, -1, "port");
+	ata_port_pbar_desc(ap, 4, ap->port_no * 8, "bmdma");
+}
+
+static int vt6420_prepare_host(struct pci_dev *pdev, struct ata_host **r_host)
+{
+	const struct ata_port_info *ppi[] = { &vt6420_port_info, NULL };
+	struct ata_host *host;
+	int rc;
+
+	if (vt6420_hotplug) {
+		ppi[0]->port_ops->scr_read = svia_scr_read;
+		ppi[0]->port_ops->scr_write = svia_scr_write;
+	}
+
+	rc = ata_pci_bmdma_prepare_host(pdev, ppi, &host);
+	if (rc)
+		return rc;
+	*r_host = host;
+
+	rc = pcim_iomap_regions(pdev, 1 << 5, DRV_NAME);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to iomap PCI BAR 5\n");
+		return rc;
+	}
+
+	host->ports[0]->ioaddr.scr_addr = svia_scr_addr(host->iomap[5], 0);
+	host->ports[1]->ioaddr.scr_addr = svia_scr_addr(host->iomap[5], 1);
+
+	return 0;
+}
+
+static int vt6421_prepare_host(struct pci_dev *pdev, struct ata_host **r_host)
+{
+	const struct ata_port_info *ppi[] =
+		{ &vt6421_sport_info, &vt6421_sport_info, &vt6421_pport_info };
+	struct ata_host *host;
+	int i, rc;
+
+	*r_host = host = ata_host_alloc_pinfo(&pdev->dev, ppi, ARRAY_SIZE(ppi));
+	if (!host) {
+		dev_err(&pdev->dev, "failed to allocate host\n");
+		return -ENOMEM;
+	}
+
+	rc = pcim_iomap_regions(pdev, 0x3f, DRV_NAME);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to request/iomap PCI BARs (errno=%d)\n",
+			rc);
+		return rc;
+	}
+	host->iomap = pcim_iomap_table(pdev);
+
+	for (i = 0; i < host->n_ports; i++)
+		vt6421_init_addrs(host->ports[i]);
+
+	return dma_set_mask_and_coherent(&pdev->dev, ATA_DMA_MASK);
+}
+
+static int vt8251_prepare_host(struct pci_dev *pdev, struct ata_host **r_host)
+{
+	const struct ata_port_info *ppi[] = { &vt8251_port_info, NULL };
+	struct ata_host *host;
+	int i, rc;
+
+	rc = ata_pci_bmdma_prepare_host(pdev, ppi, &host);
+	if (rc)
+		return rc;
+	*r_host = host;
+
+	rc = pcim_iomap_regions(pdev, 1 << 5, DRV_NAME);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to iomap PCI BAR 5\n");
+		return rc;
+	}
+
+	/* 8251 hosts four sata ports as M/S of the two channels */
+	for (i = 0; i < host->n_ports; i++)
+		ata_slave_link_init(host->ports[i]);
+
+	return 0;
+}
+
+static void svia_wd_fix(struct pci_dev *pdev)
+{
+	u8 tmp8;
+
+	pci_read_config_byte(pdev, 0x52, &tmp8);
+	pci_write_config_byte(pdev, 0x52, tmp8 | BIT(2));
+}
+
+static irqreturn_t vt642x_interrupt(int irq, void *dev_instance)
+{
+	struct ata_host *host = dev_instance;
+	irqreturn_t rc = ata_bmdma_interrupt(irq, dev_instance);
+
+	/* if the IRQ was not handled, it might be a hotplug IRQ */
+	if (rc != IRQ_HANDLED) {
+		u32 serror;
+		unsigned long flags;
+
+		spin_lock_irqsave(&host->lock, flags);
+		/* check for hotplug on port 0 */
+		svia_scr_read(&host->ports[0]->link, SCR_ERROR, &serror);
+		if (serror & SERR_PHYRDY_CHG) {
+			ata_ehi_hotplugged(&host->ports[0]->link.eh_info);
+			ata_port_freeze(host->ports[0]);
+			rc = IRQ_HANDLED;
+		}
+		/* check for hotplug on port 1 */
+		svia_scr_read(&host->ports[1]->link, SCR_ERROR, &serror);
+		if (serror & SERR_PHYRDY_CHG) {
+			ata_ehi_hotplugged(&host->ports[1]->link.eh_info);
+			ata_port_freeze(host->ports[1]);
+			rc = IRQ_HANDLED;
+		}
+		spin_unlock_irqrestore(&host->lock, flags);
+	}
+
+	return rc;
+}
+
+static void vt6421_error_handler(struct ata_port *ap)
+{
+	struct svia_priv *hpriv = ap->host->private_data;
+	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
+	u32 serror;
+
+	/* see svia_configure() for description */
+	if (!hpriv->wd_workaround) {
+		svia_scr_read(&ap->link, SCR_ERROR, &serror);
+		if (serror == 0x1000500) {
+			ata_port_warn(ap, "Incompatible drive: enabling workaround. This slows down transfer rate to ~60 MB/s");
+			svia_wd_fix(pdev);
+			hpriv->wd_workaround = true;
+			ap->link.eh_context.i.flags |= ATA_EHI_QUIET;
+		}
+	}
+
+	ata_sff_error_handler(ap);
+}
+
+static void svia_configure(struct pci_dev *pdev, int board_id,
+			   struct svia_priv *hpriv)
+{
+	u8 tmp8;
+
+	pci_read_config_byte(pdev, PCI_INTERRUPT_LINE, &tmp8);
+	dev_info(&pdev->dev, "routed to hard irq line %d\n",
+		 (int) (tmp8 & 0xf0) == 0xf0 ? 0 : tmp8 & 0x0f);
+
+	/* make sure SATA channels are enabled */
+	pci_read_config_byte(pdev, SATA_CHAN_ENAB, &tmp8);
+	if ((tmp8 & ALL_PORTS) != ALL_PORTS) {
+		dev_dbg(&pdev->dev, "enabling SATA channels (0x%x)\n",
+			(int)tmp8);
+		tmp8 |= ALL_PORTS;
+		pci_write_config_byte(pdev, SATA_CHAN_ENAB, tmp8);
+	}
+
+	/* make sure interrupts for each channel sent to us */
+	pci_read_config_byte(pdev, SATA_INT_GATE, &tmp8);
+	if ((tmp8 & ALL_PORTS) != ALL_PORTS) {
+		dev_dbg(&pdev->dev, "enabling SATA channel interrupts (0x%x)\n",
+			(int) tmp8);
+		tmp8 |= ALL_PORTS;
+		pci_write_config_byte(pdev, SATA_INT_GATE, tmp8);
+	}
+
+	/* make sure native mode is enabled */
+	pci_read_config_byte(pdev, SATA_NATIVE_MODE, &tmp8);
+	if ((tmp8 & NATIVE_MODE_ALL) != NATIVE_MODE_ALL) {
+		dev_dbg(&pdev->dev,
+			"enabling SATA channel native mode (0x%x)\n",
+			(int) tmp8);
+		tmp8 |= NATIVE_MODE_ALL;
+		pci_write_config_byte(pdev, SATA_NATIVE_MODE, tmp8);
+	}
+
+	if ((board_id == vt6420 && vt6420_hotplug) || board_id == vt6421) {
+		/* enable IRQ on hotplug */
+		pci_read_config_byte(pdev, SVIA_MISC_3, &tmp8);
+		if ((tmp8 & SATA_HOTPLUG) != SATA_HOTPLUG) {
+			dev_dbg(&pdev->dev,
+				"enabling SATA hotplug (0x%x)\n",
+				(int) tmp8);
+			tmp8 |= SATA_HOTPLUG;
+			pci_write_config_byte(pdev, SVIA_MISC_3, tmp8);
+		}
+	}
+
+	/*
+	 * vt6420/1 has problems talking to some drives.  The following
+	 * is the fix from Joseph Chan <JosephChan@via.com.tw>.
+	 *
+	 * When host issues HOLD, device may send up to 20DW of data
+	 * before acknowledging it with HOLDA and the host should be
+	 * able to buffer them in FIFO.  Unfortunately, some WD drives
+	 * send up to 40DW before acknowledging HOLD and, in the
+	 * default configuration, this ends up overflowing vt6421's
+	 * FIFO, making the controller abort the transaction with
+	 * R_ERR.
+	 *
+	 * Rx52[2] is the internal 128DW FIFO Flow control watermark
+	 * adjusting mechanism enable bit and the default value 0
+	 * means host will issue HOLD to device when the left FIFO
+	 * size goes below 32DW.  Setting it to 1 makes the watermark
+	 * 64DW.
+	 *
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=15173
+	 * http://article.gmane.org/gmane.linux.ide/46352
+	 * http://thread.gmane.org/gmane.linux.kernel/1062139
+	 *
+	 * As the fix slows down data transfer, apply it only if the error
+	 * actually appears - see vt6421_error_handler()
+	 * Apply the fix always on vt6420 as we don't know if SCR_ERROR can be
+	 * read safely.
+	 */
+	if (board_id == vt6420) {
+		svia_wd_fix(pdev);
+		hpriv->wd_workaround = true;
+	}
+}
+
+static int svia_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
+{
+	unsigned int i;
+	int rc;
+	struct ata_host *host = NULL;
+	int board_id = (int) ent->driver_data;
+	const unsigned *bar_sizes;
+	struct svia_priv *hpriv;
+
+	ata_print_version_once(&pdev->dev, DRV_VERSION);
+
+	rc = pcim_enable_device(pdev);
+	if (rc)
+		return rc;
+
+	if (board_id == vt6421)
+		bar_sizes = &vt6421_bar_sizes[0];
+	else
+		bar_sizes = &svia_bar_sizes[0];
+
+	for (i = 0; i < ARRAY_SIZE(svia_bar_sizes); i++)
+		if ((pci_resource_start(pdev, i) == 0) ||
+		    (pci_resource_len(pdev, i) < bar_sizes[i])) {
+			dev_err(&pdev->dev,
+				"invalid PCI BAR %u (sz 0x%llx, val 0x%llx)\n",
+				i,
+				(unsigned long long)pci_resource_start(pdev, i),
+				(unsigned long long)pci_resource_len(pdev, i));
+			return -ENODEV;
+		}
+
+	switch (board_id) {
+	case vt6420:
+		rc = vt6420_prepare_host(pdev, &host);
+		break;
+	case vt6421:
+		rc = vt6421_prepare_host(pdev, &host);
+		break;
+	case vt8251:
+		rc = vt8251_prepare_host(pdev, &host);
+		break;
+	default:
+		rc = -EINVAL;
+	}
+	if (rc)
+		return rc;
+
+	hpriv = devm_kzalloc(&pdev->dev, sizeof(*hpriv), GFP_KERNEL);
+	if (!hpriv)
+		return -ENOMEM;
+	host->private_data = hpriv;
+
+	svia_configure(pdev, board_id, hpriv);
+
+	pci_set_master(pdev);
+	if ((board_id == vt6420 && vt6420_hotplug) || board_id == vt6421)
+		return ata_host_activate(host, pdev->irq, vt642x_interrupt,
+					 IRQF_SHARED, &svia_sht);
+	else
+		return ata_host_activate(host, pdev->irq, ata_bmdma_interrupt,
+					 IRQF_SHARED, &svia_sht);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int svia_pci_device_resume(struct pci_dev *pdev)
+{
+	struct ata_host *host = pci_get_drvdata(pdev);
+	struct svia_priv *hpriv = host->private_data;
+	int rc;
+
+	rc = ata_pci_device_do_resume(pdev);
+	if (rc)
+		return rc;
+
+	if (hpriv->wd_workaround)
+		svia_wd_fix(pdev);
+	ata_host_resume(host);
+
+	return 0;
+}
+#endif
+
+module_pci_driver(svia_pci_driver);