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, 908 insertions, 0 deletions

diff --git a/drivers/video/fbdev/aty/mach64_gx.c b/drivers/video/fbdev/aty/mach64_gx.c
new file mode 100644
index 000000000..d06d24830
--- /dev/null
+++ b/drivers/video/fbdev/aty/mach64_gx.c
@@ -0,0 +1,908 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ *  ATI Mach64 GX Support
+ */
+
+#include <linux/delay.h>
+#include <linux/fb.h>
+
+#include <asm/io.h>
+
+#include <video/mach64.h>
+#include "atyfb.h"
+
+/* Definitions for the ICS 2595 == ATI 18818_1 Clockchip */
+
+#define REF_FREQ_2595       1432	/*  14.33 MHz  (exact   14.31818) */
+#define REF_DIV_2595          46	/* really 43 on ICS 2595 !!!  */
+				  /* ohne Prescaler */
+#define MAX_FREQ_2595      15938	/* 159.38 MHz  (really 170.486) */
+#define MIN_FREQ_2595       8000	/*  80.00 MHz  (        85.565) */
+				  /* mit Prescaler 2, 4, 8 */
+#define ABS_MIN_FREQ_2595   1000	/*  10.00 MHz  (really  10.697) */
+#define N_ADJ_2595           257
+
+#define STOP_BITS_2595     0x1800
+
+
+#define MIN_N_408		2
+
+#define MIN_N_1703		6
+
+#define MIN_M		2
+#define MAX_M		30
+#define MIN_N		35
+#define MAX_N		255-8
+
+
+    /*
+     *  Support Functions
+     */
+
+static void aty_dac_waste4(const struct atyfb_par *par)
+{
+	(void) aty_ld_8(DAC_REGS, par);
+
+	(void) aty_ld_8(DAC_REGS + 2, par);
+	(void) aty_ld_8(DAC_REGS + 2, par);
+	(void) aty_ld_8(DAC_REGS + 2, par);
+	(void) aty_ld_8(DAC_REGS + 2, par);
+}
+
+static void aty_StrobeClock(const struct atyfb_par *par)
+{
+	u8 tmp;
+
+	udelay(26);
+
+	tmp = aty_ld_8(CLOCK_CNTL, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, tmp | CLOCK_STROBE, par);
+	return;
+}
+
+
+    /*
+     *  IBM RGB514 DAC and Clock Chip
+     */
+
+static void aty_st_514(int offset, u8 val, const struct atyfb_par *par)
+{
+	aty_st_8(DAC_CNTL, 1, par);
+	/* right addr byte */
+	aty_st_8(DAC_W_INDEX, offset & 0xff, par);
+	/* left addr byte */
+	aty_st_8(DAC_DATA, (offset >> 8) & 0xff, par);
+	aty_st_8(DAC_MASK, val, par);
+	aty_st_8(DAC_CNTL, 0, par);
+}
+
+static int aty_set_dac_514(const struct fb_info *info,
+			   const union aty_pll *pll, u32 bpp, u32 accel)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	static struct {
+		u8 pixel_dly;
+		u8 misc2_cntl;
+		u8 pixel_rep;
+		u8 pixel_cntl_index;
+		u8 pixel_cntl_v1;
+	} tab[3] = {
+		{
+		0, 0x41, 0x03, 0x71, 0x45},	/* 8 bpp */
+		{
+		0, 0x45, 0x04, 0x0c, 0x01},	/* 555 */
+		{
+		0, 0x45, 0x06, 0x0e, 0x00},	/* XRGB */
+	};
+	int i;
+
+	switch (bpp) {
+	case 8:
+	default:
+		i = 0;
+		break;
+	case 16:
+		i = 1;
+		break;
+	case 32:
+		i = 2;
+		break;
+	}
+	aty_st_514(0x90, 0x00, par);	/* VRAM Mask Low */
+	aty_st_514(0x04, tab[i].pixel_dly, par);	/* Horizontal Sync Control */
+	aty_st_514(0x05, 0x00, par);	/* Power Management */
+	aty_st_514(0x02, 0x01, par);	/* Misc Clock Control */
+	aty_st_514(0x71, tab[i].misc2_cntl, par);	/* Misc Control 2 */
+	aty_st_514(0x0a, tab[i].pixel_rep, par);	/* Pixel Format */
+	aty_st_514(tab[i].pixel_cntl_index, tab[i].pixel_cntl_v1, par);
+	/* Misc Control 2 / 16 BPP Control / 32 BPP Control */
+	return 0;
+}
+
+static int aty_var_to_pll_514(const struct fb_info *info, u32 vclk_per,
+			      u32 bpp, union aty_pll *pll)
+{
+	/*
+	 *  FIXME: use real calculations instead of using fixed values from the old
+	 *         driver
+	 */
+	static struct {
+		u32 limit;	/* pixlock rounding limit (arbitrary) */
+		u8 m;		/* (df<<6) | vco_div_count */
+		u8 n;		/* ref_div_count */
+	} RGB514_clocks[7] = {
+		{
+		8000, (3 << 6) | 20, 9},	/*  7395 ps / 135.2273 MHz */
+		{
+		10000, (1 << 6) | 19, 3},	/*  9977 ps / 100.2273 MHz */
+		{
+		13000, (1 << 6) | 2, 3},	/* 12509 ps /  79.9432 MHz */
+		{
+		14000, (2 << 6) | 8, 7},	/* 13394 ps /  74.6591 MHz */
+		{
+		16000, (1 << 6) | 44, 6},	/* 15378 ps /  65.0284 MHz */
+		{
+		25000, (1 << 6) | 15, 5},	/* 17460 ps /  57.2727 MHz */
+		{
+		50000, (0 << 6) | 53, 7},	/* 33145 ps /  30.1705 MHz */
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(RGB514_clocks); i++)
+		if (vclk_per <= RGB514_clocks[i].limit) {
+			pll->ibm514.m = RGB514_clocks[i].m;
+			pll->ibm514.n = RGB514_clocks[i].n;
+			return 0;
+		}
+	return -EINVAL;
+}
+
+static u32 aty_pll_514_to_var(const struct fb_info *info,
+			      const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u8 df, vco_div_count, ref_div_count;
+
+	df = pll->ibm514.m >> 6;
+	vco_div_count = pll->ibm514.m & 0x3f;
+	ref_div_count = pll->ibm514.n;
+
+	return ((par->ref_clk_per * ref_div_count) << (3 - df))/
+	    		(vco_div_count + 65);
+}
+
+static void aty_set_pll_514(const struct fb_info *info,
+			    const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+
+	aty_st_514(0x06, 0x02, par);	/* DAC Operation */
+	aty_st_514(0x10, 0x01, par);	/* PLL Control 1 */
+	aty_st_514(0x70, 0x01, par);	/* Misc Control 1 */
+	aty_st_514(0x8f, 0x1f, par);	/* PLL Ref. Divider Input */
+	aty_st_514(0x03, 0x00, par);	/* Sync Control */
+	aty_st_514(0x05, 0x00, par);	/* Power Management */
+	aty_st_514(0x20, pll->ibm514.m, par);	/* F0 / M0 */
+	aty_st_514(0x21, pll->ibm514.n, par);	/* F1 / N0 */
+}
+
+const struct aty_dac_ops aty_dac_ibm514 = {
+	.set_dac	= aty_set_dac_514,
+};
+
+const struct aty_pll_ops aty_pll_ibm514 = {
+	.var_to_pll	= aty_var_to_pll_514,
+	.pll_to_var	= aty_pll_514_to_var,
+	.set_pll	= aty_set_pll_514,
+};
+
+
+    /*
+     *  ATI 68860-B DAC
+     */
+
+static int aty_set_dac_ATI68860_B(const struct fb_info *info,
+				  const union aty_pll *pll, u32 bpp,
+				  u32 accel)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 gModeReg, devSetupRegA, temp, mask;
+
+	gModeReg = 0;
+	devSetupRegA = 0;
+
+	switch (bpp) {
+	case 8:
+		gModeReg = 0x83;
+		devSetupRegA =
+		    0x60 | 0x00 /*(info->mach64DAC8Bit ? 0x00 : 0x01) */ ;
+		break;
+	case 15:
+		gModeReg = 0xA0;
+		devSetupRegA = 0x60;
+		break;
+	case 16:
+		gModeReg = 0xA1;
+		devSetupRegA = 0x60;
+		break;
+	case 24:
+		gModeReg = 0xC0;
+		devSetupRegA = 0x60;
+		break;
+	case 32:
+		gModeReg = 0xE3;
+		devSetupRegA = 0x60;
+		break;
+	}
+
+	if (!accel) {
+		gModeReg = 0x80;
+		devSetupRegA = 0x61;
+	}
+
+	temp = aty_ld_8(DAC_CNTL, par);
+	aty_st_8(DAC_CNTL, (temp & ~DAC_EXT_SEL_RS2) | DAC_EXT_SEL_RS3,
+		 par);
+
+	aty_st_8(DAC_REGS + 2, 0x1D, par);
+	aty_st_8(DAC_REGS + 3, gModeReg, par);
+	aty_st_8(DAC_REGS, 0x02, par);
+
+	temp = aty_ld_8(DAC_CNTL, par);
+	aty_st_8(DAC_CNTL, temp | DAC_EXT_SEL_RS2 | DAC_EXT_SEL_RS3, par);
+
+	if (info->fix.smem_len < ONE_MB)
+		mask = 0x04;
+	else if (info->fix.smem_len == ONE_MB)
+		mask = 0x08;
+	else
+		mask = 0x0C;
+
+	/* The following assumes that the BIOS has correctly set R7 of the
+	 * Device Setup Register A at boot time.
+	 */
+#define A860_DELAY_L	0x80
+
+	temp = aty_ld_8(DAC_REGS, par);
+	aty_st_8(DAC_REGS, (devSetupRegA | mask) | (temp & A860_DELAY_L),
+		 par);
+	temp = aty_ld_8(DAC_CNTL, par);
+	aty_st_8(DAC_CNTL, (temp & ~(DAC_EXT_SEL_RS2 | DAC_EXT_SEL_RS3)),
+		 par);
+
+	aty_st_le32(BUS_CNTL, 0x890e20f1, par);
+	aty_st_le32(DAC_CNTL, 0x47052100, par);
+	return 0;
+}
+
+const struct aty_dac_ops aty_dac_ati68860b = {
+	.set_dac	= aty_set_dac_ATI68860_B,
+};
+
+
+    /*
+     *  AT&T 21C498 DAC
+     */
+
+static int aty_set_dac_ATT21C498(const struct fb_info *info,
+				 const union aty_pll *pll, u32 bpp,
+				 u32 accel)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 dotClock;
+	int muxmode = 0;
+	int DACMask = 0;
+
+	dotClock = 100000000 / pll->ics2595.period_in_ps;
+
+	switch (bpp) {
+	case 8:
+		if (dotClock > 8000) {
+			DACMask = 0x24;
+			muxmode = 1;
+		} else
+			DACMask = 0x04;
+		break;
+	case 15:
+		DACMask = 0x16;
+		break;
+	case 16:
+		DACMask = 0x36;
+		break;
+	case 24:
+		DACMask = 0xE6;
+		break;
+	case 32:
+		DACMask = 0xE6;
+		break;
+	}
+
+	if (1 /* info->mach64DAC8Bit */ )
+		DACMask |= 0x02;
+
+	aty_dac_waste4(par);
+	aty_st_8(DAC_REGS + 2, DACMask, par);
+
+	aty_st_le32(BUS_CNTL, 0x890e20f1, par);
+	aty_st_le32(DAC_CNTL, 0x00072000, par);
+	return muxmode;
+}
+
+const struct aty_dac_ops aty_dac_att21c498 = {
+	.set_dac	= aty_set_dac_ATT21C498,
+};
+
+
+    /*
+     *  ATI 18818 / ICS 2595 Clock Chip
+     */
+
+static int aty_var_to_pll_18818(const struct fb_info *info, u32 vclk_per,
+				u32 bpp, union aty_pll *pll)
+{
+	u32 MHz100;		/* in 0.01 MHz */
+	u32 program_bits;
+	u32 post_divider;
+
+	/* Calculate the programming word */
+	MHz100 = 100000000 / vclk_per;
+
+	program_bits = -1;
+	post_divider = 1;
+
+	if (MHz100 > MAX_FREQ_2595) {
+		return -EINVAL;
+	} else if (MHz100 < ABS_MIN_FREQ_2595) {
+		return -EINVAL;
+	} else {
+		while (MHz100 < MIN_FREQ_2595) {
+			MHz100 *= 2;
+			post_divider *= 2;
+		}
+	}
+	MHz100 *= 1000;
+	MHz100 = (REF_DIV_2595 * MHz100) / REF_FREQ_2595;
+ 
+	MHz100 += 500;		/* + 0.5 round */
+	MHz100 /= 1000;
+
+	if (program_bits == -1) {
+		program_bits = MHz100 - N_ADJ_2595;
+		switch (post_divider) {
+		case 1:
+			program_bits |= 0x0600;
+			break;
+		case 2:
+			program_bits |= 0x0400;
+			break;
+		case 4:
+			program_bits |= 0x0200;
+			break;
+		case 8:
+		default:
+			break;
+		}
+	}
+
+	program_bits |= STOP_BITS_2595;
+
+	pll->ics2595.program_bits = program_bits;
+	pll->ics2595.locationAddr = 0;
+	pll->ics2595.post_divider = post_divider;
+	pll->ics2595.period_in_ps = vclk_per;
+
+	return 0;
+}
+
+static u32 aty_pll_18818_to_var(const struct fb_info *info,
+				const union aty_pll *pll)
+{
+	return (pll->ics2595.period_in_ps);	/* default for now */
+}
+
+static void aty_ICS2595_put1bit(u8 data, const struct atyfb_par *par)
+{
+	u8 tmp;
+
+	data &= 0x01;
+	tmp = aty_ld_8(CLOCK_CNTL, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset,
+		 (tmp & ~0x04) | (data << 2), par);
+
+	tmp = aty_ld_8(CLOCK_CNTL, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, (tmp & ~0x08) | (0 << 3),
+		 par);
+
+	aty_StrobeClock(par);
+
+	tmp = aty_ld_8(CLOCK_CNTL, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, (tmp & ~0x08) | (1 << 3),
+		 par);
+
+	aty_StrobeClock(par);
+	return;
+}
+
+static void aty_set_pll18818(const struct fb_info *info,
+			     const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 program_bits;
+	u32 locationAddr;
+
+	u32 i;
+
+	u8 old_clock_cntl;
+	u8 old_crtc_ext_disp;
+
+	old_clock_cntl = aty_ld_8(CLOCK_CNTL, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, 0, par);
+
+	old_crtc_ext_disp = aty_ld_8(CRTC_GEN_CNTL + 3, par);
+	aty_st_8(CRTC_GEN_CNTL + 3,
+		 old_crtc_ext_disp | (CRTC_EXT_DISP_EN >> 24), par);
+
+	mdelay(15);		/* delay for 50 (15) ms */
+
+	program_bits = pll->ics2595.program_bits;
+	locationAddr = pll->ics2595.locationAddr;
+
+	/* Program the clock chip */
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, 0, par);	/* Strobe = 0 */
+	aty_StrobeClock(par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset, 1, par);	/* Strobe = 0 */
+	aty_StrobeClock(par);
+
+	aty_ICS2595_put1bit(1, par);	/* Send start bits */
+	aty_ICS2595_put1bit(0, par);	/* Start bit */
+	aty_ICS2595_put1bit(0, par);	/* Read / ~Write */
+
+	for (i = 0; i < 5; i++) {	/* Location 0..4 */
+		aty_ICS2595_put1bit(locationAddr & 1, par);
+		locationAddr >>= 1;
+	}
+
+	for (i = 0; i < 8 + 1 + 2 + 2; i++) {
+		aty_ICS2595_put1bit(program_bits & 1, par);
+		program_bits >>= 1;
+	}
+
+	mdelay(1);		/* delay for 1 ms */
+
+	(void) aty_ld_8(DAC_REGS, par);	/* Clear DAC Counter */
+	aty_st_8(CRTC_GEN_CNTL + 3, old_crtc_ext_disp, par);
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset,
+		 old_clock_cntl | CLOCK_STROBE, par);
+
+	mdelay(50);		/* delay for 50 (15) ms */
+	aty_st_8(CLOCK_CNTL + par->clk_wr_offset,
+		 ((pll->ics2595.locationAddr & 0x0F) | CLOCK_STROBE), par);
+	return;
+}
+
+const struct aty_pll_ops aty_pll_ati18818_1 = {
+	.var_to_pll	= aty_var_to_pll_18818,
+	.pll_to_var	= aty_pll_18818_to_var,
+	.set_pll	= aty_set_pll18818,
+};
+
+
+    /*
+     *  STG 1703 Clock Chip
+     */
+
+static int aty_var_to_pll_1703(const struct fb_info *info, u32 vclk_per,
+			       u32 bpp, union aty_pll *pll)
+{
+	u32 mhz100;		/* in 0.01 MHz */
+	u32 program_bits;
+	/* u32 post_divider; */
+	u32 mach64MinFreq, mach64MaxFreq, mach64RefFreq;
+	u32 temp, tempB;
+	u16 remainder, preRemainder;
+	short divider = 0, tempA;
+
+	/* Calculate the programming word */
+	mhz100 = 100000000 / vclk_per;
+	mach64MinFreq = MIN_FREQ_2595;
+	mach64MaxFreq = MAX_FREQ_2595;
+	mach64RefFreq = REF_FREQ_2595;	/* 14.32 MHz */
+
+	/* Calculate program word */
+	if (mhz100 == 0)
+		program_bits = 0xE0;
+	else {
+		if (mhz100 < mach64MinFreq)
+			mhz100 = mach64MinFreq;
+		if (mhz100 > mach64MaxFreq)
+			mhz100 = mach64MaxFreq;
+
+		divider = 0;
+		while (mhz100 < (mach64MinFreq << 3)) {
+			mhz100 <<= 1;
+			divider += 0x20;
+		}
+
+		temp = (unsigned int) (mhz100);
+		temp = (unsigned int) (temp * (MIN_N_1703 + 2));
+		temp -= (short) (mach64RefFreq << 1);
+
+		tempA = MIN_N_1703;
+		preRemainder = 0xffff;
+
+		do {
+			tempB = temp;
+			remainder = tempB % mach64RefFreq;
+			tempB = tempB / mach64RefFreq;
+
+			if ((tempB & 0xffff) <= 127
+			    && (remainder <= preRemainder)) {
+				preRemainder = remainder;
+				divider &= ~0x1f;
+				divider |= tempA;
+				divider =
+				    (divider & 0x00ff) +
+				    ((tempB & 0xff) << 8);
+			}
+
+			temp += mhz100;
+			tempA++;
+		} while (tempA <= (MIN_N_1703 << 1));
+
+		program_bits = divider;
+	}
+
+	pll->ics2595.program_bits = program_bits;
+	pll->ics2595.locationAddr = 0;
+	pll->ics2595.post_divider = divider;	/* fuer nix */
+	pll->ics2595.period_in_ps = vclk_per;
+
+	return 0;
+}
+
+static u32 aty_pll_1703_to_var(const struct fb_info *info,
+			       const union aty_pll *pll)
+{
+	return (pll->ics2595.period_in_ps);	/* default for now */
+}
+
+static void aty_set_pll_1703(const struct fb_info *info,
+			     const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 program_bits;
+	u32 locationAddr;
+
+	char old_crtc_ext_disp;
+
+	old_crtc_ext_disp = aty_ld_8(CRTC_GEN_CNTL + 3, par);
+	aty_st_8(CRTC_GEN_CNTL + 3,
+		 old_crtc_ext_disp | (CRTC_EXT_DISP_EN >> 24), par);
+
+	program_bits = pll->ics2595.program_bits;
+	locationAddr = pll->ics2595.locationAddr;
+
+	/* Program clock */
+	aty_dac_waste4(par);
+
+	(void) aty_ld_8(DAC_REGS + 2, par);
+	aty_st_8(DAC_REGS + 2, (locationAddr << 1) + 0x20, par);
+	aty_st_8(DAC_REGS + 2, 0, par);
+	aty_st_8(DAC_REGS + 2, (program_bits & 0xFF00) >> 8, par);
+	aty_st_8(DAC_REGS + 2, (program_bits & 0xFF), par);
+
+	(void) aty_ld_8(DAC_REGS, par);	/* Clear DAC Counter */
+	aty_st_8(CRTC_GEN_CNTL + 3, old_crtc_ext_disp, par);
+	return;
+}
+
+const struct aty_pll_ops aty_pll_stg1703 = {
+	.var_to_pll	= aty_var_to_pll_1703,
+	.pll_to_var	= aty_pll_1703_to_var,
+	.set_pll	= aty_set_pll_1703,
+};
+
+
+    /*
+     *  Chrontel 8398 Clock Chip
+     */
+
+static int aty_var_to_pll_8398(const struct fb_info *info, u32 vclk_per,
+			       u32 bpp, union aty_pll *pll)
+{
+	u32 tempA, tempB, fOut, longMHz100, diff, preDiff;
+
+	u32 mhz100;		/* in 0.01 MHz */
+	u32 program_bits;
+	/* u32 post_divider; */
+	u32 mach64MinFreq, mach64MaxFreq;
+	u16 m, n, k = 0, save_m, save_n, twoToKth;
+
+	/* Calculate the programming word */
+	mhz100 = 100000000 / vclk_per;
+	mach64MinFreq = MIN_FREQ_2595;
+	mach64MaxFreq = MAX_FREQ_2595;
+
+	save_m = 0;
+	save_n = 0;
+
+	/* Calculate program word */
+	if (mhz100 == 0)
+		program_bits = 0xE0;
+	else {
+		if (mhz100 < mach64MinFreq)
+			mhz100 = mach64MinFreq;
+		if (mhz100 > mach64MaxFreq)
+			mhz100 = mach64MaxFreq;
+
+		longMHz100 = mhz100 * 256 / 100;	/* 8 bit scale this */
+
+		while (mhz100 < (mach64MinFreq << 3)) {
+			mhz100 <<= 1;
+			k++;
+		}
+
+		twoToKth = 1 << k;
+		diff = 0;
+		preDiff = 0xFFFFFFFF;
+
+		for (m = MIN_M; m <= MAX_M; m++) {
+			for (n = MIN_N; n <= MAX_N; n++) {
+				tempA = 938356;		/* 14.31818 * 65536 */
+				tempA *= (n + 8);	/* 43..256 */
+				tempB = twoToKth * 256;
+				tempB *= (m + 2);	/* 4..32 */
+				fOut = tempA / tempB;	/* 8 bit scale */
+
+				if (longMHz100 > fOut)
+					diff = longMHz100 - fOut;
+				else
+					diff = fOut - longMHz100;
+
+				if (diff < preDiff) {
+					save_m = m;
+					save_n = n;
+					preDiff = diff;
+				}
+			}
+		}
+
+		program_bits = (k << 6) + (save_m) + (save_n << 8);
+	}
+
+	pll->ics2595.program_bits = program_bits;
+	pll->ics2595.locationAddr = 0;
+	pll->ics2595.post_divider = 0;
+	pll->ics2595.period_in_ps = vclk_per;
+
+	return 0;
+}
+
+static u32 aty_pll_8398_to_var(const struct fb_info *info,
+			       const union aty_pll *pll)
+{
+	return (pll->ics2595.period_in_ps);	/* default for now */
+}
+
+static void aty_set_pll_8398(const struct fb_info *info,
+			     const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 program_bits;
+	u32 locationAddr;
+
+	char old_crtc_ext_disp;
+	char tmp;
+
+	old_crtc_ext_disp = aty_ld_8(CRTC_GEN_CNTL + 3, par);
+	aty_st_8(CRTC_GEN_CNTL + 3,
+		 old_crtc_ext_disp | (CRTC_EXT_DISP_EN >> 24), par);
+
+	program_bits = pll->ics2595.program_bits;
+	locationAddr = pll->ics2595.locationAddr;
+
+	/* Program clock */
+	tmp = aty_ld_8(DAC_CNTL, par);
+	aty_st_8(DAC_CNTL, tmp | DAC_EXT_SEL_RS2 | DAC_EXT_SEL_RS3, par);
+
+	aty_st_8(DAC_REGS, locationAddr, par);
+	aty_st_8(DAC_REGS + 1, (program_bits & 0xff00) >> 8, par);
+	aty_st_8(DAC_REGS + 1, (program_bits & 0xff), par);
+
+	tmp = aty_ld_8(DAC_CNTL, par);
+	aty_st_8(DAC_CNTL, (tmp & ~DAC_EXT_SEL_RS2) | DAC_EXT_SEL_RS3,
+		 par);
+
+	(void) aty_ld_8(DAC_REGS, par);	/* Clear DAC Counter */
+	aty_st_8(CRTC_GEN_CNTL + 3, old_crtc_ext_disp, par);
+
+	return;
+}
+
+const struct aty_pll_ops aty_pll_ch8398 = {
+	.var_to_pll	= aty_var_to_pll_8398,
+	.pll_to_var	= aty_pll_8398_to_var,
+	.set_pll	= aty_set_pll_8398,
+};
+
+
+    /*
+     *  AT&T 20C408 Clock Chip
+     */
+
+static int aty_var_to_pll_408(const struct fb_info *info, u32 vclk_per,
+			      u32 bpp, union aty_pll *pll)
+{
+	u32 mhz100;		/* in 0.01 MHz */
+	u32 program_bits;
+	/* u32 post_divider; */
+	u32 mach64MinFreq, mach64MaxFreq, mach64RefFreq;
+	u32 temp, tempB;
+	u16 remainder, preRemainder;
+	short divider = 0, tempA;
+
+	/* Calculate the programming word */
+	mhz100 = 100000000 / vclk_per;
+	mach64MinFreq = MIN_FREQ_2595;
+	mach64MaxFreq = MAX_FREQ_2595;
+	mach64RefFreq = REF_FREQ_2595;	/* 14.32 MHz */
+
+	/* Calculate program word */
+	if (mhz100 == 0)
+		program_bits = 0xFF;
+	else {
+		if (mhz100 < mach64MinFreq)
+			mhz100 = mach64MinFreq;
+		if (mhz100 > mach64MaxFreq)
+			mhz100 = mach64MaxFreq;
+
+		while (mhz100 < (mach64MinFreq << 3)) {
+			mhz100 <<= 1;
+			divider += 0x40;
+		}
+
+		temp = (unsigned int) mhz100;
+		temp = (unsigned int) (temp * (MIN_N_408 + 2));
+		temp -= ((short) (mach64RefFreq << 1));
+
+		tempA = MIN_N_408;
+		preRemainder = 0xFFFF;
+
+		do {
+			tempB = temp;
+			remainder = tempB % mach64RefFreq;
+			tempB = tempB / mach64RefFreq;
+			if (((tempB & 0xFFFF) <= 255)
+			    && (remainder <= preRemainder)) {
+				preRemainder = remainder;
+				divider &= ~0x3f;
+				divider |= tempA;
+				divider =
+				    (divider & 0x00FF) +
+				    ((tempB & 0xFF) << 8);
+			}
+			temp += mhz100;
+			tempA++;
+		} while (tempA <= 32);
+
+		program_bits = divider;
+	}
+
+	pll->ics2595.program_bits = program_bits;
+	pll->ics2595.locationAddr = 0;
+	pll->ics2595.post_divider = divider;	/* fuer nix */
+	pll->ics2595.period_in_ps = vclk_per;
+
+	return 0;
+}
+
+static u32 aty_pll_408_to_var(const struct fb_info *info,
+			      const union aty_pll *pll)
+{
+	return (pll->ics2595.period_in_ps);	/* default for now */
+}
+
+static void aty_set_pll_408(const struct fb_info *info,
+			    const union aty_pll *pll)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+	u32 program_bits;
+	u32 locationAddr;
+
+	u8 tmpA, tmpB, tmpC;
+	char old_crtc_ext_disp;
+
+	old_crtc_ext_disp = aty_ld_8(CRTC_GEN_CNTL + 3, par);
+	aty_st_8(CRTC_GEN_CNTL + 3,
+		 old_crtc_ext_disp | (CRTC_EXT_DISP_EN >> 24), par);
+
+	program_bits = pll->ics2595.program_bits;
+	locationAddr = pll->ics2595.locationAddr;
+
+	/* Program clock */
+	aty_dac_waste4(par);
+	tmpB = aty_ld_8(DAC_REGS + 2, par) | 1;
+	aty_dac_waste4(par);
+	aty_st_8(DAC_REGS + 2, tmpB, par);
+
+	tmpA = tmpB;
+	tmpC = tmpA;
+	tmpA |= 8;
+	tmpB = 1;
+
+	aty_st_8(DAC_REGS, tmpB, par);
+	aty_st_8(DAC_REGS + 2, tmpA, par);
+
+	udelay(400);		/* delay for 400 us */
+
+	locationAddr = (locationAddr << 2) + 0x40;
+	tmpB = locationAddr;
+	tmpA = program_bits >> 8;
+
+	aty_st_8(DAC_REGS, tmpB, par);
+	aty_st_8(DAC_REGS + 2, tmpA, par);
+
+	tmpB = locationAddr + 1;
+	tmpA = (u8) program_bits;
+
+	aty_st_8(DAC_REGS, tmpB, par);
+	aty_st_8(DAC_REGS + 2, tmpA, par);
+
+	tmpB = locationAddr + 2;
+	tmpA = 0x77;
+
+	aty_st_8(DAC_REGS, tmpB, par);
+	aty_st_8(DAC_REGS + 2, tmpA, par);
+
+	udelay(400);		/* delay for 400 us */
+	tmpA = tmpC & (~(1 | 8));
+	tmpB = 1;
+
+	aty_st_8(DAC_REGS, tmpB, par);
+	aty_st_8(DAC_REGS + 2, tmpA, par);
+
+	(void) aty_ld_8(DAC_REGS, par);	/* Clear DAC Counter */
+	aty_st_8(CRTC_GEN_CNTL + 3, old_crtc_ext_disp, par);
+	return;
+}
+
+const struct aty_pll_ops aty_pll_att20c408 = {
+	.var_to_pll	= aty_var_to_pll_408,
+	.pll_to_var	= aty_pll_408_to_var,
+	.set_pll	= aty_set_pll_408,
+};
+
+
+    /*
+     *  Unsupported DAC and Clock Chip
+     */
+
+static int aty_set_dac_unsupported(const struct fb_info *info,
+				   const union aty_pll *pll, u32 bpp,
+				   u32 accel)
+{
+	struct atyfb_par *par = (struct atyfb_par *) info->par;
+
+	aty_st_le32(BUS_CNTL, 0x890e20f1, par);
+	aty_st_le32(DAC_CNTL, 0x47052100, par);
+	/* new in 2.2.3p1 from Geert. ???????? */
+	aty_st_le32(BUS_CNTL, 0x590e10ff, par);
+	aty_st_le32(DAC_CNTL, 0x47012100, par);
+	return 0;
+}
+
+static int dummy(void)
+{
+	return 0;
+}
+
+const struct aty_dac_ops aty_dac_unsupported = {
+	.set_dac	= aty_set_dac_unsupported,
+};
+
+const struct aty_pll_ops aty_pll_unsupported = {
+	.var_to_pll	= (void *) dummy,
+	.pll_to_var	= (void *) dummy,
+	.set_pll	= (void *) dummy,
+};