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, 582 insertions, 0 deletions

diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
new file mode 100644
index 000000000..bd0274c75
--- /dev/null
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -0,0 +1,582 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/arch/m68k/kernel/sys_m68k.c
+ *
+ * This file contains various random system calls that
+ * have a non-standard calling sequence on the Linux/m68k
+ * platform.
+ */
+
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <linux/sem.h>
+#include <linux/msg.h>
+#include <linux/shm.h>
+#include <linux/stat.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
+#include <linux/file.h>
+#include <linux/ipc.h>
+
+#include <asm/setup.h>
+#include <linux/uaccess.h>
+#include <asm/cachectl.h>
+#include <asm/traps.h>
+#include <asm/page.h>
+#include <asm/unistd.h>
+#include <asm/cacheflush.h>
+
+#ifdef CONFIG_MMU
+
+#include <asm/tlb.h>
+
+asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address,
+			     unsigned long error_code);
+
+asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
+	unsigned long prot, unsigned long flags,
+	unsigned long fd, unsigned long pgoff)
+{
+	/*
+	 * This is wrong for sun3 - there PAGE_SIZE is 8Kb,
+	 * so we need to shift the argument down by 1; m68k mmap64(3)
+	 * (in libc) expects the last argument of mmap2 in 4Kb units.
+	 */
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, pgoff);
+}
+
+/* Convert virtual (user) address VADDR to physical address PADDR */
+#define virt_to_phys_040(vaddr)						\
+({									\
+  unsigned long _mmusr, _paddr;						\
+									\
+  __asm__ __volatile__ (".chip 68040\n\t"				\
+			"ptestr (%1)\n\t"				\
+			"movec %%mmusr,%0\n\t"				\
+			".chip 68k"					\
+			: "=r" (_mmusr)					\
+			: "a" (vaddr));					\
+  _paddr = (_mmusr & MMU_R_040) ? (_mmusr & PAGE_MASK) : 0;		\
+  _paddr;								\
+})
+
+static inline int
+cache_flush_040 (unsigned long addr, int scope, int cache, unsigned long len)
+{
+  unsigned long paddr, i;
+
+  switch (scope)
+    {
+    case FLUSH_SCOPE_ALL:
+      switch (cache)
+	{
+	case FLUSH_CACHE_DATA:
+	  /* This nop is needed for some broken versions of the 68040.  */
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %dc\n\t"
+				".chip 68k");
+	  break;
+	case FLUSH_CACHE_INSN:
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %ic\n\t"
+				".chip 68k");
+	  break;
+	default:
+	case FLUSH_CACHE_BOTH:
+	  __asm__ __volatile__ ("nop\n\t"
+				".chip 68040\n\t"
+				"cpusha %bc\n\t"
+				".chip 68k");
+	  break;
+	}
+      break;
+
+    case FLUSH_SCOPE_LINE:
+      /* Find the physical address of the first mapped page in the
+	 address range.  */
+      if ((paddr = virt_to_phys_040(addr))) {
+        paddr += addr & ~(PAGE_MASK | 15);
+        len = (len + (addr & 15) + 15) >> 4;
+      } else {
+	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
+
+	if (len <= tmp)
+	  return 0;
+	addr += tmp;
+	len -= tmp;
+	tmp = PAGE_SIZE;
+	for (;;)
+	  {
+	    if ((paddr = virt_to_phys_040(addr)))
+	      break;
+	    if (len <= tmp)
+	      return 0;
+	    addr += tmp;
+	    len -= tmp;
+	  }
+	len = (len + 15) >> 4;
+      }
+      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
+      while (len--)
+	{
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushl %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	  if (!--i && len)
+	    {
+	      /*
+	       * No need to page align here since it is done by
+	       * virt_to_phys_040().
+	       */
+	      addr += PAGE_SIZE;
+	      i = PAGE_SIZE / 16;
+	      /* Recompute physical address when crossing a page
+	         boundary. */
+	      for (;;)
+		{
+		  if ((paddr = virt_to_phys_040(addr)))
+		    break;
+		  if (len <= i)
+		    return 0;
+		  len -= i;
+		  addr += PAGE_SIZE;
+		}
+	    }
+	  else
+	    paddr += 16;
+	}
+      break;
+
+    default:
+    case FLUSH_SCOPE_PAGE:
+      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
+      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
+	{
+	  if (!(paddr = virt_to_phys_040(addr)))
+	    continue;
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ ("nop\n\t"
+				    ".chip 68040\n\t"
+				    "cpushp %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	}
+      break;
+    }
+  return 0;
+}
+
+#define virt_to_phys_060(vaddr)				\
+({							\
+  unsigned long paddr;					\
+  __asm__ __volatile__ (".chip 68060\n\t"		\
+			"plpar (%0)\n\t"		\
+			".chip 68k"			\
+			: "=a" (paddr)			\
+			: "0" (vaddr));			\
+  (paddr); /* XXX */					\
+})
+
+static inline int
+cache_flush_060 (unsigned long addr, int scope, int cache, unsigned long len)
+{
+  unsigned long paddr, i;
+
+  /*
+   * 68060 manual says:
+   *  cpush %dc : flush DC, remains valid (with our %cacr setup)
+   *  cpush %ic : invalidate IC
+   *  cpush %bc : flush DC + invalidate IC
+   */
+  switch (scope)
+    {
+    case FLUSH_SCOPE_ALL:
+      switch (cache)
+	{
+	case FLUSH_CACHE_DATA:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %dc\n\t"
+				".chip 68k");
+	  break;
+	case FLUSH_CACHE_INSN:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %ic\n\t"
+				".chip 68k");
+	  break;
+	default:
+	case FLUSH_CACHE_BOTH:
+	  __asm__ __volatile__ (".chip 68060\n\t"
+				"cpusha %bc\n\t"
+				".chip 68k");
+	  break;
+	}
+      break;
+
+    case FLUSH_SCOPE_LINE:
+      /* Find the physical address of the first mapped page in the
+	 address range.  */
+      len += addr & 15;
+      addr &= -16;
+      if (!(paddr = virt_to_phys_060(addr))) {
+	unsigned long tmp = PAGE_SIZE - (addr & ~PAGE_MASK);
+
+	if (len <= tmp)
+	  return 0;
+	addr += tmp;
+	len -= tmp;
+	tmp = PAGE_SIZE;
+	for (;;)
+	  {
+	    if ((paddr = virt_to_phys_060(addr)))
+	      break;
+	    if (len <= tmp)
+	      return 0;
+	    addr += tmp;
+	    len -= tmp;
+	  }
+      }
+      len = (len + 15) >> 4;
+      i = (PAGE_SIZE - (paddr & ~PAGE_MASK)) >> 4;
+      while (len--)
+	{
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushl %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	  if (!--i && len)
+	    {
+
+	      /*
+	       * We just want to jump to the first cache line
+	       * in the next page.
+	       */
+	      addr += PAGE_SIZE;
+	      addr &= PAGE_MASK;
+
+	      i = PAGE_SIZE / 16;
+	      /* Recompute physical address when crossing a page
+	         boundary. */
+	      for (;;)
+	        {
+	          if ((paddr = virt_to_phys_060(addr)))
+	            break;
+	          if (len <= i)
+	            return 0;
+	          len -= i;
+	          addr += PAGE_SIZE;
+	        }
+	    }
+	  else
+	    paddr += 16;
+	}
+      break;
+
+    default:
+    case FLUSH_SCOPE_PAGE:
+      len += (addr & ~PAGE_MASK) + (PAGE_SIZE - 1);
+      addr &= PAGE_MASK;	/* Workaround for bug in some
+				   revisions of the 68060 */
+      for (len >>= PAGE_SHIFT; len--; addr += PAGE_SIZE)
+	{
+	  if (!(paddr = virt_to_phys_060(addr)))
+	    continue;
+	  switch (cache)
+	    {
+	    case FLUSH_CACHE_DATA:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%dc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    case FLUSH_CACHE_INSN:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%ic,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    default:
+	    case FLUSH_CACHE_BOTH:
+	      __asm__ __volatile__ (".chip 68060\n\t"
+				    "cpushp %%bc,(%0)\n\t"
+				    ".chip 68k"
+				    : : "a" (paddr));
+	      break;
+	    }
+	}
+      break;
+    }
+  return 0;
+}
+
+/* sys_cacheflush -- flush (part of) the processor cache.  */
+asmlinkage int
+sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
+{
+	int ret = -EINVAL;
+
+	if (scope < FLUSH_SCOPE_LINE || scope > FLUSH_SCOPE_ALL ||
+	    cache & ~FLUSH_CACHE_BOTH)
+		goto out;
+
+	if (scope == FLUSH_SCOPE_ALL) {
+		/* Only the superuser may explicitly flush the whole cache. */
+		ret = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto out;
+
+		mmap_read_lock(current->mm);
+	} else {
+		struct vm_area_struct *vma;
+
+		/* Check for overflow.  */
+		if (addr + len < addr)
+			goto out;
+
+		/*
+		 * Verify that the specified address region actually belongs
+		 * to this process.
+		 */
+		mmap_read_lock(current->mm);
+		vma = vma_lookup(current->mm, addr);
+		if (!vma || addr + len > vma->vm_end)
+			goto out_unlock;
+	}
+
+	if (CPU_IS_020_OR_030) {
+		if (scope == FLUSH_SCOPE_LINE && len < 256) {
+			unsigned long cacr;
+			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
+			if (cache & FLUSH_CACHE_INSN)
+				cacr |= 4;
+			if (cache & FLUSH_CACHE_DATA)
+				cacr |= 0x400;
+			len >>= 2;
+			while (len--) {
+				__asm__ __volatile__ ("movec %1, %%caar\n\t"
+						      "movec %0, %%cacr"
+						      : /* no outputs */
+						      : "r" (cacr), "r" (addr));
+				addr += 4;
+			}
+		} else {
+			/* Flush the whole cache, even if page granularity requested. */
+			unsigned long cacr;
+			__asm__ ("movec %%cacr, %0" : "=r" (cacr));
+			if (cache & FLUSH_CACHE_INSN)
+				cacr |= 8;
+			if (cache & FLUSH_CACHE_DATA)
+				cacr |= 0x800;
+			__asm__ __volatile__ ("movec %0, %%cacr" : : "r" (cacr));
+		}
+		ret = 0;
+		goto out_unlock;
+	} else {
+	    /*
+	     * 040 or 060: don't blindly trust 'scope', someone could
+	     * try to flush a few megs of memory.
+	     */
+
+	    if (len>=3*PAGE_SIZE && scope<FLUSH_SCOPE_PAGE)
+	        scope=FLUSH_SCOPE_PAGE;
+	    if (len>=10*PAGE_SIZE && scope<FLUSH_SCOPE_ALL)
+	        scope=FLUSH_SCOPE_ALL;
+	    if (CPU_IS_040) {
+		ret = cache_flush_040 (addr, scope, cache, len);
+	    } else if (CPU_IS_060) {
+		ret = cache_flush_060 (addr, scope, cache, len);
+	    }
+	}
+out_unlock:
+	mmap_read_unlock(current->mm);
+out:
+	return ret;
+}
+
+/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
+   D1 (newval).  */
+asmlinkage int
+sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
+		      unsigned long __user * mem)
+{
+	/* This was borrowed from ARM's implementation.  */
+	for (;;) {
+		struct mm_struct *mm = current->mm;
+		pgd_t *pgd;
+		p4d_t *p4d;
+		pud_t *pud;
+		pmd_t *pmd;
+		pte_t *pte;
+		spinlock_t *ptl;
+		unsigned long mem_value;
+
+		mmap_read_lock(mm);
+		pgd = pgd_offset(mm, (unsigned long)mem);
+		if (!pgd_present(*pgd))
+			goto bad_access;
+		p4d = p4d_offset(pgd, (unsigned long)mem);
+		if (!p4d_present(*p4d))
+			goto bad_access;
+		pud = pud_offset(p4d, (unsigned long)mem);
+		if (!pud_present(*pud))
+			goto bad_access;
+		pmd = pmd_offset(pud, (unsigned long)mem);
+		if (!pmd_present(*pmd))
+			goto bad_access;
+		pte = pte_offset_map_lock(mm, pmd, (unsigned long)mem, &ptl);
+		if (!pte_present(*pte) || !pte_dirty(*pte)
+		    || !pte_write(*pte)) {
+			pte_unmap_unlock(pte, ptl);
+			goto bad_access;
+		}
+
+		/*
+		 * No need to check for EFAULT; we know that the page is
+		 * present and writable.
+		 */
+		__get_user(mem_value, mem);
+		if (mem_value == oldval)
+			__put_user(newval, mem);
+
+		pte_unmap_unlock(pte, ptl);
+		mmap_read_unlock(mm);
+		return mem_value;
+
+	      bad_access:
+		mmap_read_unlock(mm);
+		/* This is not necessarily a bad access, we can get here if
+		   a memory we're trying to write to should be copied-on-write.
+		   Make the kernel do the necessary page stuff, then re-iterate.
+		   Simulate a write access fault to do that.  */
+		{
+			/* The first argument of the function corresponds to
+			   D1, which is the first field of struct pt_regs.  */
+			struct pt_regs *fp = (struct pt_regs *)&newval;
+
+			/* '3' is an RMW flag.  */
+			if (do_page_fault(fp, (unsigned long)mem, 3))
+				/* If the do_page_fault() failed, we don't
+				   have anything meaningful to return.
+				   There should be a SIGSEGV pending for
+				   the process.  */
+				return 0xdeadbeef;
+		}
+	}
+}
+
+#else
+
+/* sys_cacheflush -- flush (part of) the processor cache.  */
+asmlinkage int
+sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
+{
+	flush_cache_all();
+	return 0;
+}
+
+/* This syscall gets its arguments in A0 (mem), D2 (oldval) and
+   D1 (newval).  */
+asmlinkage int
+sys_atomic_cmpxchg_32(unsigned long newval, int oldval, int d3, int d4, int d5,
+		      unsigned long __user * mem)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long mem_value;
+
+	mmap_read_lock(mm);
+
+	mem_value = *mem;
+	if (mem_value == oldval)
+		*mem = newval;
+
+	mmap_read_unlock(mm);
+	return mem_value;
+}
+
+#endif /* CONFIG_MMU */
+
+asmlinkage int sys_getpagesize(void)
+{
+	return PAGE_SIZE;
+}
+
+asmlinkage unsigned long sys_get_thread_area(void)
+{
+	return current_thread_info()->tp_value;
+}
+
+asmlinkage int sys_set_thread_area(unsigned long tp)
+{
+	current_thread_info()->tp_value = tp;
+	return 0;
+}
+
+asmlinkage int sys_atomic_barrier(void)
+{
+	/* no code needed for uniprocs */
+	return 0;
+}