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, 688 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c
new file mode 100644
index 000000000..162dfeb1c
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmd.c
@@ -0,0 +1,688 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright 2009-2020 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#include <linux/sched/signal.h>
+
+#include <drm/ttm/ttm_placement.h>
+
+#include "vmwgfx_drv.h"
+#include "vmwgfx_devcaps.h"
+
+bool vmw_supports_3d(struct vmw_private *dev_priv)
+{
+	uint32_t fifo_min, hwversion;
+	const struct vmw_fifo_state *fifo = dev_priv->fifo;
+
+	if (!(dev_priv->capabilities & SVGA_CAP_3D))
+		return false;
+
+	if (dev_priv->capabilities & SVGA_CAP_GBOBJECTS) {
+		uint32_t result;
+
+		if (!dev_priv->has_mob)
+			return false;
+
+		result = vmw_devcap_get(dev_priv, SVGA3D_DEVCAP_3D);
+
+		return (result != 0);
+	}
+
+	if (!(dev_priv->capabilities & SVGA_CAP_EXTENDED_FIFO))
+		return false;
+
+	BUG_ON(vmw_is_svga_v3(dev_priv));
+
+	fifo_min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
+	if (fifo_min <= SVGA_FIFO_3D_HWVERSION * sizeof(unsigned int))
+		return false;
+
+	hwversion = vmw_fifo_mem_read(dev_priv,
+				      ((fifo->capabilities &
+					SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ?
+					       SVGA_FIFO_3D_HWVERSION_REVISED :
+					       SVGA_FIFO_3D_HWVERSION));
+
+	if (hwversion == 0)
+		return false;
+
+	if (hwversion < SVGA3D_HWVERSION_WS8_B1)
+		return false;
+
+	/* Legacy Display Unit does not support surfaces */
+	if (dev_priv->active_display_unit == vmw_du_legacy)
+		return false;
+
+	return true;
+}
+
+bool vmw_fifo_have_pitchlock(struct vmw_private *dev_priv)
+{
+	uint32_t caps;
+
+	if (!(dev_priv->capabilities & SVGA_CAP_EXTENDED_FIFO))
+		return false;
+
+	caps = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_CAPABILITIES);
+	if (caps & SVGA_FIFO_CAP_PITCHLOCK)
+		return true;
+
+	return false;
+}
+
+struct vmw_fifo_state *vmw_fifo_create(struct vmw_private *dev_priv)
+{
+	struct vmw_fifo_state *fifo;
+	uint32_t max;
+	uint32_t min;
+
+	if (!dev_priv->fifo_mem)
+		return NULL;
+
+	fifo = kzalloc(sizeof(*fifo), GFP_KERNEL);
+	if (!fifo)
+		return ERR_PTR(-ENOMEM);
+	fifo->static_buffer_size = VMWGFX_FIFO_STATIC_SIZE;
+	fifo->static_buffer = vmalloc(fifo->static_buffer_size);
+	if (unlikely(fifo->static_buffer == NULL)) {
+		kfree(fifo);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	fifo->dynamic_buffer = NULL;
+	fifo->reserved_size = 0;
+	fifo->using_bounce_buffer = false;
+
+	mutex_init(&fifo->fifo_mutex);
+	init_rwsem(&fifo->rwsem);
+	min = 4;
+	if (dev_priv->capabilities & SVGA_CAP_EXTENDED_FIFO)
+		min = vmw_read(dev_priv, SVGA_REG_MEM_REGS);
+	min <<= 2;
+
+	if (min < PAGE_SIZE)
+		min = PAGE_SIZE;
+
+	vmw_fifo_mem_write(dev_priv, SVGA_FIFO_MIN, min);
+	vmw_fifo_mem_write(dev_priv, SVGA_FIFO_MAX, dev_priv->fifo_mem_size);
+	wmb();
+	vmw_fifo_mem_write(dev_priv, SVGA_FIFO_NEXT_CMD, min);
+	vmw_fifo_mem_write(dev_priv, SVGA_FIFO_STOP, min);
+	vmw_fifo_mem_write(dev_priv, SVGA_FIFO_BUSY, 0);
+	mb();
+
+	vmw_write(dev_priv, SVGA_REG_CONFIG_DONE, 1);
+
+	max = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MAX);
+	min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
+	fifo->capabilities = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_CAPABILITIES);
+
+	drm_info(&dev_priv->drm,
+		 "Fifo max 0x%08x min 0x%08x cap 0x%08x\n",
+		 (unsigned int) max,
+		 (unsigned int) min,
+		 (unsigned int) fifo->capabilities);
+
+	if (unlikely(min >= max)) {
+		drm_warn(&dev_priv->drm,
+			 "FIFO memory is not usable. Driver failed to initialize.");
+		return ERR_PTR(-ENXIO);
+	}
+
+	return fifo;
+}
+
+void vmw_fifo_ping_host(struct vmw_private *dev_priv, uint32_t reason)
+{
+	u32 *fifo_mem = dev_priv->fifo_mem;
+	if (fifo_mem && cmpxchg(fifo_mem + SVGA_FIFO_BUSY, 0, 1) == 0)
+		vmw_write(dev_priv, SVGA_REG_SYNC, reason);
+
+}
+
+void vmw_fifo_destroy(struct vmw_private *dev_priv)
+{
+	struct vmw_fifo_state *fifo = dev_priv->fifo;
+
+	if (!fifo)
+		return;
+
+	if (likely(fifo->static_buffer != NULL)) {
+		vfree(fifo->static_buffer);
+		fifo->static_buffer = NULL;
+	}
+
+	if (likely(fifo->dynamic_buffer != NULL)) {
+		vfree(fifo->dynamic_buffer);
+		fifo->dynamic_buffer = NULL;
+	}
+	kfree(fifo);
+	dev_priv->fifo = NULL;
+}
+
+static bool vmw_fifo_is_full(struct vmw_private *dev_priv, uint32_t bytes)
+{
+	uint32_t max = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MAX);
+	uint32_t next_cmd = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_NEXT_CMD);
+	uint32_t min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
+	uint32_t stop = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_STOP);
+
+	return ((max - next_cmd) + (stop - min) <= bytes);
+}
+
+static int vmw_fifo_wait_noirq(struct vmw_private *dev_priv,
+			       uint32_t bytes, bool interruptible,
+			       unsigned long timeout)
+{
+	int ret = 0;
+	unsigned long end_jiffies = jiffies + timeout;
+	DEFINE_WAIT(__wait);
+
+	DRM_INFO("Fifo wait noirq.\n");
+
+	for (;;) {
+		prepare_to_wait(&dev_priv->fifo_queue, &__wait,
+				(interruptible) ?
+				TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+		if (!vmw_fifo_is_full(dev_priv, bytes))
+			break;
+		if (time_after_eq(jiffies, end_jiffies)) {
+			ret = -EBUSY;
+			DRM_ERROR("SVGA device lockup.\n");
+			break;
+		}
+		schedule_timeout(1);
+		if (interruptible && signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+	}
+	finish_wait(&dev_priv->fifo_queue, &__wait);
+	wake_up_all(&dev_priv->fifo_queue);
+	DRM_INFO("Fifo noirq exit.\n");
+	return ret;
+}
+
+static int vmw_fifo_wait(struct vmw_private *dev_priv,
+			 uint32_t bytes, bool interruptible,
+			 unsigned long timeout)
+{
+	long ret = 1L;
+
+	if (likely(!vmw_fifo_is_full(dev_priv, bytes)))
+		return 0;
+
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_FIFOFULL);
+	if (!(dev_priv->capabilities & SVGA_CAP_IRQMASK))
+		return vmw_fifo_wait_noirq(dev_priv, bytes,
+					   interruptible, timeout);
+
+	vmw_generic_waiter_add(dev_priv, SVGA_IRQFLAG_FIFO_PROGRESS,
+			       &dev_priv->fifo_queue_waiters);
+
+	if (interruptible)
+		ret = wait_event_interruptible_timeout
+		    (dev_priv->fifo_queue,
+		     !vmw_fifo_is_full(dev_priv, bytes), timeout);
+	else
+		ret = wait_event_timeout
+		    (dev_priv->fifo_queue,
+		     !vmw_fifo_is_full(dev_priv, bytes), timeout);
+
+	if (unlikely(ret == 0))
+		ret = -EBUSY;
+	else if (likely(ret > 0))
+		ret = 0;
+
+	vmw_generic_waiter_remove(dev_priv, SVGA_IRQFLAG_FIFO_PROGRESS,
+				  &dev_priv->fifo_queue_waiters);
+
+	return ret;
+}
+
+/*
+ * Reserve @bytes number of bytes in the fifo.
+ *
+ * This function will return NULL (error) on two conditions:
+ *  If it timeouts waiting for fifo space, or if @bytes is larger than the
+ *   available fifo space.
+ *
+ * Returns:
+ *   Pointer to the fifo, or null on error (possible hardware hang).
+ */
+static void *vmw_local_fifo_reserve(struct vmw_private *dev_priv,
+				    uint32_t bytes)
+{
+	struct vmw_fifo_state *fifo_state = dev_priv->fifo;
+	u32  *fifo_mem = dev_priv->fifo_mem;
+	uint32_t max;
+	uint32_t min;
+	uint32_t next_cmd;
+	uint32_t reserveable = fifo_state->capabilities & SVGA_FIFO_CAP_RESERVE;
+	int ret;
+
+	mutex_lock(&fifo_state->fifo_mutex);
+	max = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MAX);
+	min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
+	next_cmd = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_NEXT_CMD);
+
+	if (unlikely(bytes >= (max - min)))
+		goto out_err;
+
+	BUG_ON(fifo_state->reserved_size != 0);
+	BUG_ON(fifo_state->dynamic_buffer != NULL);
+
+	fifo_state->reserved_size = bytes;
+
+	while (1) {
+		uint32_t stop = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_STOP);
+		bool need_bounce = false;
+		bool reserve_in_place = false;
+
+		if (next_cmd >= stop) {
+			if (likely((next_cmd + bytes < max ||
+				    (next_cmd + bytes == max && stop > min))))
+				reserve_in_place = true;
+
+			else if (vmw_fifo_is_full(dev_priv, bytes)) {
+				ret = vmw_fifo_wait(dev_priv, bytes,
+						    false, 3 * HZ);
+				if (unlikely(ret != 0))
+					goto out_err;
+			} else
+				need_bounce = true;
+
+		} else {
+
+			if (likely((next_cmd + bytes < stop)))
+				reserve_in_place = true;
+			else {
+				ret = vmw_fifo_wait(dev_priv, bytes,
+						    false, 3 * HZ);
+				if (unlikely(ret != 0))
+					goto out_err;
+			}
+		}
+
+		if (reserve_in_place) {
+			if (reserveable || bytes <= sizeof(uint32_t)) {
+				fifo_state->using_bounce_buffer = false;
+
+				if (reserveable)
+					vmw_fifo_mem_write(dev_priv,
+							   SVGA_FIFO_RESERVED,
+							   bytes);
+				return (void __force *) (fifo_mem +
+							 (next_cmd >> 2));
+			} else {
+				need_bounce = true;
+			}
+		}
+
+		if (need_bounce) {
+			fifo_state->using_bounce_buffer = true;
+			if (bytes < fifo_state->static_buffer_size)
+				return fifo_state->static_buffer;
+			else {
+				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
+				return fifo_state->dynamic_buffer;
+			}
+		}
+	}
+out_err:
+	fifo_state->reserved_size = 0;
+	mutex_unlock(&fifo_state->fifo_mutex);
+
+	return NULL;
+}
+
+void *vmw_cmd_ctx_reserve(struct vmw_private *dev_priv, uint32_t bytes,
+			  int ctx_id)
+{
+	void *ret;
+
+	if (dev_priv->cman)
+		ret = vmw_cmdbuf_reserve(dev_priv->cman, bytes,
+					 ctx_id, false, NULL);
+	else if (ctx_id == SVGA3D_INVALID_ID)
+		ret = vmw_local_fifo_reserve(dev_priv, bytes);
+	else {
+		WARN(1, "Command buffer has not been allocated.\n");
+		ret = NULL;
+	}
+	if (IS_ERR_OR_NULL(ret))
+		return NULL;
+
+	return ret;
+}
+
+static void vmw_fifo_res_copy(struct vmw_fifo_state *fifo_state,
+			      struct vmw_private *vmw,
+			      uint32_t next_cmd,
+			      uint32_t max, uint32_t min, uint32_t bytes)
+{
+	u32 *fifo_mem = vmw->fifo_mem;
+	uint32_t chunk_size = max - next_cmd;
+	uint32_t rest;
+	uint32_t *buffer = (fifo_state->dynamic_buffer != NULL) ?
+	    fifo_state->dynamic_buffer : fifo_state->static_buffer;
+
+	if (bytes < chunk_size)
+		chunk_size = bytes;
+
+	vmw_fifo_mem_write(vmw, SVGA_FIFO_RESERVED, bytes);
+	mb();
+	memcpy(fifo_mem + (next_cmd >> 2), buffer, chunk_size);
+	rest = bytes - chunk_size;
+	if (rest)
+		memcpy(fifo_mem + (min >> 2), buffer + (chunk_size >> 2), rest);
+}
+
+static void vmw_fifo_slow_copy(struct vmw_fifo_state *fifo_state,
+			       struct vmw_private *vmw,
+			       uint32_t next_cmd,
+			       uint32_t max, uint32_t min, uint32_t bytes)
+{
+	uint32_t *buffer = (fifo_state->dynamic_buffer != NULL) ?
+	    fifo_state->dynamic_buffer : fifo_state->static_buffer;
+
+	while (bytes > 0) {
+		vmw_fifo_mem_write(vmw, (next_cmd >> 2), *buffer++);
+		next_cmd += sizeof(uint32_t);
+		if (unlikely(next_cmd == max))
+			next_cmd = min;
+		mb();
+		vmw_fifo_mem_write(vmw, SVGA_FIFO_NEXT_CMD, next_cmd);
+		mb();
+		bytes -= sizeof(uint32_t);
+	}
+}
+
+static void vmw_local_fifo_commit(struct vmw_private *dev_priv, uint32_t bytes)
+{
+	struct vmw_fifo_state *fifo_state = dev_priv->fifo;
+	uint32_t next_cmd = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_NEXT_CMD);
+	uint32_t max = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MAX);
+	uint32_t min = vmw_fifo_mem_read(dev_priv, SVGA_FIFO_MIN);
+	bool reserveable = fifo_state->capabilities & SVGA_FIFO_CAP_RESERVE;
+
+	BUG_ON((bytes & 3) != 0);
+	BUG_ON(bytes > fifo_state->reserved_size);
+
+	fifo_state->reserved_size = 0;
+
+	if (fifo_state->using_bounce_buffer) {
+		if (reserveable)
+			vmw_fifo_res_copy(fifo_state, dev_priv,
+					  next_cmd, max, min, bytes);
+		else
+			vmw_fifo_slow_copy(fifo_state, dev_priv,
+					   next_cmd, max, min, bytes);
+
+		if (fifo_state->dynamic_buffer) {
+			vfree(fifo_state->dynamic_buffer);
+			fifo_state->dynamic_buffer = NULL;
+		}
+
+	}
+
+	down_write(&fifo_state->rwsem);
+	if (fifo_state->using_bounce_buffer || reserveable) {
+		next_cmd += bytes;
+		if (next_cmd >= max)
+			next_cmd -= max - min;
+		mb();
+		vmw_fifo_mem_write(dev_priv, SVGA_FIFO_NEXT_CMD, next_cmd);
+	}
+
+	if (reserveable)
+		vmw_fifo_mem_write(dev_priv, SVGA_FIFO_RESERVED, 0);
+	mb();
+	up_write(&fifo_state->rwsem);
+	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
+	mutex_unlock(&fifo_state->fifo_mutex);
+}
+
+void vmw_cmd_commit(struct vmw_private *dev_priv, uint32_t bytes)
+{
+	if (dev_priv->cman)
+		vmw_cmdbuf_commit(dev_priv->cman, bytes, NULL, false);
+	else
+		vmw_local_fifo_commit(dev_priv, bytes);
+}
+
+
+/**
+ * vmw_cmd_commit_flush - Commit fifo space and flush any buffered commands.
+ *
+ * @dev_priv: Pointer to device private structure.
+ * @bytes: Number of bytes to commit.
+ */
+void vmw_cmd_commit_flush(struct vmw_private *dev_priv, uint32_t bytes)
+{
+	if (dev_priv->cman)
+		vmw_cmdbuf_commit(dev_priv->cman, bytes, NULL, true);
+	else
+		vmw_local_fifo_commit(dev_priv, bytes);
+}
+
+/**
+ * vmw_cmd_flush - Flush any buffered commands and make sure command processing
+ * starts.
+ *
+ * @dev_priv: Pointer to device private structure.
+ * @interruptible: Whether to wait interruptible if function needs to sleep.
+ */
+int vmw_cmd_flush(struct vmw_private *dev_priv, bool interruptible)
+{
+	might_sleep();
+
+	if (dev_priv->cman)
+		return vmw_cmdbuf_cur_flush(dev_priv->cman, interruptible);
+	else
+		return 0;
+}
+
+int vmw_cmd_send_fence(struct vmw_private *dev_priv, uint32_t *seqno)
+{
+	struct svga_fifo_cmd_fence *cmd_fence;
+	u32 *fm;
+	int ret = 0;
+	uint32_t bytes = sizeof(u32) + sizeof(*cmd_fence);
+
+	fm = VMW_CMD_RESERVE(dev_priv, bytes);
+	if (unlikely(fm == NULL)) {
+		*seqno = atomic_read(&dev_priv->marker_seq);
+		ret = -ENOMEM;
+		(void)vmw_fallback_wait(dev_priv, false, true, *seqno,
+					false, 3*HZ);
+		goto out_err;
+	}
+
+	do {
+		*seqno = atomic_add_return(1, &dev_priv->marker_seq);
+	} while (*seqno == 0);
+
+	if (!vmw_has_fences(dev_priv)) {
+
+		/*
+		 * Don't request hardware to send a fence. The
+		 * waiting code in vmwgfx_irq.c will emulate this.
+		 */
+
+		vmw_cmd_commit(dev_priv, 0);
+		return 0;
+	}
+
+	*fm++ = SVGA_CMD_FENCE;
+	cmd_fence = (struct svga_fifo_cmd_fence *) fm;
+	cmd_fence->fence = *seqno;
+	vmw_cmd_commit_flush(dev_priv, bytes);
+	vmw_update_seqno(dev_priv);
+
+out_err:
+	return ret;
+}
+
+/**
+ * vmw_cmd_emit_dummy_legacy_query - emits a dummy query to the fifo using
+ * legacy query commands.
+ *
+ * @dev_priv: The device private structure.
+ * @cid: The hardware context id used for the query.
+ *
+ * See the vmw_cmd_emit_dummy_query documentation.
+ */
+static int vmw_cmd_emit_dummy_legacy_query(struct vmw_private *dev_priv,
+					    uint32_t cid)
+{
+	/*
+	 * A query wait without a preceding query end will
+	 * actually finish all queries for this cid
+	 * without writing to the query result structure.
+	 */
+
+	struct ttm_buffer_object *bo = &dev_priv->dummy_query_bo->base;
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdWaitForQuery body;
+	} *cmd;
+
+	cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd));
+	if (unlikely(cmd == NULL))
+		return -ENOMEM;
+
+	cmd->header.id = SVGA_3D_CMD_WAIT_FOR_QUERY;
+	cmd->header.size = sizeof(cmd->body);
+	cmd->body.cid = cid;
+	cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION;
+
+	if (bo->resource->mem_type == TTM_PL_VRAM) {
+		cmd->body.guestResult.gmrId = SVGA_GMR_FRAMEBUFFER;
+		cmd->body.guestResult.offset = bo->resource->start << PAGE_SHIFT;
+	} else {
+		cmd->body.guestResult.gmrId = bo->resource->start;
+		cmd->body.guestResult.offset = 0;
+	}
+
+	vmw_cmd_commit(dev_priv, sizeof(*cmd));
+
+	return 0;
+}
+
+/**
+ * vmw_cmd_emit_dummy_gb_query - emits a dummy query to the fifo using
+ * guest-backed resource query commands.
+ *
+ * @dev_priv: The device private structure.
+ * @cid: The hardware context id used for the query.
+ *
+ * See the vmw_cmd_emit_dummy_query documentation.
+ */
+static int vmw_cmd_emit_dummy_gb_query(struct vmw_private *dev_priv,
+				       uint32_t cid)
+{
+	/*
+	 * A query wait without a preceding query end will
+	 * actually finish all queries for this cid
+	 * without writing to the query result structure.
+	 */
+
+	struct ttm_buffer_object *bo = &dev_priv->dummy_query_bo->base;
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdWaitForGBQuery body;
+	} *cmd;
+
+	cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd));
+	if (unlikely(cmd == NULL))
+		return -ENOMEM;
+
+	cmd->header.id = SVGA_3D_CMD_WAIT_FOR_GB_QUERY;
+	cmd->header.size = sizeof(cmd->body);
+	cmd->body.cid = cid;
+	cmd->body.type = SVGA3D_QUERYTYPE_OCCLUSION;
+	BUG_ON(bo->resource->mem_type != VMW_PL_MOB);
+	cmd->body.mobid = bo->resource->start;
+	cmd->body.offset = 0;
+
+	vmw_cmd_commit(dev_priv, sizeof(*cmd));
+
+	return 0;
+}
+
+
+/**
+ * vmw_cmd_emit_dummy_query - emits a dummy query to the fifo using
+ * appropriate resource query commands.
+ *
+ * @dev_priv: The device private structure.
+ * @cid: The hardware context id used for the query.
+ *
+ * This function is used to emit a dummy occlusion query with
+ * no primitives rendered between query begin and query end.
+ * It's used to provide a query barrier, in order to know that when
+ * this query is finished, all preceding queries are also finished.
+ *
+ * A Query results structure should have been initialized at the start
+ * of the dev_priv->dummy_query_bo buffer object. And that buffer object
+ * must also be either reserved or pinned when this function is called.
+ *
+ * Returns -ENOMEM on failure to reserve fifo space.
+ */
+int vmw_cmd_emit_dummy_query(struct vmw_private *dev_priv,
+			      uint32_t cid)
+{
+	if (dev_priv->has_mob)
+		return vmw_cmd_emit_dummy_gb_query(dev_priv, cid);
+
+	return vmw_cmd_emit_dummy_legacy_query(dev_priv, cid);
+}
+
+
+/**
+ * vmw_cmd_supported - returns true if the given device supports
+ * command queues.
+ *
+ * @vmw: The device private structure.
+ *
+ * Returns true if we can issue commands.
+ */
+bool vmw_cmd_supported(struct vmw_private *vmw)
+{
+	bool has_cmdbufs =
+		(vmw->capabilities & (SVGA_CAP_COMMAND_BUFFERS |
+				      SVGA_CAP_CMD_BUFFERS_2)) != 0;
+	if (vmw_is_svga_v3(vmw))
+		return (has_cmdbufs &&
+			(vmw->capabilities & SVGA_CAP_GBOBJECTS) != 0);
+	/*
+	 * We have FIFO cmd's
+	 */
+	return has_cmdbufs || vmw->fifo_mem != NULL;
+}