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, 651 insertions, 0 deletions

diff --git a/drivers/gpu/drm/qxl/qxl_cmd.c b/drivers/gpu/drm/qxl/qxl_cmd.c
new file mode 100644
index 000000000..63aa96a69
--- /dev/null
+++ b/drivers/gpu/drm/qxl/qxl_cmd.c
@@ -0,0 +1,651 @@
+/*
+ * Copyright 2013 Red Hat Inc.
+ *
+ * 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, sublicense,
+ * 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 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 NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) 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.
+ *
+ * Authors: Dave Airlie
+ *          Alon Levy
+ */
+
+/* QXL cmd/ring handling */
+
+#include <linux/delay.h>
+
+#include <drm/drm_util.h>
+
+#include "qxl_drv.h"
+#include "qxl_object.h"
+
+static int qxl_reap_surface_id(struct qxl_device *qdev, int max_to_reap);
+
+struct ring {
+	struct qxl_ring_header      header;
+	uint8_t                     elements[];
+};
+
+struct qxl_ring {
+	struct ring	       *ring;
+	int			element_size;
+	int			n_elements;
+	int			prod_notify;
+	wait_queue_head_t      *push_event;
+	spinlock_t             lock;
+};
+
+void qxl_ring_free(struct qxl_ring *ring)
+{
+	kfree(ring);
+}
+
+struct qxl_ring *
+qxl_ring_create(struct qxl_ring_header *header,
+		int element_size,
+		int n_elements,
+		int prod_notify,
+		wait_queue_head_t *push_event)
+{
+	struct qxl_ring *ring;
+
+	ring = kmalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring)
+		return NULL;
+
+	ring->ring = (struct ring *)header;
+	ring->element_size = element_size;
+	ring->n_elements = n_elements;
+	ring->prod_notify = prod_notify;
+	ring->push_event = push_event;
+	spin_lock_init(&ring->lock);
+	return ring;
+}
+
+static int qxl_check_header(struct qxl_ring *ring)
+{
+	int ret;
+	struct qxl_ring_header *header = &(ring->ring->header);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	ret = header->prod - header->cons < header->num_items;
+	if (ret == 0)
+		header->notify_on_cons = header->cons + 1;
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return ret;
+}
+
+int qxl_check_idle(struct qxl_ring *ring)
+{
+	int ret;
+	struct qxl_ring_header *header = &(ring->ring->header);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	ret = header->prod == header->cons;
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return ret;
+}
+
+int qxl_ring_push(struct qxl_ring *ring,
+		  const void *new_elt, bool interruptible)
+{
+	struct qxl_ring_header *header = &(ring->ring->header);
+	uint8_t *elt;
+	int idx, ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	if (header->prod - header->cons == header->num_items) {
+		header->notify_on_cons = header->cons + 1;
+		mb();
+		spin_unlock_irqrestore(&ring->lock, flags);
+		if (!drm_can_sleep()) {
+			while (!qxl_check_header(ring))
+				udelay(1);
+		} else {
+			if (interruptible) {
+				ret = wait_event_interruptible(*ring->push_event,
+							       qxl_check_header(ring));
+				if (ret)
+					return ret;
+			} else {
+				wait_event(*ring->push_event,
+					   qxl_check_header(ring));
+			}
+
+		}
+		spin_lock_irqsave(&ring->lock, flags);
+	}
+
+	idx = header->prod & (ring->n_elements - 1);
+	elt = ring->ring->elements + idx * ring->element_size;
+
+	memcpy((void *)elt, new_elt, ring->element_size);
+
+	header->prod++;
+
+	mb();
+
+	if (header->prod == header->notify_on_prod)
+		outb(0, ring->prod_notify);
+
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return 0;
+}
+
+static bool qxl_ring_pop(struct qxl_ring *ring,
+			 void *element)
+{
+	volatile struct qxl_ring_header *header = &(ring->ring->header);
+	volatile uint8_t *ring_elt;
+	int idx;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ring->lock, flags);
+	if (header->cons == header->prod) {
+		header->notify_on_prod = header->cons + 1;
+		spin_unlock_irqrestore(&ring->lock, flags);
+		return false;
+	}
+
+	idx = header->cons & (ring->n_elements - 1);
+	ring_elt = ring->ring->elements + idx * ring->element_size;
+
+	memcpy(element, (void *)ring_elt, ring->element_size);
+
+	header->cons++;
+
+	spin_unlock_irqrestore(&ring->lock, flags);
+	return true;
+}
+
+int
+qxl_push_command_ring_release(struct qxl_device *qdev, struct qxl_release *release,
+			      uint32_t type, bool interruptible)
+{
+	struct qxl_command cmd;
+
+	cmd.type = type;
+	cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
+
+	return qxl_ring_push(qdev->command_ring, &cmd, interruptible);
+}
+
+int
+qxl_push_cursor_ring_release(struct qxl_device *qdev, struct qxl_release *release,
+			     uint32_t type, bool interruptible)
+{
+	struct qxl_command cmd;
+
+	cmd.type = type;
+	cmd.data = qxl_bo_physical_address(qdev, release->release_bo, release->release_offset);
+
+	return qxl_ring_push(qdev->cursor_ring, &cmd, interruptible);
+}
+
+bool qxl_queue_garbage_collect(struct qxl_device *qdev, bool flush)
+{
+	if (!qxl_check_idle(qdev->release_ring)) {
+		schedule_work(&qdev->gc_work);
+		if (flush)
+			flush_work(&qdev->gc_work);
+		return true;
+	}
+	return false;
+}
+
+int qxl_garbage_collect(struct qxl_device *qdev)
+{
+	struct qxl_release *release;
+	uint64_t id, next_id;
+	int i = 0;
+	union qxl_release_info *info;
+
+	while (qxl_ring_pop(qdev->release_ring, &id)) {
+		DRM_DEBUG_DRIVER("popped %lld\n", id);
+		while (id) {
+			release = qxl_release_from_id_locked(qdev, id);
+			if (release == NULL)
+				break;
+
+			info = qxl_release_map(qdev, release);
+			next_id = info->next;
+			qxl_release_unmap(qdev, release, info);
+
+			DRM_DEBUG_DRIVER("popped %lld, next %lld\n", id,
+					 next_id);
+
+			switch (release->type) {
+			case QXL_RELEASE_DRAWABLE:
+			case QXL_RELEASE_SURFACE_CMD:
+			case QXL_RELEASE_CURSOR_CMD:
+				break;
+			default:
+				DRM_ERROR("unexpected release type\n");
+				break;
+			}
+			id = next_id;
+
+			qxl_release_free(qdev, release);
+			++i;
+		}
+	}
+
+	wake_up_all(&qdev->release_event);
+	DRM_DEBUG_DRIVER("%d\n", i);
+
+	return i;
+}
+
+int qxl_alloc_bo_reserved(struct qxl_device *qdev,
+			  struct qxl_release *release,
+			  unsigned long size,
+			  struct qxl_bo **_bo)
+{
+	struct qxl_bo *bo;
+	int ret;
+
+	ret = qxl_bo_create(qdev, size, false /* not kernel - device */,
+			    false, QXL_GEM_DOMAIN_VRAM, 0, NULL, &bo);
+	if (ret) {
+		DRM_ERROR("failed to allocate VRAM BO\n");
+		return ret;
+	}
+	ret = qxl_release_list_add(release, bo);
+	if (ret)
+		goto out_unref;
+
+	*_bo = bo;
+	return 0;
+out_unref:
+	qxl_bo_unref(&bo);
+	return ret;
+}
+
+static int wait_for_io_cmd_user(struct qxl_device *qdev, uint8_t val, long port, bool intr)
+{
+	int irq_num;
+	long addr = qdev->io_base + port;
+	int ret;
+
+	mutex_lock(&qdev->async_io_mutex);
+	irq_num = atomic_read(&qdev->irq_received_io_cmd);
+	if (qdev->last_sent_io_cmd > irq_num) {
+		if (intr)
+			ret = wait_event_interruptible_timeout(qdev->io_cmd_event,
+							       atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+		else
+			ret = wait_event_timeout(qdev->io_cmd_event,
+						 atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+		/* 0 is timeout, just bail the "hw" has gone away */
+		if (ret <= 0)
+			goto out;
+		irq_num = atomic_read(&qdev->irq_received_io_cmd);
+	}
+	outb(val, addr);
+	qdev->last_sent_io_cmd = irq_num + 1;
+	if (intr)
+		ret = wait_event_interruptible_timeout(qdev->io_cmd_event,
+						       atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+	else
+		ret = wait_event_timeout(qdev->io_cmd_event,
+					 atomic_read(&qdev->irq_received_io_cmd) > irq_num, 5*HZ);
+out:
+	if (ret > 0)
+		ret = 0;
+	mutex_unlock(&qdev->async_io_mutex);
+	return ret;
+}
+
+static void wait_for_io_cmd(struct qxl_device *qdev, uint8_t val, long port)
+{
+	int ret;
+
+restart:
+	ret = wait_for_io_cmd_user(qdev, val, port, false);
+	if (ret == -ERESTARTSYS)
+		goto restart;
+}
+
+int qxl_io_update_area(struct qxl_device *qdev, struct qxl_bo *surf,
+			const struct qxl_rect *area)
+{
+	int surface_id;
+	uint32_t surface_width, surface_height;
+	int ret;
+
+	if (!surf->hw_surf_alloc)
+		DRM_ERROR("got io update area with no hw surface\n");
+
+	if (surf->is_primary)
+		surface_id = 0;
+	else
+		surface_id = surf->surface_id;
+	surface_width = surf->surf.width;
+	surface_height = surf->surf.height;
+
+	if (area->left < 0 || area->top < 0 ||
+	    area->right > surface_width || area->bottom > surface_height)
+		return -EINVAL;
+
+	mutex_lock(&qdev->update_area_mutex);
+	qdev->ram_header->update_area = *area;
+	qdev->ram_header->update_surface = surface_id;
+	ret = wait_for_io_cmd_user(qdev, 0, QXL_IO_UPDATE_AREA_ASYNC, true);
+	mutex_unlock(&qdev->update_area_mutex);
+	return ret;
+}
+
+void qxl_io_notify_oom(struct qxl_device *qdev)
+{
+	outb(0, qdev->io_base + QXL_IO_NOTIFY_OOM);
+}
+
+void qxl_io_flush_release(struct qxl_device *qdev)
+{
+	outb(0, qdev->io_base + QXL_IO_FLUSH_RELEASE);
+}
+
+void qxl_io_flush_surfaces(struct qxl_device *qdev)
+{
+	wait_for_io_cmd(qdev, 0, QXL_IO_FLUSH_SURFACES_ASYNC);
+}
+
+void qxl_io_destroy_primary(struct qxl_device *qdev)
+{
+	wait_for_io_cmd(qdev, 0, QXL_IO_DESTROY_PRIMARY_ASYNC);
+	qdev->primary_bo->is_primary = false;
+	drm_gem_object_put(&qdev->primary_bo->tbo.base);
+	qdev->primary_bo = NULL;
+}
+
+void qxl_io_create_primary(struct qxl_device *qdev, struct qxl_bo *bo)
+{
+	struct qxl_surface_create *create;
+
+	if (WARN_ON(qdev->primary_bo))
+		return;
+
+	DRM_DEBUG_DRIVER("qdev %p, ram_header %p\n", qdev, qdev->ram_header);
+	create = &qdev->ram_header->create_surface;
+	create->format = bo->surf.format;
+	create->width = bo->surf.width;
+	create->height = bo->surf.height;
+	create->stride = bo->surf.stride;
+	create->mem = qxl_bo_physical_address(qdev, bo, 0);
+
+	DRM_DEBUG_DRIVER("mem = %llx, from %p\n", create->mem, bo->kptr);
+
+	create->flags = QXL_SURF_FLAG_KEEP_DATA;
+	create->type = QXL_SURF_TYPE_PRIMARY;
+
+	wait_for_io_cmd(qdev, 0, QXL_IO_CREATE_PRIMARY_ASYNC);
+	qdev->primary_bo = bo;
+	qdev->primary_bo->is_primary = true;
+	drm_gem_object_get(&qdev->primary_bo->tbo.base);
+}
+
+void qxl_io_memslot_add(struct qxl_device *qdev, uint8_t id)
+{
+	DRM_DEBUG_DRIVER("qxl_memslot_add %d\n", id);
+	wait_for_io_cmd(qdev, id, QXL_IO_MEMSLOT_ADD_ASYNC);
+}
+
+void qxl_io_reset(struct qxl_device *qdev)
+{
+	outb(0, qdev->io_base + QXL_IO_RESET);
+}
+
+void qxl_io_monitors_config(struct qxl_device *qdev)
+{
+	wait_for_io_cmd(qdev, 0, QXL_IO_MONITORS_CONFIG_ASYNC);
+}
+
+int qxl_surface_id_alloc(struct qxl_device *qdev,
+		      struct qxl_bo *surf)
+{
+	uint32_t handle;
+	int idr_ret;
+	int count = 0;
+again:
+	idr_preload(GFP_ATOMIC);
+	spin_lock(&qdev->surf_id_idr_lock);
+	idr_ret = idr_alloc(&qdev->surf_id_idr, NULL, 1, 0, GFP_NOWAIT);
+	spin_unlock(&qdev->surf_id_idr_lock);
+	idr_preload_end();
+	if (idr_ret < 0)
+		return idr_ret;
+	handle = idr_ret;
+
+	if (handle >= qdev->rom->n_surfaces) {
+		count++;
+		spin_lock(&qdev->surf_id_idr_lock);
+		idr_remove(&qdev->surf_id_idr, handle);
+		spin_unlock(&qdev->surf_id_idr_lock);
+		qxl_reap_surface_id(qdev, 2);
+		goto again;
+	}
+	surf->surface_id = handle;
+
+	spin_lock(&qdev->surf_id_idr_lock);
+	qdev->last_alloced_surf_id = handle;
+	spin_unlock(&qdev->surf_id_idr_lock);
+	return 0;
+}
+
+void qxl_surface_id_dealloc(struct qxl_device *qdev,
+			    uint32_t surface_id)
+{
+	spin_lock(&qdev->surf_id_idr_lock);
+	idr_remove(&qdev->surf_id_idr, surface_id);
+	spin_unlock(&qdev->surf_id_idr_lock);
+}
+
+int qxl_hw_surface_alloc(struct qxl_device *qdev,
+			 struct qxl_bo *surf)
+{
+	struct qxl_surface_cmd *cmd;
+	struct qxl_release *release;
+	int ret;
+
+	if (surf->hw_surf_alloc)
+		return 0;
+
+	ret = qxl_alloc_surface_release_reserved(qdev, QXL_SURFACE_CMD_CREATE,
+						 NULL,
+						 &release);
+	if (ret)
+		return ret;
+
+	ret = qxl_release_reserve_list(release, true);
+	if (ret) {
+		qxl_release_free(qdev, release);
+		return ret;
+	}
+	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
+	cmd->type = QXL_SURFACE_CMD_CREATE;
+	cmd->flags = QXL_SURF_FLAG_KEEP_DATA;
+	cmd->u.surface_create.format = surf->surf.format;
+	cmd->u.surface_create.width = surf->surf.width;
+	cmd->u.surface_create.height = surf->surf.height;
+	cmd->u.surface_create.stride = surf->surf.stride;
+	cmd->u.surface_create.data = qxl_bo_physical_address(qdev, surf, 0);
+	cmd->surface_id = surf->surface_id;
+	qxl_release_unmap(qdev, release, &cmd->release_info);
+
+	surf->surf_create = release;
+
+	/* no need to add a release to the fence for this surface bo,
+	   since it is only released when we ask to destroy the surface
+	   and it would never signal otherwise */
+	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
+
+	surf->hw_surf_alloc = true;
+	spin_lock(&qdev->surf_id_idr_lock);
+	idr_replace(&qdev->surf_id_idr, surf, surf->surface_id);
+	spin_unlock(&qdev->surf_id_idr_lock);
+	return 0;
+}
+
+int qxl_hw_surface_dealloc(struct qxl_device *qdev,
+			   struct qxl_bo *surf)
+{
+	struct qxl_surface_cmd *cmd;
+	struct qxl_release *release;
+	int ret;
+	int id;
+
+	if (!surf->hw_surf_alloc)
+		return 0;
+
+	ret = qxl_alloc_surface_release_reserved(qdev, QXL_SURFACE_CMD_DESTROY,
+						 surf->surf_create,
+						 &release);
+	if (ret)
+		return ret;
+
+	surf->surf_create = NULL;
+	/* remove the surface from the idr, but not the surface id yet */
+	spin_lock(&qdev->surf_id_idr_lock);
+	idr_replace(&qdev->surf_id_idr, NULL, surf->surface_id);
+	spin_unlock(&qdev->surf_id_idr_lock);
+	surf->hw_surf_alloc = false;
+
+	id = surf->surface_id;
+	surf->surface_id = 0;
+
+	release->surface_release_id = id;
+	cmd = (struct qxl_surface_cmd *)qxl_release_map(qdev, release);
+	cmd->type = QXL_SURFACE_CMD_DESTROY;
+	cmd->surface_id = id;
+	qxl_release_unmap(qdev, release, &cmd->release_info);
+
+	qxl_release_fence_buffer_objects(release);
+	qxl_push_command_ring_release(qdev, release, QXL_CMD_SURFACE, false);
+
+	return 0;
+}
+
+static int qxl_update_surface(struct qxl_device *qdev, struct qxl_bo *surf)
+{
+	struct qxl_rect rect;
+	int ret;
+
+	/* if we are evicting, we need to make sure the surface is up
+	   to date */
+	rect.left = 0;
+	rect.right = surf->surf.width;
+	rect.top = 0;
+	rect.bottom = surf->surf.height;
+retry:
+	ret = qxl_io_update_area(qdev, surf, &rect);
+	if (ret == -ERESTARTSYS)
+		goto retry;
+	return ret;
+}
+
+static void qxl_surface_evict_locked(struct qxl_device *qdev, struct qxl_bo *surf, bool do_update_area)
+{
+	/* no need to update area if we are just freeing the surface normally */
+	if (do_update_area)
+		qxl_update_surface(qdev, surf);
+
+	/* nuke the surface id at the hw */
+	qxl_hw_surface_dealloc(qdev, surf);
+}
+
+void qxl_surface_evict(struct qxl_device *qdev, struct qxl_bo *surf, bool do_update_area)
+{
+	mutex_lock(&qdev->surf_evict_mutex);
+	qxl_surface_evict_locked(qdev, surf, do_update_area);
+	mutex_unlock(&qdev->surf_evict_mutex);
+}
+
+static int qxl_reap_surf(struct qxl_device *qdev, struct qxl_bo *surf, bool stall)
+{
+	int ret;
+
+	ret = qxl_bo_reserve(surf);
+	if (ret)
+		return ret;
+
+	if (stall)
+		mutex_unlock(&qdev->surf_evict_mutex);
+
+	ret = ttm_bo_wait(&surf->tbo, true, !stall);
+
+	if (stall)
+		mutex_lock(&qdev->surf_evict_mutex);
+	if (ret) {
+		qxl_bo_unreserve(surf);
+		return ret;
+	}
+
+	qxl_surface_evict_locked(qdev, surf, true);
+	qxl_bo_unreserve(surf);
+	return 0;
+}
+
+static int qxl_reap_surface_id(struct qxl_device *qdev, int max_to_reap)
+{
+	int num_reaped = 0;
+	int i, ret;
+	bool stall = false;
+	int start = 0;
+
+	mutex_lock(&qdev->surf_evict_mutex);
+again:
+
+	spin_lock(&qdev->surf_id_idr_lock);
+	start = qdev->last_alloced_surf_id + 1;
+	spin_unlock(&qdev->surf_id_idr_lock);
+
+	for (i = start; i < start + qdev->rom->n_surfaces; i++) {
+		void *objptr;
+		int surfid = i % qdev->rom->n_surfaces;
+
+		/* this avoids the case where the objects is in the
+		   idr but has been evicted half way - its makes
+		   the idr lookup atomic with the eviction */
+		spin_lock(&qdev->surf_id_idr_lock);
+		objptr = idr_find(&qdev->surf_id_idr, surfid);
+		spin_unlock(&qdev->surf_id_idr_lock);
+
+		if (!objptr)
+			continue;
+
+		ret = qxl_reap_surf(qdev, objptr, stall);
+		if (ret == 0)
+			num_reaped++;
+		if (num_reaped >= max_to_reap)
+			break;
+	}
+	if (num_reaped == 0 && stall == false) {
+		stall = true;
+		goto again;
+	}
+
+	mutex_unlock(&qdev->surf_evict_mutex);
+	if (num_reaped) {
+		usleep_range(500, 1000);
+		qxl_queue_garbage_collect(qdev, true);
+	}
+
+	return 0;
+}