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, 781 insertions, 0 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
new file mode 100644
index 000000000..9f6764bf3
--- /dev/null
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -0,0 +1,781 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/*
+ * Copyright 2020 Advanced Micro Devices, 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: Christian König
+ */
+
+/* Pooling of allocated pages is necessary because changing the caching
+ * attributes on x86 of the linear mapping requires a costly cross CPU TLB
+ * invalidate for those addresses.
+ *
+ * Additional to that allocations from the DMA coherent API are pooled as well
+ * cause they are rather slow compared to alloc_pages+map.
+ */
+
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
+#include <linux/sched/mm.h>
+
+#ifdef CONFIG_X86
+#include <asm/set_memory.h>
+#endif
+
+#include <drm/ttm/ttm_pool.h>
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_tt.h>
+
+#include "ttm_module.h"
+
+/**
+ * struct ttm_pool_dma - Helper object for coherent DMA mappings
+ *
+ * @addr: original DMA address returned for the mapping
+ * @vaddr: original vaddr return for the mapping and order in the lower bits
+ */
+struct ttm_pool_dma {
+	dma_addr_t addr;
+	unsigned long vaddr;
+};
+
+static unsigned long page_pool_size;
+
+MODULE_PARM_DESC(page_pool_size, "Number of pages in the WC/UC/DMA pool");
+module_param(page_pool_size, ulong, 0644);
+
+static atomic_long_t allocated_pages;
+
+static struct ttm_pool_type global_write_combined[MAX_ORDER];
+static struct ttm_pool_type global_uncached[MAX_ORDER];
+
+static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
+static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
+
+static spinlock_t shrinker_lock;
+static struct list_head shrinker_list;
+static struct shrinker mm_shrinker;
+
+/* Allocate pages of size 1 << order with the given gfp_flags */
+static struct page *ttm_pool_alloc_page(struct ttm_pool *pool, gfp_t gfp_flags,
+					unsigned int order)
+{
+	unsigned long attr = DMA_ATTR_FORCE_CONTIGUOUS;
+	struct ttm_pool_dma *dma;
+	struct page *p;
+	void *vaddr;
+
+	/* Don't set the __GFP_COMP flag for higher order allocations.
+	 * Mapping pages directly into an userspace process and calling
+	 * put_page() on a TTM allocated page is illegal.
+	 */
+	if (order)
+		gfp_flags |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN |
+			__GFP_KSWAPD_RECLAIM;
+
+	if (!pool->use_dma_alloc) {
+		p = alloc_pages(gfp_flags, order);
+		if (p)
+			p->private = order;
+		return p;
+	}
+
+	dma = kmalloc(sizeof(*dma), GFP_KERNEL);
+	if (!dma)
+		return NULL;
+
+	if (order)
+		attr |= DMA_ATTR_NO_WARN;
+
+	vaddr = dma_alloc_attrs(pool->dev, (1ULL << order) * PAGE_SIZE,
+				&dma->addr, gfp_flags, attr);
+	if (!vaddr)
+		goto error_free;
+
+	/* TODO: This is an illegal abuse of the DMA API, but we need to rework
+	 * TTM page fault handling and extend the DMA API to clean this up.
+	 */
+	if (is_vmalloc_addr(vaddr))
+		p = vmalloc_to_page(vaddr);
+	else
+		p = virt_to_page(vaddr);
+
+	dma->vaddr = (unsigned long)vaddr | order;
+	p->private = (unsigned long)dma;
+	return p;
+
+error_free:
+	kfree(dma);
+	return NULL;
+}
+
+/* Reset the caching and pages of size 1 << order */
+static void ttm_pool_free_page(struct ttm_pool *pool, enum ttm_caching caching,
+			       unsigned int order, struct page *p)
+{
+	unsigned long attr = DMA_ATTR_FORCE_CONTIGUOUS;
+	struct ttm_pool_dma *dma;
+	void *vaddr;
+
+#ifdef CONFIG_X86
+	/* We don't care that set_pages_wb is inefficient here. This is only
+	 * used when we have to shrink and CPU overhead is irrelevant then.
+	 */
+	if (caching != ttm_cached && !PageHighMem(p))
+		set_pages_wb(p, 1 << order);
+#endif
+
+	if (!pool || !pool->use_dma_alloc) {
+		__free_pages(p, order);
+		return;
+	}
+
+	if (order)
+		attr |= DMA_ATTR_NO_WARN;
+
+	dma = (void *)p->private;
+	vaddr = (void *)(dma->vaddr & PAGE_MASK);
+	dma_free_attrs(pool->dev, (1UL << order) * PAGE_SIZE, vaddr, dma->addr,
+		       attr);
+	kfree(dma);
+}
+
+/* Apply a new caching to an array of pages */
+static int ttm_pool_apply_caching(struct page **first, struct page **last,
+				  enum ttm_caching caching)
+{
+#ifdef CONFIG_X86
+	unsigned int num_pages = last - first;
+
+	if (!num_pages)
+		return 0;
+
+	switch (caching) {
+	case ttm_cached:
+		break;
+	case ttm_write_combined:
+		return set_pages_array_wc(first, num_pages);
+	case ttm_uncached:
+		return set_pages_array_uc(first, num_pages);
+	}
+#endif
+	return 0;
+}
+
+/* Map pages of 1 << order size and fill the DMA address array  */
+static int ttm_pool_map(struct ttm_pool *pool, unsigned int order,
+			struct page *p, dma_addr_t **dma_addr)
+{
+	dma_addr_t addr;
+	unsigned int i;
+
+	if (pool->use_dma_alloc) {
+		struct ttm_pool_dma *dma = (void *)p->private;
+
+		addr = dma->addr;
+	} else {
+		size_t size = (1ULL << order) * PAGE_SIZE;
+
+		addr = dma_map_page(pool->dev, p, 0, size, DMA_BIDIRECTIONAL);
+		if (dma_mapping_error(pool->dev, addr))
+			return -EFAULT;
+	}
+
+	for (i = 1 << order; i ; --i) {
+		*(*dma_addr)++ = addr;
+		addr += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+/* Unmap pages of 1 << order size */
+static void ttm_pool_unmap(struct ttm_pool *pool, dma_addr_t dma_addr,
+			   unsigned int num_pages)
+{
+	/* Unmapped while freeing the page */
+	if (pool->use_dma_alloc)
+		return;
+
+	dma_unmap_page(pool->dev, dma_addr, (long)num_pages << PAGE_SHIFT,
+		       DMA_BIDIRECTIONAL);
+}
+
+/* Give pages into a specific pool_type */
+static void ttm_pool_type_give(struct ttm_pool_type *pt, struct page *p)
+{
+	unsigned int i, num_pages = 1 << pt->order;
+
+	for (i = 0; i < num_pages; ++i) {
+		if (PageHighMem(p))
+			clear_highpage(p + i);
+		else
+			clear_page(page_address(p + i));
+	}
+
+	spin_lock(&pt->lock);
+	list_add(&p->lru, &pt->pages);
+	spin_unlock(&pt->lock);
+	atomic_long_add(1 << pt->order, &allocated_pages);
+}
+
+/* Take pages from a specific pool_type, return NULL when nothing available */
+static struct page *ttm_pool_type_take(struct ttm_pool_type *pt)
+{
+	struct page *p;
+
+	spin_lock(&pt->lock);
+	p = list_first_entry_or_null(&pt->pages, typeof(*p), lru);
+	if (p) {
+		atomic_long_sub(1 << pt->order, &allocated_pages);
+		list_del(&p->lru);
+	}
+	spin_unlock(&pt->lock);
+
+	return p;
+}
+
+/* Initialize and add a pool type to the global shrinker list */
+static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
+			       enum ttm_caching caching, unsigned int order)
+{
+	pt->pool = pool;
+	pt->caching = caching;
+	pt->order = order;
+	spin_lock_init(&pt->lock);
+	INIT_LIST_HEAD(&pt->pages);
+
+	spin_lock(&shrinker_lock);
+	list_add_tail(&pt->shrinker_list, &shrinker_list);
+	spin_unlock(&shrinker_lock);
+}
+
+/* Remove a pool_type from the global shrinker list and free all pages */
+static void ttm_pool_type_fini(struct ttm_pool_type *pt)
+{
+	struct page *p;
+
+	spin_lock(&shrinker_lock);
+	list_del(&pt->shrinker_list);
+	spin_unlock(&shrinker_lock);
+
+	while ((p = ttm_pool_type_take(pt)))
+		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
+}
+
+/* Return the pool_type to use for the given caching and order */
+static struct ttm_pool_type *ttm_pool_select_type(struct ttm_pool *pool,
+						  enum ttm_caching caching,
+						  unsigned int order)
+{
+	if (pool->use_dma_alloc)
+		return &pool->caching[caching].orders[order];
+
+#ifdef CONFIG_X86
+	switch (caching) {
+	case ttm_write_combined:
+		if (pool->use_dma32)
+			return &global_dma32_write_combined[order];
+
+		return &global_write_combined[order];
+	case ttm_uncached:
+		if (pool->use_dma32)
+			return &global_dma32_uncached[order];
+
+		return &global_uncached[order];
+	default:
+		break;
+	}
+#endif
+
+	return NULL;
+}
+
+/* Free pages using the global shrinker list */
+static unsigned int ttm_pool_shrink(void)
+{
+	struct ttm_pool_type *pt;
+	unsigned int num_pages;
+	struct page *p;
+
+	spin_lock(&shrinker_lock);
+	pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
+	list_move_tail(&pt->shrinker_list, &shrinker_list);
+	spin_unlock(&shrinker_lock);
+
+	p = ttm_pool_type_take(pt);
+	if (p) {
+		ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
+		num_pages = 1 << pt->order;
+	} else {
+		num_pages = 0;
+	}
+
+	return num_pages;
+}
+
+/* Return the allocation order based for a page */
+static unsigned int ttm_pool_page_order(struct ttm_pool *pool, struct page *p)
+{
+	if (pool->use_dma_alloc) {
+		struct ttm_pool_dma *dma = (void *)p->private;
+
+		return dma->vaddr & ~PAGE_MASK;
+	}
+
+	return p->private;
+}
+
+/* Called when we got a page, either from a pool or newly allocated */
+static int ttm_pool_page_allocated(struct ttm_pool *pool, unsigned int order,
+				   struct page *p, dma_addr_t **dma_addr,
+				   unsigned long *num_pages,
+				   struct page ***pages)
+{
+	unsigned int i;
+	int r;
+
+	if (*dma_addr) {
+		r = ttm_pool_map(pool, order, p, dma_addr);
+		if (r)
+			return r;
+	}
+
+	*num_pages -= 1 << order;
+	for (i = 1 << order; i; --i, ++(*pages), ++p)
+		**pages = p;
+
+	return 0;
+}
+
+/**
+ * ttm_pool_alloc - Fill a ttm_tt object
+ *
+ * @pool: ttm_pool to use
+ * @tt: ttm_tt object to fill
+ * @ctx: operation context
+ *
+ * Fill the ttm_tt object with pages and also make sure to DMA map them when
+ * necessary.
+ *
+ * Returns: 0 on successe, negative error code otherwise.
+ */
+int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
+		   struct ttm_operation_ctx *ctx)
+{
+	unsigned long num_pages = tt->num_pages;
+	dma_addr_t *dma_addr = tt->dma_address;
+	struct page **caching = tt->pages;
+	struct page **pages = tt->pages;
+	gfp_t gfp_flags = GFP_USER;
+	unsigned int i, order;
+	struct page *p;
+	int r;
+
+	WARN_ON(!num_pages || ttm_tt_is_populated(tt));
+	WARN_ON(dma_addr && !pool->dev);
+
+	if (tt->page_flags & TTM_TT_FLAG_ZERO_ALLOC)
+		gfp_flags |= __GFP_ZERO;
+
+	if (ctx->gfp_retry_mayfail)
+		gfp_flags |= __GFP_RETRY_MAYFAIL;
+
+	if (pool->use_dma32)
+		gfp_flags |= GFP_DMA32;
+	else
+		gfp_flags |= GFP_HIGHUSER;
+
+	for (order = min_t(unsigned int, MAX_ORDER - 1, __fls(num_pages));
+	     num_pages;
+	     order = min_t(unsigned int, order, __fls(num_pages))) {
+		struct ttm_pool_type *pt;
+
+		pt = ttm_pool_select_type(pool, tt->caching, order);
+		p = pt ? ttm_pool_type_take(pt) : NULL;
+		if (p) {
+			r = ttm_pool_apply_caching(caching, pages,
+						   tt->caching);
+			if (r)
+				goto error_free_page;
+
+			do {
+				r = ttm_pool_page_allocated(pool, order, p,
+							    &dma_addr,
+							    &num_pages,
+							    &pages);
+				if (r)
+					goto error_free_page;
+
+				if (num_pages < (1 << order))
+					break;
+
+				p = ttm_pool_type_take(pt);
+			} while (p);
+			caching = pages;
+		}
+
+		while (num_pages >= (1 << order) &&
+		       (p = ttm_pool_alloc_page(pool, gfp_flags, order))) {
+
+			if (PageHighMem(p)) {
+				r = ttm_pool_apply_caching(caching, pages,
+							   tt->caching);
+				if (r)
+					goto error_free_page;
+			}
+			r = ttm_pool_page_allocated(pool, order, p, &dma_addr,
+						    &num_pages, &pages);
+			if (r)
+				goto error_free_page;
+			if (PageHighMem(p))
+				caching = pages;
+		}
+
+		if (!p) {
+			if (order) {
+				--order;
+				continue;
+			}
+			r = -ENOMEM;
+			goto error_free_all;
+		}
+	}
+
+	r = ttm_pool_apply_caching(caching, pages, tt->caching);
+	if (r)
+		goto error_free_all;
+
+	return 0;
+
+error_free_page:
+	ttm_pool_free_page(pool, tt->caching, order, p);
+
+error_free_all:
+	num_pages = tt->num_pages - num_pages;
+	for (i = 0; i < num_pages; ) {
+		order = ttm_pool_page_order(pool, tt->pages[i]);
+		ttm_pool_free_page(pool, tt->caching, order, tt->pages[i]);
+		i += 1 << order;
+	}
+
+	return r;
+}
+EXPORT_SYMBOL(ttm_pool_alloc);
+
+/**
+ * ttm_pool_free - Free the backing pages from a ttm_tt object
+ *
+ * @pool: Pool to give pages back to.
+ * @tt: ttm_tt object to unpopulate
+ *
+ * Give the packing pages back to a pool or free them
+ */
+void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt)
+{
+	unsigned int i;
+
+	for (i = 0; i < tt->num_pages; ) {
+		struct page *p = tt->pages[i];
+		unsigned int order, num_pages;
+		struct ttm_pool_type *pt;
+
+		order = ttm_pool_page_order(pool, p);
+		num_pages = 1ULL << order;
+		if (tt->dma_address)
+			ttm_pool_unmap(pool, tt->dma_address[i], num_pages);
+
+		pt = ttm_pool_select_type(pool, tt->caching, order);
+		if (pt)
+			ttm_pool_type_give(pt, tt->pages[i]);
+		else
+			ttm_pool_free_page(pool, tt->caching, order,
+					   tt->pages[i]);
+
+		i += num_pages;
+	}
+
+	while (atomic_long_read(&allocated_pages) > page_pool_size)
+		ttm_pool_shrink();
+}
+EXPORT_SYMBOL(ttm_pool_free);
+
+/**
+ * ttm_pool_init - Initialize a pool
+ *
+ * @pool: the pool to initialize
+ * @dev: device for DMA allocations and mappings
+ * @use_dma_alloc: true if coherent DMA alloc should be used
+ * @use_dma32: true if GFP_DMA32 should be used
+ *
+ * Initialize the pool and its pool types.
+ */
+void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
+		   bool use_dma_alloc, bool use_dma32)
+{
+	unsigned int i, j;
+
+	WARN_ON(!dev && use_dma_alloc);
+
+	pool->dev = dev;
+	pool->use_dma_alloc = use_dma_alloc;
+	pool->use_dma32 = use_dma32;
+
+	if (use_dma_alloc) {
+		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
+			for (j = 0; j < MAX_ORDER; ++j)
+				ttm_pool_type_init(&pool->caching[i].orders[j],
+						   pool, i, j);
+	}
+}
+
+/**
+ * ttm_pool_fini - Cleanup a pool
+ *
+ * @pool: the pool to clean up
+ *
+ * Free all pages in the pool and unregister the types from the global
+ * shrinker.
+ */
+void ttm_pool_fini(struct ttm_pool *pool)
+{
+	unsigned int i, j;
+
+	if (pool->use_dma_alloc) {
+		for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i)
+			for (j = 0; j < MAX_ORDER; ++j)
+				ttm_pool_type_fini(&pool->caching[i].orders[j]);
+	}
+
+	/* We removed the pool types from the LRU, but we need to also make sure
+	 * that no shrinker is concurrently freeing pages from the pool.
+	 */
+	synchronize_shrinkers();
+}
+
+/* As long as pages are available make sure to release at least one */
+static unsigned long ttm_pool_shrinker_scan(struct shrinker *shrink,
+					    struct shrink_control *sc)
+{
+	unsigned long num_freed = 0;
+
+	do
+		num_freed += ttm_pool_shrink();
+	while (!num_freed && atomic_long_read(&allocated_pages));
+
+	return num_freed;
+}
+
+/* Return the number of pages available or SHRINK_EMPTY if we have none */
+static unsigned long ttm_pool_shrinker_count(struct shrinker *shrink,
+					     struct shrink_control *sc)
+{
+	unsigned long num_pages = atomic_long_read(&allocated_pages);
+
+	return num_pages ? num_pages : SHRINK_EMPTY;
+}
+
+#ifdef CONFIG_DEBUG_FS
+/* Count the number of pages available in a pool_type */
+static unsigned int ttm_pool_type_count(struct ttm_pool_type *pt)
+{
+	unsigned int count = 0;
+	struct page *p;
+
+	spin_lock(&pt->lock);
+	/* Only used for debugfs, the overhead doesn't matter */
+	list_for_each_entry(p, &pt->pages, lru)
+		++count;
+	spin_unlock(&pt->lock);
+
+	return count;
+}
+
+/* Print a nice header for the order */
+static void ttm_pool_debugfs_header(struct seq_file *m)
+{
+	unsigned int i;
+
+	seq_puts(m, "\t ");
+	for (i = 0; i < MAX_ORDER; ++i)
+		seq_printf(m, " ---%2u---", i);
+	seq_puts(m, "\n");
+}
+
+/* Dump information about the different pool types */
+static void ttm_pool_debugfs_orders(struct ttm_pool_type *pt,
+				    struct seq_file *m)
+{
+	unsigned int i;
+
+	for (i = 0; i < MAX_ORDER; ++i)
+		seq_printf(m, " %8u", ttm_pool_type_count(&pt[i]));
+	seq_puts(m, "\n");
+}
+
+/* Dump the total amount of allocated pages */
+static void ttm_pool_debugfs_footer(struct seq_file *m)
+{
+	seq_printf(m, "\ntotal\t: %8lu of %8lu\n",
+		   atomic_long_read(&allocated_pages), page_pool_size);
+}
+
+/* Dump the information for the global pools */
+static int ttm_pool_debugfs_globals_show(struct seq_file *m, void *data)
+{
+	ttm_pool_debugfs_header(m);
+
+	spin_lock(&shrinker_lock);
+	seq_puts(m, "wc\t:");
+	ttm_pool_debugfs_orders(global_write_combined, m);
+	seq_puts(m, "uc\t:");
+	ttm_pool_debugfs_orders(global_uncached, m);
+	seq_puts(m, "wc 32\t:");
+	ttm_pool_debugfs_orders(global_dma32_write_combined, m);
+	seq_puts(m, "uc 32\t:");
+	ttm_pool_debugfs_orders(global_dma32_uncached, m);
+	spin_unlock(&shrinker_lock);
+
+	ttm_pool_debugfs_footer(m);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ttm_pool_debugfs_globals);
+
+/**
+ * ttm_pool_debugfs - Debugfs dump function for a pool
+ *
+ * @pool: the pool to dump the information for
+ * @m: seq_file to dump to
+ *
+ * Make a debugfs dump with the per pool and global information.
+ */
+int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
+{
+	unsigned int i;
+
+	if (!pool->use_dma_alloc) {
+		seq_puts(m, "unused\n");
+		return 0;
+	}
+
+	ttm_pool_debugfs_header(m);
+
+	spin_lock(&shrinker_lock);
+	for (i = 0; i < TTM_NUM_CACHING_TYPES; ++i) {
+		seq_puts(m, "DMA ");
+		switch (i) {
+		case ttm_cached:
+			seq_puts(m, "\t:");
+			break;
+		case ttm_write_combined:
+			seq_puts(m, "wc\t:");
+			break;
+		case ttm_uncached:
+			seq_puts(m, "uc\t:");
+			break;
+		}
+		ttm_pool_debugfs_orders(pool->caching[i].orders, m);
+	}
+	spin_unlock(&shrinker_lock);
+
+	ttm_pool_debugfs_footer(m);
+	return 0;
+}
+EXPORT_SYMBOL(ttm_pool_debugfs);
+
+/* Test the shrinker functions and dump the result */
+static int ttm_pool_debugfs_shrink_show(struct seq_file *m, void *data)
+{
+	struct shrink_control sc = { .gfp_mask = GFP_NOFS };
+
+	fs_reclaim_acquire(GFP_KERNEL);
+	seq_printf(m, "%lu/%lu\n", ttm_pool_shrinker_count(&mm_shrinker, &sc),
+		   ttm_pool_shrinker_scan(&mm_shrinker, &sc));
+	fs_reclaim_release(GFP_KERNEL);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ttm_pool_debugfs_shrink);
+
+#endif
+
+/**
+ * ttm_pool_mgr_init - Initialize globals
+ *
+ * @num_pages: default number of pages
+ *
+ * Initialize the global locks and lists for the MM shrinker.
+ */
+int ttm_pool_mgr_init(unsigned long num_pages)
+{
+	unsigned int i;
+
+	if (!page_pool_size)
+		page_pool_size = num_pages;
+
+	spin_lock_init(&shrinker_lock);
+	INIT_LIST_HEAD(&shrinker_list);
+
+	for (i = 0; i < MAX_ORDER; ++i) {
+		ttm_pool_type_init(&global_write_combined[i], NULL,
+				   ttm_write_combined, i);
+		ttm_pool_type_init(&global_uncached[i], NULL, ttm_uncached, i);
+
+		ttm_pool_type_init(&global_dma32_write_combined[i], NULL,
+				   ttm_write_combined, i);
+		ttm_pool_type_init(&global_dma32_uncached[i], NULL,
+				   ttm_uncached, i);
+	}
+
+#ifdef CONFIG_DEBUG_FS
+	debugfs_create_file("page_pool", 0444, ttm_debugfs_root, NULL,
+			    &ttm_pool_debugfs_globals_fops);
+	debugfs_create_file("page_pool_shrink", 0400, ttm_debugfs_root, NULL,
+			    &ttm_pool_debugfs_shrink_fops);
+#endif
+
+	mm_shrinker.count_objects = ttm_pool_shrinker_count;
+	mm_shrinker.scan_objects = ttm_pool_shrinker_scan;
+	mm_shrinker.seeks = 1;
+	return register_shrinker(&mm_shrinker, "drm-ttm_pool");
+}
+
+/**
+ * ttm_pool_mgr_fini - Finalize globals
+ *
+ * Cleanup the global pools and unregister the MM shrinker.
+ */
+void ttm_pool_mgr_fini(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < MAX_ORDER; ++i) {
+		ttm_pool_type_fini(&global_write_combined[i]);
+		ttm_pool_type_fini(&global_uncached[i]);
+
+		ttm_pool_type_fini(&global_dma32_write_combined[i]);
+		ttm_pool_type_fini(&global_dma32_uncached[i]);
+	}
+
+	unregister_shrinker(&mm_shrinker);
+	WARN_ON(!list_empty(&shrinker_list));
+}