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, 503 insertions, 0 deletions

diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
new file mode 100644
index 000000000..e9e384908
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -0,0 +1,503 @@
+/*
+ * Copyright © 2017 Intel Corporation
+ *
+ * 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 (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 NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS 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.
+ *
+ */
+
+#ifndef __INTEL_UNCORE_H__
+#define __INTEL_UNCORE_H__
+
+#include <linux/spinlock.h>
+#include <linux/notifier.h>
+#include <linux/hrtimer.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+#include <linux/types.h>
+
+#include "i915_reg_defs.h"
+
+struct drm_device;
+struct drm_i915_private;
+struct intel_runtime_pm;
+struct intel_uncore;
+struct intel_gt;
+
+struct intel_uncore_mmio_debug {
+	spinlock_t lock; /** lock is also taken in irq contexts. */
+	int unclaimed_mmio_check;
+	int saved_mmio_check;
+	u32 suspend_count;
+};
+
+enum forcewake_domain_id {
+	FW_DOMAIN_ID_RENDER = 0,
+	FW_DOMAIN_ID_GT,        /* also includes blitter engine */
+	FW_DOMAIN_ID_MEDIA,
+	FW_DOMAIN_ID_MEDIA_VDBOX0,
+	FW_DOMAIN_ID_MEDIA_VDBOX1,
+	FW_DOMAIN_ID_MEDIA_VDBOX2,
+	FW_DOMAIN_ID_MEDIA_VDBOX3,
+	FW_DOMAIN_ID_MEDIA_VDBOX4,
+	FW_DOMAIN_ID_MEDIA_VDBOX5,
+	FW_DOMAIN_ID_MEDIA_VDBOX6,
+	FW_DOMAIN_ID_MEDIA_VDBOX7,
+	FW_DOMAIN_ID_MEDIA_VEBOX0,
+	FW_DOMAIN_ID_MEDIA_VEBOX1,
+	FW_DOMAIN_ID_MEDIA_VEBOX2,
+	FW_DOMAIN_ID_MEDIA_VEBOX3,
+	FW_DOMAIN_ID_GSC,
+
+	FW_DOMAIN_ID_COUNT
+};
+
+enum forcewake_domains {
+	FORCEWAKE_RENDER	= BIT(FW_DOMAIN_ID_RENDER),
+	FORCEWAKE_GT		= BIT(FW_DOMAIN_ID_GT),
+	FORCEWAKE_MEDIA		= BIT(FW_DOMAIN_ID_MEDIA),
+	FORCEWAKE_MEDIA_VDBOX0	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX0),
+	FORCEWAKE_MEDIA_VDBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX1),
+	FORCEWAKE_MEDIA_VDBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX2),
+	FORCEWAKE_MEDIA_VDBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX3),
+	FORCEWAKE_MEDIA_VDBOX4	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX4),
+	FORCEWAKE_MEDIA_VDBOX5	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX5),
+	FORCEWAKE_MEDIA_VDBOX6	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX6),
+	FORCEWAKE_MEDIA_VDBOX7	= BIT(FW_DOMAIN_ID_MEDIA_VDBOX7),
+	FORCEWAKE_MEDIA_VEBOX0	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX0),
+	FORCEWAKE_MEDIA_VEBOX1	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX1),
+	FORCEWAKE_MEDIA_VEBOX2	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX2),
+	FORCEWAKE_MEDIA_VEBOX3	= BIT(FW_DOMAIN_ID_MEDIA_VEBOX3),
+	FORCEWAKE_GSC		= BIT(FW_DOMAIN_ID_GSC),
+
+	FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1,
+};
+
+struct intel_uncore_fw_get {
+	void (*force_wake_get)(struct intel_uncore *uncore,
+			       enum forcewake_domains domains);
+};
+
+struct intel_uncore_funcs {
+	enum forcewake_domains (*read_fw_domains)(struct intel_uncore *uncore,
+						  i915_reg_t r);
+	enum forcewake_domains (*write_fw_domains)(struct intel_uncore *uncore,
+						   i915_reg_t r);
+
+	u8 (*mmio_readb)(struct intel_uncore *uncore,
+			 i915_reg_t r, bool trace);
+	u16 (*mmio_readw)(struct intel_uncore *uncore,
+			  i915_reg_t r, bool trace);
+	u32 (*mmio_readl)(struct intel_uncore *uncore,
+			  i915_reg_t r, bool trace);
+	u64 (*mmio_readq)(struct intel_uncore *uncore,
+			  i915_reg_t r, bool trace);
+
+	void (*mmio_writeb)(struct intel_uncore *uncore,
+			    i915_reg_t r, u8 val, bool trace);
+	void (*mmio_writew)(struct intel_uncore *uncore,
+			    i915_reg_t r, u16 val, bool trace);
+	void (*mmio_writel)(struct intel_uncore *uncore,
+			    i915_reg_t r, u32 val, bool trace);
+};
+
+struct intel_forcewake_range {
+	u32 start;
+	u32 end;
+
+	enum forcewake_domains domains;
+};
+
+/* Other register ranges (e.g., shadow tables, MCR tables, etc.) */
+struct i915_range {
+	u32 start;
+	u32 end;
+};
+
+struct intel_uncore {
+	void __iomem *regs;
+
+	struct drm_i915_private *i915;
+	struct intel_gt *gt;
+	struct intel_runtime_pm *rpm;
+
+	spinlock_t lock; /** lock is also taken in irq contexts. */
+
+	/*
+	 * Do we need to apply an additional offset to reach the beginning
+	 * of the basic non-engine GT registers (referred to as "GSI" on
+	 * newer platforms, or "GT block" on older platforms)?  If so, we'll
+	 * track that here and apply it transparently to registers in the
+	 * appropriate range to maintain compatibility with our existing
+	 * register definitions and GT code.
+	 */
+	u32 gsi_offset;
+
+	unsigned int flags;
+#define UNCORE_HAS_FORCEWAKE		BIT(0)
+#define UNCORE_HAS_FPGA_DBG_UNCLAIMED	BIT(1)
+#define UNCORE_HAS_DBG_UNCLAIMED	BIT(2)
+#define UNCORE_HAS_FIFO			BIT(3)
+
+	const struct intel_forcewake_range *fw_domains_table;
+	unsigned int fw_domains_table_entries;
+
+	/*
+	 * Shadowed registers are special cases where we can safely write
+	 * to the register *without* grabbing forcewake.
+	 */
+	const struct i915_range *shadowed_reg_table;
+	unsigned int shadowed_reg_table_entries;
+
+	struct notifier_block pmic_bus_access_nb;
+	const struct intel_uncore_fw_get *fw_get_funcs;
+	struct intel_uncore_funcs funcs;
+
+	unsigned int fifo_count;
+
+	enum forcewake_domains fw_domains;
+	enum forcewake_domains fw_domains_active;
+	enum forcewake_domains fw_domains_timer;
+	enum forcewake_domains fw_domains_saved; /* user domains saved for S3 */
+
+	struct intel_uncore_forcewake_domain {
+		struct intel_uncore *uncore;
+		enum forcewake_domain_id id;
+		enum forcewake_domains mask;
+		unsigned int wake_count;
+		bool active;
+		struct hrtimer timer;
+		u32 __iomem *reg_set;
+		u32 __iomem *reg_ack;
+	} *fw_domain[FW_DOMAIN_ID_COUNT];
+
+	unsigned int user_forcewake_count;
+
+	struct intel_uncore_mmio_debug *debug;
+};
+
+/* Iterate over initialised fw domains */
+#define for_each_fw_domain_masked(domain__, mask__, uncore__, tmp__) \
+	for (tmp__ = (mask__); tmp__ ;) \
+		for_each_if(domain__ = (uncore__)->fw_domain[__mask_next_bit(tmp__)])
+
+#define for_each_fw_domain(domain__, uncore__, tmp__) \
+	for_each_fw_domain_masked(domain__, (uncore__)->fw_domains, uncore__, tmp__)
+
+static inline bool
+intel_uncore_has_forcewake(const struct intel_uncore *uncore)
+{
+	return uncore->flags & UNCORE_HAS_FORCEWAKE;
+}
+
+static inline bool
+intel_uncore_has_fpga_dbg_unclaimed(const struct intel_uncore *uncore)
+{
+	return uncore->flags & UNCORE_HAS_FPGA_DBG_UNCLAIMED;
+}
+
+static inline bool
+intel_uncore_has_dbg_unclaimed(const struct intel_uncore *uncore)
+{
+	return uncore->flags & UNCORE_HAS_DBG_UNCLAIMED;
+}
+
+static inline bool
+intel_uncore_has_fifo(const struct intel_uncore *uncore)
+{
+	return uncore->flags & UNCORE_HAS_FIFO;
+}
+
+void intel_uncore_mmio_debug_init_early(struct drm_i915_private *i915);
+void intel_uncore_init_early(struct intel_uncore *uncore,
+			     struct intel_gt *gt);
+int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr);
+int intel_uncore_init_mmio(struct intel_uncore *uncore);
+void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
+					  struct intel_gt *gt);
+bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore);
+bool intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore);
+void intel_uncore_cleanup_mmio(struct intel_uncore *uncore);
+void intel_uncore_fini_mmio(struct drm_device *dev, void *data);
+void intel_uncore_suspend(struct intel_uncore *uncore);
+void intel_uncore_resume_early(struct intel_uncore *uncore);
+void intel_uncore_runtime_resume(struct intel_uncore *uncore);
+
+void assert_forcewakes_inactive(struct intel_uncore *uncore);
+void assert_forcewakes_active(struct intel_uncore *uncore,
+			      enum forcewake_domains fw_domains);
+const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id);
+
+enum forcewake_domains
+intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
+			       i915_reg_t reg, unsigned int op);
+#define FW_REG_READ  (1)
+#define FW_REG_WRITE (2)
+
+void intel_uncore_forcewake_get(struct intel_uncore *uncore,
+				enum forcewake_domains domains);
+void intel_uncore_forcewake_put(struct intel_uncore *uncore,
+				enum forcewake_domains domains);
+void intel_uncore_forcewake_put_delayed(struct intel_uncore *uncore,
+					enum forcewake_domains domains);
+void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
+				  enum forcewake_domains fw_domains);
+
+/*
+ * Like above but the caller must manage the uncore.lock itself.
+ * Must be used with intel_uncore_read_fw() and friends.
+ */
+void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
+					enum forcewake_domains domains);
+void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore,
+					enum forcewake_domains domains);
+
+void intel_uncore_forcewake_user_get(struct intel_uncore *uncore);
+void intel_uncore_forcewake_user_put(struct intel_uncore *uncore);
+
+int __intel_wait_for_register(struct intel_uncore *uncore,
+			      i915_reg_t reg,
+			      u32 mask,
+			      u32 value,
+			      unsigned int fast_timeout_us,
+			      unsigned int slow_timeout_ms,
+			      u32 *out_value);
+static inline int
+intel_wait_for_register(struct intel_uncore *uncore,
+			i915_reg_t reg,
+			u32 mask,
+			u32 value,
+			unsigned int timeout_ms)
+{
+	return __intel_wait_for_register(uncore, reg, mask, value, 2,
+					 timeout_ms, NULL);
+}
+
+int __intel_wait_for_register_fw(struct intel_uncore *uncore,
+				 i915_reg_t reg,
+				 u32 mask,
+				 u32 value,
+				 unsigned int fast_timeout_us,
+				 unsigned int slow_timeout_ms,
+				 u32 *out_value);
+static inline int
+intel_wait_for_register_fw(struct intel_uncore *uncore,
+			   i915_reg_t reg,
+			   u32 mask,
+			   u32 value,
+			       unsigned int timeout_ms)
+{
+	return __intel_wait_for_register_fw(uncore, reg, mask, value,
+					    2, timeout_ms, NULL);
+}
+
+#define IS_GSI_REG(reg) ((reg) < 0x40000)
+
+/* register access functions */
+#define __raw_read(x__, s__) \
+static inline u##x__ __raw_uncore_read##x__(const struct intel_uncore *uncore, \
+					    i915_reg_t reg) \
+{ \
+	u32 offset = i915_mmio_reg_offset(reg); \
+	if (IS_GSI_REG(offset)) \
+		offset += uncore->gsi_offset; \
+	return read##s__(uncore->regs + offset); \
+}
+
+#define __raw_write(x__, s__) \
+static inline void __raw_uncore_write##x__(const struct intel_uncore *uncore, \
+					   i915_reg_t reg, u##x__ val) \
+{ \
+	u32 offset = i915_mmio_reg_offset(reg); \
+	if (IS_GSI_REG(offset)) \
+		offset += uncore->gsi_offset; \
+	write##s__(val, uncore->regs + offset); \
+}
+__raw_read(8, b)
+__raw_read(16, w)
+__raw_read(32, l)
+__raw_read(64, q)
+
+__raw_write(8, b)
+__raw_write(16, w)
+__raw_write(32, l)
+__raw_write(64, q)
+
+#undef __raw_read
+#undef __raw_write
+
+#define __uncore_read(name__, x__, s__, trace__) \
+static inline u##x__ intel_uncore_##name__(struct intel_uncore *uncore, \
+					   i915_reg_t reg) \
+{ \
+	return uncore->funcs.mmio_read##s__(uncore, reg, (trace__)); \
+}
+
+#define __uncore_write(name__, x__, s__, trace__) \
+static inline void intel_uncore_##name__(struct intel_uncore *uncore, \
+					 i915_reg_t reg, u##x__ val) \
+{ \
+	uncore->funcs.mmio_write##s__(uncore, reg, val, (trace__)); \
+}
+
+__uncore_read(read8, 8, b, true)
+__uncore_read(read16, 16, w, true)
+__uncore_read(read, 32, l, true)
+__uncore_read(read16_notrace, 16, w, false)
+__uncore_read(read_notrace, 32, l, false)
+
+__uncore_write(write8, 8, b, true)
+__uncore_write(write16, 16, w, true)
+__uncore_write(write, 32, l, true)
+__uncore_write(write_notrace, 32, l, false)
+
+/* Be very careful with read/write 64-bit values. On 32-bit machines, they
+ * will be implemented using 2 32-bit writes in an arbitrary order with
+ * an arbitrary delay between them. This can cause the hardware to
+ * act upon the intermediate value, possibly leading to corruption and
+ * machine death. For this reason we do not support intel_uncore_write64,
+ * or uncore->funcs.mmio_writeq.
+ *
+ * When reading a 64-bit value as two 32-bit values, the delay may cause
+ * the two reads to mismatch, e.g. a timestamp overflowing. Also note that
+ * occasionally a 64-bit register does not actually support a full readq
+ * and must be read using two 32-bit reads.
+ *
+ * You have been warned.
+ */
+__uncore_read(read64, 64, q, true)
+
+#define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__))
+#define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__))
+
+#undef __uncore_read
+#undef __uncore_write
+
+/* These are untraced mmio-accessors that are only valid to be used inside
+ * critical sections, such as inside IRQ handlers, where forcewake is explicitly
+ * controlled.
+ *
+ * Think twice, and think again, before using these.
+ *
+ * As an example, these accessors can possibly be used between:
+ *
+ * spin_lock_irq(&uncore->lock);
+ * intel_uncore_forcewake_get__locked();
+ *
+ * and
+ *
+ * intel_uncore_forcewake_put__locked();
+ * spin_unlock_irq(&uncore->lock);
+ *
+ *
+ * Note: some registers may not need forcewake held, so
+ * intel_uncore_forcewake_{get,put} can be omitted, see
+ * intel_uncore_forcewake_for_reg().
+ *
+ * Certain architectures will die if the same cacheline is concurrently accessed
+ * by different clients (e.g. on Ivybridge). Access to registers should
+ * therefore generally be serialised, by either the dev_priv->uncore.lock or
+ * a more localised lock guarding all access to that bank of registers.
+ */
+#define intel_uncore_read_fw(...) __raw_uncore_read32(__VA_ARGS__)
+#define intel_uncore_write_fw(...) __raw_uncore_write32(__VA_ARGS__)
+#define intel_uncore_write64_fw(...) __raw_uncore_write64(__VA_ARGS__)
+#define intel_uncore_posting_read_fw(...) ((void)intel_uncore_read_fw(__VA_ARGS__))
+
+static inline u32 intel_uncore_rmw(struct intel_uncore *uncore,
+				   i915_reg_t reg, u32 clear, u32 set)
+{
+	u32 old, val;
+
+	old = intel_uncore_read(uncore, reg);
+	val = (old & ~clear) | set;
+	intel_uncore_write(uncore, reg, val);
+	return old;
+}
+
+static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
+				       i915_reg_t reg, u32 clear, u32 set)
+{
+	u32 old, val;
+
+	old = intel_uncore_read_fw(uncore, reg);
+	val = (old & ~clear) | set;
+	if (val != old)
+		intel_uncore_write_fw(uncore, reg, val);
+}
+
+static inline u64
+intel_uncore_read64_2x32(struct intel_uncore *uncore,
+			 i915_reg_t lower_reg, i915_reg_t upper_reg)
+{
+	u32 upper, lower, old_upper, loop = 0;
+	enum forcewake_domains fw_domains;
+	unsigned long flags;
+
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg,
+						    FW_REG_READ);
+
+	fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg,
+						    FW_REG_READ);
+
+	spin_lock_irqsave(&uncore->lock, flags);
+	intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+	upper = intel_uncore_read_fw(uncore, upper_reg);
+	do {
+		old_upper = upper;
+		lower = intel_uncore_read_fw(uncore, lower_reg);
+		upper = intel_uncore_read_fw(uncore, upper_reg);
+	} while (upper != old_upper && loop++ < 2);
+
+	intel_uncore_forcewake_put__locked(uncore, fw_domains);
+	spin_unlock_irqrestore(&uncore->lock, flags);
+
+	return (u64)upper << 32 | lower;
+}
+
+static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
+						i915_reg_t reg, u32 val,
+						u32 mask, u32 expected_val)
+{
+	u32 reg_val;
+
+	intel_uncore_write(uncore, reg, val);
+	reg_val = intel_uncore_read(uncore, reg);
+
+	return (reg_val & mask) != expected_val ? -EINVAL : 0;
+}
+
+/*
+ * The raw_reg_{read,write} macros are intended as a micro-optimization for
+ * interrupt handlers so that the pointer indirection on uncore->regs can
+ * be computed once (and presumably cached in a register) instead of generating
+ * extra load instructions for each MMIO access.
+ *
+ * Given that these macros are only intended for non-GSI interrupt registers
+ * (and the goal is to avoid extra instructions generated by the compiler),
+ * these macros do not account for uncore->gsi_offset.  Any caller that needs
+ * to use these macros on a GSI register is responsible for adding the
+ * appropriate GSI offset to the 'base' parameter.
+ */
+#define raw_reg_read(base, reg) \
+	readl(base + i915_mmio_reg_offset(reg))
+#define raw_reg_write(base, reg, value) \
+	writel(value, base + i915_mmio_reg_offset(reg))
+
+#endif /* !__INTEL_UNCORE_H__ */