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, 493 insertions, 0 deletions

diff --git a/arch/arm/mach-omap2/sleep43xx.S b/arch/arm/mach-omap2/sleep43xx.S
new file mode 100644
index 000000000..832c91327
--- /dev/null
+++ b/arch/arm/mach-omap2/sleep43xx.S
@@ -0,0 +1,493 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Low level suspend code for AM43XX SoCs
+ *
+ * Copyright (C) 2013-2018 Texas Instruments Incorporated - https://www.ti.com/
+ *	Dave Gerlach, Vaibhav Bedia
+ */
+
+#include <linux/linkage.h>
+#include <linux/ti-emif-sram.h>
+#include <linux/platform_data/pm33xx.h>
+#include <asm/assembler.h>
+#include <asm/hardware/cache-l2x0.h>
+#include <asm/memory.h>
+
+#include "cm33xx.h"
+#include "common.h"
+#include "iomap.h"
+#include "omap-secure.h"
+#include "omap44xx.h"
+#include "pm-asm-offsets.h"
+#include "prm33xx.h"
+#include "prcm43xx.h"
+
+/* replicated define because linux/bitops.h cannot be included in assembly */
+#define BIT(nr)			(1 << (nr))
+
+#define AM33XX_CM_CLKCTRL_MODULESTATE_DISABLED		0x00030000
+#define AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE		0x0003
+#define AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE		0x0002
+
+#define AM43XX_EMIF_POWEROFF_ENABLE			0x1
+#define AM43XX_EMIF_POWEROFF_DISABLE			0x0
+
+#define AM43XX_CM_CLKSTCTRL_CLKTRCTRL_SW_SLEEP		0x1
+#define AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO		0x3
+
+#define AM43XX_CM_BASE					0x44DF0000
+
+#define AM43XX_CM_REGADDR(inst, reg)                           \
+       AM33XX_L4_WK_IO_ADDRESS(AM43XX_CM_BASE + (inst) + (reg))
+
+#define AM43XX_CM_MPU_CLKSTCTRL AM43XX_CM_REGADDR(AM43XX_CM_MPU_INST, \
+					AM43XX_CM_MPU_MPU_CDOFFS)
+#define AM43XX_CM_MPU_MPU_CLKCTRL AM43XX_CM_REGADDR(AM43XX_CM_MPU_INST, \
+					AM43XX_CM_MPU_MPU_CLKCTRL_OFFSET)
+#define AM43XX_CM_PER_EMIF_CLKCTRL  AM43XX_CM_REGADDR(AM43XX_CM_PER_INST, \
+					AM43XX_CM_PER_EMIF_CLKCTRL_OFFSET)
+#define AM43XX_PRM_EMIF_CTRL_OFFSET			0x0030
+
+#define RTC_SECONDS_REG					0x0
+#define RTC_PMIC_REG					0x98
+#define RTC_PMIC_POWER_EN				BIT(16)
+#define RTC_PMIC_EXT_WAKEUP_STS				BIT(12)
+#define RTC_PMIC_EXT_WAKEUP_POL				BIT(4)
+#define RTC_PMIC_EXT_WAKEUP_EN				BIT(0)
+
+	.arm
+	.arch armv7-a
+	.arch_extension sec
+	.align 3
+
+ENTRY(am43xx_do_wfi)
+	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
+
+	/* Save wfi_flags arg to data space */
+	mov	r4, r0
+	adr	r3, am43xx_pm_ro_sram_data
+	ldr	r2, [r3, #AMX3_PM_RO_SRAM_DATA_VIRT_OFFSET]
+	str	r4, [r2, #AMX3_PM_WFI_FLAGS_OFFSET]
+
+#ifdef CONFIG_CACHE_L2X0
+	/* Retrieve l2 cache virt address BEFORE we shut off EMIF */
+	ldr	r1, get_l2cache_base
+	blx	r1
+	mov	r8, r0
+#endif
+
+	/* Only flush cache is we know we are losing MPU context */
+	tst	r4, #WFI_FLAG_FLUSH_CACHE
+	beq	cache_skip_flush
+
+	/*
+	 * Flush all data from the L1 and L2 data cache before disabling
+	 * SCTLR.C bit.
+	 */
+	ldr	r1, kernel_flush
+	blx	r1
+
+	/*
+	 * Clear the SCTLR.C bit to prevent further data cache
+	 * allocation. Clearing SCTLR.C would make all the data accesses
+	 * strongly ordered and would not hit the cache.
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	bic	r0, r0, #(1 << 2)	@ Disable the C bit
+	mcr	p15, 0, r0, c1, c0, 0
+	isb
+	dsb
+
+	/*
+	 * Invalidate L1 and L2 data cache.
+	 */
+	ldr	r1, kernel_flush
+	blx	r1
+
+#ifdef CONFIG_CACHE_L2X0
+	/*
+	 * Clean and invalidate the L2 cache.
+	 */
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x03
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+	mov	r0, r8
+	adr	r4, am43xx_pm_ro_sram_data
+	ldr	r3, [r4, #AMX3_PM_RO_SRAM_DATA_VIRT_OFFSET]
+
+	mov	r2, r0
+	ldr	r0, [r2, #L2X0_AUX_CTRL]
+	str	r0, [r3, #AMX3_PM_L2_AUX_CTRL_VAL_OFFSET]
+	ldr	r0, [r2, #L310_PREFETCH_CTRL]
+	str	r0, [r3, #AMX3_PM_L2_PREFETCH_CTRL_VAL_OFFSET]
+
+	ldr	r0, l2_val
+	str	r0, [r2, #L2X0_CLEAN_INV_WAY]
+wait:
+	ldr	r0, [r2, #L2X0_CLEAN_INV_WAY]
+	ldr	r1, l2_val
+	ands	r0, r0, r1
+	bne	wait
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x00
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+l2x_sync:
+	mov	r0, r8
+	mov	r2, r0
+	mov	r0, #0x0
+	str	r0, [r2, #L2X0_CACHE_SYNC]
+sync:
+	ldr	r0, [r2, #L2X0_CACHE_SYNC]
+	ands	r0, r0, #0x1
+	bne	sync
+#endif
+
+	/* Restore wfi_flags */
+	adr	r3, am43xx_pm_ro_sram_data
+	ldr	r2, [r3, #AMX3_PM_RO_SRAM_DATA_VIRT_OFFSET]
+	ldr	r4, [r2, #AMX3_PM_WFI_FLAGS_OFFSET]
+
+cache_skip_flush:
+	/*
+	 * If we are trying to enter RTC+DDR mode we must perform
+	 * a read from the rtc address space to ensure translation
+	 * presence in the TLB to avoid page table walk after DDR
+	 * is unavailable.
+	 */
+	tst	r4, #WFI_FLAG_RTC_ONLY
+	beq	skip_rtc_va_refresh
+
+	adr	r3, am43xx_pm_ro_sram_data
+	ldr	r1, [r3, #AMX3_PM_RTC_BASE_VIRT_OFFSET]
+	ldr	r0, [r1]
+
+skip_rtc_va_refresh:
+	/* Check if we want self refresh */
+	tst	r4, #WFI_FLAG_SELF_REFRESH
+	beq	emif_skip_enter_sr
+
+	adr     r9, am43xx_emif_sram_table
+
+	ldr     r3, [r9, #EMIF_PM_ENTER_SR_OFFSET]
+	blx     r3
+
+emif_skip_enter_sr:
+	/* Only necessary if PER is losing context */
+	tst	r4, #WFI_FLAG_SAVE_EMIF
+	beq	emif_skip_save
+
+	ldr     r3, [r9, #EMIF_PM_SAVE_CONTEXT_OFFSET]
+	blx	r3
+
+emif_skip_save:
+	/* Only can disable EMIF if we have entered self refresh */
+	tst	r4, #WFI_FLAG_SELF_REFRESH
+	beq	emif_skip_disable
+
+	/* Disable EMIF */
+	ldr	r1, am43xx_virt_emif_clkctrl
+	ldr	r2, [r1]
+	bic	r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str	r2, [r1]
+
+wait_emif_disable:
+	ldr	r2, [r1]
+	mov	r3, #AM33XX_CM_CLKCTRL_MODULESTATE_DISABLED
+	cmp	r2, r3
+	bne	wait_emif_disable
+
+emif_skip_disable:
+	tst	r4, #WFI_FLAG_RTC_ONLY
+	beq	skip_rtc_only
+
+	adr	r3, am43xx_pm_ro_sram_data
+	ldr	r1, [r3, #AMX3_PM_RTC_BASE_VIRT_OFFSET]
+
+	ldr	r0, [r1, #RTC_PMIC_REG]
+	orr	r0, r0, #RTC_PMIC_POWER_EN
+	orr	r0, r0, #RTC_PMIC_EXT_WAKEUP_STS
+	orr	r0, r0, #RTC_PMIC_EXT_WAKEUP_EN
+	orr	r0, r0, #RTC_PMIC_EXT_WAKEUP_POL
+	str	r0, [r1, #RTC_PMIC_REG]
+	ldr	r0, [r1, #RTC_PMIC_REG]
+	/* Wait for 2 seconds to lose power */
+	mov	r3, #2
+	ldr	r2, [r1, #RTC_SECONDS_REG]
+rtc_loop:
+	ldr	r0, [r1, #RTC_SECONDS_REG]
+	cmp	r0, r2
+	beq	rtc_loop
+	mov	r2, r0
+	subs	r3, r3, #1
+	bne	rtc_loop
+
+	b	re_enable_emif
+
+skip_rtc_only:
+
+	tst	r4, #WFI_FLAG_WAKE_M3
+	beq	wkup_m3_skip
+
+	/*
+	 * For the MPU WFI to be registered as an interrupt
+	 * to WKUP_M3, MPU_CLKCTRL.MODULEMODE needs to be set
+	 * to DISABLED
+	 */
+	ldr	r1, am43xx_virt_mpu_clkctrl
+	ldr	r2, [r1]
+	bic	r2, r2, #AM33XX_CM_CLKCTRL_MODULEMODE_DISABLE
+	str	r2, [r1]
+
+	/*
+	 * Put MPU CLKDM to SW_SLEEP
+	 */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_SW_SLEEP
+	str	r2, [r1]
+
+wkup_m3_skip:
+	/*
+	 * Execute a barrier instruction to ensure that all cache,
+	 * TLB and branch predictor maintenance operations issued
+	 * have completed.
+	 */
+	dsb
+	dmb
+
+	/*
+	 * Execute a WFI instruction and wait until the
+	 * STANDBYWFI output is asserted to indicate that the
+	 * CPU is in idle and low power state. CPU can specualatively
+	 * prefetch the instructions so add NOPs after WFI. Sixteen
+	 * NOPs as per Cortex-A9 pipeline.
+	 */
+	wfi
+
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* We come here in case of an abort due to a late interrupt */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO
+	str	r2, [r1]
+
+	/* Set MPU_CLKCTRL.MODULEMODE back to ENABLE */
+	ldr	r1, am43xx_virt_mpu_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+
+re_enable_emif:
+	/* Re-enable EMIF */
+	ldr	r1, am43xx_virt_emif_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+wait_emif_enable:
+	ldr	r3, [r1]
+	cmp	r2, r3
+	bne	wait_emif_enable
+
+	tst	r4, #WFI_FLAG_FLUSH_CACHE
+	beq	cache_skip_restore
+
+	/*
+	 * Set SCTLR.C bit to allow data cache allocation
+	 */
+	mrc	p15, 0, r0, c1, c0, 0
+	orr	r0, r0, #(1 << 2)	@ Enable the C bit
+	mcr	p15, 0, r0, c1, c0, 0
+	isb
+
+cache_skip_restore:
+	/* Only necessary if PER is losing context */
+	tst	r4, #WFI_FLAG_SELF_REFRESH
+	beq	emif_skip_exit_sr_abt
+
+	adr	r9, am43xx_emif_sram_table
+	ldr	r1, [r9, #EMIF_PM_ABORT_SR_OFFSET]
+	blx	r1
+
+emif_skip_exit_sr_abt:
+	/* Let the suspend code know about the abort */
+	mov	r0, #1
+	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
+ENDPROC(am43xx_do_wfi)
+
+	.align
+ENTRY(am43xx_resume_offset)
+	.word . - am43xx_do_wfi
+
+ENTRY(am43xx_resume_from_deep_sleep)
+	/* Set MPU CLKSTCTRL to HW AUTO so that CPUidle works properly */
+	ldr	r1, am43xx_virt_mpu_clkstctrl
+	mov	r2, #AM43XX_CM_CLKSTCTRL_CLKTRCTRL_HW_AUTO
+	str	r2, [r1]
+
+	/* For AM43xx, use EMIF power down until context is restored */
+	ldr	r2, am43xx_phys_emif_poweroff
+	mov	r1, #AM43XX_EMIF_POWEROFF_ENABLE
+	str	r1, [r2, #0x0]
+
+	/* Re-enable EMIF */
+	ldr	r1, am43xx_phys_emif_clkctrl
+	mov	r2, #AM33XX_CM_CLKCTRL_MODULEMODE_ENABLE
+	str	r2, [r1]
+wait_emif_enable1:
+	ldr	r3, [r1]
+	cmp	r2, r3
+	bne	wait_emif_enable1
+
+	adr     r9, am43xx_emif_sram_table
+
+	ldr     r1, [r9, #EMIF_PM_RESTORE_CONTEXT_OFFSET]
+	blx     r1
+
+	ldr     r1, [r9, #EMIF_PM_EXIT_SR_OFFSET]
+	blx     r1
+
+	ldr     r2, am43xx_phys_emif_poweroff
+	mov     r1, #AM43XX_EMIF_POWEROFF_DISABLE
+	str     r1, [r2, #0x0]
+
+	ldr     r1, [r9, #EMIF_PM_RUN_HW_LEVELING]
+	blx     r1
+
+#ifdef CONFIG_CACHE_L2X0
+	ldr	r2, l2_cache_base
+	ldr	r0, [r2, #L2X0_CTRL]
+	and	r0, #0x0f
+	cmp	r0, #1
+	beq	skip_l2en			@ Skip if already enabled
+
+	adr	r4, am43xx_pm_ro_sram_data
+	ldr	r3, [r4, #AMX3_PM_RO_SRAM_DATA_PHYS_OFFSET]
+	ldr     r0, [r3, #AMX3_PM_L2_PREFETCH_CTRL_VAL_OFFSET]
+
+	ldr	r12, l2_smc1
+	dsb
+	smc	#0
+	dsb
+set_aux_ctrl:
+	ldr     r0, [r3, #AMX3_PM_L2_AUX_CTRL_VAL_OFFSET]
+	ldr	r12, l2_smc2
+	dsb
+	smc	#0
+	dsb
+
+	/* L2 invalidate on resume */
+	ldr	r0, l2_val
+	ldr	r2, l2_cache_base
+	str	r0, [r2, #L2X0_INV_WAY]
+wait2:
+	ldr	r0, [r2, #L2X0_INV_WAY]
+	ldr	r1, l2_val
+	ands	r0, r0, r1
+	bne	wait2
+#ifdef CONFIG_PL310_ERRATA_727915
+	mov	r0, #0x00
+	mov	r12, #OMAP4_MON_L2X0_DBG_CTRL_INDEX
+	dsb
+	smc	#0
+	dsb
+#endif
+l2x_sync2:
+	ldr	r2, l2_cache_base
+	mov	r0, #0x0
+	str	r0, [r2, #L2X0_CACHE_SYNC]
+sync2:
+	ldr	r0, [r2, #L2X0_CACHE_SYNC]
+	ands	r0, r0, #0x1
+	bne	sync2
+
+	mov	r0, #0x1
+	ldr	r12, l2_smc3
+	dsb
+	smc	#0
+	dsb
+#endif
+skip_l2en:
+	/* We are back. Branch to the common CPU resume routine */
+	mov	r0, #0
+	ldr	pc, resume_addr
+ENDPROC(am43xx_resume_from_deep_sleep)
+
+/*
+ * Local variables
+ */
+	.align
+kernel_flush:
+	.word   v7_flush_dcache_all
+ddr_start:
+	.word	PAGE_OFFSET
+
+am43xx_phys_emif_poweroff:
+	.word   (AM43XX_CM_BASE + AM43XX_PRM_DEVICE_INST + \
+		 AM43XX_PRM_EMIF_CTRL_OFFSET)
+am43xx_virt_mpu_clkstctrl:
+	.word	(AM43XX_CM_MPU_CLKSTCTRL)
+am43xx_virt_mpu_clkctrl:
+	.word	(AM43XX_CM_MPU_MPU_CLKCTRL)
+am43xx_virt_emif_clkctrl:
+	.word	(AM43XX_CM_PER_EMIF_CLKCTRL)
+am43xx_phys_emif_clkctrl:
+	.word	(AM43XX_CM_BASE + AM43XX_CM_PER_INST + \
+		 AM43XX_CM_PER_EMIF_CLKCTRL_OFFSET)
+
+#ifdef CONFIG_CACHE_L2X0
+/* L2 cache related defines for AM437x */
+get_l2cache_base:
+	.word	omap4_get_l2cache_base
+l2_cache_base:
+	.word	OMAP44XX_L2CACHE_BASE
+l2_smc1:
+	.word	OMAP4_MON_L2X0_PREFETCH_INDEX
+l2_smc2:
+	.word	OMAP4_MON_L2X0_AUXCTRL_INDEX
+l2_smc3:
+	.word	OMAP4_MON_L2X0_CTRL_INDEX
+l2_val:
+	.word	0xffff
+#endif
+
+.align 3
+/* DDR related defines */
+ENTRY(am43xx_emif_sram_table)
+	.space EMIF_PM_FUNCTIONS_SIZE
+
+ENTRY(am43xx_pm_sram)
+	.word am43xx_do_wfi
+	.word am43xx_do_wfi_sz
+	.word am43xx_resume_offset
+	.word am43xx_emif_sram_table
+	.word am43xx_pm_ro_sram_data
+
+resume_addr:
+	.word   cpu_resume - PAGE_OFFSET + 0x80000000
+.align 3
+
+ENTRY(am43xx_pm_ro_sram_data)
+	.space AMX3_PM_RO_SRAM_DATA_SIZE
+
+ENTRY(am43xx_do_wfi_sz)
+	.word	. - am43xx_do_wfi