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, 569 insertions, 0 deletions

diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
new file mode 100644
index 000000000..781a131b4
--- /dev/null
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -0,0 +1,569 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * (C) Copyright 2007
+ * Texas Instruments
+ * Karthik Dasu <karthik-dp@ti.com>
+ *
+ * (C) Copyright 2004
+ * Texas Instruments, <www.ti.com>
+ * Richard Woodruff <r-woodruff2@ti.com>
+ */
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+
+#include "omap34xx.h"
+#include "iomap.h"
+#include "cm3xxx.h"
+#include "prm3xxx.h"
+#include "sdrc.h"
+#include "sram.h"
+#include "control.h"
+
+/*
+ * Registers access definitions
+ */
+#define SDRC_SCRATCHPAD_SEM_OFFS	0xc
+#define SDRC_SCRATCHPAD_SEM_V	OMAP343X_SCRATCHPAD_REGADDR\
+					(SDRC_SCRATCHPAD_SEM_OFFS)
+#define PM_PREPWSTST_CORE_P	OMAP3430_PRM_BASE + CORE_MOD +\
+					OMAP3430_PM_PREPWSTST
+#define PM_PWSTCTRL_MPU_P	OMAP3430_PRM_BASE + MPU_MOD + OMAP2_PM_PWSTCTRL
+#define CM_IDLEST1_CORE_V	OMAP34XX_CM_REGADDR(CORE_MOD, CM_IDLEST1)
+#define CM_IDLEST_CKGEN_V	OMAP34XX_CM_REGADDR(PLL_MOD, CM_IDLEST)
+#define SRAM_BASE_P		OMAP3_SRAM_PA
+#define CONTROL_STAT		OMAP343X_CTRL_BASE + OMAP343X_CONTROL_STATUS
+#define CONTROL_MEM_RTA_CTRL	(OMAP343X_CTRL_BASE +\
+					OMAP36XX_CONTROL_MEM_RTA_CTRL)
+
+/* Move this as correct place is available */
+#define SCRATCHPAD_MEM_OFFS	0x310
+#define SCRATCHPAD_BASE_P	(OMAP343X_CTRL_BASE +\
+					OMAP343X_CONTROL_MEM_WKUP +\
+					SCRATCHPAD_MEM_OFFS)
+#define SDRC_POWER_V		OMAP34XX_SDRC_REGADDR(SDRC_POWER)
+#define SDRC_SYSCONFIG_P	(OMAP343X_SDRC_BASE + SDRC_SYSCONFIG)
+#define SDRC_MR_0_P		(OMAP343X_SDRC_BASE + SDRC_MR_0)
+#define SDRC_EMR2_0_P		(OMAP343X_SDRC_BASE + SDRC_EMR2_0)
+#define SDRC_MANUAL_0_P		(OMAP343X_SDRC_BASE + SDRC_MANUAL_0)
+#define SDRC_MR_1_P		(OMAP343X_SDRC_BASE + SDRC_MR_1)
+#define SDRC_EMR2_1_P		(OMAP343X_SDRC_BASE + SDRC_EMR2_1)
+#define SDRC_MANUAL_1_P		(OMAP343X_SDRC_BASE + SDRC_MANUAL_1)
+#define SDRC_DLLA_STATUS_V	OMAP34XX_SDRC_REGADDR(SDRC_DLLA_STATUS)
+#define SDRC_DLLA_CTRL_V	OMAP34XX_SDRC_REGADDR(SDRC_DLLA_CTRL)
+
+/*
+ * This file needs be built unconditionally as ARM to interoperate correctly
+ * with non-Thumb-2-capable firmware.
+ */
+	.arm
+
+/*
+ * API functions
+ */
+
+	.text
+/*
+ * L2 cache needs to be toggled for stable OFF mode functionality on 3630.
+ * This function sets up a flag that will allow for this toggling to take
+ * place on 3630. Hopefully some version in the future may not need this.
+ */
+ENTRY(enable_omap3630_toggle_l2_on_restore)
+	stmfd	sp!, {lr}	@ save registers on stack
+	/* Setup so that we will disable and enable l2 */
+	mov	r1, #0x1
+	adr	r3, l2dis_3630_offset
+	ldr	r2, [r3]		@ value for offset
+	str	r1, [r2, r3]		@ write to l2dis_3630
+	ldmfd	sp!, {pc}	@ restore regs and return
+ENDPROC(enable_omap3630_toggle_l2_on_restore)
+
+/*
+ * Function to call rom code to save secure ram context.
+ *
+ * r0 = physical address of the parameters
+ */
+	.arch armv7-a
+	.arch_extension sec
+ENTRY(save_secure_ram_context)
+	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
+	mov	r3, r0			@ physical address of parameters
+	mov	r0, #25			@ set service ID for PPA
+	mov	r12, r0			@ copy secure service ID in r12
+	mov	r1, #0			@ set task id for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
+	mov	r6, #0xff
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
+	smc	#1			@ call SMI monitor (smi #1)
+	nop
+	nop
+	nop
+	nop
+	ldmfd	sp!, {r4 - r11, pc}
+ENDPROC(save_secure_ram_context)
+
+/*
+ * ======================
+ * == Idle entry point ==
+ * ======================
+ */
+
+/*
+ * Forces OMAP into idle state
+ *
+ * omap34xx_cpu_suspend() - This bit of code saves the CPU context if needed
+ * and executes the WFI instruction. Calling WFI effectively changes the
+ * power domains states to the desired target power states.
+ *
+ *
+ * Notes:
+ * - only the minimum set of functions gets copied to internal SRAM at boot
+ *   and after wake-up from OFF mode, cf. omap_push_sram_idle. The function
+ *   pointers in SDRAM or SRAM are called depending on the desired low power
+ *   target state.
+ * - when the OMAP wakes up it continues at different execution points
+ *   depending on the low power mode (non-OFF vs OFF modes),
+ *   cf. 'Resume path for xxx mode' comments.
+ */
+	.align	3
+ENTRY(omap34xx_cpu_suspend)
+	stmfd	sp!, {r4 - r11, lr}	@ save registers on stack
+
+	/*
+	 * r0 contains information about saving context:
+	 *   0 - No context lost
+	 *   1 - Only L1 and logic lost
+	 *   2 - Only L2 lost (Even L1 is retained we clean it along with L2)
+	 *   3 - Both L1 and L2 lost and logic lost
+	 */
+
+	/*
+	 * For OFF mode: save context and jump to WFI in SDRAM (omap3_do_wfi)
+	 * For non-OFF modes: jump to the WFI code in SRAM (omap3_do_wfi_sram)
+	 */
+	ldr	r4, omap3_do_wfi_sram_addr
+	ldr	r5, [r4]
+	cmp	r0, #0x0		@ If no context save required,
+	bxeq	r5			@  jump to the WFI code in SRAM
+
+
+	/* Otherwise fall through to the save context code */
+save_context_wfi:
+	/*
+	 * jump out to kernel flush routine
+	 *  - reuse that code is better
+	 *  - it executes in a cached space so is faster than refetch per-block
+	 *  - should be faster and will change with kernel
+	 *  - 'might' have to copy address, load and jump to it
+	 * Flush all data from the L1 data cache before disabling
+	 * SCTLR.C bit.
+	 */
+	ldr	r1, kernel_flush
+	mov	lr, pc
+	bx	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
+
+	/*
+	 * Invalidate L1 data cache. Even though only invalidate is
+	 * necessary exported flush API is used here. Doing clean
+	 * on already clean cache would be almost NOP.
+	 */
+	ldr	r1, kernel_flush
+	blx	r1
+	b	omap3_do_wfi
+ENDPROC(omap34xx_cpu_suspend)
+omap3_do_wfi_sram_addr:
+	.word omap3_do_wfi_sram
+kernel_flush:
+	.word v7_flush_dcache_all
+
+/* ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
+
+/*
+ * Do WFI instruction
+ * Includes the resume path for non-OFF modes
+ *
+ * This code gets copied to internal SRAM and is accessible
+ * from both SDRAM and SRAM:
+ * - executed from SRAM for non-off modes (omap3_do_wfi_sram),
+ * - executed from SDRAM for OFF mode (omap3_do_wfi).
+ */
+	.align	3
+ENTRY(omap3_do_wfi)
+	ldr	r4, sdrc_power		@ read the SDRC_POWER register
+	ldr	r5, [r4]		@ read the contents of SDRC_POWER
+	orr	r5, r5, #0x40		@ enable self refresh on idle req
+	str	r5, [r4]		@ write back to SDRC_POWER register
+
+	/* Data memory barrier and Data sync barrier */
+	dsb
+	dmb
+
+/*
+ * ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
+	wfi				@ wait for interrupt
+
+/*
+ * ===================================
+ * == Resume path for non-OFF modes ==
+ * ===================================
+ */
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+
+/*
+ * This function implements the erratum ID i581 WA:
+ *  SDRC state restore before accessing the SDRAM
+ *
+ * Only used at return from non-OFF mode. For OFF
+ * mode the ROM code configures the SDRC and
+ * the DPLL before calling the restore code directly
+ * from DDR.
+ */
+
+/* Make sure SDRC accesses are ok */
+wait_sdrc_ok:
+
+/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */
+	ldr	r4, cm_idlest_ckgen
+wait_dpll3_lock:
+	ldr	r5, [r4]
+	tst	r5, #1
+	beq	wait_dpll3_lock
+
+	ldr	r4, cm_idlest1_core
+wait_sdrc_ready:
+	ldr	r5, [r4]
+	tst	r5, #0x2
+	bne	wait_sdrc_ready
+	/* allow DLL powerdown upon hw idle req */
+	ldr	r4, sdrc_power
+	ldr	r5, [r4]
+	bic	r5, r5, #0x40
+	str	r5, [r4]
+
+is_dll_in_lock_mode:
+	/* Is dll in lock mode? */
+	ldr	r4, sdrc_dlla_ctrl
+	ldr	r5, [r4]
+	tst	r5, #0x4
+	bne	exit_nonoff_modes	@ Return if locked
+	/* wait till dll locks */
+wait_dll_lock_timed:
+	ldr	r4, sdrc_dlla_status
+	/* Wait 20uS for lock */
+	mov	r6, #8
+wait_dll_lock:
+	subs	r6, r6, #0x1
+	beq	kick_dll
+	ldr	r5, [r4]
+	and	r5, r5, #0x4
+	cmp	r5, #0x4
+	bne	wait_dll_lock
+	b	exit_nonoff_modes	@ Return when locked
+
+	/* disable/reenable DLL if not locked */
+kick_dll:
+	ldr	r4, sdrc_dlla_ctrl
+	ldr	r5, [r4]
+	mov	r6, r5
+	bic	r6, #(1<<3)		@ disable dll
+	str	r6, [r4]
+	dsb
+	orr	r6, r6, #(1<<3)		@ enable dll
+	str	r6, [r4]
+	dsb
+	b	wait_dll_lock_timed
+
+exit_nonoff_modes:
+	/* Re-enable C-bit if needed */
+	mrc	p15, 0, r0, c1, c0, 0
+	tst	r0, #(1 << 2)		@ Check C bit enabled?
+	orreq	r0, r0, #(1 << 2)	@ Enable the C bit if cleared
+	mcreq	p15, 0, r0, c1, c0, 0
+	isb
+
+/*
+ * ===================================
+ * == Exit point from non-OFF modes ==
+ * ===================================
+ */
+	ldmfd	sp!, {r4 - r11, pc}	@ restore regs and return
+ENDPROC(omap3_do_wfi)
+sdrc_power:
+	.word	SDRC_POWER_V
+cm_idlest1_core:
+	.word	CM_IDLEST1_CORE_V
+cm_idlest_ckgen:
+	.word	CM_IDLEST_CKGEN_V
+sdrc_dlla_status:
+	.word	SDRC_DLLA_STATUS_V
+sdrc_dlla_ctrl:
+	.word	SDRC_DLLA_CTRL_V
+ENTRY(omap3_do_wfi_sz)
+	.word	. - omap3_do_wfi
+
+
+/*
+ * ==============================
+ * == Resume path for OFF mode ==
+ * ==============================
+ */
+
+/*
+ * The restore_* functions are called by the ROM code
+ *  when back from WFI in OFF mode.
+ * Cf. the get_*restore_pointer functions.
+ *
+ *  restore_es3: applies to 34xx >= ES3.0
+ *  restore_3630: applies to 36xx
+ *  restore: common code for 3xxx
+ *
+ * Note: when back from CORE and MPU OFF mode we are running
+ *  from SDRAM, without MMU, without the caches and prediction.
+ *  Also the SRAM content has been cleared.
+ */
+ENTRY(omap3_restore_es3)
+	ldr	r5, pm_prepwstst_core_p
+	ldr	r4, [r5]
+	and	r4, r4, #0x3
+	cmp	r4, #0x0	@ Check if previous power state of CORE is OFF
+	bne	omap3_restore	@ Fall through to OMAP3 common code
+	adr	r0, es3_sdrc_fix
+	ldr	r1, sram_base
+	ldr	r2, es3_sdrc_fix_sz
+	mov	r2, r2, ror #2
+copy_to_sram:
+	ldmia	r0!, {r3}	@ val = *src
+	stmia	r1!, {r3}	@ *dst = val
+	subs	r2, r2, #0x1	@ num_words--
+	bne	copy_to_sram
+	ldr	r1, sram_base
+	blx	r1
+	b	omap3_restore	@ Fall through to OMAP3 common code
+ENDPROC(omap3_restore_es3)
+
+ENTRY(omap3_restore_3630)
+	ldr	r1, pm_prepwstst_core_p
+	ldr	r2, [r1]
+	and	r2, r2, #0x3
+	cmp	r2, #0x0	@ Check if previous power state of CORE is OFF
+	bne	omap3_restore	@ Fall through to OMAP3 common code
+	/* Disable RTA before giving control */
+	ldr	r1, control_mem_rta
+	mov	r2, #OMAP36XX_RTA_DISABLE
+	str	r2, [r1]
+ENDPROC(omap3_restore_3630)
+
+	/* Fall through to common code for the remaining logic */
+
+ENTRY(omap3_restore)
+	/*
+	 * Read the pwstctrl register to check the reason for mpu reset.
+	 * This tells us what was lost.
+	 */
+	ldr	r1, pm_pwstctrl_mpu
+	ldr	r2, [r1]
+	and	r2, r2, #0x3
+	cmp	r2, #0x0	@ Check if target power state was OFF or RET
+	bne	logic_l1_restore
+
+	adr	r1, l2dis_3630_offset	@ address for offset
+	ldr	r0, [r1]		@ value for offset
+	ldr	r0, [r1, r0]		@ value at l2dis_3630
+	cmp	r0, #0x1	@ should we disable L2 on 3630?
+	bne	skipl2dis
+	mrc	p15, 0, r0, c1, c0, 1
+	bic	r0, r0, #2	@ disable L2 cache
+	mcr	p15, 0, r0, c1, c0, 1
+skipl2dis:
+	ldr	r0, control_stat
+	ldr	r1, [r0]
+	and	r1, #0x700
+	cmp	r1, #0x300
+	beq	l2_inv_gp
+	adr	r0, l2_inv_api_params_offset
+	ldr	r3, [r0]
+	add	r3, r3, r0		@ r3 points to dummy parameters
+	mov	r0, #40			@ set service ID for PPA
+	mov	r12, r0			@ copy secure Service ID in r12
+	mov	r1, #0			@ set task id for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
+	mov	r6, #0xff
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
+	smc	#1			@ call SMI monitor (smi #1)
+	/* Write to Aux control register to set some bits */
+	mov	r0, #42			@ set service ID for PPA
+	mov	r12, r0			@ copy secure Service ID in r12
+	mov	r1, #0			@ set task id for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
+	mov	r6, #0xff
+	ldr	r4, scratchpad_base
+	ldr	r3, [r4, #0xBC]		@ r3 points to parameters
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
+	smc	#1			@ call SMI monitor (smi #1)
+
+#ifdef CONFIG_OMAP3_L2_AUX_SECURE_SAVE_RESTORE
+	/* Restore L2 aux control register */
+					@ set service ID for PPA
+	mov	r0, #CONFIG_OMAP3_L2_AUX_SECURE_SERVICE_SET_ID
+	mov	r12, r0			@ copy service ID in r12
+	mov	r1, #0			@ set task ID for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
+	mov	r6, #0xff
+	ldr	r4, scratchpad_base
+	ldr	r3, [r4, #0xBC]
+	adds	r3, r3, #8		@ r3 points to parameters
+	dsb				@ data write barrier
+	dmb				@ data memory barrier
+	smc	#1			@ call SMI monitor (smi #1)
+#endif
+	b	logic_l1_restore
+
+	.align
+l2_inv_api_params_offset:
+	.long	l2_inv_api_params - .
+l2_inv_gp:
+	/* Execute smi to invalidate L2 cache */
+	mov r12, #0x1			@ set up to invalidate L2
+	smc	#0			@ Call SMI monitor (smieq)
+	/* Write to Aux control register to set some bits */
+	ldr	r4, scratchpad_base
+	ldr	r3, [r4,#0xBC]
+	ldr	r0, [r3,#4]
+	mov	r12, #0x3
+	smc	#0			@ Call SMI monitor (smieq)
+	ldr	r4, scratchpad_base
+	ldr	r3, [r4,#0xBC]
+	ldr	r0, [r3,#12]
+	mov	r12, #0x2
+	smc	#0			@ Call SMI monitor (smieq)
+logic_l1_restore:
+	adr	r0, l2dis_3630_offset	@ address for offset
+	ldr	r1, [r0]		@ value for offset
+	ldr	r1, [r0, r1]		@ value at l2dis_3630
+	cmp	r1, #0x1		@ Test if L2 re-enable needed on 3630
+	bne	skipl2reen
+	mrc	p15, 0, r1, c1, c0, 1
+	orr	r1, r1, #2		@ re-enable L2 cache
+	mcr	p15, 0, r1, c1, c0, 1
+skipl2reen:
+
+	/* Now branch to the common CPU resume function */
+	b	cpu_resume
+ENDPROC(omap3_restore)
+
+	.ltorg
+
+/*
+ * Local variables
+ */
+pm_prepwstst_core_p:
+	.word	PM_PREPWSTST_CORE_P
+pm_pwstctrl_mpu:
+	.word	PM_PWSTCTRL_MPU_P
+scratchpad_base:
+	.word	SCRATCHPAD_BASE_P
+sram_base:
+	.word	SRAM_BASE_P + 0x8000
+control_stat:
+	.word	CONTROL_STAT
+control_mem_rta:
+	.word	CONTROL_MEM_RTA_CTRL
+l2dis_3630_offset:
+	.long	l2dis_3630 - .
+
+	.data
+	.align	2
+l2dis_3630:
+	.word	0
+
+	.data
+	.align	2
+l2_inv_api_params:
+	.word	0x1, 0x00
+
+/*
+ * Internal functions
+ */
+
+/*
+ * This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0
+ * Copied to and run from SRAM in order to reconfigure the SDRC parameters.
+ */
+	.text
+	.align	3
+ENTRY(es3_sdrc_fix)
+	ldr	r4, sdrc_syscfg		@ get config addr
+	ldr	r5, [r4]		@ get value
+	tst	r5, #0x100		@ is part access blocked
+	it	eq
+	biceq	r5, r5, #0x100		@ clear bit if set
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_mr_0		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_emr2_0		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_manual_0	@ get config addr
+	mov	r5, #0x2		@ autorefresh command
+	str	r5, [r4]		@ kick off refreshes
+	ldr	r4, sdrc_mr_1		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_emr2_1		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_manual_1	@ get config addr
+	mov	r5, #0x2		@ autorefresh command
+	str	r5, [r4]		@ kick off refreshes
+	bx	lr
+
+/*
+ * Local variables
+ */
+	.align
+sdrc_syscfg:
+	.word	SDRC_SYSCONFIG_P
+sdrc_mr_0:
+	.word	SDRC_MR_0_P
+sdrc_emr2_0:
+	.word	SDRC_EMR2_0_P
+sdrc_manual_0:
+	.word	SDRC_MANUAL_0_P
+sdrc_mr_1:
+	.word	SDRC_MR_1_P
+sdrc_emr2_1:
+	.word	SDRC_EMR2_1_P
+sdrc_manual_1:
+	.word	SDRC_MANUAL_1_P
+ENDPROC(es3_sdrc_fix)
+ENTRY(es3_sdrc_fix_sz)
+	.word	. - es3_sdrc_fix