Merge branch 'android-4.19' into android-4.19-stable

Final merge of android-4.19

Change-Id: Ifa789a66260ed6207e829555ad2050d30e3de555

Documentation/ABI/stable/sysfs-bus-nvmem

@@ -6,6 +6,8 @@ Description:
 		This file allows user to read/write the raw NVMEM contents.
 		Permissions for write to this file depends on the nvmem
 		provider configuration.
+		Note: This file is only present if CONFIG_NVMEM_SYSFS
+		is enabled
 
 		ex:
 		hexdump /sys/bus/nvmem/devices/qfprom0/nvmem

Documentation/ABI/testing/sysfs-class-power

@@ -144,7 +144,8 @@ Description:
 		Access: Read
 		Valid values: "Unknown", "Good", "Overheat", "Dead",
 			      "Over voltage", "Unspecified failure", "Cold",
-			      "Watchdog timer expire", "Safety timer expire"
+			      "Watchdog timer expire", "Safety timer expire",
+			      "Over current", "Warm", "Cool", "Hot"
 
 What:		/sys/class/power_supply/<supply_name>/precharge_current
 Date:		June 2017

Documentation/ABI/testing/sysfs-fs-f2fs

@@ -323,3 +323,18 @@ What:		/sys/fs/f2fs/<disk>/mounted_time_sec
 Date:		February 2020
 Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
 Description:	Show the mounted time in secs of this partition.
+
+What:		/sys/fs/f2fs/<disk>/data_io_flag
+Date:		April 2020
+Contact:	"Jaegeuk Kim" <jaegeuk@kernel.org>
+Description:	Give a way to attach REQ_META|FUA to data writes
+		given temperature-based bits. Now the bits indicate:
+		*      REQ_META     |      REQ_FUA      |
+		*    5 |    4 |   3 |    2 |    1 |   0 |
+		* Cold | Warm | Hot | Cold | Warm | Hot |
+
+What:		/sys/fs/f2fs/<disk>/iostat_period_ms
+Date:		April 2020
+Contact:	"Daeho Jeong" <daehojeong@google.com>
+Description:	Give a way to change iostat_period time. 3secs by default.
+		The new iostat trace gives stats gap given the period.

Documentation/admin-guide/kernel-parameters.txt

@@ -4032,7 +4032,9 @@
 				[[,]s[mp]#### \
 				[[,]b[ios] | a[cpi] | k[bd] | t[riple] | e[fi] | p[ci]] \
 				[[,]f[orce]
-			Where reboot_mode is one of warm (soft) or cold (hard) or gpio,
+			Where reboot_mode is one of warm (soft) or cold (hard) or gpio
+					(prefix with 'panic_' to set mode for panic
+					reboot only),
 			      reboot_type is one of bios, acpi, kbd, triple, efi, or pci,
 			      reboot_force is either force or not specified,
 			      reboot_cpu is s[mp]#### with #### being the processor

Documentation/arm64/index.rst

@@ -0,0 +1,27 @@
+==================
+ARM64 Architecture
+==================
+
+.. toctree::
+    :maxdepth: 1
+
+    acpi_object_usage
+    arm-acpi
+    booting
+    cpu-feature-registers
+    elf_hwcaps
+    hugetlbpage
+    legacy_instructions
+    memory
+    pointer-authentication
+    silicon-errata
+    sve
+    tagged-address-abi
+    tagged-pointers
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`

Documentation/arm64/silicon-errata.txt

@@ -59,6 +59,7 @@ stable kernels.
 | ARM            | Cortex-A73      | #858921         | ARM64_ERRATUM_858921        |
 | ARM            | Cortex-A55      | #1024718        | ARM64_ERRATUM_1024718       |
 | ARM            | Cortex-A76      | #1463225        | ARM64_ERRATUM_1463225       |
+| ARM            | Neoverse-N1     | #1542419        | ARM64_ERRATUM_1542419       |
 | ARM            | MMU-500         | #841119,#826419 | N/A                         |
 |                |                 |                 |                             |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |

Documentation/arm64/tagged-pointers.rst

@@ -0,0 +1,75 @@
+=========================================
+Tagged virtual addresses in AArch64 Linux
+=========================================
+
+Author: Will Deacon <will.deacon@arm.com>
+
+Date  : 12 June 2013
+
+This document briefly describes the provision of tagged virtual
+addresses in the AArch64 translation system and their potential uses
+in AArch64 Linux.
+
+The kernel configures the translation tables so that translations made
+via TTBR0 (i.e. userspace mappings) have the top byte (bits 63:56) of
+the virtual address ignored by the translation hardware. This frees up
+this byte for application use.
+
+
+Passing tagged addresses to the kernel
+--------------------------------------
+
+All interpretation of userspace memory addresses by the kernel assumes
+an address tag of 0x00, unless the application enables the AArch64
+Tagged Address ABI explicitly
+(Documentation/arm64/tagged-address-abi.rst).
+
+This includes, but is not limited to, addresses found in:
+
+ - pointer arguments to system calls, including pointers in structures
+   passed to system calls,
+
+ - the stack pointer (sp), e.g. when interpreting it to deliver a
+   signal,
+
+ - the frame pointer (x29) and frame records, e.g. when interpreting
+   them to generate a backtrace or call graph.
+
+Using non-zero address tags in any of these locations when the
+userspace application did not enable the AArch64 Tagged Address ABI may
+result in an error code being returned, a (fatal) signal being raised,
+or other modes of failure.
+
+For these reasons, when the AArch64 Tagged Address ABI is disabled,
+passing non-zero address tags to the kernel via system calls is
+forbidden, and using a non-zero address tag for sp is strongly
+discouraged.
+
+Programs maintaining a frame pointer and frame records that use non-zero
+address tags may suffer impaired or inaccurate debug and profiling
+visibility.
+
+
+Preserving tags
+---------------
+
+Non-zero tags are not preserved when delivering signals. This means that
+signal handlers in applications making use of tags cannot rely on the
+tag information for user virtual addresses being maintained for fields
+inside siginfo_t. One exception to this rule is for signals raised in
+response to watchpoint debug exceptions, where the tag information will
+be preserved.
+
+The architecture prevents the use of a tagged PC, so the upper byte will
+be set to a sign-extension of bit 55 on exception return.
+
+This behaviour is maintained when the AArch64 Tagged Address ABI is
+enabled.
+
+
+Other considerations
+--------------------
+
+Special care should be taken when using tagged pointers, since it is
+likely that C compilers will not hazard two virtual addresses differing
+only in the upper byte.

Documentation/sound/designs/compress-offload.rst

@@ -183,6 +183,11 @@ partial drain
   EOF is reached and now DSP can start skipping padding delay. Also next write
   data would belong to next track
 
+- set_next_track_param
+This routine is called to send to DSP codec specific data of subsequent track
+in gapless before first write.
+
+
 Sequence flow for gapless would be:
 - Open
 - Get caps / codec caps
@@ -194,6 +199,7 @@ Sequence flow for gapless would be:
 - Indicate next track data by sending set_next_track
 - Set metadata of the next track
 - then call partial_drain to flush most of buffer in DSP
+- set codec specific data of subsequent track
 - Fill data of the next track
 - DSP switches to second track
 

Documentation/sound/hd-audio/index.rst

@@ -8,3 +8,4 @@ HD-Audio
    models
    controls
    dp-mst
+   realtek-pc-beep

Documentation/sound/hd-audio/models.rst

@@ -216,8 +216,6 @@ alc298-dell-aio
     ALC298 fixups on Dell AIO machines
 alc275-dell-xps
     ALC275 fixups on Dell XPS models
-alc256-dell-xps13
-    ALC256 fixups on Dell XPS13
 lenovo-spk-noise
     Workaround for speaker noise on Lenovo machines
 lenovo-hotkey

Documentation/sound/hd-audio/realtek-pc-beep.rst

@@ -0,0 +1,129 @@
+===============================
+Realtek PC Beep Hidden Register
+===============================
+
+This file documents the "PC Beep Hidden Register", which is present in certain
+Realtek HDA codecs and controls a muxer and pair of passthrough mixers that can
+route audio between pins but aren't themselves exposed as HDA widgets. As far
+as I can tell, these hidden routes are designed to allow flexible PC Beep output
+for codecs that don't have mixer widgets in their output paths. Why it's easier
+to hide a mixer behind an undocumented vendor register than to just expose it
+as a widget, I have no idea.
+
+Register Description
+====================
+
+The register is accessed via processing coefficient 0x36 on NID 20h. Bits not
+identified below have no discernible effect on my machine, a Dell XPS 13 9350::
+
+  MSB                           LSB
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+  | |h|S|L|         | B |R|       | Known bits
+  +=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+=+
+  |0|0|1|1|  0x7  |0|0x0|1|  0x7  | Reset value
+  +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+
+1Ah input select (B): 2 bits
+  When zero, expose the PC Beep line (from the internal beep generator, when
+  enabled with the Set Beep Generation verb on NID 01h, or else from the
+  external PCBEEP pin) on the 1Ah pin node. When nonzero, expose the headphone
+  jack (or possibly Line In on some machines) input instead. If PC Beep is
+  selected, the 1Ah boost control has no effect.
+
+Amplify 1Ah loopback, left (L): 1 bit
+  Amplify the left channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Amplify 1Ah loopback, right (R): 1 bit
+  Amplify the right channel of 1Ah before mixing it into outputs as specified
+  by h and S bits. Does not affect the level of 1Ah exposed to other widgets.
+
+Loopback 1Ah to 21h [active low] (h): 1 bit
+  When zero, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 21h (headphone jack on my machine). Mixed signal respects the mute
+  setting on 21h.
+
+Loopback 1Ah to 14h (S): 1 bit
+  When one, mix 1Ah (possibly with amplification, depending on L and R bits)
+  into 14h (internal speaker on my machine). Mixed signal **ignores** the mute
+  setting on 14h and is present whenever 14h is configured as an output.
+
+Path diagrams
+=============
+
+1Ah input selection (DIV is the PC Beep divider set on NID 01h)::
+
+  <Beep generator>   <PCBEEP pin>    <Headphone jack>
+          |                |                |
+          +--DIV--+--!DIV--+       {1Ah boost control}
+                  |                         |
+                  +--(b == 0)--+--(b != 0)--+
+                               |
+               >1Ah (Beep/Headphone Mic/Line In)<
+
+Loopback of 1Ah to 21h/14h::
+
+               <1Ah (Beep/Headphone Mic/Line In)>
+                               |
+                        {amplify if L/R}
+                               |
+                  +-----!h-----+-----S-----+
+                  |                        |
+          {21h mute control}               |
+                  |                        |
+          >21h (Headphone)<     >14h (Internal Speaker)<
+
+Background
+==========
+
+All Realtek HDA codecs have a vendor-defined widget with node ID 20h which
+provides access to a bank of registers that control various codec functions.
+Registers are read and written via the standard HDA processing coefficient
+verbs (Set/Get Coefficient Index, Set/Get Processing Coefficient). The node is
+named "Realtek Vendor Registers" in public datasheets' verb listings and,
+apart from that, is entirely undocumented.
+
+This particular register, exposed at coefficient 0x36 and named in commits from
+Realtek, is of note: unlike most registers, which seem to control detailed
+amplifier parameters not in scope of the HDA specification, it controls audio
+routing which could just as easily have been defined using standard HDA mixer
+and selector widgets.
+
+Specifically, it selects between two sources for the input pin widget with Node
+ID (NID) 1Ah: the widget's signal can come either from an audio jack (on my
+laptop, a Dell XPS 13 9350, it's the headphone jack, but comments in Realtek
+commits indicate that it might be a Line In on some machines) or from the PC
+Beep line (which is itself multiplexed between the codec's internal beep
+generator and external PCBEEP pin, depending on if the beep generator is
+enabled via verbs on NID 01h). Additionally, it can mix (with optional
+amplification) that signal onto the 21h and/or 14h output pins.
+
+The register's reset value is 0x3717, corresponding to PC Beep on 1Ah that is
+then amplified and mixed into both the headphones and the speakers. Not only
+does this violate the HDA specification, which says that "[a vendor defined
+beep input pin] connection may be maintained *only* while the Link reset
+(**RST#**) is asserted", it means that we cannot ignore the register if we care
+about the input that 1Ah would otherwise expose or if the PCBEEP trace is
+poorly shielded and picks up chassis noise (both of which are the case on my
+machine).
+
+Unfortunately, there are lots of ways to get this register configuration wrong.
+Linux, it seems, has gone through most of them. For one, the register resets
+after S3 suspend: judging by existing code, this isn't the case for all vendor
+registers, and it's led to some fixes that improve behavior on cold boot but
+don't last after suspend. Other fixes have successfully switched the 1Ah input
+away from PC Beep but have failed to disable both loopback paths. On my
+machine, this means that the headphone input is amplified and looped back to
+the headphone output, which uses the exact same pins! As you might expect, this
+causes terrible headphone noise, the character of which is controlled by the
+1Ah boost control. (If you've seen instructions online to fix XPS 13 headphone
+noise by changing "Headphone Mic Boost" in ALSA, now you know why.)
+
+The information here has been obtained through black-box reverse engineering of
+the ALC256 codec's behavior and is not guaranteed to be correct. It likely
+also applies for the ALC255, ALC257, ALC235, and ALC236, since those codecs
+seem to be close relatives of the ALC256. (They all share one initialization
+function.) Additionally, other codecs like the ALC225 and ALC285 also have this
+register, judging by existing fixups in ``patch_realtek.c``, but specific
+data (e.g. node IDs, bit positions, pin mappings) for those codecs may differ
+from what I've described here.

Documentation/sysctl/vm.txt

@@ -64,7 +64,6 @@ Currently, these files are in /proc/sys/vm:
 - swappiness
 - user_reserve_kbytes
 - vfs_cache_pressure
-- watermark_boost_factor
 - watermark_scale_factor
 - zone_reclaim_mode
 
@@ -873,26 +872,6 @@ ten times more freeable objects than there are.
 
 =============================================================
 
-watermark_boost_factor:
-
-This factor controls the level of reclaim when memory is being fragmented.
-It defines the percentage of the high watermark of a zone that will be
-reclaimed if pages of different mobility are being mixed within pageblocks.
-The intent is that compaction has less work to do in the future and to
-increase the success rate of future high-order allocations such as SLUB
-allocations, THP and hugetlbfs pages.
-
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
-
-=============================================================
-
 watermark_scale_factor:
 
 This factor controls the aggressiveness of kswapd. It defines the

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 19
-SUBLEVEL = 114
+SUBLEVEL = 123
 EXTRAVERSION =
 NAME = "People's Front"
 

abi_gki_aarch64_cuttlefish_whitelist

@@ -22,7 +22,6 @@
   __cpu_online_mask
   cpus_read_lock
   cpus_read_unlock
-  debug_smp_processor_id
   delayed_work_timer_fn
   destroy_workqueue
   _dev_err
@@ -124,8 +123,6 @@
   platform_device_unregister
   __platform_driver_register
   platform_driver_unregister
-  preempt_count_add
-  preempt_count_sub
   preempt_schedule
   preempt_schedule_notrace
   prepare_to_wait_event
@@ -437,7 +434,6 @@
   copy_page
   dev_driver_string
   devres_add
-  __devres_alloc_node
   devres_destroy
   devres_free
   dma_buf_get
@@ -610,7 +606,6 @@
   kmem_cache_free
   memdup_user
   put_unused_fd
-  remove_conflicting_framebuffers
   sg_alloc_table_from_pages
   sync_file_create
   sync_file_get_fence

abi_gki_aarch64_qcom_whitelist

@@ -16,7 +16,6 @@
   __arch_copy_from_user
   __arch_copy_to_user
   arch_setup_dma_ops
-  arch_timer_read_ool_enabled
   arm64_const_caps_ready
   atomic_notifier_call_chain
   atomic_notifier_chain_register
@@ -48,6 +47,7 @@
   cdev_add
   cdev_del
   cdev_init
+  __cfi_slowpath
   __check_object_size
   __class_create
   class_destroy
@@ -108,22 +108,6 @@
   crypto_destroy_tfm
   crypto_shash_setkey
   _ctype
-  debugfs_attr_read
-  debugfs_attr_write
-  debugfs_create_atomic_t
-  debugfs_create_bool
-  debugfs_create_dir
-  debugfs_create_file
-  debugfs_create_file_unsafe
-  debugfs_create_u16
-  debugfs_create_u32
-  debugfs_create_u64
-  debugfs_create_u8
-  debugfs_create_x32
-  debugfs_create_x8
-  debugfs_print_regs32
-  debugfs_remove
-  debugfs_remove_recursive
   delayed_work_timer_fn
   del_timer
   del_timer_sync
@@ -246,6 +230,7 @@
   dma_fence_signal_locked
   __dma_flush_area
   __dma_inv_area
+  dmam_alloc_coherent
   dma_release_from_dev_coherent
   dma_request_slave_channel
   do_exit
@@ -258,8 +243,6 @@
   drm_panel_notifier_unregister
   dst_release
   dummy_dma_ops
-  __dynamic_dev_dbg
-  __dynamic_pr_debug
   enable_irq
   ether_setup
   eth_type_trans
@@ -291,23 +274,9 @@
   freezing_slow_path
   fwnode_property_read_u32_array
   gcd
-  generic_file_llseek
   generic_handle_irq
-  geni_abort_m_cmd
+  genl_register_family
-  geni_cancel_m_cmd
+  genl_unregister_family
-  geni_se_dump_dbg_regs
-  geni_se_init
-  geni_se_iommu_map_buf
-  geni_se_iommu_unmap_buf
-  geni_se_resources_init
-  geni_se_rx_dma_prep
-  geni_se_rx_dma_unprep
-  geni_se_select_mode
-  geni_setup_m_cmd
-  geni_se_tx_dma_prep
-  geni_se_tx_dma_unprep
-  geni_write_reg
-  genlmsg_put
   gen_pool_add_virt
   gen_pool_alloc
   gen_pool_create
@@ -318,9 +287,7 @@
   __get_free_pages
   get_pid_task
   get_random_bytes
-  get_se_proto
   __get_task_comm
-  get_tx_fifo_depth
   get_unused_fd_flags
   gpiochip_add_data_with_key
   gpiochip_add_pin_range
@@ -345,7 +312,6 @@
   handle_edge_irq
   handle_level_irq
   handle_nested_irq
-  hex2bin
   hex_dump_to_buffer
   hrtimer_active
   hrtimer_cancel
@@ -470,12 +436,9 @@
   kstrtoint
   kstrtoll
   kstrtos8
-  kstrtos8_from_user
   kstrtou16
   kstrtou8
-  kstrtou8_from_user
   kstrtouint
-  kstrtouint_from_user
   kstrtoull
   kthread_cancel_work_sync
   kthread_create_on_node
@@ -486,7 +449,6 @@
   kthread_stop
   kthread_worker_fn
   ktime_get
-  ktime_get_coarse_real_ts64
   ktime_get_real_ts64
   ktime_get_with_offset
   kvfree
@@ -542,7 +504,6 @@
   module_put
   __msecs_to_jiffies
   msleep
-  msleep_interruptible
   __mutex_init
   mutex_lock
   mutex_lock_interruptible
@@ -572,9 +533,9 @@
   nla_put
   __nlmsg_put
   no_llseek
-  nonseekable_open
   nr_cpu_ids
   ns_capable
+  ns_to_timespec64
   ns_to_timespec
   nvmem_cell_get
   nvmem_cell_put
@@ -749,6 +710,7 @@
   _raw_spin_lock_bh
   _raw_spin_lock_irq
   _raw_spin_lock_irqsave
+  _raw_spin_trylock
   _raw_spin_trylock_bh
   _raw_spin_unlock
   _raw_spin_unlock_bh
@@ -790,6 +752,7 @@
   __regmap_init
   regmap_multi_reg_write
   regmap_raw_read
+  regmap_raw_write
   regmap_read
   regmap_update_bits_base
   regmap_write
@@ -798,6 +761,7 @@
   regulator_disable
   regulator_enable
   regulator_get
+  regulator_get_voltage
   regulator_is_enabled
   regulator_put
   regulator_set_load
@@ -817,8 +781,6 @@
   rtc_time64_to_tm
   rtc_tm_to_time64
   rtc_valid_tm
-  rt_mutex_lock
-  rt_mutex_unlock
   rtnl_is_locked
   rtnl_unlock
   saved_command_line
@@ -827,18 +789,12 @@
   schedule
   schedule_timeout
   scnprintf
-  se_config_packing
-  se_geni_clks_off
-  se_geni_resources_off
-  se_geni_resources_on
   seq_lseek
   seq_open
   seq_printf
-  seq_putc
   seq_puts
   seq_read
   seq_release
-  seq_write
   set_normalized_timespec
   set_user_nice
   sg_alloc_table
@@ -848,15 +804,7 @@
   sg_next
   __sg_page_iter_next
   __sg_page_iter_start
-  simple_attr_open
-  simple_attr_read
-  simple_attr_release
-  simple_attr_write
-  simple_open
   simple_read_from_buffer
-  simple_write_to_buffer
-  single_open
-  single_release
   sk_alloc
   skb_add_rx_frag
   skb_clone
@@ -969,6 +917,7 @@
   sysfs_remove_group
   sysfs_remove_groups
   sysfs_streq
+  system_freezable_wq
   system_freezing_cnt
   system_highpri_wq
   system_long_wq
@@ -998,16 +947,22 @@
   trace_event_reg
   trace_handle_return
   trace_print_flags_seq
+  trace_print_hex_seq
+  trace_print_symbols_seq
   trace_raw_output_prep
   trace_seq_printf
   try_module_get
+  tty_flip_buffer_push
   typec_register_partner
   typec_register_port
   typec_set_data_role
   typec_set_pwr_role
   typec_unregister_partner
+  uart_add_one_port
+  uart_register_driver
+  uart_remove_one_port
+  uart_unregister_driver
   __udelay
-  uncached_logk
   __unregister_chrdev
   unregister_chrdev_region
   unregister_inet6addr_notifier
@@ -1035,7 +990,6 @@
   usb_free_all_descriptors
   usb_function_register
   usb_function_unregister
-  usb_func_wakeup
   usb_gadget_wakeup
   usb_get_dr_mode
   usb_interface_id
@@ -1125,7 +1079,6 @@
   iommu_group_remove_device
   iommu_group_set_iommudata
   iommu_put_dma_cookie
-  kstrtoull_from_user
   of_dma_is_coherent
   of_n_addr_cells
   of_n_size_cells
@@ -1180,9 +1133,6 @@
 # required by cam_flash.ko
   thermal_zone_get_cdev_by_name
 
-# required by cam_ife_csid.ko
-  ns_to_timespec64
-
 # required by cam_ife_hw_mgr.ko
   __ll_sc_atomic_fetch_add
 
@@ -1199,6 +1149,10 @@
   led_trigger_register_simple
   led_trigger_unregister_simple
 
+# required by cam_smmu_api.ko
+  iommu_dma_enable_best_fit_algo
+  iommu_dma_reserve_iova
+
 # required by cam_utils.ko
   gpio_free_array
   of_clk_get_from_provider
@@ -1206,13 +1160,13 @@
   __request_region
 
 # required by citadel-spi.ko
+  nonseekable_open
   spi_bus_lock
   spi_bus_unlock
   spi_sync_locked
 
 # required by clk-qcom.ko
   clk_aggregate_rate
-  clk_debug_print_hw
   __clk_determine_rate
   clk_fixed_rate_ops
   clk_hw_get_flags
@@ -1276,18 +1230,6 @@
   send_sig_info
   time64_to_tm
 
-# required by dm-default-key.ko
-  bio_crypt_alloc_ctx
-  blk_crypto_evict_key
-  blk_crypto_init_key
-  dm_get_device
-  dm_put_device
-  dm_read_arg_group
-  dm_register_target
-  dm_shift_arg
-  dm_table_get_mode
-  dm_unregister_target
-
 # required by dwc3-haps.ko
   pcim_enable_device
   __pci_register_driver
@@ -1323,7 +1265,6 @@
   pinctrl_pm_select_default_state
   pinctrl_pm_select_sleep_state
   strcat
-  system_freezable_wq
   usb_add_gadget_udc
   usb_del_gadget_udc
   usb_ep_set_maxpacket_limit
@@ -1368,12 +1309,7 @@
   xt_unregister_target
 
 # required by eud.ko
-  tty_flip_buffer_push
-  uart_add_one_port
   uart_insert_char
-  uart_register_driver
-  uart_remove_one_port
-  uart_unregister_driver
 
 # required by event_timer.ko
   cpumask_next_and
@@ -1385,7 +1321,9 @@
   of_find_i2c_device_by_node
 
 # required by ftm5.ko
+  ktime_get_coarse_real_ts64
   proc_create
+  seq_write
 
 # required by google-battery.ko
   simple_strtoull
@@ -1396,12 +1334,6 @@
 # required by governor_bw_hwmon.ko
   argv_free
   argv_split
-  __tracepoint_bw_hwmon_meas
-  __tracepoint_bw_hwmon_update
-
-# required by governor_memlat.ko
-  __tracepoint_memlat_dev_meas
-  __tracepoint_memlat_dev_update
 
 # required by gpi.ko
   dma_async_device_register
@@ -1437,11 +1369,13 @@
   i2c_put_dma_safe_msg_buf
 
 # required by ion-alloc.ko
-  dentry_path
   dma_buf_export
   dma_get_device_base
   dma_get_size
+  __ll_sc_atomic64_sub_return
+  mm_event_count
   __next_zones_zonelist
+  ptr_to_hashval
   sched_setattr
   split_page
   vm_map_ram
@@ -1452,6 +1386,7 @@
   add_wait_queue
   alloc_etherdev_mqs
   eth_mac_addr
+  kstrtos8_from_user
   pci_clear_master
   pci_disable_device
   pci_enable_device
@@ -1471,7 +1406,7 @@
 # required by lpm-stats.ko
   kobject_get
   module_ktype
-  on_each_cpu
+  simple_write_to_buffer
 
 # required by machine_dlkm.ko
   devm_snd_soc_register_card
@@ -1483,6 +1418,7 @@
   snd_soc_dai_set_pll
   snd_soc_dai_set_sysclk
   snd_soc_dai_set_tdm_slot
+  snd_soc_get_pcm_runtime
   snd_soc_of_get_dai_link_codecs
   snd_soc_of_parse_audio_routing
   snd_soc_of_parse_card_name
@@ -1538,7 +1474,6 @@
   bpf_trace_run10
   _cleanup_srcu_struct
   __clk_get_name
-  debugfs_lookup
   devfreq_cooling_unregister
   device_show_int
   device_store_int
@@ -1566,7 +1501,7 @@
   __ll_sc_atomic_or
   mmap_min_addr
   mmput
-  noop_llseek
+  mm_trace_rss_stat
   of_devfreq_cooling_register
   plist_del
   rb_last
@@ -1577,21 +1512,18 @@
   sysfs_create_bin_file
   sysfs_remove_bin_file
   sysfs_remove_files
-  trace_print_symbols_seq
   unmapped_area_topdown
   unregister_shrinker
   vm_insert_page
   vm_insert_pfn
 
 # required by msm_bus_rpmh.ko
-  __msm_bus_scale_client_update_request_cb
-  __msm_bus_scale_register_cb
-  __msm_bus_scale_register_client_cb
-  __msm_bus_scale_update_bw_cb
   of_clk_get_by_name
   raw_notifier_call_chain
   raw_notifier_chain_register
   raw_notifier_chain_unregister
+  rt_mutex_lock
+  rt_mutex_unlock
 
 # required by msm_drm.ko
   adjust_managed_page_count
@@ -1599,7 +1531,6 @@
   bpf_trace_run12
   __clk_get_hw
   clk_get_parent
-  debugfs_create_size_t
   device_create_with_groups
   devm_clk_bulk_get
   devm_of_pwm_get
@@ -1863,7 +1794,6 @@
   shmem_truncate_range
   strreplace
   timespec64_to_jiffies
-  tracing_off
   unmap_kernel_range
   unmap_mapping_range
   vm_get_page_prot
@@ -1873,15 +1803,25 @@
 # required by msm_ext_display.ko
   devm_extcon_dev_unregister
 
-# required by msm_gsi.ko
+# required by msm_geni_serial.ko
-  kstrtoint_from_user
+  console_stop
-
+  console_suspend_enabled
-# required by msm_icnss.ko
+  do_SAK
-  dmam_alloc_coherent
+  handle_sysrq
+  oops_in_progress
+  __tty_insert_flip_char
+  tty_insert_flip_string_fixed_flag
+  uart_console_device
+  uart_console_write
+  uart_get_baud_rate
+  uart_parse_options
+  uart_resume_port
+  uart_set_options
+  uart_suspend_port
+  uart_update_timeout
+  uart_write_wakeup
 
 # required by msm_ipc_logging.ko
-  debugfs_file_get
-  debugfs_file_put
   _raw_read_lock_irq
   _raw_read_unlock_irq
   _raw_write_lock_irqsave
@@ -1893,14 +1833,13 @@
   __tracepoint_clock_set_rate
 
 # required by msm_minidump.ko
-  linux_banner
+  linux_banner_ptr
 
 # required by msm_npu.ko
   kmem_cache_create_usercopy
 
 # required by msm_pm.ko
   arm_cpuidle_suspend
-  clock_debug_print_enabled
   cpu_do_idle
   cpuidle_dev
   cpuidle_register_device
@@ -1913,10 +1852,8 @@
   param_get_bool
   param_get_uint
   pending_ipi
-  pm_gpio_debug_mask
   pm_qos_request_for_cpu
   pm_qos_request_for_cpumask
-  regulator_debug_print_enabled
   s2idle_set_ops
   set_update_ipi_history_callback
   suspend_set_ops
@@ -1934,10 +1871,6 @@
   hwrng_register
   hwrng_unregister
 
-# required by msm_rtb.ko
-  arch_timer_read_counter
-  set_uncached_logk_func
-
 # required by msm_scm.ko
   __arm_smccc_smc
 
@@ -1969,14 +1902,10 @@
   irq_chip_set_wake_parent
   irq_create_fwspec_mapping
   irq_domain_free_irqs_top
-  msm_gpio_dump_builtin_cb
   of_irq_domain_map
   register_restart_handler
   unregister_restart_handler
 
-# required by pinctrl-spmi-gpio.ko
-  pmic_gpio_dump_builtin_cb
-
 # required by platform_dlkm.ko
   __ll_sc___cmpxchg_case_mb_8
   of_property_read_variable_u16_array
@@ -2115,7 +2044,6 @@
 
 # required by qpnp-smb5-charger.ko
   iio_channel_release
-  regulator_get_voltage
 
 # required by qpnp_pdphy.ko
   device_get_named_child_node
@@ -2179,9 +2107,7 @@
   csum_tcpudp_nofold
   __dev_get_by_index
   dev_queue_xmit
-  __dynamic_netdev_dbg
+  genlmsg_put
-  genl_register_family
-  genl_unregister_family
   get_current_napi_context
   gro_cells_destroy
   gro_cells_init
@@ -2201,11 +2127,11 @@
   skb_append_pagefrags
   skb_checksum
   synchronize_rcu
-  trace_print_hex_seq
   unregister_netdevice_many
 
 # required by rndis.ko
   dev_get_stats
+  print_hex_dump_bytes
 
 # required by roles.ko
   class_find_device
@@ -2424,7 +2350,6 @@
 
 # required by snd-soc-wm-adsp.ko
   regmap_async_complete
-  regmap_raw_write
   regmap_raw_write_async
   snd_compr_stop_error
   snd_soc_component_disable_pin
@@ -2432,13 +2357,6 @@
 
 # required by spi-geni-qcom.ko
   dma_release_channel
-  geni_read_reg
-  geni_se_clk_freq_match
-  geni_se_qupv3_hw_version
-  get_rx_fifo_depth
-  get_tx_fifo_width
-  se_geni_clks_on
-  se_get_packing_config
   __spi_alloc_controller
   spi_register_controller
   spi_unregister_controller
@@ -2450,7 +2368,6 @@
   spmi_controller_remove
 
 # required by st21nfc.ko
-  desc_to_gpio
   device_set_wakeup_capable
 
 # required by subsystem-restart.ko
@@ -2480,7 +2397,6 @@
   typec_set_vconn_role
   typec_unregister_altmode
   typec_unregister_port
-  usb_debug_root
 
 # required by tps-regulator.ko
   gpiod_export
@@ -2488,21 +2404,44 @@
   regulator_list_voltage_table
   regulator_map_voltage_ascend
 
-# required by ufs_qcom.ko
+# required by ufshcd-core.ko
-  ufsdbg_pr_buf_to_std
+  async_schedule
-  ufshcd_dme_get_attr
+  bio_crypt_should_process
-  ufshcd_dme_set_attr
+  blk_queue_max_segment_size
-  ufshcd_get_local_unipro_ver
+  blk_queue_rq_timeout
-  ufshcd_hold
+  blk_queue_update_dma_pad
-  ufshcd_pltfrm_init
+  dev_pm_opp_remove
-  ufshcd_pltfrm_resume
+  down_read_trylock
-  ufshcd_pltfrm_runtime_idle
+  down_write_trylock
-  ufshcd_pltfrm_runtime_resume
+  keyslot_manager_create
-  ufshcd_pltfrm_runtime_suspend
+  keyslot_manager_destroy
-  ufshcd_pltfrm_shutdown
+  keyslot_manager_private
-  ufshcd_pltfrm_suspend
+  keyslot_manager_reprogram_all_keys
-  ufshcd_release
+  keyslot_manager_set_max_dun_bytes
-  ufshcd_remove
+  __ll_sc_atomic64_fetch_andnot_release
+  __ll_sc_atomic64_fetch_or_acquire
+  __scsi_add_device
+  scsi_add_host_with_dma
+  scsi_block_requests
+  scsi_change_queue_depth
+  scsi_device_get
+  scsi_device_put
+  scsi_dma_map
+  scsi_dma_unmap
+  __scsi_execute
+  scsi_host_alloc
+  scsi_host_put
+  scsi_print_command
+  scsi_print_sense_hdr
+  scsi_remove_device
+  scsi_remove_host
+  scsi_report_bus_reset
+  scsi_scan_host
+  scsi_set_cmd_timeout_override
+  scsi_unblock_requests
+  sdev_prefix_printk
+  trace_output_call
+  utf16s_to_utf8s
 
 # required by wlan.ko
   bitmap_print_to_pagebuf
@@ -2538,7 +2477,6 @@
   cfg80211_unlink_bss
   cfg80211_update_owe_info_event
   cfg80211_vendor_cmd_reply
-  cld80211_get_genl_family
   complete_and_exit
   cpufreq_quick_get_max
   __cpuhp_remove_state
@@ -2550,10 +2488,9 @@
   crypto_alloc_skcipher
   crypto_shash_final
   crypto_shash_update
-  default_llseek
-  deregister_cld_cmd_cb
   dev_alloc_name
   dump_stack
+  hex2bin
   hex_to_bin
   ieee80211_channel_to_frequency
   ieee80211_frequency_to_channel
@@ -2561,6 +2498,7 @@
   ieee80211_hdrlen
   irq_set_affinity_hint
   mac_pton
+  msleep_interruptible
   netif_tx_stop_all_queues
   netlink_broadcast
   __netlink_kernel_create
@@ -2579,17 +2517,16 @@
   pm_system_wakeup
   proc_create_data
   proc_mkdir
-  _raw_spin_trylock
-  register_cld_cmd_cb
   register_netevent_notifier
   register_sysctl_table
   regulatory_set_wiphy_regd
   rtnl_lock
   save_stack_trace_tsk
   schedule_timeout_interruptible
-  seq_hex_dump
   seq_vprintf
   set_cpus_allowed_ptr
+  single_open
+  single_release
   skip_spaces
   strchrnul
   unregister_netevent_notifier
@@ -2635,10 +2572,10 @@
 
 # required by usb_f_gsi.ko
   dev_get_by_name
-  kstrtou16_from_user
   usb_composite_setup_continue
   usb_ep_autoconfig_by_name
   usb_func_ep_queue
+  usb_func_wakeup
   usb_gsi_ep_op
 
 # required by usb_f_mtp.ko

abi_gki_aarch64_whitelist

@@ -1,4 +1,221 @@
 [abi_whitelist]
 # commonly used symbols
+  __cfi_slowpath
+  __const_udelay
+  _dev_err
+  devm_ioremap_resource
+  devm_kmalloc
+  devm_request_threaded_irq
+  _dev_warn
+  dummy_dma_ops
+  find_next_bit
+  find_next_zero_bit
+  kfree
+  __kmalloc
+  kmalloc_caches
+  kmem_cache_alloc_trace
+  ktime_get
+  __list_add_valid
+  __ll_sc_atomic64_andnot
+  __ll_sc_atomic_add_return
   module_layout
+  __mutex_init
+  mutex_lock
+  mutex_unlock
+  of_find_property
+  of_property_read_variable_u32_array
+  platform_get_irq
+  platform_get_resource
+  printk
   __put_task_struct
+  ___ratelimit
+  _raw_spin_lock_irqsave
+  _raw_spin_unlock_irqrestore
+  snprintf
+  __stack_chk_fail
+  __stack_chk_guard
+  strcmp
+  __udelay
+
+# required by arm-smmu.ko
+  alloc_io_pgtable_ops
+  amba_bustype
+  bus_set_iommu
+  devm_free_irq
+  _dev_notice
+  driver_find_device
+  driver_for_each_device
+  free_io_pgtable_ops
+  generic_device_group
+  iommu_alloc_resv_region
+  iommu_device_link
+  iommu_device_register
+  iommu_device_sysfs_add
+  iommu_device_unlink
+  iommu_dma_get_resv_regions
+  iommu_fwspec_add_ids
+  iommu_fwspec_free
+  iommu_fwspec_init
+  iommu_get_dma_cookie
+  iommu_group_get_for_dev
+  iommu_group_put
+  iommu_group_ref_get
+  iommu_group_remove_device
+  iommu_present
+  iommu_put_dma_cookie
+  __ll_sc_atomic64_fetch_or
+  of_device_get_match_data
+  of_dma_is_coherent
+  of_phandle_iterator_args
+  of_phandle_iterator_init
+  of_phandle_iterator_next
+  param_ops_bool
+  param_ops_int
+  pci_bus_type
+  pci_device_group
+  pci_for_each_dma_alias
+  pci_request_acs
+  platform_bus_type
+  __platform_driver_register
+  platform_driver_unregister
+  put_device
+
+# required by ufshcd-core.ko
+  __alloc_workqueue_key
+  async_schedule
+  bio_crypt_should_process
+  blk_queue_max_segment_size
+  blk_queue_update_dma_pad
+  bpf_trace_run2
+  bpf_trace_run4
+  bpf_trace_run5
+  bpf_trace_run8
+  cancel_delayed_work
+  cancel_delayed_work_sync
+  cancel_work_sync
+  clk_disable
+  clk_enable
+  clk_prepare
+  clk_set_rate
+  clk_unprepare
+  complete
+  cpu_number
+  __cpu_online_mask
+  delayed_work_timer_fn
+  destroy_workqueue
+  dev_driver_string
+  devfreq_add_device
+  devfreq_remove_device
+  devfreq_resume_device
+  devfreq_suspend_device
+  device_create_file
+  device_remove_file
+  devm_clk_get
+  devm_kfree
+  devm_regulator_get
+  dev_pm_opp_add
+  dev_pm_opp_remove
+  dmam_alloc_coherent
+  down_read
+  down_read_trylock
+  down_write
+  event_triggers_call
+  find_last_bit
+  finish_wait
+  flush_work
+  free_irq
+  __init_rwsem
+  init_timer_key
+  init_wait_entry
+  __init_waitqueue_head
+  jiffies
+  jiffies_to_usecs
+  keyslot_manager_create
+  keyslot_manager_destroy
+  keyslot_manager_private
+  keyslot_manager_reprogram_all_keys
+  keyslot_manager_set_max_dun_bytes
+  kstrtouint
+  kstrtoull
+  __ll_sc_atomic64_fetch_andnot_release
+  __ll_sc_atomic64_fetch_or_acquire
+  __ll_sc_atomic_sub_return
+  memcpy
+  memset
+  memzero_explicit
+  __msecs_to_jiffies
+  msleep
+  perf_trace_buf_alloc
+  perf_trace_run_bpf_submit
+  __pm_runtime_idle
+  __pm_runtime_resume
+  preempt_schedule_notrace
+  prepare_to_wait_event
+  print_hex_dump
+  queue_delayed_work_on
+  queue_work_on
+  _raw_spin_lock
+  _raw_spin_unlock
+  regulator_count_voltages
+  regulator_disable
+  regulator_enable
+  regulator_set_load
+  regulator_set_voltage
+  request_threaded_irq
+  schedule
+  schedule_timeout
+  __scsi_add_device
+  scsi_add_host_with_dma
+  scsi_block_requests
+  scsi_change_queue_depth
+  scsi_device_get
+  scsi_device_put
+  scsi_dma_map
+  scsi_dma_unmap
+  __scsi_execute
+  scsi_host_alloc
+  scsi_host_put
+  scsi_print_command
+  scsi_print_sense_hdr
+  scsi_remove_device
+  scsi_remove_host
+  scsi_report_bus_reset
+  scsi_scan_host
+  scsi_unblock_requests
+  sdev_prefix_printk
+  sg_next
+  sprintf
+  strcpy
+  strlcpy
+  strlen
+  strncmp
+  sysfs_create_groups
+  sysfs_remove_groups
+  system_wq
+  trace_define_field
+  trace_event_buffer_commit
+  trace_event_buffer_reserve
+  trace_event_ignore_this_pid
+  trace_event_raw_init
+  trace_event_reg
+  trace_handle_return
+  trace_print_hex_seq
+  trace_print_symbols_seq
+  trace_raw_output_prep
+  trace_seq_printf
+  up_read
+  up_write
+  usleep_range
+  utf16s_to_utf8s
+  wait_for_completion_timeout
+  __wake_up
+  __warn_printk
+
+# required by ufshcd-pltfrm.ko
+  _dev_info
+  kstrdup
+  of_get_property
+  of_parse_phandle
+  of_property_read_string_helper
+  pm_runtime_enable
+  __pm_runtime_set_status

arch/arm/boot/dts/bcm283x.dtsi

@@ -476,6 +476,7 @@
 					     "dsi0_ddr2",
 					     "dsi0_ddr";
 
+			status = "disabled";
 		};
 
 		thermal: thermal@7e212000 {

arch/arm/boot/dts/imx6qdl.dtsi

@@ -1013,9 +1013,8 @@
 				compatible = "fsl,imx6q-fec";
 				reg = <0x02188000 0x4000>;
 				interrupt-names = "int0", "pps";
-				interrupts-extended =
+				interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
-					<&intc 0 118 IRQ_TYPE_LEVEL_HIGH>,
+					     <0 119 IRQ_TYPE_LEVEL_HIGH>;
-					<&intc 0 119 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET>,
 					 <&clks IMX6QDL_CLK_ENET_REF>;

arch/arm/boot/dts/imx6qp.dtsi

@@ -77,7 +77,6 @@
 };
 
 &fec {
-	/delete-property/interrupts-extended;
 	interrupts = <0 118 IRQ_TYPE_LEVEL_HIGH>,
 		     <0 119 IRQ_TYPE_LEVEL_HIGH>;
 };

arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts

@@ -318,8 +318,8 @@
 };
 
 &reg_dldo3 {
-	regulator-min-microvolt = <2800000>;
+	regulator-min-microvolt = <1800000>;
-	regulator-max-microvolt = <2800000>;
+	regulator-max-microvolt = <1800000>;
 	regulator-name = "vdd-csi";
 };
 

arch/arm/include/asm/clocksource.h

@@ -1,8 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _ASM_CLOCKSOURCE_H
 #define _ASM_CLOCKSOURCE_H
 
-struct arch_clocksource_data {
+#include <asm/vdso/clocksource.h>
-	bool vdso_direct;	/* Usable for direct VDSO access? */
-};
 
-#endif
+#endif /* _ASM_CLOCKSOURCE_H */

arch/arm/include/asm/cp15.h

@@ -50,25 +50,7 @@
 
 #ifdef CONFIG_CPU_CP15
 
-#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
+#include <asm/vdso/cp15.h>
-	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
-#define __ACCESS_CP15_64(Op1, CRm)		\
-	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
-
-#define __read_sysreg(r, w, c, t) ({				\
-	t __val;						\
-	asm volatile(r " " c : "=r" (__val));			\
-	__val;							\
-})
-#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
-
-#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
-#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
-
-#define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
-#define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
-
-#define CNTVCT				__ACCESS_CP15_64(1, c14)
 
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 

arch/arm/include/asm/processor.h

@@ -23,6 +23,7 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 #include <asm/unified.h>
+#include <asm/vdso/processor.h>
 
 #ifdef __KERNEL__
 #define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
@@ -94,16 +95,6 @@ extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
 
-#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
-#define cpu_relax()						\
-	do {							\
-		smp_mb();					\
-		__asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;");	\
-	} while (0)
-#else
-#define cpu_relax()			barrier()
-#endif
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 

arch/arm/include/asm/vdso/clocksource.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+struct arch_clocksource_data {
+	bool vdso_direct;	/* Usable for direct VDSO access? */
+};
+
+#endif /* __ASM_VDSOCLOCKSOURCE_H */

arch/arm/include/asm/vdso/cp15.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_VDSO_CP15_H
+#define __ASM_VDSO_CP15_H
+
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_CPU_CP15
+
+#include <linux/stringify.h>
+
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
+	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
+#define __ACCESS_CP15_64(Op1, CRm)		\
+	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
+
+#define __read_sysreg(r, w, c, t) ({				\
+	t __val;						\
+	asm volatile(r " " c : "=r" (__val));			\
+	__val;							\
+})
+#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
+
+#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
+#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
+
+#define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
+#define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
+
+#define CNTVCT				__ACCESS_CP15_64(1, c14)
+
+#endif /* CONFIG_CPU_CP15 */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_CP15_H */

arch/arm/include/asm/vdso/gettimeofday.h

@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/errno.h>
+#include <asm/unistd.h>
+#include <asm/vdso/cp15.h>
+#include <uapi/linux/time.h>
+
+#define VDSO_HAS_CLOCK_GETRES		1
+
+extern struct vdso_data *__get_datapage(void);
+
+static __always_inline int gettimeofday_fallback(
+				struct __kernel_old_timeval *_tv,
+				struct timezone *_tz)
+{
+	register struct timezone *tz asm("r1") = _tz;
+	register struct __kernel_old_timeval *tv asm("r0") = _tv;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_gettimeofday;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (tv), "r" (tz), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline long clock_gettime_fallback(
+					clockid_t _clkid,
+					struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_gettime64;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline long clock_gettime32_fallback(
+					clockid_t _clkid,
+					struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_gettime;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline int clock_getres_fallback(
+					clockid_t _clkid,
+					struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_getres_time64;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline int clock_getres32_fallback(
+					clockid_t _clkid,
+					struct old_timespec32 *_ts)
+{
+	register struct old_timespec32 *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_clock_getres;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static inline bool arm_vdso_hres_capable(void)
+{
+	return IS_ENABLED(CONFIG_ARM_ARCH_TIMER);
+}
+#define __arch_vdso_hres_capable arm_vdso_hres_capable
+
+static __always_inline u64 __arch_get_hw_counter(int clock_mode)
+{
+#ifdef CONFIG_ARM_ARCH_TIMER
+	u64 cycle_now;
+
+	/*
+	 * Core checks for mode already, so this raced against a concurrent
+	 * update. Return something. Core will do another round and then
+	 * see the mode change and fallback to the syscall.
+	 */
+	if (clock_mode == VDSO_CLOCKMODE_NONE)
+		return 0;
+
+	isb();
+	cycle_now = read_sysreg(CNTVCT);
+
+	return cycle_now;
+#else
+	/* Make GCC happy. This is compiled out anyway */
+	return 0;
+#endif
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return __get_datapage();
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm/include/asm/vdso/processor.h

@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+#if __LINUX_ARM_ARCH__ == 6 || defined(CONFIG_ARM_ERRATA_754327)
+#define cpu_relax()						\
+	do {							\
+		smp_mb();					\
+		__asm__ __volatile__("nop; nop; nop; nop; nop; nop; nop; nop; nop; nop;");	\
+	} while (0)
+#else
+#define cpu_relax()			barrier()
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */

arch/arm/kernel/setup.c

@@ -116,6 +116,14 @@ EXPORT_SYMBOL(elf_hwcap2);
 char* (*arch_read_hardware_id)(void);
 EXPORT_SYMBOL(arch_read_hardware_id);
 
+/* Vendor stub */
+unsigned int boot_reason;
+EXPORT_SYMBOL_GPL(boot_reason);
+
+/* Vendor stub */
+unsigned int cold_boot;
+EXPORT_SYMBOL_GPL(cold_boot);
+
 #ifdef MULTI_CPU
 struct processor processor __ro_after_init;
 #if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)

arch/arm/mach-imx/Makefile

@@ -89,8 +89,10 @@ AFLAGS_suspend-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += suspend-imx6.o
 obj-$(CONFIG_SOC_IMX53) += suspend-imx53.o
 endif
+ifeq ($(CONFIG_ARM_CPU_SUSPEND),y)
 AFLAGS_resume-imx6.o :=-Wa,-march=armv7-a
 obj-$(CONFIG_SOC_IMX6) += resume-imx6.o
+endif
 obj-$(CONFIG_SOC_IMX6) += pm-imx6.o
 
 obj-$(CONFIG_SOC_IMX1) += mach-imx1.o

arch/arm/mm/dma-mapping.c

@@ -378,7 +378,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
 static void __dma_free_remap(void *cpu_addr, size_t size)
 {
 	dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, false);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
@@ -1648,7 +1648,7 @@ void __arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 
 	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0) {
 		dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, false);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);

arch/arm/net/bpf_jit_32.c

@@ -930,7 +930,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSR operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for LSR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
@@ -956,7 +960,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do ARSH operation */
-	if (val < 32) {
+	if (val == 0) {
+		/* An immediate value of 0 encodes a shift amount of 32
+		 * for ASR. To shift by 0, don't do anything.
+		 */
+	} else if (val < 32) {
 		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
 		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
 		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
@@ -993,21 +1001,35 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 	arm_bpf_put_reg32(dst_hi, rd[0], ctx);
 }
 
+static bool is_ldst_imm(s16 off, const u8 size)
+{
+	s16 off_max = 0;
+
+	switch (size) {
+	case BPF_B:
+	case BPF_W:
+		off_max = 0xfff;
+		break;
+	case BPF_H:
+		off_max = 0xff;
+		break;
+	case BPF_DW:
+		/* Need to make sure off+4 does not overflow. */
+		off_max = 0xfff - 4;
+		break;
+	}
+	return -off_max <= off && off <= off_max;
+}
+
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src[],
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s32 off_max;
 	s8 rd;
 
 	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
 
-	if (sz == BPF_H)
+	if (!is_ldst_imm(off, sz)) {
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
-
-	if (off < 0 || off > off_max) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
 		rd = tmp[0];
@@ -1036,18 +1058,12 @@ static inline void emit_str_r(const s8 dst, const s8 src[],
 
 /* dst = *(size*)(src + off) */
 static inline void emit_ldx_r(const s8 dst[], const s8 src,
-			      s32 off, struct jit_ctx *ctx, const u8 sz){
+			      s16 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
 	s8 rm = src;
-	s32 off_max;
 
-	if (sz == BPF_H)
+	if (!is_ldst_imm(off, sz)) {
-		off_max = 0xff;
-	else
-		off_max = 0xfff;
-
-	if (off < 0 || off > off_max) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];

arch/arm64/Kconfig

@@ -100,6 +100,7 @@ config ARM64
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
+	select GENERIC_GETTIMEOFDAY
 	select HANDLE_DOMAIN_IRQ
 	select HARDIRQS_SW_RESEND
 	select HAVE_ACPI_APEI if (ACPI && EFI)
@@ -138,6 +139,8 @@ config ARM64
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_KERNEL_GZIP
+	select HAVE_KERNEL_LZ4
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP if NUMA
 	select HAVE_NMI
@@ -152,6 +155,7 @@ config ARM64
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
+	select HAVE_GENERIC_VDSO
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
@@ -503,6 +507,22 @@ config ARM64_ERRATUM_1463225
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_1542419
+	bool "Neoverse-N1: workaround mis-ordering of instruction fetches"
+	default y
+	help
+	  This option adds a workaround for ARM Neoverse-N1 erratum
+	  1542419.
+
+	  Affected Neoverse-N1 cores could execute a stale instruction when
+	  modified by another CPU. The workaround depends on a firmware
+	  counterpart.
+
+	  Workaround the issue by hiding the DIC feature from EL0. This
+	  forces user-space to perform cache maintenance.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
@@ -752,6 +772,18 @@ config HOTPLUG_CPU
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
+# The GPIO number here must be sorted by descending number. In case of
+# a multiplatform kernel, we just want the highest value required by the
+# selected platforms.
+config ARCH_NR_GPIO
+	int "Number of GPIOs in the system"
+	default 1280 if ARCH_QCOM
+	default 256
+	help
+	  Maximum number of GPIOs in the system.
+
+	  If unsure, leave the default value.
+
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support"
@@ -830,6 +862,37 @@ config ARCH_HAS_CACHE_LINE_SIZE
 config CC_HAVE_SHADOW_CALL_STACK
 	def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18)
 
+config ARM64_DMA_USE_IOMMU
+	bool "ARM64 DMA iommu integration"
+	select ARM_HAS_SG_CHAIN
+	select NEED_SG_DMA_LENGTH
+	help
+	  Enable using iommu through the standard dma apis.
+	  dma_alloc_coherent() will allocate scatter-gather memory
+	  which is made virtually contiguous via iommu.
+	  Enable if system contains IOMMU hardware.
+
+if ARM64_DMA_USE_IOMMU
+
+config ARM64_DMA_IOMMU_ALIGNMENT
+	int "Maximum PAGE_SIZE order of alignment for DMA IOMMU buffers"
+	range 4 9
+	default 9
+	help
+	  DMA mapping framework by default aligns all buffers to the smallest
+	  PAGE_SIZE order which is greater than or equal to the requested buffer
+	  size. This works well for buffers up to a few hundreds kilobytes, but
+	  for larger buffers it just a waste of address space. Drivers which has
+	  relatively small addressing window (like 64Mib) might run out of
+	  virtual space with just a few allocations.
+
+	  With this parameter you can specify the maximum PAGE_SIZE order for
+	  DMA IOMMU buffers. Larger buffers will be aligned only to this
+	  specified order. The order is expressed as a power of two multiplied
+	  by the PAGE_SIZE.
+
+endif
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -981,6 +1044,19 @@ config ARM64_TAGGED_ADDR_ABI
 	  to system calls as pointer arguments. For details, see
 	  Documentation/arm64/tagged-address-abi.rst.
 
+config COMPAT_VDSO
+	bool "Enable vDSO for 32-bit applications"
+	depends on !CPU_BIG_ENDIAN && "$(CROSS_COMPILE_COMPAT)" != ""
+	select GENERIC_COMPAT_VDSO
+	default y
+	help
+	  Place in the process address space of 32-bit applications an
+	  ELF shared object providing fast implementations of gettimeofday
+	  and clock_gettime.
+
+	  You must have a 32-bit build of glibc 2.22 or later for programs
+	  to seamlessly take advantage of this.
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
 	depends on COMPAT
@@ -1358,6 +1434,34 @@ config COMPAT
 
 	  If you want to execute 32-bit userspace applications, say Y.
 
+config KUSER_HELPERS
+	bool "Enable kuser helpers page for 32 bit applications."
+	depends on COMPAT
+	default y
+	help
+	  Warning: disabling this option may break 32-bit user programs.
+
+	  Provide kuser helpers to compat tasks. The kernel provides
+	  helper code to userspace in read only form at a fixed location
+	  to allow userspace to be independent of the CPU type fitted to
+	  the system. This permits binaries to be run on ARMv4 through
+	  to ARMv8 without modification.
+
+	  See Documentation/arm/kernel_user_helpers.txt for details.
+
+	  However, the fixed address nature of these helpers can be used
+	  by ROP (return orientated programming) authors when creating
+	  exploits.
+
+	  If all of the binaries and libraries which run on your platform
+	  are built specifically for your platform, and make no use of
+	  these helpers, then you can turn this option off to hinder
+	  such exploits. However, in that case, if a binary or library
+	  relying on those helpers is run, it will not function correctly.
+
+	  Say N here only if you are absolutely certain that you do not
+	  need these helpers; otherwise, the safe option is to say Y.
+
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC

arch/arm64/Makefile

@@ -49,10 +49,10 @@ $(warning Detected assembler with broken .inst; disassembly will be unreliable)
   endif
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)
+KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst) $(compat_vdso)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-disable-warning, psabi)
-KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
+KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst) $(compat_vdso)
 
 KBUILD_CFLAGS	+= $(call cc-option,-mabi=lp64)
 KBUILD_AFLAGS	+= $(call cc-option,-mabi=lp64)
@@ -171,6 +171,9 @@ ifeq ($(KBUILD_EXTMOD),)
 prepare: vdso_prepare
 vdso_prepare: prepare0
 	$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h
+	$(if $(CONFIG_COMPAT_VDSO),$(Q)$(MAKE) \
+		$(build)=arch/arm64/kernel/vdso32  \
+		include/generated/vdso32-offsets.h)
 endif
 
 define archhelp

arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi

@@ -70,8 +70,7 @@
 	};
 
 	pmu {
-		compatible = "arm,cortex-a53-pmu",
+		compatible = "arm,cortex-a53-pmu";
-			     "arm,armv8-pmuv3";
 		interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>,

arch/arm64/configs/gki_defconfig

@@ -2,6 +2,7 @@ CONFIG_AUDIT=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
+CONFIG_IRQ_TIME_ACCOUNTING=y
 CONFIG_TASKSTATS=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
@@ -14,12 +15,12 @@ CONFIG_MEMCG=y
 CONFIG_MEMCG_SWAP=y
 CONFIG_BLK_CGROUP=y
 CONFIG_CGROUP_SCHED=y
+# CONFIG_FAIR_GROUP_SCHED is not set
 CONFIG_CGROUP_FREEZER=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_CGROUP_BPF=y
 CONFIG_NAMESPACES=y
-# CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_SCHED_TUNE=y
 CONFIG_BLK_DEV_INITRD=y
@@ -49,6 +50,7 @@ CONFIG_SCHED_MC=y
 CONFIG_NR_CPUS=32
 CONFIG_SECCOMP=y
 CONFIG_PARAVIRT=y
+# CONFIG_ARM64_TAGGED_ADDR_ABI is not set
 CONFIG_ARMV8_DEPRECATED=y
 CONFIG_SWP_EMULATION=y
 CONFIG_CP15_BARRIER_EMULATION=y
@@ -64,6 +66,7 @@ CONFIG_ENERGY_MODEL=y
 CONFIG_CPU_IDLE=y
 CONFIG_ARM_CPUIDLE=y
 CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_TIMES=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
@@ -94,6 +97,7 @@ CONFIG_CLEANCACHE=y
 CONFIG_CMA=y
 CONFIG_CMA_AREAS=16
 CONFIG_ZSMALLOC=y
+CONFIG_MM_EVENT_STAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -106,7 +110,9 @@ CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_NET_IPIP=y
 CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPGRE=y
 CONFIG_NET_IPVTI=y
 CONFIG_INET_ESP=y
 CONFIG_INET_UDP_DIAG=y
@@ -118,6 +124,7 @@ CONFIG_INET6_ESP=y
 CONFIG_INET6_IPCOMP=y
 CONFIG_IPV6_MIP6=y
 CONFIG_IPV6_VTI=y
+CONFIG_IPV6_GRE=y
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
 CONFIG_NETFILTER=y
@@ -209,6 +216,8 @@ CONFIG_CFG80211=y
 CONFIG_MAC80211=y
 CONFIG_RFKILL=y
 # CONFIG_UEVENT_HELPER is not set
+CONFIG_FW_LOADER_USER_HELPER=y
+CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y
 # CONFIG_FW_CACHE is not set
 # CONFIG_ALLOW_DEV_COREDUMP is not set
 CONFIG_DMA_CMA=y
@@ -221,8 +230,9 @@ CONFIG_UID_SYS_STATS=y
 CONFIG_SCSI=y
 # CONFIG_SCSI_PROC_FS is not set
 CONFIG_BLK_DEV_SD=y
-CONFIG_SCSI_UFSHCD=y
+CONFIG_CHR_DEV_SG=y
-CONFIG_SCSI_UFSHCD_PLATFORM=y
+CONFIG_SCSI_UFSHCD=m
+CONFIG_SCSI_UFSHCD_PLATFORM=m
 CONFIG_SCSI_UFS_CRYPTO=y
 CONFIG_MD=y
 CONFIG_BLK_DEV_DM=y
@@ -237,6 +247,7 @@ CONFIG_DM_BOW=y
 CONFIG_NETDEVICES=y
 CONFIG_DUMMY=y
 CONFIG_TUN=y
+CONFIG_VETH=y
 # CONFIG_ETHERNET is not set
 CONFIG_PHYLIB=y
 CONFIG_PPP=y
@@ -288,31 +299,39 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_SERIAL_MSM_GENI_EARLY_CONSOLE=y
 CONFIG_SERIAL_DEV_BUS=y
 CONFIG_HW_RANDOM=y
 # CONFIG_HW_RANDOM_CAVIUM is not set
 # CONFIG_DEVPORT is not set
 # CONFIG_I2C_COMPAT is not set
+CONFIG_I2C_CHARDEV=y
 # CONFIG_I2C_HELPER_AUTO is not set
 CONFIG_SPI=y
 CONFIG_SPMI=y
+# CONFIG_SPMI_MSM_PMIC_ARB is not set
 CONFIG_PINCTRL_AMD=y
+CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_AVS=y
 CONFIG_POWER_RESET_HISI=y
-# CONFIG_HWMON is not set
 CONFIG_THERMAL=y
+CONFIG_THERMAL_STATISTICS=y
+CONFIG_THERMAL_WRITABLE_TRIPS=y
 CONFIG_THERMAL_GOV_USER_SPACE=y
 CONFIG_CPU_THERMAL=y
 CONFIG_DEVFREQ_THERMAL=y
+CONFIG_THERMAL_EMULATION=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_CORE=y
 CONFIG_MFD_ACT8945A=y
 CONFIG_MFD_SYSCON=y
 CONFIG_REGULATOR=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
+CONFIG_REGULATOR_PROXY_CONSUMER=y
 CONFIG_MEDIA_SUPPORT=y
 CONFIG_MEDIA_CAMERA_SUPPORT=y
 CONFIG_MEDIA_CONTROLLER=y
+CONFIG_VIDEO_V4L2_SUBDEV_API=y
 # CONFIG_VGA_ARB is not set
 CONFIG_DRM=y
 # CONFIG_DRM_FBDEV_EMULATION is not set
@@ -325,7 +344,6 @@ CONFIG_SND=y
 CONFIG_SND_HRTIMER=y
 CONFIG_SND_DYNAMIC_MINORS=y
 # CONFIG_SND_SUPPORT_OLD_API is not set
-# CONFIG_SND_VERBOSE_PROCFS is not set
 # CONFIG_SND_DRIVERS is not set
 CONFIG_SND_USB_AUDIO=y
 CONFIG_SND_SOC=y
@@ -354,14 +372,15 @@ CONFIG_TYPEC=y
 CONFIG_MMC=y
 # CONFIG_PWRSEQ_EMMC is not set
 # CONFIG_PWRSEQ_SIMPLE is not set
+CONFIG_MMC_CRYPTO=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TRANSIENT=y
 CONFIG_EDAC=y
 CONFIG_RTC_CLASS=y
-# CONFIG_RTC_SYSTOHC is not set
 CONFIG_RTC_DRV_PL030=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_DMADEVICES=y
@@ -373,7 +392,10 @@ CONFIG_COMMON_CLK_SCPI=y
 # CONFIG_COMMON_CLK_XGENE is not set
 CONFIG_HWSPINLOCK=y
 CONFIG_MAILBOX=y
-CONFIG_ARM_SMMU=y
+CONFIG_IOMMU_IO_PGTABLE_FAST=y
+CONFIG_ARM_SMMU=m
+CONFIG_REMOTEPROC=y
+CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y
 CONFIG_DEVFREQ_GOV_PERFORMANCE=y
 CONFIG_DEVFREQ_GOV_POWERSAVE=y
 CONFIG_DEVFREQ_GOV_USERSPACE=y
@@ -464,6 +486,8 @@ CONFIG_SECURITY=y
 CONFIG_SECURITYFS=y
 CONFIG_SECURITY_NETWORK=y
 CONFIG_HARDENED_USERCOPY=y
+CONFIG_FORTIFY_SOURCE=y
+CONFIG_STATIC_USERMODEHELPER=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_INIT_STACK_ALL=y
 CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y
@@ -487,5 +511,3 @@ CONFIG_PANIC_TIMEOUT=5
 CONFIG_SCHEDSTATS=y
 # CONFIG_DEBUG_PREEMPT is not set
 CONFIG_DEBUG_LIST=y
-CONFIG_CORESIGHT=y
-CONFIG_CORESIGHT_STM=y

arch/arm64/include/asm/cache.h

@@ -22,6 +22,7 @@
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
 #define CTR_IMINLINE_SHIFT	0
+#define CTR_IMINLINE_MASK	0xf
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
@@ -29,7 +30,7 @@
 #define CTR_DIC_SHIFT		29
 
 #define CTR_CACHE_MINLINE_MASK	\
-	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+	(0xf << CTR_DMINLINE_SHIFT | CTR_IMINLINE_MASK << CTR_IMINLINE_SHIFT)
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 

arch/arm64/include/asm/cacheflush.h

@@ -131,6 +131,15 @@ static inline void flush_cache_range(struct vm_area_struct *vma,
 extern void __dma_map_area(const void *, size_t, int);
 extern void __dma_unmap_area(const void *, size_t, int);
 extern void __dma_flush_area(const void *, size_t);
+extern void __dma_inv_area(const void *start, size_t size);
+extern void __dma_clean_area(const void *start, size_t size);
+
+#define dmac_flush_range(start, end) \
+	__dma_flush_area(start, (void *)(end) - (void *)(start))
+#define dmac_inv_range(start, end) \
+	__dma_inv_area(start, (void *)(end) - (void *)(start))
+#define dmac_clean_range(start, end) \
+	__dma_clean_area(start, (void *)(end) - (void *)(start))
 
 /*
  * Copy user data from/to a page which is mapped into a different

arch/arm64/include/asm/clocksource.h

@@ -2,8 +2,6 @@
 #ifndef _ASM_CLOCKSOURCE_H
 #define _ASM_CLOCKSOURCE_H
 
-struct arch_clocksource_data {
+#include <asm/vdso/clocksource.h>
-	bool vdso_direct;	/* Usable for direct VDSO access? */
-};
 
 #endif

arch/arm64/include/asm/cpucaps.h

@@ -53,8 +53,9 @@
 #define ARM64_HAS_STAGE2_FWB			32
 #define ARM64_WORKAROUND_1463225		33
 #define ARM64_SSBS				34
+#define ARM64_WORKAROUND_1542419		35
 
-/* kabi: reserve 35 - 62 for future cpu capabilities */
+/* kabi: reserve 36 - 62 for future cpu capabilities */
 #define ARM64_NCAPS				62
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cputype.h

@@ -80,6 +80,7 @@
 #define ARM_CPU_PART_CORTEX_A35		0xD04
 #define ARM_CPU_PART_CORTEX_A55		0xD05
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -107,6 +108,7 @@
 #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
 #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
 #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)

arch/arm64/include/asm/device.h

@@ -24,9 +24,18 @@ struct dev_archdata {
 	const struct dma_map_ops *dev_dma_ops;
 #endif
 	bool dma_coherent;
+#ifdef CONFIG_ARM64_DMA_USE_IOMMU
+	struct dma_iommu_mapping       *mapping;
+#endif
 };
 
 struct pdev_archdata {
 };
 
+#ifdef CONFIG_ARM64_DMA_USE_IOMMU
+#define to_dma_iommu_mapping(dev) ((dev)->archdata.mapping)
+#else
+#define to_dma_iommu_mapping(dev) NULL
+#endif
+
 #endif

arch/arm64/include/asm/dma-contiguous.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2013,2017-2018 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _ASM_DMA_CONTIGUOUS_H
+#define _ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);
+
+#endif
+#endif
+
+#endif

arch/arm64/include/asm/dma-iommu.h

@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef ASMARM_DMA_IOMMU_H
+#define ASMARM_DMA_IOMMU_H
+
+#ifdef __KERNEL__
+
+#include <linux/err.h>
+#include <linux/mm_types.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/kref.h>
+#include <linux/dma-mapping-fast.h>
+
+struct dma_iommu_mapping {
+	/* iommu specific data */
+	struct iommu_domain	*domain;
+	bool			init;
+	struct kref		kref;
+	const struct dma_map_ops *ops;
+
+	/* Protects bitmap */
+	spinlock_t		lock;
+	void			*bitmap;
+	size_t			bits;
+	dma_addr_t		base;
+
+	struct dma_fast_smmu_mapping *fast;
+};
+
+#ifdef CONFIG_ARM64_DMA_USE_IOMMU
+void arm_iommu_put_dma_cookie(struct iommu_domain *domain);
+#else  /* !CONFIG_ARM64_DMA_USE_IOMMU */
+static inline void arm_iommu_put_dma_cookie(struct iommu_domain *domain) {}
+#endif	/* CONFIG_ARM64_DMA_USE_IOMMU */
+
+#endif /* __KERNEL__ */
+#endif

arch/arm64/include/asm/elf.h

@@ -209,11 +209,25 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 ({									\
 	set_thread_flag(TIF_32BIT);					\
  })
+#ifdef CONFIG_COMPAT_VDSO
+#define COMPAT_ARCH_DLINFO						\
+do {									\
+	/*								\
+	 * Note that we use Elf64_Off instead of elf_addr_t because	\
+	 * elf_addr_t in compat is defined as Elf32_Addr and casting	\
+	 * current->mm->context.vdso to it triggers a cast warning of	\
+	 * cast from pointer to integer of different size.		\
+	 */								\
+	NEW_AUX_ENT(AT_SYSINFO_EHDR,					\
+			(Elf64_Off)current->mm->context.vdso);		\
+} while (0)
+#else
 #define COMPAT_ARCH_DLINFO
-extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
+#endif
-				      int uses_interp);
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+					  int uses_interp);
 #define compat_arch_setup_additional_pages \
-					aarch32_setup_vectors_page
+					aarch32_setup_additional_pages
 
 #endif /* CONFIG_COMPAT */
 

arch/arm64/include/asm/lse.h

@@ -21,7 +21,7 @@
 #else	/* __ASSEMBLER__ */
 
 #ifdef CONFIG_LTO_CLANG
-#define __LSE_PREAMBLE	".arch armv8-a+lse\n"
+#define __LSE_PREAMBLE	".arch_extension lse\n"
 #else
 __asm__(".arch_extension	lse");
 #define __LSE_PREAMBLE

arch/arm64/include/asm/processor.h

@@ -40,6 +40,8 @@
 #include <linux/stddef.h>
 #include <linux/string.h>
 
+#include <vdso/processor.h>
+
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/hw_breakpoint.h>
@@ -53,7 +55,7 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #ifdef CONFIG_COMPAT
-#ifdef CONFIG_ARM64_64K_PAGES
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
 /*
  * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
  * by the compat vectors page.
@@ -227,11 +229,6 @@ extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
 
-static inline void cpu_relax(void)
-{
-	asm volatile("yield" ::: "memory");
-}
-
 /* Thread switching */
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);

arch/arm64/include/asm/signal32.h

@@ -20,7 +20,51 @@
 #ifdef CONFIG_COMPAT
 #include <linux/compat.h>
 
-#define AARCH32_KERN_SIGRET_CODE_OFFSET	0x500
+struct compat_sigcontext {
+	/* We always set these two fields to 0 */
+	compat_ulong_t			trap_no;
+	compat_ulong_t			error_code;
+
+	compat_ulong_t			oldmask;
+	compat_ulong_t			arm_r0;
+	compat_ulong_t			arm_r1;
+	compat_ulong_t			arm_r2;
+	compat_ulong_t			arm_r3;
+	compat_ulong_t			arm_r4;
+	compat_ulong_t			arm_r5;
+	compat_ulong_t			arm_r6;
+	compat_ulong_t			arm_r7;
+	compat_ulong_t			arm_r8;
+	compat_ulong_t			arm_r9;
+	compat_ulong_t			arm_r10;
+	compat_ulong_t			arm_fp;
+	compat_ulong_t			arm_ip;
+	compat_ulong_t			arm_sp;
+	compat_ulong_t			arm_lr;
+	compat_ulong_t			arm_pc;
+	compat_ulong_t			arm_cpsr;
+	compat_ulong_t			fault_address;
+};
+
+struct compat_ucontext {
+	compat_ulong_t			uc_flags;
+	compat_uptr_t			uc_link;
+	compat_stack_t			uc_stack;
+	struct compat_sigcontext	uc_mcontext;
+	compat_sigset_t			uc_sigmask;
+	int 				__unused[32 - (sizeof(compat_sigset_t) / sizeof(int))];
+	compat_ulong_t			uc_regspace[128] __attribute__((__aligned__(8)));
+};
+
+struct compat_sigframe {
+	struct compat_ucontext	uc;
+	compat_ulong_t		retcode[2];
+};
+
+struct compat_rt_sigframe {
+	struct compat_siginfo info;
+	struct compat_sigframe sig;
+};
 
 int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
 		       struct pt_regs *regs);

arch/arm64/include/asm/sysreg.h

@@ -60,7 +60,9 @@
 #ifndef CONFIG_BROKEN_GAS_INST
 
 #ifdef __ASSEMBLY__
-#define __emit_inst(x)			.inst (x)
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x)			.inst(x)
 #else
 #define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
 #endif

arch/arm64/include/asm/unistd.h

@@ -33,8 +33,13 @@
 #define __NR_compat_exit		1
 #define __NR_compat_read		3
 #define __NR_compat_write		4
+#define __NR_compat_gettimeofday	78
 #define __NR_compat_sigreturn		119
 #define __NR_compat_rt_sigreturn	173
+#define __NR_compat_clock_gettime	263
+#define __NR_compat_clock_getres	264
+#define __NR_compat_clock_gettime64	403
+#define __NR_compat_clock_getres_time64	406
 
 /*
  * The following SVCs are ARM private.

arch/arm64/include/asm/vdso.h

@@ -28,6 +28,9 @@
 #ifndef __ASSEMBLY__
 
 #include <generated/vdso-offsets.h>
+#ifdef CONFIG_COMPAT_VDSO
+#include <generated/vdso32-offsets.h>
+#endif
 
 #define VDSO_SYMBOL(base, name)						   \
 ({									   \

arch/arm64/include/asm/vdso/clocksource.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+struct arch_clocksource_data {
+	bool vdso_direct;	/* Usable for direct VDSO access? */
+};
+
+#endif

arch/arm64/include/asm/vdso/compat_barrier.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __COMPAT_BARRIER_H
+#define __COMPAT_BARRIER_H
+
+#ifndef __ASSEMBLY__
+/*
+ * Warning: This code is meant to be used with
+ * ENABLE_COMPAT_VDSO only.
+ */
+#ifndef ENABLE_COMPAT_VDSO
+#error This header is meant to be used with ENABLE_COMPAT_VDSO only
+#endif
+
+#ifdef dmb
+#undef dmb
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 7
+#define dmb(option) __asm__ __volatile__ ("dmb " #option : : : "memory")
+#elif __LINUX_ARM_ARCH__ == 6
+#define dmb(x) __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
+				    : : "r" (0) : "memory")
+#else
+#define dmb(x) __asm__ __volatile__ ("" : : : "memory")
+#endif
+
+#if __LINUX_ARM_ARCH__ >= 8 && defined(CONFIG_AS_DMB_ISHLD)
+#define aarch32_smp_mb()	dmb(ish)
+#define aarch32_smp_rmb()	dmb(ishld)
+#define aarch32_smp_wmb()	dmb(ishst)
+#else
+#define aarch32_smp_mb()	dmb(ish)
+#define aarch32_smp_rmb()	aarch32_smp_mb()
+#define aarch32_smp_wmb()	dmb(ishst)
+#endif
+
+
+#undef smp_mb
+#undef smp_rmb
+#undef smp_wmb
+
+#define smp_mb()	aarch32_smp_mb()
+#define smp_rmb()	aarch32_smp_rmb()
+#define smp_wmb()	aarch32_smp_wmb()
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __COMPAT_BARRIER_H */

arch/arm64/include/asm/vdso/compat_gettimeofday.h

@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+#include <asm/errno.h>
+
+#include <asm/vdso/compat_barrier.h>
+
+#define __VDSO_USE_SYSCALL		ULLONG_MAX
+
+#define VDSO_HAS_CLOCK_GETRES		1
+
+#define BUILD_VDSO32			1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct timezone *tz asm("r1") = _tz;
+	register struct __kernel_old_timeval *tv asm("r0") = _tv;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_gettimeofday;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (tv), "r" (tz), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_gettime;
+
+	asm volatile(
+	"	swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("r1") = _ts;
+	register clockid_t clkid asm("r0") = _clkid;
+	register long ret asm ("r0");
+	register long nr asm("r7") = __NR_compat_clock_getres;
+
+	asm volatile(
+	"       swi #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+	u64 res;
+
+	/*
+	 * clock_mode == 0 implies that vDSO are enabled otherwise
+	 * fallback on syscall.
+	 */
+	if (clock_mode)
+		return __VDSO_USE_SYSCALL;
+
+	/*
+	 * This isb() is required to prevent that the counter value
+	 * is speculated.
+	 */
+	isb();
+	asm volatile("mrrc p15, 1, %Q0, %R0, c14" : "=r" (res));
+	/*
+	 * This isb() is required to prevent that the seq lock is
+	 * speculated.
+	 */
+	isb();
+
+	return res;
+}
+
+static __always_inline const struct vdso_data *__arch_get_vdso_data(void)
+{
+	const struct vdso_data *ret;
+
+	/*
+	 * This simply puts &_vdso_data into ret. The reason why we don't use
+	 * `ret = _vdso_data` is that the compiler tends to optimise this in a
+	 * very suboptimal way: instead of keeping &_vdso_data in a register,
+	 * it goes through a relocation almost every time _vdso_data must be
+	 * accessed (even in subfunctions). This is both time and space
+	 * consuming: each relocation uses a word in the code section, and it
+	 * has to be loaded at runtime.
+	 *
+	 * This trick hides the assignment from the compiler. Since it cannot
+	 * track where the pointer comes from, it will only use one relocation
+	 * where __arch_get_vdso_data() is called, and then keep the result in
+	 * a register.
+	 */
+	asm volatile("mov %0, %1" : "=r"(ret) : "r"(_vdso_data));
+
+	return ret;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/gettimeofday.h

@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 ARM Limited
+ */
+#ifndef __ASM_VDSO_GETTIMEOFDAY_H
+#define __ASM_VDSO_GETTIMEOFDAY_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/unistd.h>
+
+#define __VDSO_USE_SYSCALL		ULLONG_MAX
+
+#define VDSO_HAS_CLOCK_GETRES		1
+
+static __always_inline
+int gettimeofday_fallback(struct __kernel_old_timeval *_tv,
+			  struct timezone *_tz)
+{
+	register struct timezone *tz asm("x1") = _tz;
+	register struct __kernel_old_timeval *tv asm("x0") = _tv;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_gettimeofday;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (tv), "r" (tz), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("x1") = _ts;
+	register clockid_t clkid asm("x0") = _clkid;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_clock_gettime;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+	register struct __kernel_timespec *ts asm("x1") = _ts;
+	register clockid_t clkid asm("x0") = _clkid;
+	register long ret asm ("x0");
+	register long nr asm("x8") = __NR_clock_getres;
+
+	asm volatile(
+	"       svc #0\n"
+	: "=r" (ret)
+	: "r" (clkid), "r" (ts), "r" (nr)
+	: "memory");
+
+	return ret;
+}
+
+static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
+{
+	u64 res;
+
+	/*
+	 * clock_mode == 0 implies that vDSO are enabled otherwise
+	 * fallback on syscall.
+	 */
+	if (clock_mode)
+		return __VDSO_USE_SYSCALL;
+
+	/*
+	 * This isb() is required to prevent that the counter value
+	 * is speculated.
+	 */
+	isb();
+	asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory");
+	/*
+	 * This isb() is required to prevent that the seq lock is
+	 * speculated.#
+	 */
+	isb();
+
+	return res;
+}
+
+static __always_inline
+const struct vdso_data *__arch_get_vdso_data(void)
+{
+	return _vdso_data;
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_GETTIMEOFDAY_H */

arch/arm64/include/asm/vdso/processor.h

@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2020 ARM Ltd.
+ */
+#ifndef __ASM_VDSO_PROCESSOR_H
+#define __ASM_VDSO_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+
+static inline void cpu_relax(void)
+{
+	asm volatile("yield" ::: "memory");
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_PROCESSOR_H */

arch/arm64/include/asm/vdso/vsyscall.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_VDSO_VSYSCALL_H
+#define __ASM_VDSO_VSYSCALL_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/timekeeper_internal.h>
+#include <vdso/datapage.h>
+
+#define VDSO_PRECISION_MASK	~(0xFF00ULL<<48)
+
+extern struct vdso_data *vdso_data;
+
+/*
+ * Update the vDSO data page to keep in sync with kernel timekeeping.
+ */
+static __always_inline
+struct vdso_data *__arm64_get_k_vdso_data(void)
+{
+	return vdso_data;
+}
+#define __arch_get_k_vdso_data __arm64_get_k_vdso_data
+
+static __always_inline
+int __arm64_get_clock_mode(struct timekeeper *tk)
+{
+	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
+
+	return use_syscall;
+}
+#define __arch_get_clock_mode __arm64_get_clock_mode
+
+static __always_inline
+int __arm64_use_vsyscall(struct vdso_data *vdata)
+{
+	return !vdata[CS_HRES_COARSE].clock_mode;
+}
+#define __arch_use_vsyscall __arm64_use_vsyscall
+
+static __always_inline
+void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
+{
+	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
+	vdata[CS_RAW].mask		= VDSO_PRECISION_MASK;
+}
+#define __arch_update_vsyscall __arm64_update_vsyscall
+
+/* The asm-generic header needs to be included after the definitions above */
+#include <asm-generic/vdso/vsyscall.h>
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __ASM_VDSO_VSYSCALL_H */

arch/arm64/include/asm/vdso_datapage.h

@@ -1,48 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_VDSO_DATAPAGE_H
-#define __ASM_VDSO_DATAPAGE_H
-
-#ifdef __KERNEL__
-
-#ifndef __ASSEMBLY__
-
-struct vdso_data {
-	__u64 cs_cycle_last;	/* Timebase at clocksource init */
-	__u64 raw_time_sec;	/* Raw time */
-	__u64 raw_time_nsec;
-	__u64 xtime_clock_sec;	/* Kernel time */
-	__u64 xtime_clock_nsec;
-	__u64 xtime_coarse_sec;	/* Coarse time */
-	__u64 xtime_coarse_nsec;
-	__u64 wtm_clock_sec;	/* Wall to monotonic time */
-	__u64 wtm_clock_nsec;
-	__u32 tb_seq_count;	/* Timebase sequence counter */
-	/* cs_* members must be adjacent and in this order (ldp accesses) */
-	__u32 cs_mono_mult;	/* NTP-adjusted clocksource multiplier */
-	__u32 cs_shift;		/* Clocksource shift (mono = raw) */
-	__u32 cs_raw_mult;	/* Raw clocksource multiplier */
-	__u32 tz_minuteswest;	/* Whacky timezone stuff */
-	__u32 tz_dsttime;
-	__u32 use_syscall;
-	__u32 hrtimer_res;
-};
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASM_VDSO_DATAPAGE_H */

arch/arm64/include/uapi/asm/setup.h

@@ -22,6 +22,6 @@
 
 #include <linux/types.h>
 
-#define COMMAND_LINE_SIZE	2048
+#define COMMAND_LINE_SIZE	4096
 
 #endif

arch/arm64/kernel/Makefile

@@ -27,8 +27,12 @@ OBJCOPYFLAGS := --prefix-symbols=__efistub_
 $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
-arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
+arm64-obj-$(CONFIG_COMPAT)		+= sys32.o signal32.o		 	\
 					   sys_compat.o
+ifneq ($(CONFIG_COMPAT_VDSO), y)
+arm64-obj-$(CONFIG_COMPAT)		+= sigreturn32.o
+endif
+arm64-obj-$(CONFIG_KUSER_HELPERS)	+= kuser32.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
@@ -61,6 +65,7 @@ arm64-obj-$(CONFIG_SHADOW_CALL_STACK)	+= scs.o
 
 obj-y					+= $(arm64-obj-y) vdso/ probes/
 obj-m					+= $(arm64-obj-m)
+obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/
 head-y					:= head.o
 extra-y					+= $(head-y) vmlinux.lds
 

arch/arm64/kernel/arm64ksyms.c

@@ -29,6 +29,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/kprobes.h>
 
+#include <asm/cacheflush.h>
 #include <asm/checksum.h>
 
 EXPORT_SYMBOL(copy_page);
@@ -86,3 +87,15 @@ extern long long __ashrti3(long long a, int b);
 EXPORT_SYMBOL(__ashrti3);
 extern long long __lshrti3(long long a, int b);
 EXPORT_SYMBOL(__lshrti3);
+
+	/* caching functions */
+EXPORT_SYMBOL_GPL(__dma_inv_area);
+EXPORT_SYMBOL_GPL(__dma_clean_area);
+EXPORT_SYMBOL_GPL(__dma_flush_area);
+EXPORT_SYMBOL_GPL(__flush_dcache_area);
+
+EXPORT_SYMBOL_GPL(__bss_stop);
+EXPORT_SYMBOL_GPL(__per_cpu_start);
+EXPORT_SYMBOL_GPL(__per_cpu_end);
+EXPORT_SYMBOL_GPL(_sdata);
+EXPORT_SYMBOL_GPL(cpu_do_idle);

arch/arm64/kernel/armv8_deprecated.c

@@ -604,7 +604,7 @@ static struct undef_hook setend_hooks[] = {
 	},
 	{
 		/* Thumb mode */
-		.instr_mask	= 0x0000fff7,
+		.instr_mask	= 0xfffffff7,
 		.instr_val	= 0x0000b650,
 		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
 		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),

arch/arm64/kernel/asm-offsets.c

@@ -25,13 +25,14 @@
 #include <linux/kvm_host.h>
 #include <linux/preempt.h>
 #include <linux/suspend.h>
+#include <vdso/datapage.h>
 #include <asm/cpufeature.h>
 #include <asm/fixmap.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
+#include <asm/signal32.h>
 #include <asm/smp_plat.h>
 #include <asm/suspend.h>
-#include <asm/vdso_datapage.h>
 #include <linux/kbuild.h>
 #include <linux/arm-smccc.h>
 
@@ -84,6 +85,11 @@ int main(void)
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
   DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
   BLANK();
+#ifdef CONFIG_COMPAT
+  DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
+  DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET,	offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));
+  BLANK();
+#endif
   DEFINE(MM_CONTEXT_ID,		offsetof(struct mm_struct, context.id.counter));
   BLANK();
   DEFINE(VMA_VM_MM,		offsetof(struct vm_area_struct, vm_mm));
@@ -108,22 +114,28 @@ int main(void)
   DEFINE(CLOCK_COARSE_RES,	LOW_RES_NSEC);
   DEFINE(NSEC_PER_SEC,		NSEC_PER_SEC);
   BLANK();
-  DEFINE(VDSO_CS_CYCLE_LAST,	offsetof(struct vdso_data, cs_cycle_last));
+  DEFINE(VDSO_SEQ,		offsetof(struct vdso_data, seq));
-  DEFINE(VDSO_RAW_TIME_SEC,	offsetof(struct vdso_data, raw_time_sec));
+  DEFINE(VDSO_CLK_MODE,		offsetof(struct vdso_data, clock_mode));
-  DEFINE(VDSO_RAW_TIME_NSEC,	offsetof(struct vdso_data, raw_time_nsec));
+  DEFINE(VDSO_CYCLE_LAST,	offsetof(struct vdso_data, cycle_last));
-  DEFINE(VDSO_XTIME_CLK_SEC,	offsetof(struct vdso_data, xtime_clock_sec));
+  DEFINE(VDSO_MASK,		offsetof(struct vdso_data, mask));
-  DEFINE(VDSO_XTIME_CLK_NSEC,	offsetof(struct vdso_data, xtime_clock_nsec));
+  DEFINE(VDSO_MULT,		offsetof(struct vdso_data, mult));
-  DEFINE(VDSO_XTIME_CRS_SEC,	offsetof(struct vdso_data, xtime_coarse_sec));
+  DEFINE(VDSO_SHIFT,		offsetof(struct vdso_data, shift));
-  DEFINE(VDSO_XTIME_CRS_NSEC,	offsetof(struct vdso_data, xtime_coarse_nsec));
+  DEFINE(VDSO_REALTIME_SEC,	offsetof(struct vdso_data, basetime[CLOCK_REALTIME].sec));
-  DEFINE(VDSO_WTM_CLK_SEC,	offsetof(struct vdso_data, wtm_clock_sec));
+  DEFINE(VDSO_REALTIME_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_REALTIME].nsec));
-  DEFINE(VDSO_WTM_CLK_NSEC,	offsetof(struct vdso_data, wtm_clock_nsec));
+  DEFINE(VDSO_MONO_SEC,		offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC].sec));
-  DEFINE(VDSO_TB_SEQ_COUNT,	offsetof(struct vdso_data, tb_seq_count));
+  DEFINE(VDSO_MONO_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC].nsec));
-  DEFINE(VDSO_CS_MONO_MULT,	offsetof(struct vdso_data, cs_mono_mult));
+  DEFINE(VDSO_MONO_RAW_SEC,	offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC_RAW].sec));
-  DEFINE(VDSO_CS_RAW_MULT,	offsetof(struct vdso_data, cs_raw_mult));
+  DEFINE(VDSO_MONO_RAW_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC_RAW].nsec));
-  DEFINE(VDSO_CS_SHIFT,		offsetof(struct vdso_data, cs_shift));
+  DEFINE(VDSO_BOOTTIME_SEC,	offsetof(struct vdso_data, basetime[CLOCK_BOOTTIME].sec));
+  DEFINE(VDSO_BOOTTIME_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_BOOTTIME].nsec));
+  DEFINE(VDSO_TAI_SEC,		offsetof(struct vdso_data, basetime[CLOCK_TAI].sec));
+  DEFINE(VDSO_TAI_NSEC,		offsetof(struct vdso_data, basetime[CLOCK_TAI].nsec));
+  DEFINE(VDSO_RT_COARSE_SEC,	offsetof(struct vdso_data, basetime[CLOCK_REALTIME_COARSE].sec));
+  DEFINE(VDSO_RT_COARSE_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_REALTIME_COARSE].nsec));
+  DEFINE(VDSO_MONO_COARSE_SEC,	offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC_COARSE].sec));
+  DEFINE(VDSO_MONO_COARSE_NSEC,	offsetof(struct vdso_data, basetime[CLOCK_MONOTONIC_COARSE].nsec));
   DEFINE(VDSO_TZ_MINWEST,	offsetof(struct vdso_data, tz_minuteswest));
   DEFINE(VDSO_TZ_DSTTIME,	offsetof(struct vdso_data, tz_dsttime));
-  DEFINE(VDSO_USE_SYSCALL,	offsetof(struct vdso_data, use_syscall));
   BLANK();
   DEFINE(TVAL_TV_SEC,		offsetof(struct timeval, tv_sec));
   DEFINE(TVAL_TV_USEC,		offsetof(struct timeval, tv_usec));

arch/arm64/kernel/cpu_errata.c

@@ -643,6 +643,18 @@ needs_tx2_tvm_workaround(const struct arm64_cpu_capabilities *entry,
 	return false;
 }
 
+static bool __maybe_unused
+has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	u32 midr = read_cpuid_id();
+	bool has_dic = read_cpuid_cachetype() & BIT(CTR_DIC_SHIFT);
+	const struct midr_range range = MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1);
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return is_midr_in_range(midr, &range) && has_dic;
+}
+
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
 static const struct midr_range arm64_harden_el2_vectors[] = {
@@ -834,6 +846,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(tx2_family_cpus),
 		.matches = needs_tx2_tvm_workaround,
 	},
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_1542419
+	{
+		/* we depend on the firmware portion for correctness */
+		.desc = "ARM erratum 1542419 (kernel portion)",
+		.capability = ARM64_WORKAROUND_1542419,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = has_neoverse_n1_erratum_1542419,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
 #endif
 	{
 	}

arch/arm64/kernel/cpuidle.c

@@ -42,6 +42,7 @@ int arm_cpuidle_suspend(int index)
 
 	return cpu_ops[cpu]->cpu_suspend(index);
 }
+EXPORT_SYMBOL_GPL(arm_cpuidle_suspend);
 
 #ifdef CONFIG_ACPI
 

arch/arm64/kernel/head.S

@@ -674,7 +674,7 @@ ENTRY(__boot_cpu_mode)
  * with MMU turned off.
  */
 ENTRY(__early_cpu_boot_status)
-	.long 	0
+	.quad 	0
 
 	.popsection
 

arch/arm64/kernel/kuser32.S

@@ -1,29 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Low-level user helpers placed in the vectors page for AArch32.
+ * AArch32 user helpers.
  * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
  *
  * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2012-2018 ARM Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
+ * The kuser helpers below are mapped at a fixed address by
- * it under the terms of the GNU General Public License version 2 as
+ * aarch32_setup_additional_pages() and are provided for compatibility
- * published by the Free Software Foundation.
+ * reasons with 32 bit (aarch32) applications that need them.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- *
- * AArch32 user helpers.
- *
- * Each segment is 32-byte aligned and will be moved to the top of the high
- * vector page.  New segments (if ever needed) must be added in front of
- * existing ones.  This mechanism should be used only for things that are
- * really small and justified, and not be abused freely.
  *
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
@@ -77,42 +62,3 @@ __kuser_helper_version:			// 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
-
-/*
- * AArch32 sigreturn code
- *
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- *
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-	.globl __aarch32_sigret_code_start
-__aarch32_sigret_code_start:
-
-	/*
-	 * ARM Code
-	 */
-	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
-
-	/*
-	 * ARM code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
-
-        .globl __aarch32_sigret_code_end
-__aarch32_sigret_code_end:

arch/arm64/kernel/process.c

@@ -75,6 +75,7 @@ void (*pm_power_off)(void);
 EXPORT_SYMBOL_GPL(pm_power_off);
 
 void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
+EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 /*
  * This is our default idle handler.

arch/arm64/kernel/setup.c

@@ -69,6 +69,14 @@ static struct resource *standard_resources;
 
 phys_addr_t __fdt_pointer __initdata;
 
+/* Vendor stub */
+unsigned int boot_reason;
+EXPORT_SYMBOL_GPL(boot_reason);
+
+/* Vendor stub */
+unsigned int cold_boot;
+EXPORT_SYMBOL_GPL(cold_boot);
+
 /*
  * Standard memory resources
  */

arch/arm64/kernel/signal32.c

@@ -29,42 +29,7 @@
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
-
+#include <asm/vdso.h>
-struct compat_sigcontext {
-	/* We always set these two fields to 0 */
-	compat_ulong_t			trap_no;
-	compat_ulong_t			error_code;
-
-	compat_ulong_t			oldmask;
-	compat_ulong_t			arm_r0;
-	compat_ulong_t			arm_r1;
-	compat_ulong_t			arm_r2;
-	compat_ulong_t			arm_r3;
-	compat_ulong_t			arm_r4;
-	compat_ulong_t			arm_r5;
-	compat_ulong_t			arm_r6;
-	compat_ulong_t			arm_r7;
-	compat_ulong_t			arm_r8;
-	compat_ulong_t			arm_r9;
-	compat_ulong_t			arm_r10;
-	compat_ulong_t			arm_fp;
-	compat_ulong_t			arm_ip;
-	compat_ulong_t			arm_sp;
-	compat_ulong_t			arm_lr;
-	compat_ulong_t			arm_pc;
-	compat_ulong_t			arm_cpsr;
-	compat_ulong_t			fault_address;
-};
-
-struct compat_ucontext {
-	compat_ulong_t			uc_flags;
-	compat_uptr_t			uc_link;
-	compat_stack_t			uc_stack;
-	struct compat_sigcontext	uc_mcontext;
-	compat_sigset_t			uc_sigmask;
-	int		__unused[32 - (sizeof (compat_sigset_t) / sizeof (int))];
-	compat_ulong_t	uc_regspace[128] __attribute__((__aligned__(8)));
-};
 
 struct compat_vfp_sigframe {
 	compat_ulong_t	magic;
@@ -92,16 +57,6 @@ struct compat_aux_sigframe {
 	unsigned long			end_magic;
 } __attribute__((__aligned__(8)));
 
-struct compat_sigframe {
-	struct compat_ucontext	uc;
-	compat_ulong_t		retcode[2];
-};
-
-struct compat_rt_sigframe {
-	struct compat_siginfo info;
-	struct compat_sigframe sig;
-};
-
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
 
 static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
@@ -398,14 +353,38 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
 	} else {
 		/* Set up sigreturn pointer */
+#ifdef CONFIG_COMPAT_VDSO
+		void *vdso_base = current->mm->context.vdso;
+		void *vdso_trampoline;
+
+		if (ka->sa.sa_flags & SA_SIGINFO) {
+			if (thumb) {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_rt_sigreturn_thumb);
+			} else {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_rt_sigreturn_arm);
+			}
+		} else {
+			if (thumb) {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_sigreturn_thumb);
+			} else {
+				vdso_trampoline = VDSO_SYMBOL(vdso_base,
+							compat_sigreturn_arm);
+			}
+		}
+
+		retcode = ptr_to_compat(vdso_trampoline) + thumb;
+#else
 		unsigned int idx = thumb << 1;
 
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = AARCH32_VECTORS_BASE +
+		retcode = (unsigned long)current->mm->context.vdso +
-			  AARCH32_KERN_SIGRET_CODE_OFFSET +
 			  (idx << 2) + thumb;
+#endif
 	}
 
 	regs->regs[0]	= usig;

arch/arm64/kernel/sigreturn32.S

@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch32 sigreturn code.
+ * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
+ *
+ * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
+ * Copyright (C) 2012-2018 ARM Ltd.
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+
+#include <asm/unistd.h>
+
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3		// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef		// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:

arch/arm64/kernel/smp.c

@@ -597,6 +597,9 @@ static void __init acpi_parse_and_init_cpus(void)
 #else
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
 #endif
+/* Dummy vendor field */
+DEFINE_PER_CPU(bool, pending_ipi);
+EXPORT_SYMBOL_GPL(pending_ipi);
 
 static void (*__smp_update_ipi_history_cb)(int cpu);
 /*

arch/arm64/kernel/sys_compat.c

@@ -19,6 +19,7 @@
  */
 
 #include <linux/compat.h>
+#include <linux/cpufeature.h>
 #include <linux/personality.h>
 #include <linux/sched.h>
 #include <linux/sched/signal.h>
@@ -28,6 +29,7 @@
 
 #include <asm/cacheflush.h>
 #include <asm/system_misc.h>
+#include <asm/tlbflush.h>
 #include <asm/unistd.h>
 
 static long
@@ -41,6 +43,15 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 		if (fatal_signal_pending(current))
 			return 0;
 
+		if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+			/*
+			 * The workaround requires an inner-shareable tlbi.
+			 * We pick the reserved-ASID to minimise the impact.
+			 */
+			__tlbi(aside1is, __TLBI_VADDR(0, 0));
+			dsb(ish);
+		}
+
 		ret = __flush_cache_user_range(start, start + chunk);
 		if (ret)
 			return ret;

arch/arm64/kernel/traps.c

@@ -482,6 +482,15 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
 	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
 	unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
 
+	if (cpus_have_const_cap(ARM64_WORKAROUND_1542419)) {
+		/* Hide DIC so that we can trap the unnecessary maintenance...*/
+		val &= ~BIT(CTR_DIC_SHIFT);
+
+		/* ... and fake IminLine to reduce the number of traps. */
+		val &= ~CTR_IMINLINE_MASK;
+		val |= (PAGE_SHIFT - 2) & CTR_IMINLINE_MASK;
+	}
+
 	pt_regs_write_reg(regs, rt, val);
 
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);

arch/arm64/kernel/vdso.c

@@ -1,5 +1,5 @@
 /*
- * VDSO implementation for AArch64 and vector page setup for AArch32.
+ * VDSO implementations.
  *
  * Copyright (C) 2012 ARM Limited
  *
@@ -31,90 +31,74 @@
 #include <linux/slab.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
+#include <vdso/datapage.h>
+#include <vdso/helpers.h>
+#include <vdso/vsyscall.h>
 
 #include <asm/cacheflush.h>
 #include <asm/signal32.h>
 #include <asm/vdso.h>
-#include <asm/vdso_datapage.h>
 
 extern char vdso_start[], vdso_end[];
-static unsigned long vdso_pages __ro_after_init;
+#ifdef CONFIG_COMPAT_VDSO
+extern char vdso32_start[], vdso32_end[];
+#endif /* CONFIG_COMPAT_VDSO */
+
+/* vdso_lookup arch_index */
+enum arch_vdso_type {
+	ARM64_VDSO = 0,
+#ifdef CONFIG_COMPAT_VDSO
+	ARM64_VDSO32 = 1,
+#endif /* CONFIG_COMPAT_VDSO */
+};
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_TYPES		(ARM64_VDSO32 + 1)
+#else
+#define VDSO_TYPES		(ARM64_VDSO + 1)
+#endif /* CONFIG_COMPAT_VDSO */
+
+struct __vdso_abi {
+	const char *name;
+	const char *vdso_code_start;
+	const char *vdso_code_end;
+	unsigned long vdso_pages;
+	/* Data Mapping */
+	struct vm_special_mapping *dm;
+	/* Code Mapping */
+	struct vm_special_mapping *cm;
+};
+
+static struct __vdso_abi vdso_lookup[VDSO_TYPES] __ro_after_init = {
+	{
+		.name = "vdso",
+		.vdso_code_start = vdso_start,
+		.vdso_code_end = vdso_end,
+	},
+#ifdef CONFIG_COMPAT_VDSO
+	{
+		.name = "vdso32",
+		.vdso_code_start = vdso32_start,
+		.vdso_code_end = vdso32_end,
+	},
+#endif /* CONFIG_COMPAT_VDSO */
+};
 
 /*
  * The vDSO data page.
  */
 static union {
-	struct vdso_data	data;
+	struct vdso_data	data[CS_BASES];
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+struct vdso_data *vdso_data = vdso_data_store.data;
 
-#ifdef CONFIG_COMPAT
+static int __vdso_remap(enum arch_vdso_type arch_index,
-/*
+			const struct vm_special_mapping *sm,
- * Create and map the vectors page for AArch32 tasks.
+			struct vm_area_struct *new_vma)
- */
-static struct page *vectors_page[1] __ro_after_init;
-
-static int __init alloc_vectors_page(void)
-{
-	extern char __kuser_helper_start[], __kuser_helper_end[];
-	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
-
-	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
-	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
-	unsigned long vpage;
-
-	vpage = get_zeroed_page(GFP_ATOMIC);
-
-	if (!vpage)
-		return -ENOMEM;
-
-	/* kuser helpers */
-	memcpy((void *)vpage + 0x1000 - kuser_sz, __kuser_helper_start,
-		kuser_sz);
-
-	/* sigreturn code */
-	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-               __aarch32_sigret_code_start, sigret_sz);
-
-	flush_icache_range(vpage, vpage + PAGE_SIZE);
-	vectors_page[0] = virt_to_page(vpage);
-
-	return 0;
-}
-arch_initcall(alloc_vectors_page);
-
-int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = AARCH32_VECTORS_BASE;
-	static const struct vm_special_mapping spec = {
-		.name	= "[vectors]",
-		.pages	= vectors_page,
-
-	};
-	void *ret;
-
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	current->mm->context.vdso = (void *)addr;
-
-	/* Map vectors page at the high address. */
-	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
-				       &spec);
-
-	up_write(&mm->mmap_sem);
-
-	return PTR_ERR_OR_ZERO(ret);
-}
-#endif /* CONFIG_COMPAT */
-
-static int vdso_mremap(const struct vm_special_mapping *sm,
-		struct vm_area_struct *new_vma)
 {
 	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
-	unsigned long vdso_size = vdso_end - vdso_start;
+	unsigned long vdso_size = vdso_lookup[arch_index].vdso_code_end -
+				  vdso_lookup[arch_index].vdso_code_start;
 
 	if (vdso_size != new_size)
 		return -EINVAL;
@@ -124,7 +108,303 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+static int __vdso_init(enum arch_vdso_type arch_index)
+{
+	int i;
+	struct page **vdso_pagelist;
+	unsigned long pfn;
+
+	if (memcmp(vdso_lookup[arch_index].vdso_code_start, "\177ELF", 4)) {
+		pr_err("vDSO is not a valid ELF object!\n");
+		return -EINVAL;
+	}
+
+	vdso_lookup[arch_index].vdso_pages = (
+			vdso_lookup[arch_index].vdso_code_end -
+			vdso_lookup[arch_index].vdso_code_start) >>
+			PAGE_SHIFT;
+
+	/* Allocate the vDSO pagelist, plus a page for the data. */
+	vdso_pagelist = kcalloc(vdso_lookup[arch_index].vdso_pages + 1,
+				sizeof(struct page *),
+				GFP_KERNEL);
+	if (vdso_pagelist == NULL)
+		return -ENOMEM;
+
+	/* Grab the vDSO data page. */
+	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
+
+
+	/* Grab the vDSO code pages. */
+	pfn = sym_to_pfn(vdso_lookup[arch_index].vdso_code_start);
+
+	for (i = 0; i < vdso_lookup[arch_index].vdso_pages; i++)
+		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
+
+	vdso_lookup[arch_index].dm->pages = &vdso_pagelist[0];
+	vdso_lookup[arch_index].cm->pages = &vdso_pagelist[1];
+
+	return 0;
+}
+
+static int __setup_additional_pages(enum arch_vdso_type arch_index,
+				    struct mm_struct *mm,
+				    struct linux_binprm *bprm,
+				    int uses_interp)
+{
+	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	void *ret;
+
+	vdso_text_len = vdso_lookup[arch_index].vdso_pages << PAGE_SHIFT;
+	/* Be sure to map the data page */
+	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
+
+	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		ret = ERR_PTR(vdso_base);
+		goto up_fail;
+	}
+
+	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
+				       VM_READ|VM_MAYREAD,
+				       vdso_lookup[arch_index].dm);
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	vdso_base += PAGE_SIZE;
+	mm->context.vdso = (void *)vdso_base;
+	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
+				       VM_READ|VM_EXEC|
+				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+				       vdso_lookup[arch_index].cm);
+	if (IS_ERR(ret))
+		goto up_fail;
+
+	return 0;
+
+up_fail:
+	mm->context.vdso = NULL;
+	return PTR_ERR(ret);
+}
+
+#ifdef CONFIG_COMPAT
+/*
+ * Create and map the vectors page for AArch32 tasks.
+ */
+#ifdef CONFIG_COMPAT_VDSO
+static int aarch32_vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	return __vdso_remap(ARM64_VDSO32, sm, new_vma);
+}
+#endif /* CONFIG_COMPAT_VDSO */
+
+/*
+ * aarch32_vdso_pages:
+ * 0 - kuser helpers
+ * 1 - sigreturn code
+ * or (CONFIG_COMPAT_VDSO):
+ * 0 - kuser helpers
+ * 1 - vdso data
+ * 2 - vdso code
+ */
+#define C_VECTORS	0
+#ifdef CONFIG_COMPAT_VDSO
+#define C_VVAR		1
+#define C_VDSO		2
+#define C_PAGES		(C_VDSO + 1)
+#else
+#define C_SIGPAGE	1
+#define C_PAGES		(C_SIGPAGE + 1)
+#endif /* CONFIG_COMPAT_VDSO */
+static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
+static struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+	{
+		.name	= "[vectors]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_VECTORS],
+	},
+#ifdef CONFIG_COMPAT_VDSO
+	{
+		.name = "[vvar]",
+	},
+	{
+		.name = "[vdso]",
+		.mremap = aarch32_vdso_mremap,
+	},
+#else
+	{
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+	},
+#endif /* CONFIG_COMPAT_VDSO */
+};
+
+static int aarch32_alloc_kuser_vdso_page(void)
+{
+	extern char __kuser_helper_start[], __kuser_helper_end[];
+	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
+	unsigned long vdso_page;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	vdso_page = get_zeroed_page(GFP_ATOMIC);
+	if (!vdso_page)
+		return -ENOMEM;
+
+	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
+	       kuser_sz);
+	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
+	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	return 0;
+}
+
+#ifdef CONFIG_COMPAT_VDSO
+static int __aarch32_alloc_vdso_pages(void)
+{
+	int ret;
+
+	vdso_lookup[ARM64_VDSO32].dm = &aarch32_vdso_spec[C_VVAR];
+	vdso_lookup[ARM64_VDSO32].cm = &aarch32_vdso_spec[C_VDSO];
+
+	ret = __vdso_init(ARM64_VDSO32);
+	if (ret)
+		return ret;
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret) {
+		unsigned long c_vvar =
+			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VVAR]);
+		unsigned long c_vdso =
+			(unsigned long)page_to_virt(aarch32_vdso_pages[C_VDSO]);
+
+		free_page(c_vvar);
+		free_page(c_vdso);
+	}
+
+	return ret;
+}
+#else
+static int __aarch32_alloc_vdso_pages(void)
+{
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
+	unsigned long sigpage;
+	int ret;
+
+	sigpage = get_zeroed_page(GFP_ATOMIC);
+	if (!sigpage)
+		return -ENOMEM;
+
+	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
+	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret)
+		free_page(sigpage);
+
+	return ret;
+}
+#endif /* CONFIG_COMPAT_VDSO */
+
+static int __init aarch32_alloc_vdso_pages(void)
+{
+	return __aarch32_alloc_vdso_pages();
+}
+arch_initcall(aarch32_alloc_vdso_pages);
+
+static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
+{
+	void *ret;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	/*
+	 * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
+	 * not safe to CoW the page containing the CPU exception vectors.
+	 */
+	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
+				       VM_READ | VM_EXEC |
+				       VM_MAYREAD | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_VECTORS]);
+
+	return PTR_ERR_OR_ZERO(ret);
+}
+
+#ifndef CONFIG_COMPAT_VDSO
+static int aarch32_sigreturn_setup(struct mm_struct *mm)
+{
+	unsigned long addr;
+	void *ret;
+
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = ERR_PTR(addr);
+		goto out;
+	}
+
+	/*
+	 * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
+	 * set breakpoints.
+	 */
+	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
+				       VM_READ | VM_EXEC | VM_MAYREAD |
+				       VM_MAYWRITE | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_SIGPAGE]);
+	if (IS_ERR(ret))
+		goto out;
+
+	mm->context.vdso = (void *)addr;
+
+out:
+	return PTR_ERR_OR_ZERO(ret);
+}
+#endif /* !CONFIG_COMPAT_VDSO */
+
+int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	ret = aarch32_kuser_helpers_setup(mm);
+	if (ret)
+		goto out;
+
+#ifdef CONFIG_COMPAT_VDSO
+	ret = __setup_additional_pages(ARM64_VDSO32,
+				       mm,
+				       bprm,
+				       uses_interp);
+#else
+	ret = aarch32_sigreturn_setup(mm);
+#endif /* CONFIG_COMPAT_VDSO */
+
+out:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
+#endif /* CONFIG_COMPAT */
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+		struct vm_area_struct *new_vma)
+{
+	return __vdso_remap(ARM64_VDSO, sm, new_vma);
+}
+
+/*
+ * aarch64_vdso_pages:
+ * 0 - vvar
+ * 1 - vdso
+ */
+#define A_VVAR		0
+#define A_VDSO		1
+#define A_PAGES		(A_VDSO + 1)
+static struct vm_special_mapping vdso_spec[A_PAGES] __ro_after_init = {
 	{
 		.name	= "[vvar]",
 	},
@@ -136,37 +416,10 @@ static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
 
 static int __init vdso_init(void)
 {
-	int i;
+	vdso_lookup[ARM64_VDSO].dm = &vdso_spec[A_VVAR];
-	struct page **vdso_pagelist;
+	vdso_lookup[ARM64_VDSO].cm = &vdso_spec[A_VDSO];
-	unsigned long pfn;
 
-	if (memcmp(vdso_start, "\177ELF", 4)) {
+	return __vdso_init(ARM64_VDSO);
-		pr_err("vDSO is not a valid ELF object!\n");
-		return -EINVAL;
-	}
-
-	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-
-	/* Allocate the vDSO pagelist, plus a page for the data. */
-	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
-				GFP_KERNEL);
-	if (vdso_pagelist == NULL)
-		return -ENOMEM;
-
-	/* Grab the vDSO data page. */
-	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));
-
-
-	/* Grab the vDSO code pages. */
-	pfn = sym_to_pfn(vdso_start);
-
-	for (i = 0; i < vdso_pages; i++)
-		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);
-
-	vdso_spec[0].pages = &vdso_pagelist[0];
-	vdso_spec[1].pages = &vdso_pagelist[1];
-
-	return 0;
 }
 arch_initcall(vdso_init);
 
@@ -174,84 +427,17 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 				int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
-	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
+	int ret;
-	void *ret;
-
-	vdso_text_len = vdso_pages << PAGE_SHIFT;
-	/* Be sure to map the data page */
-	vdso_mapping_len = vdso_text_len + PAGE_SIZE;
 
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
-	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
-	if (IS_ERR_VALUE(vdso_base)) {
-		ret = ERR_PTR(vdso_base);
-		goto up_fail;
-	}
-	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
-				       VM_READ|VM_MAYREAD,
-				       &vdso_spec[0]);
-	if (IS_ERR(ret))
-		goto up_fail;
-
-	vdso_base += PAGE_SIZE;
-	mm->context.vdso = (void *)vdso_base;
-	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
-				       VM_READ|VM_EXEC|
-				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
-				       &vdso_spec[1]);
-	if (IS_ERR(ret))
-		goto up_fail;
 
+	ret = __setup_additional_pages(ARM64_VDSO,
+				       mm,
+				       bprm,
+				       uses_interp);
 
 	up_write(&mm->mmap_sem);
-	return 0;
 
-up_fail:
+	return ret;
-	mm->context.vdso = NULL;
-	up_write(&mm->mmap_sem);
-	return PTR_ERR(ret);
-}
-
-/*
- * Update the vDSO data page to keep in sync with kernel timekeeping.
- */
-void update_vsyscall(struct timekeeper *tk)
-{
-	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
-
-	++vdso_data->tb_seq_count;
-	smp_wmb();
-
-	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
-	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
-							tk->tkr_mono.shift;
-	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
-	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
-
-	/* Read without the seqlock held by clock_getres() */
-	WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);
-
-	if (!use_syscall) {
-		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
-		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
-		vdso_data->raw_time_sec         = tk->raw_sec;
-		vdso_data->raw_time_nsec        = tk->tkr_raw.xtime_nsec;
-		vdso_data->xtime_clock_sec	= tk->xtime_sec;
-		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
-		vdso_data->cs_mono_mult		= tk->tkr_mono.mult;
-		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
-		/* tkr_mono.shift == tkr_raw.shift */
-		vdso_data->cs_shift		= tk->tkr_mono.shift;
-	}
-
-	smp_wmb();
-	++vdso_data->tb_seq_count;
-}
-
-void update_vsyscall_tz(void)
-{
-	vdso_data->tz_minuteswest	= sys_tz.tz_minuteswest;
-	vdso_data->tz_dsttime		= sys_tz.tz_dsttime;
 }

arch/arm64/kernel/vdso/Makefile

@@ -6,26 +6,51 @@
 # Heavily based on the vDSO Makefiles for other archs.
 #
 
-obj-vdso := gettimeofday.o note.o sigreturn.o
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_AARCH64_JUMP_SLOT|R_AARCH64_GLOB_DAT|R_AARCH64_ABS64
+include $(srctree)/lib/vdso/Makefile
+
+obj-vdso := vgettimeofday.o note.o sigreturn.o
 
 # Build rules
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-ccflags-y := -shared -fno-common -fno-builtin
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
+		--build-id -n -T
-		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 ccflags-y += $(DISABLE_LTO)
 
 CFLAGS_REMOVE_vgettimeofday.o += $(CC_FLAGS_SCS)
 
+ccflags-y := -fno-common -fno-builtin -fno-stack-protector
+ccflags-y += -DDISABLE_BRANCH_PROFILING
+
+VDSO_LDFLAGS := -Bsymbolic
+
+CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+KBUILD_CFLAGS			+= $(DISABLE_LTO)
+KASAN_SANITIZE			:= n
+UBSAN_SANITIZE			:= n
+OBJECT_FILES_NON_STANDARD	:= y
+KCOV_INSTRUMENT			:= n
+
+CFLAGS_vgettimeofday.o = -O2 -mcmodel=tiny
+
+ifneq ($(c-gettimeofday-y),)
+  CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y)
+endif
+
+# Clang versions less than 8 do not support -mcmodel=tiny
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+  ifeq ($(shell test $(CONFIG_CLANG_VERSION) -lt 80000; echo $$?),0)
+    CFLAGS_REMOVE_vgettimeofday.o += -mcmodel=tiny
+  endif
+endif
+
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
-# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
-# down to collect2, resulting in silent corruption of the vDSO image.
-ccflags-y += -Wl,-shared
-
 obj-y += vdso.o
 extra-y += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
@@ -35,7 +60,7 @@ $(obj)/vdso.o : $(obj)/vdso.so
 
 # Link rule for the .so file, .lds has to be first
 $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
-	$(call if_changed,vdsold)
+	$(call if_changed,vdsold_and_vdso_check)
 
 # Strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -52,16 +77,13 @@ endef
 include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
 
-# Assembly rules for the .S files
-$(obj-vdso): %.o: %.S FORCE
-	$(call if_changed_dep,vdsoas)
-
 # Actual build commands
-quiet_cmd_vdsold = VDSOL   $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
+quiet_cmd_vdsold_and_vdso_check = LD      $@
+      cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check)
+
 # Install commands for the unstripped file
 quiet_cmd_vdso_install = INSTALL $@
       cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@

arch/arm64/kernel/vdso/gettimeofday.S

@@ -1,334 +0,0 @@
-/*
- * Userspace implementations of gettimeofday() and friends.
- *
- * Copyright (C) 2012 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/unistd.h>
-
-#define NSEC_PER_SEC_LO16	0xca00
-#define NSEC_PER_SEC_HI16	0x3b9a
-
-vdso_data	.req	x6
-seqcnt		.req	w7
-w_tmp		.req	w8
-x_tmp		.req	x8
-
-/*
- * Conventions for macro arguments:
- * - An argument is write-only if its name starts with "res".
- * - All other arguments are read-only, unless otherwise specified.
- */
-
-	.macro	seqcnt_acquire
-9999:	ldr	seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT]
-	tbnz	seqcnt, #0, 9999b
-	dmb	ishld
-	.endm
-
-	.macro	seqcnt_check fail
-	dmb	ishld
-	ldr	w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT]
-	cmp	w_tmp, seqcnt
-	b.ne	\fail
-	.endm
-
-	.macro	syscall_check fail
-	ldr	w_tmp, [vdso_data, #VDSO_USE_SYSCALL]
-	cbnz	w_tmp, \fail
-	.endm
-
-	.macro get_nsec_per_sec res
-	mov	\res, #NSEC_PER_SEC_LO16
-	movk	\res, #NSEC_PER_SEC_HI16, lsl #16
-	.endm
-
-	/*
-	 * Returns the clock delta, in nanoseconds left-shifted by the clock
-	 * shift.
-	 */
-	.macro	get_clock_shifted_nsec res, cycle_last, mult
-	/* Read the virtual counter. */
-	isb
-	mrs	x_tmp, cntvct_el0
-	/* Calculate cycle delta and convert to ns. */
-	sub	\res, x_tmp, \cycle_last
-	/* We can only guarantee 56 bits of precision. */
-	movn	x_tmp, #0xff00, lsl #48
-	and	\res, x_tmp, \res
-	mul	\res, \res, \mult
-	/*
-	 * Fake address dependency from the value computed from the counter
-	 * register to subsequent data page accesses so that the sequence
-	 * locking also orders the read of the counter.
-	 */
-	and	x_tmp, \res, xzr
-	add	vdso_data, vdso_data, x_tmp
-	.endm
-
-	/*
-	 * Returns in res_{sec,nsec} the REALTIME timespec, based on the
-	 * "wall time" (xtime) and the clock_mono delta.
-	 */
-	.macro	get_ts_realtime res_sec, res_nsec, \
-			clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec
-	add	\res_nsec, \clock_nsec, \xtime_nsec
-	udiv	x_tmp, \res_nsec, \nsec_to_sec
-	add	\res_sec, \xtime_sec, x_tmp
-	msub	\res_nsec, x_tmp, \nsec_to_sec, \res_nsec
-	.endm
-
-	/*
-	 * Returns in res_{sec,nsec} the timespec based on the clock_raw delta,
-	 * used for CLOCK_MONOTONIC_RAW.
-	 */
-	.macro	get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec
-	udiv	\res_sec, \clock_nsec, \nsec_to_sec
-	msub	\res_nsec, \res_sec, \nsec_to_sec, \clock_nsec
-	.endm
-
-	/* sec and nsec are modified in place. */
-	.macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec
-	/* Add timespec. */
-	add	\sec, \sec, \ts_sec
-	add	\nsec, \nsec, \ts_nsec
-
-	/* Normalise the new timespec. */
-	cmp	\nsec, \nsec_to_sec
-	b.lt	9999f
-	sub	\nsec, \nsec, \nsec_to_sec
-	add	\sec, \sec, #1
-9999:
-	cmp	\nsec, #0
-	b.ge	9998f
-	add	\nsec, \nsec, \nsec_to_sec
-	sub	\sec, \sec, #1
-9998:
-	.endm
-
-	.macro clock_gettime_return, shift=0
-	.if \shift == 1
-	lsr	x11, x11, x12
-	.endif
-	stp	x10, x11, [x1, #TSPEC_TV_SEC]
-	mov	x0, xzr
-	ret
-	.endm
-
-	.macro jump_slot jumptable, index, label
-	.if (. - \jumptable) != 4 * (\index)
-	.error "Jump slot index mismatch"
-	.endif
-	b	\label
-	.endm
-
-	.text
-
-/* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */
-ENTRY(__kernel_gettimeofday)
-	.cfi_startproc
-	adr	vdso_data, _vdso_data
-	/* If tv is NULL, skip to the timezone code. */
-	cbz	x0, 2f
-
-	/* Compute the time of day. */
-1:	seqcnt_acquire
-	syscall_check fail=4f
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	seqcnt_check fail=1b
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
-	/* Convert ns to us. */
-	mov	x13, #1000
-	lsl	x13, x13, x12
-	udiv	x11, x11, x13
-	stp	x10, x11, [x0, #TVAL_TV_SEC]
-2:
-	/* If tz is NULL, return 0. */
-	cbz	x1, 3f
-	ldp	w4, w5, [vdso_data, #VDSO_TZ_MINWEST]
-	stp	w4, w5, [x1, #TZ_MINWEST]
-3:
-	mov	x0, xzr
-	ret
-4:
-	/* Syscall fallback. */
-	mov	x8, #__NR_gettimeofday
-	svc	#0
-	ret
-	.cfi_endproc
-ENDPROC(__kernel_gettimeofday)
-
-#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE
-
-/* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */
-ENTRY(__kernel_clock_gettime)
-	.cfi_startproc
-	cmp	w0, #JUMPSLOT_MAX
-	b.hi	syscall
-	adr	vdso_data, _vdso_data
-	adr	x_tmp, jumptable
-	add	x_tmp, x_tmp, w0, uxtw #2
-	br	x_tmp
-
-	ALIGN
-jumptable:
-	jump_slot jumptable, CLOCK_REALTIME, realtime
-	jump_slot jumptable, CLOCK_MONOTONIC, monotonic
-	b	syscall
-	b	syscall
-	jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw
-	jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse
-	jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse
-
-	.if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1)
-	.error	"Wrong jumptable size"
-	.endif
-
-	ALIGN
-realtime:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-
-	/* All computations are done with left-shifted nsecs. */
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	seqcnt_check fail=realtime
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-monotonic:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_mono_mult, w12 = cs_shift */
-	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
-	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-
-	/* All computations are done with left-shifted nsecs. */
-	lsl	x4, x4, x12
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	seqcnt_check fail=monotonic
-	get_ts_realtime res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
-
-	add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-monotonic_raw:
-	seqcnt_acquire
-	syscall_check fail=syscall
-	ldr	x10, [vdso_data, #VDSO_CS_CYCLE_LAST]
-	/* w11 = cs_raw_mult, w12 = cs_shift */
-	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
-	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-
-	/* All computations are done with left-shifted nsecs. */
-	get_nsec_per_sec res=x9
-	lsl	x9, x9, x12
-
-	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
-	seqcnt_check fail=monotonic_raw
-	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
-		clock_nsec=x15, nsec_to_sec=x9
-
-	add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return, shift=1
-
-	ALIGN
-realtime_coarse:
-	seqcnt_acquire
-	ldp	x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
-	seqcnt_check fail=realtime_coarse
-	clock_gettime_return
-
-	ALIGN
-monotonic_coarse:
-	seqcnt_acquire
-	ldp	x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC]
-	ldp	x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic_coarse
-
-	/* Computations are done in (non-shifted) nsecs. */
-	get_nsec_per_sec res=x9
-	add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9
-	clock_gettime_return
-
-	ALIGN
-syscall: /* Syscall fallback. */
-	mov	x8, #__NR_clock_gettime
-	svc	#0
-	ret
-	.cfi_endproc
-ENDPROC(__kernel_clock_gettime)
-
-/* int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); */
-ENTRY(__kernel_clock_getres)
-	.cfi_startproc
-	cmp	w0, #CLOCK_REALTIME
-	ccmp	w0, #CLOCK_MONOTONIC, #0x4, ne
-	ccmp	w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
-	b.ne	1f
-
-	adr	vdso_data, _vdso_data
-	ldr	w2, [vdso_data, #CLOCK_REALTIME_RES]
-	b	2f
-1:
-	cmp	w0, #CLOCK_REALTIME_COARSE
-	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
-	b.ne	4f
-	ldr	x2, 5f
-2:
-	cbz	x1, 3f
-	stp	xzr, x2, [x1]
-
-3:	/* res == NULL. */
-	mov	w0, wzr
-	ret
-
-4:	/* Syscall fallback. */
-	mov	x8, #__NR_clock_getres
-	svc	#0
-	ret
-5:
-	.quad	CLOCK_COARSE_RES
-	.cfi_endproc
-ENDPROC(__kernel_clock_getres)

arch/arm64/kernel/vdso/vgettimeofday.c

@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+
+int __kernel_clock_gettime(clockid_t clock,
+			   struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __kernel_gettimeofday(struct __kernel_old_timeval *tv,
+			  struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __kernel_clock_getres(clockid_t clock_id,
+			  struct __kernel_timespec *res)
+{
+	return __cvdso_clock_getres(clock_id, res);
+}

arch/arm64/kernel/vdso32/.gitignore

@@ -0,0 +1,2 @@
+vdso.lds
+vdso.so.raw

arch/arm64/kernel/vdso32/Makefile

@@ -0,0 +1,211 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for vdso32
+#
+
+# Absolute relocation type $(ARCH_REL_TYPE_ABS) needs to be defined before
+# the inclusion of generic Makefile.
+ARCH_REL_TYPE_ABS := R_ARM_JUMP_SLOT|R_ARM_GLOB_DAT|R_ARM_ABS32
+include $(srctree)/lib/vdso/Makefile
+
+# Same as cc-*option, but using CC_COMPAT instead of CC
+ifeq ($(CONFIG_CC_IS_CLANG), y)
+COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit))
+COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..)
+
+CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)
+CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments
+ifneq ($(COMPAT_GCC_TOOLCHAIN),)
+CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN)
+endif
+
+CC_COMPAT ?= $(CC)
+CC_COMPAT += $(CC_COMPAT_CLANG_FLAGS)
+else
+CC_COMPAT ?= $(CROSS_COMPILE_COMPAT)gcc
+endif
+
+cc32-option = $(call try-run,\
+        $(CC_COMPAT) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-disable-warning = $(call try-run,\
+	$(CC_COMPAT) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1)))
+cc32-ldoption = $(call try-run,\
+        $(CC_COMPAT) $(1) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
+cc32-as-instr = $(call try-run,\
+	printf "%b\n" "$(1)" | $(CC_COMPAT) $(VDSO_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3))
+
+# We cannot use the global flags to compile the vDSO files, the main reason
+# being that the 32-bit compiler may be older than the main (64-bit) compiler
+# and therefore may not understand flags set using $(cc-option ...). Besides,
+# arch-specific options should be taken from the arm Makefile instead of the
+# arm64 one.
+# As a result we set our own flags here.
+
+# KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile
+VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include)
+VDSO_CPPFLAGS += $(LINUXINCLUDE)
+
+# Common C and assembly flags
+# From top-level Makefile
+VDSO_CAFLAGS := $(VDSO_CPPFLAGS)
+ifneq ($(shell $(CC_COMPAT) --version 2>&1 | head -n 1 | grep clang),)
+VDSO_CAFLAGS += --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%))
+endif
+
+VDSO_CAFLAGS += $(call cc32-option,-fno-PIE)
+ifdef CONFIG_DEBUG_INFO
+VDSO_CAFLAGS += -g
+endif
+
+# From arm Makefile
+VDSO_CAFLAGS += $(call cc32-option,-fno-dwarf2-cfi-asm)
+VDSO_CAFLAGS += -mabi=aapcs-linux -mfloat-abi=soft
+ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
+VDSO_CAFLAGS += -mbig-endian
+else
+VDSO_CAFLAGS += -mlittle-endian
+endif
+
+# From arm vDSO Makefile
+VDSO_CAFLAGS += -fPIC -fno-builtin -fno-stack-protector
+VDSO_CAFLAGS += -DDISABLE_BRANCH_PROFILING
+
+
+# Try to compile for ARMv8. If the compiler is too old and doesn't support it,
+# fall back to v7. There is no easy way to check for what architecture the code
+# is being compiled, so define a macro specifying that (see arch/arm/Makefile).
+VDSO_CAFLAGS += $(call cc32-option,-march=armv8-a -D__LINUX_ARM_ARCH__=8,\
+                                   -march=armv7-a -D__LINUX_ARM_ARCH__=7)
+
+VDSO_CFLAGS := $(VDSO_CAFLAGS)
+VDSO_CFLAGS += -DENABLE_COMPAT_VDSO=1
+# KBUILD_CFLAGS from top-level Makefile
+VDSO_CFLAGS += -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
+               -fno-strict-aliasing -fno-common \
+               -Werror-implicit-function-declaration \
+               -Wno-format-security \
+               -std=gnu89
+VDSO_CFLAGS  += -O2
+# Some useful compiler-dependent flags from top-level Makefile
+VDSO_CFLAGS += $(call cc32-option,-Wdeclaration-after-statement,)
+VDSO_CFLAGS += $(call cc32-option,-Wno-pointer-sign)
+VDSO_CFLAGS += $(call cc32-option,-fno-strict-overflow)
+VDSO_CFLAGS += $(call cc32-option,-Werror=strict-prototypes)
+VDSO_CFLAGS += $(call cc32-option,-Werror=date-time)
+VDSO_CFLAGS += $(call cc32-option,-Werror=incompatible-pointer-types)
+
+# The 32-bit compiler does not provide 128-bit integers, which are used in
+# some headers that are indirectly included from the vDSO code.
+# This hack makes the compiler happy and should trigger a warning/error if
+# variables of such type are referenced.
+VDSO_CFLAGS += -D__uint128_t='void*'
+# Silence some warnings coming from headers that operate on long's
+# (on GCC 4.8 or older, there is unfortunately no way to silence this warning)
+VDSO_CFLAGS += $(call cc32-disable-warning,shift-count-overflow)
+VDSO_CFLAGS += -Wno-int-to-pointer-cast
+
+VDSO_AFLAGS := $(VDSO_CAFLAGS)
+VDSO_AFLAGS += -D__ASSEMBLY__
+
+# Check for binutils support for dmb ishld
+dmbinstr := $(call cc32-as-instr,dmb ishld,-DCONFIG_AS_DMB_ISHLD=1)
+
+VDSO_CFLAGS += $(dmbinstr)
+VDSO_AFLAGS += $(dmbinstr)
+
+VDSO_LDFLAGS := $(VDSO_CPPFLAGS)
+# From arm vDSO Makefile
+VDSO_LDFLAGS += -Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1
+VDSO_LDFLAGS += -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS += -nostdlib -shared -mfloat-abi=soft
+VDSO_LDFLAGS += $(call cc32-ldoption,-Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS += $(call cc32-ldoption,-Wl$(comma)--build-id)
+VDSO_LDFLAGS += $(call cc32-ldoption,-fuse-ld=bfd)
+
+
+# Borrow vdsomunge.c from the arm vDSO
+# We have to use a relative path because scripts/Makefile.host prefixes
+# $(hostprogs-y) with $(obj)
+munge := ../../../arm/vdso/vdsomunge
+hostprogs-y := $(munge)
+
+c-obj-vdso := note.o
+c-obj-vdso-gettimeofday := vgettimeofday.o
+asm-obj-vdso := sigreturn.o
+
+ifneq ($(c-gettimeofday-y),)
+VDSO_CFLAGS_gettimeofday_o += -include $(c-gettimeofday-y)
+endif
+
+VDSO_CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os
+
+# Build rules
+targets := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso) vdso.so vdso.so.dbg vdso.so.raw
+c-obj-vdso := $(addprefix $(obj)/, $(c-obj-vdso))
+c-obj-vdso-gettimeofday := $(addprefix $(obj)/, $(c-obj-vdso-gettimeofday))
+asm-obj-vdso := $(addprefix $(obj)/, $(asm-obj-vdso))
+obj-vdso := $(c-obj-vdso) $(c-obj-vdso-gettimeofday) $(asm-obj-vdso)
+
+obj-y += vdso.o
+extra-y += vdso.lds
+CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
+
+# Force dependency (vdso.s includes vdso.so through incbin)
+$(obj)/vdso.o: $(obj)/vdso.so
+
+include/generated/vdso32-offsets.h: $(obj)/vdso.so.dbg FORCE
+	$(call if_changed,vdsosym)
+
+# Strip rule for vdso.so
+$(obj)/vdso.so: OBJCOPYFLAGS := -S
+$(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+$(obj)/vdso.so.dbg: $(obj)/vdso.so.raw $(obj)/$(munge) FORCE
+	$(call if_changed,vdsomunge)
+
+# Link rule for the .so file, .lds has to be first
+$(obj)/vdso.so.raw: $(src)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,vdsold_and_vdso_check)
+
+# Compilation rules for the vDSO sources
+$(c-obj-vdso): %.o: %.c FORCE
+	$(call if_changed_dep,vdsocc)
+$(c-obj-vdso-gettimeofday): %.o: %.c FORCE
+	$(call if_changed_dep,vdsocc_gettimeofday)
+$(asm-obj-vdso): %.o: %.S FORCE
+	$(call if_changed_dep,vdsoas)
+
+# Actual build commands
+quiet_cmd_vdsold_and_vdso_check = LD32    $@
+      cmd_vdsold_and_vdso_check = $(cmd_vdsold); $(cmd_vdso_check)
+
+quiet_cmd_vdsold = LD32    $@
+      cmd_vdsold = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_LDFLAGS) \
+                   -Wl,-T $(filter %.lds,$^) $(filter %.o,$^) -o $@
+quiet_cmd_vdsocc = CC32    $@
+      cmd_vdsocc = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) -c -o $@ $<
+quiet_cmd_vdsocc_gettimeofday = CC32    $@
+      cmd_vdsocc_gettimeofday = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_CFLAGS) $(VDSO_CFLAGS_gettimeofday_o) -c -o $@ $<
+quiet_cmd_vdsoas = AS32    $@
+      cmd_vdsoas = $(CC_COMPAT) -Wp,-MD,$(depfile) $(VDSO_AFLAGS) -c -o $@ $<
+
+quiet_cmd_vdsomunge = MUNGE   $@
+      cmd_vdsomunge = $(obj)/$(munge) $< $@
+
+# Generate vDSO offsets using helper script (borrowed from the 64-bit vDSO)
+gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh
+quiet_cmd_vdsosym = VDSOSYM $@
+# The AArch64 nm should be able to read an AArch32 binary
+      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
+
+# Install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so
+
+vdso.so: $(obj)/vdso.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso.so

arch/arm64/kernel/vdso32/note.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2012-2018 ARM Limited
+ *
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+#include <linux/build-salt.h>
+
+ELFNOTE32("Linux", 0, LINUX_VERSION_CODE);
+BUILD_SALT;

arch/arm64/kernel/vdso32/sigreturn.S

@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file provides both A32 and T32 versions, in accordance with the
+ * arm sigreturn code.
+ *
+ * Copyright (C) 2018 ARM Limited
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+#define ARM_ENTRY(name)		\
+	ENTRY(name)
+
+#define ARM_ENDPROC(name)	\
+	.type name, %function;	\
+	END(name)
+
+	.text
+
+	.arm
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_sigreturn_arm)
+	mov r7, #__NR_compat_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_sigreturn_arm)
+
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_rt_sigreturn_arm)
+	mov r7, #__NR_compat_rt_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_arm)
+
+	.thumb
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_sigreturn_thumb)
+	mov r7, #__NR_compat_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_sigreturn_thumb)
+
+	.fnstart
+	.save {r0-r15}
+	.pad #COMPAT_RT_SIGFRAME_REGS_OFFSET
+	nop
+ARM_ENTRY(__kernel_rt_sigreturn_thumb)
+	mov r7, #__NR_compat_rt_sigreturn
+	svc #0
+	.fnend
+ARM_ENDPROC(__kernel_rt_sigreturn_thumb)

arch/arm64/kernel/vdso32/vdso.S

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2012 ARM Limited
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/const.h>
+#include <asm/page.h>
+
+	.globl vdso32_start, vdso32_end
+	.section .rodata
+	.balign PAGE_SIZE
+vdso32_start:
+	.incbin "arch/arm64/kernel/vdso32/vdso.so"
+	.balign PAGE_SIZE
+vdso32_end:
+
+	.previous

arch/arm64/kernel/vdso32/vdso.lds.S

@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Adapted from arm64 version.
+ *
+ * GNU linker script for the VDSO library.
+ * Heavily based on the vDSO linker scripts for other archs.
+ *
+ * Copyright (C) 2012-2018 ARM Limited
+ */
+
+#include <linux/const.h>
+#include <asm/page.h>
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf32-littlearm", "elf32-bigarm", "elf32-littlearm")
+OUTPUT_ARCH(arm)
+
+SECTIONS
+{
+	PROVIDE_HIDDEN(_vdso_data = . - PAGE_SIZE);
+	. = VDSO_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.rodata		: { *(.rodata*) }		:text
+
+	.text		: { *(.text*) }			:text	=0xe7f001f2
+
+	.got		: { *(.got) }
+	.rel.plt	: { *(.rel.plt) }
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD		FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+	dynamic		PT_DYNAMIC	FLAGS(4);		/* PF_R */
+	note		PT_NOTE		FLAGS(4);		/* PF_R */
+}
+
+VERSION
+{
+	LINUX_2.6 {
+	global:
+		__vdso_clock_gettime;
+		__vdso_gettimeofday;
+		__vdso_clock_getres;
+		__kernel_sigreturn_arm;
+		__kernel_sigreturn_thumb;
+		__kernel_rt_sigreturn_arm;
+		__kernel_rt_sigreturn_thumb;
+		__vdso_clock_gettime64;
+	local: *;
+	};
+}
+
+/*
+ * Make the sigreturn code visible to the kernel.
+ */
+VDSO_compat_sigreturn_arm	= __kernel_sigreturn_arm;
+VDSO_compat_sigreturn_thumb	= __kernel_sigreturn_thumb;
+VDSO_compat_rt_sigreturn_arm	= __kernel_rt_sigreturn_arm;
+VDSO_compat_rt_sigreturn_thumb	= __kernel_rt_sigreturn_thumb;

arch/arm64/kernel/vdso32/vgettimeofday.c

@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 compat userspace implementations of gettimeofday() and similar.
+ *
+ * Copyright (C) 2018 ARM Limited
+ *
+ */
+
+int __vdso_clock_gettime(clockid_t clock,
+			 struct old_timespec32 *ts)
+{
+	return __cvdso_clock_gettime32(clock, ts);
+}
+
+int __vdso_clock_gettime64(clockid_t clock,
+			   struct __kernel_timespec *ts)
+{
+	return __cvdso_clock_gettime(clock, ts);
+}
+
+int __vdso_gettimeofday(struct __kernel_old_timeval *tv,
+			struct timezone *tz)
+{
+	return __cvdso_gettimeofday(tv, tz);
+}
+
+int __vdso_clock_getres(clockid_t clock_id,
+			struct old_timespec32 *res)
+{
+	return __cvdso_clock_getres_time32(clock_id, res);
+}
+
+/* Avoid unresolved references emitted by GCC */
+
+void __aeabi_unwind_cpp_pr0(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr1(void)
+{
+}
+
+void __aeabi_unwind_cpp_pr2(void)
+{
+}

arch/arm64/kvm/guest.c

@@ -179,6 +179,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id));
+
+	if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) {
+		int i;
+
+		for (i = 0; i < 16; i++)
+			*vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i);
+	}
 out:
 	return err;
 }

arch/arm64/mm/cache.S

@@ -230,7 +230,7 @@ ENTRY(__inval_dcache_area)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-__dma_inv_area:
+ENTRY(__dma_inv_area)
 	add	x1, x1, x0
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
@@ -269,7 +269,7 @@ ENTRY(__clean_dcache_area_poc)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-__dma_clean_area:
+ENTRY(__dma_clean_area)
 	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
 ENDPIPROC(__clean_dcache_area_poc)

arch/arm64/mm/dma-mapping.c

@@ -26,26 +26,47 @@
 #include <linux/genalloc.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-contiguous.h>
+#include <linux/mm.h>
+#include <linux/iommu.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
 #include <linux/dma-removed.h>
 #include <linux/pci.h>
+#include <linux/io.h>
 
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
+#include <asm/dma-iommu.h>
+#include <linux/of_address.h>
+#include <linux/dma-mapping-fast.h>
 
 static int swiotlb __ro_after_init;
 
 static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
 				 bool coherent)
 {
-	if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE))
+	if (attrs & DMA_ATTR_STRONGLY_ORDERED)
+		return pgprot_noncached(prot);
+	else if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE))
 		return pgprot_writecombine(prot);
 	return prot;
 }
 
+static bool is_dma_coherent(struct device *dev, unsigned long attrs)
+{
+
+	if (attrs & DMA_ATTR_FORCE_COHERENT)
+		return true;
+	else if (attrs & DMA_ATTR_FORCE_NON_COHERENT)
+		return false;
+	else if (is_device_dma_coherent(dev))
+		return true;
+	else
+		return false;
+}
 static struct gen_pool *atomic_pool __ro_after_init;
 
+#define NO_KERNEL_MAPPING_DUMMY 0x2222
 #define DEFAULT_DMA_COHERENT_POOL_SIZE  SZ_256K
 static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
 
@@ -93,13 +114,50 @@ static int __free_from_pool(void *start, size_t size)
 	return 1;
 }
 
+static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
+			    void *data)
+{
+	struct page *page = virt_to_page(addr);
+	pgprot_t prot = *(pgprot_t *)data;
+
+	set_pte(pte, mk_pte(page, prot));
+	return 0;
+}
+
+static int __dma_clear_pte(pte_t *pte, pgtable_t token, unsigned long addr,
+			    void *data)
+{
+	pte_clear(&init_mm, addr, pte);
+	return 0;
+}
+
+static void __dma_remap(struct page *page, size_t size, pgprot_t prot,
+			bool no_kernel_map)
+{
+	unsigned long start = (unsigned long) page_address(page);
+	unsigned long end = start + size;
+	int (*func)(pte_t *pte, pgtable_t token, unsigned long addr,
+			    void *data);
+
+	if (no_kernel_map)
+		func = __dma_clear_pte;
+	else
+		func = __dma_update_pte;
+
+	apply_to_page_range(&init_mm, start, size, func, &prot);
+	/* ensure prot is applied before returning */
+	mb();
+	flush_tlb_kernel_range(start, end);
+}
+
+
 static void *__dma_alloc(struct device *dev, size_t size,
 			 dma_addr_t *dma_handle, gfp_t flags,
 			 unsigned long attrs)
 {
 	struct page *page;
 	void *ptr, *coherent_ptr;
-	bool coherent = is_device_dma_coherent(dev);
+	bool coherent = is_dma_coherent(dev, attrs);
 	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
 
 	size = PAGE_ALIGN(size);
@@ -115,6 +173,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	}
 
 	ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs);
+
 	if (!ptr)
 		goto no_mem;
 
@@ -122,19 +181,31 @@ static void *__dma_alloc(struct device *dev, size_t size,
 	if (coherent)
 		return ptr;
 
-	/* remove any dirty cache lines on the kernel alias */
 	__dma_flush_area(ptr, size);
 
-	/* create a coherent mapping */
+	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING) {
-	page = virt_to_page(ptr);
+		coherent_ptr = (void *)NO_KERNEL_MAPPING_DUMMY;
-	coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+		__dma_remap(virt_to_page(ptr), size, __pgprot(0), true);
-						   prot, __builtin_return_address(0));
+	} else {
-	if (!coherent_ptr)
+		if ((attrs & DMA_ATTR_STRONGLY_ORDERED))
-		goto no_map;
+			__dma_remap(virt_to_page(ptr), size, __pgprot(0), true);
 
+		/* create a coherent mapping */
+		page = virt_to_page(ptr);
+		coherent_ptr = dma_common_contiguous_remap(
+					page, size, VM_USERMAP, prot,
+					__builtin_return_address(0));
+		if (!coherent_ptr)
+			goto no_map;
+	}
 	return coherent_ptr;
 
 no_map:
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) ||
+	    (attrs & DMA_ATTR_STRONGLY_ORDERED))
+		__dma_remap(phys_to_page(dma_to_phys(dev, *dma_handle)),
+				size, PAGE_KERNEL, false);
+
 	swiotlb_free(dev, size, ptr, *dma_handle, attrs);
 no_mem:
 	return NULL;
@@ -148,11 +219,17 @@ static void __dma_free(struct device *dev, size_t size,
 
 	size = PAGE_ALIGN(size);
 
-	if (!is_device_dma_coherent(dev)) {
+	if (!is_dma_coherent(dev, attrs)) {
 		if (__free_from_pool(vaddr, size))
 			return;
-		vunmap(vaddr);
+		if (!(attrs & DMA_ATTR_NO_KERNEL_MAPPING))
+			vunmap(vaddr);
 	}
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) ||
+	    (attrs & DMA_ATTR_STRONGLY_ORDERED))
+		__dma_remap(phys_to_page(dma_to_phys(dev, dma_handle)),
+				size, PAGE_KERNEL, false);
+
 	swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs);
 }
 
@@ -164,7 +241,7 @@ static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
 	dma_addr_t dev_addr;
 
 	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
-	if (!is_device_dma_coherent(dev) &&
+	if (!is_dma_coherent(dev, attrs) &&
 	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
 
@@ -176,7 +253,7 @@ static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
 				 size_t size, enum dma_data_direction dir,
 				 unsigned long attrs)
 {
-	if (!is_device_dma_coherent(dev) &&
+	if (!is_dma_coherent(dev, attrs) &&
 	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
 	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
@@ -190,7 +267,7 @@ static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
 	int i, ret;
 
 	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
-	if (!is_device_dma_coherent(dev) &&
+	if (!is_dma_coherent(dev, attrs) &&
 	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		for_each_sg(sgl, sg, ret, i)
 			__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
@@ -207,7 +284,7 @@ static void __swiotlb_unmap_sg_attrs(struct device *dev,
 	struct scatterlist *sg;
 	int i;
 
-	if (!is_device_dma_coherent(dev) &&
+	if (!is_dma_coherent(dev, attrs) &&
 	    (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		for_each_sg(sgl, sg, nelems, i)
 			__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
@@ -284,11 +361,11 @@ static int __swiotlb_mmap(struct device *dev,
 			  void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			  unsigned long attrs)
 {
-	int ret;
+	int ret = -ENXIO;
 	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
 
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
-					     is_device_dma_coherent(dev));
+			is_dma_coherent(dev, attrs));
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
@@ -447,7 +524,7 @@ static int __init atomic_pool_init(void)
 	goto out;
 
 remove_mapping:
-	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP);
+	dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP, false);
 destroy_genpool:
 	gen_pool_destroy(atomic_pool);
 	atomic_pool = NULL;
@@ -468,6 +545,7 @@ static void *__dummy_alloc(struct device *dev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flags,
 			   unsigned long attrs)
 {
+	WARN(1, "dma alloc failure, device may be missing a call to arch_setup_dma_ops");
 	return NULL;
 }
 
@@ -582,7 +660,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 				 dma_addr_t *handle, gfp_t gfp,
 				 unsigned long attrs)
 {
-	bool coherent = is_device_dma_coherent(dev);
+	bool coherent = is_dma_coherent(dev, attrs);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
 	size_t iosize = size;
 	void *addr;
@@ -596,7 +674,8 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 	 * Some drivers rely on this, and we probably don't want the
 	 * possibility of stale kernel data being read by devices anyway.
 	 */
-	gfp |= __GFP_ZERO;
+	if (!(attrs & DMA_ATTR_SKIP_ZEROING))
+		gfp |= __GFP_ZERO;
 
 	if (!gfpflags_allow_blocking(gfp)) {
 		struct page *page;
@@ -688,17 +767,16 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		__free_from_pool(cpu_addr, size);
 	} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
 		struct page *page = vmalloc_to_page(cpu_addr);
-
 		iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
 		dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+		dma_common_free_remap(cpu_addr, size, VM_USERMAP, false);
-	} else if (is_vmalloc_addr(cpu_addr)){
+	} else if (is_vmalloc_addr(cpu_addr)) {
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
 		if (WARN_ON(!area || !area->pages))
 			return;
 		iommu_dma_free(dev, area->pages, iosize, &handle);
-		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
+		dma_common_free_remap(cpu_addr, size, VM_USERMAP, false);
 	} else {
 		iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
 		__free_pages(virt_to_page(cpu_addr), get_order(size));
@@ -711,32 +789,31 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 {
 	struct vm_struct *area;
 	int ret;
+	unsigned long pfn = 0;
 
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
-					     is_device_dma_coherent(dev));
+					     is_dma_coherent(dev, attrs));
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
-	if (!is_vmalloc_addr(cpu_addr)) {
-		unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
-		return __swiotlb_mmap_pfn(vma, pfn, size);
-	}
-
-	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
-		/*
-		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
-		 * hence in the vmalloc space.
-		 */
-		unsigned long pfn = vmalloc_to_pfn(cpu_addr);
-		return __swiotlb_mmap_pfn(vma, pfn, size);
-	}
-
 	area = find_vm_area(cpu_addr);
-	if (WARN_ON(!area || !area->pages))
-		return -ENXIO;
 
-	return iommu_dma_mmap(area->pages, size, vma);
+	if (area && area->pages)
+		return iommu_dma_mmap(area->pages, size, vma);
+	else if (!is_vmalloc_addr(cpu_addr))
+		pfn = page_to_pfn(virt_to_page(cpu_addr));
+	else if (is_vmalloc_addr(cpu_addr))
+		/*
+		 * DMA_ATTR_FORCE_CONTIGUOUS and atomic pool allocations are
+		 * always remapped, hence in the vmalloc space.
+		 */
+		pfn = vmalloc_to_pfn(cpu_addr);
+
+	if (pfn)
+		return __swiotlb_mmap_pfn(vma, pfn, size);
+
+	return -ENXIO;
 }
 
 static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
@@ -744,27 +821,24 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 			       size_t size, unsigned long attrs)
 {
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = NULL;
 	struct vm_struct *area = find_vm_area(cpu_addr);
 
-	if (!is_vmalloc_addr(cpu_addr)) {
+	if (area && area->pages)
-		struct page *page = virt_to_page(cpu_addr);
+		return sg_alloc_table_from_pages(sgt, area->pages, count, 0,
-		return __swiotlb_get_sgtable_page(sgt, page, size);
+					size, GFP_KERNEL);
-	}
+	else if (!is_vmalloc_addr(cpu_addr))
-
+		page = virt_to_page(cpu_addr);
-	if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+	else if (is_vmalloc_addr(cpu_addr))
 		/*
-		 * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+		 * DMA_ATTR_FORCE_CONTIGUOUS and atomic pool allocations
-		 * hence in the vmalloc space.
+		 * are always remapped, hence in the vmalloc space.
 		 */
-		struct page *page = vmalloc_to_page(cpu_addr);
+		page = vmalloc_to_page(cpu_addr);
+
+	if (page)
 		return __swiotlb_get_sgtable_page(sgt, page, size);
-	}
+	return -ENXIO;
-
-	if (WARN_ON(!area || !area->pages))
-		return -ENXIO;
-
-	return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size,
-					 GFP_KERNEL);
 }
 
 static void __iommu_sync_single_for_cpu(struct device *dev,
@@ -772,11 +846,12 @@ static void __iommu_sync_single_for_cpu(struct device *dev,
 					enum dma_data_direction dir)
 {
 	phys_addr_t phys;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
-	if (is_device_dma_coherent(dev))
+	if (!domain || iommu_is_iova_coherent(domain, dev_addr))
 		return;
 
-	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	phys = iommu_iova_to_phys(domain, dev_addr);
 	__dma_unmap_area(phys_to_virt(phys), size, dir);
 }
 
@@ -785,11 +860,12 @@ static void __iommu_sync_single_for_device(struct device *dev,
 					   enum dma_data_direction dir)
 {
 	phys_addr_t phys;
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 
-	if (is_device_dma_coherent(dev))
+	if (!domain || iommu_is_iova_coherent(domain, dev_addr))
 		return;
 
-	phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
+	phys = iommu_iova_to_phys(domain, dev_addr);
 	__dma_map_area(phys_to_virt(phys), size, dir);
 }
 
@@ -798,7 +874,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
-	bool coherent = is_device_dma_coherent(dev);
+	bool coherent = is_dma_coherent(dev, attrs);
 	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
 
@@ -824,9 +900,11 @@ static void __iommu_sync_sg_for_cpu(struct device *dev,
 				    enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
+	dma_addr_t iova = sg_dma_address(sgl);
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	int i;
 
-	if (is_device_dma_coherent(dev))
+	if (!domain || iommu_is_iova_coherent(domain, iova))
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
@@ -838,9 +916,11 @@ static void __iommu_sync_sg_for_device(struct device *dev,
 				       enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
+	dma_addr_t iova = sg_dma_address(sgl);
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
 	int i;
 
-	if (is_device_dma_coherent(dev))
+	if (!domain || iommu_is_iova_coherent(domain, iova))
 		return;
 
 	for_each_sg(sgl, sg, nelems, i)
@@ -851,13 +931,18 @@ static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
 				int nelems, enum dma_data_direction dir,
 				unsigned long attrs)
 {
-	bool coherent = is_device_dma_coherent(dev);
+	bool coherent = is_dma_coherent(dev, attrs);
+	int ret;
+
+	ret =  iommu_dma_map_sg(dev, sgl, nelems,
+				dma_info_to_prot(dir, coherent, attrs));
+	if (!ret)
+		return ret;
 
 	if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
 
-	return iommu_dma_map_sg(dev, sgl, nelems,
+	return ret;
-				dma_info_to_prot(dir, coherent, attrs));
 }
 
 static void __iommu_unmap_sg_attrs(struct device *dev,
@@ -895,50 +980,14 @@ static int __init __iommu_dma_init(void)
 }
 arch_initcall(__iommu_dma_init);
 
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  const struct iommu_ops *ops)
-{
-	struct iommu_domain *domain;
-
-	if (!ops)
-		return;
-
-	/*
-	 * The IOMMU core code allocates the default DMA domain, which the
-	 * underlying IOMMU driver needs to support via the dma-iommu layer.
-	 */
-	domain = iommu_get_domain_for_dev(dev);
-
-	if (!domain)
-		goto out_err;
-
-	if (domain->type == IOMMU_DOMAIN_DMA) {
-		if (iommu_dma_init_domain(domain, dma_base, size, dev))
-			goto out_err;
-
-		dev->dma_ops = &iommu_dma_ops;
-	}
-
-	return;
-
-out_err:
-	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-		 dev_name(dev));
-}
-
 void arch_teardown_dma_ops(struct device *dev)
 {
 	dev->dma_ops = NULL;
 }
-
-#else
-
-static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				  const struct iommu_ops *iommu)
-{ }
-
 #endif  /* CONFIG_IOMMU_DMA */
 
+static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size);
+
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
@@ -950,7 +999,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	}
 
 	dev->archdata.dma_coherent = coherent;
-	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
+	arm_iommu_setup_dma_ops(dev, dma_base, size);
 
 #ifdef CONFIG_XEN
 	if (xen_initial_domain()) {
@@ -960,3 +1009,149 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 #endif
 }
 EXPORT_SYMBOL_GPL(arch_setup_dma_ops);
+
+#ifdef CONFIG_ARM64_DMA_USE_IOMMU
+
+/* guards initialization of default_domain->iova_cookie */
+static DEFINE_MUTEX(iommu_dma_init_mutex);
+
+static int
+iommu_init_mapping(struct device *dev, struct dma_iommu_mapping *mapping)
+{
+	struct iommu_domain *domain = mapping->domain;
+	dma_addr_t dma_base = mapping->base;
+	u64 size = mapping->bits << PAGE_SHIFT;
+	int ret;
+	bool own_cookie;
+
+	/*
+	 * if own_cookie is false, then we are sharing the iova_cookie with
+	 * another driver, and should not free it on error. Cleanup will be
+	 * done when the iommu_domain is freed.
+	 */
+	own_cookie = !domain->iova_cookie;
+
+	if (own_cookie) {
+		ret = iommu_get_dma_cookie(domain);
+		if (ret) {
+			dev_err(dev, "iommu_get_dma_cookie failed: %d\n", ret);
+			return ret;
+		}
+	}
+
+	ret = iommu_dma_init_domain(domain, dma_base, size, dev);
+	if (ret) {
+		dev_err(dev, "iommu_dma_init_domain failed: %d\n", ret);
+		if (own_cookie)
+			iommu_put_dma_cookie(domain);
+		return ret;
+	}
+
+	mapping->ops = &iommu_dma_ops;
+	return 0;
+}
+
+static int arm_iommu_get_dma_cookie(struct device *dev,
+				    struct dma_iommu_mapping *mapping)
+{
+	int s1_bypass = 0, is_fast = 0;
+	int err = 0;
+
+	mutex_lock(&iommu_dma_init_mutex);
+
+	iommu_domain_get_attr(mapping->domain, DOMAIN_ATTR_S1_BYPASS,
+					&s1_bypass);
+	iommu_domain_get_attr(mapping->domain, DOMAIN_ATTR_FAST, &is_fast);
+
+	if (s1_bypass)
+		mapping->ops = &arm64_swiotlb_dma_ops;
+	else if (is_fast)
+		err = fast_smmu_init_mapping(dev, mapping);
+	else
+		err = iommu_init_mapping(dev, mapping);
+
+	mutex_unlock(&iommu_dma_init_mutex);
+	return err;
+}
+
+/*
+ * Checks for "qcom,iommu-dma-addr-pool" property.
+ * If not present, leaves dma_addr and dma_size unmodified.
+ */
+static void arm_iommu_get_dma_window(struct device *dev, u64 *dma_addr,
+					u64 *dma_size)
+{
+	struct device_node *np;
+	int naddr, nsize, len;
+	const __be32 *ranges;
+
+	if (!dev->of_node)
+		return;
+
+	np = of_parse_phandle(dev->of_node, "qcom,iommu-group", 0);
+	if (!np)
+		np = dev->of_node;
+
+	ranges = of_get_property(np, "qcom,iommu-dma-addr-pool", &len);
+	if (!ranges)
+		return;
+
+	len /= sizeof(u32);
+	naddr = of_n_addr_cells(np);
+	nsize = of_n_size_cells(np);
+	if (len < naddr + nsize) {
+		dev_err(dev, "Invalid length for qcom,iommu-dma-addr-pool, expected %d cells\n",
+			naddr + nsize);
+		return;
+	}
+	if (naddr == 0 || nsize == 0) {
+		dev_err(dev, "Invalid #address-cells %d or #size-cells %d\n",
+			naddr, nsize);
+		return;
+	}
+
+	*dma_addr = of_read_number(ranges, naddr);
+	*dma_size = of_read_number(ranges + naddr, nsize);
+}
+
+static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size)
+{
+	struct iommu_domain *domain;
+	struct iommu_group *group;
+	struct dma_iommu_mapping mapping = {0};
+
+	group = dev->iommu_group;
+	if (!group)
+		return;
+
+	arm_iommu_get_dma_window(dev, &dma_base, &size);
+
+	domain = iommu_get_domain_for_dev(dev);
+	if (!domain)
+		return;
+
+	/* Allow iommu-debug to call arch_setup_dma_ops to reconfigure itself */
+	if (domain->type != IOMMU_DOMAIN_DMA &&
+	    !of_device_is_compatible(dev->of_node, "iommu-debug-test")) {
+		dev_err(dev, "Invalid iommu domain type!\n");
+		return;
+	}
+
+	mapping.base = dma_base;
+	mapping.bits = size >> PAGE_SHIFT;
+	mapping.domain = domain;
+
+	if (arm_iommu_get_dma_cookie(dev, &mapping)) {
+		dev_err(dev, "Failed to get dma cookie\n");
+		return;
+	}
+
+	set_dma_ops(dev, mapping.ops);
+}
+
+#else /*!CONFIG_ARM64_DMA_USE_IOMMU */
+
+static void arm_iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size)
+{
+}
+#endif

arch/arm64/mm/hugetlbpage.c

@@ -218,6 +218,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 		ptep = (pte_t *)pudp;
 	} else if (sz == (PAGE_SIZE * CONT_PTES)) {
 		pmdp = pmd_alloc(mm, pudp, addr);
+		if (!pmdp)
+			return NULL;
 
 		WARN_ON(addr & (sz - 1));
 		/*

arch/arm64/mm/init.c

@@ -53,6 +53,8 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
+EXPORT_SYMBOL_GPL(kimage_vaddr);
+
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()

arch/arm64/mm/mmu.c

@@ -32,6 +32,8 @@
 #include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/dma-contiguous.h>
+#include <linux/cma.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -67,6 +69,40 @@ static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
 static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
 static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
 
+struct dma_contig_early_reserve {
+	phys_addr_t base;
+	unsigned long size;
+};
+
+static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS];
+static int dma_mmu_remap_num;
+
+void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+	if (dma_mmu_remap_num >= ARRAY_SIZE(dma_mmu_remap)) {
+		pr_err("ARM64: Not enough slots for DMA fixup reserved regions!\n");
+		return;
+	}
+	dma_mmu_remap[dma_mmu_remap_num].base = base;
+	dma_mmu_remap[dma_mmu_remap_num].size = size;
+	dma_mmu_remap_num++;
+}
+
+static bool dma_overlap(phys_addr_t start, phys_addr_t end)
+{
+	int i;
+
+	for (i = 0; i < dma_mmu_remap_num; i++) {
+		phys_addr_t dma_base = dma_mmu_remap[i].base;
+		phys_addr_t dma_end = dma_mmu_remap[i].base +
+			dma_mmu_remap[i].size;
+
+		if ((dma_base < end) && (dma_end > start))
+			return true;
+	}
+	return false;
+}
+
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -200,7 +236,8 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
-		    (flags & NO_BLOCK_MAPPINGS) == 0) {
+		    (flags & NO_BLOCK_MAPPINGS) == 0 &&
+		    !dma_overlap(phys, phys + next - addr)) {
 			pmd_set_huge(pmdp, phys, prot);
 
 			/*
@@ -299,7 +336,8 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
 		if (use_1G_block(addr, next, phys) &&
-		    (flags & NO_BLOCK_MAPPINGS) == 0) {
+		    (flags & NO_BLOCK_MAPPINGS) == 0 &&
+		    !dma_overlap(phys, phys + next - addr)) {
 			pud_set_huge(pudp, phys, prot);
 
 			/*
@@ -720,6 +758,7 @@ int kern_addr_valid(unsigned long addr)
 
 	return pfn_valid(pte_pfn(pte));
 }
+EXPORT_SYMBOL_GPL(kern_addr_valid);
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 #if !ARM64_SWAPPER_USES_SECTION_MAPS
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,

arch/hexagon/include/asm/io.h

@@ -186,16 +186,10 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 
 #define mmiowb()
 
-/*
+void __iomem *ioremap(unsigned long phys_addr, unsigned long size);
- * Need an mtype somewhere in here, for cache type deals?
+#define ioremap_nocache ioremap
- * This is probably too long for an inline.
+#define ioremap_uc(X, Y) ioremap((X), (Y))
- */
-void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size);
 
-static inline void __iomem *ioremap(unsigned long phys_addr, unsigned long size)
-{
-	return ioremap_nocache(phys_addr, size);
-}
 
 static inline void iounmap(volatile void __iomem *addr)
 {

arch/hexagon/kernel/hexagon_ksyms.c

@@ -33,7 +33,7 @@ EXPORT_SYMBOL(__vmgetie);
 EXPORT_SYMBOL(__vmsetie);
 EXPORT_SYMBOL(__vmyield);
 EXPORT_SYMBOL(empty_zero_page);
-EXPORT_SYMBOL(ioremap_nocache);
+EXPORT_SYMBOL(ioremap);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memset);
 

arch/hexagon/mm/ioremap.c

@@ -22,7 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 
-void __iomem *ioremap_nocache(unsigned long phys_addr, unsigned long size)
+void __iomem *ioremap(unsigned long phys_addr, unsigned long size)
 {
 	unsigned long last_addr, addr;
 	unsigned long offset = phys_addr & ~PAGE_MASK;

arch/mips/Kconfig

@@ -21,6 +21,7 @@ config MIPS
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_GETTIMEOFDAY
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_LIB_ASHLDI3
@@ -71,6 +72,7 @@ config MIPS
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING_GEN if 64BIT || !SMP
+	select HAVE_GENERIC_VDSO
 	select IRQ_FORCED_THREADING
 	select MODULES_USE_ELF_RELA if MODULES && 64BIT
 	select MODULES_USE_ELF_REL if MODULES

arch/mips/cavium-octeon/octeon-irq.c

@@ -2199,6 +2199,9 @@ static int octeon_irq_cib_map(struct irq_domain *d,
 	}
 
 	cd = kzalloc(sizeof(*cd), GFP_KERNEL);
+	if (!cd)
+		return -ENOMEM;
+
 	cd->host_data = host_data;
 	cd->bit = hw;
 

arch/mips/include/asm/clocksource.h

@@ -11,19 +11,6 @@
 #ifndef __ASM_CLOCKSOURCE_H
 #define __ASM_CLOCKSOURCE_H
 
-#include <linux/types.h>
+#include <asm/vdso/clocksource.h>
-
-/* VDSO clocksources. */
-#define VDSO_CLOCK_NONE		0	/* No suitable clocksource. */
-#define VDSO_CLOCK_R4K		1	/* Use the coprocessor 0 count. */
-#define VDSO_CLOCK_GIC		2	/* Use the GIC. */
-
-/**
- * struct arch_clocksource_data - Architecture-specific clocksource information.
- * @vdso_clock_mode: Method the VDSO should use to access the clocksource.
- */
-struct arch_clocksource_data {
-	u8 vdso_clock_mode;
-};
 
 #endif /* __ASM_CLOCKSOURCE_H */

arch/mips/include/asm/processor.h

@@ -22,6 +22,7 @@
 #include <asm/dsemul.h>
 #include <asm/mipsregs.h>
 #include <asm/prefetch.h>
+#include <asm/vdso/processor.h>
 
 /*
  * Return current * instruction pointer ("program counter").
@@ -386,21 +387,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
-#ifdef CONFIG_CPU_LOONGSON3
-/*
- * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
- * tight read loop is executed, because reads take priority over writes & the
- * hardware (incorrectly) doesn't ensure that writes will eventually occur.
- *
- * Since spin loops of any kind should have a cpu_relax() in them, force an SFB
- * flush from cpu_relax() such that any pending writes will become visible as
- * expected.
- */
-#define cpu_relax()	smp_mb()
-#else
-#define cpu_relax()	barrier()
-#endif
-
 /*
  * Return_address is a replacement for __builtin_return_address(count)
  * which on certain architectures cannot reasonably be implemented in GCC

arch/mips/include/asm/vdso.h

@@ -12,6 +12,7 @@
 #define __ASM_VDSO_H
 
 #include <linux/mm_types.h>
+#include <vdso/datapage.h>
 
 #include <asm/barrier.h>
 
@@ -53,84 +54,9 @@ extern struct mips_vdso_image vdso_image_o32;
 extern struct mips_vdso_image vdso_image_n32;
 #endif
 
-/**
- * union mips_vdso_data - Data provided by the kernel for the VDSO.
- * @xtime_sec:		Current real time (seconds part).
- * @xtime_nsec:		Current real time (nanoseconds part, shifted).
- * @wall_to_mono_sec:	Wall-to-monotonic offset (seconds part).
- * @wall_to_mono_nsec:	Wall-to-monotonic offset (nanoseconds part).
- * @seq_count:		Counter to synchronise updates (odd = updating).
- * @cs_shift:		Clocksource shift value.
- * @clock_mode:		Clocksource to use for time functions.
- * @cs_mult:		Clocksource multiplier value.
- * @cs_cycle_last:	Clock cycle value at last update.
- * @cs_mask:		Clocksource mask value.
- * @tz_minuteswest:	Minutes west of Greenwich (from timezone).
- * @tz_dsttime:		Type of DST correction (from timezone).
- *
- * This structure contains data needed by functions within the VDSO. It is
- * populated by the kernel and mapped read-only into user memory. The time
- * fields are mirrors of internal data from the timekeeping infrastructure.
- *
- * Note: Care should be taken when modifying as the layout must remain the same
- * for both 64- and 32-bit (for 32-bit userland on 64-bit kernel).
- */
 union mips_vdso_data {
-	struct {
+	struct vdso_data data[CS_BASES];
-		u64 xtime_sec;
-		u64 xtime_nsec;
-		u64 wall_to_mono_sec;
-		u64 wall_to_mono_nsec;
-		u32 seq_count;
-		u32 cs_shift;
-		u8 clock_mode;
-		u32 cs_mult;
-		u64 cs_cycle_last;
-		u64 cs_mask;
-		s32 tz_minuteswest;
-		s32 tz_dsttime;
-	};
-
 	u8 page[PAGE_SIZE];
 };
 
-static inline u32 vdso_data_read_begin(const union mips_vdso_data *data)
-{
-	u32 seq;
-
-	while (true) {
-		seq = READ_ONCE(data->seq_count);
-		if (likely(!(seq & 1))) {
-			/* Paired with smp_wmb() in vdso_data_write_*(). */
-			smp_rmb();
-			return seq;
-		}
-
-		cpu_relax();
-	}
-}
-
-static inline bool vdso_data_read_retry(const union mips_vdso_data *data,
-					u32 start_seq)
-{
-	/* Paired with smp_wmb() in vdso_data_write_*(). */
-	smp_rmb();
-	return unlikely(data->seq_count != start_seq);
-}
-
-static inline void vdso_data_write_begin(union mips_vdso_data *data)
-{
-	++data->seq_count;
-
-	/* Ensure sequence update is written before other data page values. */
-	smp_wmb();
-}
-
-static inline void vdso_data_write_end(union mips_vdso_data *data)
-{
-	/* Ensure data values are written before updating sequence again. */
-	smp_wmb();
-	++data->seq_count;
-}
-
 #endif /* __ASM_VDSO_H */

arch/mips/include/asm/vdso/clocksource.h

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef __ASM_VDSOCLOCKSOURCE_H
+#define __ASM_VDSOCLOCKSOURCE_H
+
+#include <linux/types.h>
+
+/* VDSO clocksources. */
+#define VDSO_CLOCK_NONE		0	/* No suitable clocksource. */
+#define VDSO_CLOCK_R4K		1	/* Use the coprocessor 0 count. */
+#define VDSO_CLOCK_GIC		2	/* Use the GIC. */
+
+/**
+ * struct arch_clocksource_data - Architecture-specific clocksource information.
+ * @vdso_clock_mode: Method the VDSO should use to access the clocksource.
+ */
+struct arch_clocksource_data {
+	u8 vdso_clock_mode;
+};
+
+#endif /* __ASM_VDSOCLOCKSOURCE_H */