Merge tag 'v5.0-rc5' into locking/core to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

.clang-format

@@ -72,6 +72,10 @@ ForEachMacros:
   - 'apei_estatus_for_each_section'
   - 'ata_for_each_dev'
   - 'ata_for_each_link'
+  - '__ata_qc_for_each'
+  - 'ata_qc_for_each'
+  - 'ata_qc_for_each_raw'
+  - 'ata_qc_for_each_with_internal'
   - 'ax25_for_each'
   - 'ax25_uid_for_each'
   - 'bio_for_each_integrity_vec'
@@ -85,6 +89,7 @@ ForEachMacros:
   - 'blk_queue_for_each_rl'
   - 'bond_for_each_slave'
   - 'bond_for_each_slave_rcu'
+  - 'bpf_for_each_spilled_reg'
   - 'btree_for_each_safe128'
   - 'btree_for_each_safe32'
   - 'btree_for_each_safe64'
@@ -103,6 +108,8 @@ ForEachMacros:
   - 'drm_atomic_crtc_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane'
   - 'drm_atomic_crtc_state_for_each_plane_state'
+  - 'drm_atomic_for_each_plane_damage'
+  - 'drm_connector_for_each_possible_encoder'
   - 'drm_for_each_connector_iter'
   - 'drm_for_each_crtc'
   - 'drm_for_each_encoder'
@@ -121,11 +128,21 @@ ForEachMacros:
   - 'for_each_bio'
   - 'for_each_board_func_rsrc'
   - 'for_each_bvec'
+  - 'for_each_card_components'
+  - 'for_each_card_links'
+  - 'for_each_card_links_safe'
+  - 'for_each_card_prelinks'
+  - 'for_each_card_rtds'
+  - 'for_each_card_rtds_safe'
+  - 'for_each_cgroup_storage_type'
   - 'for_each_child_of_node'
   - 'for_each_clear_bit'
   - 'for_each_clear_bit_from'
   - 'for_each_cmsghdr'
   - 'for_each_compatible_node'
+  - 'for_each_component_dais'
+  - 'for_each_component_dais_safe'
+  - 'for_each_comp_order'
   - 'for_each_console'
   - 'for_each_cpu'
   - 'for_each_cpu_and'
@@ -133,6 +150,10 @@ ForEachMacros:
   - 'for_each_cpu_wrap'
   - 'for_each_dev_addr'
   - 'for_each_dma_cap_mask'
+  - 'for_each_dpcm_be'
+  - 'for_each_dpcm_be_rollback'
+  - 'for_each_dpcm_be_safe'
+  - 'for_each_dpcm_fe'
   - 'for_each_drhd_unit'
   - 'for_each_dss_dev'
   - 'for_each_efi_memory_desc'
@@ -149,6 +170,7 @@ ForEachMacros:
   - 'for_each_iommu'
   - 'for_each_ip_tunnel_rcu'
   - 'for_each_irq_nr'
+  - 'for_each_link_codecs'
   - 'for_each_lru'
   - 'for_each_matching_node'
   - 'for_each_matching_node_and_match'
@@ -160,6 +182,7 @@ ForEachMacros:
   - 'for_each_mem_range_rev'
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
+  - 'for_each_msi_entry_safe'
   - 'for_each_net'
   - 'for_each_netdev'
   - 'for_each_netdev_continue'
@@ -183,12 +206,14 @@ ForEachMacros:
   - 'for_each_node_with_property'
   - 'for_each_of_allnodes'
   - 'for_each_of_allnodes_from'
+  - 'for_each_of_cpu_node'
   - 'for_each_of_pci_range'
   - 'for_each_old_connector_in_state'
   - 'for_each_old_crtc_in_state'
   - 'for_each_oldnew_connector_in_state'
   - 'for_each_oldnew_crtc_in_state'
   - 'for_each_oldnew_plane_in_state'
+  - 'for_each_oldnew_plane_in_state_reverse'
   - 'for_each_oldnew_private_obj_in_state'
   - 'for_each_old_plane_in_state'
   - 'for_each_old_private_obj_in_state'
@@ -206,14 +231,17 @@ ForEachMacros:
   - 'for_each_process'
   - 'for_each_process_thread'
   - 'for_each_property_of_node'
+  - 'for_each_registered_fb'
   - 'for_each_reserved_mem_region'
-  - 'for_each_resv_unavail_range'
+  - 'for_each_rtd_codec_dai'
+  - 'for_each_rtd_codec_dai_rollback'
   - 'for_each_rtdcom'
   - 'for_each_rtdcom_safe'
   - 'for_each_set_bit'
   - 'for_each_set_bit_from'
   - 'for_each_sg'
   - 'for_each_sg_page'
+  - 'for_each_sibling_event'
   - '__for_each_thread'
   - 'for_each_thread'
   - 'for_each_zone'
@@ -251,6 +279,8 @@ ForEachMacros:
   - 'hlist_nulls_for_each_entry_from'
   - 'hlist_nulls_for_each_entry_rcu'
   - 'hlist_nulls_for_each_entry_safe'
+  - 'i3c_bus_for_each_i2cdev'
+  - 'i3c_bus_for_each_i3cdev'
   - 'ide_host_for_each_port'
   - 'ide_port_for_each_dev'
   - 'ide_port_for_each_present_dev'
@@ -267,11 +297,14 @@ ForEachMacros:
   - 'kvm_for_each_memslot'
   - 'kvm_for_each_vcpu'
   - 'list_for_each'
+  - 'list_for_each_codec'
+  - 'list_for_each_codec_safe'
   - 'list_for_each_entry'
   - 'list_for_each_entry_continue'
   - 'list_for_each_entry_continue_rcu'
   - 'list_for_each_entry_continue_reverse'
   - 'list_for_each_entry_from'
+  - 'list_for_each_entry_from_rcu'
   - 'list_for_each_entry_from_reverse'
   - 'list_for_each_entry_lockless'
   - 'list_for_each_entry_rcu'
@@ -291,6 +324,7 @@ ForEachMacros:
   - 'media_device_for_each_intf'
   - 'media_device_for_each_link'
   - 'media_device_for_each_pad'
+  - 'nanddev_io_for_each_page'
   - 'netdev_for_each_lower_dev'
   - 'netdev_for_each_lower_private'
   - 'netdev_for_each_lower_private_rcu'
@@ -357,12 +391,14 @@ ForEachMacros:
   - 'sk_nulls_for_each'
   - 'sk_nulls_for_each_from'
   - 'sk_nulls_for_each_rcu'
+  - 'snd_array_for_each'
   - 'snd_pcm_group_for_each_entry'
   - 'snd_soc_dapm_widget_for_each_path'
   - 'snd_soc_dapm_widget_for_each_path_safe'
   - 'snd_soc_dapm_widget_for_each_sink_path'
   - 'snd_soc_dapm_widget_for_each_source_path'
   - 'tb_property_for_each'
+  - 'tcf_exts_for_each_action'
   - 'udp_portaddr_for_each_entry'
   - 'udp_portaddr_for_each_entry_rcu'
   - 'usb_hub_for_each_child'
@@ -371,6 +407,11 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_dst_buf_safe'
   - 'v4l2_m2m_for_each_src_buf'
   - 'v4l2_m2m_for_each_src_buf_safe'
+  - 'virtio_device_for_each_vq'
+  - 'xa_for_each'
+  - 'xas_for_each'
+  - 'xas_for_each_conflict'
+  - 'xas_for_each_marked'
   - 'zorro_for_each_dev'
 
 #IncludeBlocks: Preserve # Unknown to clang-format-5.0

Documentation/core-api/xarray.rst

@@ -108,12 +108,13 @@ some, but not all of the other indices changing.
 
 Sometimes you need to ensure that a subsequent call to :c:func:`xa_store`
 will not need to allocate memory.  The :c:func:`xa_reserve` function
-will store a reserved entry at the indicated index.  Users of the normal
+will store a reserved entry at the indicated index.  Users of the
-API will see this entry as containing ``NULL``.  If you do not need to
+normal API will see this entry as containing ``NULL``.  If you do
-use the reserved entry, you can call :c:func:`xa_release` to remove the
+not need to use the reserved entry, you can call :c:func:`xa_release`
-unused entry.  If another user has stored to the entry in the meantime,
+to remove the unused entry.  If another user has stored to the entry
-:c:func:`xa_release` will do nothing; if instead you want the entry to
+in the meantime, :c:func:`xa_release` will do nothing; if instead you
-become ``NULL``, you should use :c:func:`xa_erase`.
+want the entry to become ``NULL``, you should use :c:func:`xa_erase`.
+Using :c:func:`xa_insert` on a reserved entry will fail.
 
 If all entries in the array are ``NULL``, the :c:func:`xa_empty` function
 will return ``true``.
@@ -183,6 +184,8 @@ Takes xa_lock internally:
  * :c:func:`xa_store_bh`
  * :c:func:`xa_store_irq`
  * :c:func:`xa_insert`
+ * :c:func:`xa_insert_bh`
+ * :c:func:`xa_insert_irq`
  * :c:func:`xa_erase`
  * :c:func:`xa_erase_bh`
  * :c:func:`xa_erase_irq`

Documentation/devicetree/bindings/Makefile

@@ -17,7 +17,11 @@ extra-y += $(DT_TMP_SCHEMA)
 quiet_cmd_mk_schema = SCHEMA  $@
       cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(filter-out FORCE, $^)
 
-DT_DOCS = $(shell cd $(srctree)/$(src) && find * -name '*.yaml')
+DT_DOCS = $(shell \
+	cd $(srctree)/$(src) && \
+	find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \
+	)
+
 DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS))
 
 extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES))

Documentation/devicetree/bindings/display/msm/gpu.txt

@@ -27,7 +27,6 @@ Example:
 		reg = <0x04300000 0x20000>;
 		reg-names = "kgsl_3d0_reg_memory";
 		interrupts = <GIC_SPI 80 0>;
-		interrupt-names = "kgsl_3d0_irq";
 		clock-names =
 		    "core",
 		    "iface",

Documentation/devicetree/bindings/serio/olpc,ap-sp.txt

@@ -4,14 +4,10 @@ Required properties:
 - compatible : "olpc,ap-sp"
 - reg : base address and length of SoC's WTM registers
 - interrupts : SP-AP interrupt
-- clocks : phandle + clock-specifier for the clock that drives the WTM
-- clock-names:  should be "sp"
 
 Example:
 	ap-sp@d4290000 {
 		compatible = "olpc,ap-sp";
 		reg = <0xd4290000 0x1000>;
 		interrupts = <40>;
-		clocks = <&soc_clocks MMP2_CLK_SP>;
-		clock-names = "sp";
 	}

Documentation/fb/fbcon.txt

@@ -163,6 +163,14 @@ C. Boot options
 	be preserved until there actually is some text is output to the console.
 	This option causes fbcon to bind immediately to the fbdev device.
 
+7. fbcon=logo-pos:<location>
+
+	The only possible 'location' is 'center' (without quotes), and when
+	given, the bootup logo is moved from the default top-left corner
+	location to the center of the framebuffer. If more than one logo is
+	displayed due to multiple CPUs, the collected line of logos is moved
+	as a whole.
+
 C. Attaching, Detaching and Unloading
 
 Before going on to how to attach, detach and unload the framebuffer console, an

Documentation/networking/index.rst

@@ -11,19 +11,19 @@ Contents:
    batman-adv
    can
    can_ucan_protocol
-   dpaa2/index
+   device_drivers/freescale/dpaa2/index
-   e100
+   device_drivers/intel/e100
-   e1000
+   device_drivers/intel/e1000
-   e1000e
+   device_drivers/intel/e1000e
-   fm10k
+   device_drivers/intel/fm10k
-   igb
+   device_drivers/intel/igb
-   igbvf
+   device_drivers/intel/igbvf
-   ixgb
+   device_drivers/intel/ixgb
-   ixgbe
+   device_drivers/intel/ixgbe
-   ixgbevf
+   device_drivers/intel/ixgbevf
-   i40e
+   device_drivers/intel/i40e
-   iavf
+   device_drivers/intel/iavf
-   ice
+   device_drivers/intel/ice
    kapi
    z8530book
    msg_zerocopy

Documentation/networking/rxrpc.txt

@@ -1000,51 +1000,6 @@ The kernel interface functions are as follows:
      size should be set when the call is begun.  tx_total_len may not be less
      than zero.
 
- (*) Check to see the completion state of a call so that the caller can assess
-     whether it needs to be retried.
-
-	enum rxrpc_call_completion {
-		RXRPC_CALL_SUCCEEDED,
-		RXRPC_CALL_REMOTELY_ABORTED,
-		RXRPC_CALL_LOCALLY_ABORTED,
-		RXRPC_CALL_LOCAL_ERROR,
-		RXRPC_CALL_NETWORK_ERROR,
-	};
-
-	int rxrpc_kernel_check_call(struct socket *sock, struct rxrpc_call *call,
-				    enum rxrpc_call_completion *_compl,
-				    u32 *_abort_code);
-
-     On return, -EINPROGRESS will be returned if the call is still ongoing; if
-     it is finished, *_compl will be set to indicate the manner of completion,
-     *_abort_code will be set to any abort code that occurred.  0 will be
-     returned on a successful completion, -ECONNABORTED will be returned if the
-     client failed due to a remote abort and anything else will return an
-     appropriate error code.
-
-     The caller should look at this information to decide if it's worth
-     retrying the call.
-
- (*) Retry a client call.
-
-	int rxrpc_kernel_retry_call(struct socket *sock,
-				    struct rxrpc_call *call,
-				    struct sockaddr_rxrpc *srx,
-				    struct key *key);
-
-     This attempts to partially reinitialise a call and submit it again while
-     reusing the original call's Tx queue to avoid the need to repackage and
-     re-encrypt the data to be sent.  call indicates the call to retry, srx the
-     new address to send it to and key the encryption key to use for signing or
-     encrypting the packets.
-
-     For this to work, the first Tx data packet must still be in the transmit
-     queue, and currently this is only permitted for local and network errors
-     and the call must not have been aborted.  Any partially constructed Tx
-     packet is left as is and can continue being filled afterwards.
-
-     It returns 0 if the call was requeued and an error otherwise.
-
  (*) Get call RTT.
 
 	u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call);

Documentation/networking/snmp_counter.rst

@@ -336,7 +336,26 @@ time client replies ACK, this socket will get another chance to move
 to the accept queue.
 
 
-TCP Fast Open
+* TcpEstabResets
+Defined in `RFC1213 tcpEstabResets`_.
+
+.. _RFC1213 tcpEstabResets: https://tools.ietf.org/html/rfc1213#page-48
+
+* TcpAttemptFails
+Defined in `RFC1213 tcpAttemptFails`_.
+
+.. _RFC1213 tcpAttemptFails: https://tools.ietf.org/html/rfc1213#page-48
+
+* TcpOutRsts
+Defined in `RFC1213 tcpOutRsts`_. The RFC says this counter indicates
+the 'segments sent containing the RST flag', but in linux kernel, this
+couner indicates the segments kerenl tried to send. The sending
+process might be failed due to some errors (e.g. memory alloc failed).
+
+.. _RFC1213 tcpOutRsts: https://tools.ietf.org/html/rfc1213#page-52
+
+
+TCP Fast Path
 ============
 When kernel receives a TCP packet, it has two paths to handler the
 packet, one is fast path, another is slow path. The comment in kernel
@@ -383,8 +402,6 @@ increase 1.
 
 TCP abort
 ========
-
-
 * TcpExtTCPAbortOnData
 It means TCP layer has data in flight, but need to close the
 connection. So TCP layer sends a RST to the other side, indicate the
@@ -545,7 +562,6 @@ packet yet, the sender would know packet 4 is out of order. The TCP
 stack of kernel will increase TcpExtTCPSACKReorder for both of the
 above scenarios.
 
-
 DSACK
 =====
 The DSACK is defined in `RFC2883`_. The receiver uses DSACK to report
@@ -566,13 +582,63 @@ The TCP stack receives an out of order duplicate packet, so it sends a
 DSACK to the sender.
 
 * TcpExtTCPDSACKRecv
-The TCP stack receives a DSACK, which indicate an acknowledged
+The TCP stack receives a DSACK, which indicates an acknowledged
 duplicate packet is received.
 
 * TcpExtTCPDSACKOfoRecv
 The TCP stack receives a DSACK, which indicate an out of order
 duplicate packet is received.
 
+invalid SACK and DSACK
+====================
+When a SACK (or DSACK) block is invalid, a corresponding counter would
+be updated. The validation method is base on the start/end sequence
+number of the SACK block. For more details, please refer the comment
+of the function tcp_is_sackblock_valid in the kernel source code. A
+SACK option could have up to 4 blocks, they are checked
+individually. E.g., if 3 blocks of a SACk is invalid, the
+corresponding counter would be updated 3 times. The comment of the
+`Add counters for discarded SACK blocks`_ patch has additional
+explaination:
+
+.. _Add counters for discarded SACK blocks: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=18f02545a9a16c9a89778b91a162ad16d510bb32
+
+* TcpExtTCPSACKDiscard
+This counter indicates how many SACK blocks are invalid. If the invalid
+SACK block is caused by ACK recording, the TCP stack will only ignore
+it and won't update this counter.
+
+* TcpExtTCPDSACKIgnoredOld and TcpExtTCPDSACKIgnoredNoUndo
+When a DSACK block is invalid, one of these two counters would be
+updated. Which counter will be updated depends on the undo_marker flag
+of the TCP socket. If the undo_marker is not set, the TCP stack isn't
+likely to re-transmit any packets, and we still receive an invalid
+DSACK block, the reason might be that the packet is duplicated in the
+middle of the network. In such scenario, TcpExtTCPDSACKIgnoredNoUndo
+will be updated. If the undo_marker is set, TcpExtTCPDSACKIgnoredOld
+will be updated. As implied in its name, it might be an old packet.
+
+SACK shift
+=========
+The linux networking stack stores data in sk_buff struct (skb for
+short). If a SACK block acrosses multiple skb, the TCP stack will try
+to re-arrange data in these skb. E.g. if a SACK block acknowledges seq
+10 to 15, skb1 has seq 10 to 13, skb2 has seq 14 to 20. The seq 14 and
+15 in skb2 would be moved to skb1. This operation is 'shift'. If a
+SACK block acknowledges seq 10 to 20, skb1 has seq 10 to 13, skb2 has
+seq 14 to 20. All data in skb2 will be moved to skb1, and skb2 will be
+discard, this operation is 'merge'.
+
+* TcpExtTCPSackShifted
+A skb is shifted
+
+* TcpExtTCPSackMerged
+A skb is merged
+
+* TcpExtTCPSackShiftFallback
+A skb should be shifted or merged, but the TCP stack doesn't do it for
+some reasons.
+
 TCP out of order
 ===============
 * TcpExtTCPOFOQueue
@@ -662,6 +728,60 @@ unacknowledged number (more strict than `RFC 5961 section 5.2`_).
 .. _RFC 5961 section 4.2: https://tools.ietf.org/html/rfc5961#page-9
 .. _RFC 5961 section 5.2: https://tools.ietf.org/html/rfc5961#page-11
 
+TCP receive window
+=================
+* TcpExtTCPWantZeroWindowAdv
+Depending on current memory usage, the TCP stack tries to set receive
+window to zero. But the receive window might still be a no-zero
+value. For example, if the previous window size is 10, and the TCP
+stack receives 3 bytes, the current window size would be 7 even if the
+window size calculated by the memory usage is zero.
+
+* TcpExtTCPToZeroWindowAdv
+The TCP receive window is set to zero from a no-zero value.
+
+* TcpExtTCPFromZeroWindowAdv
+The TCP receive window is set to no-zero value from zero.
+
+
+Delayed ACK
+==========
+The TCP Delayed ACK is a technique which is used for reducing the
+packet count in the network. For more details, please refer the
+`Delayed ACK wiki`_
+
+.. _Delayed ACK wiki: https://en.wikipedia.org/wiki/TCP_delayed_acknowledgment
+
+* TcpExtDelayedACKs
+A delayed ACK timer expires. The TCP stack will send a pure ACK packet
+and exit the delayed ACK mode.
+
+* TcpExtDelayedACKLocked
+A delayed ACK timer expires, but the TCP stack can't send an ACK
+immediately due to the socket is locked by a userspace program. The
+TCP stack will send a pure ACK later (after the userspace program
+unlock the socket). When the TCP stack sends the pure ACK later, the
+TCP stack will also update TcpExtDelayedACKs and exit the delayed ACK
+mode.
+
+* TcpExtDelayedACKLost
+It will be updated when the TCP stack receives a packet which has been
+ACKed. A Delayed ACK loss might cause this issue, but it would also be
+triggered by other reasons, such as a packet is duplicated in the
+network.
+
+Tail Loss Probe (TLP)
+===================
+TLP is an algorithm which is used to detect TCP packet loss. For more
+details, please refer the `TLP paper`_.
+
+.. _TLP paper: https://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01
+
+* TcpExtTCPLossProbes
+A TLP probe packet is sent.
+
+* TcpExtTCPLossProbeRecovery
+A packet loss is detected and recovered by TLP.
 
 examples
 =======

Documentation/networking/timestamping.txt

@@ -417,7 +417,7 @@ is again deprecated and ts[2] holds a hardware timestamp if set.
 
 Hardware time stamping must also be initialized for each device driver
 that is expected to do hardware time stamping. The parameter is defined in
-/include/linux/net_tstamp.h as:
+include/uapi/linux/net_tstamp.h as:
 
 struct hwtstamp_config {
 	int flags;	/* no flags defined right now, must be zero */
@@ -487,7 +487,7 @@ enum {
 	HWTSTAMP_FILTER_PTP_V1_L4_EVENT,
 
 	/* for the complete list of values, please check
-	 * the include file /include/linux/net_tstamp.h
+	 * the include file include/uapi/linux/net_tstamp.h
 	 */
 };
 

Documentation/sysctl/fs.txt

@@ -56,26 +56,32 @@ of any kernel data structures.
 
 dentry-state:
 
-From linux/fs/dentry.c:
+From linux/include/linux/dcache.h:
 --------------------------------------------------------------
-struct {
+struct dentry_stat_t dentry_stat {
         int nr_dentry;
         int nr_unused;
         int age_limit;         /* age in seconds */
         int want_pages;        /* pages requested by system */
-        int dummy[2];
+        int nr_negative;       /* # of unused negative dentries */
-} dentry_stat = {0, 0, 45, 0,};
+        int dummy;             /* Reserved for future use */
--------------------------------------------------------------- 
+};
+--------------------------------------------------------------
+
+Dentries are dynamically allocated and deallocated.
+
+nr_dentry shows the total number of dentries allocated (active
++ unused). nr_unused shows the number of dentries that are not
+actively used, but are saved in the LRU list for future reuse.
 
-Dentries are dynamically allocated and deallocated, and
-nr_dentry seems to be 0 all the time. Hence it's safe to
-assume that only nr_unused, age_limit and want_pages are
-used. Nr_unused seems to be exactly what its name says.
 Age_limit is the age in seconds after which dcache entries
 can be reclaimed when memory is short and want_pages is
 nonzero when shrink_dcache_pages() has been called and the
 dcache isn't pruned yet.
 
+nr_negative shows the number of unused dentries that are also
+negative dentries which do not mapped to actual files.
+
 ==============================================================
 
 dquot-max & dquot-nr:

Documentation/x86/resctrl_ui.txt

@@ -9,7 +9,7 @@ Fenghua Yu <fenghua.yu@intel.com>
 Tony Luck <tony.luck@intel.com>
 Vikas Shivappa <vikas.shivappa@intel.com>
 
-This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo
+This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo
 flag bits:
 RDT (Resource Director Technology) Allocation - "rdt_a"
 CAT (Cache Allocation Technology) - "cat_l3", "cat_l2"

MAINTAINERS

@@ -3052,8 +3052,8 @@ F:	include/linux/bcm963xx_nvram.h
 F:	include/linux/bcm963xx_tag.h
 
 BROADCOM BNX2 GIGABIT ETHERNET DRIVER
-M:	Rasesh Mody <rasesh.mody@cavium.com>
+M:	Rasesh Mody <rmody@marvell.com>
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2.*
@@ -3072,9 +3072,9 @@ S:	Supported
 F:	drivers/scsi/bnx2i/
 
 BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M:	Ariel Elior <ariel.elior@cavium.com>
+M:	Ariel Elior <aelior@marvell.com>
-M:	Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
+M:	Sudarsana Kalluru <skalluru@marvell.com>
-M:	everest-linux-l2@cavium.com
+M:	GR-everest-linux-l2@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
@@ -3249,9 +3249,9 @@ S:	Supported
 F:	drivers/scsi/bfa/
 
 BROCADE BNA 10 GIGABIT ETHERNET DRIVER
-M:	Rasesh Mody <rasesh.mody@cavium.com>
+M:	Rasesh Mody <rmody@marvell.com>
-M:	Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
+M:	Sudarsana Kalluru <skalluru@marvell.com>
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/brocade/bna/
@@ -3471,10 +3471,9 @@ F:	drivers/i2c/busses/i2c-octeon*
 F:	drivers/i2c/busses/i2c-thunderx*
 
 CAVIUM LIQUIDIO NETWORK DRIVER
-M:	Derek Chickles <derek.chickles@caviumnetworks.com>
+M:	Derek Chickles <dchickles@marvell.com>
-M:	Satanand Burla <satananda.burla@caviumnetworks.com>
+M:	Satanand Burla <sburla@marvell.com>
-M:	Felix Manlunas <felix.manlunas@caviumnetworks.com>
+M:	Felix Manlunas <fmanlunas@marvell.com>
-M:	Raghu Vatsavayi <raghu.vatsavayi@caviumnetworks.com>
 L:	netdev@vger.kernel.org
 W:	http://www.cavium.com
 S:	Supported
@@ -3979,6 +3978,7 @@ F:	drivers/cpufreq/arm_big_little.c
 CPU POWER MONITORING SUBSYSTEM
 M:	Thomas Renninger <trenn@suse.com>
 M:	Shuah Khan <shuah@kernel.org>
+M:	Shuah Khan <skhan@linuxfoundation.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 F:	tools/power/cpupower/
@@ -8259,6 +8259,7 @@ F:	include/uapi/linux/sunrpc/
 
 KERNEL SELFTEST FRAMEWORK
 M:	Shuah Khan <shuah@kernel.org>
+M:	Shuah Khan <skhan@linuxfoundation.org>
 L:	linux-kselftest@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git
 Q:	https://patchwork.kernel.org/project/linux-kselftest/list/
@@ -10689,9 +10690,9 @@ S:	Maintained
 F:	drivers/net/netdevsim/*
 
 NETXEN (1/10) GbE SUPPORT
-M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Manish Chopra <manishc@marvell.com>
-M:	Rahul Verma <rahul.verma@cavium.com>
+M:	Rahul Verma <rahulv@marvell.com>
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/netxen/
@@ -12475,8 +12476,8 @@ S:	Supported
 F:	drivers/scsi/qedi/
 
 QLOGIC QL4xxx ETHERNET DRIVER
-M:	Ariel Elior <Ariel.Elior@cavium.com>
+M:	Ariel Elior <aelior@marvell.com>
-M:	everest-linux-l2@cavium.com
+M:	GR-everest-linux-l2@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qed/
@@ -12484,8 +12485,8 @@ F:	include/linux/qed/
 F:	drivers/net/ethernet/qlogic/qede/
 
 QLOGIC QL4xxx RDMA DRIVER
-M:	Michal Kalderon <Michal.Kalderon@cavium.com>
+M:	Michal Kalderon <mkalderon@marvell.com>
-M:	Ariel Elior <Ariel.Elior@cavium.com>
+M:	Ariel Elior <aelior@marvell.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/qedr/
@@ -12505,7 +12506,7 @@ F:	Documentation/scsi/LICENSE.qla2xxx
 F:	drivers/scsi/qla2xxx/
 
 QLOGIC QLA3XXX NETWORK DRIVER
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	Documentation/networking/device_drivers/qlogic/LICENSE.qla3xxx
@@ -12519,16 +12520,16 @@ F:	Documentation/scsi/LICENSE.qla4xxx
 F:	drivers/scsi/qla4xxx/
 
 QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M:	Shahed Shaikh <Shahed.Shaikh@cavium.com>
+M:	Shahed Shaikh <shshaikh@marvell.com>
-M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Manish Chopra <manishc@marvell.com>
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qlcnic/
 
 QLOGIC QLGE 10Gb ETHERNET DRIVER
-M:	Manish Chopra <manish.chopra@cavium.com>
+M:	Manish Chopra <manishc@marvell.com>
-M:	Dept-GELinuxNICDev@cavium.com
+M:	GR-Linux-NIC-Dev@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qlge/
@@ -15842,6 +15843,7 @@ F:	drivers/usb/common/usb-otg-fsm.c
 USB OVER IP DRIVER
 M:	Valentina Manea <valentina.manea.m@gmail.com>
 M:	Shuah Khan <shuah@kernel.org>
+M:	Shuah Khan <skhan@linuxfoundation.org>
 L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	Documentation/usb/usbip_protocol.txt
@@ -16639,6 +16641,15 @@ S:	Maintained
 F:	drivers/platform/x86/
 F:	drivers/platform/olpc/
 
+X86 PLATFORM DRIVERS - ARCH
+R:	Darren Hart <dvhart@infradead.org>
+R:	Andy Shevchenko <andy@infradead.org>
+L:	platform-driver-x86@vger.kernel.org
+L:	x86@kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core
+S:	Maintained
+F:	arch/x86/platform
+
 X86 VDSO
 M:	Andy Lutomirski <luto@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -16671,6 +16682,24 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/tuners/tuner-xc2028.*
 
+XDP (eXpress Data Path)
+M:	Alexei Starovoitov <ast@kernel.org>
+M:	Daniel Borkmann <daniel@iogearbox.net>
+M:	David S. Miller <davem@davemloft.net>
+M:	Jakub Kicinski <jakub.kicinski@netronome.com>
+M:	Jesper Dangaard Brouer <hawk@kernel.org>
+M:	John Fastabend <john.fastabend@gmail.com>
+L:	netdev@vger.kernel.org
+L:	xdp-newbies@vger.kernel.org
+S:	Supported
+F:	net/core/xdp.c
+F:	include/net/xdp.h
+F:	kernel/bpf/devmap.c
+F:	kernel/bpf/cpumap.c
+F:	include/trace/events/xdp.h
+K:	xdp
+N:	xdp
+
 XDP SOCKETS (AF_XDP)
 M:	Björn Töpel <bjorn.topel@intel.com>
 M:	Magnus Karlsson <magnus.karlsson@intel.com>

Makefile

@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc5
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*

arch/arc/include/asm/Kbuild

@@ -3,23 +3,19 @@ generic-y += bugs.h
 generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
-generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += extable.h
-generic-y += fb.h
 generic-y += ftrace.h
 generic-y += hardirq.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
-generic-y += kmap_types.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msi.h
 generic-y += parport.h
-generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += topology.h

arch/arc/include/asm/arcregs.h

@@ -216,6 +216,14 @@ struct bcr_fp_arcv2 {
 #endif
 };
 
+struct bcr_actionpoint {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:21, min:1, num:2, ver:8;
+#else
+	unsigned int ver:8, num:2, min:1, pad:21;
+#endif
+};
+
 #include <soc/arc/timers.h>
 
 struct bcr_bpu_arcompact {
@@ -283,7 +291,7 @@ struct cpuinfo_arc_cache {
 };
 
 struct cpuinfo_arc_bpu {
-	unsigned int ver, full, num_cache, num_pred;
+	unsigned int ver, full, num_cache, num_pred, ret_stk;
 };
 
 struct cpuinfo_arc_ccm {
@@ -302,7 +310,7 @@ struct cpuinfo_arc {
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
 			     fpu_sp:1, fpu_dp:1, dual:1, dual_enb:1, pad2:4,
-			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
+			     ap_num:4, ap_full:1, smart:1, rtt:1, pad3:1,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;

arch/arc/include/asm/bitops.h

@@ -340,7 +340,7 @@ static inline __attribute__ ((const)) int __fls(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
 {
 	if (!word)
 		return word;
@@ -400,9 +400,9 @@ static inline __attribute__ ((const)) int ffs(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 {
-	int n;
+	unsigned long n;
 
 	asm volatile(
 	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */

arch/arc/include/asm/perf_event.h

@@ -103,7 +103,8 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",

arch/arc/kernel/perf_event.c

@@ -1,15 +1,10 @@
-/*
+// SPDX-License-Identifier: GPL-2.0+
- * Linux performance counter support for ARC700 series
+//
- *
+// Linux performance counter support for ARC CPUs.
- * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com)
+// This code is inspired by the perf support of various other architectures.
- *
+//
- * This code is inspired by the perf support of various other architectures.
+// Copyright (C) 2013-2018 Synopsys, Inc. (www.synopsys.com)
- *
+
- * 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.
- *
- */
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -19,12 +14,31 @@
 #include <asm/arcregs.h>
 #include <asm/stacktrace.h>
 
+/* HW holds 8 symbols + one for null terminator */
+#define ARCPMU_EVENT_NAME_LEN	9
+
+enum arc_pmu_attr_groups {
+	ARCPMU_ATTR_GR_EVENTS,
+	ARCPMU_ATTR_GR_FORMATS,
+	ARCPMU_NR_ATTR_GR
+};
+
+struct arc_pmu_raw_event_entry {
+	char name[ARCPMU_EVENT_NAME_LEN];
+};
+
 struct arc_pmu {
 	struct pmu	pmu;
 	unsigned int	irq;
 	int		n_counters;
+	int		n_events;
 	u64		max_period;
 	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
+
+	struct arc_pmu_raw_event_entry	*raw_entry;
+	struct attribute		**attrs;
+	struct perf_pmu_events_attr	*attr;
+	const struct attribute_group	*attr_groups[ARCPMU_NR_ATTR_GR + 1];
 };
 
 struct arc_pmu_cpu {
@@ -49,6 +63,7 @@ static int callchain_trace(unsigned int addr, void *data)
 {
 	struct arc_callchain_trace *ctrl = data;
 	struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
+
 	perf_callchain_store(entry, addr);
 
 	if (ctrl->depth++ < 3)
@@ -57,8 +72,8 @@ static int callchain_trace(unsigned int addr, void *data)
 	return -1;
 }
 
-void
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
-perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+			   struct pt_regs *regs)
 {
 	struct arc_callchain_trace ctrl = {
 		.depth = 0,
@@ -68,8 +83,8 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	arc_unwind_core(NULL, regs, callchain_trace, &ctrl);
 }
 
-void
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
-perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+			 struct pt_regs *regs)
 {
 	/*
 	 * User stack can't be unwound trivially with kernel dwarf unwinder
@@ -82,10 +97,10 @@ static struct arc_pmu *arc_pmu;
 static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);
 
 /* read counter #idx; note that counter# != event# on ARC! */
-static uint64_t arc_pmu_read_counter(int idx)
+static u64 arc_pmu_read_counter(int idx)
 {
-	uint32_t tmp;
+	u32 tmp;
-	uint64_t result;
+	u64 result;
 
 	/*
 	 * ARC supports making 'snapshots' of the counters, so we don't
@@ -94,7 +109,7 @@ static uint64_t arc_pmu_read_counter(int idx)
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
-	result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
+	result = (u64) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
 	result |= read_aux_reg(ARC_REG_PCT_SNAPL);
 
 	return result;
@@ -103,9 +118,9 @@ static uint64_t arc_pmu_read_counter(int idx)
 static void arc_perf_event_update(struct perf_event *event,
 				  struct hw_perf_event *hwc, int idx)
 {
-	uint64_t prev_raw_count = local64_read(&hwc->prev_count);
+	u64 prev_raw_count = local64_read(&hwc->prev_count);
-	uint64_t new_raw_count = arc_pmu_read_counter(idx);
+	u64 new_raw_count = arc_pmu_read_counter(idx);
-	int64_t delta = new_raw_count - prev_raw_count;
+	s64 delta = new_raw_count - prev_raw_count;
 
 	/*
 	 * We aren't afraid of hwc->prev_count changing beneath our feet
@@ -155,7 +170,7 @@ static int arc_pmu_event_init(struct perf_event *event)
 	int ret;
 
 	if (!is_sampling_event(event)) {
-		hwc->sample_period  = arc_pmu->max_period;
+		hwc->sample_period = arc_pmu->max_period;
 		hwc->last_period = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -192,6 +207,18 @@ static int arc_pmu_event_init(struct perf_event *event)
 		pr_debug("init cache event with h/w %08x \'%s\'\n",
 			 (int)hwc->config, arc_pmu_ev_hw_map[ret]);
 		return 0;
+
+	case PERF_TYPE_RAW:
+		if (event->attr.config >= arc_pmu->n_events)
+			return -ENOENT;
+
+		hwc->config |= event->attr.config;
+		pr_debug("init raw event with idx %lld \'%s\'\n",
+			 event->attr.config,
+			 arc_pmu->raw_entry[event->attr.config].name);
+
+		return 0;
+
 	default:
 		return -ENOENT;
 	}
@@ -200,7 +227,7 @@ static int arc_pmu_event_init(struct perf_event *event)
 /* starts all counters */
 static void arc_pmu_enable(struct pmu *pmu)
 {
-	uint32_t tmp;
+	u32 tmp;
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
 }
@@ -208,7 +235,7 @@ static void arc_pmu_enable(struct pmu *pmu)
 /* stops all counters */
 static void arc_pmu_disable(struct pmu *pmu)
 {
-	uint32_t tmp;
+	u32 tmp;
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
 }
@@ -228,7 +255,7 @@ static int arc_pmu_event_set_period(struct perf_event *event)
 		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		overflow = 1;
-	} else	if (unlikely(left <= 0)) {
+	} else if (unlikely(left <= 0)) {
 		/* left underflowed by less than period. */
 		left += period;
 		local64_set(&hwc->period_left, left);
@@ -246,8 +273,8 @@ static int arc_pmu_event_set_period(struct perf_event *event)
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);
 
 	/* Write value */
-	write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value);
+	write_aux_reg(ARC_REG_PCT_COUNTL, lower_32_bits(value));
-	write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32));
+	write_aux_reg(ARC_REG_PCT_COUNTH, upper_32_bits(value));
 
 	perf_event_update_userpage(event);
 
@@ -277,7 +304,7 @@ static void arc_pmu_start(struct perf_event *event, int flags)
 	/* Enable interrupt for this counter */
 	if (is_sampling_event(event))
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
 
 	/* enable ARC pmu here */
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);		/* counter # */
@@ -295,9 +322,9 @@ static void arc_pmu_stop(struct perf_event *event, int flags)
 		 * Reset interrupt flag by writing of 1. This is required
 		 * to make sure pending interrupt was not left.
 		 */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx));
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~BIT(idx));
 	}
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -349,9 +376,10 @@ static int arc_pmu_add(struct perf_event *event, int flags)
 
 	if (is_sampling_event(event)) {
 		/* Mimic full counter overflow as other arches do */
-		write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period);
+		write_aux_reg(ARC_REG_PCT_INT_CNTL,
+			      lower_32_bits(arc_pmu->max_period));
 		write_aux_reg(ARC_REG_PCT_INT_CNTH,
-			      (arc_pmu->max_period >> 32));
+			      upper_32_bits(arc_pmu->max_period));
 	}
 
 	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
@@ -392,7 +420,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 		idx = __ffs(active_ints);
 
 		/* Reset interrupt flag by writing of 1 */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
 
 		/*
 		 * On reset of "interrupt active" bit corresponding
@@ -400,7 +428,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 		 * Now we need to re-enable interrupt for the counter.
 		 */
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+			read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
 
 		event = pmu_cpu->act_counter[idx];
 		hwc = &event->hw;
@@ -414,7 +442,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 				arc_pmu_stop(event, 0);
 		}
 
-		active_ints &= ~(1U << idx);
+		active_ints &= ~BIT(idx);
 	} while (active_ints);
 
 done:
@@ -441,19 +469,108 @@ static void arc_cpu_pmu_irq_init(void *data)
 	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
 }
 
+/* Event field occupies the bottom 15 bits of our config field */
+PMU_FORMAT_ATTR(event, "config:0-14");
+static struct attribute *arc_pmu_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group arc_pmu_format_attr_gr = {
+	.name = "format",
+	.attrs = arc_pmu_format_attrs,
+};
+
+static ssize_t arc_pmu_events_sysfs_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+/*
+ * We don't add attrs here as we don't have pre-defined list of perf events.
+ * We will generate and add attrs dynamically in probe() after we read HW
+ * configuration.
+ */
+static struct attribute_group arc_pmu_events_attr_gr = {
+	.name = "events",
+};
+
+static void arc_pmu_add_raw_event_attr(int j, char *str)
+{
+	memmove(arc_pmu->raw_entry[j].name, str, ARCPMU_EVENT_NAME_LEN - 1);
+	arc_pmu->attr[j].attr.attr.name = arc_pmu->raw_entry[j].name;
+	arc_pmu->attr[j].attr.attr.mode = VERIFY_OCTAL_PERMISSIONS(0444);
+	arc_pmu->attr[j].attr.show = arc_pmu_events_sysfs_show;
+	arc_pmu->attr[j].id = j;
+	arc_pmu->attrs[j] = &(arc_pmu->attr[j].attr.attr);
+}
+
+static int arc_pmu_raw_alloc(struct device *dev)
+{
+	arc_pmu->attr = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attr), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attr)
+		return -ENOMEM;
+
+	arc_pmu->attrs = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attrs), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attrs)
+		return -ENOMEM;
+
+	arc_pmu->raw_entry = devm_kmalloc_array(dev, arc_pmu->n_events,
+		sizeof(*arc_pmu->raw_entry), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->raw_entry)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline bool event_in_hw_event_map(int i, char *name)
+{
+	if (!arc_pmu_ev_hw_map[i])
+		return false;
+
+	if (!strlen(arc_pmu_ev_hw_map[i]))
+		return false;
+
+	if (strcmp(arc_pmu_ev_hw_map[i], name))
+		return false;
+
+	return true;
+}
+
+static void arc_pmu_map_hw_event(int j, char *str)
+{
+	int i;
+
+	/* See if HW condition has been mapped to a perf event_id */
+	for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
+		if (event_in_hw_event_map(i, str)) {
+			pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
+				 i, str, j);
+			arc_pmu->ev_hw_idx[i] = j;
+		}
+	}
+}
+
 static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, j, has_interrupts;
+	int i, has_interrupts;
 	int counter_size;	/* in bits */
 
 	union cc_name {
 		struct {
-			uint32_t word0, word1;
+			u32 word0, word1;
 			char sentinel;
 		} indiv;
-		char str[9];
+		char str[ARCPMU_EVENT_NAME_LEN];
 	} cc_name;
 
 
@@ -463,15 +580,22 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 	BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
-	BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
+	if (WARN_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS))
+		return -EINVAL;
 
 	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
-	BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */
+	if (WARN(!cc_bcr.v, "Counters exist but No countable conditions?"))
+		return -EINVAL;
 
 	arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
 	if (!arc_pmu)
 		return -ENOMEM;
 
+	arc_pmu->n_events = cc_bcr.c;
+
+	if (arc_pmu_raw_alloc(&pdev->dev))
+		return -ENOMEM;
+
 	has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;
 
 	arc_pmu->n_counters = pct_bcr.c;
@@ -481,30 +605,26 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 	pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
 		arc_pmu->n_counters, counter_size, cc_bcr.c,
-		has_interrupts ? ", [overflow IRQ support]":"");
+		has_interrupts ? ", [overflow IRQ support]" : "");
 
-	cc_name.str[8] = 0;
+	cc_name.str[ARCPMU_EVENT_NAME_LEN - 1] = 0;
 	for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
 		arc_pmu->ev_hw_idx[i] = -1;
 
 	/* loop thru all available h/w condition indexes */
-	for (j = 0; j < cc_bcr.c; j++) {
+	for (i = 0; i < cc_bcr.c; i++) {
-		write_aux_reg(ARC_REG_CC_INDEX, j);
+		write_aux_reg(ARC_REG_CC_INDEX, i);
 		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
 		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
 
-		/* See if it has been mapped to a perf event_id */
+		arc_pmu_map_hw_event(i, cc_name.str);
-		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
+		arc_pmu_add_raw_event_attr(i, cc_name.str);
-			if (arc_pmu_ev_hw_map[i] &&
-			    !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
-			    strlen(arc_pmu_ev_hw_map[i])) {
-				pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
-					 i, cc_name.str, j);
-				arc_pmu->ev_hw_idx[i] = j;
-			}
-		}
 	}
 
+	arc_pmu_events_attr_gr.attrs = arc_pmu->attrs;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_EVENTS] = &arc_pmu_events_attr_gr;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_FORMATS] = &arc_pmu_format_attr_gr;
+
 	arc_pmu->pmu = (struct pmu) {
 		.pmu_enable	= arc_pmu_enable,
 		.pmu_disable	= arc_pmu_disable,
@@ -514,6 +634,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.start		= arc_pmu_start,
 		.stop		= arc_pmu_stop,
 		.read		= arc_pmu_read,
+		.attr_groups	= arc_pmu->attr_groups,
 	};
 
 	if (has_interrupts) {
@@ -535,17 +656,19 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
-	return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
+	/*
+	 * perf parser doesn't really like '-' symbol in events name, so let's
+	 * use '_' in arc pct name as it goes to kernel PMU event prefix.
+	 */
+	return perf_pmu_register(&arc_pmu->pmu, "arc_pct", PERF_TYPE_RAW);
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id arc_pmu_match[] = {
 	{ .compatible = "snps,arc700-pct" },
 	{ .compatible = "snps,archs-pct" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, arc_pmu_match);
-#endif
 
 static struct platform_driver arc_pmu_driver = {
 	.driver	= {

arch/arc/kernel/setup.c

@@ -123,6 +123,7 @@ static void read_arc_build_cfg_regs(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	const struct id_to_str *tbl;
 	struct bcr_isa_arcv2 isa;
+	struct bcr_actionpoint ap;
 
 	FIX_PTR(cpu);
 
@@ -195,6 +196,7 @@ static void read_arc_build_cfg_regs(void)
 		cpu->bpu.full = bpu.ft;
 		cpu->bpu.num_cache = 256 << bpu.bce;
 		cpu->bpu.num_pred = 2048 << bpu.pte;
+		cpu->bpu.ret_stk = 4 << bpu.rse;
 
 		if (cpu->core.family >= 0x54) {
 			unsigned int exec_ctrl;
@@ -207,8 +209,11 @@ static void read_arc_build_cfg_regs(void)
 		}
 	}
 
-	READ_BCR(ARC_REG_AP_BCR, bcr);
+	READ_BCR(ARC_REG_AP_BCR, ap);
-	cpu->extn.ap = bcr.ver ? 1 : 0;
+	if (ap.ver) {
+		cpu->extn.ap_num = 2 << ap.num;
+		cpu->extn.ap_full = !!ap.min;
+	}
 
 	READ_BCR(ARC_REG_SMART_BCR, bcr);
 	cpu->extn.smart = bcr.ver ? 1 : 0;
@@ -216,8 +221,6 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(ARC_REG_RTT_BCR, bcr);
 	cpu->extn.rtt = bcr.ver ? 1 : 0;
 
-	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
-
 	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
 
 	/* some hacks for lack of feature BCR info in old ARC700 cores */
@@ -299,10 +302,10 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 
 	if (cpu->bpu.ver)
 		n += scnprintf(buf + n, len - n,
-			      "BPU\t\t: %s%s match, cache:%d, Predict Table:%d",
+			      "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d",
 			      IS_AVAIL1(cpu->bpu.full, "full"),
 			      IS_AVAIL1(!cpu->bpu.full, "partial"),
-			      cpu->bpu.num_cache, cpu->bpu.num_pred);
+			      cpu->bpu.num_cache, cpu->bpu.num_pred, cpu->bpu.ret_stk);
 
 	if (is_isa_arcv2()) {
 		struct bcr_lpb lpb;
@@ -336,11 +339,17 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 			       IS_AVAIL1(cpu->extn.fpu_sp, "SP "),
 			       IS_AVAIL1(cpu->extn.fpu_dp, "DP "));
 
-	if (cpu->extn.debug)
+	if (cpu->extn.ap_num | cpu->extn.smart | cpu->extn.rtt) {
-		n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s%s\n",
+		n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s",
-			       IS_AVAIL1(cpu->extn.ap, "ActionPoint "),
 			       IS_AVAIL1(cpu->extn.smart, "smaRT "),
 			       IS_AVAIL1(cpu->extn.rtt, "RTT "));
+		if (cpu->extn.ap_num) {
+			n += scnprintf(buf + n, len - n, "ActionPoint %d/%s",
+				       cpu->extn.ap_num,
+				       cpu->extn.ap_full ? "full":"min");
+		}
+		n += scnprintf(buf + n, len - n, "\n");
+	}
 
 	if (cpu->dccm.sz || cpu->iccm.sz)
 		n += scnprintf(buf + n, len - n, "Extn [CCM]\t: DCCM @ %x, %d KB / ICCM: @ %x, %d KB\n",

arch/arc/kernel/troubleshoot.c

@@ -18,6 +18,8 @@
 #include <asm/arcregs.h>
 #include <asm/irqflags.h>
 
+#define ARC_PATH_MAX	256
+
 /*
  * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
  *   -Prints 3 regs per line and a CR.
@@ -58,11 +60,12 @@ static void show_callee_regs(struct callee_regs *cregs)
 	print_reg_file(&(cregs->r13), 13);
 }
 
-static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
+static void print_task_path_n_nm(struct task_struct *tsk)
 {
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
+	char buf[ARC_PATH_MAX];
 
 	mm = get_task_mm(tsk);
 	if (!mm)
@@ -72,7 +75,7 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 	mmput(mm);
 
 	if (exe_file) {
-		path_nm = file_path(exe_file, buf, 255);
+		path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1);
 		fput(exe_file);
 	}
 
@@ -80,10 +83,9 @@ done:
 	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
 }
 
-static void show_faulting_vma(unsigned long address, char *buf)
+static void show_faulting_vma(unsigned long address)
 {
 	struct vm_area_struct *vma;
-	char *nm = buf;
 	struct mm_struct *active_mm = current->active_mm;
 
 	/* can't use print_vma_addr() yet as it doesn't check for
@@ -96,8 +98,11 @@ static void show_faulting_vma(unsigned long address, char *buf)
 	 * if the container VMA is not found
 	 */
 	if (vma && (vma->vm_start <= address)) {
+		char buf[ARC_PATH_MAX];
+		char *nm = "?";
+
 		if (vma->vm_file) {
-			nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
+			nm = file_path(vma->vm_file, buf, ARC_PATH_MAX-1);
 			if (IS_ERR(nm))
 				nm = "?";
 		}
@@ -173,13 +178,14 @@ void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
 	struct callee_regs *cregs;
-	char *buf;
 
-	buf = (char *)__get_free_page(GFP_KERNEL);
+	/*
-	if (!buf)
+	 * generic code calls us with preemption disabled, but some calls
-		return;
+	 * here could sleep, so re-enable to avoid lockdep splat
+	 */
+	preempt_enable();
 
-	print_task_path_n_nm(tsk, buf);
+	print_task_path_n_nm(tsk);
 	show_regs_print_info(KERN_INFO);
 
 	show_ecr_verbose(regs);
@@ -189,7 +195,7 @@ void show_regs(struct pt_regs *regs)
 		(void *)regs->blink, (void *)regs->ret);
 
 	if (user_mode(regs))
-		show_faulting_vma(regs->ret, buf); /* faulting code, not data */
+		show_faulting_vma(regs->ret); /* faulting code, not data */
 
 	pr_info("[STAT32]: 0x%08lx", regs->status32);
 
@@ -222,7 +228,7 @@ void show_regs(struct pt_regs *regs)
 	if (cregs)
 		show_callee_regs(cregs);
 
-	free_page((unsigned long)buf);
+	preempt_disable();
 }
 
 void show_kernel_fault_diag(const char *str, struct pt_regs *regs,

arch/arc/lib/memset-archs.S

@@ -7,11 +7,39 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/cache.h>
 
-#undef PREALLOC_NOT_AVAIL
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR	reg, off
+	prealloc	[\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+	prefetchw	[\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR
+.endm
+
+.macro PREFETCHW_INSTR
+.endm
+
+#endif
 
 ENTRY_CFI(memset)
-	prefetchw [r0]		; Prefetch the write location
+	PREFETCHW_INSTR	r0, 0	; Prefetch the first write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -48,11 +76,8 @@ ENTRY_CFI(memset)
 
 	lpnz	@.Lset64bytes
 	;; LOOP START
-#ifdef PREALLOC_NOT_AVAIL
+	PREALLOC_INSTR	r3, 64	; alloc next line w/o fetching
-	prefetchw [r3, 64]	;Prefetch the next write location
+
-#else
-	prealloc  [r3, 64]
-#endif
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -85,7 +110,6 @@ ENTRY_CFI(memset)
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
-	prefetchw   [r3, 32]	;Prefetch the next write location
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]

arch/arc/mm/fault.c

@@ -141,12 +141,17 @@ good_area:
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
 	if (fatal_signal_pending(current)) {
-		if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
+
-			up_read(&mm->mmap_sem);
+		/*
-		if (user_mode(regs))
+		 * if fault retry, mmap_sem already relinquished by core mm
+		 * so OK to return to user mode (with signal handled first)
+		 */
+		if (fault & VM_FAULT_RETRY) {
+			if (!user_mode(regs))
+				goto no_context;
 			return;
+		}
 	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

arch/arc/mm/init.c

@@ -119,7 +119,8 @@ void __init setup_arch_memory(void)
 	 */
 
 	memblock_add_node(low_mem_start, low_mem_sz, 0);
-	memblock_reserve(low_mem_start, __pa(_end) - low_mem_start);
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (phys_initrd_size) {

arch/arm/include/asm/xen/page-coherent.h

@@ -1 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
+
+static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dev_dma_ops)
+		return dev->archdata.dev_dma_ops;
+	return get_arch_dma_ops(NULL);
+}
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+	return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+	xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (local)
+		xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->unmap_page)
+			xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+	} else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
+			xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->sync_single_for_device)
+			xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

arch/arm/mach-cns3xxx/pcie.c

@@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus,
 	} else /* remote PCI bus */
 		base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
 
-	return base + (where & 0xffc) + (devfn << 12);
+	return base + where + (devfn << 12);
 }
 
 static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
@@ -93,7 +93,7 @@ static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
 	u32 mask = (0x1ull << (size * 8)) - 1;
 	int shift = (where % 4) * 8;
 
-	ret = pci_generic_config_read32(bus, devfn, where, size, val);
+	ret = pci_generic_config_read(bus, devfn, where, size, val);
 
 	if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn &&
 	    (where & 0xffc) == PCI_CLASS_REVISION)

arch/arm64/include/asm/cache.h

@@ -60,8 +60,6 @@
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
-#else
-#define ARCH_SLAB_MINALIGN	__alignof__(unsigned long long)
 #endif
 
 #ifndef __ASSEMBLY__

arch/arm64/include/asm/device.h

@@ -20,9 +20,6 @@ struct dev_archdata {
 #ifdef CONFIG_IOMMU_API
 	void *iommu;			/* private IOMMU data */
 #endif
-#ifdef CONFIG_XEN
-	const struct dma_map_ops *dev_dma_ops;
-#endif
 };
 
 struct pdev_archdata {

arch/arm64/include/asm/mmu.h

@@ -60,8 +60,11 @@ static inline bool arm64_kernel_use_ng_mappings(void)
 	 * later determine that kpti is required, then
 	 * kpti_install_ng_mappings() will make them non-global.
 	 */
+	if (arm64_kernel_unmapped_at_el0())
+		return true;
+
 	if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return arm64_kernel_unmapped_at_el0();
+		return false;
 
 	/*
 	 * KASLR is enabled so we're going to be enabling kpti on non-broken

arch/arm64/include/asm/xen/page-coherent.h

@@ -1 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
+#define _ASM_ARM64_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	if (local)
+		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (pfn_valid(pfn))
+		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+	else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */

arch/arm64/kernel/hibernate.c

@@ -299,8 +299,10 @@ int swsusp_arch_suspend(void)
 		dcache_clean_range(__idmap_text_start, __idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
-		if (el2_reset_needed())
+		if (el2_reset_needed()) {
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+		}
 
 		/* make the crash dump kernel image protected again */
 		crash_post_resume();

arch/arm64/kernel/hyp-stub.S

@@ -28,6 +28,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)

arch/arm64/kernel/kaslr.c

@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
@@ -43,7 +44,7 @@ static __init u64 get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
 {
 	static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
 
@@ -87,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -109,7 +111,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	cmdline = get_cmdline(fdt);
+	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
 	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
 		return 0;
@@ -169,5 +171,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
 	return offset;
 }

arch/arm64/kernel/probes/kprobes.c

@@ -478,13 +478,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
 	    addr < (unsigned long)__entry_text_end) ||
 	    (addr >= (unsigned long)__idmap_text_start &&
 	    addr < (unsigned long)__idmap_text_end) ||
+	    (addr >= (unsigned long)__hyp_text_start &&
+	    addr < (unsigned long)__hyp_text_end) ||
 	    !!search_exception_tables(addr))
 		return true;
 
 	if (!is_kernel_in_hyp_mode()) {
-		if ((addr >= (unsigned long)__hyp_text_start &&
+		if ((addr >= (unsigned long)__hyp_idmap_text_start &&
-		    addr < (unsigned long)__hyp_text_end) ||
-		    (addr >= (unsigned long)__hyp_idmap_text_start &&
 		    addr < (unsigned long)__hyp_idmap_text_end))
 			return true;
 	}

arch/arm64/mm/dma-mapping.c

@@ -466,9 +466,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
+	if (xen_initial_domain())
-		dev->archdata.dev_dma_ops = dev->dma_ops;
 		dev->dma_ops = xen_dma_ops;
-	}
 #endif
 }

arch/arm64/mm/flush.c

@@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, unsigned long len)
 		__clean_dcache_area_pou(kaddr, len);
 		__flush_icache_all();
 	} else {
-		flush_icache_range(addr, addr + len);
+		/*
+		 * Don't issue kick_all_cpus_sync() after I-cache invalidation
+		 * for user mappings.
+		 */
+		__flush_icache_range(addr, addr + len);
 	}
 }
 

arch/c6x/include/asm/Kbuild

@@ -30,6 +30,7 @@ generic-y += pgalloc.h
 generic-y += preempt.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += tlbflush.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/c6x/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/h8300/include/asm/Kbuild

@@ -40,6 +40,7 @@ generic-y += preempt.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += spinlock.h
 generic-y += timex.h

arch/h8300/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/hexagon/include/asm/Kbuild

@@ -30,6 +30,7 @@ generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/hexagon/include/uapi/asm/Kbuild

@@ -1,4 +1,3 @@
 include include/uapi/asm-generic/Kbuild.asm
 
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/m68k/include/asm/Kbuild

@@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += sections.h
+generic-y += shmparam.h
 generic-y += spinlock.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/m68k/include/uapi/asm/Kbuild

@@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h

arch/microblaze/include/asm/Kbuild

@@ -26,6 +26,7 @@ generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += syscalls.h
 generic-y += topology.h
 generic-y += trace_clock.h

arch/microblaze/include/uapi/asm/Kbuild

@@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/mips/Kconfig

@@ -3155,6 +3155,7 @@ config MIPS32_O32
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
 	depends on 64BIT
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select COMPAT
 	select MIPS32_COMPAT
 	select SYSVIPC_COMPAT if SYSVIPC

arch/mips/bcm47xx/setup.c

@@ -173,6 +173,31 @@ void __init plat_mem_setup(void)
 	pm_power_off = bcm47xx_machine_halt;
 }
 
+#ifdef CONFIG_BCM47XX_BCMA
+static struct device * __init bcm47xx_setup_device(void)
+{
+	struct device *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	err = dev_set_name(dev, "bcm47xx_soc");
+	if (err) {
+		pr_err("Failed to set SoC device name: %d\n", err);
+		kfree(dev);
+		return NULL;
+	}
+
+	err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (err)
+		pr_err("Failed to set SoC DMA mask: %d\n", err);
+
+	return dev;
+}
+#endif
+
 /*
  * This finishes bus initialization doing things that were not possible without
  * kmalloc. Make sure to call it late enough (after mm_init).
@@ -183,6 +208,10 @@ void __init bcm47xx_bus_setup(void)
 	if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) {
 		int err;
 
+		bcm47xx_bus.bcma.dev = bcm47xx_setup_device();
+		if (!bcm47xx_bus.bcma.dev)
+			panic("Failed to setup SoC device\n");
+
 		err = bcma_host_soc_init(&bcm47xx_bus.bcma);
 		if (err)
 			panic("Failed to initialize BCMA bus (err %d)", err);
@@ -235,6 +264,8 @@ static int __init bcm47xx_register_bus_complete(void)
 #endif
 #ifdef CONFIG_BCM47XX_BCMA
 	case BCM47XX_BUS_TYPE_BCMA:
+		if (device_register(bcm47xx_bus.bcma.dev))
+			pr_err("Failed to register SoC device\n");
 		bcma_bus_register(&bcm47xx_bus.bcma.bus);
 		break;
 #endif

arch/mips/cavium-octeon/setup.c

@@ -98,7 +98,7 @@ static void octeon_kexec_smp_down(void *ignored)
 	"	sync						\n"
 	"	synci	($0)					\n");
 
-	relocated_kexec_smp_wait(NULL);
+	kexec_reboot();
 }
 #endif
 

arch/mips/configs/ath79_defconfig

@@ -66,6 +66,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_SERIAL_8250_PCI is not set
 CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AR933X=y
 CONFIG_SERIAL_AR933X_CONSOLE=y
 # CONFIG_HW_RANDOM is not set

arch/mips/include/asm/mach-lantiq/falcon/falcon_irq.h

@@ -18,8 +18,6 @@
 #define INT_NUM_EXTRA_START		(INT_NUM_IM4_IRL0 + 32)
 #define INT_NUM_IM_OFFSET		(INT_NUM_IM1_IRL0 - INT_NUM_IM0_IRL0)
 
-#define MIPS_CPU_TIMER_IRQ			7
-
 #define MAX_IM			5
 
 #endif /* _FALCON_IRQ__ */

arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h

@@ -19,8 +19,6 @@
 
 #define LTQ_DMA_CH0_INT		(INT_NUM_IM2_IRL0)
 
-#define MIPS_CPU_TIMER_IRQ	7
-
 #define MAX_IM			5
 
 #endif

arch/mips/jazz/jazzdma.c

@@ -74,14 +74,15 @@ static int __init vdma_init(void)
 						    get_order(VDMA_PGTBL_SIZE));
 	BUG_ON(!pgtbl);
 	dma_cache_wback_inv((unsigned long)pgtbl, VDMA_PGTBL_SIZE);
-	pgtbl = (VDMA_PGTBL_ENTRY *)KSEG1ADDR(pgtbl);
+	pgtbl = (VDMA_PGTBL_ENTRY *)CKSEG1ADDR((unsigned long)pgtbl);
 
 	/*
 	 * Clear the R4030 translation table
 	 */
 	vdma_pgtbl_init();
 
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE, CPHYSADDR(pgtbl));
+	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE,
+			  CPHYSADDR((unsigned long)pgtbl));
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_LIM, VDMA_PGTBL_SIZE);
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
 

arch/mips/lantiq/irq.c

@@ -224,9 +224,11 @@ static struct irq_chip ltq_eiu_type = {
 	.irq_set_type = ltq_eiu_settype,
 };
 
-static void ltq_hw_irqdispatch(int module)
+static void ltq_hw_irq_handler(struct irq_desc *desc)
 {
+	int module = irq_desc_get_irq(desc) - 2;
 	u32 irq;
+	int hwirq;
 
 	irq = ltq_icu_r32(module, LTQ_ICU_IM0_IOSR);
 	if (irq == 0)
@@ -237,7 +239,8 @@ static void ltq_hw_irqdispatch(int module)
 	 * other bits might be bogus
 	 */
 	irq = __fls(irq);
-	do_IRQ((int)irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module));
+	hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module);
+	generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq));
 
 	/* if this is a EBU irq, we need to ack it or get a deadlock */
 	if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT)
@@ -245,49 +248,6 @@ static void ltq_hw_irqdispatch(int module)
 			LTQ_EBU_PCC_ISTAT);
 }
 
-#define DEFINE_HWx_IRQDISPATCH(x)					\
-	static void ltq_hw ## x ## _irqdispatch(void)			\
-	{								\
-		ltq_hw_irqdispatch(x);					\
-	}
-DEFINE_HWx_IRQDISPATCH(0)
-DEFINE_HWx_IRQDISPATCH(1)
-DEFINE_HWx_IRQDISPATCH(2)
-DEFINE_HWx_IRQDISPATCH(3)
-DEFINE_HWx_IRQDISPATCH(4)
-
-#if MIPS_CPU_TIMER_IRQ == 7
-static void ltq_hw5_irqdispatch(void)
-{
-	do_IRQ(MIPS_CPU_TIMER_IRQ);
-}
-#else
-DEFINE_HWx_IRQDISPATCH(5)
-#endif
-
-static void ltq_hw_irq_handler(struct irq_desc *desc)
-{
-	ltq_hw_irqdispatch(irq_desc_get_irq(desc) - 2);
-}
-
-asmlinkage void plat_irq_dispatch(void)
-{
-	unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
-	int irq;
-
-	if (!pending) {
-		spurious_interrupt();
-		return;
-	}
-
-	pending >>= CAUSEB_IP;
-	while (pending) {
-		irq = fls(pending) - 1;
-		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
-		pending &= ~BIT(irq);
-	}
-}
-
 static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 {
 	struct irq_chip *chip = &ltq_irq_type;
@@ -343,38 +303,13 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent)
 	for (i = 0; i < MAX_IM; i++)
 		irq_set_chained_handler(i + 2, ltq_hw_irq_handler);
 
-	if (cpu_has_vint) {
-		pr_info("Setting up vectored interrupts\n");
-		set_vi_handler(2, ltq_hw0_irqdispatch);
-		set_vi_handler(3, ltq_hw1_irqdispatch);
-		set_vi_handler(4, ltq_hw2_irqdispatch);
-		set_vi_handler(5, ltq_hw3_irqdispatch);
-		set_vi_handler(6, ltq_hw4_irqdispatch);
-		set_vi_handler(7, ltq_hw5_irqdispatch);
-	}
-
 	ltq_domain = irq_domain_add_linear(node,
 		(MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE,
 		&irq_domain_ops, 0);
 
-#ifndef CONFIG_MIPS_MT_SMP
-	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
-		IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#else
-	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 |
-		IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#endif
-
 	/* tell oprofile which irq to use */
 	ltq_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ);
 
-	/*
-	 * if the timer irq is not one of the mips irqs we need to
-	 * create a mapping
-	 */
-	if (MIPS_CPU_TIMER_IRQ != 7)
-		irq_create_mapping(ltq_domain, MIPS_CPU_TIMER_IRQ);
-
 	/* the external interrupts are optional and xway only */
 	eiu_node = of_find_compatible_node(NULL, NULL, "lantiq,eiu-xway");
 	if (eiu_node && !of_address_to_resource(eiu_node, 0, &res)) {
@@ -411,7 +346,7 @@ EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
-	return MIPS_CPU_TIMER_IRQ;
+	return CP0_LEGACY_COMPARE_IRQ;
 }
 
 static struct of_device_id __initdata of_irq_ids[] = {

arch/mips/pci/msi-octeon.c

@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
 	int irq;
 	struct irq_chip *msi;
 
-	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+		return 0;
+	} else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
 		msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
 		msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
 		msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;

arch/openrisc/include/asm/Kbuild

@@ -34,6 +34,7 @@ generic-y += qrwlock_types.h
 generic-y += qrwlock.h
 generic-y += sections.h
 generic-y += segment.h
+generic-y += shmparam.h
 generic-y += string.h
 generic-y += switch_to.h
 generic-y += topology.h

arch/openrisc/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/powerpc/include/uapi/asm/perf_regs.h

@@ -47,6 +47,7 @@ enum perf_event_powerpc_regs {
 	PERF_REG_POWERPC_DAR,
 	PERF_REG_POWERPC_DSISR,
 	PERF_REG_POWERPC_SIER,
+	PERF_REG_POWERPC_MMCRA,
 	PERF_REG_POWERPC_MAX,
 };
 #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */

arch/powerpc/kernel/head_8xx.S

@@ -852,11 +852,12 @@ start_here:
 
 	/* set up the PTE pointers for the Abatron bdiGDB.
 	*/
-	tovirt(r6,r6)
 	lis	r5, abatron_pteptrs@h
 	ori	r5, r5, abatron_pteptrs@l
 	stw	r5, 0xf0(0)	/* Must match your Abatron config file */
 	tophys(r5,r5)
+	lis	r6, swapper_pg_dir@h
+	ori	r6, r6, swapper_pg_dir@l
 	stw	r6, 0(r5)
 
 /* Now turn on the MMU for real! */

arch/powerpc/kernel/signal_64.c

@@ -755,11 +755,12 @@ SYSCALL_DEFINE0(rt_sigreturn)
 		if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
 					   &uc_transact->uc_mcontext))
 			goto badframe;
-	}
+	} else
 #endif
-	/* Fall through, for non-TM restore */
+	{
-	if (!MSR_TM_ACTIVE(msr)) {
 		/*
+		 * Fall through, for non-TM restore
+		 *
 		 * Unset MSR[TS] on the thread regs since MSR from user
 		 * context does not have MSR active, and recheckpoint was
 		 * not called since restore_tm_sigcontexts() was not called

arch/powerpc/kernel/trace/ftrace.c

@@ -967,13 +967,6 @@ out:
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return sys_call_table[nr*2];
-}
-#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
-
 #ifdef PPC64_ELF_ABI_v1
 char *arch_ftrace_match_adjust(char *str, const char *search)
 {

arch/powerpc/perf/perf_regs.c

@@ -70,6 +70,7 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar),
+	PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
 };
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
@@ -83,6 +84,11 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	    !is_sier_available()))
 		return 0;
 
+	if (idx == PERF_REG_POWERPC_MMCRA &&
+	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
+	    IS_ENABLED(CONFIG_PPC32)))
+		return 0;
+
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 

arch/powerpc/platforms/4xx/ocm.c

@@ -237,12 +237,12 @@ static int ocm_debugfs_show(struct seq_file *m, void *v)
 			continue;
 
 		seq_printf(m, "PPC4XX OCM   : %d\n", ocm->index);
-		seq_printf(m, "PhysAddr     : %pa[p]\n", &(ocm->phys));
+		seq_printf(m, "PhysAddr     : %pa\n", &(ocm->phys));
 		seq_printf(m, "MemTotal     : %d Bytes\n", ocm->memtotal);
 		seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal);
 		seq_printf(m, "MemTotal(C)  : %d Bytes\n\n", ocm->c.memtotal);
 
-		seq_printf(m, "NC.PhysAddr  : %pa[p]\n", &(ocm->nc.phys));
+		seq_printf(m, "NC.PhysAddr  : %pa\n", &(ocm->nc.phys));
 		seq_printf(m, "NC.VirtAddr  : 0x%p\n", ocm->nc.virt);
 		seq_printf(m, "NC.MemTotal  : %d Bytes\n", ocm->nc.memtotal);
 		seq_printf(m, "NC.MemFree   : %d Bytes\n", ocm->nc.memfree);
@@ -252,7 +252,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v)
 							blk->size, blk->owner);
 		}
 
-		seq_printf(m, "\nC.PhysAddr   : %pa[p]\n", &(ocm->c.phys));
+		seq_printf(m, "\nC.PhysAddr   : %pa\n", &(ocm->c.phys));
 		seq_printf(m, "C.VirtAddr   : 0x%p\n", ocm->c.virt);
 		seq_printf(m, "C.MemTotal   : %d Bytes\n", ocm->c.memtotal);
 		seq_printf(m, "C.MemFree    : %d Bytes\n", ocm->c.memfree);

arch/powerpc/platforms/chrp/setup.c

@@ -538,8 +538,7 @@ static void __init chrp_init_IRQ(void)
 	/* see if there is a keyboard in the device tree
 	   with a parent of type "adb" */
 	for_each_node_by_name(kbd, "keyboard")
-		if (kbd->parent && kbd->parent->type
+		if (of_node_is_type(kbd->parent, "adb"))
-		    && strcmp(kbd->parent->type, "adb") == 0)
 			break;
 	of_node_put(kbd);
 	if (kbd)

arch/powerpc/platforms/powernv/npu-dma.c

@@ -564,7 +564,7 @@ struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
 		}
 	} else {
 		/* Create a group for 1 GPU and attached NPUs for POWER8 */
-		pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL);
+		pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL);
 		table_group = &pe->npucomp->table_group;
 		table_group->ops = &pnv_npu_peers_ops;
 		iommu_register_group(table_group, hose->global_number,

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -2681,7 +2681,8 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		if (phb->type == PNV_PHB_NPU_NVLINK)
+		if (phb->type == PNV_PHB_NPU_NVLINK ||
+		    phb->type == PNV_PHB_NPU_OCAPI)
 			continue;
 
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {

arch/powerpc/platforms/pseries/pci.c

@@ -264,7 +264,9 @@ void __init pSeries_final_fixup(void)
 			if (!of_device_is_compatible(nvdn->parent,
 						"ibm,power9-npu"))
 				continue;
+#ifdef CONFIG_PPC_POWERNV
 			WARN_ON_ONCE(pnv_npu2_init(hose));
+#endif
 			break;
 		}
 	}

arch/riscv/Kconfig

@@ -103,7 +103,7 @@ choice
 	prompt "Base ISA"
 	default ARCH_RV64I
 	help
-	  This selects the base ISA that this kernel will traget and must match
+	  This selects the base ISA that this kernel will target and must match
 	  the target platform.
 
 config ARCH_RV32I

arch/riscv/configs/defconfig

@@ -13,8 +13,6 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_SMP=y
-CONFIG_PCI=y
-CONFIG_PCIE_XILINX=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_NET=y
@@ -28,6 +26,10 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
 CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
@@ -63,7 +65,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_UAS=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_SIFIVE_PLIC=y
-CONFIG_RAS=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS4_FS=y
@@ -77,5 +78,6 @@ CONFIG_NFS_V4_1=y
 CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_RCU_TRACE is not set

arch/riscv/include/asm/page.h

@@ -80,7 +80,7 @@ typedef struct page *pgtable_t;
 #define __pgd(x)	((pgd_t) { (x) })
 #define __pgprot(x)	((pgprot_t) { (x) })
 
-#ifdef CONFIG_64BITS
+#ifdef CONFIG_64BIT
 #define PTE_FMT "%016lx"
 #else
 #define PTE_FMT "%08lx"

arch/riscv/include/asm/processor.h

@@ -22,7 +22,7 @@
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE >> 1)
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
 
 #define STACK_TOP		TASK_SIZE
 #define STACK_TOP_MAX		STACK_TOP

arch/riscv/kernel/asm-offsets.c

@@ -39,6 +39,7 @@ void asm_offsets(void)
 	OFFSET(TASK_STACK, task_struct, stack);
 	OFFSET(TASK_TI, task_struct, thread_info);
 	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
 	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);

arch/riscv/kernel/entry.S

@@ -144,6 +144,10 @@ _save_context:
 	REG_L x2,  PT_SP(sp)
 	.endm
 
+#if !IS_ENABLED(CONFIG_PREEMPT)
+.set resume_kernel, restore_all
+#endif
+
 ENTRY(handle_exception)
 	SAVE_ALL
 
@@ -228,7 +232,7 @@ ret_from_exception:
 	REG_L s0, PT_SSTATUS(sp)
 	csrc sstatus, SR_SIE
 	andi s0, s0, SR_SPP
-	bnez s0, restore_all
+	bnez s0, resume_kernel
 
 resume_userspace:
 	/* Interrupts must be disabled here so flags are checked atomically */
@@ -250,6 +254,18 @@ restore_all:
 	RESTORE_ALL
 	sret
 
+#if IS_ENABLED(CONFIG_PREEMPT)
+resume_kernel:
+	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
+	bnez s0, restore_all
+need_resched:
+	REG_L s0, TASK_TI_FLAGS(tp)
+	andi s0, s0, _TIF_NEED_RESCHED
+	beqz s0, restore_all
+	call preempt_schedule_irq
+	j need_resched
+#endif
+
 work_pending:
 	/* Enter slow path for supplementary processing */
 	la ra, ret_from_exception

arch/riscv/kernel/setup.c

@@ -181,7 +181,7 @@ static void __init setup_bootmem(void)
 	BUG_ON(mem_size == 0);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = memblock_end_of_DRAM();
+	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();

arch/riscv/kernel/smpboot.c

@@ -57,15 +57,12 @@ void __init setup_smp(void)
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
 		hart = riscv_of_processor_hartid(dn);
-		if (hart < 0) {
+		if (hart < 0)
-			of_node_put(dn);
 			continue;
-		}
 
 		if (hart == cpuid_to_hartid_map(0)) {
 			BUG_ON(found_boot_cpu);
 			found_boot_cpu = 1;
-			of_node_put(dn);
 			continue;
 		}
 
@@ -73,7 +70,6 @@ void __init setup_smp(void)
 		set_cpu_possible(cpuid, true);
 		set_cpu_present(cpuid, true);
 		cpuid++;
-		of_node_put(dn);
 	}
 
 	BUG_ON(!found_boot_cpu);

arch/riscv/mm/init.c

@@ -28,7 +28,8 @@ static void __init zone_sizes_init(void)
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G,
+			(unsigned long) PFN_PHYS(max_low_pfn)));
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 

arch/s390/include/asm/mmu_context.h

@@ -25,7 +25,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	atomic_set(&mm->context.flush_count, 0);
 	mm->context.gmap_asce = 0;
 	mm->context.flush_mm = 0;
-	mm->context.compat_mm = 0;
+	mm->context.compat_mm = test_thread_flag(TIF_31BIT);
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste ||
 		test_thread_flag(TIF_PGSTE) ||
@@ -90,8 +90,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	if (prev == next)
-		return;
 	S390_lowcore.user_asce = next->context.asce;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
 	/* Clear previous user-ASCE from CR1 and CR7 */
@@ -103,7 +101,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__ctl_load(S390_lowcore.vdso_asce, 7, 7);
 		clear_cpu_flag(CIF_ASCE_SECONDARY);
 	}
-	cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+	if (prev != next)
+		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch

arch/s390/kernel/early.c

@@ -63,10 +63,10 @@ static noinline __init void detect_machine_type(void)
 	if (stsi(vmms, 3, 2, 2) || !vmms->count)
 		return;
 
-	/* Running under KVM? If not we assume z/VM */
+	/* Detect known hypervisors */
 	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
-	else
+	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 

arch/s390/kernel/setup.c

@@ -1006,6 +1006,8 @@ void __init setup_arch(char **cmdline_p)
 		pr_info("Linux is running under KVM in 64-bit mode\n");
 	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 64-bit mode\n");
+	else
+		pr_info("Linux is running as a guest in 64-bit mode\n");
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */

arch/s390/kernel/smp.c

@@ -381,8 +381,13 @@ void smp_call_online_cpu(void (*func)(void *), void *data)
  */
 void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
+	struct lowcore *lc = pcpu_devices->lowcore;
+
+	if (pcpu_devices[0].address == stap())
+		lc = &S390_lowcore;
+
 	pcpu_delegate(&pcpu_devices[0], func, data,
-		      pcpu_devices->lowcore->nodat_stack);
+		      lc->nodat_stack);
 }
 
 int smp_find_processor_id(u16 address)
@@ -1166,7 +1171,11 @@ static ssize_t __ref rescan_store(struct device *dev,
 {
 	int rc;
 
+	rc = lock_device_hotplug_sysfs();
+	if (rc)
+		return rc;
 	rc = smp_rescan_cpus();
+	unlock_device_hotplug();
 	return rc ? rc : count;
 }
 static DEVICE_ATTR_WO(rescan);

arch/s390/kernel/vdso.c

@@ -224,10 +224,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	vdso_pages = vdso64_pages;
 #ifdef CONFIG_COMPAT
-	if (is_compat_task()) {
+	mm->context.compat_mm = is_compat_task();
+	if (mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
-		mm->context.compat_mm = 1;
-	}
 #endif
 	/*
 	 * vDSO has a problem and was disabled, just don't "enable" it for

arch/unicore32/include/asm/Kbuild

@@ -28,6 +28,7 @@ generic-y += preempt.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += syscalls.h
 generic-y += topology.h

arch/unicore32/include/uapi/asm/Kbuild

@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h

arch/x86/Kconfig

@@ -198,7 +198,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
-	select PCI_LOCKLESS_CONFIG
+	select PCI_LOCKLESS_CONFIG		if PCI
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB
@@ -446,12 +446,12 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
-config X86_RESCTRL
+config X86_CPU_RESCTRL
-	bool "Resource Control support"
+	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
 	select KERNFS
 	help
-	  Enable Resource Control support.
+	  Enable x86 CPU resource control support.
 
 	  Provide support for the allocation and monitoring of system resources
 	  usage by the CPU.
@@ -617,7 +617,7 @@ config X86_INTEL_QUARK
 
 config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
-	depends on X86 && ACPI
+	depends on X86 && ACPI && PCI
 	select COMMON_CLK
 	select PINCTRL
 	select IOSF_MBI

arch/x86/boot/compressed/head_64.S

@@ -600,6 +600,14 @@ ENTRY(trampoline_32bit_src)
 	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
 	movl	%eax, %cr3
 3:
+	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
+	pushl	%ecx
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+	popl	%ecx
+
 	/* Enable PAE and LA57 (if required) paging modes */
 	movl	$X86_CR4_PAE, %eax
 	cmpl	$0, %edx

arch/x86/boot/compressed/pgtable.h

@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x60
+#define TRAMPOLINE_32BIT_CODE_SIZE	0x70
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 

arch/x86/entry/entry_64_compat.S

@@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat)
 
 	/* Need to switch before accessing the thread stack. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
+	/* In the Xen PV case we already run on the thread stack. */
+	ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq	6*8(%rdi)		/* regs->ss */
@@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat)
 	pushq	3*8(%rdi)		/* regs->cs */
 	pushq	2*8(%rdi)		/* regs->ip */
 	pushq	1*8(%rdi)		/* regs->orig_ax */
-
 	pushq	(%rdi)			/* pt_regs->di */
+.Lint80_keep_stack:
+
 	pushq	%rsi			/* pt_regs->si */
 	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */

arch/x86/include/asm/intel-family.h

@@ -6,7 +6,7 @@
  * "Big Core" Processors (Branded as Core, Xeon, etc...)
  *
  * The "_X" parts are generally the EP and EX Xeons, or the
- * "Extreme" ones, like Broadwell-E.
+ * "Extreme" ones, like Broadwell-E, or Atom microserver.
  *
  * While adding a new CPUID for a new microarchitecture, add a new
  * group to keep logically sorted out in chronological order. Within
@@ -71,6 +71,7 @@
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
 #define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
 #define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
+#define INTEL_FAM6_ATOM_TREMONT_X	0x86 /* Jacobsville */
 
 /* Xeon Phi */
 

arch/x86/include/asm/mmu_context.h

@@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 
 void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+/*
+ * Init a new mm.  Used on mm copies, like at fork()
+ * and on mm's that are brand-new, like at execve().
+ */
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
@@ -228,8 +232,22 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+
+	/* Duplicate the oldmm pkey state in mm: */
+	mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+	mm->context.execute_only_pkey   = oldmm->context.execute_only_pkey;
+#endif
+}
+
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
+	arch_dup_pkeys(oldmm, mm);
 	paravirt_arch_dup_mmap(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }

arch/x86/include/asm/page_64_types.h

@@ -7,7 +7,11 @@
 #endif
 
 #ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
 #define KASAN_STACK_ORDER 1
+#endif
 #else
 #define KASAN_STACK_ORDER 0
 #endif

arch/x86/include/asm/resctrl_sched.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_RESCTRL_SCHED_H
 #define _ASM_X86_RESCTRL_SCHED_H
 
-#ifdef CONFIG_X86_RESCTRL
+#ifdef CONFIG_X86_CPU_RESCTRL
 
 #include <linux/sched.h>
 #include <linux/jump_label.h>
@@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void)
 
 static inline void resctrl_sched_in(void) {}
 
-#endif /* CONFIG_X86_RESCTRL */
+#endif /* CONFIG_X86_CPU_RESCTRL */
 
 #endif /* _ASM_X86_RESCTRL_SCHED_H */

arch/x86/include/asm/uaccess.h

@@ -711,7 +711,7 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 {
 	if (unlikely(!access_ok(ptr,len)))
 		return 0;
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	return 1;
 }
 #define user_access_begin(a,b)	user_access_begin(a,b)

arch/x86/kernel/cpu/Makefile

@@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
-obj-$(CONFIG_X86_RESCTRL)		+= resctrl/
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= resctrl/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 

arch/x86/kernel/cpu/bugs.c

@@ -71,7 +71,7 @@ void __init check_bugs(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology_early();
+	cpu_smt_check_topology();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");

arch/x86/kernel/cpu/microcode/amd.c

@@ -855,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 	if (!p) {
 		return ret;
 	} else {
-		if (boot_cpu_data.microcode == p->patch_id)
+		if (boot_cpu_data.microcode >= p->patch_id)
 			return ret;
 
 		ret = UCODE_NEW;

arch/x86/kernel/cpu/resctrl/Makefile

@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_X86_RESCTRL)	+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
-obj-$(CONFIG_X86_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
 CFLAGS_pseudo_lock.o = -I$(src)

arch/x86/kernel/crash.c

@@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image)
 
 	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret) {
 		vfree((void *)image->arch.elf_headers);

arch/x86/kernel/hpet.c

@@ -21,10 +21,6 @@
 
 #define HPET_MASK			CLOCKSOURCE_MASK(32)
 
-/* FSEC = 10^-15
-   NSEC = 10^-9 */
-#define FSEC_PER_NSEC			1000000L
-
 #define HPET_DEV_USED_BIT		2
 #define HPET_DEV_USED			(1 << HPET_DEV_USED_BIT)
 #define HPET_DEV_VALID			0x8

arch/x86/kernel/kexec-bzimage64.c

@@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	struct efi_info *current_ei = &boot_params.efi_info;
 	struct efi_info *ei = &params->efi_info;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
 	if (!current_ei->efi_memmap_size)
 		return 0;
 
@@ -434,6 +437,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
 	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out_free_params;
@@ -448,6 +452,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out_free_params;

arch/x86/kernel/kvm.c

@@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 #else
 	u64 ipi_bitmap = 0;
 #endif
+	long ret;
 
 	if (cpumask_empty(mask))
 		return;
@@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
 			max = apic_id < max ? max : apic_id;
 		} else {
-			kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 				(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+			WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 			min = max = apic_id;
 			ipi_bitmap = 0;
 		}
@@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 	}
 
 	if (ipi_bitmap) {
-		kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+		ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 			(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+		WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 	}
 
 	local_irq_restore(flags);