Merge branch 'timers/urgent' into timers/core

Pick up urgent bug fix and resolve the conflict.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -375,3 +375,19 @@ Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	information about CPUs heterogeneity.
 
 		cpu_capacity: capacity of cpu#.
+
+What:		/sys/devices/system/cpu/vulnerabilities
+		/sys/devices/system/cpu/vulnerabilities/meltdown
+		/sys/devices/system/cpu/vulnerabilities/spectre_v1
+		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+Date:		January 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Information about CPU vulnerabilities
+
+		The files are named after the code names of CPU
+		vulnerabilities. The output of those files reflects the
+		state of the CPUs in the system. Possible output values:
+
+		"Not affected"	  CPU is not affected by the vulnerability
+		"Vulnerable"	  CPU is affected and no mitigation in effect
+		"Mitigation: $M"  CPU is affected and mitigation $M is in effect

Documentation/admin-guide/kernel-parameters.txt

@@ -713,9 +713,6 @@
 			It will be ignored when crashkernel=X,high is not used
 			or memory reserved is below 4G.
 
-	crossrelease_fullstack
-			[KNL] Allow to record full stack trace in cross-release
-
 	cryptomgr.notests
                         [KNL] Disable crypto self-tests
 
@@ -2626,6 +2623,11 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
+			(indirect branch prediction) vulnerability. System may
+			allow data leaks with this option, which is equivalent
+			to spectre_v2=off.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -2712,8 +2714,6 @@
 			steal time is computed, but won't influence scheduler
 			behaviour
 
-	nopti		[X86-64] Disable kernel page table isolation
-
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
@@ -3100,6 +3100,12 @@
 		pcie_scan_all	Scan all possible PCIe devices.  Otherwise we
 				only look for one device below a PCIe downstream
 				port.
+		big_root_window	Try to add a big 64bit memory window to the PCIe
+				root complex on AMD CPUs. Some GFX hardware
+				can resize a BAR to allow access to all VRAM.
+				Adding the window is slightly risky (it may
+				conflict with unreported devices), so this
+				taints the kernel.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -3288,11 +3294,20 @@
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
-	pti=		[X86_64]
-			Control user/kernel address space isolation:
-			on - enable
-			off - disable
-			auto - default setting
+	pti=		[X86_64] Control Page Table Isolation of user and
+			kernel address spaces.  Disabling this feature
+			removes hardening, but improves performance of
+			system calls and interrupts.
+
+			on   - unconditionally enable
+			off  - unconditionally disable
+			auto - kernel detects whether your CPU model is
+			       vulnerable to issues that PTI mitigates
+
+			Not specifying this option is equivalent to pti=auto.
+
+	nopti		[X86_64]
+			Equivalent to pti=off
 
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
@@ -3943,6 +3958,29 @@
 	sonypi.*=	[HW] Sony Programmable I/O Control Device driver
 			See Documentation/laptops/sonypi.txt
 
+	spectre_v2=	[X86] Control mitigation of Spectre variant 2
+			(indirect branch speculation) vulnerability.
+
+			on   - unconditionally enable
+			off  - unconditionally disable
+			auto - kernel detects whether your CPU model is
+			       vulnerable
+
+			Selecting 'on' will, and 'auto' may, choose a
+			mitigation method at run time according to the
+			CPU, the available microcode, the setting of the
+			CONFIG_RETPOLINE configuration option, and the
+			compiler with which the kernel was built.
+
+			Specific mitigations can also be selected manually:
+
+			retpoline	  - replace indirect branches
+			retpoline,generic - google's original retpoline
+			retpoline,amd     - AMD-specific minimal thunk
+
+			Not specifying this option is equivalent to
+			spectre_v2=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=

Documentation/filesystems/nilfs2.txt

@@ -25,8 +25,8 @@ available from the following download page.  At least "mkfs.nilfs2",
 cleaner or garbage collector) are required.  Details on the tools are
 described in the man pages included in the package.
 
-Project web page:    http://nilfs.sourceforge.net/
-Download page:       http://nilfs.sourceforge.net/en/download.html
+Project web page:    https://nilfs.sourceforge.io/
+Download page:       https://nilfs.sourceforge.io/en/download.html
 List info:           http://vger.kernel.org/vger-lists.html#linux-nilfs
 
 Caveats

Documentation/kbuild/kconfig-language.txt

@@ -200,10 +200,14 @@ module state. Dependency expressions have the following syntax:
 <expr> ::= <symbol>                             (1)
            <symbol> '=' <symbol>                (2)
            <symbol> '!=' <symbol>               (3)
-           '(' <expr> ')'                       (4)
-           '!' <expr>                           (5)
-           <expr> '&&' <expr>                   (6)
-           <expr> '||' <expr>                   (7)
+           <symbol1> '<' <symbol2>              (4)
+           <symbol1> '>' <symbol2>              (4)
+           <symbol1> '<=' <symbol2>             (4)
+           <symbol1> '>=' <symbol2>             (4)
+           '(' <expr> ')'                       (5)
+           '!' <expr>                           (6)
+           <expr> '&&' <expr>                   (7)
+           <expr> '||' <expr>                   (8)
 
 Expressions are listed in decreasing order of precedence. 
 
@@ -214,10 +218,13 @@ Expressions are listed in decreasing order of precedence.
     otherwise 'n'.
 (3) If the values of both symbols are equal, it returns 'n',
     otherwise 'y'.
-(4) Returns the value of the expression. Used to override precedence.
-(5) Returns the result of (2-/expr/).
-(6) Returns the result of min(/expr/, /expr/).
-(7) Returns the result of max(/expr/, /expr/).
+(4) If value of <symbol1> is respectively lower, greater, lower-or-equal,
+    or greater-or-equal than value of <symbol2>, it returns 'y',
+    otherwise 'n'.
+(5) Returns the value of the expression. Used to override precedence.
+(6) Returns the result of (2-/expr/).
+(7) Returns the result of min(/expr/, /expr/).
+(8) Returns the result of max(/expr/, /expr/).
 
 An expression can have a value of 'n', 'm' or 'y' (or 0, 1, 2
 respectively for calculations). A menu entry becomes visible when its

Documentation/networking/index.rst

@@ -9,6 +9,7 @@ Contents:
    batman-adv
    kapi
    z8530book
+   msg_zerocopy
 
 .. only::  subproject
 
@@ -16,4 +17,3 @@ Contents:
    =======
 
    * :ref:`genindex`
-

Documentation/networking/msg_zerocopy.rst

@@ -72,6 +72,10 @@ this flag, a process must first signal intent by setting a socket option:
 	if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &one, sizeof(one)))
 		error(1, errno, "setsockopt zerocopy");
 
+Setting the socket option only works when the socket is in its initial
+(TCP_CLOSED) state.  Trying to set the option for a socket returned by accept(),
+for example, will lead to an EBUSY error. In this case, the option should be set
+to the listening socket and it will be inherited by the accepted sockets.
 
 Transmission
 ------------

Documentation/usb/gadget-testing.txt

@@ -693,7 +693,7 @@ such specification consists of a number of lines with an inverval value
 in each line. The rules stated above are best illustrated with an example:
 
 # mkdir functions/uvc.usb0/control/header/h
-# cd functions/uvc.usb0/control/header/h
+# cd functions/uvc.usb0/control/
 # ln -s header/h class/fs
 # ln -s header/h class/ss
 # mkdir -p functions/uvc.usb0/streaming/uncompressed/u/360p

Documentation/virtual/kvm/api.txt

@@ -3403,6 +3403,52 @@ invalid, if invalid pages are written to (e.g. after the end of memory)
 or if no page table is present for the addresses (e.g. when using
 hugepages).
 
+4.108 KVM_PPC_GET_CPU_CHAR
+
+Capability: KVM_CAP_PPC_GET_CPU_CHAR
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_ppc_cpu_char (out)
+Returns: 0 on successful completion
+	 -EFAULT if struct kvm_ppc_cpu_char cannot be written
+
+This ioctl gives userspace information about certain characteristics
+of the CPU relating to speculative execution of instructions and
+possible information leakage resulting from speculative execution (see
+CVE-2017-5715, CVE-2017-5753 and CVE-2017-5754).  The information is
+returned in struct kvm_ppc_cpu_char, which looks like this:
+
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+For extensibility, the character_mask and behaviour_mask fields
+indicate which bits of character and behaviour have been filled in by
+the kernel.  If the set of defined bits is extended in future then
+userspace will be able to tell whether it is running on a kernel that
+knows about the new bits.
+
+The character field describes attributes of the CPU which can help
+with preventing inadvertent information disclosure - specifically,
+whether there is an instruction to flash-invalidate the L1 data cache
+(ori 30,30,0 or mtspr SPRN_TRIG2,rN), whether the L1 data cache is set
+to a mode where entries can only be used by the thread that created
+them, whether the bcctr[l] instruction prevents speculation, and
+whether a speculation barrier instruction (ori 31,31,0) is provided.
+
+The behaviour field describes actions that software should take to
+prevent inadvertent information disclosure, and thus describes which
+vulnerabilities the hardware is subject to; specifically whether the
+L1 data cache should be flushed when returning to user mode from the
+kernel, and whether a speculation barrier should be placed between an
+array bounds check and the array access.
+
+These fields use the same bit definitions as the new
+H_GET_CPU_CHARACTERISTICS hypercall.
+
 5. The kvm_run structure
 ------------------------
 

Documentation/x86/pti.txt

@@ -0,0 +1,186 @@
+Overview
+========
+
+Page Table Isolation (pti, previously known as KAISER[1]) is a
+countermeasure against attacks on the shared user/kernel address
+space such as the "Meltdown" approach[2].
+
+To mitigate this class of attacks, we create an independent set of
+page tables for use only when running userspace applications.  When
+the kernel is entered via syscalls, interrupts or exceptions, the
+page tables are switched to the full "kernel" copy.  When the system
+switches back to user mode, the user copy is used again.
+
+The userspace page tables contain only a minimal amount of kernel
+data: only what is needed to enter/exit the kernel such as the
+entry/exit functions themselves and the interrupt descriptor table
+(IDT).  There are a few strictly unnecessary things that get mapped
+such as the first C function when entering an interrupt (see
+comments in pti.c).
+
+This approach helps to ensure that side-channel attacks leveraging
+the paging structures do not function when PTI is enabled.  It can be
+enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time.
+Once enabled at compile-time, it can be disabled at boot with the
+'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt).
+
+Page Table Management
+=====================
+
+When PTI is enabled, the kernel manages two sets of page tables.
+The first set is very similar to the single set which is present in
+kernels without PTI.  This includes a complete mapping of userspace
+that the kernel can use for things like copy_to_user().
+
+Although _complete_, the user portion of the kernel page tables is
+crippled by setting the NX bit in the top level.  This ensures
+that any missed kernel->user CR3 switch will immediately crash
+userspace upon executing its first instruction.
+
+The userspace page tables map only the kernel data needed to enter
+and exit the kernel.  This data is entirely contained in the 'struct
+cpu_entry_area' structure which is placed in the fixmap which gives
+each CPU's copy of the area a compile-time-fixed virtual address.
+
+For new userspace mappings, the kernel makes the entries in its
+page tables like normal.  The only difference is when the kernel
+makes entries in the top (PGD) level.  In addition to setting the
+entry in the main kernel PGD, a copy of the entry is made in the
+userspace page tables' PGD.
+
+This sharing at the PGD level also inherently shares all the lower
+layers of the page tables.  This leaves a single, shared set of
+userspace page tables to manage.  One PTE to lock, one set of
+accessed bits, dirty bits, etc...
+
+Overhead
+========
+
+Protection against side-channel attacks is important.  But,
+this protection comes at a cost:
+
+1. Increased Memory Use
+  a. Each process now needs an order-1 PGD instead of order-0.
+     (Consumes an additional 4k per process).
+  b. The 'cpu_entry_area' structure must be 2MB in size and 2MB
+     aligned so that it can be mapped by setting a single PMD
+     entry.  This consumes nearly 2MB of RAM once the kernel
+     is decompressed, but no space in the kernel image itself.
+
+2. Runtime Cost
+  a. CR3 manipulation to switch between the page table copies
+     must be done at interrupt, syscall, and exception entry
+     and exit (it can be skipped when the kernel is interrupted,
+     though.)  Moves to CR3 are on the order of a hundred
+     cycles, and are required at every entry and exit.
+  b. A "trampoline" must be used for SYSCALL entry.  This
+     trampoline depends on a smaller set of resources than the
+     non-PTI SYSCALL entry code, so requires mapping fewer
+     things into the userspace page tables.  The downside is
+     that stacks must be switched at entry time.
+  c. Global pages are disabled for all kernel structures not
+     mapped into both kernel and userspace page tables.  This
+     feature of the MMU allows different processes to share TLB
+     entries mapping the kernel.  Losing the feature means more
+     TLB misses after a context switch.  The actual loss of
+     performance is very small, however, never exceeding 1%.
+  d. Process Context IDentifiers (PCID) is a CPU feature that
+     allows us to skip flushing the entire TLB when switching page
+     tables by setting a special bit in CR3 when the page tables
+     are changed.  This makes switching the page tables (at context
+     switch, or kernel entry/exit) cheaper.  But, on systems with
+     PCID support, the context switch code must flush both the user
+     and kernel entries out of the TLB.  The user PCID TLB flush is
+     deferred until the exit to userspace, minimizing the cost.
+     See intel.com/sdm for the gory PCID/INVPCID details.
+  e. The userspace page tables must be populated for each new
+     process.  Even without PTI, the shared kernel mappings
+     are created by copying top-level (PGD) entries into each
+     new process.  But, with PTI, there are now *two* kernel
+     mappings: one in the kernel page tables that maps everything
+     and one for the entry/exit structures.  At fork(), we need to
+     copy both.
+  f. In addition to the fork()-time copying, there must also
+     be an update to the userspace PGD any time a set_pgd() is done
+     on a PGD used to map userspace.  This ensures that the kernel
+     and userspace copies always map the same userspace
+     memory.
+  g. On systems without PCID support, each CR3 write flushes
+     the entire TLB.  That means that each syscall, interrupt
+     or exception flushes the TLB.
+  h. INVPCID is a TLB-flushing instruction which allows flushing
+     of TLB entries for non-current PCIDs.  Some systems support
+     PCIDs, but do not support INVPCID.  On these systems, addresses
+     can only be flushed from the TLB for the current PCID.  When
+     flushing a kernel address, we need to flush all PCIDs, so a
+     single kernel address flush will require a TLB-flushing CR3
+     write upon the next use of every PCID.
+
+Possible Future Work
+====================
+1. We can be more careful about not actually writing to CR3
+   unless its value is actually changed.
+2. Allow PTI to be enabled/disabled at runtime in addition to the
+   boot-time switching.
+
+Testing
+========
+
+To test stability of PTI, the following test procedure is recommended,
+ideally doing all of these in parallel:
+
+1. Set CONFIG_DEBUG_ENTRY=y
+2. Run several copies of all of the tools/testing/selftests/x86/ tests
+   (excluding MPX and protection_keys) in a loop on multiple CPUs for
+   several minutes.  These tests frequently uncover corner cases in the
+   kernel entry code.  In general, old kernels might cause these tests
+   themselves to crash, but they should never crash the kernel.
+3. Run the 'perf' tool in a mode (top or record) that generates many
+   frequent performance monitoring non-maskable interrupts (see "NMI"
+   in /proc/interrupts).  This exercises the NMI entry/exit code which
+   is known to trigger bugs in code paths that did not expect to be
+   interrupted, including nested NMIs.  Using "-c" boosts the rate of
+   NMIs, and using two -c with separate counters encourages nested NMIs
+   and less deterministic behavior.
+
+	while true; do perf record -c 10000 -e instructions,cycles -a sleep 10; done
+
+4. Launch a KVM virtual machine.
+5. Run 32-bit binaries on systems supporting the SYSCALL instruction.
+   This has been a lightly-tested code path and needs extra scrutiny.
+
+Debugging
+=========
+
+Bugs in PTI cause a few different signatures of crashes
+that are worth noting here.
+
+ * Failures of the selftests/x86 code.  Usually a bug in one of the
+   more obscure corners of entry_64.S
+ * Crashes in early boot, especially around CPU bringup.  Bugs
+   in the trampoline code or mappings cause these.
+ * Crashes at the first interrupt.  Caused by bugs in entry_64.S,
+   like screwing up a page table switch.  Also caused by
+   incorrectly mapping the IRQ handler entry code.
+ * Crashes at the first NMI.  The NMI code is separate from main
+   interrupt handlers and can have bugs that do not affect
+   normal interrupts.  Also caused by incorrectly mapping NMI
+   code.  NMIs that interrupt the entry code must be very
+   careful and can be the cause of crashes that show up when
+   running perf.
+ * Kernel crashes at the first exit to userspace.  entry_64.S
+   bugs, or failing to map some of the exit code.
+ * Crashes at first interrupt that interrupts userspace. The paths
+   in entry_64.S that return to userspace are sometimes separate
+   from the ones that return to the kernel.
+ * Double faults: overflowing the kernel stack because of page
+   faults upon page faults.  Caused by touching non-pti-mapped
+   data in the entry code, or forgetting to switch to kernel
+   CR3 before calling into C functions which are not pti-mapped.
+ * Userspace segfaults early in boot, sometimes manifesting
+   as mount(8) failing to mount the rootfs.  These have
+   tended to be TLB invalidation issues.  Usually invalidating
+   the wrong PCID, or otherwise missing an invalidation.
+
+1. https://gruss.cc/files/kaiser.pdf
+2. https://meltdownattack.com/meltdown.pdf

MAINTAINERS

@@ -62,7 +62,15 @@ trivial patch so apply some common sense.
 
 7.	When sending security related changes or reports to a maintainer
 	please Cc: security@kernel.org, especially if the maintainer
-	does not respond.
+	does not respond. Please keep in mind that the security team is
+	a small set of people who can be efficient only when working on
+	verified bugs. Please only Cc: this list when you have identified
+	that the bug would present a short-term risk to other users if it
+	were publicly disclosed. For example, reports of address leaks do
+	not represent an immediate threat and are better handled publicly,
+	and ideally, should come with a patch proposal. Please do not send
+	automated reports to this list either. Such bugs will be handled
+	better and faster in the usual public places.
 
 8.	Happy hacking.
 
@@ -9085,6 +9093,7 @@ F:	drivers/usb/image/microtek.*
 
 MIPS
 M:	Ralf Baechle <ralf@linux-mips.org>
+M:	James Hogan <jhogan@kernel.org>
 L:	linux-mips@linux-mips.org
 W:	http://www.linux-mips.org/
 T:	git git://git.linux-mips.org/pub/scm/ralf/linux.git
@@ -9638,8 +9647,8 @@ F:	include/uapi/linux/sunrpc/
 NILFS2 FILESYSTEM
 M:	Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
 L:	linux-nilfs@vger.kernel.org
-W:	http://nilfs.sourceforge.net/
-W:	http://nilfs.osdn.jp/
+W:	https://nilfs.sourceforge.io/
+W:	https://nilfs.osdn.jp/
 T:	git git://github.com/konis/nilfs2.git
 S:	Supported
 F:	Documentation/filesystems/nilfs2.txt
@@ -10134,7 +10143,7 @@ F:	drivers/irqchip/irq-ompic.c
 F:	drivers/irqchip/irq-or1k-*
 
 OPENVSWITCH
-M:	Pravin Shelar <pshelar@nicira.com>
+M:	Pravin B Shelar <pshelar@ovn.org>
 L:	netdev@vger.kernel.org
 L:	dev@openvswitch.org
 W:	http://openvswitch.org
@@ -12232,7 +12241,7 @@ M:	Security Officers <security@kernel.org>
 S:	Supported
 
 SECURITY SUBSYSTEM
-M:	James Morris <james.l.morris@oracle.com>
+M:	James Morris <jmorris@namei.org>
 M:	"Serge E. Hallyn" <serge@hallyn.com>
 L:	linux-security-module@vger.kernel.org (suggested Cc:)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc9
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -484,26 +484,6 @@ CLANG_GCC_TC	:= --gcc-toolchain=$(GCC_TOOLCHAIN)
 endif
 KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
 KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
-KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
-KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
-# Quiet clang warning: comparison of unsigned expression < 0 is always false
-KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
-# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
-# source of a reference will be _MergedGlobals and not on of the whitelisted names.
-# See modpost pattern 2
-KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
-KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
-KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
-KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
-else
-
-# These warnings generated too much noise in a regular build.
-# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
-KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
 endif
 
 ifeq ($(config-targets),1)
@@ -716,6 +696,29 @@ ifdef CONFIG_CC_STACKPROTECTOR
 endif
 KBUILD_CFLAGS += $(stackp-flag)
 
+ifeq ($(cc-name),clang)
+KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
+KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
+# Quiet clang warning: comparison of unsigned expression < 0 is always false
+KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
+# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
+# source of a reference will be _MergedGlobals and not on of the whitelisted names.
+# See modpost pattern 2
+KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,)
+KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior)
+KBUILD_CFLAGS += $(call cc-option, -no-integrated-as)
+KBUILD_AFLAGS += $(call cc-option, -no-integrated-as)
+else
+
+# These warnings generated too much noise in a regular build.
+# Use make W=1 to enable them (see scripts/Makefile.extrawarn)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable)
+KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable)
+endif
+
 ifdef CONFIG_FRAME_POINTER
 KBUILD_CFLAGS	+= -fno-omit-frame-pointer -fno-optimize-sibling-calls
 else

arch/alpha/kernel/sys_sio.c

@@ -102,6 +102,15 @@ sio_pci_route(void)
 				   alpha_mv.sys.sio.route_tab);
 }
 
+static bool sio_pci_dev_irq_needs_level(const struct pci_dev *dev)
+{
+	if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
+	    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		return false;
+
+	return true;
+}
+
 static unsigned int __init
 sio_collect_irq_levels(void)
 {
@@ -110,8 +119,7 @@ sio_collect_irq_levels(void)
 
 	/* Iterate through the devices, collecting IRQ levels.  */
 	for_each_pci_dev(dev) {
-		if ((dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) &&
-		    (dev->class >> 8 != PCI_CLASS_BRIDGE_PCMCIA))
+		if (!sio_pci_dev_irq_needs_level(dev))
 			continue;
 
 		if (dev->irq)
@@ -120,8 +128,7 @@ sio_collect_irq_levels(void)
 	return level_bits;
 }
 
-static void __init
-sio_fixup_irq_levels(unsigned int level_bits)
+static void __sio_fixup_irq_levels(unsigned int level_bits, bool reset)
 {
 	unsigned int old_level_bits;
 
@@ -139,12 +146,21 @@ sio_fixup_irq_levels(unsigned int level_bits)
 	 */
 	old_level_bits = inb(0x4d0) | (inb(0x4d1) << 8);
 
-	level_bits |= (old_level_bits & 0x71ff);
+	if (reset)
+		old_level_bits &= 0x71ff;
+
+	level_bits |= old_level_bits;
 
 	outb((level_bits >> 0) & 0xff, 0x4d0);
 	outb((level_bits >> 8) & 0xff, 0x4d1);
 }
 
+static inline void
+sio_fixup_irq_levels(unsigned int level_bits)
+{
+	__sio_fixup_irq_levels(level_bits, true);
+}
+
 static inline int
 noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
@@ -181,7 +197,14 @@ noname_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	const long min_idsel = 6, max_idsel = 14, irqs_per_slot = 5;
 	int irq = COMMON_TABLE_LOOKUP, tmp;
 	tmp = __kernel_extbl(alpha_mv.sys.sio.route_tab, irq);
-	return irq >= 0 ? tmp : -1;
+
+	irq = irq >= 0 ? tmp : -1;
+
+	/* Fixup IRQ level if an actual IRQ mapping is detected */
+	if (sio_pci_dev_irq_needs_level(dev) && irq >= 0)
+		__sio_fixup_irq_levels(1 << irq, false);
+
+	return irq;
 }
 
 static inline int

arch/alpha/lib/ev6-memset.S

@@ -18,7 +18,7 @@
  * The algorithm for the leading and trailing quadwords remains the same,
  * however the loop has been unrolled to enable better memory throughput,
  * and the code has been replicated for each of the entry points: __memset
- * and __memsetw to permit better scheduling to eliminate the stalling
+ * and __memset16 to permit better scheduling to eliminate the stalling
  * encountered during the mask replication.
  * A future enhancement might be to put in a byte store loop for really
  * small (say < 32 bytes) memset()s.  Whether or not that change would be
@@ -34,7 +34,7 @@
 	.globl memset
 	.globl __memset
 	.globl ___memset
-	.globl __memsetw
+	.globl __memset16
 	.globl __constant_c_memset
 
 	.ent ___memset
@@ -415,9 +415,9 @@ end:
 	 * to mask stalls.  Note that entry point names also had to change
 	 */
 	.align 5
-	.ent __memsetw
+	.ent __memset16
 
-__memsetw:
+__memset16:
 	.frame $30,0,$26,0
 	.prologue 0
 
@@ -596,8 +596,8 @@ end_w:
 	nop
 	ret $31,($26),1		# L0 :
 
-	.end __memsetw
-	EXPORT_SYMBOL(__memsetw)
+	.end __memset16
+	EXPORT_SYMBOL(__memset16)
 
 memset = ___memset
 __memset = ___memset

arch/arc/boot/dts/axc003.dtsi

@@ -35,6 +35,14 @@
 			reg = <0x80 0x10>, <0x100 0x10>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 90MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <90000000>;
 		};
 
 		core_intc: archs-intc@cpu {

arch/arc/boot/dts/axc003_idu.dtsi

@@ -35,6 +35,14 @@
 			reg = <0x80 0x10>, <0x100 0x10>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 100MHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <100000000>;
 		};
 
 		core_intc: archs-intc@cpu {

arch/arc/boot/dts/hsdk.dts

@@ -114,6 +114,14 @@
 			reg = <0x00 0x10>, <0x14B8 0x4>;
 			#clock-cells = <0>;
 			clocks = <&input_clk>;
+
+			/*
+			 * Set initial core pll output frequency to 1GHz.
+			 * It will be applied at the core pll driver probing
+			 * on early boot.
+			 */
+			assigned-clocks = <&core_clk>;
+			assigned-clock-rates = <1000000000>;
 		};
 
 		serial: serial@5000 {

arch/arc/configs/hsdk_defconfig

@@ -49,10 +49,11 @@ CONFIG_SERIAL_8250_DW=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
+CONFIG_DRM=y
+# CONFIG_DRM_FBDEV_EMULATION is not set
+CONFIG_DRM_UDL=y
 CONFIG_FB=y
-CONFIG_FB_UDL=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
-CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
 CONFIG_USB_OHCI_HCD=y

arch/arc/include/asm/uaccess.h

@@ -668,6 +668,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 		return 0;
 
 	__asm__ __volatile__(
+	"	mov	lp_count, %5		\n"
 	"	lp	3f			\n"
 	"1:	ldb.ab  %3, [%2, 1]		\n"
 	"	breq.d	%3, 0, 3f               \n"
@@ -684,8 +685,8 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 	"	.word   1b, 4b			\n"
 	"	.previous			\n"
 	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
-	: "g"(-EFAULT), "l"(count)
-	: "memory");
+	: "g"(-EFAULT), "r"(count)
+	: "lp_count", "lp_start", "lp_end", "memory");
 
 	return res;
 }

arch/arc/kernel/setup.c

@@ -199,7 +199,7 @@ static void read_arc_build_cfg_regs(void)
 			unsigned int exec_ctrl;
 
 			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-			cpu->extn.dual_enb = exec_ctrl & 1;
+			cpu->extn.dual_enb = !(exec_ctrl & 1);
 
 			/* dual issue always present for this core */
 			cpu->extn.dual = 1;

arch/arc/kernel/stacktrace.c

@@ -163,7 +163,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs,
  */
 static int __print_sym(unsigned int address, void *unused)
 {
-	__print_symbol("  %s\n", address);
+	printk("  %pS\n", (void *)address);
 	return 0;
 }
 

arch/arc/kernel/traps.c

@@ -83,6 +83,7 @@ DO_ERROR_INFO(SIGILL, "Illegal Insn (or Seq)", insterror_is_error, ILL_ILLOPC)
 DO_ERROR_INFO(SIGBUS, "Invalid Mem Access", __weak do_memory_error, BUS_ADRERR)
 DO_ERROR_INFO(SIGTRAP, "Breakpoint Set", trap_is_brkpt, TRAP_BRKPT)
 DO_ERROR_INFO(SIGBUS, "Misaligned Access", do_misaligned_error, BUS_ADRALN)
+DO_ERROR_INFO(SIGSEGV, "gcc generated __builtin_trap", do_trap5_error, 0)
 
 /*
  * Entry Point for Misaligned Data access Exception, for emulating in software
@@ -115,6 +116,8 @@ void do_machine_check_fault(unsigned long address, struct pt_regs *regs)
  * Thus TRAP_S <n> can be used for specific purpose
  *  -1 used for software breakpointing (gdb)
  *  -2 used by kprobes
+ *  -5 __builtin_trap() generated by gcc (2018.03 onwards) for toggle such as
+ *     -fno-isolate-erroneous-paths-dereference
  */
 void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
 {
@@ -134,6 +137,9 @@ void do_non_swi_trap(unsigned long address, struct pt_regs *regs)
 		kgdb_trap(regs);
 		break;
 
+	case 5:
+		do_trap5_error(address, regs);
+		break;
 	default:
 		break;
 	}
@@ -155,3 +161,11 @@ void do_insterror_or_kprobe(unsigned long address, struct pt_regs *regs)
 
 	insterror_is_error(address, regs);
 }
+
+/*
+ * abort() call generated by older gcc for __builtin_trap()
+ */
+void abort(void)
+{
+	__asm__ __volatile__("trap_s  5\n");
+}

arch/arc/kernel/troubleshoot.c

@@ -163,6 +163,9 @@ static void show_ecr_verbose(struct pt_regs *regs)
 		else
 			pr_cont("Bus Error, check PRM\n");
 #endif
+	} else if (vec == ECR_V_TRAP) {
+		if (regs->ecr_param == 5)
+			pr_cont("gcc generated __builtin_trap\n");
 	} else {
 		pr_cont("Check Programmer's Manual\n");
 	}

arch/arc/plat-axs10x/axs10x.c

@@ -317,25 +317,23 @@ static void __init axs103_early_init(void)
 	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
 	 * of fudging the freq in DT
 	 */
+#define AXS103_QUAD_CORE_CPU_FREQ_HZ	50000000
+
 	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
 	if (num_cores > 2) {
-		u32 freq = 50, orig;
-		/*
-		 * TODO: use cpu node "cpu-freq" param instead of platform-specific
-		 * "/cpu_card/core_clk" as it works only if we use fixed-clock for cpu.
-		 */
+		u32 freq;
 		int off = fdt_path_offset(initial_boot_params, "/cpu_card/core_clk");
 		const struct fdt_property *prop;
 
 		prop = fdt_get_property(initial_boot_params, off,
-					"clock-frequency", NULL);
-		orig = be32_to_cpu(*(u32*)(prop->data)) / 1000000;
+					"assigned-clock-rates", NULL);
+		freq = be32_to_cpu(*(u32 *)(prop->data));
 
 		/* Patching .dtb in-place with new core clock value */
-		if (freq != orig ) {
-			freq = cpu_to_be32(freq * 1000000);
+		if (freq != AXS103_QUAD_CORE_CPU_FREQ_HZ) {
+			freq = cpu_to_be32(AXS103_QUAD_CORE_CPU_FREQ_HZ);
 			fdt_setprop_inplace(initial_boot_params, off,
-					    "clock-frequency", &freq, sizeof(freq));
+					    "assigned-clock-rates", &freq, sizeof(freq));
 		}
 	}
 #endif

arch/arc/plat-hsdk/platform.c

@@ -38,42 +38,6 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define CREG_PAE		(CREG_BASE + 0x180)
 #define CREG_PAE_UPDATE		(CREG_BASE + 0x194)
 
-#define CREG_CORE_IF_CLK_DIV	(CREG_BASE + 0x4B8)
-#define CREG_CORE_IF_CLK_DIV_2	0x1
-#define CGU_BASE		ARC_PERIPHERAL_BASE
-#define CGU_PLL_STATUS		(ARC_PERIPHERAL_BASE + 0x4)
-#define CGU_PLL_CTRL		(ARC_PERIPHERAL_BASE + 0x0)
-#define CGU_PLL_STATUS_LOCK	BIT(0)
-#define CGU_PLL_STATUS_ERR	BIT(1)
-#define CGU_PLL_CTRL_1GHZ	0x3A10
-#define HSDK_PLL_LOCK_TIMEOUT	500
-
-#define HSDK_PLL_LOCKED() \
-	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK)
-
-#define HSDK_PLL_ERR() \
-	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR)
-
-static void __init hsdk_set_cpu_freq_1ghz(void)
-{
-	u32 timeout = HSDK_PLL_LOCK_TIMEOUT;
-
-	/*
-	 * As we set cpu clock which exceeds 500MHz, the divider for the interface
-	 * clock must be programmed to div-by-2.
-	 */
-	iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV);
-
-	/* Set cpu clock to 1GHz */
-	iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL);
-
-	while (!HSDK_PLL_LOCKED() && timeout--)
-		cpu_relax();
-
-	if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR())
-		pr_err("Failed to setup CPU frequency to 1GHz!");
-}
-
 #define SDIO_BASE		(ARC_PERIPHERAL_BASE + 0xA000)
 #define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
 #define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
@@ -98,12 +62,6 @@ static void __init hsdk_init_early(void)
 	 * minimum possible div-by-2.
 	 */
 	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
-
-	/*
-	 * Setup CPU frequency to 1GHz.
-	 * TODO: remove it after smart hsdk pll driver will be introduced.
-	 */
-	hsdk_set_cpu_freq_1ghz();
 }
 
 static const char *hsdk_compat[] __initconst = {

arch/arm/boot/dts/da850-lcdk.dts

@@ -293,12 +293,12 @@
 					label = "u-boot env";
 					reg = <0 0x020000>;
 				};
-				partition@0x020000 {
+				partition@20000 {
 					/* The LCDK defaults to booting from this partition */
 					label = "u-boot";
 					reg = <0x020000 0x080000>;
 				};
-				partition@0x0a0000 {
+				partition@a0000 {
 					label = "free space";
 					reg = <0x0a0000 0>;
 				};

arch/arm/boot/dts/kirkwood-openblocks_a7.dts

@@ -53,7 +53,8 @@
 		};
 
 		pinctrl: pin-controller@10000 {
-			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header>;
+			pinctrl-0 = <&pmx_dip_switches &pmx_gpio_header
+				     &pmx_gpio_header_gpo>;
 			pinctrl-names = "default";
 
 			pmx_uart0: pmx-uart0 {
@@ -85,11 +86,16 @@
 			 * ground.
 			 */
 			pmx_gpio_header: pmx-gpio-header {
-				marvell,pins = "mpp17", "mpp7", "mpp29", "mpp28",
+				marvell,pins = "mpp17", "mpp29", "mpp28",
 					       "mpp35", "mpp34", "mpp40";
 				marvell,function = "gpio";
 			};
 
+			pmx_gpio_header_gpo: pxm-gpio-header-gpo {
+				marvell,pins = "mpp7";
+				marvell,function = "gpo";
+			};
+
 			pmx_gpio_init: pmx-init {
 				marvell,pins = "mpp38";
 				marvell,function = "gpio";

arch/arm/boot/dts/sun4i-a10.dtsi

@@ -1104,7 +1104,7 @@
 
 					be1_out_tcon0: endpoint@0 {
 						reg = <0>;
-						remote-endpoint = <&tcon1_in_be0>;
+						remote-endpoint = <&tcon0_in_be1>;
 					};
 
 					be1_out_tcon1: endpoint@1 {

arch/arm/boot/dts/sun7i-a20.dtsi

@@ -1354,7 +1354,7 @@
 
 					be1_out_tcon0: endpoint@0 {
 						reg = <0>;
-						remote-endpoint = <&tcon1_in_be0>;
+						remote-endpoint = <&tcon0_in_be1>;
 					};
 
 					be1_out_tcon1: endpoint@1 {

arch/arm/configs/sunxi_defconfig

@@ -10,6 +10,7 @@ CONFIG_SMP=y
 CONFIG_NR_CPUS=8
 CONFIG_AEABI=y
 CONFIG_HIGHMEM=y
+CONFIG_CMA=y
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
@@ -33,6 +34,7 @@ CONFIG_CAN_SUN4I=y
 # CONFIG_WIRELESS is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DMA_CMA=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_ATA=y
 CONFIG_AHCI_SUNXI=y

arch/arm/net/bpf_jit_32.c

@@ -27,14 +27,58 @@
 
 int bpf_jit_enable __read_mostly;
 
+/*
+ * eBPF prog stack layout:
+ *
+ *                         high
+ * original ARM_SP =>     +-----+
+ *                        |     | callee saved registers
+ *                        +-----+ <= (BPF_FP + SCRATCH_SIZE)
+ *                        | ... | eBPF JIT scratch space
+ * eBPF fp register =>    +-----+
+ *   (BPF_FP)             | ... | eBPF prog stack
+ *                        +-----+
+ *                        |RSVD | JIT scratchpad
+ * current ARM_SP =>      +-----+ <= (BPF_FP - STACK_SIZE + SCRATCH_SIZE)
+ *                        |     |
+ *                        | ... | Function call stack
+ *                        |     |
+ *                        +-----+
+ *                          low
+ *
+ * The callee saved registers depends on whether frame pointers are enabled.
+ * With frame pointers (to be compliant with the ABI):
+ *
+ *                                high
+ * original ARM_SP =>     +------------------+ \
+ *                        |        pc        | |
+ * current ARM_FP =>      +------------------+ } callee saved registers
+ *                        |r4-r8,r10,fp,ip,lr| |
+ *                        +------------------+ /
+ *                                low
+ *
+ * Without frame pointers:
+ *
+ *                                high
+ * original ARM_SP =>     +------------------+
+ *                        | r4-r8,r10,fp,lr  | callee saved registers
+ * current ARM_FP =>      +------------------+
+ *                                low
+ *
+ * When popping registers off the stack at the end of a BPF function, we
+ * reference them via the current ARM_FP register.
+ */
+#define CALLEE_MASK	(1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
+			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+			 1 << ARM_FP)
+#define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
+#define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
+
 #define STACK_OFFSET(k)	(k)
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)	/* TEMP Register 2 */
 #define TCALL_CNT	(MAX_BPF_JIT_REG + 2)	/* Tail Call Count */
 
-/* Flags used for JIT optimization */
-#define SEEN_CALL	(1 << 0)
-
 #define FLAG_IMM_OVERFLOW	(1 << 0)
 
 /*
@@ -95,7 +139,6 @@ static const u8 bpf2a32[][2] = {
  * idx			:	index of current last JITed instruction.
  * prologue_bytes	:	bytes used in prologue.
  * epilogue_offset	:	offset of epilogue starting.
- * seen			:	bit mask used for JIT optimization.
  * offsets		:	array of eBPF instruction offsets in
  *				JITed code.
  * target		:	final JITed code.
@@ -110,7 +153,6 @@ struct jit_ctx {
 	unsigned int idx;
 	unsigned int prologue_bytes;
 	unsigned int epilogue_offset;
-	u32 seen;
 	u32 flags;
 	u32 *offsets;
 	u32 *target;
@@ -179,8 +221,13 @@ static void jit_fill_hole(void *area, unsigned int size)
 		*ptr++ = __opcode_to_mem_arm(ARM_INST_UDF);
 }
 
-/* Stack must be multiples of 16 Bytes */
-#define STACK_ALIGN(sz) (((sz) + 3) & ~3)
+#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5)
+/* EABI requires the stack to be aligned to 64-bit boundaries */
+#define STACK_ALIGNMENT	8
+#else
+/* Stack must be aligned to 32-bit boundaries */
+#define STACK_ALIGNMENT	4
+#endif
 
 /* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
  * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
@@ -194,7 +241,7 @@ static void jit_fill_hole(void *area, unsigned int size)
 	 + SCRATCH_SIZE + \
 	 + 4 /* extra for skb_copy_bits buffer */)
 
-#define STACK_SIZE STACK_ALIGN(_STACK_SIZE)
+#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
 /* Get the offset of eBPF REGISTERs stored on scratch space. */
 #define STACK_VAR(off) (STACK_SIZE-off-4)
@@ -285,16 +332,19 @@ static inline void emit_mov_i(const u8 rd, u32 val, struct jit_ctx *ctx)
 		emit_mov_i_no8m(rd, val, ctx);
 }
 
-static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+static void emit_bx_r(u8 tgt_reg, struct jit_ctx *ctx)
 {
-	ctx->seen |= SEEN_CALL;
-#if __LINUX_ARM_ARCH__ < 5
-	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
-
 	if (elf_hwcap & HWCAP_THUMB)
 		emit(ARM_BX(tgt_reg), ctx);
 	else
 		emit(ARM_MOV_R(ARM_PC, tgt_reg), ctx);
+}
+
+static inline void emit_blx_r(u8 tgt_reg, struct jit_ctx *ctx)
+{
+#if __LINUX_ARM_ARCH__ < 5
+	emit(ARM_MOV_R(ARM_LR, ARM_PC), ctx);
+	emit_bx_r(tgt_reg, ctx);
 #else
 	emit(ARM_BLX_R(tgt_reg), ctx);
 #endif
@@ -354,7 +404,6 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 	}
 
 	/* Call appropriate function */
-	ctx->seen |= SEEN_CALL;
 	emit_mov_i(ARM_IP, op == BPF_DIV ?
 		   (u32)jit_udiv32 : (u32)jit_mod32, ctx);
 	emit_blx_r(ARM_IP, ctx);
@@ -620,8 +669,6 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do LSH operation */
 	emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
@@ -656,8 +703,6 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do the ARSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
@@ -692,8 +737,6 @@ static inline void emit_a32_lsr_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do LSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
@@ -828,8 +871,6 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
 	/* Do Multiplication */
 	emit(ARM_MUL(ARM_IP, rd, rn), ctx);
 	emit(ARM_MUL(ARM_LR, rm, rt), ctx);
-	/* As we are using ARM_LR */
-	ctx->seen |= SEEN_CALL;
 	emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
 
 	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
@@ -872,33 +913,53 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
 }
 
 /* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst, const u8 src, bool dstk,
-			      const s32 off, struct jit_ctx *ctx, const u8 sz){
+static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+			      s32 off, struct jit_ctx *ctx, const u8 sz){
 	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst;
+	const u8 *rd = dstk ? tmp : dst;
 	u8 rm = src;
+	s32 off_max;
 
-	if (off) {
+	if (sz == BPF_H)
+		off_max = 0xff;
+	else
+		off_max = 0xfff;
+
+	if (off < 0 || off > off_max) {
 		emit_a32_mov_i(tmp[0], off, false, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
+		off = 0;
+	} else if (rd[1] == rm) {
+		emit(ARM_MOV_R(tmp[0], rm), ctx);
+		rm = tmp[0];
 	}
 	switch (sz) {
-	case BPF_W:
-		/* Load a Word */
-		emit(ARM_LDR_I(rd, rm, 0), ctx);
+	case BPF_B:
+		/* Load a Byte */
+		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
-		emit(ARM_LDRH_I(rd, rm, 0), ctx);
+		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
 		break;
-	case BPF_B:
-		/* Load a Byte */
-		emit(ARM_LDRB_I(rd, rm, 0), ctx);
+	case BPF_W:
+		/* Load a Word */
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		break;
+	case BPF_DW:
+		/* Load a Double Word */
+		emit(ARM_LDR_I(rd[1], rm, off), ctx);
+		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
 	if (dstk)
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
+	if (dstk && sz == BPF_DW)
+		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
 }
 
 /* Arithmatic Operation */
@@ -906,7 +967,6 @@ static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
 			     const u8 rn, struct jit_ctx *ctx, u8 op) {
 	switch (op) {
 	case BPF_JSET:
-		ctx->seen |= SEEN_CALL;
 		emit(ARM_AND_R(ARM_IP, rt, rn), ctx);
 		emit(ARM_AND_R(ARM_LR, rd, rm), ctx);
 		emit(ARM_ORRS_R(ARM_IP, ARM_LR, ARM_IP), ctx);
@@ -945,7 +1005,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	const u8 *tcc = bpf2a32[TCALL_CNT];
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
-#define jmp_offset (out_offset - (cur_offset))
+#define jmp_offset (out_offset - (cur_offset) - 2)
 	u32 off, lo, hi;
 
 	/* if (index >= array->map.max_entries)
@@ -956,7 +1016,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit_a32_mov_i(tmp[1], off, false, ctx);
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
 	emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
-	/* index (64 bit) */
+	/* index is 32-bit for arrays */
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
 	/* index >= array->map.max_entries */
 	emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
@@ -997,7 +1057,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit_a32_mov_i(tmp2[1], off, false, ctx);
 	emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
 	emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
-	emit(ARM_BX(tmp[1]), ctx);
+	emit_bx_r(tmp[1], ctx);
 
 	/* out: */
 	if (out_offset == -1)
@@ -1070,54 +1130,22 @@ static void build_prologue(struct jit_ctx *ctx)
 	const u8 r2 = bpf2a32[BPF_REG_1][1];
 	const u8 r3 = bpf2a32[BPF_REG_1][0];
 	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 r5 = bpf2a32[BPF_REG_6][0];
-	const u8 r6 = bpf2a32[TMP_REG_1][1];
-	const u8 r7 = bpf2a32[TMP_REG_1][0];
-	const u8 r8 = bpf2a32[TMP_REG_2][1];
-	const u8 r10 = bpf2a32[TMP_REG_2][0];
 	const u8 fplo = bpf2a32[BPF_REG_FP][1];
 	const u8 fphi = bpf2a32[BPF_REG_FP][0];
-	const u8 sp = ARM_SP;
 	const u8 *tcc = bpf2a32[TCALL_CNT];
 
-	u16 reg_set = 0;
-
-	/*
-	 * eBPF prog stack layout
-	 *
-	 *                         high
-	 * original ARM_SP =>     +-----+ eBPF prologue
-	 *                        |FP/LR|
-	 * current ARM_FP =>      +-----+
-	 *                        | ... | callee saved registers
-	 * eBPF fp register =>    +-----+ <= (BPF_FP)
-	 *                        | ... | eBPF JIT scratch space
-	 *                        |     | eBPF prog stack
-	 *                        +-----+
-	 *			  |RSVD | JIT scratchpad
-	 * current A64_SP =>      +-----+ <= (BPF_FP - STACK_SIZE)
-	 *                        |     |
-	 *                        | ... | Function call stack
-	 *                        |     |
-	 *                        +-----+
-	 *                          low
-	 */
-
 	/* Save callee saved registers. */
-	reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
 #ifdef CONFIG_FRAME_POINTER
-	reg_set |= (1<<ARM_FP) | (1<<ARM_IP) | (1<<ARM_LR) | (1<<ARM_PC);
-	emit(ARM_MOV_R(ARM_IP, sp), ctx);
+	u16 reg_set = CALLEE_PUSH_MASK | 1 << ARM_IP | 1 << ARM_PC;
+	emit(ARM_MOV_R(ARM_IP, ARM_SP), ctx);
 	emit(ARM_PUSH(reg_set), ctx);
 	emit(ARM_SUB_I(ARM_FP, ARM_IP, 4), ctx);
 #else
-	/* Check if call instruction exists in BPF body */
-	if (ctx->seen & SEEN_CALL)
-		reg_set |= (1<<ARM_LR);
-	emit(ARM_PUSH(reg_set), ctx);
+	emit(ARM_PUSH(CALLEE_PUSH_MASK), ctx);
+	emit(ARM_MOV_R(ARM_FP, ARM_SP), ctx);
 #endif
 	/* Save frame pointer for later */
-	emit(ARM_SUB_I(ARM_IP, sp, SCRATCH_SIZE), ctx);
+	emit(ARM_SUB_I(ARM_IP, ARM_SP, SCRATCH_SIZE), ctx);
 
 	ctx->stack_size = imm8m(STACK_SIZE);
 
@@ -1140,33 +1168,19 @@ static void build_prologue(struct jit_ctx *ctx)
 	/* end of prologue */
 }
 
+/* restore callee saved registers. */
 static void build_epilogue(struct jit_ctx *ctx)
 {
-	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 r5 = bpf2a32[BPF_REG_6][0];
-	const u8 r6 = bpf2a32[TMP_REG_1][1];
-	const u8 r7 = bpf2a32[TMP_REG_1][0];
-	const u8 r8 = bpf2a32[TMP_REG_2][1];
-	const u8 r10 = bpf2a32[TMP_REG_2][0];
-	u16 reg_set = 0;
-
-	/* unwind function call stack */
-	emit(ARM_ADD_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
-
-	/* restore callee saved registers. */
-	reg_set |= (1<<r4) | (1<<r5) | (1<<r6) | (1<<r7) | (1<<r8) | (1<<r10);
 #ifdef CONFIG_FRAME_POINTER
-	/* the first instruction of the prologue was: mov ip, sp */
-	reg_set |= (1<<ARM_FP) | (1<<ARM_SP) | (1<<ARM_PC);
+	/* When using frame pointers, some additional registers need to
+	 * be loaded. */
+	u16 reg_set = CALLEE_POP_MASK | 1 << ARM_SP;
+	emit(ARM_SUB_I(ARM_SP, ARM_FP, hweight16(reg_set) * 4), ctx);
 	emit(ARM_LDM(ARM_SP, reg_set), ctx);
 #else
-	if (ctx->seen & SEEN_CALL)
-		reg_set |= (1<<ARM_PC);
 	/* Restore callee saved registers. */
-	emit(ARM_POP(reg_set), ctx);
-	/* Return back to the callee function */
-	if (!(ctx->seen & SEEN_CALL))
-		emit(ARM_BX(ARM_LR), ctx);
+	emit(ARM_MOV_R(ARM_SP, ARM_FP), ctx);
+	emit(ARM_POP(CALLEE_POP_MASK), ctx);
 #endif
 }
 
@@ -1394,8 +1408,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			emit_rev32(rt, rt, ctx);
 			goto emit_bswap_uxt;
 		case 64:
-			/* Because of the usage of ARM_LR */
-			ctx->seen |= SEEN_CALL;
 			emit_rev32(ARM_LR, rt, ctx);
 			emit_rev32(rt, rd, ctx);
 			emit(ARM_MOV_R(rd, ARM_LR), ctx);
@@ -1448,22 +1460,7 @@ exit:
 		rn = sstk ? tmp2[1] : src_lo;
 		if (sstk)
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-		switch (BPF_SIZE(code)) {
-		case BPF_W:
-			/* Load a Word */
-		case BPF_H:
-			/* Load a Half-Word */
-		case BPF_B:
-			/* Load a Byte */
-			emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_SIZE(code));
-			emit_a32_mov_i(dst_hi, 0, dstk, ctx);
-			break;
-		case BPF_DW:
-			/* Load a double word */
-			emit_ldx_r(dst_lo, rn, dstk, off, ctx, BPF_W);
-			emit_ldx_r(dst_hi, rn, dstk, off+4, ctx, BPF_W);
-			break;
-		}
+		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
 		break;
 	/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
 	case BPF_LD | BPF_ABS | BPF_W:

arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi

@@ -66,6 +66,7 @@
 				     <&cpu1>,
 				     <&cpu2>,
 				     <&cpu3>;
+		interrupt-parent = <&intc>;
 	};
 
 	psci {

arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi

@@ -63,8 +63,10 @@
 			cpm_ethernet: ethernet@0 {
 				compatible = "marvell,armada-7k-pp22";
 				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>, <&cpm_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
+				clocks = <&cpm_clk 1 3>, <&cpm_clk 1 9>,
+					 <&cpm_clk 1 5>, <&cpm_clk 1 18>;
+				clock-names = "pp_clk", "gop_clk",
+					      "mg_clk","axi_clk";
 				marvell,system-controller = <&cpm_syscon0>;
 				status = "disabled";
 				dma-coherent;
@@ -155,7 +157,8 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x12a200 0x10>;
-				clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>;
+				clocks = <&cpm_clk 1 9>, <&cpm_clk 1 5>,
+					 <&cpm_clk 1 6>, <&cpm_clk 1 18>;
 				status = "disabled";
 			};
 
@@ -338,8 +341,8 @@
 				compatible = "marvell,armada-cp110-sdhci";
 				reg = <0x780000 0x300>;
 				interrupts = <ICU_GRP_NSR 27 IRQ_TYPE_LEVEL_HIGH>;
-				clock-names = "core";
-				clocks = <&cpm_clk 1 4>;
+				clock-names = "core","axi";
+				clocks = <&cpm_clk 1 4>, <&cpm_clk 1 18>;
 				dma-coherent;
 				status = "disabled";
 			};

arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi

@@ -63,8 +63,10 @@
 			cps_ethernet: ethernet@0 {
 				compatible = "marvell,armada-7k-pp22";
 				reg = <0x0 0x100000>, <0x129000 0xb000>;
-				clocks = <&cps_clk 1 3>, <&cps_clk 1 9>, <&cps_clk 1 5>;
-				clock-names = "pp_clk", "gop_clk", "mg_clk";
+				clocks = <&cps_clk 1 3>, <&cps_clk 1 9>,
+					 <&cps_clk 1 5>, <&cps_clk 1 18>;
+				clock-names = "pp_clk", "gop_clk",
+					      "mg_clk", "axi_clk";
 				marvell,system-controller = <&cps_syscon0>;
 				status = "disabled";
 				dma-coherent;
@@ -155,7 +157,8 @@
 				#size-cells = <0>;
 				compatible = "marvell,orion-mdio";
 				reg = <0x12a200 0x10>;
-				clocks = <&cps_clk 1 9>, <&cps_clk 1 5>;
+				clocks = <&cps_clk 1 9>, <&cps_clk 1 5>,
+					 <&cps_clk 1 6>, <&cps_clk 1 18>;
 				status = "disabled";
 			};
 

arch/arm64/kvm/handle_exit.c

@@ -45,7 +45,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	ret = kvm_psci_call(vcpu);
 	if (ret < 0) {
-		kvm_inject_undefined(vcpu);
+		vcpu_set_reg(vcpu, 0, ~0UL);
 		return 1;
 	}
 
@@ -54,7 +54,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
-	kvm_inject_undefined(vcpu);
+	vcpu_set_reg(vcpu, 0, ~0UL);
 	return 1;
 }
 

arch/arm64/net/bpf_jit_comp.c

@@ -148,7 +148,8 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 /* Stack must be multiples of 16B */
 #define STACK_ALIGN(sz) (((sz) + 15) & ~15)
 
-#define PROLOGUE_OFFSET 8
+/* Tail call offset to jump into */
+#define PROLOGUE_OFFSET 7
 
 static int build_prologue(struct jit_ctx *ctx)
 {
@@ -200,19 +201,19 @@ static int build_prologue(struct jit_ctx *ctx)
 	/* Initialize tail_call_cnt */
 	emit(A64_MOVZ(1, tcc, 0, 0), ctx);
 
-	/* 4 byte extra for skb_copy_bits buffer */
-	ctx->stack_size = prog->aux->stack_depth + 4;
-	ctx->stack_size = STACK_ALIGN(ctx->stack_size);
-
-	/* Set up function call stack */
-	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
-
 	cur_offset = ctx->idx - idx0;
 	if (cur_offset != PROLOGUE_OFFSET) {
 		pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
 			    cur_offset, PROLOGUE_OFFSET);
 		return -1;
 	}
+
+	/* 4 byte extra for skb_copy_bits buffer */
+	ctx->stack_size = prog->aux->stack_depth + 4;
+	ctx->stack_size = STACK_ALIGN(ctx->stack_size);
+
+	/* Set up function call stack */
+	emit(A64_SUB_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 	return 0;
 }
 
@@ -260,11 +261,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit(A64_LDR64(prg, tmp, prg), ctx);
 	emit(A64_CBZ(1, prg, jmp_offset), ctx);
 
-	/* goto *(prog->bpf_func + prologue_size); */
+	/* goto *(prog->bpf_func + prologue_offset); */
 	off = offsetof(struct bpf_prog, bpf_func);
 	emit_a64_mov_i64(tmp, off, ctx);
 	emit(A64_LDR64(tmp, prg, tmp), ctx);
 	emit(A64_ADD_I(1, tmp, tmp, sizeof(u32) * PROLOGUE_OFFSET), ctx);
+	emit(A64_ADD_I(1, A64_SP, A64_SP, ctx->stack_size), ctx);
 	emit(A64_BR(tmp), ctx);
 
 	/* out: */

arch/ia64/include/asm/atomic.h

@@ -65,29 +65,30 @@ ia64_atomic_fetch_##op (int i, atomic_t *v)				\
 ATOMIC_OPS(add, +)
 ATOMIC_OPS(sub, -)
 
-#define atomic_add_return(i,v)						\
+#ifdef __OPTIMIZE__
+#define __ia64_atomic_const(i)	__builtin_constant_p(i) ?		\
+		((i) == 1 || (i) == 4 || (i) == 8 || (i) == 16 ||	\
+		 (i) == -1 || (i) == -4 || (i) == -8 || (i) == -16) : 0
+
+#define atomic_add_return(i, v)						\
 ({									\
-	int __ia64_aar_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_aar_i ==  1) || (__ia64_aar_i ==   4)		\
-	     || (__ia64_aar_i ==  8) || (__ia64_aar_i ==  16)		\
-	     || (__ia64_aar_i == -1) || (__ia64_aar_i ==  -4)		\
-	     || (__ia64_aar_i == -8) || (__ia64_aar_i == -16)))		\
-		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
-		: ia64_atomic_add(__ia64_aar_i, v);			\
+	int __i = (i);							\
+	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
+	__ia64_atomic_p ? ia64_fetch_and_add(__i, &(v)->counter) :	\
+				ia64_atomic_add(__i, v);		\
 })
 
-#define atomic_sub_return(i,v)						\
+#define atomic_sub_return(i, v)						\
 ({									\
-	int __ia64_asr_i = (i);						\
-	(__builtin_constant_p(i)					\
-	 && (   (__ia64_asr_i ==   1) || (__ia64_asr_i ==   4)		\
-	     || (__ia64_asr_i ==   8) || (__ia64_asr_i ==  16)		\
-	     || (__ia64_asr_i ==  -1) || (__ia64_asr_i ==  -4)		\
-	     || (__ia64_asr_i ==  -8) || (__ia64_asr_i == -16)))	\
-		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
-		: ia64_atomic_sub(__ia64_asr_i, v);			\
+	int __i = (i);							\
+	static const int __ia64_atomic_p = __ia64_atomic_const(i);	\
+	__ia64_atomic_p ? ia64_fetch_and_add(-__i, &(v)->counter) :	\
+				ia64_atomic_sub(__i, v);		\
 })
+#else
+#define atomic_add_return(i, v)	ia64_atomic_add(i, v)
+#define atomic_sub_return(i, v)	ia64_atomic_sub(i, v)
+#endif
 
 #define atomic_fetch_add(i,v)						\
 ({									\

arch/ia64/kernel/time.c

@@ -88,7 +88,7 @@ void vtime_flush(struct task_struct *tsk)
 	}
 
 	if (ti->softirq_time) {
-		delta = cycle_to_nsec(ti->softirq_time));
+		delta = cycle_to_nsec(ti->softirq_time);
 		account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
 	}
 

arch/mips/Kconfig

@@ -259,6 +259,7 @@ config BCM47XX
 	select LEDS_GPIO_REGISTER
 	select BCM47XX_NVRAM
 	select BCM47XX_SPROM
+	select BCM47XX_SSB if !BCM47XX_BCMA
 	help
 	 Support for BCM47XX based boards
 
@@ -389,6 +390,7 @@ config LANTIQ
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_HAS_EARLY_PRINTK
 	select GPIOLIB
 	select SWAP_IO_SPACE
@@ -516,6 +518,7 @@ config MIPS_MALTA
 	select SYS_SUPPORTS_MIPS16
 	select SYS_SUPPORTS_MULTITHREADING
 	select SYS_SUPPORTS_SMARTMIPS
+	select SYS_SUPPORTS_VPE_LOADER
 	select SYS_SUPPORTS_ZBOOT
 	select SYS_SUPPORTS_RELOCATABLE
 	select USE_OF
@@ -2281,9 +2284,16 @@ config MIPSR2_TO_R6_EMULATOR
 	  The only reason this is a build-time option is to save ~14K from the
 	  final kernel image.
 
+config SYS_SUPPORTS_VPE_LOADER
+	bool
+	depends on SYS_SUPPORTS_MULTITHREADING
+	help
+	  Indicates that the platform supports the VPE loader, and provides
+	  physical_memsize.
+
 config MIPS_VPE_LOADER
 	bool "VPE loader support."
-	depends on SYS_SUPPORTS_MULTITHREADING && MODULES
+	depends on SYS_SUPPORTS_VPE_LOADER && MODULES
 	select CPU_MIPSR2_IRQ_VI
 	select CPU_MIPSR2_IRQ_EI
 	select MIPS_MT

arch/mips/Kconfig.debug

@@ -124,30 +124,36 @@ config SCACHE_DEBUGFS
 
 	  If unsure, say N.
 
-menuconfig MIPS_CPS_NS16550
+menuconfig MIPS_CPS_NS16550_BOOL
 	bool "CPS SMP NS16550 UART output"
 	depends on MIPS_CPS
 	help
 	  Output debug information via an ns16550 compatible UART if exceptions
 	  occur early in the boot process of a secondary core.
 
-if MIPS_CPS_NS16550
+if MIPS_CPS_NS16550_BOOL
+
+config MIPS_CPS_NS16550
+	def_bool MIPS_CPS_NS16550_BASE != 0
 
 config MIPS_CPS_NS16550_BASE
 	hex "UART Base Address"
 	default 0x1b0003f8 if MIPS_MALTA
+	default 0
 	help
 	  The base address of the ns16550 compatible UART on which to output
 	  debug information from the early stages of core startup.
 
+	  This is only used if non-zero.
+
 config MIPS_CPS_NS16550_SHIFT
 	int "UART Register Shift"
-	default 0 if MIPS_MALTA
+	default 0
 	help
 	  The number of bits to shift ns16550 register indices by in order to
 	  form their addresses. That is, log base 2 of the span between
 	  adjacent ns16550 registers in the system.
 
-endif # MIPS_CPS_NS16550
+endif # MIPS_CPS_NS16550_BOOL
 
 endmenu

arch/mips/ar7/platform.c

@@ -575,7 +575,7 @@ static int __init ar7_register_uarts(void)
 	uart_port.type		= PORT_AR7;
 	uart_port.uartclk	= clk_get_rate(bus_clk) / 2;
 	uart_port.iotype	= UPIO_MEM32;
-	uart_port.flags		= UPF_FIXED_TYPE;
+	uart_port.flags		= UPF_FIXED_TYPE | UPF_BOOT_AUTOCONF;
 	uart_port.regshift	= 2;
 
 	uart_port.line		= 0;

arch/mips/ath25/devices.c

@@ -73,6 +73,7 @@ const char *get_system_type(void)
 
 void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 {
+#ifdef CONFIG_SERIAL_8250_CONSOLE
 	struct uart_port s;
 
 	memset(&s, 0, sizeof(s));
@@ -85,6 +86,7 @@ void __init ath25_serial_setup(u32 mapbase, int irq, unsigned int uartclk)
 	s.uartclk = uartclk;
 
 	early_serial_setup(&s);
+#endif /* CONFIG_SERIAL_8250_CONSOLE */
 }
 
 int __init ath25_add_wmac(int nr, u32 base, int irq)

arch/mips/kernel/cps-vec.S

@@ -235,6 +235,7 @@ LEAF(mips_cps_core_init)
 	has_mt	t0, 3f
 
 	.set	push
+	.set	MIPS_ISA_LEVEL_RAW
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -388,6 +389,7 @@ LEAF(mips_cps_boot_vpes)
 #elif defined(CONFIG_MIPS_MT)
 
 	.set	push
+	.set	MIPS_ISA_LEVEL_RAW
 	.set	mt
 
 	/* If the core doesn't support MT then return */

arch/mips/kernel/mips-cm.c

@@ -292,7 +292,6 @@ void mips_cm_lock_other(unsigned int cluster, unsigned int core,
 				  *this_cpu_ptr(&cm_core_lock_flags));
 	} else {
 		WARN_ON(cluster != 0);
-		WARN_ON(vp != 0);
 		WARN_ON(block != CM_GCR_Cx_OTHER_BLOCK_LOCAL);
 
 		/*

arch/mips/kernel/process.c

@@ -705,6 +705,18 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	struct task_struct *t;
 	int max_users;
 
+	/* If nothing to change, return right away, successfully.  */
+	if (value == mips_get_process_fp_mode(task))
+		return 0;
+
+	/* Only accept a mode change if 64-bit FP enabled for o32.  */
+	if (!IS_ENABLED(CONFIG_MIPS_O32_FP64_SUPPORT))
+		return -EOPNOTSUPP;
+
+	/* And only for o32 tasks.  */
+	if (IS_ENABLED(CONFIG_64BIT) && !test_thread_flag(TIF_32BIT_REGS))
+		return -EOPNOTSUPP;
+
 	/* Check the value is valid */
 	if (value & ~known_bits)
 		return -EOPNOTSUPP;

arch/mips/kernel/ptrace.c

@@ -419,63 +419,160 @@ static int gpr64_set(struct task_struct *target,
 
 #endif /* CONFIG_64BIT */
 
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * !CONFIG_CPU_HAS_MSA variant.  FP context's general register slots
+ * correspond 1:1 to buffer slots.  Only general registers are copied.
+ */
+static int fpr_get_fpa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       void **kbuf, void __user **ubuf)
+{
+	return user_regset_copyout(pos, count, kbuf, ubuf,
+				   &target->thread.fpu,
+				   0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer,
+ * CONFIG_CPU_HAS_MSA variant.  Only lower 64 bits of FP context's
+ * general register slots are copied to buffer slots.  Only general
+ * registers are copied.
+ */
+static int fpr_get_msa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       void **kbuf, void __user **ubuf)
+{
+	unsigned int i;
+	u64 fpr_val;
+	int err;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS; i++) {
+		fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
+		err = user_regset_copyout(pos, count, kbuf, ubuf,
+					  &fpr_val, i * sizeof(elf_fpreg_t),
+					  (i + 1) * sizeof(elf_fpreg_t));
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+/*
+ * Copy the floating-point context to the supplied NT_PRFPREG buffer.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ */
 static int fpr_get(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   void *kbuf, void __user *ubuf)
 {
-	unsigned i;
+	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
 	int err;
-	u64 fpr_val;
 
-	/* XXX fcr31  */
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		err = fpr_get_fpa(target, &pos, &count, &kbuf, &ubuf);
+	else
+		err = fpr_get_msa(target, &pos, &count, &kbuf, &ubuf);
+	if (err)
+		return err;
 
-	if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
-		return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					   &target->thread.fpu,
-					   0, sizeof(elf_fpregset_t));
+	err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.fcr31,
+				  fcr31_pos, fcr31_pos + sizeof(u32));
 
-	for (i = 0; i < NUM_FPU_REGS; i++) {
-		fpr_val = get_fpr64(&target->thread.fpu.fpr[i], 0);
-		err = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-					  &fpr_val, i * sizeof(elf_fpreg_t),
-					  (i + 1) * sizeof(elf_fpreg_t));
+	return err;
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * !CONFIG_CPU_HAS_MSA variant.   Buffer slots correspond 1:1 to FP
+ * context's general register slots.  Only general registers are copied.
+ */
+static int fpr_set_fpa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       const void **kbuf, const void __user **ubuf)
+{
+	return user_regset_copyin(pos, count, kbuf, ubuf,
+				  &target->thread.fpu,
+				  0, NUM_FPU_REGS * sizeof(elf_fpreg_t));
+}
+
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context,
+ * CONFIG_CPU_HAS_MSA variant.  Buffer slots are copied to lower 64
+ * bits only of FP context's general register slots.  Only general
+ * registers are copied.
+ */
+static int fpr_set_msa(struct task_struct *target,
+		       unsigned int *pos, unsigned int *count,
+		       const void **kbuf, const void __user **ubuf)
+{
+	unsigned int i;
+	u64 fpr_val;
+	int err;
+
+	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
+	for (i = 0; i < NUM_FPU_REGS && *count > 0; i++) {
+		err = user_regset_copyin(pos, count, kbuf, ubuf,
+					 &fpr_val, i * sizeof(elf_fpreg_t),
+					 (i + 1) * sizeof(elf_fpreg_t));
 		if (err)
 			return err;
+		set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
 	}
 
 	return 0;
 }
 
+/*
+ * Copy the supplied NT_PRFPREG buffer to the floating-point context.
+ * Choose the appropriate helper for general registers, and then copy
+ * the FCSR register separately.
+ *
+ * We optimize for the case where `count % sizeof(elf_fpreg_t) == 0',
+ * which is supposed to have been guaranteed by the kernel before
+ * calling us, e.g. in `ptrace_regset'.  We enforce that requirement,
+ * so that we can safely avoid preinitializing temporaries for
+ * partial register writes.
+ */
 static int fpr_set(struct task_struct *target,
 		   const struct user_regset *regset,
 		   unsigned int pos, unsigned int count,
 		   const void *kbuf, const void __user *ubuf)
 {
-	unsigned i;
+	const int fcr31_pos = NUM_FPU_REGS * sizeof(elf_fpreg_t);
+	u32 fcr31;
 	int err;
-	u64 fpr_val;
 
-	/* XXX fcr31  */
+	BUG_ON(count % sizeof(elf_fpreg_t));
+
+	if (pos + count > sizeof(elf_fpregset_t))
+		return -EIO;
 
 	init_fp_ctx(target);
 
-	if (sizeof(target->thread.fpu.fpr[i]) == sizeof(elf_fpreg_t))
-		return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					  &target->thread.fpu,
-					  0, sizeof(elf_fpregset_t));
+	if (sizeof(target->thread.fpu.fpr[0]) == sizeof(elf_fpreg_t))
+		err = fpr_set_fpa(target, &pos, &count, &kbuf, &ubuf);
+	else
+		err = fpr_set_msa(target, &pos, &count, &kbuf, &ubuf);
+	if (err)
+		return err;
 
-	BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t));
-	for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) {
+	if (count > 0) {
 		err = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-					 &fpr_val, i * sizeof(elf_fpreg_t),
-					 (i + 1) * sizeof(elf_fpreg_t));
+					 &fcr31,
+					 fcr31_pos, fcr31_pos + sizeof(u32));
 		if (err)
 			return err;
-		set_fpr64(&target->thread.fpu.fpr[i], 0, fpr_val);
+
+		ptrace_setfcr31(target, fcr31);
 	}
 
-	return 0;
+	return err;
 }
 
 enum mips_regset {

arch/mips/lib/Makefile

@@ -16,4 +16,5 @@ obj-$(CONFIG_CPU_R3000)		+= r3k_dump_tlb.o
 obj-$(CONFIG_CPU_TX39XX)	+= r3k_dump_tlb.o
 
 # libgcc-style stuff needed in the kernel
-obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o ucmpdi2.o
+obj-y += ashldi3.o ashrdi3.o bswapsi.o bswapdi.o cmpdi2.o lshrdi3.o multi3.o \
+	 ucmpdi2.o

arch/mips/lib/libgcc.h

@@ -10,10 +10,18 @@ typedef int word_type __attribute__ ((mode (__word__)));
 struct DWstruct {
 	int high, low;
 };
+
+struct TWstruct {
+	long long high, low;
+};
 #elif defined(__LITTLE_ENDIAN)
 struct DWstruct {
 	int low, high;
 };
+
+struct TWstruct {
+	long long low, high;
+};
 #else
 #error I feel sick.
 #endif
@@ -23,4 +31,13 @@ typedef union {
 	long long ll;
 } DWunion;
 
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6)
+typedef int ti_type __attribute__((mode(TI)));
+
+typedef union {
+	struct TWstruct s;
+	ti_type ti;
+} TWunion;
+#endif
+
 #endif /* __ASM_LIBGCC_H */

arch/mips/lib/multi3.c

@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+
+#include "libgcc.h"
+
+/*
+ * GCC 7 suboptimally generates __multi3 calls for mips64r6, so for that
+ * specific case only we'll implement it here.
+ *
+ * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82981
+ */
+#if defined(CONFIG_64BIT) && defined(CONFIG_CPU_MIPSR6) && (__GNUC__ == 7)
+
+/* multiply 64-bit values, low 64-bits returned */
+static inline long long notrace dmulu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmulu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 64-bit unsigned values, high 64-bits of 128-bit result returned */
+static inline long long notrace dmuhu(long long a, long long b)
+{
+	long long res;
+
+	asm ("dmuhu %0,%1,%2" : "=r" (res) : "r" (a), "r" (b));
+	return res;
+}
+
+/* multiply 128-bit values, low 128-bits returned */
+ti_type notrace __multi3(ti_type a, ti_type b)
+{
+	TWunion res, aa, bb;
+
+	aa.ti = a;
+	bb.ti = b;
+
+	/*
+	 * a * b =           (a.lo * b.lo)
+	 *         + 2^64  * (a.hi * b.lo + a.lo * b.hi)
+	 *        [+ 2^128 * (a.hi * b.hi)]
+	 */
+	res.s.low = dmulu(aa.s.low, bb.s.low);
+	res.s.high = dmuhu(aa.s.low, bb.s.low);
+	res.s.high += dmulu(aa.s.high, bb.s.low);
+	res.s.high += dmulu(aa.s.low, bb.s.high);
+
+	return res.ti;
+}
+EXPORT_SYMBOL(__multi3);
+
+#endif /* 64BIT && CPU_MIPSR6 && GCC7 */

arch/mips/mm/uasm-micromips.c

@@ -40,7 +40,7 @@
 
 #include "uasm.c"
 
-static const struct insn const insn_table_MM[insn_invalid] = {
+static const struct insn insn_table_MM[insn_invalid] = {
 	[insn_addu]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_addu32_op), RT | RS | RD},
 	[insn_addiu]	= {M(mm_addiu32_op, 0, 0, 0, 0, 0), RT | RS | SIMM},
 	[insn_and]	= {M(mm_pool32a_op, 0, 0, 0, 0, mm_and_op), RT | RS | RD},

arch/mips/ralink/timer.c

@@ -109,9 +109,9 @@ static int rt_timer_probe(struct platform_device *pdev)
 	}
 
 	rt->irq = platform_get_irq(pdev, 0);
-	if (!rt->irq) {
+	if (rt->irq < 0) {
 		dev_err(&pdev->dev, "failed to load irq\n");
-		return -ENOENT;
+		return rt->irq;
 	}
 
 	rt->membase = devm_ioremap_resource(&pdev->dev, res);

arch/mips/rb532/Makefile

@@ -2,4 +2,6 @@
 # Makefile for the RB532 board specific parts of the kernel
 #
 
-obj-y	 += irq.o time.o setup.o serial.o prom.o gpio.o devices.o
+obj-$(CONFIG_SERIAL_8250_CONSOLE) += serial.o
+
+obj-y	 += irq.o time.o setup.o prom.o gpio.o devices.o

arch/mips/rb532/devices.c

@@ -310,6 +310,8 @@ static int __init plat_setup_devices(void)
 	return platform_add_devices(rb532_devs, ARRAY_SIZE(rb532_devs));
 }
 
+#ifdef CONFIG_NET
+
 static int __init setup_kmac(char *s)
 {
 	printk(KERN_INFO "korina mac = %s\n", s);
@@ -322,4 +324,6 @@ static int __init setup_kmac(char *s)
 
 __setup("kmac=", setup_kmac);
 
+#endif /* CONFIG_NET */
+
 arch_initcall(plat_setup_devices);

arch/parisc/include/asm/ldcw.h

@@ -12,6 +12,7 @@
    for the semaphore.  */
 
 #define __PA_LDCW_ALIGNMENT	16
+#define __PA_LDCW_ALIGN_ORDER	4
 #define __ldcw_align(a) ({					\
 	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
 	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
@@ -29,6 +30,7 @@
    ldcd). */
 
 #define __PA_LDCW_ALIGNMENT	4
+#define __PA_LDCW_ALIGN_ORDER	2
 #define __ldcw_align(a) (&(a)->slock)
 #define __LDCW	"ldcw,co"
 

arch/parisc/kernel/drivers.c

@@ -870,7 +870,7 @@ static void print_parisc_device(struct parisc_device *dev)
 	static int count;
 
 	print_pa_hwpath(dev, hw_path);
-	printk(KERN_INFO "%d. %s at 0x%p [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
+	printk(KERN_INFO "%d. %s at 0x%px [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
 		++count, dev->name, (void*) dev->hpa.start, hw_path, dev->id.hw_type,
 		dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
 

arch/parisc/kernel/entry.S

@@ -35,6 +35,7 @@
 #include <asm/pgtable.h>
 #include <asm/signal.h>
 #include <asm/unistd.h>
+#include <asm/ldcw.h>
 #include <asm/thread_info.h>
 
 #include <linux/linkage.h>
@@ -46,6 +47,14 @@
 #endif
 
 	.import		pa_tlb_lock,data
+	.macro  load_pa_tlb_lock reg
+#if __PA_LDCW_ALIGNMENT > 4
+	load32	PA(pa_tlb_lock) + __PA_LDCW_ALIGNMENT-1, \reg
+	depi	0,31,__PA_LDCW_ALIGN_ORDER, \reg
+#else
+	load32	PA(pa_tlb_lock), \reg
+#endif
+	.endm
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -457,7 +466,7 @@
 	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_tlb_lock),\tmp
+	load_pa_tlb_lock \tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
@@ -480,7 +489,7 @@
 	/* Release pa_tlb_lock lock. */
 	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_tlb_lock),\tmp
+	load_pa_tlb_lock \tmp
 	tlb_unlock0	\spc,\tmp
 #endif
 	.endm

arch/parisc/kernel/pacache.S

@@ -36,6 +36,7 @@
 #include <asm/assembly.h>
 #include <asm/pgtable.h>
 #include <asm/cache.h>
+#include <asm/ldcw.h>
 #include <linux/linkage.h>
 
 	.text
@@ -333,8 +334,12 @@ ENDPROC_CFI(flush_data_cache_local)
 
 	.macro	tlb_lock	la,flags,tmp
 #ifdef CONFIG_SMP
-	ldil		L%pa_tlb_lock,%r1
-	ldo		R%pa_tlb_lock(%r1),\la
+#if __PA_LDCW_ALIGNMENT > 4
+	load32		pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
+	depi		0,31,__PA_LDCW_ALIGN_ORDER, \la
+#else
+	load32		pa_tlb_lock, \la
+#endif
 	rsm		PSW_SM_I,\flags
 1:	LDCW		0(\la),\tmp
 	cmpib,<>,n	0,\tmp,3f

arch/parisc/kernel/process.c

@@ -39,6 +39,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/personality.h>
 #include <linux/ptrace.h>
@@ -183,6 +184,44 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r)
 	return 1;
 }
 
+/*
+ * Idle thread support
+ *
+ * Detect when running on QEMU with SeaBIOS PDC Firmware and let
+ * QEMU idle the host too.
+ */
+
+int running_on_qemu __read_mostly;
+
+void __cpuidle arch_cpu_idle_dead(void)
+{
+	/* nop on real hardware, qemu will offline CPU. */
+	asm volatile("or %%r31,%%r31,%%r31\n":::);
+}
+
+void __cpuidle arch_cpu_idle(void)
+{
+	local_irq_enable();
+
+	/* nop on real hardware, qemu will idle sleep. */
+	asm volatile("or %%r10,%%r10,%%r10\n":::);
+}
+
+static int __init parisc_idle_init(void)
+{
+	const char *marker;
+
+	/* check QEMU/SeaBIOS marker in PAGE0 */
+	marker = (char *) &PAGE0->pad0;
+	running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
+
+	if (!running_on_qemu)
+		cpu_idle_poll_ctrl(1);
+
+	return 0;
+}
+arch_initcall(parisc_idle_init);
+
 /*
  * Copy architecture-specific thread state
  */

arch/parisc/mm/init.c

@@ -631,11 +631,11 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 #ifdef CONFIG_DEBUG_KERNEL /* double-sanity-check paranoia */
 	printk("virtual kernel memory layout:\n"
-	       "    vmalloc : 0x%p - 0x%p   (%4ld MB)\n"
-	       "    memory  : 0x%p - 0x%p   (%4ld MB)\n"
-	       "      .init : 0x%p - 0x%p   (%4ld kB)\n"
-	       "      .data : 0x%p - 0x%p   (%4ld kB)\n"
-	       "      .text : 0x%p - 0x%p   (%4ld kB)\n",
+	       "    vmalloc : 0x%px - 0x%px   (%4ld MB)\n"
+	       "    memory  : 0x%px - 0x%px   (%4ld MB)\n"
+	       "      .init : 0x%px - 0x%px   (%4ld kB)\n"
+	       "      .data : 0x%px - 0x%px   (%4ld kB)\n"
+	       "      .text : 0x%px - 0x%px   (%4ld kB)\n",
 
 	       (void*)VMALLOC_START, (void*)VMALLOC_END,
 	       (VMALLOC_END - VMALLOC_START) >> 20,

arch/powerpc/Kconfig

@@ -166,6 +166,7 @@ config PPC
 	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES	if PPC_BOOK3S_64
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
 	select GENERIC_SMP_IDLE_THREAD

arch/powerpc/include/asm/exception-64e.h

@@ -209,5 +209,11 @@ exc_##label##_book3e:
 	ori	r3,r3,vector_offset@l;		\
 	mtspr	SPRN_IVOR##vector_number,r3;
 
+#define RFI_TO_KERNEL							\
+	rfi
+
+#define RFI_TO_USER							\
+	rfi
+
 #endif /* _ASM_POWERPC_EXCEPTION_64E_H */
 

arch/powerpc/include/asm/exception-64s.h

@@ -74,6 +74,59 @@
  */
 #define EX_R3		EX_DAR
 
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ */
+#define RFI_FLUSH_SLOT							\
+	RFI_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop
+
+#define RFI_TO_KERNEL							\
+	rfid
+
+#define RFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define HRFI_TO_KERNEL							\
+	hrfid
+
+#define HRFI_TO_USER							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_GUEST							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN							\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
 #ifdef CONFIG_RELOCATABLE
 #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h)			\
 	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
@@ -218,7 +271,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 #define EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
@@ -232,7 +285,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 	mtspr	SPRN_##h##SRR0,r12;					\
 	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
 	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
+	h##RFI_TO_KERNEL;						\
 	b	.	/* prevent speculative execution */
 
 #define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h)			\

arch/powerpc/include/asm/feature-fixups.h

@@ -187,7 +187,20 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET label##1b-label##3b;		\
 	.popsection;
 
+#define RFI_FLUSH_FIXUP_SECTION				\
+951:							\
+	.pushsection __rfi_flush_fixup,"a";		\
+	.align 2;					\
+952:							\
+	FTR_ENTRY_OFFSET 951b-952b;			\
+	.popsection;
+
+
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
+
 void apply_feature_fixups(void);
 void setup_feature_keys(void);
 #endif

arch/powerpc/include/asm/hvcall.h

@@ -241,6 +241,7 @@
 #define H_GET_HCA_INFO          0x1B8
 #define H_GET_PERF_COUNT        0x1BC
 #define H_MANAGE_TRACE          0x1C0
+#define H_GET_CPU_CHARACTERISTICS 0x1C8
 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4
 #define H_QUERY_INT_STATE       0x1E4
 #define H_POLL_PENDING		0x1D8
@@ -330,6 +331,17 @@
 #define H_SIGNAL_SYS_RESET_ALL_OTHERS		-2
 /* >= 0 values are CPU number */
 
+/* H_GET_CPU_CHARACTERISTICS return values */
+#define H_CPU_CHAR_SPEC_BAR_ORI31	(1ull << 63) // IBM bit 0
+#define H_CPU_CHAR_BCCTRL_SERIALISED	(1ull << 62) // IBM bit 1
+#define H_CPU_CHAR_L1D_FLUSH_ORI30	(1ull << 61) // IBM bit 2
+#define H_CPU_CHAR_L1D_FLUSH_TRIG2	(1ull << 60) // IBM bit 3
+#define H_CPU_CHAR_L1D_THREAD_PRIV	(1ull << 59) // IBM bit 4
+
+#define H_CPU_BEHAV_FAVOUR_SECURITY	(1ull << 63) // IBM bit 0
+#define H_CPU_BEHAV_L1D_FLUSH_PR	(1ull << 62) // IBM bit 1
+#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ull << 61) // IBM bit 2
+
 /* Flag values used in H_REGISTER_PROC_TBL hcall */
 #define PROC_TABLE_OP_MASK	0x18
 #define PROC_TABLE_DEREG	0x10
@@ -341,6 +353,7 @@
 #define PROC_TABLE_GTSE		0x01
 
 #ifndef __ASSEMBLY__
+#include <linux/types.h>
 
 /**
  * plpar_hcall_norets: - Make a pseries hypervisor call with no return arguments
@@ -436,6 +449,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc)
 	}
 }
 
+struct h_cpu_char_result {
+	u64 character;
+	u64 behaviour;
+};
+
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */

arch/powerpc/include/asm/paca.h

@@ -232,6 +232,16 @@ struct paca_struct {
 	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 #endif
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * rfi fallback flush must be in its own cacheline to prevent
+	 * other paca data leaking into the L1d
+	 */
+	u64 exrfi[EX_SIZE] __aligned(0x80);
+	void *rfi_flush_fallback_area;
+	u64 l1d_flush_congruence;
+	u64 l1d_flush_sets;
+#endif
 };
 
 extern void copy_mm_to_paca(struct mm_struct *mm);

arch/powerpc/include/asm/plpar_wrappers.h

@@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu)
 	return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu);
 }
 
+static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p)
+{
+	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
+	long rc;
+
+	rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf);
+	if (rc == H_SUCCESS) {
+		p->character = retbuf[0];
+		p->behaviour = retbuf[1];
+	}
+
+	return rc;
+}
+
 #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */

arch/powerpc/include/asm/setup.h

@@ -39,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {}
 static inline void pseries_little_endian_exceptions(void) {}
 #endif /* CONFIG_PPC_PSERIES */
 
+void rfi_flush_enable(bool enable);
+
+/* These are bit flags */
+enum l1d_flush_type {
+	L1D_FLUSH_NONE		= 0x1,
+	L1D_FLUSH_FALLBACK	= 0x2,
+	L1D_FLUSH_ORI		= 0x4,
+	L1D_FLUSH_MTTRIG	= 0x8,
+};
+
+void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void do_rfi_flush_fixups(enum l1d_flush_type types);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif	/* _ASM_POWERPC_SETUP_H */

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

@@ -443,6 +443,31 @@ struct kvm_ppc_rmmu_info {
 	__u32	ap_encodings[8];
 };
 
+/* For KVM_PPC_GET_CPU_CHAR */
+struct kvm_ppc_cpu_char {
+	__u64	character;		/* characteristics of the CPU */
+	__u64	behaviour;		/* recommended software behaviour */
+	__u64	character_mask;		/* valid bits in character */
+	__u64	behaviour_mask;		/* valid bits in behaviour */
+};
+
+/*
+ * Values for character and character_mask.
+ * These are identical to the values used by H_GET_CPU_CHARACTERISTICS.
+ */
+#define KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31		(1ULL << 63)
+#define KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED	(1ULL << 62)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30	(1ULL << 61)
+#define KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2	(1ULL << 60)
+#define KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV	(1ULL << 59)
+#define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
+#define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
+#define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+
+#define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
+#define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
+#define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
 

arch/powerpc/kernel/asm-offsets.c

@@ -237,6 +237,11 @@ int main(void)
 	OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp);
 	OFFSET(PACA_IN_MCE, paca_struct, in_mce);
 	OFFSET(PACA_IN_NMI, paca_struct, in_nmi);
+	OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area);
+	OFFSET(PACA_EXRFI, paca_struct, exrfi);
+	OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence);
+	OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets);
+
 #endif
 	OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id);
 	OFFSET(PACAKEXECSTATE, paca_struct, kexec_state);

arch/powerpc/kernel/entry_64.S

@@ -37,6 +37,11 @@
 #include <asm/tm.h>
 #include <asm/ppc-opcode.h>
 #include <asm/export.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
 
 /*
  * System calls.
@@ -262,13 +267,23 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	ld	r2,GPR2(r1)
+	ld	r1,GPR1(r1)
+	mtlr	r4
+	mtcr	r5
+	mtspr	SPRN_SRR0,r7
+	mtspr	SPRN_SRR1,r8
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+
+	/* exit to kernel */
 1:	ld	r2,GPR2(r1)
 	ld	r1,GPR1(r1)
 	mtlr	r4
 	mtcr	r5
 	mtspr	SPRN_SRR0,r7
 	mtspr	SPRN_SRR1,r8
-	RFI
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 .Lsyscall_error:
@@ -397,8 +412,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	mtmsrd	r10, 1
 	mtspr	SPRN_SRR0, r11
 	mtspr	SPRN_SRR1, r12
-
-	rfid
+	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
 _ASM_NOKPROBE_SYMBOL(system_call_common);
@@ -878,7 +892,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
 	REST_GPR(13, r1)
-1:
+
 	mtspr	SPRN_SRR1,r3
 
 	ld	r2,_CCR(r1)
@@ -891,8 +905,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	ld	r3,GPR3(r1)
 	ld	r4,GPR4(r1)
 	ld	r1,GPR1(r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
 
-	rfid
+1:	mtspr	SPRN_SRR1,r3
+
+	ld	r2,_CCR(r1)
+	mtcrf	0xFF,r2
+	ld	r2,_NIP(r1)
+	mtspr	SPRN_SRR0,r2
+
+	ld	r0,GPR0(r1)
+	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r4,GPR4(r1)
+	ld	r1,GPR1(r1)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 #endif /* CONFIG_PPC_BOOK3E */
@@ -1073,7 +1101,7 @@ __enter_rtas:
 	
 	mtspr	SPRN_SRR0,r5
 	mtspr	SPRN_SRR1,r6
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
 rtas_return_loc:
@@ -1098,7 +1126,7 @@ rtas_return_loc:
 
 	mtspr	SPRN_SRR0,r3
 	mtspr	SPRN_SRR1,r4
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 _ASM_NOKPROBE_SYMBOL(__enter_rtas)
 _ASM_NOKPROBE_SYMBOL(rtas_return_loc)
@@ -1171,7 +1199,7 @@ _GLOBAL(enter_prom)
 	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
 	andc	r11,r11,r12
 	mtsrr1	r11
-	rfid
+	RFI_TO_KERNEL
 #endif /* CONFIG_PPC_BOOK3E */
 
 1:	/* Return from OF */

arch/powerpc/kernel/exceptions-64s.S

@@ -256,7 +256,7 @@ BEGIN_FTR_SECTION
 	LOAD_HANDLER(r12, machine_check_handle_early)
 1:	mtspr	SPRN_SRR0,r12
 	mtspr	SPRN_SRR1,r11
-	rfid
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 2:
 	/* Stack overflow. Stay on emergency stack and panic.
@@ -445,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	li	r3,MSR_ME
 	andc	r10,r10,r3		/* Turn off MSR_ME */
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 2:
 	/*
@@ -463,7 +463,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early)
 	 */
 	bl	machine_check_queue_event
 	MACHINE_CHECK_HANDLER_WINDUP
-	rfid
+	RFI_TO_USER_OR_KERNEL
 9:
 	/* Deliver the machine check to host kernel in V mode. */
 	MACHINE_CHECK_HANDLER_WINDUP
@@ -598,6 +598,9 @@ EXC_COMMON_BEGIN(slb_miss_common)
 	stw	r9,PACA_EXSLB+EX_CCR(r13)	/* save CR in exc. frame */
 	std	r10,PACA_EXSLB+EX_LR(r13)	/* save LR */
 
+	andi.	r9,r11,MSR_PR	// Check for exception from userspace
+	cmpdi	cr4,r9,MSR_PR	// And save the result in CR4 for later
+
 	/*
 	 * Test MSR_RI before calling slb_allocate_realmode, because the
 	 * MSR in r11 gets clobbered. However we still want to allocate
@@ -624,9 +627,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 
 	/* All done -- return from exception. */
 
+	bne	cr4,1f		/* returning to kernel */
+
 .machine	push
 .machine	"power4"
 	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
 	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
 	mtcrf	0x02,r9		/* I/D indication is in cr6 */
 	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
@@ -640,9 +646,30 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	ld	r11,PACA_EXSLB+EX_R11(r13)
 	ld	r12,PACA_EXSLB+EX_R12(r13)
 	ld	r13,PACA_EXSLB+EX_R13(r13)
-	rfid
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
+1:
+.machine	push
+.machine	"power4"
+	mtcrf	0x80,r9
+	mtcrf	0x08,r9		/* MSR[PR] indication is in cr4 */
+	mtcrf	0x04,r9		/* MSR[RI] indication is in cr5 */
+	mtcrf	0x02,r9		/* I/D indication is in cr6 */
+	mtcrf	0x01,r9		/* slb_allocate uses cr0 and cr7 */
+.machine	pop
+
+	RESTORE_CTR(r9, PACA_EXSLB)
+	RESTORE_PPR_PACA(PACA_EXSLB, r9)
+	mr	r3,r12
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	ld	r11,PACA_EXSLB+EX_R11(r13)
+	ld	r12,PACA_EXSLB+EX_R12(r13)
+	ld	r13,PACA_EXSLB+EX_R13(r13)
+	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
+
 2:	std     r3,PACA_EXSLB+EX_DAR(r13)
 	mr	r3,r12
 	mfspr	r11,SPRN_SRR0
@@ -651,7 +678,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 8:	std     r3,PACA_EXSLB+EX_DAR(r13)
@@ -662,7 +689,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX)
 	mtspr	SPRN_SRR0,r10
 	ld	r10,PACAKMSR(r13)
 	mtspr	SPRN_SRR1,r10
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 EXC_COMMON_BEGIN(unrecov_slb)
@@ -901,7 +928,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception)
 	mtspr	SPRN_SRR0,r10 ; 				\
 	ld	r10,PACAKMSR(r13) ;				\
 	mtspr	SPRN_SRR1,r10 ; 				\
-	rfid ; 							\
+	RFI_TO_KERNEL ;						\
 	b	. ;	/* prevent speculative execution */
 
 #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH
@@ -917,7 +944,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)				\
 	xori	r12,r12,MSR_LE ;				\
 	mtspr	SPRN_SRR1,r12 ;					\
 	mr	r13,r9 ;					\
-	rfid ;		/* return to userspace */		\
+	RFI_TO_USER ;	/* return to userspace */		\
 	b	. ;	/* prevent speculative execution */
 #else
 #define SYSCALL_FASTENDIAN_TEST
@@ -1063,7 +1090,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early)
 	mtcr	r11
 	REST_GPR(11, r1)
 	ld	r1,GPR1(r1)
-	hrfid
+	HRFI_TO_USER_OR_KERNEL
 
 1:	mtcr	r11
 	REST_GPR(11, r1)
@@ -1314,7 +1341,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	ld	r11,PACA_EXGEN+EX_R11(r13)
 	ld	r12,PACA_EXGEN+EX_R12(r13)
 	ld	r13,PACA_EXGEN+EX_R13(r13)
-	HRFID
+	HRFI_TO_UNKNOWN
 	b	.
 #endif
 
@@ -1418,10 +1445,94 @@ masked_##_H##interrupt:					\
 	ld	r10,PACA_EXGEN+EX_R10(r13);		\
 	ld	r11,PACA_EXGEN+EX_R11(r13);		\
 	/* returns to kernel where r13 must be set up, so don't restore it */ \
-	##_H##rfid;					\
+	##_H##RFI_TO_KERNEL;				\
 	b	.;					\
 	MASKED_DEC_HANDLER(_H)
 
+TRAMP_REAL_BEGIN(rfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	rfid
+
+TRAMP_REAL_BEGIN(hrfi_flush_fallback)
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	std	r12,PACA_EXRFI+EX_R12(r13)
+	std	r8,PACA_EXRFI+EX_R13(r13)
+	mfctr	r9
+	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+	ld	r11,PACA_L1D_FLUSH_SETS(r13)
+	ld	r12,PACA_L1D_FLUSH_CONGRUENCE(r13)
+	/*
+	 * The load adresses are at staggered offsets within cachelines,
+	 * which suits some pipelines better (on others it should not
+	 * hurt).
+	 */
+	addi	r12,r12,8
+	mtctr	r11
+	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+	/* order ld/st prior to dcbt stop all streams with flushing */
+	sync
+1:	li	r8,0
+	.rept	8 /* 8-way set associative */
+	ldx	r11,r10,r8
+	add	r8,r8,r12
+	xor	r11,r11,r11	// Ensure r11 is 0 even if fallback area is not
+	add	r8,r8,r11	// Add 0, this creates a dependency on the ldx
+	.endr
+	addi	r10,r10,128 /* 128 byte cache line */
+	bdnz	1b
+
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	ld	r12,PACA_EXRFI+EX_R12(r13)
+	ld	r8,PACA_EXRFI+EX_R13(r13)
+	GET_SCRATCH0(r13);
+	hrfid
+
 /*
  * Real mode exceptions actually use this too, but alternate
  * instruction code patches (which end up in the common .text area)
@@ -1441,7 +1552,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_SRR0, r13
 	GET_SCRATCH0(r13)
-	rfid
+	RFI_TO_KERNEL
 	b	.
 
 TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
@@ -1453,7 +1564,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt)
 	addi	r13, r13, 4
 	mtspr	SPRN_HSRR0, r13
 	GET_SCRATCH0(r13)
-	hrfid
+	HRFI_TO_KERNEL
 	b	.
 #endif
 

arch/powerpc/kernel/setup-common.c

@@ -242,14 +242,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	unsigned short maj;
 	unsigned short min;
 
-	/* We only show online cpus: disable preempt (overzealous, I
-	 * knew) to prevent cpu going down. */
-	preempt_disable();
-	if (!cpu_online(cpu_id)) {
-		preempt_enable();
-		return 0;
-	}
-
 #ifdef CONFIG_SMP
 	pvr = per_cpu(cpu_pvr, cpu_id);
 #else
@@ -358,9 +350,6 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 #ifdef CONFIG_SMP
 	seq_printf(m, "\n");
 #endif
-
-	preempt_enable();
-
 	/* If this is the last cpu, print the summary */
 	if (cpumask_next(cpu_id, cpu_online_mask) >= nr_cpu_ids)
 		show_cpuinfo_summary(m);

arch/powerpc/kernel/setup_64.c

@@ -38,6 +38,7 @@
 #include <linux/memory.h>
 #include <linux/nmi.h>
 
+#include <asm/debugfs.h>
 #include <asm/io.h>
 #include <asm/kdump.h>
 #include <asm/prom.h>
@@ -801,3 +802,141 @@ static int __init disable_hardlockup_detector(void)
 	return 0;
 }
 early_initcall(disable_hardlockup_detector);
+
+#ifdef CONFIG_PPC_BOOK3S_64
+static enum l1d_flush_type enabled_flush_types;
+static void *l1d_flush_fallback_area;
+static bool no_rfi_flush;
+bool rfi_flush;
+
+static int __init handle_no_rfi_flush(char *p)
+{
+	pr_info("rfi-flush: disabled on command line.");
+	no_rfi_flush = true;
+	return 0;
+}
+early_param("no_rfi_flush", handle_no_rfi_flush);
+
+/*
+ * The RFI flush is not KPTI, but because users will see doco that says to use
+ * nopti we hijack that option here to also disable the RFI flush.
+ */
+static int __init handle_no_pti(char *p)
+{
+	pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
+	handle_no_rfi_flush(NULL);
+	return 0;
+}
+early_param("nopti", handle_no_pti);
+
+static void do_nothing(void *unused)
+{
+	/*
+	 * We don't need to do the flush explicitly, just enter+exit kernel is
+	 * sufficient, the RFI exit handlers will do the right thing.
+	 */
+}
+
+void rfi_flush_enable(bool enable)
+{
+	if (rfi_flush == enable)
+		return;
+
+	if (enable) {
+		do_rfi_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else
+		do_rfi_flush_fixups(L1D_FLUSH_NONE);
+
+	rfi_flush = enable;
+}
+
+static void init_fallback_flush(void)
+{
+	u64 l1d_size, limit;
+	int cpu;
+
+	l1d_size = ppc64_caches.l1d.size;
+	limit = min(safe_stack_limit(), ppc64_rma_size);
+
+	/*
+	 * Align to L1d size, and size it at 2x L1d size, to catch possible
+	 * hardware prefetch runoff. We don't have a recipe for load patterns to
+	 * reliably avoid the prefetcher.
+	 */
+	l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
+	memset(l1d_flush_fallback_area, 0, l1d_size * 2);
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * The fallback flush is currently coded for 8-way
+		 * associativity. Different associativity is possible, but it
+		 * will be treated as 8-way and may not evict the lines as
+		 * effectively.
+		 *
+		 * 128 byte lines are mandatory.
+		 */
+		u64 c = l1d_size / 8;
+
+		paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
+		paca[cpu].l1d_flush_congruence = c;
+		paca[cpu].l1d_flush_sets = c / 128;
+	}
+}
+
+void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+{
+	if (types & L1D_FLUSH_FALLBACK) {
+		pr_info("rfi-flush: Using fallback displacement flush\n");
+		init_fallback_flush();
+	}
+
+	if (types & L1D_FLUSH_ORI)
+		pr_info("rfi-flush: Using ori type flush\n");
+
+	if (types & L1D_FLUSH_MTTRIG)
+		pr_info("rfi-flush: Using mttrig type flush\n");
+
+	enabled_flush_types = types;
+
+	if (!no_rfi_flush)
+		rfi_flush_enable(enable);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int rfi_flush_set(void *data, u64 val)
+{
+	if (val == 1)
+		rfi_flush_enable(true);
+	else if (val == 0)
+		rfi_flush_enable(false);
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int rfi_flush_get(void *data, u64 *val)
+{
+	*val = rfi_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+
+static __init int rfi_flush_debugfs_init(void)
+{
+	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+	return 0;
+}
+device_initcall(rfi_flush_debugfs_init);
+#endif
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	if (rfi_flush)
+		return sprintf(buf, "Mitigation: RFI Flush\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */

arch/powerpc/kernel/vmlinux.lds.S

@@ -132,6 +132,15 @@ SECTIONS
 	/* Read-only data */
 	RO_DATA(PAGE_SIZE)
 
+#ifdef CONFIG_PPC64
+	. = ALIGN(8);
+	__rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) {
+		__start___rfi_flush_fixup = .;
+		*(__rfi_flush_fixup)
+		__stop___rfi_flush_fixup = .;
+	}
+#endif
+
 	EXCEPTION_TABLE(0)
 
 	NOTES :kernel :notes

arch/powerpc/kvm/book3s_64_mmu.c

@@ -235,6 +235,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		gpte->may_read = true;
 		gpte->may_write = true;
 		gpte->page_size = MMU_PAGE_4K;
+		gpte->wimg = HPTE_R_M;
 
 		return 0;
 	}

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -65,11 +65,17 @@ struct kvm_resize_hpt {
 	u32 order;
 
 	/* These fields protected by kvm->lock */
+
+	/* Possible values and their usage:
+	 *  <0     an error occurred during allocation,
+	 *  -EBUSY allocation is in the progress,
+	 *  0      allocation made successfuly.
+	 */
 	int error;
-	bool prepare_done;
 
-	/* Private to the work thread, until prepare_done is true,
-	 * then protected by kvm->resize_hpt_sem */
+	/* Private to the work thread, until error != -EBUSY,
+	 * then protected by kvm->lock.
+	 */
 	struct kvm_hpt_info hpt;
 };
 
@@ -159,8 +165,6 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 		 * Reset all the reverse-mapping chains for all memslots
 		 */
 		kvmppc_rmap_reset(kvm);
-		/* Ensure that each vcpu will flush its TLB on next entry. */
-		cpumask_setall(&kvm->arch.need_tlb_flush);
 		err = 0;
 		goto out;
 	}
@@ -176,6 +180,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 	kvmppc_set_hpt(kvm, &info);
 
 out:
+	if (err == 0)
+		/* Ensure that each vcpu will flush its TLB on next entry. */
+		cpumask_setall(&kvm->arch.need_tlb_flush);
+
 	mutex_unlock(&kvm->lock);
 	return err;
 }
@@ -1413,16 +1421,20 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)
 
 static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
 {
-	BUG_ON(kvm->arch.resize_hpt != resize);
+	if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+		return;
 
 	if (!resize)
 		return;
 
-	if (resize->hpt.virt)
-		kvmppc_free_hpt(&resize->hpt);
+	if (resize->error != -EBUSY) {
+		if (resize->hpt.virt)
+			kvmppc_free_hpt(&resize->hpt);
+		kfree(resize);
+	}
 
-	kvm->arch.resize_hpt = NULL;
-	kfree(resize);
+	if (kvm->arch.resize_hpt == resize)
+		kvm->arch.resize_hpt = NULL;
 }
 
 static void resize_hpt_prepare_work(struct work_struct *work)
@@ -1431,17 +1443,41 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 						     struct kvm_resize_hpt,
 						     work);
 	struct kvm *kvm = resize->kvm;
-	int err;
+	int err = 0;
 
-	resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
-			 resize->order);
-
-	err = resize_hpt_allocate(resize);
+	if (WARN_ON(resize->error != -EBUSY))
+		return;
 
 	mutex_lock(&kvm->lock);
 
+	/* Request is still current? */
+	if (kvm->arch.resize_hpt == resize) {
+		/* We may request large allocations here:
+		 * do not sleep with kvm->lock held for a while.
+		 */
+		mutex_unlock(&kvm->lock);
+
+		resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
+				 resize->order);
+
+		err = resize_hpt_allocate(resize);
+
+		/* We have strict assumption about -EBUSY
+		 * when preparing for HPT resize.
+		 */
+		if (WARN_ON(err == -EBUSY))
+			err = -EINPROGRESS;
+
+		mutex_lock(&kvm->lock);
+		/* It is possible that kvm->arch.resize_hpt != resize
+		 * after we grab kvm->lock again.
+		 */
+	}
+
 	resize->error = err;
-	resize->prepare_done = true;
+
+	if (kvm->arch.resize_hpt != resize)
+		resize_hpt_release(kvm, resize);
 
 	mutex_unlock(&kvm->lock);
 }
@@ -1466,14 +1502,12 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 
 	if (resize) {
 		if (resize->order == shift) {
-			/* Suitable resize in progress */
-			if (resize->prepare_done) {
-				ret = resize->error;
-				if (ret != 0)
-					resize_hpt_release(kvm, resize);
-			} else {
+			/* Suitable resize in progress? */
+			ret = resize->error;
+			if (ret == -EBUSY)
 				ret = 100; /* estimated time in ms */
-			}
+			else if (ret)
+				resize_hpt_release(kvm, resize);
 
 			goto out;
 		}
@@ -1493,6 +1527,8 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 		ret = -ENOMEM;
 		goto out;
 	}
+
+	resize->error = -EBUSY;
 	resize->order = shift;
 	resize->kvm = kvm;
 	INIT_WORK(&resize->work, resize_hpt_prepare_work);
@@ -1547,16 +1583,12 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
 	if (!resize || (resize->order != shift))
 		goto out;
 
-	ret = -EBUSY;
-	if (!resize->prepare_done)
-		goto out;
-
 	ret = resize->error;
-	if (ret != 0)
+	if (ret)
 		goto out;
 
 	ret = resize_hpt_rehash(resize);
-	if (ret != 0)
+	if (ret)
 		goto out;
 
 	resize_hpt_pivot(resize);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -79,7 +79,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline)
 	mtmsrd	r0,1		/* clear RI in MSR */
 	mtsrr0	r5
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 kvmppc_call_hv_entry:
 BEGIN_FTR_SECTION
@@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtmsrd	r6, 1			/* Clear RI in MSR */
 	mtsrr0	r8
 	mtsrr1	r7
-	RFI
+	RFI_TO_KERNEL
 
 	/* Virtual-mode return */
 .Lvirt_return:
@@ -1167,8 +1167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 	ld	r0, VCPU_GPR(R0)(r4)
 	ld	r4, VCPU_GPR(R4)(r4)
-
-	hrfid
+	HRFI_TO_GUEST
 	b	.
 
 secondary_too_late:
@@ -3320,7 +3319,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	ld	r4, PACAKMSR(r13)
 	mtspr	SPRN_SRR0, r3
 	mtspr	SPRN_SRR1, r4
-	rfid
+	RFI_TO_KERNEL
 9:	addi	r3, r1, STACK_FRAME_OVERHEAD
 	bl	kvmppc_bad_interrupt
 	b	9b

arch/powerpc/kvm/book3s_pr.c

@@ -60,6 +60,7 @@ static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 #define MSR_USER32 MSR_USER
 #define MSR_USER64 MSR_USER
 #define HW_PAGE_SIZE PAGE_SIZE
+#define HPTE_R_M   _PAGE_COHERENT
 #endif
 
 static bool kvmppc_is_split_real(struct kvm_vcpu *vcpu)
@@ -557,6 +558,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
 		pte.page_size = MMU_PAGE_64K;
+		pte.wimg = HPTE_R_M;
 	}
 
 	switch (kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) {

arch/powerpc/kvm/book3s_rmhandlers.S

@@ -46,6 +46,9 @@
 
 #define FUNC(name)		name
 
+#define RFI_TO_KERNEL	RFI
+#define RFI_TO_GUEST	RFI
+
 .macro INTERRUPT_TRAMPOLINE intno
 
 .global kvmppc_trampoline_\intno
@@ -141,7 +144,7 @@ kvmppc_handler_skip_ins:
 	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
-	RFI
+	RFI_TO_KERNEL
 #endif
 
 /*
@@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline)
 	ori	r5, r5, MSR_EE
 	mtsrr0	r7
 	mtsrr1	r6
-	RFI
+	RFI_TO_KERNEL
 
 #include "book3s_segment.S"

arch/powerpc/kvm/book3s_segment.S

@@ -156,7 +156,7 @@ no_dcbz32_on:
 	PPC_LL	r9, SVCPU_R9(r3)
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
-	RFI
+	RFI_TO_GUEST
 kvmppc_handler_trampoline_enter_end:
 
 
@@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	cmpwi	r12, BOOK3S_INTERRUPT_DOORBELL
 	beqa	BOOK3S_INTERRUPT_DOORBELL
 
-	RFI
+	RFI_TO_KERNEL
 kvmppc_handler_trampoline_exit_end:

arch/powerpc/kvm/powerpc.c

@@ -39,6 +39,10 @@
 #include <asm/iommu.h>
 #include <asm/switch_to.h>
 #include <asm/xive.h>
+#ifdef CONFIG_PPC_PSERIES
+#include <asm/hvcall.h>
+#include <asm/plpar_wrappers.h>
+#endif
 
 #include "timing.h"
 #include "irq.h"
@@ -548,6 +552,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_KVM_XICS
 	case KVM_CAP_IRQ_XICS:
 #endif
+	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
 
@@ -1759,6 +1764,124 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return r;
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * These functions check whether the underlying hardware is safe
+ * against attacks based on observing the effects of speculatively
+ * executed instructions, and whether it supplies instructions for
+ * use in workarounds.  The information comes from firmware, either
+ * via the device tree on powernv platforms or from an hcall on
+ * pseries platforms.
+ */
+#ifdef CONFIG_PPC_PSERIES
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct h_cpu_char_result c;
+	unsigned long rc;
+
+	if (!machine_is(pseries))
+		return -ENOTTY;
+
+	rc = plpar_get_cpu_characteristics(&c);
+	if (rc == H_SUCCESS) {
+		cp->character = c.character;
+		cp->behaviour = c.behaviour;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_BR_HINT_HONOURED |
+			KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+	}
+	return 0;
+}
+#else
+static int pseries_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	return -ENOTTY;
+}
+#endif
+
+static inline bool have_fw_feat(struct device_node *fw_features,
+				const char *state, const char *name)
+{
+	struct device_node *np;
+	bool r = false;
+
+	np = of_get_child_by_name(fw_features, name);
+	if (np) {
+		r = of_property_read_bool(np, state);
+		of_node_put(np);
+	}
+	return r;
+}
+
+static int kvmppc_get_cpu_char(struct kvm_ppc_cpu_char *cp)
+{
+	struct device_node *np, *fw_features;
+	int r;
+
+	memset(cp, 0, sizeof(*cp));
+	r = pseries_get_cpu_char(cp);
+	if (r != -ENOTTY)
+		return r;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	if (np) {
+		fw_features = of_get_child_by_name(np, "fw-features");
+		of_node_put(np);
+		if (!fw_features)
+			return 0;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-spec-barrier-ori31,31,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-bcctrl-serialized"))
+			cp->character |= KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-ori30,30,0"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30;
+		if (have_fw_feat(fw_features, "enabled",
+				 "inst-l1d-flush-trig2"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-l1d-thread-split"))
+			cp->character |= KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV;
+		if (have_fw_feat(fw_features, "enabled",
+				 "fw-count-cache-disabled"))
+			cp->character |= KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+		cp->character_mask = KVM_PPC_CPU_CHAR_SPEC_BAR_ORI31 |
+			KVM_PPC_CPU_CHAR_BCCTRL_SERIALISED |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_ORI30 |
+			KVM_PPC_CPU_CHAR_L1D_FLUSH_TRIG2 |
+			KVM_PPC_CPU_CHAR_L1D_THREAD_PRIV |
+			KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS;
+
+		if (have_fw_feat(fw_features, "enabled",
+				 "speculation-policy-favor-security"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-l1d-flush-msr-pr-0-to-1"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR;
+		if (!have_fw_feat(fw_features, "disabled",
+				  "needs-spec-barrier-for-bound-checks"))
+			cp->behaviour |= KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+		cp->behaviour_mask = KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY |
+			KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR |
+			KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR;
+
+		of_node_put(fw_features);
+	}
+
+	return 0;
+}
+#endif
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
@@ -1861,6 +1984,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_GET_CPU_CHAR: {
+		struct kvm_ppc_cpu_char cpuchar;
+
+		r = kvmppc_get_cpu_char(&cpuchar);
+		if (r >= 0 && copy_to_user(argp, &cpuchar, sizeof(cpuchar)))
+			r = -EFAULT;
+		break;
+	}
 	default: {
 		struct kvm *kvm = filp->private_data;
 		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);

arch/powerpc/lib/feature-fixups.c

@@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+#ifdef CONFIG_PPC_BOOK3S_64
+void do_rfi_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___rfi_flush_fixup),
+	end = PTRRELOC(&__stop___rfi_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	if (types & L1D_FLUSH_FALLBACK)
+		/* b .+16 to fallback flush */
+		instrs[0] = 0x48000010;
+
+	i = 0;
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+		patch_instruction(dest + 1, instrs[1]);
+		patch_instruction(dest + 2, instrs[2]);
+	}
+
+	printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i);
+}
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 {
 	long *start, *end;

arch/powerpc/mm/fault.c

@@ -145,6 +145,11 @@ static noinline int bad_area(struct pt_regs *regs, unsigned long address)
 	return __bad_area(regs, address, SEGV_MAPERR);
 }
 
+static noinline int bad_access(struct pt_regs *regs, unsigned long address)
+{
+	return __bad_area(regs, address, SEGV_ACCERR);
+}
+
 static int do_sigbus(struct pt_regs *regs, unsigned long address,
 		     unsigned int fault)
 {
@@ -490,7 +495,7 @@ retry:
 
 good_area:
 	if (unlikely(access_error(is_write, is_exec, vma)))
-		return bad_area(regs, address);
+		return bad_access(regs, address);
 
 	/*
 	 * If for any reason at all we couldn't handle the fault,

arch/powerpc/platforms/powernv/setup.c

@@ -37,13 +37,62 @@
 #include <asm/kexec.h>
 #include <asm/smp.h>
 #include <asm/tm.h>
+#include <asm/setup.h>
 
 #include "powernv.h"
 
+static void pnv_setup_rfi_flush(void)
+{
+	struct device_node *np, *fw_features;
+	enum l1d_flush_type type;
+	int enable;
+
+	/* Default to fallback in case fw-features are not available */
+	type = L1D_FLUSH_FALLBACK;
+	enable = 1;
+
+	np = of_find_node_by_name(NULL, "ibm,opal");
+	fw_features = of_get_child_by_name(np, "fw-features");
+	of_node_put(np);
+
+	if (fw_features) {
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_MTTRIG;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0");
+		if (np && of_property_read_bool(np, "enabled"))
+			type = L1D_FLUSH_ORI;
+
+		of_node_put(np);
+
+		/* Enable unless firmware says NOT to */
+		enable = 2;
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+
+		np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1");
+		if (np && of_property_read_bool(np, "disabled"))
+			enable--;
+
+		of_node_put(np);
+		of_node_put(fw_features);
+	}
+
+	setup_rfi_flush(type, enable > 0);
+}
+
 static void __init pnv_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
 
+	pnv_setup_rfi_flush();
+
 	/* Initialize SMP */
 	pnv_smp_init();
 

arch/powerpc/platforms/pseries/dlpar.c

@@ -574,11 +574,26 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr,
 
 static CLASS_ATTR_RW(dlpar);
 
-static int __init pseries_dlpar_init(void)
+int __init dlpar_workqueue_init(void)
 {
+	if (pseries_hp_wq)
+		return 0;
+
 	pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue",
-					WQ_UNBOUND, 1);
+			WQ_UNBOUND, 1);
+
+	return pseries_hp_wq ? 0 : -ENOMEM;
+}
+
+static int __init dlpar_sysfs_init(void)
+{
+	int rc;
+
+	rc = dlpar_workqueue_init();
+	if (rc)
+		return rc;
+
 	return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
 }
-machine_device_initcall(pseries, pseries_dlpar_init);
+machine_device_initcall(pseries, dlpar_sysfs_init);
 

arch/powerpc/platforms/pseries/pseries.h

@@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page_size(void)
 	return CMO_PageSize;
 }
 
+int dlpar_workqueue_init(void);
+
 #endif /* _PSERIES_PSERIES_H */

arch/powerpc/platforms/pseries/ras.c

@@ -69,7 +69,8 @@ static int __init init_ras_IRQ(void)
 	/* Hotplug Events */
 	np = of_find_node_by_path("/event-sources/hot-plug-events");
 	if (np != NULL) {
-		request_event_sources_irqs(np, ras_hotplug_interrupt,
+		if (dlpar_workqueue_init() == 0)
+			request_event_sources_irqs(np, ras_hotplug_interrupt,
 					   "RAS_HOTPLUG");
 		of_node_put(np);
 	}

arch/powerpc/platforms/pseries/setup.c

@@ -459,6 +459,39 @@ static void __init find_and_init_phbs(void)
 	of_pci_check_probe_only();
 }
 
+static void pseries_setup_rfi_flush(void)
+{
+	struct h_cpu_char_result result;
+	enum l1d_flush_type types;
+	bool enable;
+	long rc;
+
+	/* Enable by default */
+	enable = true;
+
+	rc = plpar_get_cpu_characteristics(&result);
+	if (rc == H_SUCCESS) {
+		types = L1D_FLUSH_NONE;
+
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2)
+			types |= L1D_FLUSH_MTTRIG;
+		if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30)
+			types |= L1D_FLUSH_ORI;
+
+		/* Use fallback if nothing set in hcall */
+		if (types == L1D_FLUSH_NONE)
+			types = L1D_FLUSH_FALLBACK;
+
+		if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR))
+			enable = false;
+	} else {
+		/* Default to fallback if case hcall is not available */
+		types = L1D_FLUSH_FALLBACK;
+	}
+
+	setup_rfi_flush(types, enable);
+}
+
 static void __init pSeries_setup_arch(void)
 {
 	set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT);
@@ -476,6 +509,8 @@ static void __init pSeries_setup_arch(void)
 
 	fwnmi_init();
 
+	pseries_setup_rfi_flush();
+
 	/* By default, only probe PCI (can be overridden by rtas_pci) */
 	pci_add_flags(PCI_PROBE_ONLY);
 

arch/powerpc/xmon/xmon.c

@@ -2344,10 +2344,10 @@ static void dump_one_paca(int cpu)
 	DUMP(p, kernel_toc, "lx");
 	DUMP(p, kernelbase, "lx");
 	DUMP(p, kernel_msr, "lx");
-	DUMP(p, emergency_sp, "p");
+	DUMP(p, emergency_sp, "px");
 #ifdef CONFIG_PPC_BOOK3S_64
-	DUMP(p, nmi_emergency_sp, "p");
-	DUMP(p, mc_emergency_sp, "p");
+	DUMP(p, nmi_emergency_sp, "px");
+	DUMP(p, mc_emergency_sp, "px");
 	DUMP(p, in_nmi, "x");
 	DUMP(p, in_mce, "x");
 	DUMP(p, hmi_event_available, "x");
@@ -2375,17 +2375,21 @@ static void dump_one_paca(int cpu)
 	DUMP(p, slb_cache_ptr, "x");
 	for (i = 0; i < SLB_CACHE_ENTRIES; i++)
 		printf(" slb_cache[%d]:        = 0x%016lx\n", i, p->slb_cache[i]);
+
+	DUMP(p, rfi_flush_fallback_area, "px");
+	DUMP(p, l1d_flush_congruence, "llx");
+	DUMP(p, l1d_flush_sets, "llx");
 #endif
 	DUMP(p, dscr_default, "llx");
 #ifdef CONFIG_PPC_BOOK3E
-	DUMP(p, pgd, "p");
-	DUMP(p, kernel_pgd, "p");
-	DUMP(p, tcd_ptr, "p");
-	DUMP(p, mc_kstack, "p");
-	DUMP(p, crit_kstack, "p");
-	DUMP(p, dbg_kstack, "p");
+	DUMP(p, pgd, "px");
+	DUMP(p, kernel_pgd, "px");
+	DUMP(p, tcd_ptr, "px");
+	DUMP(p, mc_kstack, "px");
+	DUMP(p, crit_kstack, "px");
+	DUMP(p, dbg_kstack, "px");
 #endif
-	DUMP(p, __current, "p");
+	DUMP(p, __current, "px");
 	DUMP(p, kstack, "lx");
 	printf(" kstack_base          = 0x%016lx\n", p->kstack & ~(THREAD_SIZE - 1));
 	DUMP(p, stab_rr, "lx");
@@ -2403,7 +2407,7 @@ static void dump_one_paca(int cpu)
 #endif
 
 #ifdef CONFIG_PPC_POWERNV
-	DUMP(p, core_idle_state_ptr, "p");
+	DUMP(p, core_idle_state_ptr, "px");
 	DUMP(p, thread_idle_state, "x");
 	DUMP(p, thread_mask, "x");
 	DUMP(p, subcore_sibling_mask, "x");

arch/riscv/configs/defconfig

@@ -0,0 +1,75 @@
+CONFIG_SMP=y
+CONFIG_PCI=y
+CONFIG_PCIE_XILINX=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_RAS=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+# CONFIG_RCU_TRACE is not set
+CONFIG_CRYPTO_USER_API_HASH=y

arch/riscv/include/asm/csr.h

@@ -17,10 +17,10 @@
 #include <linux/const.h>
 
 /* Status register flags */
-#define SR_IE   _AC(0x00000002, UL) /* Interrupt Enable */
-#define SR_PIE  _AC(0x00000020, UL) /* Previous IE */
-#define SR_PS   _AC(0x00000100, UL) /* Previously Supervisor */
-#define SR_SUM  _AC(0x00040000, UL) /* Supervisor may access User Memory */
+#define SR_SIE	_AC(0x00000002, UL) /* Supervisor Interrupt Enable */
+#define SR_SPIE	_AC(0x00000020, UL) /* Previous Supervisor IE */
+#define SR_SPP	_AC(0x00000100, UL) /* Previously Supervisor */
+#define SR_SUM	_AC(0x00040000, UL) /* Supervisor may access User Memory */
 
 #define SR_FS           _AC(0x00006000, UL) /* Floating-point Status */
 #define SR_FS_OFF       _AC(0x00000000, UL)

arch/riscv/include/asm/io.h

@@ -21,8 +21,6 @@
 
 #include <linux/types.h>
 
-#ifdef CONFIG_MMU
-
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
 /*
@@ -36,8 +34,6 @@ extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
 extern void iounmap(volatile void __iomem *addr);
 
-#endif /* CONFIG_MMU */
-
 /* Generic IO read/write.  These perform native-endian accesses. */
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)

arch/riscv/include/asm/irqflags.h

@@ -27,25 +27,25 @@ static inline unsigned long arch_local_save_flags(void)
 /* unconditionally enable interrupts */
 static inline void arch_local_irq_enable(void)
 {
-	csr_set(sstatus, SR_IE);
+	csr_set(sstatus, SR_SIE);
 }
 
 /* unconditionally disable interrupts */
 static inline void arch_local_irq_disable(void)
 {
-	csr_clear(sstatus, SR_IE);
+	csr_clear(sstatus, SR_SIE);
 }
 
 /* get status and disable interrupts */
 static inline unsigned long arch_local_irq_save(void)
 {
-	return csr_read_clear(sstatus, SR_IE);
+	return csr_read_clear(sstatus, SR_SIE);
 }
 
 /* test flags */
 static inline int arch_irqs_disabled_flags(unsigned long flags)
 {
-	return !(flags & SR_IE);
+	return !(flags & SR_SIE);
 }
 
 /* test hardware interrupt enable bit */
@@ -57,7 +57,7 @@ static inline int arch_irqs_disabled(void)
 /* set interrupt enabled status */
 static inline void arch_local_irq_restore(unsigned long flags)
 {
-	csr_set(sstatus, flags & SR_IE);
+	csr_set(sstatus, flags & SR_SIE);
 }
 
 #endif /* _ASM_RISCV_IRQFLAGS_H */

arch/riscv/include/asm/pgtable.h

@@ -20,8 +20,6 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
-
 /* Page Upper Directory not used in RISC-V */
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/page.h>
@@ -413,8 +411,6 @@ static inline void pgtable_cache_init(void)
 	/* No page table caches to initialize */
 }
 
-#endif /* CONFIG_MMU */
-
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)

arch/riscv/include/asm/ptrace.h

@@ -66,7 +66,7 @@ struct pt_regs {
 #define REG_FMT "%08lx"
 #endif
 
-#define user_mode(regs) (((regs)->sstatus & SR_PS) == 0)
+#define user_mode(regs) (((regs)->sstatus & SR_SPP) == 0)
 
 
 /* Helpers for working with the instruction pointer */

arch/riscv/include/asm/tlbflush.h

@@ -15,8 +15,6 @@
 #ifndef _ASM_RISCV_TLBFLUSH_H
 #define _ASM_RISCV_TLBFLUSH_H
 
-#ifdef CONFIG_MMU
-
 #include <linux/mm_types.h>
 
 /*
@@ -64,6 +62,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	flush_tlb_all();
 }
 
-#endif /* CONFIG_MMU */
-
 #endif /* _ASM_RISCV_TLBFLUSH_H */

arch/riscv/include/asm/uaccess.h

@@ -127,7 +127,6 @@ extern int fixup_exception(struct pt_regs *state);
  * call.
  */
 
-#ifdef CONFIG_MMU
 #define __get_user_asm(insn, x, ptr, err)			\
 do {								\
 	uintptr_t __tmp;					\
@@ -153,13 +152,11 @@ do {								\
 	__disable_user_access();				\
 	(x) = __x;						\
 } while (0)
-#endif /* CONFIG_MMU */
 
 #ifdef CONFIG_64BIT
 #define __get_user_8(x, ptr, err) \
 	__get_user_asm("ld", x, ptr, err)
 #else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
 #define __get_user_8(x, ptr, err)				\
 do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
@@ -193,7 +190,6 @@ do {								\
 	(x) = (__typeof__(x))((__typeof__((x)-(x)))(		\
 		(((u64)__hi << 32) | __lo)));			\
 } while (0)
-#endif /* CONFIG_MMU */
 #endif /* CONFIG_64BIT */
 
 
@@ -267,8 +263,6 @@ do {								\
 		((x) = 0, -EFAULT);				\
 })
 
-
-#ifdef CONFIG_MMU
 #define __put_user_asm(insn, x, ptr, err)			\
 do {								\
 	uintptr_t __tmp;					\
@@ -292,14 +286,11 @@ do {								\
 		: "rJ" (__x), "i" (-EFAULT));			\
 	__disable_user_access();				\
 } while (0)
-#endif /* CONFIG_MMU */
-
 
 #ifdef CONFIG_64BIT
 #define __put_user_8(x, ptr, err) \
 	__put_user_asm("sd", x, ptr, err)
 #else /* !CONFIG_64BIT */
-#ifdef CONFIG_MMU
 #define __put_user_8(x, ptr, err)				\
 do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
@@ -329,7 +320,6 @@ do {								\
 		: "rJ" (__x), "rJ" (__x >> 32), "i" (-EFAULT));	\
 	__disable_user_access();				\
 } while (0)
-#endif /* CONFIG_MMU */
 #endif /* CONFIG_64BIT */
 
 
@@ -438,7 +428,6 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
  * will set "err" to -EFAULT, while successful accesses return the previous
  * value.
  */
-#ifdef CONFIG_MMU
 #define __cmpxchg_user(ptr, old, new, err, size, lrb, scb)	\
 ({								\
 	__typeof__(ptr) __ptr = (ptr);				\
@@ -508,6 +497,5 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
 	(err) = __err;						\
 	__ret;							\
 })
-#endif /* CONFIG_MMU */
 
 #endif /* _ASM_RISCV_UACCESS_H */

arch/riscv/include/asm/unistd.h

@@ -14,3 +14,4 @@
 #define __ARCH_HAVE_MMU
 #define __ARCH_WANT_SYS_CLONE
 #include <uapi/asm/unistd.h>
+#include <uapi/asm/syscalls.h>

arch/riscv/include/asm/vdso-syscalls.h

@@ -1,28 +0,0 @@
-/*
- * Copyright (C) 2017 SiFive
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef _ASM_RISCV_VDSO_SYSCALLS_H
-#define _ASM_RISCV_VDSO_SYSCALLS_H
-
-#ifdef CONFIG_SMP
-
-/* These syscalls are only used by the vDSO and are not in the uapi. */
-#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
-__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
-
-#endif
-
-#endif /* _ASM_RISCV_VDSO_H */

arch/riscv/include/uapi/asm/syscalls.h

@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2017 SiFive
+ */
+
+#ifndef _ASM__UAPI__SYSCALLS_H
+#define _ASM__UAPI__SYSCALLS_H
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
+
+#endif

arch/riscv/kernel/entry.S

@@ -196,7 +196,7 @@ handle_syscall:
 	addi s2, s2, 0x4
 	REG_S s2, PT_SEPC(sp)
 	/* System calls run with interrupts enabled */
-	csrs sstatus, SR_IE
+	csrs sstatus, SR_SIE
 	/* Trace syscalls, but only if requested by the user. */
 	REG_L t0, TASK_TI_FLAGS(tp)
 	andi t0, t0, _TIF_SYSCALL_TRACE
@@ -224,8 +224,8 @@ ret_from_syscall:
 
 ret_from_exception:
 	REG_L s0, PT_SSTATUS(sp)
-	csrc sstatus, SR_IE
-	andi s0, s0, SR_PS
+	csrc sstatus, SR_SIE
+	andi s0, s0, SR_SPP
 	bnez s0, restore_all
 
 resume_userspace:
@@ -255,7 +255,7 @@ work_pending:
 	bnez s1, work_resched
 work_notifysig:
 	/* Handle pending signals and notify-resume requests */
-	csrs sstatus, SR_IE /* Enable interrupts for do_notify_resume() */
+	csrs sstatus, SR_SIE /* Enable interrupts for do_notify_resume() */
 	move a0, sp /* pt_regs */
 	move a1, s0 /* current_thread_info->flags */
 	tail do_notify_resume