Merge tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "This is a bit late, partly due to me travelling, and partly due to a
  power outage knocking out some of my test systems *while* I was
  travelling.

   - Initial support for running on a system with an Ultravisor, which
     is software that runs below the hypervisor and protects guests
     against some attacks by the hypervisor.

   - Support for building the kernel to run as a "Secure Virtual
     Machine", ie. as a guest capable of running on a system with an
     Ultravisor.

   - Some changes to our DMA code on bare metal, to allow devices with
     medium sized DMA masks (> 32 && < 59 bits) to use more than 2GB of
     DMA space.

   - Support for firmware assisted crash dumps on bare metal (powernv).

   - Two series fixing bugs in and refactoring our PCI EEH code.

   - A large series refactoring our exception entry code to use gas
     macros, both to make it more readable and also enable some future
     optimisations.

  As well as many cleanups and other minor features & fixups.

  Thanks to: Adam Zerella, Alexey Kardashevskiy, Alistair Popple, Andrew
  Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anshuman Khandual,
  Balbir Singh, Benjamin Herrenschmidt, Cédric Le Goater, Christophe
  JAILLET, Christophe Leroy, Christopher M. Riedl, Christoph Hellwig,
  Claudio Carvalho, Daniel Axtens, David Gibson, David Hildenbrand,
  Desnes A. Nunes do Rosario, Ganesh Goudar, Gautham R. Shenoy, Greg
  Kurz, Guerney Hunt, Gustavo Romero, Halil Pasic, Hari Bathini, Joakim
  Tjernlund, Jonathan Neuschafer, Jordan Niethe, Leonardo Bras, Lianbo
  Jiang, Madhavan Srinivasan, Mahesh Salgaonkar, Mahesh Salgaonkar,
  Masahiro Yamada, Maxiwell S. Garcia, Michael Anderson, Nathan
  Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver
  O'Halloran, Qian Cai, Ram Pai, Ravi Bangoria, Reza Arbab, Ryan Grimm,
  Sam Bobroff, Santosh Sivaraj, Segher Boessenkool, Sukadev Bhattiprolu,
  Thiago Bauermann, Thiago Jung Bauermann, Thomas Gleixner, Tom
  Lendacky, Vasant Hegde"

* tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (264 commits)
  powerpc/mm/mce: Keep irqs disabled during lockless page table walk
  powerpc: Use ftrace_graph_ret_addr() when unwinding
  powerpc/ftrace: Enable HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
  ftrace: Look up the address of return_to_handler() using helpers
  powerpc: dump kernel log before carrying out fadump or kdump
  docs: powerpc: Add missing documentation reference
  powerpc/xmon: Fix output of XIVE IPI
  powerpc/xmon: Improve output of XIVE interrupts
  powerpc/mm/radix: remove useless kernel messages
  powerpc/fadump: support holes in kernel boot memory area
  powerpc/fadump: remove RMA_START and RMA_END macros
  powerpc/fadump: update documentation about option to release opalcore
  powerpc/fadump: consider f/w load area
  powerpc/opalcore: provide an option to invalidate /sys/firmware/opal/core file
  powerpc/opalcore: export /sys/firmware/opal/core for analysing opal crashes
  powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP
  powerpc/fadump: add support to preserve crash data on FADUMP disabled kernel
  powerpc/fadump: improve how crashed kernel's memory is reserved
  powerpc/fadump: consider reserved ranges while releasing memory
  powerpc/fadump: make crash memory ranges array allocation generic
  ...

3 files changed, 167 insertions, 0 deletions

diff --git a/tools/testing/selftests/powerpc/eeh/Makefile b/tools/testing/selftests/powerpc/eeh/Makefile
new file mode 100644
index 000000000000..b397babd569b
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+noarg:
+	$(MAKE) -C ../
+
+TEST_PROGS := eeh-basic.sh
+TEST_FILES := eeh-functions.sh
+
+top_srcdir = ../../../../..
+include ../../lib.mk
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-basic.sh b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
new file mode 100755
index 000000000000..f988d2f42e8f
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/eeh-basic.sh
@@ -0,0 +1,82 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+. ./eeh-functions.sh
+
+if ! eeh_supported ; then
+	echo "EEH not supported on this system, skipping"
+	exit 0;
+fi
+
+if [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_check" ] && \
+   [ ! -e "/sys/kernel/debug/powerpc/eeh_dev_break" ] ; then
+	echo "debugfs EEH testing files are missing. Is debugfs mounted?"
+	exit 1;
+fi
+
+pre_lspci=`mktemp`
+lspci > $pre_lspci
+
+# Bump the max freeze count to something absurd so we don't
+# trip over it while breaking things.
+echo 5000 > /sys/kernel/debug/powerpc/eeh_max_freezes
+
+# record the devices that we break in here. Assuming everything
+# goes to plan we should get them back once the recover process
+# is finished.
+devices=""
+
+# Build up a list of candidate devices.
+for dev in `ls -1 /sys/bus/pci/devices/ | grep '\.0$'` ; do
+	# skip bridges since we can't recover them (yet...)
+	if [ -e "/sys/bus/pci/devices/$dev/pci_bus" ] ; then
+		echo "$dev, Skipped: bridge"
+		continue;
+	fi
+
+	# Skip VFs for now since we don't have a reliable way
+	# to break them.
+	if [ -e "/sys/bus/pci/devices/$dev/physfn" ] ; then
+		echo "$dev, Skipped: virtfn"
+		continue;
+	fi
+
+	# Don't inject errosr into an already-frozen PE. This happens with
+	# PEs that contain multiple PCI devices (e.g. multi-function cards)
+	# and injecting new errors during the recovery process will probably
+	# result in the recovery failing and the device being marked as
+	# failed.
+	if ! pe_ok $dev ; then
+		echo "$dev, Skipped: Bad initial PE state"
+		continue;
+	fi
+
+	echo "$dev, Added"
+
+	# Add to this list of device to check
+	devices="$devices $dev"
+done
+
+dev_count="$(echo $devices | wc -w)"
+echo "Found ${dev_count} breakable devices..."
+
+failed=0
+for dev in $devices ; do
+	echo "Breaking $dev..."
+
+	if ! pe_ok $dev ; then
+		echo "Skipping $dev, Initial PE state is not ok"
+		failed="$((failed + 1))"
+		continue;
+	fi
+
+	if ! eeh_one_dev $dev ; then
+		failed="$((failed + 1))"
+	fi
+done
+
+echo "$failed devices failed to recover ($dev_count tested)"
+lspci | diff -u $pre_lspci -
+rm -f $pre_lspci
+
+exit $failed
diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
new file mode 100755
index 000000000000..26112ab5cdf4
--- /dev/null
+++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh
@@ -0,0 +1,76 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+
+pe_ok() {
+	local dev="$1"
+	local path="/sys/bus/pci/devices/$dev/eeh_pe_state"
+
+	if ! [ -e "$path" ] ; then
+		return 1;
+	fi
+
+	local fw_state="$(cut -d' ' -f1 < $path)"
+	local sw_state="$(cut -d' ' -f2 < $path)"
+
+	# If EEH_PE_ISOLATED or EEH_PE_RECOVERING are set then the PE is in an
+	# error state or being recovered. Either way, not ok.
+	if [ "$((sw_state & 0x3))" -ne 0 ] ; then
+		return 1
+	fi
+
+	# A functioning PE should have the EEH_STATE_MMIO_ACTIVE and
+	# EEH_STATE_DMA_ACTIVE flags set. For some goddamn stupid reason
+	# the platform backends set these when the PE is in reset. The
+	# RECOVERING check above should stop any false positives though.
+	if [ "$((fw_state & 0x18))" -ne "$((0x18))" ] ; then
+		return 1
+	fi
+
+	return 0;
+}
+
+eeh_supported() {
+	test -e /proc/powerpc/eeh && \
+	grep -q 'EEH Subsystem is enabled' /proc/powerpc/eeh
+}
+
+eeh_one_dev() {
+	local dev="$1"
+
+	# Using this function from the command line is sometimes useful for
+	# testing so check that the argument is a well-formed sysfs device
+	# name.
+	if ! test -e /sys/bus/pci/devices/$dev/ ; then
+		echo "Error: '$dev' must be a sysfs device name (DDDD:BB:DD.F)"
+		return 1;
+	fi
+
+	# Break it
+	echo $dev >/sys/kernel/debug/powerpc/eeh_dev_break
+
+	# Force an EEH device check. If the kernel has already
+	# noticed the EEH (due to a driver poll or whatever), this
+	# is a no-op.
+	echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check
+
+	# Enforce a 30s timeout for recovery. Even the IPR, which is infamously
+	# slow to reset, should recover within 30s.
+	max_wait=30
+
+	for i in `seq 0 ${max_wait}` ; do
+		if pe_ok $dev ; then
+			break;
+		fi
+		echo "$dev, waited $i/${max_wait}"
+		sleep 1
+	done
+
+	if ! pe_ok $dev ; then
+		echo "$dev, Failed to recover!"
+		return 1;
+	fi
+
+	echo "$dev, Recovered after $i seconds"
+	return 0;
+}
+