Merge tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - A big series refactoring parts of our KVM code, and converting some
   to C.

 - Support for ARCH_HAS_SET_MEMORY, and ARCH_HAS_STRICT_MODULE_RWX on
   some CPUs.

 - Support for the Microwatt soft-core.

 - Optimisations to our interrupt return path on 64-bit.

 - Support for userspace access to the NX GZIP accelerator on PowerVM on
   Power10.

 - Enable KUAP and KUEP by default on 32-bit Book3S CPUs.

 - Other smaller features, fixes & cleanups.

Thanks to: Andy Shevchenko, Aneesh Kumar K.V, Arnd Bergmann, Athira
Rajeev, Baokun Li, Benjamin Herrenschmidt, Bharata B Rao, Christophe
Leroy, Daniel Axtens, Daniel Henrique Barboza, Finn Thain, Geoff Levand,
Haren Myneni, Jason Wang, Jiapeng Chong, Joel Stanley, Jordan Niethe,
Kajol Jain, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas
Piggin, Nick Desaulniers, Paul Mackerras, Russell Currey, Sathvika
Vasireddy, Shaokun Zhang, Stephen Rothwell, Sudeep Holla, Suraj Jitindar
Singh, Tom Rix, Vaibhav Jain, YueHaibing, Zhang Jianhua, and Zhen Lei.

* tag 'powerpc-5.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (218 commits)
  powerpc: Only build restart_table.c for 64s
  powerpc/64s: move ret_from_fork etc above __end_soft_masked
  powerpc/64s/interrupt: clean up interrupt return labels
  powerpc/64/interrupt: add missing kprobe annotations on interrupt exit symbols
  powerpc/64: enable MSR[EE] in irq replay pt_regs
  powerpc/64s/interrupt: preserve regs->softe for NMI interrupts
  powerpc/64s: add a table of implicit soft-masked addresses
  powerpc/64e: remove implicit soft-masking and interrupt exit restart logic
  powerpc/64e: fix CONFIG_RELOCATABLE build warnings
  powerpc/64s: fix hash page fault interrupt handler
  powerpc/4xx: Fix setup_kuep() on SMP
  powerpc/32s: Fix setup_{kuap/kuep}() on SMP
  powerpc/interrupt: Use names in check_return_regs_valid()
  powerpc/interrupt: Also use exit_must_hard_disable() on PPC32
  powerpc/sysfs: Replace sizeof(arr)/sizeof(arr[0]) with ARRAY_SIZE
  powerpc/ptrace: Refactor regs_set_return_{msr/ip}
  powerpc/ptrace: Move set_return_regs_changed() before regs_set_return_{msr/ip}
  powerpc/stacktrace: Fix spurious "stale" traces in raise_backtrace_ipi()
  powerpc/pseries/vas: Include irqdomain.h
  powerpc: mark local variables around longjmp as volatile
  ...

8 files changed, 216 insertions, 31 deletions

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 2b8da923ceca..e312ea802aa6 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -163,6 +163,8 @@ src-plat-$(CONFIG_PPC_POWERNV) += pseries-head.S
 src-plat-$(CONFIG_PPC_IBM_CELL_BLADE) += pseries-head.S
 src-plat-$(CONFIG_MVME7100) += motload-head.S mvme7100.c
 
+src-plat-$(CONFIG_PPC_MICROWATT) += fixed-head.S microwatt.c
+
 src-wlib := $(sort $(src-wlib-y))
 src-plat := $(sort $(src-plat-y))
 src-boot := $(src-wlib) $(src-plat) empty.c
@@ -227,7 +229,7 @@ $(obj)/wrapper.a: $(obj-wlib) FORCE
 
 hostprogs	:= addnote hack-coff mktree
 
-targets		+= $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a)
+targets		+= $(patsubst $(obj)/%,%,$(obj-boot) wrapper.a) zImage.lds
 extra-y		:= $(obj)/wrapper.a $(obj-plat) $(obj)/empty.o \
 		   $(obj)/zImage.lds $(obj)/zImage.coff.lds $(obj)/zImage.ps3.lds
 
@@ -355,6 +357,8 @@ image-$(CONFIG_MVME5100)		+= dtbImage.mvme5100
 # Board port in arch/powerpc/platform/amigaone/Kconfig
 image-$(CONFIG_AMIGAONE)		+= cuImage.amigaone
 
+image-$(CONFIG_PPC_MICROWATT)		+= dtbImage.microwatt
+
 # For 32-bit powermacs, build the COFF and miboot images
 # as well as the ELF images.
 ifdef CONFIG_PPC32
diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c
index 6098b879ac97..977eb15a6d17 100644
--- a/arch/powerpc/boot/decompress.c
+++ b/arch/powerpc/boot/decompress.c
@@ -99,8 +99,8 @@ static void print_err(char *s)
  * partial_decompress - decompresses part or all of a compressed buffer
  * @inbuf:       input buffer
  * @input_size:  length of the input buffer
- * @outbuf:      input buffer
- * @output_size: length of the input buffer
+ * @outbuf:      output buffer
+ * @output_size: length of the output buffer
  * @skip         number of output bytes to ignore
  *
  * This function takes compressed data from inbuf, decompresses and write it to
diff --git a/arch/powerpc/boot/devtree.c b/arch/powerpc/boot/devtree.c
index 5d91036ad626..58fbcfcc98c9 100644
--- a/arch/powerpc/boot/devtree.c
+++ b/arch/powerpc/boot/devtree.c
@@ -13,6 +13,7 @@
 #include "string.h"
 #include "stdio.h"
 #include "ops.h"
+#include "of.h"
 
 void dt_fixup_memory(u64 start, u64 size)
 {
@@ -23,21 +24,25 @@ void dt_fixup_memory(u64 start, u64 size)
 	root = finddevice("/");
 	if (getprop(root, "#address-cells", &naddr, sizeof(naddr)) < 0)
 		naddr = 2;
+	else
+		naddr = be32_to_cpu(naddr);
 	if (naddr < 1 || naddr > 2)
 		fatal("Can't cope with #address-cells == %d in /\n\r", naddr);
 
 	if (getprop(root, "#size-cells", &nsize, sizeof(nsize)) < 0)
 		nsize = 1;
+	else
+		nsize = be32_to_cpu(nsize);
 	if (nsize < 1 || nsize > 2)
 		fatal("Can't cope with #size-cells == %d in /\n\r", nsize);
 
 	i = 0;
 	if (naddr == 2)
-		memreg[i++] = start >> 32;
-	memreg[i++] = start & 0xffffffff;
+		memreg[i++] = cpu_to_be32(start >> 32);
+	memreg[i++] = cpu_to_be32(start & 0xffffffff);
 	if (nsize == 2)
-		memreg[i++] = size >> 32;
-	memreg[i++] = size & 0xffffffff;
+		memreg[i++] = cpu_to_be32(size >> 32);
+	memreg[i++] = cpu_to_be32(size & 0xffffffff);
 
 	memory = finddevice("/memory");
 	if (! memory) {
@@ -45,9 +50,9 @@ void dt_fixup_memory(u64 start, u64 size)
 		setprop_str(memory, "device_type", "memory");
 	}
 
-	printf("Memory <- <0x%x", memreg[0]);
+	printf("Memory <- <0x%x", be32_to_cpu(memreg[0]));
 	for (i = 1; i < (naddr + nsize); i++)
-		printf(" 0x%x", memreg[i]);
+		printf(" 0x%x", be32_to_cpu(memreg[i]));
 	printf("> (%ldMB)\n\r", (unsigned long)(size >> 20));
 
 	setprop(memory, "reg", memreg, (naddr + nsize)*sizeof(u32));
@@ -65,10 +70,10 @@ void dt_fixup_cpu_clocks(u32 cpu, u32 tb, u32 bus)
 		printf("CPU bus-frequency <- 0x%x (%dMHz)\n\r", bus, MHZ(bus));
 
 	while ((devp = find_node_by_devtype(devp, "cpu"))) {
-		setprop_val(devp, "clock-frequency", cpu);
-		setprop_val(devp, "timebase-frequency", tb);
+		setprop_val(devp, "clock-frequency", cpu_to_be32(cpu));
+		setprop_val(devp, "timebase-frequency", cpu_to_be32(tb));
 		if (bus > 0)
-			setprop_val(devp, "bus-frequency", bus);
+			setprop_val(devp, "bus-frequency", cpu_to_be32(bus));
 	}
 
 	timebase_period_ns = 1000000000 / tb;
@@ -80,7 +85,7 @@ void dt_fixup_clock(const char *path, u32 freq)
 
 	if (devp) {
 		printf("%s: clock-frequency <- %x (%dMHz)\n\r", path, freq, MHZ(freq));
-		setprop_val(devp, "clock-frequency", freq);
+		setprop_val(devp, "clock-frequency", cpu_to_be32(freq));
 	}
 }
 
@@ -133,8 +138,12 @@ void dt_get_reg_format(void *node, u32 *naddr, u32 *nsize)
 {
 	if (getprop(node, "#address-cells", naddr, 4) != 4)
 		*naddr = 2;
+	else
+		*naddr = be32_to_cpu(*naddr);
 	if (getprop(node, "#size-cells", nsize, 4) != 4)
 		*nsize = 1;
+	else
+		*nsize = be32_to_cpu(*nsize);
 }
 
 static void copy_val(u32 *dest, u32 *src, int naddr)
@@ -163,9 +172,9 @@ static int add_reg(u32 *reg, u32 *add, int naddr)
 	int i, carry = 0;
 
 	for (i = MAX_ADDR_CELLS - 1; i >= MAX_ADDR_CELLS - naddr; i--) {
-		u64 tmp = (u64)reg[i] + add[i] + carry;
+		u64 tmp = (u64)be32_to_cpu(reg[i]) + be32_to_cpu(add[i]) + carry;
 		carry = tmp >> 32;
-		reg[i] = (u32)tmp;
+		reg[i] = cpu_to_be32((u32)tmp);
 	}
 
 	return !carry;
@@ -180,18 +189,18 @@ static int compare_reg(u32 *reg, u32 *range, u32 *rangesize)
 	u32 end;
 
 	for (i = 0; i < MAX_ADDR_CELLS; i++) {
-		if (reg[i] < range[i])
+		if (be32_to_cpu(reg[i]) < be32_to_cpu(range[i]))
 			return 0;
-		if (reg[i] > range[i])
+		if (be32_to_cpu(reg[i]) > be32_to_cpu(range[i]))
 			break;
 	}
 
 	for (i = 0; i < MAX_ADDR_CELLS; i++) {
-		end = range[i] + rangesize[i];
+		end = be32_to_cpu(range[i]) + be32_to_cpu(rangesize[i]);
 
-		if (reg[i] < end)
+		if (be32_to_cpu(reg[i]) < end)
 			break;
-		if (reg[i] > end)
+		if (be32_to_cpu(reg[i]) > end)
 			return 0;
 	}
 
@@ -240,7 +249,6 @@ static int dt_xlate(void *node, int res, int reglen, unsigned long *addr,
 		return 0;
 
 	dt_get_reg_format(parent, &naddr, &nsize);
-
 	if (nsize > 2)
 		return 0;
 
@@ -252,10 +260,10 @@ static int dt_xlate(void *node, int res, int reglen, unsigned long *addr,
 
 	copy_val(last_addr, prop_buf + offset, naddr);
 
-	ret_size = prop_buf[offset + naddr];
+	ret_size = be32_to_cpu(prop_buf[offset + naddr]);
 	if (nsize == 2) {
 		ret_size <<= 32;
-		ret_size |= prop_buf[offset + naddr + 1];
+		ret_size |= be32_to_cpu(prop_buf[offset + naddr + 1]);
 	}
 
 	for (;;) {
@@ -278,7 +286,6 @@ static int dt_xlate(void *node, int res, int reglen, unsigned long *addr,
 
 		offset = find_range(last_addr, prop_buf, prev_naddr,
 		                    naddr, prev_nsize, buflen / 4);
-
 		if (offset < 0)
 			return 0;
 
@@ -296,8 +303,7 @@ static int dt_xlate(void *node, int res, int reglen, unsigned long *addr,
 	if (naddr > 2)
 		return 0;
 
-	ret_addr = ((u64)last_addr[2] << 32) | last_addr[3];
-
+	ret_addr = ((u64)be32_to_cpu(last_addr[2]) << 32) | be32_to_cpu(last_addr[3]);
 	if (sizeof(void *) == 4 &&
 	    (ret_addr >= 0x100000000ULL || ret_size > 0x100000000ULL ||
 	     ret_addr + ret_size > 0x100000000ULL))
@@ -350,11 +356,14 @@ int dt_is_compatible(void *node, const char *compat)
 int dt_get_virtual_reg(void *node, void **addr, int nres)
 {
 	unsigned long xaddr;
-	int n;
+	int n, i;
 
 	n = getprop(node, "virtual-reg", addr, nres * 4);
-	if (n > 0)
+	if (n > 0) {
+		for (i = 0; i < n/4; i ++)
+			((u32 *)addr)[i] = be32_to_cpu(((u32 *)addr)[i]);
 		return n / 4;
+	}
 
 	for (n = 0; n < nres; n++) {
 		if (!dt_xlate_reg(node, n, &xaddr, NULL))
diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
new file mode 100644
index 000000000000..974abbdda249
--- /dev/null
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -0,0 +1,138 @@
+/dts-v1/;
+
+/ {
+	#size-cells = <0x02>;
+	#address-cells = <0x02>;
+	model-name = "microwatt";
+	compatible = "microwatt-soc";
+
+	aliases {
+		serial0 = &UART0;
+	};
+
+	reserved-memory {
+		#size-cells = <0x02>;
+		#address-cells = <0x02>;
+		ranges;
+	};
+
+	memory@0 {
+		device_type = "memory";
+		reg = <0x00000000 0x00000000 0x00000000 0x10000000>;
+	};
+
+	cpus {
+		#size-cells = <0x00>;
+		#address-cells = <0x01>;
+
+		ibm,powerpc-cpu-features {
+			display-name = "Microwatt";
+			isa = <3000>;
+			device_type = "cpu-features";
+			compatible = "ibm,powerpc-cpu-features";
+
+			mmu-radix {
+				isa = <3000>;
+				usable-privilege = <2>;
+			};
+
+			little-endian {
+				isa = <2050>;
+				usable-privilege = <3>;
+				hwcap-bit-nr = <1>;
+			};
+
+			cache-inhibited-large-page {
+				isa = <2040>;
+				usable-privilege = <2>;
+			};
+
+			fixed-point-v3 {
+				isa = <3000>;
+				usable-privilege = <3>;
+			};
+
+			no-execute {
+				isa = <2010>;
+				usable-privilege = <2>;
+			};
+
+			floating-point {
+				hwcap-bit-nr = <27>;
+				isa = <0>;
+				usable-privilege = <3>;
+			};
+		};
+
+		PowerPC,Microwatt@0 {
+			i-cache-sets = <2>;
+			ibm,dec-bits = <64>;
+			reservation-granule-size = <64>;
+			clock-frequency = <100000000>;
+			timebase-frequency = <100000000>;
+			i-tlb-sets = <1>;
+			ibm,ppc-interrupt-server#s = <0>;
+			i-cache-block-size = <64>;
+			d-cache-block-size = <64>;
+			d-cache-sets = <2>;
+			i-tlb-size = <64>;
+			cpu-version = <0x990000>;
+			status = "okay";
+			i-cache-size = <0x1000>;
+			ibm,processor-radix-AP-encodings = <0x0c 0xa0000010 0x20000015 0x4000001e>;
+			tlb-size = <0>;
+			tlb-sets = <0>;
+			device_type = "cpu";
+			d-tlb-size = <128>;
+			d-tlb-sets = <2>;
+			reg = <0>;
+			general-purpose;
+			64-bit;
+			d-cache-size = <0x1000>;
+			ibm,chip-id = <0>;
+		};
+	};
+
+	soc@c0000000 {
+		compatible = "simple-bus";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupt-parent = <&ICS>;
+
+		ranges = <0 0 0xc0000000 0x40000000>;
+
+		interrupt-controller@4000 {
+			compatible = "openpower,xics-presentation", "ibm,ppc-xicp";
+			ibm,interrupt-server-ranges = <0x0 0x1>;
+			reg = <0x4000 0x100>;
+		};
+
+		ICS: interrupt-controller@5000 {
+			compatible = "openpower,xics-sources";
+			interrupt-controller;
+			interrupt-ranges = <0x10 0x10>;
+			reg = <0x5000 0x100>;
+			#address-cells = <0>;
+			#size-cells = <0>;
+			#interrupt-cells = <2>;
+		};
+
+		UART0: serial@2000 {
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x2000 0x8>;
+			clock-frequency = <100000000>;
+			current-speed = <115200>;
+			reg-shift = <2>;
+			fifo-size = <16>;
+			interrupts = <0x10 0x1>;
+		};
+	};
+
+	chosen {
+		bootargs = "";
+		ibm,architecture-vec-5 = [19 00 10 00 00 00 00 00 00 00 00 00 00 00 00 00
+					  00 00 00 00 00 00 00 00 40 00 40];
+		stdout-path = &UART0;
+	};
+};
diff --git a/arch/powerpc/boot/microwatt.c b/arch/powerpc/boot/microwatt.c
new file mode 100644
index 000000000000..ca9d83617fc1
--- /dev/null
+++ b/arch/powerpc/boot/microwatt.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <stddef.h>
+#include "stdio.h"
+#include "types.h"
+#include "io.h"
+#include "ops.h"
+
+BSS_STACK(8192);
+
+void platform_init(unsigned long r3, unsigned long r4, unsigned long r5)
+{
+	unsigned long heapsize = 16*1024*1024 - (unsigned long)_end;
+
+	/*
+	 * Disable interrupts and turn off MSR_RI, since we'll
+	 * shortly be overwriting the interrupt vectors.
+	 */
+	__asm__ volatile("mtmsrd %0,1" : : "r" (0));
+
+	simple_alloc_init(_end, heapsize, 32, 64);
+	fdt_init(_dtb_start);
+	serial_console_init();
+}
diff --git a/arch/powerpc/boot/ns16550.c b/arch/powerpc/boot/ns16550.c
index b0da4466d419..f16d2be1d0f3 100644
--- a/arch/powerpc/boot/ns16550.c
+++ b/arch/powerpc/boot/ns16550.c
@@ -15,6 +15,7 @@
 #include "stdio.h"
 #include "io.h"
 #include "ops.h"
+#include "of.h"
 
 #define UART_DLL	0	/* Out: Divisor Latch Low */
 #define UART_DLM	1	/* Out: Divisor Latch High */
@@ -58,16 +59,20 @@ int ns16550_console_init(void *devp, struct serial_console_data *scdp)
 	int n;
 	u32 reg_offset;
 
-	if (dt_get_virtual_reg(devp, (void **)&reg_base, 1) < 1)
+	if (dt_get_virtual_reg(devp, (void **)&reg_base, 1) < 1) {
+		printf("virt reg parse fail...\r\n");
 		return -1;
+	}
 
 	n = getprop(devp, "reg-offset", &reg_offset, sizeof(reg_offset));
 	if (n == sizeof(reg_offset))
-		reg_base += reg_offset;
+		reg_base += be32_to_cpu(reg_offset);
 
 	n = getprop(devp, "reg-shift", &reg_shift, sizeof(reg_shift));
 	if (n != sizeof(reg_shift))
 		reg_shift = 0;
+	else
+		reg_shift = be32_to_cpu(reg_shift);
 
 	scdp->open = ns16550_open;
 	scdp->putc = ns16550_putc;
diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper
index cdb796b76e2e..1f4676bab786 100755
--- a/arch/powerpc/boot/wrapper
+++ b/arch/powerpc/boot/wrapper
@@ -342,6 +342,11 @@ gamecube|wii)
     link_address='0x600000'
     platformo="$object/$platform-head.o $object/$platform.o"
     ;;
+microwatt)
+    link_address='0x500000'
+    platformo="$object/fixed-head.o $object/$platform.o"
+    binary=y
+    ;;
 treeboot-currituck)
     link_address='0x1000000'
     ;;
diff --git a/arch/powerpc/boot/zImage.ps3.lds.S b/arch/powerpc/boot/zImage.ps3.lds.S
index 7b2ff2eaa73a..d0ffb493614d 100644
--- a/arch/powerpc/boot/zImage.ps3.lds.S
+++ b/arch/powerpc/boot/zImage.ps3.lds.S
@@ -8,7 +8,7 @@ SECTIONS
   .kernel:vmlinux.bin : { *(.kernel:vmlinux.bin) }
   _vmlinux_end =  .;
 
-  . = ALIGN(4096);
+  . = ALIGN(8);
   _dtb_start = .;
   .kernel:dtb : { *(.kernel:dtb) }
   _dtb_end = .;