diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-17 19:05:46 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-17 19:05:46 +0300 |
| commit | ff2632d7d08edc11e8bd0629e9fcfebab25c78b4 (patch) | |
| tree | 06ae34f7cb364ba23e01d9339dfb940a9e98b615 /arch/powerpc | |
| parent | 4853f1f6ace32c68a04287353e428c4cfc3fa8ed (diff) | |
| parent | 61700f816e6f58f6b1aaa881a69a784d146e30f0 (diff) | |
| download | linux-ff2632d7d08edc11e8bd0629e9fcfebab25c78b4.tar.xz | |
Merge tag 'powerpc-6.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
- Enable BPF Kernel Functions (kfuncs) in the powerpc BPF JIT.
- Allow per-process DEXCR (Dynamic Execution Control Register) settings
via prctl, notably NPHIE which controls hashst/hashchk for ROP
protection.
- Install powerpc selftests in sub-directories. Note this changes the
way run_kselftest.sh needs to be invoked for powerpc selftests.
- Change fadump (Firmware Assisted Dump) to better handle memory
add/remove.
- Add support for passing additional parameters to the fadump kernel.
- Add support for updating the kdump image on CPU/memory add/remove
events.
- Other small features, cleanups and fixes.
Thanks to Andrew Donnellan, Andy Shevchenko, Aneesh Kumar K.V, Arnd
Bergmann, Benjamin Gray, Bjorn Helgaas, Christian Zigotzky, Christophe
Jaillet, Christophe Leroy, Colin Ian King, Cédric Le Goater, Dr. David
Alan Gilbert, Erhard Furtner, Frank Li, GUO Zihua, Ganesh Goudar, Geoff
Levand, Ghanshyam Agrawal, Greg Kurz, Hari Bathini, Joel Stanley, Justin
Stitt, Kunwu Chan, Li Yang, Lidong Zhong, Madhavan Srinivasan, Mahesh
Salgaonkar, Masahiro Yamada, Matthias Schiffer, Naresh Kamboju, Nathan
Chancellor, Nathan Lynch, Naveen N Rao, Nicholas Miehlbradt, Ran Wang,
Randy Dunlap, Ritesh Harjani, Sachin Sant, Shirisha Ganta, Shrikanth
Hegde, Sourabh Jain, Stephen Rothwell, sundar, Thorsten Blum, Vaibhav
Jain, Xiaowei Bao, Yang Li, and Zhao Chenhui.
* tag 'powerpc-6.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (85 commits)
powerpc/fadump: Fix section mismatch warning
powerpc/85xx: fix compile error without CONFIG_CRASH_DUMP
powerpc/fadump: update documentation about bootargs_append
powerpc/fadump: pass additional parameters when fadump is active
powerpc/fadump: setup additional parameters for dump capture kernel
powerpc/pseries/fadump: add support for multiple boot memory regions
selftests/powerpc/dexcr: Fix spelling mistake "predicition" -> "prediction"
KVM: PPC: Book3S HV nestedv2: Fix an error handling path in gs_msg_ops_kvmhv_nestedv2_config_fill_info()
KVM: PPC: Fix documentation for ppc mmu caps
KVM: PPC: code cleanup for kvmppc_book3s_irqprio_deliver
KVM: PPC: Book3S HV nestedv2: Cancel pending DEC exception
powerpc/xmon: Check cpu id in commands "c#", "dp#" and "dx#"
powerpc/code-patching: Use dedicated memory routines for patching
powerpc/code-patching: Test patch_instructions() during boot
powerpc64/kasan: Pass virtual addresses to kasan_init_phys_region()
powerpc: rename SPRN_HID2 define to SPRN_HID2_750FX
powerpc: Fix typos
powerpc/eeh: Fix spelling of the word "auxillary" and update comment
macintosh/ams: Fix unused variable warning
powerpc/Makefile: Remove bits related to the previous use of -mcmodel=large
...
Diffstat (limited to 'arch/powerpc')
136 files changed, 2106 insertions, 1006 deletions
diff --git a/arch/powerpc/Kbuild b/arch/powerpc/Kbuild index 22cd0d55a892..571f260b0842 100644 --- a/arch/powerpc/Kbuild +++ b/arch/powerpc/Kbuild @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror +subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror -Wa,--fatal-warnings +subdir-asflags-$(CONFIG_PPC_WERROR) := -Wa,--fatal-warnings obj-y += kernel/ obj-y += mm/ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index c7076e223fcd..70e118f140eb 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -687,6 +687,10 @@ config ARCH_SELECTS_CRASH_DUMP depends on CRASH_DUMP select RELOCATABLE if PPC64 || 44x || PPC_85xx +config ARCH_SUPPORTS_CRASH_HOTPLUG + def_bool y + depends on PPC64 + config FA_DUMP bool "Firmware-assisted dump" depends on CRASH_DUMP && PPC64 && (PPC_RTAS || PPC_POWERNV) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 65261cbe5bfd..0a0c57aee1ae 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -114,7 +114,6 @@ LDFLAGS_vmlinux := $(LDFLAGS_vmlinux-y) ifdef CONFIG_PPC64 ifndef CONFIG_PPC_KERNEL_PCREL -ifeq ($(call cc-option-yn,-mcmodel=medium),y) # -mcmodel=medium breaks modules because it uses 32bit offsets from # the TOC pointer to create pointers where possible. Pointers into the # percpu data area are created by this method. @@ -124,9 +123,6 @@ ifeq ($(call cc-option-yn,-mcmodel=medium),y) # kernel percpu data space (starting with 0xc...). We need a full # 64bit relocation for this to work, hence -mcmodel=large. KBUILD_CFLAGS_MODULE += -mcmodel=large -else - export NO_MINIMAL_TOC := -mno-minimal-toc -endif endif endif @@ -139,7 +135,7 @@ CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mabi=elfv1) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcall-aixdesc) endif endif -CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc)) +CFLAGS-$(CONFIG_PPC64) += -mcmodel=medium CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mno-pointers-to-nested-functions) CFLAGS-$(CONFIG_PPC64) += $(call cc-option,-mlong-double-128) diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 968aee2025b8..9c2b6e527ed1 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -108,8 +108,8 @@ DTC_FLAGS ?= -p 1024 # these files into the build dir, fix up any includes and ensure that dependent # files are copied in the right order. -# these need to be seperate variables because they are copied out of different -# directories in the kernel tree. Sure you COULd merge them, but it's a +# these need to be separate variables because they are copied out of different +# directories in the kernel tree. Sure you COULD merge them, but it's a # cure-is-worse-than-disease situation. zlib-decomp-$(CONFIG_KERNEL_GZIP) := decompress_inflate.c zlib-$(CONFIG_KERNEL_GZIP) := inffast.c inflate.c inftrees.c diff --git a/arch/powerpc/boot/decompress.c b/arch/powerpc/boot/decompress.c index 977eb15a6d17..6835cb53f034 100644 --- a/arch/powerpc/boot/decompress.c +++ b/arch/powerpc/boot/decompress.c @@ -101,7 +101,7 @@ static void print_err(char *s) * @input_size: length of the input buffer * @outbuf: output buffer * @output_size: length of the output buffer - * @skip number of output bytes to ignore + * @_skip: number of output bytes to ignore * * This function takes compressed data from inbuf, decompresses and write it to * outbuf. Once output_size bytes are written to the output buffer, or the diff --git a/arch/powerpc/boot/dts/acadia.dts b/arch/powerpc/boot/dts/acadia.dts index deb52e41ab84..5fedda811378 100644 --- a/arch/powerpc/boot/dts/acadia.dts +++ b/arch/powerpc/boot/dts/acadia.dts @@ -172,7 +172,7 @@ reg = <0xef602800 0x60>; interrupt-parent = <&UIC0>; interrupts = <0x4 0x4>; - /* This thing is a bit weird. It has it's own UIC + /* This thing is a bit weird. It has its own UIC * that it uses to generate snapshot triggers. We * don't really support this device yet, and it needs * work to figure this out. diff --git a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi index 4f044b41a776..fb3200b006ad 100644 --- a/arch/powerpc/boot/dts/fsl/b4si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/b4si-post.dtsi @@ -50,7 +50,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <25 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts index 8da984251abc..0ba86a6dce1b 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts +++ b/arch/powerpc/boot/dts/fsl/bsc9131rdb.dts @@ -15,7 +15,7 @@ device_type = "memory"; }; - board_ifc: ifc: ifc@ff71e000 { + board_ifc: ifc: memory-controller@ff71e000 { /* NAND Flash on board */ ranges = <0x0 0x0 0x0 0xff800000 0x00004000>; reg = <0x0 0xff71e000 0x0 0x2000>; diff --git a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi index 2a677fd323eb..5c53cee8755f 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/bsc9131si-post.dtsi @@ -35,7 +35,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <16 2 0 0 20 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts index 7cb2158dfe58..ce642e879a1b 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9132qds.dts +++ b/arch/powerpc/boot/dts/fsl/bsc9132qds.dts @@ -15,7 +15,7 @@ device_type = "memory"; }; - ifc: ifc@ff71e000 { + ifc: memory-controller@ff71e000 { /* NOR, NAND Flash on board */ ranges = <0x0 0x0 0x0 0x88000000 0x08000000 0x1 0x0 0x0 0xff800000 0x00010000>; diff --git a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi index b8e0edd1ac69..4da451e000d9 100644 --- a/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/bsc9132si-post.dtsi @@ -35,7 +35,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; /* FIXME: Test whether interrupts are split */ interrupts = <16 2 0 0 20 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/c293pcie.dts b/arch/powerpc/boot/dts/fsl/c293pcie.dts index 5e905e0857cf..e2fdac2ed420 100644 --- a/arch/powerpc/boot/dts/fsl/c293pcie.dts +++ b/arch/powerpc/boot/dts/fsl/c293pcie.dts @@ -42,7 +42,7 @@ device_type = "memory"; }; - ifc: ifc@fffe1e000 { + ifc: memory-controller@fffe1e000 { reg = <0xf 0xffe1e000 0 0x2000>; ranges = <0x0 0x0 0xf 0xec000000 0x04000000 0x1 0x0 0xf 0xff800000 0x00010000 diff --git a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi index f208fb8f64b3..2d443d519274 100644 --- a/arch/powerpc/boot/dts/fsl/c293si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/c293si-post.dtsi @@ -35,7 +35,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <19 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi index 41935709ebe8..fba40a1bccc0 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/mpc8536si-post.dtsi @@ -199,6 +199,10 @@ /include/ "pq3-dma-0.dtsi" /include/ "pq3-etsec1-0.dtsi" + enet0: ethernet@24000 { + fsl,wake-on-filer; + fsl,pmc-handle = <&etsec1_clk>; + }; /include/ "pq3-etsec1-timer-0.dtsi" usb@22000 { @@ -222,9 +226,10 @@ }; /include/ "pq3-etsec1-2.dtsi" - - ethernet@26000 { + enet2: ethernet@26000 { cell-index = <1>; + fsl,wake-on-filer; + fsl,pmc-handle = <&etsec3_clk>; }; usb@2b000 { @@ -249,4 +254,9 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" + power@e0070 { + compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc"; + }; }; diff --git a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi index b68eb119faef..ea7416af7ee3 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/mpc8544si-post.dtsi @@ -188,4 +188,6 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi index 579d76cb8e32..dddb7374508d 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/mpc8548si-post.dtsi @@ -156,4 +156,6 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi index 49294cf36b4e..40a6cff77032 100644 --- a/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/mpc8572si-post.dtsi @@ -193,4 +193,6 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts index 3a94acbb3c03..ce3346d77858 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts +++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb.dts @@ -29,3 +29,19 @@ }; /include/ "p1010si-post.dtsi" + +&pci0 { + pcie@0 { + interrupt-map = < + /* IDSEL 0x0 */ + /* + *irq[4:5] are active-high + *irq[6:7] are active-low + */ + 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0 + 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0 + 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0 + 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0 + >; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts index 4cf255fedc96..83590354f9a0 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts +++ b/arch/powerpc/boot/dts/fsl/p1010rdb-pb_36b.dts @@ -56,3 +56,19 @@ }; /include/ "p1010si-post.dtsi" + +&pci0 { + pcie@0 { + interrupt-map = < + /* IDSEL 0x0 */ + /* + *irq[4:5] are active-high + *irq[6:7] are active-low + */ + 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0 + 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0 + 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0 + 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0 + >; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi index 2ca9cee2ddeb..ef49a7d6c69d 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010rdb.dtsi @@ -215,19 +215,3 @@ phy-connection-type = "sgmii"; }; }; - -&pci0 { - pcie@0 { - interrupt-map = < - /* IDSEL 0x0 */ - /* - *irq[4:5] are active-high - *irq[6:7] are active-low - */ - 0000 0x0 0x0 0x1 &mpic 0x4 0x2 0x0 0x0 - 0000 0x0 0x0 0x2 &mpic 0x5 0x2 0x0 0x0 - 0000 0x0 0x0 0x3 &mpic 0x6 0x1 0x0 0x0 - 0000 0x0 0x0 0x4 &mpic 0x7 0x1 0x0 0x0 - >; - }; -}; diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi index fdc19aab2f70..583a6cd05079 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010rdb_32b.dtsi @@ -36,7 +36,7 @@ memory { device_type = "memory"; }; -board_ifc: ifc: ifc@ffe1e000 { +board_ifc: ifc: memory-controller@ffe1e000 { /* NOR, NAND Flashes and CPLD on board */ ranges = <0x0 0x0 0x0 0xee000000 0x02000000 0x1 0x0 0x0 0xff800000 0x00010000 diff --git a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi index de2fceed4f79..4d41efe0038f 100644 --- a/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010rdb_36b.dtsi @@ -36,7 +36,7 @@ memory { device_type = "memory"; }; -board_ifc: ifc: ifc@fffe1e000 { +board_ifc: ifc: memory-controller@fffe1e000 { /* NOR, NAND Flashes and CPLD on board */ ranges = <0x0 0x0 0xf 0xee000000 0x02000000 0x1 0x0 0xf 0xff800000 0x00010000 diff --git a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi index ccda0a91abf0..2d2550729dcc 100644 --- a/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1010si-post.dtsi @@ -35,7 +35,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <16 2 0 0 19 2 0 0>; }; @@ -183,9 +183,23 @@ /include/ "pq3-etsec2-1.dtsi" /include/ "pq3-etsec2-2.dtsi" + enet0: ethernet@b0000 { + fsl,pmc-handle = <&etsec1_clk>; + }; + + enet1: ethernet@b1000 { + fsl,pmc-handle = <&etsec2_clk>; + }; + + enet2: ethernet@b2000 { + fsl,pmc-handle = <&etsec3_clk>; + }; + global-utilities@e0000 { compatible = "fsl,p1010-guts"; reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi index 642dc3a83d0e..cc4c7461003b 100644 --- a/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1020si-post.dtsi @@ -163,14 +163,17 @@ /include/ "pq3-etsec2-0.dtsi" enet0: enet0_grp2: ethernet@b0000 { + fsl,pmc-handle = <&etsec1_clk>; }; /include/ "pq3-etsec2-1.dtsi" enet1: enet1_grp2: ethernet@b1000 { + fsl,pmc-handle = <&etsec2_clk>; }; /include/ "pq3-etsec2-2.dtsi" enet2: enet2_grp2: ethernet@b2000 { + fsl,pmc-handle = <&etsec3_clk>; }; global-utilities@e0000 { @@ -178,6 +181,8 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; /include/ "pq3-etsec2-grp2-0.dtsi" diff --git a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi index 407cb5fd0f5b..378195db9fca 100644 --- a/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1021si-post.dtsi @@ -159,14 +159,17 @@ /include/ "pq3-etsec2-0.dtsi" enet0: enet0_grp2: ethernet@b0000 { + fsl,pmc-handle = <&etsec1_clk>; }; /include/ "pq3-etsec2-1.dtsi" enet1: enet1_grp2: ethernet@b1000 { + fsl,pmc-handle = <&etsec2_clk>; }; /include/ "pq3-etsec2-2.dtsi" enet2: enet2_grp2: ethernet@b2000 { + fsl,pmc-handle = <&etsec3_clk>; }; global-utilities@e0000 { @@ -174,6 +177,8 @@ reg = <0xe0000 0x1000>; fsl,has-rstcr; }; + +/include/ "pq3-power.dtsi" }; &qe { diff --git a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi index 093e4e3ed368..6ac21e81344a 100644 --- a/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p1022si-post.dtsi @@ -225,11 +225,13 @@ /include/ "pq3-etsec2-0.dtsi" enet0: enet0_grp2: ethernet@b0000 { fsl,wake-on-filer; + fsl,pmc-handle = <&etsec1_clk>; }; /include/ "pq3-etsec2-1.dtsi" enet1: enet1_grp2: ethernet@b1000 { fsl,wake-on-filer; + fsl,pmc-handle = <&etsec2_clk>; }; global-utilities@e0000 { @@ -238,9 +240,10 @@ fsl,has-rstcr; }; +/include/ "pq3-power.dtsi" power@e0070 { - compatible = "fsl,mpc8536-pmc", "fsl,mpc8548-pmc"; - reg = <0xe0070 0x20>; + compatible = "fsl,p1022-pmc", "fsl,mpc8536-pmc", + "fsl,mpc8548-pmc"; }; }; diff --git a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi index 81b9ab2119be..d410082d21c0 100644 --- a/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p2020si-post.dtsi @@ -178,6 +178,10 @@ compatible = "fsl-usb2-dr-v1.6", "fsl-usb2-dr"; }; /include/ "pq3-etsec1-0.dtsi" + enet0: ethernet@24000 { + fsl,pmc-handle = <&etsec1_clk>; + + }; /include/ "pq3-etsec1-timer-0.dtsi" ptp_clock@24e00 { @@ -186,7 +190,15 @@ /include/ "pq3-etsec1-1.dtsi" + enet1: ethernet@25000 { + fsl,pmc-handle = <&etsec2_clk>; + }; + /include/ "pq3-etsec1-2.dtsi" + enet2: ethernet@26000 { + fsl,pmc-handle = <&etsec3_clk>; + }; + /include/ "pq3-esdhc-0.dtsi" sdhc@2e000 { compatible = "fsl,p2020-esdhc", "fsl,esdhc"; @@ -202,8 +214,5 @@ fsl,has-rstcr; }; - pmc: power@e0070 { - compatible = "fsl,mpc8548-pmc"; - reg = <0xe0070 0x20>; - }; +/include/ "pq3-power.dtsi" }; diff --git a/arch/powerpc/boot/dts/fsl/pq3-power.dtsi b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi new file mode 100644 index 000000000000..6af12401004d --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/pq3-power.dtsi @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: (GPL-2.0+) +/* + * Copyright 2024 NXP + */ + +power@e0070 { + compatible = "fsl,mpc8548-pmc"; + reg = <0xe0070 0x20>; + + etsec1_clk: soc-clk@24 { + fsl,pmcdr-mask = <0x00000080>; + }; + etsec2_clk: soc-clk@25 { + fsl,pmcdr-mask = <0x00000040>; + }; + etsec3_clk: soc-clk@26 { + fsl,pmcdr-mask = <0x00000020>; + }; +}; diff --git a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi index aa5152ca8120..8ef0c020206b 100644 --- a/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1023si-post.dtsi @@ -52,7 +52,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <25 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts index 270aaf631f2a..7d003e07a9fb 100644 --- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts @@ -91,7 +91,7 @@ board-control@2,0 { #address-cells = <1>; #size-cells = <1>; - compatible = "fsl,t1024-cpld"; + compatible = "fsl,t1024-cpld", "fsl,deepsleep-cpld"; reg = <3 0 0x300>; ranges = <0 3 0 0x300>; bank-width = <1>; diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts index dd3aab81e9de..4347924e9aa7 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts @@ -104,7 +104,7 @@ ifc: localbus@ffe124000 { cpld@3,0 { - compatible = "fsl,t1040rdb-cpld"; + compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld"; }; }; }; diff --git a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi index 776788623204..c9542b73bd7f 100644 --- a/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t1040si-post.dtsi @@ -52,7 +52,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <25 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb.dts b/arch/powerpc/boot/dts/fsl/t1042rdb.dts index 3ebb712224cb..099764322b33 100644 --- a/arch/powerpc/boot/dts/fsl/t1042rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1042rdb.dts @@ -68,7 +68,7 @@ ifc: localbus@ffe124000 { cpld@3,0 { - compatible = "fsl,t1042rdb-cpld"; + compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld"; }; }; }; diff --git a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts index 8ec3ff45e6fc..b10cab1a347b 100644 --- a/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts +++ b/arch/powerpc/boot/dts/fsl/t1042rdb_pi.dts @@ -41,7 +41,7 @@ ifc: localbus@ffe124000 { cpld@3,0 { - compatible = "fsl,t1042rdb_pi-cpld"; + compatible = "fsl,t104xrdb-cpld", "fsl,deepsleep-cpld"; }; }; diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi index 27714dc2f04a..6bb95878d39d 100644 --- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi @@ -50,7 +50,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <25 2 0 0>; }; diff --git a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi index fcac73486d48..65f3e17c0d41 100644 --- a/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/t4240si-post.dtsi @@ -50,7 +50,7 @@ &ifc { #address-cells = <2>; #size-cells = <1>; - compatible = "fsl,ifc", "simple-bus"; + compatible = "fsl,ifc"; interrupts = <25 2 0 0>; }; diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index cae31a6e8f02..2c0e2a1cab01 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -188,7 +188,7 @@ static inline void prep_esm_blob(struct addr_range vmlinux, void *chosen) { } /* A buffer that may be edited by tools operating on a zImage binary so as to * edit the command line passed to vmlinux (by setting /chosen/bootargs). - * The buffer is put in it's own section so that tools may locate it easier. + * The buffer is put in its own section so that tools may locate it easier. */ static char cmdline[BOOT_COMMAND_LINE_SIZE] __attribute__((__section__("__builtin_cmdline"))); diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c index f157717ae814..89ff46b8b225 100644 --- a/arch/powerpc/boot/ps3.c +++ b/arch/powerpc/boot/ps3.c @@ -25,7 +25,7 @@ BSS_STACK(4096); /* A buffer that may be edited by tools operating on a zImage binary so as to * edit the command line passed to vmlinux (by setting /chosen/bootargs). - * The buffer is put in it's own section so that tools may locate it easier. + * The buffer is put in its own section so that tools may locate it easier. */ static char cmdline[BOOT_COMMAND_LINE_SIZE] diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 727d4b321937..0efabccd820c 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -29,7 +29,7 @@ static __always_inline bool cpu_has_feature(unsigned long feature) #endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG - if (!static_key_initialized) { + if (!static_key_feature_checks_initialized) { printk("Warning! cpu_has_feature() used prior to jump label init!\n"); dump_stack(); return early_cpu_has_feature(feature); diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 514dd056c2c8..91a9fd53254f 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -82,7 +82,7 @@ struct eeh_pe { int false_positives; /* Times of reported #ff's */ atomic_t pass_dev_cnt; /* Count of passed through devs */ struct eeh_pe *parent; /* Parent PE */ - void *data; /* PE auxillary data */ + void *data; /* PE auxiliary data */ struct list_head child_list; /* List of PEs below this PE */ struct list_head child; /* Memb. child_list/eeh_phb_pe */ struct list_head edevs; /* List of eeh_dev in this PE */ diff --git a/arch/powerpc/include/asm/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h index 27f9e11eda28..e83869a4eb6a 100644 --- a/arch/powerpc/include/asm/fadump-internal.h +++ b/arch/powerpc/include/asm/fadump-internal.h @@ -42,13 +42,38 @@ static inline u64 fadump_str_to_u64(const char *str) #define FADUMP_CPU_UNKNOWN (~((u32)0)) -#define FADUMP_CRASH_INFO_MAGIC fadump_str_to_u64("FADMPINF") +/* + * The introduction of new fields in the fadump crash info header has + * led to a change in the magic key from `FADMPINF` to `FADMPSIG` for + * identifying a kernel crash from an old kernel. + * + * To prevent the need for further changes to the magic number in the + * event of future modifications to the fadump crash info header, a + * version field has been introduced to track the fadump crash info + * header version. + * + * Consider a few points before adding new members to the fadump crash info + * header structure: + * + * - Append new members; avoid adding them in between. + * - Non-primitive members should have a size member as well. + * - For every change in the fadump header, increment the + * fadump header version. This helps the updated kernel decide how to + * handle kernel dumps from older kernels. + */ +#define FADUMP_CRASH_INFO_MAGIC_OLD fadump_str_to_u64("FADMPINF") +#define FADUMP_CRASH_INFO_MAGIC fadump_str_to_u64("FADMPSIG") +#define FADUMP_HEADER_VERSION 1 /* fadump crash info structure */ struct fadump_crash_info_header { u64 magic_number; - u64 elfcorehdr_addr; + u32 version; u32 crashing_cpu; + u64 vmcoreinfo_raddr; + u64 vmcoreinfo_size; + u32 pt_regs_sz; + u32 cpu_mask_sz; struct pt_regs regs; struct cpumask cpu_mask; }; @@ -94,9 +119,13 @@ struct fw_dump { u64 boot_mem_regs_cnt; unsigned long fadumphdr_addr; + u64 elfcorehdr_addr; + u64 elfcorehdr_size; unsigned long cpu_notes_buf_vaddr; unsigned long cpu_notes_buf_size; + unsigned long param_area; + /* * Maximum size supported by firmware to copy from source to * destination address per entry. @@ -111,6 +140,7 @@ struct fw_dump { unsigned long dump_active:1; unsigned long dump_registered:1; unsigned long nocma:1; + unsigned long param_area_supported:1; struct fadump_ops *ops; }; @@ -129,6 +159,7 @@ struct fadump_ops { struct seq_file *m); void (*fadump_trigger)(struct fadump_crash_info_header *fdh, const char *msg); + int (*fadump_max_boot_mem_rgns)(void); }; /* Helper functions */ @@ -136,7 +167,6 @@ s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus); void fadump_free_cpu_notes_buf(void); u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs); void __init fadump_update_elfcore_header(char *bufp); -bool is_fadump_boot_mem_contiguous(void); bool is_fadump_reserved_mem_contiguous(void); #else /* !CONFIG_PRESERVE_FA_DUMP */ diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h index 526a6a647312..ef40c9b6972a 100644 --- a/arch/powerpc/include/asm/fadump.h +++ b/arch/powerpc/include/asm/fadump.h @@ -19,12 +19,14 @@ extern int is_fadump_active(void); extern int should_fadump_crash(void); extern void crash_fadump(struct pt_regs *, const char *); extern void fadump_cleanup(void); +extern void fadump_append_bootargs(void); #else /* CONFIG_FA_DUMP */ static inline int is_fadump_active(void) { return 0; } static inline int should_fadump_crash(void) { return 0; } static inline void crash_fadump(struct pt_regs *regs, const char *str) { } static inline void fadump_cleanup(void) { } +static inline void fadump_append_bootargs(void) { } #endif /* !CONFIG_FA_DUMP */ #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 77824bd289a3..17d168dd8b49 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -291,6 +291,8 @@ extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; +extern bool static_key_feature_checks_initialized; + void apply_feature_fixups(void); void update_mmu_feature_fixups(unsigned long mask); void setup_feature_keys(void); diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index a41e542ba94d..7a8495660c2f 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -524,7 +524,7 @@ long plpar_hcall_norets_notrace(unsigned long opcode, ...); * Used for all but the craziest of phyp interfaces (see plpar_hcall9) */ #define PLPAR_HCALL_BUFSIZE 4 -long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall_raw: - Make a hypervisor call without calculating hcall stats @@ -538,7 +538,7 @@ long plpar_hcall(unsigned long opcode, unsigned long *retbuf, ...); * plpar_hcall, but plpar_hcall_raw works in real mode and does not * calculate hypervisor call statistics. */ -long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL_BUFSIZE], ...); /** * plpar_hcall9: - Make a pseries hypervisor call with up to 9 return arguments @@ -549,8 +549,8 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); * PLPAR_HCALL9_BUFSIZE to size the return argument buffer. */ #define PLPAR_HCALL9_BUFSIZE 9 -long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); -long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); +long plpar_hcall9(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); +long plpar_hcall9_raw(unsigned long opcode, unsigned long retbuf[static PLPAR_HCALL9_BUFSIZE], ...); /* pseries hcall tracing */ extern struct static_key hcall_tracepoint_key; @@ -570,7 +570,7 @@ struct hvcall_mpp_data { unsigned long backing_mem; }; -int h_get_mpp(struct hvcall_mpp_data *); +long h_get_mpp(struct hvcall_mpp_data *mpp_data); struct hvcall_mpp_x_data { unsigned long coalesced_bytes; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index 7b610864b364..2d6c886b40f4 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -336,6 +336,14 @@ static inline void interrupt_nmi_enter_prepare(struct pt_regs *regs, struct inte if (IS_ENABLED(CONFIG_KASAN)) return; + /* + * Likewise, do not use it in real mode if percpu first chunk is not + * embedded. With CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK enabled there + * are chances where percpu allocation can come from vmalloc area. + */ + if (percpu_first_chunk_is_paged) + return; + /* Otherwise, it should be safe to call it */ nmi_enter(); } @@ -351,6 +359,8 @@ static inline void interrupt_nmi_exit_prepare(struct pt_regs *regs, struct inter // no nmi_exit for a pseries hash guest taking a real mode exception } else if (IS_ENABLED(CONFIG_KASAN)) { // no nmi_exit for KASAN in real mode + } else if (percpu_first_chunk_is_paged) { + // no nmi_exit if percpu first chunk is not embedded } else { nmi_exit(); } diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 08c550ed49be..52e1b1d15ff6 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -37,7 +37,7 @@ extern struct pci_dev *isa_bridge_pcidev; * define properly based on the platform */ #ifndef CONFIG_PCI -#define _IO_BASE 0 +#define _IO_BASE POISON_POINTER_DELTA #define _ISA_MEM_BASE 0 #define PCI_DRAM_OFFSET 0 #elif defined(CONFIG_PPC32) @@ -585,12 +585,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_inw(port) _rec_inw(port) #define __do_inl(port) _rec_inl(port) #else /* CONFIG_PPC32 */ -#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)_IO_BASE+port); -#define __do_inb(port) readb((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inw(port) readw((PCI_IO_ADDR)_IO_BASE + port); -#define __do_inl(port) readl((PCI_IO_ADDR)_IO_BASE + port); +#define __do_outb(val, port) writeb(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outw(val, port) writew(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_outl(val, port) writel(val,(PCI_IO_ADDR)(_IO_BASE+port)); +#define __do_inb(port) readb((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inw(port) readw((PCI_IO_ADDR)(_IO_BASE + port)); +#define __do_inl(port) readl((PCI_IO_ADDR)(_IO_BASE + port)); #endif /* !CONFIG_PPC32 */ #ifdef CONFIG_EEH @@ -606,12 +606,12 @@ __do_out_asm(_rec_outl, "stwbrx") #define __do_writesw(a, b, n) _outsw(PCI_FIX_ADDR(a),(b),(n)) #define __do_writesl(a, b, n) _outsl(PCI_FIX_ADDR(a),(b),(n)) -#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)_IO_BASE+(p), (b), (n)) -#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) -#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)_IO_BASE+(p),(b),(n)) +#define __do_insb(p, b, n) readsb((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insw(p, b, n) readsw((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_insl(p, b, n) readsl((PCI_IO_ADDR)(_IO_BASE+(p)), (b), (n)) +#define __do_outsb(p, b, n) writesb((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsw(p, b, n) writesw((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) +#define __do_outsl(p, b, n) writesl((PCI_IO_ADDR)(_IO_BASE+(p)),(b),(n)) #define __do_memset_io(addr, c, n) \ _memset_io(PCI_FIX_ADDR(addr), c, n) @@ -982,7 +982,7 @@ static inline phys_addr_t page_to_phys(struct page *page) } /* - * 32 bits still uses virt_to_bus() for it's implementation of DMA + * 32 bits still uses virt_to_bus() for its implementation of DMA * mappings se we have to keep it defined here. We also have some old * drivers (shame shame shame) that use bus_to_virt() and haven't been * fixed yet so I need to define it here. diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index fdb90e24dc74..95a98b390d62 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -135,6 +135,17 @@ static inline void crash_setup_regs(struct pt_regs *newregs, ppc_save_regs(newregs); } +#ifdef CONFIG_CRASH_HOTPLUG +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); +#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support + +unsigned int arch_crash_get_elfcorehdr_size(void); +#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size +#endif /* CONFIG_CRASH_HOTPLUG */ + extern int crashing_cpu; extern void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)); extern void crash_ipi_callback(struct pt_regs *regs); @@ -185,6 +196,10 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) #endif /* CONFIG_CRASH_DUMP */ +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +int update_cpus_node(void *fdt); +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/kexec.h> #endif diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index f83866a19e87..14055896cbcb 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -7,19 +7,9 @@ void sort_memory_ranges(struct crash_mem *mrngs, bool merge); struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); -int add_tce_mem_ranges(struct crash_mem **mem_ranges); -int add_initrd_mem_range(struct crash_mem **mem_ranges); -#ifdef CONFIG_PPC_64S_HASH_MMU -int add_htab_mem_range(struct crash_mem **mem_ranges); -#else -static inline int add_htab_mem_range(struct crash_mem **mem_ranges) -{ - return 0; -} -#endif -int add_kernel_mem_range(struct crash_mem **mem_ranges); -int add_rtas_mem_range(struct crash_mem **mem_ranges); -int add_opal_mem_range(struct crash_mem **mem_ranges); -int add_reserved_mem_ranges(struct crash_mem **mem_ranges); - +int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); +int get_exclude_memory_ranges(struct crash_mem **mem_ranges); +int get_reserved_memory_ranges(struct crash_mem **mem_ranges); +int get_crash_memory_ranges(struct crash_mem **mem_ranges); +int get_usable_memory_ranges(struct crash_mem **mem_ranges); #endif /* _ASM_POWERPC_KEXEC_RANGES_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 3b72c7ed24cf..24f830cf9bb4 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -251,7 +251,7 @@ static __always_inline bool mmu_has_feature(unsigned long feature) #endif #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG - if (!static_key_initialized) { + if (!static_key_feature_checks_initialized) { printk("Warning! mmu_has_feature() used prior to jump label init!\n"); dump_stack(); return early_mmu_has_feature(feature); diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h index a8e2e8339fb7..300c777cc307 100644 --- a/arch/powerpc/include/asm/module.h +++ b/arch/powerpc/include/asm/module.h @@ -48,11 +48,6 @@ struct mod_arch_specific { unsigned long tramp; unsigned long tramp_regs; #endif - - /* List of BUG addresses, source line numbers and filenames */ - struct list_head bug_list; - struct bug_entry *bug_table; - unsigned int num_bugs; }; /* diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h index a2bc4b95e703..8c9d4b26bf57 100644 --- a/arch/powerpc/include/asm/opal-api.h +++ b/arch/powerpc/include/asm/opal-api.h @@ -1027,10 +1027,10 @@ struct opal_i2c_request { * The host will pass on OPAL, a buffer of length OPAL_SYSEPOW_MAX * with individual elements being 16 bits wide to fetch the system * wide EPOW status. Each element in the buffer will contain the - * EPOW status in it's bit representation for a particular EPOW sub + * EPOW status in its bit representation for a particular EPOW sub * class as defined here. So multiple detailed EPOW status bits * specific for any sub class can be represented in a single buffer - * element as it's bit representation. + * element as its bit representation. */ /* System EPOW type */ diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index 8e5b7d0b851c..634970ce13c6 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -15,6 +15,16 @@ #endif /* CONFIG_SMP */ #endif /* __powerpc64__ */ +#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK) && defined(CONFIG_SMP) +#include <linux/jump_label.h> +DECLARE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); + +#define percpu_first_chunk_is_paged \ + (static_key_enabled(&__percpu_first_chunk_is_paged.key)) +#else +#define percpu_first_chunk_is_paged false +#endif /* CONFIG_PPC64 && CONFIG_SMP */ + #include <asm-generic/percpu.h> #include <asm/paca.h> diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h index 2495866f2e97..420e2878ae67 100644 --- a/arch/powerpc/include/asm/pmac_feature.h +++ b/arch/powerpc/include/asm/pmac_feature.h @@ -192,7 +192,7 @@ static inline long pmac_call_feature(int selector, struct device_node* node, /* PMAC_FTR_BMAC_ENABLE (struct device_node* node, 0, int value) * enable/disable the bmac (ethernet) cell of a mac-io ASIC, also drive - * it's reset line + * its reset line */ #define PMAC_FTR_BMAC_ENABLE PMAC_FTR_DEF(6) diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 005601243dda..076ae60b4a55 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -510,6 +510,7 @@ #define PPC_RAW_STB(r, base, i) (0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LBZ(r, base, i) (0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LHA(r, base, i) (0xa8000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) #define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) #define PPC_RAW_LWBRX(r, base, b) (0x7c00042c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) @@ -532,6 +533,7 @@ #define PPC_RAW_MULW(d, a, b) (0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_MULHWU(d, a, b) (0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_MULI(d, a, i) (0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_DIVW(d, a, b) (0x7c0003d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVWU(d, a, b) (0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVDU(d, a, b) (0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) #define PPC_RAW_DIVDE(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) @@ -550,6 +552,8 @@ #define PPC_RAW_XOR(d, a, b) (0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) #define PPC_RAW_XORI(d, a, i) (0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) #define PPC_RAW_XORIS(d, a, i) (0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_EXTSB(d, a) (0x7c000774 | ___PPC_RA(d) | ___PPC_RS(a)) +#define PPC_RAW_EXTSH(d, a) (0x7c000734 | ___PPC_RA(d) | ___PPC_RS(a)) #define PPC_RAW_EXTSW(d, a) (0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a)) #define PPC_RAW_SLW(d, a, s) (0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) #define PPC_RAW_SLD(d, a, s) (0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index b2c51d337e60..e44cac0da346 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -260,7 +260,8 @@ struct thread_struct { unsigned long sier2; unsigned long sier3; unsigned long hashkeyr; - + unsigned long dexcr; + unsigned long dexcr_onexec; /* Reset value to load on exec */ #endif }; @@ -333,6 +334,16 @@ extern int set_endian(struct task_struct *tsk, unsigned int val); extern int get_unalign_ctl(struct task_struct *tsk, unsigned long adr); extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); +#ifdef CONFIG_PPC_BOOK3S_64 + +#define PPC_GET_DEXCR_ASPECT(tsk, asp) get_dexcr_prctl((tsk), (asp)) +#define PPC_SET_DEXCR_ASPECT(tsk, asp, val) set_dexcr_prctl((tsk), (asp), (val)) + +int get_dexcr_prctl(struct task_struct *tsk, unsigned long asp); +int set_dexcr_prctl(struct task_struct *tsk, unsigned long asp, unsigned long val); + +#endif + extern void load_fp_state(struct thread_fp_state *fp); extern void store_fp_state(struct thread_fp_state *fp); extern void load_vr_state(struct thread_vr_state *vr); diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index d3d1aea009b4..eed33cb916d0 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -615,7 +615,7 @@ #define HID1_ABE (1<<10) /* 7450 Address Broadcast Enable */ #define HID1_PS (1<<16) /* 750FX PLL selection */ #endif -#define SPRN_HID2 0x3F8 /* Hardware Implementation Register 2 */ +#define SPRN_HID2_750FX 0x3F8 /* IBM 750FX HID2 Register */ #define SPRN_HID2_GEKKO 0x398 /* Gekko HID2 Register */ #define SPRN_HID2_G2_LE 0x3F3 /* G2_LE HID2 Register */ #define HID2_G2_LE_HBE (1<<18) /* High BAT Enable (G2_LE) */ diff --git a/arch/powerpc/include/asm/uninorth.h b/arch/powerpc/include/asm/uninorth.h index e278299b9b37..6949b5daa37d 100644 --- a/arch/powerpc/include/asm/uninorth.h +++ b/arch/powerpc/include/asm/uninorth.h @@ -144,7 +144,7 @@ #define UNI_N_HWINIT_STATE_SLEEPING 0x01 #define UNI_N_HWINIT_STATE_RUNNING 0x02 /* This last bit appear to be used by the bootROM to know the second - * CPU has started and will enter it's sleep loop with IP=0 + * CPU has started and will enter its sleep loop with IP=0 */ #define UNI_N_HWINIT_STATE_CPU1_FLAG 0x10000000 diff --git a/arch/powerpc/include/uapi/asm/bootx.h b/arch/powerpc/include/uapi/asm/bootx.h index 6728c7e24e58..1b8c121071d9 100644 --- a/arch/powerpc/include/uapi/asm/bootx.h +++ b/arch/powerpc/include/uapi/asm/bootx.h @@ -108,7 +108,7 @@ typedef struct boot_infos /* ALL BELOW NEW (vers. 4) */ /* This defines the physical memory. Valid with BOOT_ARCH_NUBUS flag - (non-PCI) only. On PCI, memory is contiguous and it's size is in the + (non-PCI) only. On PCI, memory is contiguous and its size is in the device-tree. */ boot_info_map_entry_t physMemoryMap[MAX_MEM_MAP_SIZE]; /* Where the phys memory is */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index d3282fbea4f2..8585d03c02d3 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -3,9 +3,6 @@ # Makefile for the linux kernel. # -ifdef CONFIG_PPC64 -CFLAGS_prom_init.o += $(NO_MINIMAL_TOC) -endif ifdef CONFIG_PPC32 CFLAGS_prom_init.o += -fPIC CFLAGS_btext.o += -fPIC @@ -87,6 +84,7 @@ obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_DAWR) += dawr.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_ppc970.o cpu_setup_pa6t.o obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o +obj-$(CONFIG_PPC_BOOK3S_64) += dexcr.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_64e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o @@ -190,9 +188,6 @@ GCOV_PROFILE_kprobes-ftrace.o := n KCOV_INSTRUMENT_kprobes-ftrace.o := n KCSAN_SANITIZE_kprobes-ftrace.o := n UBSAN_SANITIZE_kprobes-ftrace.o := n -GCOV_PROFILE_syscall_64.o := n -KCOV_INSTRUMENT_syscall_64.o := n -UBSAN_SANITIZE_syscall_64.o := n UBSAN_SANITIZE_vdso.o := n # Necessary for booting with kcov enabled on book3e machines diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index bfd3f442e5eb..ab3ca74e6730 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -401,7 +401,7 @@ _GLOBAL(__save_cpu_setup) andi. r3,r3,0xff00 cmpwi cr0,r3,0x0200 bne 1f - mfspr r4,SPRN_HID2 + mfspr r4,SPRN_HID2_750FX stw r4,CS_HID2(r5) 1: mtcr r7 @@ -496,7 +496,7 @@ _GLOBAL(__restore_cpu_setup) bne 4f lwz r4,CS_HID2(r5) rlwinm r4,r4,0,19,17 - mtspr SPRN_HID2,r4 + mtspr SPRN_HID2_750FX,r4 sync 4: lwz r4,CS_HID1(r5) diff --git a/arch/powerpc/kernel/dexcr.c b/arch/powerpc/kernel/dexcr.c new file mode 100644 index 000000000000..3a0358e91c60 --- /dev/null +++ b/arch/powerpc/kernel/dexcr.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/capability.h> +#include <linux/cpu.h> +#include <linux/init.h> +#include <linux/prctl.h> +#include <linux/sched.h> + +#include <asm/cpu_has_feature.h> +#include <asm/cputable.h> +#include <asm/processor.h> +#include <asm/reg.h> + +static int __init init_task_dexcr(void) +{ + if (!early_cpu_has_feature(CPU_FTR_ARCH_31)) + return 0; + + current->thread.dexcr_onexec = mfspr(SPRN_DEXCR); + + return 0; +} +early_initcall(init_task_dexcr) + +/* Allow thread local configuration of these by default */ +#define DEXCR_PRCTL_EDITABLE ( \ + DEXCR_PR_IBRTPD | \ + DEXCR_PR_SRAPD | \ + DEXCR_PR_NPHIE) + +static int prctl_to_aspect(unsigned long which, unsigned int *aspect) +{ + switch (which) { + case PR_PPC_DEXCR_SBHE: + *aspect = DEXCR_PR_SBHE; + break; + case PR_PPC_DEXCR_IBRTPD: + *aspect = DEXCR_PR_IBRTPD; + break; + case PR_PPC_DEXCR_SRAPD: + *aspect = DEXCR_PR_SRAPD; + break; + case PR_PPC_DEXCR_NPHIE: + *aspect = DEXCR_PR_NPHIE; + break; + default: + return -ENODEV; + } + + return 0; +} + +int get_dexcr_prctl(struct task_struct *task, unsigned long which) +{ + unsigned int aspect; + int ret; + + ret = prctl_to_aspect(which, &aspect); + if (ret) + return ret; + + if (aspect & DEXCR_PRCTL_EDITABLE) + ret |= PR_PPC_DEXCR_CTRL_EDITABLE; + + if (aspect & mfspr(SPRN_DEXCR)) + ret |= PR_PPC_DEXCR_CTRL_SET; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR; + + if (aspect & task->thread.dexcr_onexec) + ret |= PR_PPC_DEXCR_CTRL_SET_ONEXEC; + else + ret |= PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC; + + return ret; +} + +int set_dexcr_prctl(struct task_struct *task, unsigned long which, unsigned long ctrl) +{ + unsigned long dexcr; + unsigned int aspect; + int err = 0; + + err = prctl_to_aspect(which, &aspect); + if (err) + return err; + + if (!(aspect & DEXCR_PRCTL_EDITABLE)) + return -EPERM; + + if (ctrl & ~PR_PPC_DEXCR_CTRL_MASK) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET && ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + return -EINVAL; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC && ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + return -EINVAL; + + /* + * We do not want an unprivileged process being able to disable + * a setuid process's hash check instructions + */ + if (aspect == DEXCR_PR_NPHIE && + ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC && + !capable(CAP_SYS_ADMIN)) + return -EPERM; + + dexcr = mfspr(SPRN_DEXCR); + + if (ctrl & PR_PPC_DEXCR_CTRL_SET) + dexcr |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR) + dexcr &= ~aspect; + + if (ctrl & PR_PPC_DEXCR_CTRL_SET_ONEXEC) + task->thread.dexcr_onexec |= aspect; + else if (ctrl & PR_PPC_DEXCR_CTRL_CLEAR_ONEXEC) + task->thread.dexcr_onexec &= ~aspect; + + mtspr(SPRN_DEXCR, dexcr); + + return 0; +} diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index ab316e155ea9..6670063a7a6c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -506,9 +506,18 @@ int eeh_dev_check_failure(struct eeh_dev *edev) * We will punt with the following conditions: Failure to get * PE's state, EEH not support and Permanently unavailable * state, PE is in good state. + * + * On the pSeries, after reaching the threshold, get_state might + * return EEH_STATE_NOT_SUPPORT. However, it's possible that the + * device state remains uncleared if the device is not marked + * pci_channel_io_perm_failure. Therefore, consider logging the + * event to let device removal happen. + * */ if ((ret < 0) || - (ret == EEH_STATE_NOT_SUPPORT) || eeh_state_active(ret)) { + (ret == EEH_STATE_NOT_SUPPORT && + dev->error_state == pci_channel_io_perm_failure) || + eeh_state_active(ret)) { eeh_stats.false_positives++; pe->false_positives++; rc = 0; diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 48773d2d9be3..7efe04c68f0f 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -865,9 +865,18 @@ void eeh_handle_normal_event(struct eeh_pe *pe) devices++; if (!devices) { - pr_debug("EEH: Frozen PHB#%x-PE#%x is empty!\n", + pr_warn("EEH: Frozen PHB#%x-PE#%x is empty!\n", pe->phb->global_number, pe->addr); - goto out; /* nothing to recover */ + /* + * The device is removed, tear down its state, on powernv + * hotplug driver would take care of it but not on pseries, + * permanently disable the card as it is hot removed. + * + * In the case of powernv, note that the removal of device + * is covered by pci rescan lock, so no problem even if hotplug + * driver attempts to remove the device. + */ + goto recover_failed; } /* Log the event */ diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index e0ce81279624..d1030bc52564 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -24,10 +24,10 @@ static int eeh_pe_aux_size = 0; static LIST_HEAD(eeh_phb_pe); /** - * eeh_set_pe_aux_size - Set PE auxillary data size - * @size: PE auxillary data size + * eeh_set_pe_aux_size - Set PE auxiliary data size + * @size: PE auxiliary data size in bytes * - * Set PE auxillary data size + * Set PE auxiliary data size. */ void eeh_set_pe_aux_size(int size) { @@ -527,7 +527,7 @@ EXPORT_SYMBOL_GPL(eeh_pe_state_mark); * eeh_pe_mark_isolated * @pe: EEH PE * - * Record that a PE has been isolated by marking the PE and it's children as + * Record that a PE has been isolated by marking the PE and its children as * EEH_PE_ISOLATED (and EEH_PE_CFG_BLOCKED, if required) and their PCI devices * as pci_channel_io_frozen. */ diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index d14eda1e8589..60f974775fc8 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -53,8 +53,6 @@ static struct kobject *fadump_kobj; static atomic_t cpus_in_fadump; static DEFINE_MUTEX(fadump_mutex); -static struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false }; - #define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */ #define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \ sizeof(struct fadump_memory_range)) @@ -133,6 +131,41 @@ static int __init fadump_cma_init(void) static int __init fadump_cma_init(void) { return 1; } #endif /* CONFIG_CMA */ +/* + * Additional parameters meant for capture kernel are placed in a dedicated area. + * If this is capture kernel boot, append these parameters to bootargs. + */ +void __init fadump_append_bootargs(void) +{ + char *append_args; + size_t len; + + if (!fw_dump.dump_active || !fw_dump.param_area_supported || !fw_dump.param_area) + return; + + if (fw_dump.param_area >= fw_dump.boot_mem_top) { + if (memblock_reserve(fw_dump.param_area, COMMAND_LINE_SIZE)) { + pr_warn("WARNING: Can't use additional parameters area!\n"); + fw_dump.param_area = 0; + return; + } + } + + append_args = (char *)fw_dump.param_area; + len = strlen(boot_command_line); + + /* + * Too late to fail even if cmdline size exceeds. Truncate additional parameters + * to cmdline size and proceed anyway. + */ + if (len + strlen(append_args) >= COMMAND_LINE_SIZE - 1) + pr_warn("WARNING: Appending parameters exceeds cmdline size. Truncating!\n"); + + pr_debug("Cmdline: %s\n", boot_command_line); + snprintf(boot_command_line + len, COMMAND_LINE_SIZE - len, " %s", append_args); + pr_info("Updated cmdline: %s\n", boot_command_line); +} + /* Scan the Firmware Assisted dump configuration details. */ int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) @@ -223,28 +256,6 @@ static bool is_fadump_mem_area_contiguous(u64 d_start, u64 d_end) } /* - * Returns true, if there are no holes in boot memory area, - * false otherwise. - */ -bool is_fadump_boot_mem_contiguous(void) -{ - unsigned long d_start, d_end; - bool ret = false; - int i; - - for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { - d_start = fw_dump.boot_mem_addr[i]; - d_end = d_start + fw_dump.boot_mem_sz[i]; - - ret = is_fadump_mem_area_contiguous(d_start, d_end); - if (!ret) - break; - } - - return ret; -} - -/* * Returns true, if there are no holes in reserved memory area, * false otherwise. */ @@ -373,12 +384,6 @@ static unsigned long __init get_fadump_area_size(void) size = PAGE_ALIGN(size); size += fw_dump.boot_memory_size; size += sizeof(struct fadump_crash_info_header); - size += sizeof(struct elfhdr); /* ELF core header.*/ - size += sizeof(struct elf_phdr); /* place holder for cpu notes */ - /* Program headers for crash memory regions. */ - size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2); - - size = PAGE_ALIGN(size); /* This is to hold kernel metadata on platforms that support it */ size += (fw_dump.ops->fadump_get_metadata_size ? @@ -389,10 +394,11 @@ static unsigned long __init get_fadump_area_size(void) static int __init add_boot_mem_region(unsigned long rstart, unsigned long rsize) { + int max_boot_mem_rgns = fw_dump.ops->fadump_max_boot_mem_rgns(); int i = fw_dump.boot_mem_regs_cnt++; - if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) { - fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS; + if (fw_dump.boot_mem_regs_cnt > max_boot_mem_rgns) { + fw_dump.boot_mem_regs_cnt = max_boot_mem_rgns; return 0; } @@ -573,22 +579,6 @@ int __init fadump_reserve_mem(void) } } - /* - * Calculate the memory boundary. - * If memory_limit is less than actual memory boundary then reserve - * the memory for fadump beyond the memory_limit and adjust the - * memory_limit accordingly, so that the running kernel can run with - * specified memory_limit. - */ - if (memory_limit && memory_limit < memblock_end_of_DRAM()) { - size = get_fadump_area_size(); - if ((memory_limit + size) < memblock_end_of_DRAM()) - memory_limit += size; - else - memory_limit = memblock_end_of_DRAM(); - printk(KERN_INFO "Adjusted memory_limit for firmware-assisted" - " dump, now %#016llx\n", memory_limit); - } if (memory_limit) mem_boundary = memory_limit; else @@ -705,7 +695,7 @@ void crash_fadump(struct pt_regs *regs, const char *str) * old_cpu == -1 means this is the first CPU which has come here, * go ahead and trigger fadump. * - * old_cpu != -1 means some other CPU has already on it's way + * old_cpu != -1 means some other CPU has already on its way * to trigger fadump, just keep looping here. */ this_cpu = smp_processor_id(); @@ -931,36 +921,6 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, return 0; } -static int fadump_exclude_reserved_area(u64 start, u64 end) -{ - u64 ra_start, ra_end; - int ret = 0; - - ra_start = fw_dump.reserve_dump_area_start; - ra_end = ra_start + fw_dump.reserve_dump_area_size; - - if ((ra_start < end) && (ra_end > start)) { - if ((start < ra_start) && (end > ra_end)) { - ret = fadump_add_mem_range(&crash_mrange_info, - start, ra_start); - if (ret) - return ret; - - ret = fadump_add_mem_range(&crash_mrange_info, - ra_end, end); - } else if (start < ra_start) { - ret = fadump_add_mem_range(&crash_mrange_info, - start, ra_start); - } else if (ra_end < end) { - ret = fadump_add_mem_range(&crash_mrange_info, - ra_end, end); - } - } else - ret = fadump_add_mem_range(&crash_mrange_info, start, end); - - return ret; -} - static int fadump_init_elfcore_header(char *bufp) { struct elfhdr *elf; @@ -998,52 +958,6 @@ static int fadump_init_elfcore_header(char *bufp) } /* - * Traverse through memblock structure and setup crash memory ranges. These - * ranges will be used create PT_LOAD program headers in elfcore header. - */ -static int fadump_setup_crash_memory_ranges(void) -{ - u64 i, start, end; - int ret; - - pr_debug("Setup crash memory ranges.\n"); - crash_mrange_info.mem_range_cnt = 0; - - /* - * Boot memory region(s) registered with firmware are moved to - * different location at the time of crash. Create separate program - * header(s) for this memory chunk(s) with the correct offset. - */ - for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { - start = fw_dump.boot_mem_addr[i]; - end = start + fw_dump.boot_mem_sz[i]; - ret = fadump_add_mem_range(&crash_mrange_info, start, end); - if (ret) - return ret; - } - - for_each_mem_range(i, &start, &end) { - /* - * skip the memory chunk that is already added - * (0 through boot_memory_top). - */ - if (start < fw_dump.boot_mem_top) { - if (end > fw_dump.boot_mem_top) - start = fw_dump.boot_mem_top; - else - continue; - } - - /* add this range excluding the reserved dump area. */ - ret = fadump_exclude_reserved_area(start, end); - if (ret) - return ret; - } - - return 0; -} - -/* * If the given physical address falls within the boot memory region then * return the relocated address that points to the dump region reserved * for saving initial boot memory contents. @@ -1073,36 +987,50 @@ static inline unsigned long fadump_relocate(unsigned long paddr) return raddr; } -static int fadump_create_elfcore_headers(char *bufp) +static void __init populate_elf_pt_load(struct elf_phdr *phdr, u64 start, + u64 size, unsigned long long offset) { - unsigned long long raddr, offset; - struct elf_phdr *phdr; + phdr->p_align = 0; + phdr->p_memsz = size; + phdr->p_filesz = size; + phdr->p_paddr = start; + phdr->p_offset = offset; + phdr->p_type = PT_LOAD; + phdr->p_flags = PF_R|PF_W|PF_X; + phdr->p_vaddr = (unsigned long)__va(start); +} + +static void __init fadump_populate_elfcorehdr(struct fadump_crash_info_header *fdh) +{ + char *bufp; struct elfhdr *elf; - int i, j; + struct elf_phdr *phdr; + u64 boot_mem_dest_offset; + unsigned long long i, ra_start, ra_end, ra_size, mstart, mend; + bufp = (char *) fw_dump.elfcorehdr_addr; fadump_init_elfcore_header(bufp); elf = (struct elfhdr *)bufp; bufp += sizeof(struct elfhdr); /* - * setup ELF PT_NOTE, place holder for cpu notes info. The notes info - * will be populated during second kernel boot after crash. Hence - * this PT_NOTE will always be the first elf note. + * Set up ELF PT_NOTE, a placeholder for CPU notes information. + * The notes info will be populated later by platform-specific code. + * Hence, this PT_NOTE will always be the first ELF note. * * NOTE: Any new ELF note addition should be placed after this note. */ phdr = (struct elf_phdr *)bufp; bufp += sizeof(struct elf_phdr); phdr->p_type = PT_NOTE; - phdr->p_flags = 0; - phdr->p_vaddr = 0; - phdr->p_align = 0; - - phdr->p_offset = 0; - phdr->p_paddr = 0; - phdr->p_filesz = 0; - phdr->p_memsz = 0; - + phdr->p_flags = 0; + phdr->p_vaddr = 0; + phdr->p_align = 0; + phdr->p_offset = 0; + phdr->p_paddr = 0; + phdr->p_filesz = 0; + phdr->p_memsz = 0; + /* Increment number of program headers. */ (elf->e_phnum)++; /* setup ELF PT_NOTE for vmcoreinfo */ @@ -1112,55 +1040,66 @@ static int fadump_create_elfcore_headers(char *bufp) phdr->p_flags = 0; phdr->p_vaddr = 0; phdr->p_align = 0; - - phdr->p_paddr = fadump_relocate(paddr_vmcoreinfo_note()); - phdr->p_offset = phdr->p_paddr; - phdr->p_memsz = phdr->p_filesz = VMCOREINFO_NOTE_SIZE; - + phdr->p_paddr = phdr->p_offset = fdh->vmcoreinfo_raddr; + phdr->p_memsz = phdr->p_filesz = fdh->vmcoreinfo_size; /* Increment number of program headers. */ (elf->e_phnum)++; - /* setup PT_LOAD sections. */ - j = 0; - offset = 0; - raddr = fw_dump.boot_mem_addr[0]; - for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) { - u64 mbase, msize; - - mbase = crash_mrange_info.mem_ranges[i].base; - msize = crash_mrange_info.mem_ranges[i].size; - if (!msize) - continue; - + /* + * Setup PT_LOAD sections. first include boot memory regions + * and then add rest of the memory regions. + */ + boot_mem_dest_offset = fw_dump.boot_mem_dest_addr; + for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) { phdr = (struct elf_phdr *)bufp; bufp += sizeof(struct elf_phdr); - phdr->p_type = PT_LOAD; - phdr->p_flags = PF_R|PF_W|PF_X; - phdr->p_offset = mbase; - - if (mbase == raddr) { - /* - * The entire real memory region will be moved by - * firmware to the specified destination_address. - * Hence set the correct offset. - */ - phdr->p_offset = fw_dump.boot_mem_dest_addr + offset; - if (j < (fw_dump.boot_mem_regs_cnt - 1)) { - offset += fw_dump.boot_mem_sz[j]; - raddr = fw_dump.boot_mem_addr[++j]; - } + populate_elf_pt_load(phdr, fw_dump.boot_mem_addr[i], + fw_dump.boot_mem_sz[i], + boot_mem_dest_offset); + /* Increment number of program headers. */ + (elf->e_phnum)++; + boot_mem_dest_offset += fw_dump.boot_mem_sz[i]; + } + + /* Memory reserved for fadump in first kernel */ + ra_start = fw_dump.reserve_dump_area_start; + ra_size = get_fadump_area_size(); + ra_end = ra_start + ra_size; + + phdr = (struct elf_phdr *)bufp; + for_each_mem_range(i, &mstart, &mend) { + /* Boot memory regions already added, skip them now */ + if (mstart < fw_dump.boot_mem_top) { + if (mend > fw_dump.boot_mem_top) + mstart = fw_dump.boot_mem_top; + else + continue; } - phdr->p_paddr = mbase; - phdr->p_vaddr = (unsigned long)__va(mbase); - phdr->p_filesz = msize; - phdr->p_memsz = msize; - phdr->p_align = 0; + /* Handle memblock regions overlaps with fadump reserved area */ + if ((ra_start < mend) && (ra_end > mstart)) { + if ((mstart < ra_start) && (mend > ra_end)) { + populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart); + /* Increment number of program headers. */ + (elf->e_phnum)++; + bufp += sizeof(struct elf_phdr); + phdr = (struct elf_phdr *)bufp; + populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end); + } else if (mstart < ra_start) { + populate_elf_pt_load(phdr, mstart, ra_start - mstart, mstart); + } else if (ra_end < mend) { + populate_elf_pt_load(phdr, ra_end, mend - ra_end, ra_end); + } + } else { + /* No overlap with fadump reserved memory region */ + populate_elf_pt_load(phdr, mstart, mend - mstart, mstart); + } /* Increment number of program headers. */ (elf->e_phnum)++; + bufp += sizeof(struct elf_phdr); + phdr = (struct elf_phdr *) bufp; } - return 0; } static unsigned long init_fadump_header(unsigned long addr) @@ -1175,14 +1114,25 @@ static unsigned long init_fadump_header(unsigned long addr) memset(fdh, 0, sizeof(struct fadump_crash_info_header)); fdh->magic_number = FADUMP_CRASH_INFO_MAGIC; - fdh->elfcorehdr_addr = addr; + fdh->version = FADUMP_HEADER_VERSION; /* We will set the crashing cpu id in crash_fadump() during crash. */ fdh->crashing_cpu = FADUMP_CPU_UNKNOWN; + + /* + * The physical address and size of vmcoreinfo are required in the + * second kernel to prepare elfcorehdr. + */ + fdh->vmcoreinfo_raddr = fadump_relocate(paddr_vmcoreinfo_note()); + fdh->vmcoreinfo_size = VMCOREINFO_NOTE_SIZE; + + + fdh->pt_regs_sz = sizeof(struct pt_regs); /* * When LPAR is terminated by PYHP, ensure all possible CPUs' * register data is processed while exporting the vmcore. */ fdh->cpu_mask = *cpu_possible_mask; + fdh->cpu_mask_sz = sizeof(struct cpumask); return addr; } @@ -1190,8 +1140,6 @@ static unsigned long init_fadump_header(unsigned long addr) static int register_fadump(void) { unsigned long addr; - void *vaddr; - int ret; /* * If no memory is reserved then we can not register for firmware- @@ -1200,18 +1148,10 @@ static int register_fadump(void) if (!fw_dump.reserve_dump_area_size) return -ENODEV; - ret = fadump_setup_crash_memory_ranges(); - if (ret) - return ret; - addr = fw_dump.fadumphdr_addr; /* Initialize fadump crash info header. */ addr = init_fadump_header(addr); - vaddr = __va(addr); - - pr_debug("Creating ELF core headers at %#016lx\n", addr); - fadump_create_elfcore_headers(vaddr); /* register the future kernel dump with firmware. */ pr_debug("Registering for firmware-assisted kernel dump...\n"); @@ -1230,7 +1170,6 @@ void fadump_cleanup(void) } else if (fw_dump.dump_registered) { /* Un-register Firmware-assisted dump if it was registered. */ fw_dump.ops->fadump_unregister(&fw_dump); - fadump_free_mem_ranges(&crash_mrange_info); } if (fw_dump.ops->fadump_cleanup) @@ -1416,6 +1355,22 @@ static void fadump_release_memory(u64 begin, u64 end) fadump_release_reserved_area(tstart, end); } +static void fadump_free_elfcorehdr_buf(void) +{ + if (fw_dump.elfcorehdr_addr == 0 || fw_dump.elfcorehdr_size == 0) + return; + + /* + * Before freeing the memory of `elfcorehdr`, reset the global + * `elfcorehdr_addr` to prevent modules like `vmcore` from accessing + * invalid memory. + */ + elfcorehdr_addr = ELFCORE_ADDR_ERR; + fadump_free_buffer(fw_dump.elfcorehdr_addr, fw_dump.elfcorehdr_size); + fw_dump.elfcorehdr_addr = 0; + fw_dump.elfcorehdr_size = 0; +} + static void fadump_invalidate_release_mem(void) { mutex_lock(&fadump_mutex); @@ -1427,6 +1382,7 @@ static void fadump_invalidate_release_mem(void) fadump_cleanup(); mutex_unlock(&fadump_mutex); + fadump_free_elfcorehdr_buf(); fadump_release_memory(fw_dump.boot_mem_top, memblock_end_of_DRAM()); fadump_free_cpu_notes_buf(); @@ -1484,6 +1440,18 @@ static ssize_t enabled_show(struct kobject *kobj, return sprintf(buf, "%d\n", fw_dump.fadump_enabled); } +/* + * /sys/kernel/fadump/hotplug_ready sysfs node returns 1, which inidcates + * to usersapce that fadump re-registration is not required on memory + * hotplug events. + */ +static ssize_t hotplug_ready_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", 1); +} + static ssize_t mem_reserved_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -1498,6 +1466,43 @@ static ssize_t registered_show(struct kobject *kobj, return sprintf(buf, "%d\n", fw_dump.dump_registered); } +static ssize_t bootargs_append_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + return sprintf(buf, "%s\n", (char *)__va(fw_dump.param_area)); +} + +static ssize_t bootargs_append_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + char *params; + + if (!fw_dump.fadump_enabled || fw_dump.dump_active) + return -EPERM; + + if (count >= COMMAND_LINE_SIZE) + return -EINVAL; + + /* + * Fail here instead of handling this scenario with + * some silly workaround in capture kernel. + */ + if (saved_command_line_len + count >= COMMAND_LINE_SIZE) { + pr_err("Appending parameters exceeds cmdline size!\n"); + return -ENOSPC; + } + + params = __va(fw_dump.param_area); + strscpy_pad(params, buf, COMMAND_LINE_SIZE); + /* Remove newline character at the end. */ + if (params[count-1] == '\n') + params[count-1] = '\0'; + + return count; +} + static ssize_t registered_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) @@ -1556,11 +1561,14 @@ static struct kobj_attribute release_attr = __ATTR_WO(release_mem); static struct kobj_attribute enable_attr = __ATTR_RO(enabled); static struct kobj_attribute register_attr = __ATTR_RW(registered); static struct kobj_attribute mem_reserved_attr = __ATTR_RO(mem_reserved); +static struct kobj_attribute hotplug_ready_attr = __ATTR_RO(hotplug_ready); +static struct kobj_attribute bootargs_append_attr = __ATTR_RW(bootargs_append); static struct attribute *fadump_attrs[] = { &enable_attr.attr, ®ister_attr.attr, &mem_reserved_attr.attr, + &hotplug_ready_attr.attr, NULL, }; @@ -1632,6 +1640,150 @@ static void __init fadump_init_files(void) return; } +static int __init fadump_setup_elfcorehdr_buf(void) +{ + int elf_phdr_cnt; + unsigned long elfcorehdr_size; + + /* + * Program header for CPU notes comes first, followed by one for + * vmcoreinfo, and the remaining program headers correspond to + * memory regions. + */ + elf_phdr_cnt = 2 + fw_dump.boot_mem_regs_cnt + memblock_num_regions(memory); + elfcorehdr_size = sizeof(struct elfhdr) + (elf_phdr_cnt * sizeof(struct elf_phdr)); + elfcorehdr_size = PAGE_ALIGN(elfcorehdr_size); + + fw_dump.elfcorehdr_addr = (u64)fadump_alloc_buffer(elfcorehdr_size); + if (!fw_dump.elfcorehdr_addr) { + pr_err("Failed to allocate %lu bytes for elfcorehdr\n", + elfcorehdr_size); + return -ENOMEM; + } + fw_dump.elfcorehdr_size = elfcorehdr_size; + return 0; +} + +/* + * Check if the fadump header of crashed kernel is compatible with fadump kernel. + * + * It checks the magic number, endianness, and size of non-primitive type + * members of fadump header to ensure safe dump collection. + */ +static bool __init is_fadump_header_compatible(struct fadump_crash_info_header *fdh) +{ + if (fdh->magic_number == FADUMP_CRASH_INFO_MAGIC_OLD) { + pr_err("Old magic number, can't process the dump.\n"); + return false; + } + + if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { + if (fdh->magic_number == swab64(FADUMP_CRASH_INFO_MAGIC)) + pr_err("Endianness mismatch between the crashed and fadump kernels.\n"); + else + pr_err("Fadump header is corrupted.\n"); + + return false; + } + + /* + * Dump collection is not safe if the size of non-primitive type members + * of the fadump header do not match between crashed and fadump kernel. + */ + if (fdh->pt_regs_sz != sizeof(struct pt_regs) || + fdh->cpu_mask_sz != sizeof(struct cpumask)) { + pr_err("Fadump header size mismatch.\n"); + return false; + } + + return true; +} + +static void __init fadump_process(void) +{ + struct fadump_crash_info_header *fdh; + + fdh = (struct fadump_crash_info_header *) __va(fw_dump.fadumphdr_addr); + if (!fdh) { + pr_err("Crash info header is empty.\n"); + goto err_out; + } + + /* Avoid processing the dump if fadump header isn't compatible */ + if (!is_fadump_header_compatible(fdh)) + goto err_out; + + /* Allocate buffer for elfcorehdr */ + if (fadump_setup_elfcorehdr_buf()) + goto err_out; + + fadump_populate_elfcorehdr(fdh); + + /* Let platform update the CPU notes in elfcorehdr */ + if (fw_dump.ops->fadump_process(&fw_dump) < 0) + goto err_out; + + /* + * elfcorehdr is now ready to be exported. + * + * set elfcorehdr_addr so that vmcore module will export the + * elfcorehdr through '/proc/vmcore'. + */ + elfcorehdr_addr = virt_to_phys((void *)fw_dump.elfcorehdr_addr); + return; + +err_out: + fadump_invalidate_release_mem(); +} + +/* + * Reserve memory to store additional parameters to be passed + * for fadump/capture kernel. + */ +static void __init fadump_setup_param_area(void) +{ + phys_addr_t range_start, range_end; + + if (!fw_dump.param_area_supported || fw_dump.dump_active) + return; + + /* This memory can't be used by PFW or bootloader as it is shared across kernels */ + if (radix_enabled()) { + /* + * Anywhere in the upper half should be good enough as all memory + * is accessible in real mode. + */ + range_start = memblock_end_of_DRAM() / 2; + range_end = memblock_end_of_DRAM(); + } else { + /* + * Passing additional parameters is supported for hash MMU only + * if the first memory block size is 768MB or higher. + */ + if (ppc64_rma_size < 0x30000000) + return; + + /* + * 640 MB to 768 MB is not used by PFW/bootloader. So, try reserving + * memory for passing additional parameters in this range to avoid + * being stomped on by PFW/bootloader. + */ + range_start = 0x2A000000; + range_end = range_start + 0x4000000; + } + + fw_dump.param_area = memblock_phys_alloc_range(COMMAND_LINE_SIZE, + COMMAND_LINE_SIZE, + range_start, + range_end); + if (!fw_dump.param_area || sysfs_create_file(fadump_kobj, &bootargs_append_attr.attr)) { + pr_warn("WARNING: Could not setup area to pass additional parameters!\n"); + return; + } + + memset(phys_to_virt(fw_dump.param_area), 0, COMMAND_LINE_SIZE); +} + /* * Prepare for firmware-assisted dump. */ @@ -1651,15 +1803,11 @@ int __init setup_fadump(void) * saving it to the disk. */ if (fw_dump.dump_active) { - /* - * if dump process fails then invalidate the registration - * and release memory before proceeding for re-registration. - */ - if (fw_dump.ops->fadump_process(&fw_dump) < 0) - fadump_invalidate_release_mem(); + fadump_process(); } /* Initialize the kernel dump memory structure and register with f/w */ else if (fw_dump.reserve_dump_area_size) { + fadump_setup_param_area(); fw_dump.ops->fadump_init_mem_struct(&fw_dump); register_fadump(); } diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 1a8cdafd68e8..91123e102db4 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -192,7 +192,7 @@ _GLOBAL(scom970_read) xori r0,r0,MSR_EE mtmsrd r0,1 - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits * (including parity). On current CPUs they must be 0'd, * and finally or in RW bit */ @@ -226,7 +226,7 @@ _GLOBAL(scom970_write) xori r0,r0,MSR_EE mtmsrd r0,1 - /* rotate 24 bits SCOM address 8 bits left and mask out it's low 8 bits + /* rotate 24 bits SCOM address 8 bits left and mask out its low 8 bits * (including parity). On current CPUs they must be 0'd. */ diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index 77ea82e9dc5f..baeb24c102c8 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -16,8 +16,6 @@ #include <asm/setup.h> #include <asm/sections.h> -static LIST_HEAD(module_bug_list); - static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, const char *name) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 9452a54d356c..a7671786764b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1185,6 +1185,9 @@ static inline void save_sprs(struct thread_struct *t) if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) t->hashkeyr = mfspr(SPRN_HASHKEYR); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + t->dexcr = mfspr(SPRN_DEXCR); #endif } @@ -1267,6 +1270,10 @@ static inline void restore_sprs(struct thread_struct *old_thread, if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && old_thread->hashkeyr != new_thread->hashkeyr) mtspr(SPRN_HASHKEYR, new_thread->hashkeyr); + + if (cpu_has_feature(CPU_FTR_ARCH_31) && + old_thread->dexcr != new_thread->dexcr) + mtspr(SPRN_DEXCR, new_thread->dexcr); #endif } @@ -1634,6 +1641,13 @@ void arch_setup_new_exec(void) current->thread.regs->amr = default_amr; current->thread.regs->iamr = default_iamr; #endif + +#ifdef CONFIG_PPC_BOOK3S_64 + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + current->thread.dexcr = current->thread.dexcr_onexec; + mtspr(SPRN_DEXCR, current->thread.dexcr); + } +#endif /* CONFIG_PPC_BOOK3S_64 */ } #ifdef CONFIG_PPC64 @@ -1647,7 +1661,7 @@ void arch_setup_new_exec(void) * cases will happen: * * 1. The correct thread is running, the wrong thread is not - * In this situation, the correct thread is woken and proceeds to pass it's + * In this situation, the correct thread is woken and proceeds to pass its * condition check. * * 2. Neither threads are running @@ -1657,15 +1671,15 @@ void arch_setup_new_exec(void) * for the wrong thread, or they will execute the condition check immediately. * * 3. The wrong thread is running, the correct thread is not - * The wrong thread will be woken, but will fail it's condition check and + * The wrong thread will be woken, but will fail its condition check and * re-execute wait. The correct thread, when scheduled, will execute either - * it's condition check (which will pass), or wait, which returns immediately - * when called the first time after the thread is scheduled, followed by it's + * its condition check (which will pass), or wait, which returns immediately + * when called the first time after the thread is scheduled, followed by its * condition check (which will pass). * * 4. Both threads are running - * Both threads will be woken. The wrong thread will fail it's condition check - * and execute another wait, while the correct thread will pass it's condition + * Both threads will be woken. The wrong thread will fail its condition check + * and execute another wait, while the correct thread will pass its condition * check. * * @t: the task to set the thread ID for @@ -1878,6 +1892,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) #ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) p->thread.hashkeyr = current->thread.hashkeyr; + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + p->thread.dexcr = mfspr(SPRN_DEXCR); #endif return 0; } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index cd8d8883de90..60819751e55e 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -779,7 +779,7 @@ static inline void save_fscr_to_task(void) {} void __init early_init_devtree(void *params) { - phys_addr_t limit; + phys_addr_t int_vector_size; DBG(" -> early_init_devtree(%px)\n", params); @@ -813,6 +813,9 @@ void __init early_init_devtree(void *params) */ of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line); + /* Append additional parameters passed for fadump capture kernel */ + fadump_append_bootargs(); + /* Scan memory nodes and rebuild MEMBLOCKs */ early_init_dt_scan_root(); early_init_dt_scan_memory_ppc(); @@ -832,9 +835,16 @@ void __init early_init_devtree(void *params) setup_initial_memory_limit(memstart_addr, first_memblock_size); /* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */ memblock_reserve(PHYSICAL_START, __pa(_end) - PHYSICAL_START); +#ifdef CONFIG_PPC64 + /* If relocatable, reserve at least 32k for interrupt vectors etc. */ + int_vector_size = __end_interrupts - _stext; + int_vector_size = max_t(phys_addr_t, SZ_32K, int_vector_size); +#else /* If relocatable, reserve first 32k for interrupt vectors etc. */ + int_vector_size = SZ_32K; +#endif if (PHYSICAL_START > MEMORY_START) - memblock_reserve(MEMORY_START, 0x8000); + memblock_reserve(MEMORY_START, int_vector_size); reserve_kdump_trampoline(); #if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) /* @@ -846,9 +856,12 @@ void __init early_init_devtree(void *params) reserve_crashkernel(); early_reserve_mem(); - /* Ensure that total memory size is page-aligned. */ - limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); - memblock_enforce_memory_limit(limit); + if (memory_limit > memblock_phys_mem_size()) + memory_limit = 0; + + /* Align down to 16 MB which is large page size with hash page translation */ + memory_limit = ALIGN_DOWN(memory_limit ?: memblock_phys_mem_size(), SZ_16M); + memblock_enforce_memory_limit(memory_limit); #if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES) if (!early_radix_enabled()) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 0ef358285337..fbb68fc28ed3 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -817,8 +817,8 @@ static void __init early_cmdline_parse(void) opt += 4; prom_memory_limit = prom_memparse(opt, (const char **)&opt); #ifdef CONFIG_PPC64 - /* Align to 16 MB == size of ppc64 large page */ - prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000); + /* Align down to 16 MB which is large page size with hash page translation */ + prom_memory_limit = ALIGN_DOWN(prom_memory_limit, SZ_16M); #endif } diff --git a/arch/powerpc/kernel/ptrace/ptrace-tm.c b/arch/powerpc/kernel/ptrace/ptrace-tm.c index 210ea834e603..447bff87fd21 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-tm.c +++ b/arch/powerpc/kernel/ptrace/ptrace-tm.c @@ -12,7 +12,7 @@ void flush_tmregs_to_thread(struct task_struct *tsk) { /* * If task is not current, it will have been flushed already to - * it's thread_struct during __switch_to(). + * its thread_struct during __switch_to(). * * A reclaim flushes ALL the state or if not in TM save TM SPRs * in the appropriate thread structures from live. diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 584cf5c3df50..c1819e0a6684 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -469,12 +469,7 @@ static int dexcr_get(struct task_struct *target, const struct user_regset *regse if (!cpu_has_feature(CPU_FTR_ARCH_31)) return -ENODEV; - /* - * The DEXCR is currently static across all CPUs, so we don't - * store the target's value anywhere, but the static value - * will also be correct. - */ - membuf_store(&to, (u64)lower_32_bits(DEXCR_INIT)); + membuf_store(&to, (u64)lower_32_bits(target->thread.dexcr)); /* * Technically the HDEXCR is per-cpu, but a hypervisor can't reasonably diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 01ed1263e1a9..4bd2f87616ba 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -405,7 +405,7 @@ static void __init cpu_init_thread_core_maps(int tpc) cpumask_set_cpu(i, &threads_core_mask); printk(KERN_INFO "CPU maps initialized for %d thread%s per core\n", - tpc, tpc > 1 ? "s" : ""); + tpc, str_plural(tpc)); printk(KERN_DEBUG " (thread shift is %d)\n", threads_shift); } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 2f19d5e94485..ae36a129789f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -834,6 +834,7 @@ static __init int pcpu_cpu_to_node(int cpu) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +DEFINE_STATIC_KEY_FALSE(__percpu_first_chunk_is_paged); void __init setup_per_cpu_areas(void) { @@ -876,6 +877,7 @@ void __init setup_per_cpu_areas(void) if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); + static_key_enable(&__percpu_first_chunk_is_paged.key); delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start; for_each_possible_cpu(cpu) { __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu]; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 12e53b3d7923..46e6d2cd7a2d 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1567,7 +1567,7 @@ static void add_cpu_to_masks(int cpu) /* * This CPU will not be in the online mask yet so we need to manually - * add it to it's own thread sibling mask. + * add it to its own thread sibling mask. */ map_cpu_to_node(cpu, cpu_to_node(cpu)); cpumask_set_cpu(cpu, cpu_sibling_mask(cpu)); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 0f39a6b84132..b842c83ab497 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -139,7 +139,7 @@ static unsigned long dscr_default; * @val: Returned cpu specific DSCR default value * * This function returns the per cpu DSCR default value - * for any cpu which is contained in it's PACA structure. + * for any cpu which is contained in its PACA structure. */ static void read_dscr(void *val) { @@ -152,7 +152,7 @@ static void read_dscr(void *val) * @val: New cpu specific DSCR default value to update * * This function updates the per cpu DSCR default value - * for any cpu which is contained in it's PACA structure. + * for any cpu which is contained in its PACA structure. */ static void write_dscr(void *val) { diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile index 8e469c4da3f8..470eb0453e17 100644 --- a/arch/powerpc/kexec/Makefile +++ b/arch/powerpc/kexec/Makefile @@ -3,11 +3,11 @@ # Makefile for the linux kernel. # -obj-y += core.o core_$(BITS).o +obj-y += core.o core_$(BITS).o ranges.o obj-$(CONFIG_PPC32) += relocate_32.o -obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o +obj-$(CONFIG_KEXEC_FILE) += file_load.o file_load_$(BITS).o elf_$(BITS).o obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o obj-$(CONFIG_CRASH_DUMP) += crash.o diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 762e4d09aacf..85050be08a23 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -17,6 +17,7 @@ #include <linux/cpu.h> #include <linux/hardirq.h> #include <linux/of.h> +#include <linux/libfdt.h> #include <asm/page.h> #include <asm/current.h> @@ -30,6 +31,7 @@ #include <asm/hw_breakpoint.h> #include <asm/svm.h> #include <asm/ultravisor.h> +#include <asm/crashdump-ppc64.h> int machine_kexec_prepare(struct kimage *image) { @@ -419,3 +421,92 @@ static int __init export_htab_values(void) } late_initcall(export_htab_values); #endif /* CONFIG_PPC_64S_HASH_MMU */ + +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +/** + * add_node_props - Reads node properties from device node structure and add + * them to fdt. + * @fdt: Flattened device tree of the kernel + * @node_offset: offset of the node to add a property at + * @dn: device node pointer + * + * Returns 0 on success, negative errno on error. + */ +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) +{ + int ret = 0; + struct property *pp; + + if (!dn) + return -EINVAL; + + for_each_property_of_node(dn, pp) { + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); + if (ret < 0) { + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); + return ret; + } + } + return ret; +} + +/** + * update_cpus_node - Update cpus node of flattened device tree using of_root + * device node. + * @fdt: Flattened device tree of the kernel. + * + * Returns 0 on success, negative errno on error. + */ +int update_cpus_node(void *fdt) +{ + struct device_node *cpus_node, *dn; + int cpus_offset, cpus_subnode_offset, ret = 0; + + cpus_offset = fdt_path_offset(fdt, "/cpus"); + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { + pr_err("Malformed device tree: error reading /cpus node: %s\n", + fdt_strerror(cpus_offset)); + return cpus_offset; + } + + if (cpus_offset > 0) { + ret = fdt_del_node(fdt, cpus_offset); + if (ret < 0) { + pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); + return -EINVAL; + } + } + + /* Add cpus node to fdt */ + cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); + if (cpus_offset < 0) { + pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); + return -EINVAL; + } + + /* Add cpus node properties */ + cpus_node = of_find_node_by_path("/cpus"); + ret = add_node_props(fdt, cpus_offset, cpus_node); + of_node_put(cpus_node); + if (ret < 0) + return ret; + + /* Loop through all subnodes of cpus and add them to fdt */ + for_each_node_by_type(dn, "cpu") { + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); + if (cpus_subnode_offset < 0) { + pr_err("Unable to add %s subnode: %s\n", dn->full_name, + fdt_strerror(cpus_subnode_offset)); + ret = cpus_subnode_offset; + goto out; + } + + ret = add_node_props(fdt, cpus_subnode_offset, dn); + if (ret < 0) + goto out; + } +out: + of_node_put(dn); + return ret; +} +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ diff --git a/arch/powerpc/kexec/crash.c b/arch/powerpc/kexec/crash.c index ef5c2d25ec39..9ac3266e4965 100644 --- a/arch/powerpc/kexec/crash.c +++ b/arch/powerpc/kexec/crash.c @@ -16,6 +16,8 @@ #include <linux/delay.h> #include <linux/irq.h> #include <linux/types.h> +#include <linux/libfdt.h> +#include <linux/memory.h> #include <asm/processor.h> #include <asm/machdep.h> @@ -24,6 +26,7 @@ #include <asm/setjmp.h> #include <asm/debug.h> #include <asm/interrupt.h> +#include <asm/kexec_ranges.h> /* * The primary CPU waits a while for all secondary CPUs to enter. This is to @@ -392,3 +395,195 @@ void default_machine_crash_shutdown(struct pt_regs *regs) if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(1, 0); } + +#ifdef CONFIG_CRASH_HOTPLUG +#undef pr_fmt +#define pr_fmt(fmt) "crash hp: " fmt + +/* + * Advertise preferred elfcorehdr size to userspace via + * /sys/kernel/crash_elfcorehdr_size sysfs interface. + */ +unsigned int arch_crash_get_elfcorehdr_size(void) +{ + unsigned long phdr_cnt; + + /* A program header for possible CPUs + vmcoreinfo */ + phdr_cnt = num_possible_cpus() + 1; + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) + phdr_cnt += CONFIG_CRASH_MAX_MEMORY_RANGES; + + return sizeof(struct elfhdr) + (phdr_cnt * sizeof(Elf64_Phdr)); +} + +/** + * update_crash_elfcorehdr() - Recreate the elfcorehdr and replace it with old + * elfcorehdr in the kexec segment array. + * @image: the active struct kimage + * @mn: struct memory_notify data handler + */ +static void update_crash_elfcorehdr(struct kimage *image, struct memory_notify *mn) +{ + int ret; + struct crash_mem *cmem = NULL; + struct kexec_segment *ksegment; + void *ptr, *mem, *elfbuf = NULL; + unsigned long elfsz, memsz, base_addr, size; + + ksegment = &image->segment[image->elfcorehdr_index]; + mem = (void *) ksegment->mem; + memsz = ksegment->memsz; + + ret = get_crash_memory_ranges(&cmem); + if (ret) { + pr_err("Failed to get crash mem range\n"); + return; + } + + /* + * The hot unplugged memory is part of crash memory ranges, + * remove it here. + */ + if (image->hp_action == KEXEC_CRASH_HP_REMOVE_MEMORY) { + base_addr = PFN_PHYS(mn->start_pfn); + size = mn->nr_pages * PAGE_SIZE; + ret = remove_mem_range(&cmem, base_addr, size); + if (ret) { + pr_err("Failed to remove hot-unplugged memory from crash memory ranges\n"); + goto out; + } + } + + ret = crash_prepare_elf64_headers(cmem, false, &elfbuf, &elfsz); + if (ret) { + pr_err("Failed to prepare elf header\n"); + goto out; + } + + /* + * It is unlikely that kernel hit this because elfcorehdr kexec + * segment (memsz) is built with addition space to accommodate growing + * number of crash memory ranges while loading the kdump kernel. It is + * Just to avoid any unforeseen case. + */ + if (elfsz > memsz) { + pr_err("Updated crash elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz); + goto out; + } + + ptr = __va(mem); + if (ptr) { + /* Temporarily invalidate the crash image while it is replaced */ + xchg(&kexec_crash_image, NULL); + + /* Replace the old elfcorehdr with newly prepared elfcorehdr */ + memcpy((void *)ptr, elfbuf, elfsz); + + /* The crash image is now valid once again */ + xchg(&kexec_crash_image, image); + } +out: + kvfree(cmem); + kvfree(elfbuf); +} + +/** + * get_fdt_index - Loop through the kexec segment array and find + * the index of the FDT segment. + * @image: a pointer to kexec_crash_image + * + * Returns the index of FDT segment in the kexec segment array + * if found; otherwise -1. + */ +static int get_fdt_index(struct kimage *image) +{ + void *ptr; + unsigned long mem; + int i, fdt_index = -1; + + /* Find the FDT segment index in kexec segment array. */ + for (i = 0; i < image->nr_segments; i++) { + mem = image->segment[i].mem; + ptr = __va(mem); + + if (ptr && fdt_magic(ptr) == FDT_MAGIC) { + fdt_index = i; + break; + } + } + + return fdt_index; +} + +/** + * update_crash_fdt - updates the cpus node of the crash FDT. + * + * @image: a pointer to kexec_crash_image + */ +static void update_crash_fdt(struct kimage *image) +{ + void *fdt; + int fdt_index; + + fdt_index = get_fdt_index(image); + if (fdt_index < 0) { + pr_err("Unable to locate FDT segment.\n"); + return; + } + + fdt = __va((void *)image->segment[fdt_index].mem); + + /* Temporarily invalidate the crash image while it is replaced */ + xchg(&kexec_crash_image, NULL); + + /* update FDT to reflect changes in CPU resources */ + if (update_cpus_node(fdt)) + pr_err("Failed to update crash FDT"); + + /* The crash image is now valid once again */ + xchg(&kexec_crash_image, image); +} + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) +{ +#ifdef CONFIG_KEXEC_FILE + if (image->file_mode) + return 1; +#endif + return kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT; +} + +/** + * arch_crash_handle_hotplug_event - Handle crash CPU/Memory hotplug events to update the + * necessary kexec segments based on the hotplug event. + * @image: a pointer to kexec_crash_image + * @arg: struct memory_notify handler for memory hotplug case and NULL for CPU hotplug case. + * + * Update the kdump image based on the type of hotplug event, represented by image->hp_action. + * CPU add: Update the FDT segment to include the newly added CPU. + * CPU remove: No action is needed, with the assumption that it's okay to have offline CPUs + * part of the FDT. + * Memory add/remove: No action is taken as this is not yet supported. + */ +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) +{ + struct memory_notify *mn; + + switch (image->hp_action) { + case KEXEC_CRASH_HP_REMOVE_CPU: + return; + + case KEXEC_CRASH_HP_ADD_CPU: + update_crash_fdt(image); + break; + + case KEXEC_CRASH_HP_REMOVE_MEMORY: + case KEXEC_CRASH_HP_ADD_MEMORY: + mn = (struct memory_notify *)arg; + update_crash_elfcorehdr(image, mn); + return; + default: + pr_warn_once("Unknown hotplug action\n"); + } +} +#endif /* CONFIG_CRASH_HOTPLUG */ diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c index 6d8951e8e966..214c071c58ed 100644 --- a/arch/powerpc/kexec/elf_64.c +++ b/arch/powerpc/kexec/elf_64.c @@ -116,7 +116,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, if (ret) goto out_free_fdt; - fdt_pack(fdt); + if (!IS_ENABLED(CONFIG_CRASH_HOTPLUG) || image->type != KEXEC_TYPE_CRASH) + fdt_pack(fdt); kbuf.buffer = fdt; kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 1bc65de6174f..925a69ad2468 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -30,6 +30,7 @@ #include <asm/iommu.h> #include <asm/prom.h> #include <asm/plpks.h> +#include <asm/cputhreads.h> struct umem_info { __be64 *buf; /* data buffer for usable-memory property */ @@ -48,83 +49,6 @@ const struct kexec_file_ops * const kexec_file_loaders[] = { }; /** - * get_exclude_memory_ranges - Get exclude memory ranges. This list includes - * regions like opal/rtas, tce-table, initrd, - * kernel, htab which should be avoided while - * setting up kexec load segments. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_exclude_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - ret = add_tce_mem_ranges(mem_ranges); - if (ret) - goto out; - - ret = add_initrd_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_htab_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_kernel_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_reserved_mem_ranges(mem_ranges); - if (ret) - goto out; - - /* exclude memory ranges should be sorted for easy lookup */ - sort_memory_ranges(*mem_ranges, true); -out: - if (ret) - pr_err("Failed to setup exclude memory ranges\n"); - return ret; -} - -/** - * get_reserved_memory_ranges - Get reserve memory ranges. This list includes - * memory regions that should be added to the - * memory reserve map to ensure the region is - * protected from any mischief. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_reserved_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_tce_mem_ranges(mem_ranges); - if (ret) - goto out; - - ret = add_reserved_mem_ranges(mem_ranges); -out: - if (ret) - pr_err("Failed to setup reserved memory ranges\n"); - return ret; -} - -/** * __locate_mem_hole_top_down - Looks top down for a large enough memory hole * in the memory regions between buf_min & buf_max * for the buffer. If found, sets kbuf->mem. @@ -323,119 +247,6 @@ static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf, #ifdef CONFIG_CRASH_DUMP /** - * get_usable_memory_ranges - Get usable memory ranges. This list includes - * regions like crashkernel, opal/rtas & tce-table, - * that kdump kernel could use. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_usable_memory_ranges(struct crash_mem **mem_ranges) -{ - int ret; - - /* - * Early boot failure observed on guests when low memory (first memory - * block?) is not added to usable memory. So, add [0, crashk_res.end] - * instead of [crashk_res.start, crashk_res.end] to workaround it. - * Also, crashed kernel's memory must be added to reserve map to - * avoid kdump kernel from using it. - */ - ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); - if (ret) - goto out; - - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_tce_mem_ranges(mem_ranges); -out: - if (ret) - pr_err("Failed to setup usable memory ranges\n"); - return ret; -} - -/** - * get_crash_memory_ranges - Get crash memory ranges. This list includes - * first/crashing kernel's memory regions that - * would be exported via an elfcore. - * @mem_ranges: Range list to add the memory ranges to. - * - * Returns 0 on success, negative errno on error. - */ -static int get_crash_memory_ranges(struct crash_mem **mem_ranges) -{ - phys_addr_t base, end; - struct crash_mem *tmem; - u64 i; - int ret; - - for_each_mem_range(i, &base, &end) { - u64 size = end - base; - - /* Skip backup memory region, which needs a separate entry */ - if (base == BACKUP_SRC_START) { - if (size > BACKUP_SRC_SIZE) { - base = BACKUP_SRC_END + 1; - size -= BACKUP_SRC_SIZE; - } else - continue; - } - - ret = add_mem_range(mem_ranges, base, size); - if (ret) - goto out; - - /* Try merging adjacent ranges before reallocation attempt */ - if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) - sort_memory_ranges(*mem_ranges, true); - } - - /* Reallocate memory ranges if there is no space to split ranges */ - tmem = *mem_ranges; - if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { - tmem = realloc_mem_ranges(mem_ranges); - if (!tmem) - goto out; - } - - /* Exclude crashkernel region */ - ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end); - if (ret) - goto out; - - /* - * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL - * regions are exported to save their context at the time of - * crash, they should actually be backed up just like the - * first 64K bytes of memory. - */ - ret = add_rtas_mem_range(mem_ranges); - if (ret) - goto out; - - ret = add_opal_mem_range(mem_ranges); - if (ret) - goto out; - - /* create a separate program header for the backup region */ - ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); - if (ret) - goto out; - - sort_memory_ranges(*mem_ranges, false); -out: - if (ret) - pr_err("Failed to setup crash memory ranges\n"); - return ret; -} - -/** * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries * @um_info: Usable memory buffer and ranges info. * @cnt: No. of entries to accommodate. @@ -784,6 +595,23 @@ static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) } } +static unsigned int kdump_extra_elfcorehdr_size(struct crash_mem *cmem) +{ +#if defined(CONFIG_CRASH_HOTPLUG) && defined(CONFIG_MEMORY_HOTPLUG) + unsigned int extra_sz = 0; + + if (CONFIG_CRASH_MAX_MEMORY_RANGES > (unsigned int)PN_XNUM) + pr_warn("Number of Phdrs %u exceeds max\n", CONFIG_CRASH_MAX_MEMORY_RANGES); + else if (cmem->nr_ranges >= CONFIG_CRASH_MAX_MEMORY_RANGES) + pr_warn("Configured crash mem ranges may not be enough\n"); + else + extra_sz = (CONFIG_CRASH_MAX_MEMORY_RANGES - cmem->nr_ranges) * sizeof(Elf64_Phdr); + + return extra_sz; +#endif + return 0; +} + /** * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr * segment needed to load kdump kernel. @@ -815,7 +643,8 @@ static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) kbuf->buffer = headers; kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; - kbuf->bufsz = kbuf->memsz = headers_sz; + kbuf->bufsz = headers_sz; + kbuf->memsz = headers_sz + kdump_extra_elfcorehdr_size(cmem); kbuf->top_down = false; ret = kexec_add_buffer(kbuf); @@ -979,6 +808,9 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image) unsigned int cpu_nodes, extra_size = 0; struct device_node *dn; u64 usm_entries; +#ifdef CONFIG_CRASH_HOTPLUG + unsigned int possible_cpu_nodes; +#endif if (!IS_ENABLED(CONFIG_CRASH_DUMP) || image->type != KEXEC_TYPE_CRASH) return 0; @@ -1006,6 +838,19 @@ static unsigned int kdump_extra_fdt_size_ppc64(struct kimage *image) if (cpu_nodes > boot_cpu_node_count) extra_size += (cpu_nodes - boot_cpu_node_count) * cpu_node_size(); +#ifdef CONFIG_CRASH_HOTPLUG + /* + * Make sure enough space is reserved to accommodate possible CPU nodes + * in the crash FDT. This allows packing possible CPU nodes which are + * not yet present in the system without regenerating the entire FDT. + */ + if (image->type == KEXEC_TYPE_CRASH) { + possible_cpu_nodes = num_possible_cpus() / threads_per_core; + if (possible_cpu_nodes > cpu_nodes) + extra_size += (possible_cpu_nodes - cpu_nodes) * cpu_node_size(); + } +#endif + return extra_size; } @@ -1028,93 +873,6 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) return extra_size + kdump_extra_fdt_size_ppc64(image); } -/** - * add_node_props - Reads node properties from device node structure and add - * them to fdt. - * @fdt: Flattened device tree of the kernel - * @node_offset: offset of the node to add a property at - * @dn: device node pointer - * - * Returns 0 on success, negative errno on error. - */ -static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) -{ - int ret = 0; - struct property *pp; - - if (!dn) - return -EINVAL; - - for_each_property_of_node(dn, pp) { - ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); - if (ret < 0) { - pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); - return ret; - } - } - return ret; -} - -/** - * update_cpus_node - Update cpus node of flattened device tree using of_root - * device node. - * @fdt: Flattened device tree of the kernel. - * - * Returns 0 on success, negative errno on error. - */ -static int update_cpus_node(void *fdt) -{ - struct device_node *cpus_node, *dn; - int cpus_offset, cpus_subnode_offset, ret = 0; - - cpus_offset = fdt_path_offset(fdt, "/cpus"); - if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { - pr_err("Malformed device tree: error reading /cpus node: %s\n", - fdt_strerror(cpus_offset)); - return cpus_offset; - } - - if (cpus_offset > 0) { - ret = fdt_del_node(fdt, cpus_offset); - if (ret < 0) { - pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); - return -EINVAL; - } - } - - /* Add cpus node to fdt */ - cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); - if (cpus_offset < 0) { - pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); - return -EINVAL; - } - - /* Add cpus node properties */ - cpus_node = of_find_node_by_path("/cpus"); - ret = add_node_props(fdt, cpus_offset, cpus_node); - of_node_put(cpus_node); - if (ret < 0) - return ret; - - /* Loop through all subnodes of cpus and add them to fdt */ - for_each_node_by_type(dn, "cpu") { - cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); - if (cpus_subnode_offset < 0) { - pr_err("Unable to add %s subnode: %s\n", dn->full_name, - fdt_strerror(cpus_subnode_offset)); - ret = cpus_subnode_offset; - goto out; - } - - ret = add_node_props(fdt, cpus_subnode_offset, dn); - if (ret < 0) - goto out; - } -out: - of_node_put(dn); - return ret; -} - static int copy_property(void *fdt, int node_offset, const struct device_node *dn, const char *propname) { diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c index 33b780049aaf..3702b0bdab14 100644 --- a/arch/powerpc/kexec/ranges.c +++ b/arch/powerpc/kexec/ranges.c @@ -20,9 +20,13 @@ #include <linux/kexec.h> #include <linux/of.h> #include <linux/slab.h> +#include <linux/memblock.h> +#include <linux/crash_core.h> #include <asm/sections.h> #include <asm/kexec_ranges.h> +#include <asm/crashdump-ppc64.h> +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) /** * get_max_nr_ranges - Get the max no. of ranges crash_mem structure * could hold, given the size allocated for it. @@ -234,13 +238,16 @@ int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) return __add_mem_range(mem_ranges, base, size); } +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ + +#ifdef CONFIG_KEXEC_FILE /** * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list. * @mem_ranges: Range list to add the memory range(s) to. * * Returns 0 on success, negative errno on error. */ -int add_tce_mem_ranges(struct crash_mem **mem_ranges) +static int add_tce_mem_ranges(struct crash_mem **mem_ranges) { struct device_node *dn = NULL; int ret = 0; @@ -279,7 +286,7 @@ int add_tce_mem_ranges(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_initrd_mem_range(struct crash_mem **mem_ranges) +static int add_initrd_mem_range(struct crash_mem **mem_ranges) { u64 base, end; int ret; @@ -296,7 +303,6 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges) return ret; } -#ifdef CONFIG_PPC_64S_HASH_MMU /** * add_htab_mem_range - Adds htab range to the given memory ranges list, * if it exists @@ -304,14 +310,18 @@ int add_initrd_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_htab_mem_range(struct crash_mem **mem_ranges) +static int add_htab_mem_range(struct crash_mem **mem_ranges) { + +#ifdef CONFIG_PPC_64S_HASH_MMU if (!htab_address) return 0; return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes); -} +#else + return 0; #endif +} /** * add_kernel_mem_range - Adds kernel text region to the given @@ -320,18 +330,20 @@ int add_htab_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_kernel_mem_range(struct crash_mem **mem_ranges) +static int add_kernel_mem_range(struct crash_mem **mem_ranges) { return add_mem_range(mem_ranges, 0, __pa(_end)); } +#endif /* CONFIG_KEXEC_FILE */ +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) /** * add_rtas_mem_range - Adds RTAS region to the given memory ranges list. * @mem_ranges: Range list to add the memory range to. * * Returns 0 on success, negative errno on error. */ -int add_rtas_mem_range(struct crash_mem **mem_ranges) +static int add_rtas_mem_range(struct crash_mem **mem_ranges) { struct device_node *dn; u32 base, size; @@ -356,7 +368,7 @@ int add_rtas_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_opal_mem_range(struct crash_mem **mem_ranges) +static int add_opal_mem_range(struct crash_mem **mem_ranges) { struct device_node *dn; u64 base, size; @@ -374,7 +386,9 @@ int add_opal_mem_range(struct crash_mem **mem_ranges) of_node_put(dn); return ret; } +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ +#ifdef CONFIG_KEXEC_FILE /** * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w * to the given memory ranges list. @@ -382,7 +396,7 @@ int add_opal_mem_range(struct crash_mem **mem_ranges) * * Returns 0 on success, negative errno on error. */ -int add_reserved_mem_ranges(struct crash_mem **mem_ranges) +static int add_reserved_mem_ranges(struct crash_mem **mem_ranges) { int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0; struct device_node *root = of_find_node_by_path("/"); @@ -412,3 +426,283 @@ int add_reserved_mem_ranges(struct crash_mem **mem_ranges) return ret; } + +/** + * get_reserved_memory_ranges - Get reserve memory ranges. This list includes + * memory regions that should be added to the + * memory reserve map to ensure the region is + * protected from any mischief. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_reserved_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup reserved memory ranges\n"); + return ret; +} + +/** + * get_exclude_memory_ranges - Get exclude memory ranges. This list includes + * regions like opal/rtas, tce-table, initrd, + * kernel, htab which should be avoided while + * setting up kexec load segments. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_exclude_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_initrd_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_htab_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_kernel_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); + if (ret) + goto out; + + /* exclude memory ranges should be sorted for easy lookup */ + sort_memory_ranges(*mem_ranges, true); +out: + if (ret) + pr_err("Failed to setup exclude memory ranges\n"); + return ret; +} + +#ifdef CONFIG_CRASH_DUMP +/** + * get_usable_memory_ranges - Get usable memory ranges. This list includes + * regions like crashkernel, opal/rtas & tce-table, + * that kdump kernel could use. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_usable_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + /* + * Early boot failure observed on guests when low memory (first memory + * block?) is not added to usable memory. So, add [0, crashk_res.end] + * instead of [crashk_res.start, crashk_res.end] to workaround it. + * Also, crashed kernel's memory must be added to reserve map to + * avoid kdump kernel from using it. + */ + ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup usable memory ranges\n"); + return ret; +} +#endif /* CONFIG_CRASH_DUMP */ +#endif /* CONFIG_KEXEC_FILE */ + +#ifdef CONFIG_CRASH_DUMP +/** + * get_crash_memory_ranges - Get crash memory ranges. This list includes + * first/crashing kernel's memory regions that + * would be exported via an elfcore. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int get_crash_memory_ranges(struct crash_mem **mem_ranges) +{ + phys_addr_t base, end; + struct crash_mem *tmem; + u64 i; + int ret; + + for_each_mem_range(i, &base, &end) { + u64 size = end - base; + + /* Skip backup memory region, which needs a separate entry */ + if (base == BACKUP_SRC_START) { + if (size > BACKUP_SRC_SIZE) { + base = BACKUP_SRC_END + 1; + size -= BACKUP_SRC_SIZE; + } else + continue; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + goto out; + + /* Try merging adjacent ranges before reallocation attempt */ + if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) + sort_memory_ranges(*mem_ranges, true); + } + + /* Reallocate memory ranges if there is no space to split ranges */ + tmem = *mem_ranges; + if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { + tmem = realloc_mem_ranges(mem_ranges); + if (!tmem) + goto out; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end); + if (ret) + goto out; + + /* + * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL + * regions are exported to save their context at the time of + * crash, they should actually be backed up just like the + * first 64K bytes of memory. + */ + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + /* create a separate program header for the backup region */ + ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); + if (ret) + goto out; + + sort_memory_ranges(*mem_ranges, false); +out: + if (ret) + pr_err("Failed to setup crash memory ranges\n"); + return ret; +} + +/** + * remove_mem_range - Removes the given memory range from the range list. + * @mem_ranges: Range list to remove the memory range to. + * @base: Base address of the range to remove. + * @size: Size of the memory range to remove. + * + * (Re)allocates memory, if needed. + * + * Returns 0 on success, negative errno on error. + */ +int remove_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) +{ + u64 end; + int ret = 0; + unsigned int i; + u64 mstart, mend; + struct crash_mem *mem_rngs = *mem_ranges; + + if (!size) + return 0; + + /* + * Memory range are stored as start and end address, use + * the same format to do remove operation. + */ + end = base + size - 1; + + for (i = 0; i < mem_rngs->nr_ranges; i++) { + mstart = mem_rngs->ranges[i].start; + mend = mem_rngs->ranges[i].end; + + /* + * Memory range to remove is not part of this range entry + * in the memory range list + */ + if (!(base >= mstart && end <= mend)) + continue; + + /* + * Memory range to remove is equivalent to this entry in the + * memory range list. Remove the range entry from the list. + */ + if (base == mstart && end == mend) { + for (; i < mem_rngs->nr_ranges - 1; i++) { + mem_rngs->ranges[i].start = mem_rngs->ranges[i+1].start; + mem_rngs->ranges[i].end = mem_rngs->ranges[i+1].end; + } + mem_rngs->nr_ranges--; + goto out; + } + /* + * Start address of the memory range to remove and the + * current memory range entry in the list is same. Just + * move the start address of the current memory range + * entry in the list to end + 1. + */ + else if (base == mstart) { + mem_rngs->ranges[i].start = end + 1; + goto out; + } + /* + * End address of the memory range to remove and the + * current memory range entry in the list is same. + * Just move the end address of the current memory + * range entry in the list to base - 1. + */ + else if (end == mend) { + mem_rngs->ranges[i].end = base - 1; + goto out; + } + /* + * Memory range to remove is not at the edge of current + * memory range entry. Split the current memory entry into + * two half. + */ + else { + mem_rngs->ranges[i].end = base - 1; + size = mem_rngs->ranges[i].end - end; + ret = add_mem_range(mem_ranges, end + 1, size); + } + } +out: + return ret; +} +#endif /* CONFIG_CRASH_DUMP */ diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 0d0624088e6b..ff6c38373957 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -360,10 +360,6 @@ static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, break; } -#if 0 - printk(KERN_INFO "Deliver interrupt 0x%x? %x\n", vec, deliver); -#endif - if (deliver) kvmppc_inject_interrupt(vcpu, vec, 0); diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 5bbfb2eed127..de126d153328 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -714,7 +714,7 @@ int kvmppc_core_emulate_mtspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_HID1: to_book3s(vcpu)->hid[1] = spr_val; break; - case SPRN_HID2: + case SPRN_HID2_750FX: to_book3s(vcpu)->hid[2] = spr_val; break; case SPRN_HID2_GEKKO: @@ -900,7 +900,7 @@ int kvmppc_core_emulate_mfspr_pr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val case SPRN_HID1: *spr_val = to_book3s(vcpu)->hid[1]; break; - case SPRN_HID2: + case SPRN_HID2_750FX: case SPRN_HID2_GEKKO: *spr_val = to_book3s(vcpu)->hid[2]; break; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 35cb014a0c51..daaf7faf21a5 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4857,7 +4857,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, * entering a nested guest in which case the decrementer is now owned * by L2 and the L1 decrementer is provided in hdec_expires */ - if (!kvmhv_is_nestedv2() && kvmppc_core_pending_dec(vcpu) && + if (kvmppc_core_pending_dec(vcpu) && ((tb < kvmppc_dec_expires_host_tb(vcpu)) || (trap == BOOK3S_INTERRUPT_SYSCALL && kvmppc_get_gpr(vcpu, 3) == H_ENTER_NESTED))) diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c index 8e6f5355f08b..1091f7a83b25 100644 --- a/arch/powerpc/kvm/book3s_hv_nestedv2.c +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -71,8 +71,8 @@ gs_msg_ops_kvmhv_nestedv2_config_fill_info(struct kvmppc_gs_buff *gsb, } if (kvmppc_gsm_includes(gsm, KVMPPC_GSID_RUN_OUTPUT)) { - kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT, - cfg->vcpu_run_output_cfg); + rc = kvmppc_gse_put_buff_info(gsb, KVMPPC_GSID_RUN_OUTPUT, + cfg->vcpu_run_output_cfg); if (rc < 0) return rc; } diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 29a382249770..1362c672387e 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -531,7 +531,7 @@ static int xive_vm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr) xc->cppr = xive_prio_from_guest(new_cppr); /* - * IPIs are synthetized from MFRR and thus don't need + * IPIs are synthesized from MFRR and thus don't need * any special EOI handling. The underlying interrupt * used to signal MFRR changes is EOId when fetched from * the queue. diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 0ab65eeb93ee..f14ecab674a3 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -3,8 +3,6 @@ # Makefile for ppc-specific library files.. # -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) - CFLAGS_code-patching.o += -fno-stack-protector CFLAGS_feature-fixups.o += -fno-stack-protector diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 7af791446ddf..0d1f3ee91115 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -372,9 +372,32 @@ int patch_instruction(u32 *addr, ppc_inst_t instr) } NOKPROBE_SYMBOL(patch_instruction); +static int patch_memset64(u64 *addr, u64 val, size_t count) +{ + for (u64 *end = addr + count; addr < end; addr++) + __put_kernel_nofault(addr, &val, u64, failed); + + return 0; + +failed: + return -EPERM; +} + +static int patch_memset32(u32 *addr, u32 val, size_t count) +{ + for (u32 *end = addr + count; addr < end; addr++) + __put_kernel_nofault(addr, &val, u32, failed); + + return 0; + +failed: + return -EPERM; +} + static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool repeat_instr) { unsigned long start = (unsigned long)patch_addr; + int err; /* Repeat instruction */ if (repeat_instr) { @@ -383,19 +406,19 @@ static int __patch_instructions(u32 *patch_addr, u32 *code, size_t len, bool rep if (ppc_inst_prefixed(instr)) { u64 val = ppc_inst_as_ulong(instr); - memset64((u64 *)patch_addr, val, len / 8); + err = patch_memset64((u64 *)patch_addr, val, len / 8); } else { u32 val = ppc_inst_val(instr); - memset32(patch_addr, val, len / 4); + err = patch_memset32(patch_addr, val, len / 4); } } else { - memcpy(patch_addr, code, len); + err = copy_to_kernel_nofault(patch_addr, code, len); } smp_wmb(); /* smp write barrier */ flush_icache_range(start, start + len); - return 0; + return err; } /* diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 4f82581ca203..b7201ba50b2e 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -25,6 +25,13 @@ #include <asm/firmware.h> #include <asm/inst.h> +/* + * Used to generate warnings if mmu or cpu feature check functions that + * use static keys before they are initialized. + */ +bool static_key_feature_checks_initialized __read_mostly; +EXPORT_SYMBOL_GPL(static_key_feature_checks_initialized); + struct fixup_entry { unsigned long mask; unsigned long value; @@ -679,6 +686,7 @@ void __init setup_feature_keys(void) jump_label_init(); cpu_feature_keys_init(); mmu_feature_keys_init(); + static_key_feature_checks_initialized = true; } static int __init check_features(void) diff --git a/arch/powerpc/lib/test-code-patching.c b/arch/powerpc/lib/test-code-patching.c index c44823292f73..f76030087f98 100644 --- a/arch/powerpc/lib/test-code-patching.c +++ b/arch/powerpc/lib/test-code-patching.c @@ -347,6 +347,97 @@ static void __init test_prefixed_patching(void) check(!memcmp(iptr, expected, sizeof(expected))); } +static void __init test_multi_instruction_patching(void) +{ + u32 code[32]; + void *buf; + u32 *addr32; + u64 *addr64; + ppc_inst_t inst64 = ppc_inst_prefix(OP_PREFIX << 26 | 3UL << 24, PPC_RAW_TRAP()); + u32 inst32 = PPC_RAW_NOP(); + + buf = vzalloc(PAGE_SIZE * 8); + check(buf); + if (!buf) + return; + + /* Test single page 32-bit repeated instruction */ + addr32 = buf + PAGE_SIZE; + check(!patch_instructions(addr32 + 1, &inst32, 12, true)); + + check(addr32[0] == 0); + check(addr32[1] == inst32); + check(addr32[2] == inst32); + check(addr32[3] == inst32); + check(addr32[4] == 0); + + /* Test single page 64-bit repeated instruction */ + if (IS_ENABLED(CONFIG_PPC64)) { + check(ppc_inst_prefixed(inst64)); + + addr64 = buf + PAGE_SIZE * 2; + ppc_inst_write(code, inst64); + check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true)); + + check(addr64[0] == 0); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64)); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64)); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64)); + check(addr64[4] == 0); + } + + /* Test single page memcpy */ + addr32 = buf + PAGE_SIZE * 3; + + for (int i = 0; i < ARRAY_SIZE(code); i++) + code[i] = i + 1; + + check(!patch_instructions(addr32 + 1, code, sizeof(code), false)); + + check(addr32[0] == 0); + check(!memcmp(&addr32[1], code, sizeof(code))); + check(addr32[ARRAY_SIZE(code) + 1] == 0); + + /* Test multipage 32-bit repeated instruction */ + addr32 = buf + PAGE_SIZE * 4 - 8; + check(!patch_instructions(addr32 + 1, &inst32, 12, true)); + + check(addr32[0] == 0); + check(addr32[1] == inst32); + check(addr32[2] == inst32); + check(addr32[3] == inst32); + check(addr32[4] == 0); + + /* Test multipage 64-bit repeated instruction */ + if (IS_ENABLED(CONFIG_PPC64)) { + check(ppc_inst_prefixed(inst64)); + + addr64 = buf + PAGE_SIZE * 5 - 8; + ppc_inst_write(code, inst64); + check(!patch_instructions((u32 *)(addr64 + 1), code, 24, true)); + + check(addr64[0] == 0); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[1]), inst64)); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[2]), inst64)); + check(ppc_inst_equal(ppc_inst_read((u32 *)&addr64[3]), inst64)); + check(addr64[4] == 0); + } + + /* Test multipage memcpy */ + addr32 = buf + PAGE_SIZE * 6 - 12; + + for (int i = 0; i < ARRAY_SIZE(code); i++) + code[i] = i + 1; + + check(!patch_instructions(addr32 + 1, code, sizeof(code), false)); + + check(addr32[0] == 0); + check(!memcmp(&addr32[1], code, sizeof(code))); + check(addr32[ARRAY_SIZE(code) + 1] == 0); + + vfree(buf); +} + static int __init test_code_patching(void) { pr_info("Running code patching self-tests ...\n"); @@ -356,6 +447,7 @@ static int __init test_code_patching(void) test_create_function_call(); test_translate_branch(); test_prefixed_patching(); + test_multi_instruction_patching(); return 0; } diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index 503a6e249940..0fe2f085c05a 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -3,8 +3,6 @@ # Makefile for the linux ppc-specific parts of the memory manager. # -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) - obj-y := fault.o mem.o pgtable.o maccess.o pageattr.o \ init_$(BITS).o pgtable_$(BITS).o \ pgtable-frag.o ioremap.o ioremap_$(BITS).o \ diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile index cad2abc1730f..33af5795856a 100644 --- a/arch/powerpc/mm/book3s64/Makefile +++ b/arch/powerpc/mm/book3s64/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y := $(NO_MINIMAL_TOC) - obj-y += mmu_context.o pgtable.o trace.o ifdef CONFIG_PPC_64S_HASH_MMU CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE) diff --git a/arch/powerpc/mm/cacheflush.c b/arch/powerpc/mm/cacheflush.c index 15189592da09..7186516eca52 100644 --- a/arch/powerpc/mm/cacheflush.c +++ b/arch/powerpc/mm/cacheflush.c @@ -78,7 +78,7 @@ EXPORT_SYMBOL(flush_icache_range); #ifdef CONFIG_HIGHMEM /** - * flush_dcache_icache_phys() - Flush a page by it's physical address + * flush_dcache_icache_phys() - Flush a page by its physical address * @physaddr: the physical address of the page */ static void flush_dcache_icache_phys(unsigned long physaddr) diff --git a/arch/powerpc/mm/kasan/init_book3e_64.c b/arch/powerpc/mm/kasan/init_book3e_64.c index 11519e88dc6b..43c03b84ff32 100644 --- a/arch/powerpc/mm/kasan/init_book3e_64.c +++ b/arch/powerpc/mm/kasan/init_book3e_64.c @@ -112,7 +112,7 @@ void __init kasan_init(void) pte_t zero_pte = pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL_RO); for_each_mem_range(i, &start, &end) - kasan_init_phys_region((void *)start, (void *)end); + kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end)); if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) kasan_remove_zero_shadow((void *)VMALLOC_START, VMALLOC_SIZE); diff --git a/arch/powerpc/mm/kasan/init_book3s_64.c b/arch/powerpc/mm/kasan/init_book3s_64.c index 9300d641cf9a..3fb5ce4f48f4 100644 --- a/arch/powerpc/mm/kasan/init_book3s_64.c +++ b/arch/powerpc/mm/kasan/init_book3s_64.c @@ -62,7 +62,7 @@ void __init kasan_init(void) } for_each_mem_range(i, &start, &end) - kasan_init_phys_region((void *)start, (void *)end); + kasan_init_phys_region(phys_to_virt(start), phys_to_virt(end)); for (i = 0; i < PTRS_PER_PTE; i++) __set_pte_at(&init_mm, (unsigned long)kasan_early_shadow_page, diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5de62a3c1d4b..22cc978cdb47 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -31,7 +31,7 @@ #include <mm/mmu_decl.h> -unsigned long long memory_limit; +unsigned long long memory_limit __initdata; unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index f3894e79d5f7..b3f0498dd42f 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) - obj-y += mmu_context.o tlb.o tlb_low.o kup.o obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o obj-$(CONFIG_40x) += 40x.o diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index cdff129abb14..5c8d1bb98b3e 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -376,7 +376,7 @@ notrace void __init kaslr_early_init(void *dt_ptr, phys_addr_t size) create_kaslr_tlb_entry(1, tlb_virt, tlb_phys); } - /* Copy the kernel to it's new location and run */ + /* Copy the kernel to its new location and run */ memcpy((void *)kernstart_virt_addr, (void *)_stext, kernel_sz); flush_icache_range(kernstart_virt_addr, kernstart_virt_addr + kernel_sz); diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index 9a601587836b..a6baa6166d94 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -491,7 +491,7 @@ static void walk_vmemmap(struct pg_state *st) * Traverse the vmemmaped memory and dump pages that are in the hash * pagetable. */ - while (ptr->list) { + while (ptr) { hpte_find(st, ptr->virt_addr, mmu_vmemmap_psize); ptr = ptr->list; } diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 0f9a21783329..984655419da5 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -359,3 +359,13 @@ void bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } + +bool bpf_jit_supports_kfunc_call(void) +{ + return true; +} + +bool bpf_jit_supports_far_kfunc_call(void) +{ + return IS_ENABLED(CONFIG_PPC64); +} diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 2f39c50ca729..43b97032a91c 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -450,10 +450,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code } break; case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */ - EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg)); + if (off) + EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, src_reg)); + else + EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, src_reg)); break; case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */ - EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg)); + if (off) + EMIT(PPC_RAW_DIVW(_R0, src2_reg, src_reg)); + else + EMIT(PPC_RAW_DIVWU(_R0, src2_reg, src_reg)); EMIT(PPC_RAW_MULW(_R0, src_reg, _R0)); EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); break; @@ -467,10 +473,16 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (imm == 1) { EMIT(PPC_RAW_MR(dst_reg, src2_reg)); } else if (is_power_of_2((u32)imm)) { - EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm))); + if (off) + EMIT(PPC_RAW_SRAWI(dst_reg, src2_reg, ilog2(imm))); + else + EMIT(PPC_RAW_SRWI(dst_reg, src2_reg, ilog2(imm))); } else { PPC_LI32(_R0, imm); - EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0)); + if (off) + EMIT(PPC_RAW_DIVW(dst_reg, src2_reg, _R0)); + else + EMIT(PPC_RAW_DIVWU(dst_reg, src2_reg, _R0)); } break; case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */ @@ -480,11 +492,19 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code if (!is_power_of_2((u32)imm)) { bpf_set_seen_register(ctx, tmp_reg); PPC_LI32(tmp_reg, imm); - EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg)); + if (off) + EMIT(PPC_RAW_DIVW(_R0, src2_reg, tmp_reg)); + else + EMIT(PPC_RAW_DIVWU(_R0, src2_reg, tmp_reg)); EMIT(PPC_RAW_MULW(_R0, tmp_reg, _R0)); EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); } else if (imm == 1) { EMIT(PPC_RAW_LI(dst_reg, 0)); + } else if (off) { + EMIT(PPC_RAW_SRAWI(_R0, src2_reg, ilog2(imm))); + EMIT(PPC_RAW_ADDZE(_R0, _R0)); + EMIT(PPC_RAW_SLWI(_R0, _R0, ilog2(imm))); + EMIT(PPC_RAW_SUB(dst_reg, src2_reg, _R0)); } else { imm = ilog2((u32)imm); EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - imm, 31)); @@ -497,11 +517,21 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code imm = -imm; if (!is_power_of_2(imm)) return -EOPNOTSUPP; - if (imm == 1) + if (imm == 1) { EMIT(PPC_RAW_LI(dst_reg, 0)); - else + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } else if (off) { + EMIT(PPC_RAW_SRAWI(dst_reg_h, src2_reg_h, 31)); + EMIT(PPC_RAW_XOR(dst_reg, src2_reg, dst_reg_h)); + EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg)); + EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 32 - ilog2(imm), 31)); + EMIT(PPC_RAW_XOR(dst_reg, dst_reg, dst_reg_h)); + EMIT(PPC_RAW_SUBFC(dst_reg, dst_reg_h, dst_reg)); + EMIT(PPC_RAW_SUBFE(dst_reg_h, dst_reg_h, dst_reg_h)); + } else { EMIT(PPC_RAW_RLWINM(dst_reg, src2_reg, 0, 32 - ilog2(imm), 31)); - EMIT(PPC_RAW_LI(dst_reg_h, 0)); + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } break; case BPF_ALU64 | BPF_DIV | BPF_K: /* dst /= imm */ if (!imm) @@ -727,15 +757,30 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * MOV */ case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ - if (dst_reg == src_reg) - break; - EMIT(PPC_RAW_MR(dst_reg, src_reg)); - EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h)); + if (off == 8) { + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); + } else if (off == 16) { + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); + } else if (off == 32 && dst_reg == src_reg) { + EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31)); + } else if (off == 32) { + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + EMIT(PPC_RAW_SRAWI(dst_reg_h, src_reg, 31)); + } else if (dst_reg != src_reg) { + EMIT(PPC_RAW_MR(dst_reg, src_reg)); + EMIT(PPC_RAW_MR(dst_reg_h, src_reg_h)); + } break; case BPF_ALU | BPF_MOV | BPF_X: /* (u32) dst = src */ /* special mov32 for zext */ if (imm == 1) EMIT(PPC_RAW_LI(dst_reg_h, 0)); + else if (off == 8) + EMIT(PPC_RAW_EXTSB(dst_reg, src_reg)); + else if (off == 16) + EMIT(PPC_RAW_EXTSH(dst_reg, src_reg)); else if (dst_reg != src_reg) EMIT(PPC_RAW_MR(dst_reg, src_reg)); break; @@ -751,6 +796,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * BPF_FROM_BE/LE */ case BPF_ALU | BPF_END | BPF_FROM_LE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: switch (imm) { case 16: /* Copy 16 bits to upper part */ @@ -785,6 +831,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code EMIT(PPC_RAW_MR(dst_reg_h, tmp_reg)); break; } + if (BPF_CLASS(code) == BPF_ALU64 && imm != 64) + EMIT(PPC_RAW_LI(dst_reg_h, 0)); break; case BPF_ALU | BPF_END | BPF_FROM_BE: switch (imm) { @@ -918,11 +966,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * BPF_LDX */ case BPF_LDX | BPF_MEM | BPF_B: /* dst = *(u8 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: case BPF_LDX | BPF_PROBE_MEM | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_H: case BPF_LDX | BPF_PROBE_MEM | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_W: case BPF_LDX | BPF_PROBE_MEM | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */ case BPF_LDX | BPF_PROBE_MEM | BPF_DW: /* @@ -931,7 +985,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * load only if addr is kernel address (see is_kernel_addr()), otherwise * set dst_reg=0 and move on. */ - if (BPF_MODE(code) == BPF_PROBE_MEM) { + if (BPF_MODE(code) == BPF_PROBE_MEM || BPF_MODE(code) == BPF_PROBE_MEMSX) { PPC_LI32(_R0, TASK_SIZE - off); EMIT(PPC_RAW_CMPLW(src_reg, _R0)); PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4); @@ -953,30 +1007,48 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code * as there are two load instructions for dst_reg_h & dst_reg * respectively. */ - if (size == BPF_DW) + if (size == BPF_DW || + (size == BPF_B && BPF_MODE(code) == BPF_PROBE_MEMSX)) PPC_JMP((ctx->idx + 3) * 4); else PPC_JMP((ctx->idx + 2) * 4); } - switch (size) { - case BPF_B: - EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); - break; - case BPF_H: - EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off)); - break; - case BPF_W: - EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); - break; - case BPF_DW: - EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off)); - EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4)); - break; - } + if (BPF_MODE(code) == BPF_MEMSX || BPF_MODE(code) == BPF_PROBE_MEMSX) { + switch (size) { + case BPF_B: + EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); + EMIT(PPC_RAW_EXTSB(dst_reg, dst_reg)); + break; + case BPF_H: + EMIT(PPC_RAW_LHA(dst_reg, src_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); + break; + } + if (!fp->aux->verifier_zext) + EMIT(PPC_RAW_SRAWI(dst_reg_h, dst_reg, 31)); - if (size != BPF_DW && !fp->aux->verifier_zext) - EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } else { + switch (size) { + case BPF_B: + EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); + break; + case BPF_H: + EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off)); + break; + case BPF_W: + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); + break; + case BPF_DW: + EMIT(PPC_RAW_LWZ(dst_reg_h, src_reg, off)); + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off + 4)); + break; + } + if (size != BPF_DW && !fp->aux->verifier_zext) + EMIT(PPC_RAW_LI(dst_reg_h, 0)); + } if (BPF_MODE(code) == BPF_PROBE_MEM) { int insn_idx = ctx->idx - 1; @@ -1068,6 +1140,9 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code case BPF_JMP | BPF_JA: PPC_JMP(addrs[i + 1 + off]); break; + case BPF_JMP32 | BPF_JA: + PPC_JMP(addrs[i + 1 + imm]); + break; case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 79f23974a320..8afc14a4a125 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -202,29 +202,47 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); } -static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func) +static int +bpf_jit_emit_func_call_hlp(u32 *image, u32 *fimage, struct codegen_context *ctx, u64 func) { unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0; long reladdr; - if (WARN_ON_ONCE(!core_kernel_text(func_addr))) + if (WARN_ON_ONCE(!kernel_text_address(func_addr))) return -EINVAL; - if (IS_ENABLED(CONFIG_PPC_KERNEL_PCREL)) { - reladdr = func_addr - CTX_NIA(ctx); - - if (reladdr >= (long)SZ_8G || reladdr < -(long)SZ_8G) { - pr_err("eBPF: address of %ps out of range of pcrel address.\n", - (void *)func); - return -ERANGE; - } - /* pla r12,addr */ - EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr)); - EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr)); - EMIT(PPC_RAW_MTCTR(_R12)); - EMIT(PPC_RAW_BCTR()); +#ifdef CONFIG_PPC_KERNEL_PCREL + reladdr = func_addr - local_paca->kernelbase; + if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) { + EMIT(PPC_RAW_LD(_R12, _R13, offsetof(struct paca_struct, kernelbase))); + /* Align for subsequent prefix instruction */ + if (!IS_ALIGNED((unsigned long)fimage + CTX_NIA(ctx), 8)) + EMIT(PPC_RAW_NOP()); + /* paddi r12,r12,addr */ + EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(0) | IMM_H18(reladdr)); + EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | ___PPC_RA(_R12) | IMM_L(reladdr)); } else { + unsigned long pc = (unsigned long)fimage + CTX_NIA(ctx); + bool alignment_needed = !IS_ALIGNED(pc, 8); + + reladdr = func_addr - (alignment_needed ? pc + 4 : pc); + + if (reladdr < (long)SZ_8G && reladdr >= -(long)SZ_8G) { + if (alignment_needed) + EMIT(PPC_RAW_NOP()); + /* pla r12,addr */ + EMIT(PPC_PREFIX_MLS | __PPC_PRFX_R(1) | IMM_H18(reladdr)); + EMIT(PPC_INST_PADDI | ___PPC_RT(_R12) | IMM_L(reladdr)); + } else { + /* We can clobber r12 */ + PPC_LI64(_R12, func); + } + } + EMIT(PPC_RAW_MTCTR(_R12)); + EMIT(PPC_RAW_BCTRL()); +#else + if (core_kernel_text(func_addr)) { reladdr = func_addr - kernel_toc_addr(); if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func); @@ -235,7 +253,32 @@ static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr))); EMIT(PPC_RAW_MTCTR(_R12)); EMIT(PPC_RAW_BCTRL()); + } else { + if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V1)) { + /* func points to the function descriptor */ + PPC_LI64(bpf_to_ppc(TMP_REG_2), func); + /* Load actual entry point from function descriptor */ + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_2), 0)); + /* ... and move it to CTR */ + EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1))); + /* + * Load TOC from function descriptor at offset 8. + * We can clobber r2 since we get called through a + * function pointer (so caller will save/restore r2). + */ + EMIT(PPC_RAW_LD(_R2, bpf_to_ppc(TMP_REG_2), 8)); + } else { + PPC_LI64(_R12, func); + EMIT(PPC_RAW_MTCTR(_R12)); + } + EMIT(PPC_RAW_BCTRL()); + /* + * Load r2 with kernel TOC as kernel TOC is used if function address falls + * within core kernel text. + */ + EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc))); } +#endif return 0; } @@ -285,7 +328,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o int b2p_index = bpf_to_ppc(BPF_REG_3); int bpf_tailcall_prologue_size = 8; - if (IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) + if (!IS_ENABLED(CONFIG_PPC_KERNEL_PCREL) && IS_ENABLED(CONFIG_PPC64_ELF_ABI_V2)) bpf_tailcall_prologue_size += 4; /* skip past the toc load */ /* @@ -993,7 +1036,7 @@ emit_clear: return ret; if (func_addr_fixed) - ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_hlp(image, fimage, ctx, func_addr); else ret = bpf_jit_emit_func_call_rel(image, fimage, ctx, func_addr); diff --git a/arch/powerpc/platforms/512x/mpc512x_shared.c b/arch/powerpc/platforms/512x/mpc512x_shared.c index 8f75e9574c27..8c1f3b629fc7 100644 --- a/arch/powerpc/platforms/512x/mpc512x_shared.c +++ b/arch/powerpc/platforms/512x/mpc512x_shared.c @@ -279,7 +279,7 @@ static void __init mpc512x_setup_diu(void) * and so negatively affect boot time. Instead we reserve the * already configured frame buffer area so that it won't be * destroyed. The starting address of the area to reserve and - * also it's length is passed to memblock_reserve(). It will be + * also its length is passed to memblock_reserve(). It will be * freed later on first open of fbdev, when splash image is not * needed any more. */ diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S index 0b12647e7b42..0ec2522ee4ad 100644 --- a/arch/powerpc/platforms/52xx/lite5200_sleep.S +++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S @@ -203,7 +203,8 @@ lite5200_wakeup: /* HIDs, MSR */ LOAD_SPRN(HID1, 0x19) - LOAD_SPRN(HID2, 0x1a) + /* FIXME: Should this use HID2_G2_LE? */ + LOAD_SPRN(HID2_750FX, 0x1a) /* address translation is tricky (see turn_on_mmu) */ @@ -283,7 +284,8 @@ SYM_FUNC_START_LOCAL(save_regs) SAVE_SPRN(HID0, 0x18) SAVE_SPRN(HID1, 0x19) - SAVE_SPRN(HID2, 0x1a) + /* FIXME: Should this use HID2_G2_LE? */ + SAVE_SPRN(HID2_750FX, 0x1a) mfmsr r10 stw r10, (4*0x1b)(r4) /*SAVE_SPRN(LR, 0x1c) have to save it before the call */ diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c index b4938e344f71..253421ffb4e5 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_common.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c @@ -12,12 +12,10 @@ #undef DEBUG -#include <linux/gpio.h> #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/of_address.h> #include <linux/of_platform.h> -#include <linux/of_gpio.h> #include <linux/export.h> #include <asm/io.h> #include <asm/mpc52xx.h> diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c index 581059527c36..2bd6abcdc113 100644 --- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c +++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c @@ -48,6 +48,7 @@ * the output mode. This driver does not change the output mode setting. */ +#include <linux/gpio/driver.h> #include <linux/irq.h> #include <linux/interrupt.h> #include <linux/io.h> @@ -56,7 +57,6 @@ #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_gpio.h> #include <linux/platform_device.h> #include <linux/kernel.h> #include <linux/property.h> diff --git a/arch/powerpc/platforms/83xx/suspend-asm.S b/arch/powerpc/platforms/83xx/suspend-asm.S index bc6bd4d0ae96..6a62ed6082c9 100644 --- a/arch/powerpc/platforms/83xx/suspend-asm.S +++ b/arch/powerpc/platforms/83xx/suspend-asm.S @@ -68,7 +68,8 @@ _GLOBAL(mpc83xx_enter_deep_sleep) mfspr r5, SPRN_HID0 mfspr r6, SPRN_HID1 - mfspr r7, SPRN_HID2 + /* FIXME: Should this use SPRN_HID2_G2_LE? */ + mfspr r7, SPRN_HID2_750FX stw r5, SS_HID+0(r3) stw r6, SS_HID+4(r3) @@ -396,7 +397,8 @@ mpc83xx_deep_resume: mtspr SPRN_HID0, r5 mtspr SPRN_HID1, r6 - mtspr SPRN_HID2, r7 + /* FIXME: Should this use SPRN_HID2_G2_LE? */ + mtspr SPRN_HID2_750FX, r7 lwz r4, SS_IABR+0(r3) lwz r5, SS_IABR+4(r3) diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index 40aa58206888..e52b848b64b7 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -398,6 +398,7 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary) hard_irq_disable(); mpic_teardown_this_cpu(secondary); +#ifdef CONFIG_CRASH_DUMP if (cpu == crashing_cpu && cpu_thread_in_core(cpu) != 0) { /* * We enter the crash kernel on whatever cpu crashed, @@ -406,9 +407,11 @@ static void mpc85xx_smp_kexec_cpu_down(int crash_shutdown, int secondary) */ disable_threadbit = 1; disable_cpu = cpu_first_thread_sibling(cpu); - } else if (sibling != crashing_cpu && - cpu_thread_in_core(cpu) == 0 && - cpu_thread_in_core(sibling) != 0) { + } else if (sibling == crashing_cpu) { + return; + } +#endif + if (cpu_thread_in_core(cpu) == 0 && cpu_thread_in_core(sibling) != 0) { disable_threadbit = 2; disable_cpu = sibling; } diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c index 1202a69b0a20..4cd9c0de22c2 100644 --- a/arch/powerpc/platforms/cell/iommu.c +++ b/arch/powerpc/platforms/cell/iommu.c @@ -424,23 +424,6 @@ static void __init cell_iommu_setup_hardware(struct cbe_iommu *iommu, cell_iommu_enable_hardware(iommu); } -#if 0/* Unused for now */ -static struct iommu_window *find_window(struct cbe_iommu *iommu, - unsigned long offset, unsigned long size) -{ - struct iommu_window *window; - - /* todo: check for overlapping (but not equal) windows) */ - - list_for_each_entry(window, &(iommu->windows), list) { - if (window->offset == offset && window->size == size) - return window; - } - - return NULL; -} -#endif - static inline u32 cell_iommu_get_ioid(struct device_node *np) { const u32 *ioid; diff --git a/arch/powerpc/platforms/cell/smp.c b/arch/powerpc/platforms/cell/smp.c index 30394c6f8894..fee638fd8970 100644 --- a/arch/powerpc/platforms/cell/smp.c +++ b/arch/powerpc/platforms/cell/smp.c @@ -54,6 +54,7 @@ static cpumask_t of_spin_map; /** * smp_startup_cpu() - start the given cpu + * @lcpu: Logical CPU ID of the CPU to be started. * * At boot time, there is nothing to do for primary threads which were * started from Open Firmware. For anything else, call RTAS with the diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 02a8158c469d..7f4e0db8eb08 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1704,23 +1704,11 @@ static int spufs_mfc_flush(struct file *file, fl_owner_t id) ret = spu_acquire(ctx); if (ret) - goto out; -#if 0 -/* this currently hangs */ - ret = spufs_wait(ctx->mfc_wq, - ctx->ops->set_mfc_query(ctx, ctx->tagwait, 2)); - if (ret) - goto out; - ret = spufs_wait(ctx->mfc_wq, - ctx->ops->read_mfc_tagstatus(ctx) == ctx->tagwait); - if (ret) - goto out; -#else - ret = 0; -#endif + return ret; + spu_release(ctx); -out: - return ret; + + return 0; } static int spufs_mfc_fsync(struct file *file, loff_t start, loff_t end, int datasync) diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 99bd027a7f7c..610ca8570682 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -868,7 +868,7 @@ static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio) } /** - * spu_deactivate - unbind a context from it's physical spu + * spu_deactivate - unbind a context from its physical spu * @ctx: spu context to unbind * * Unbind @ctx from the physical spu it is running on and schedule diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index b911b31717cc..b9ff37c7f6f0 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -595,7 +595,7 @@ void __init maple_pci_init(void) /* Probe root PCI hosts, that is on U3 the AGP host and the * HyperTransport host. That one is actually "kept" around - * and actually added last as it's resource management relies + * and actually added last as its resource management relies * on the AGP resources to have been setup first */ root = of_find_node_by_path("/"); diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 7135ea1d7db6..2202bf77c7a3 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -2,7 +2,7 @@ /* * Support for the interrupt controllers found on Power Macintosh, * currently Apple's "Grand Central" interrupt controller in all - * it's incarnations. OpenPIC support used on newer machines is + * its incarnations. OpenPIC support used on newer machines is * in a separate file * * Copyright (C) 1997 Paul Mackerras (paulus@samba.org) diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index d497a60003d2..822ed70cdcbf 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -176,7 +176,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) * memory location containing the PC to resume from * at address 0. * - On Core99, we must store the wakeup vector at - * address 0x80 and eventually it's parameters + * address 0x80 and eventually its parameters * at address 0x84. I've have some trouble with those * parameters however and I no longer use them. */ diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c index 964f464b1b0e..c9c1dfb35464 100644 --- a/arch/powerpc/platforms/powernv/opal-fadump.c +++ b/arch/powerpc/platforms/powernv/opal-fadump.c @@ -513,8 +513,8 @@ out: final_note(note_buf); pr_debug("Updating elfcore header (%llx) with cpu notes\n", - fdh->elfcorehdr_addr); - fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr)); + fadump_conf->elfcorehdr_addr); + fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr); return 0; } @@ -526,12 +526,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf) if (!opal_fdm_active || !fadump_conf->fadumphdr_addr) return rc; - /* Validate the fadump crash info header */ fdh = __va(fadump_conf->fadumphdr_addr); - if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { - pr_err("Crash info header is not valid.\n"); - return rc; - } #ifdef CONFIG_OPAL_CORE /* @@ -545,18 +540,7 @@ static int __init opal_fadump_process(struct fw_dump *fadump_conf) kernel_initiated = true; #endif - rc = opal_fadump_build_cpu_notes(fadump_conf, fdh); - if (rc) - return rc; - - /* - * We are done validating dump info and elfcore header is now ready - * to be exported. set elfcorehdr_addr so that vmcore module will - * export the elfcore header through '/proc/vmcore'. - */ - elfcorehdr_addr = fdh->elfcorehdr_addr; - - return rc; + return opal_fadump_build_cpu_notes(fadump_conf, fdh); } static void opal_fadump_region_show(struct fw_dump *fadump_conf, @@ -615,6 +599,12 @@ static void opal_fadump_trigger(struct fadump_crash_info_header *fdh, pr_emerg("No backend support for MPIPL!\n"); } +/* FADUMP_MAX_MEM_REGS or lower */ +static int opal_fadump_max_boot_mem_rgns(void) +{ + return FADUMP_MAX_MEM_REGS; +} + static struct fadump_ops opal_fadump_ops = { .fadump_init_mem_struct = opal_fadump_init_mem_struct, .fadump_get_metadata_size = opal_fadump_get_metadata_size, @@ -627,6 +617,7 @@ static struct fadump_ops opal_fadump_ops = { .fadump_process = opal_fadump_process, .fadump_region_show = opal_fadump_region_show, .fadump_trigger = opal_fadump_trigger, + .fadump_max_boot_mem_rgns = opal_fadump_max_boot_mem_rgns, }; void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) @@ -674,8 +665,10 @@ void __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) } } - fadump_conf->ops = &opal_fadump_ops; - fadump_conf->fadump_supported = 1; + fadump_conf->ops = &opal_fadump_ops; + fadump_conf->fadump_supported = 1; + /* TODO: Add support to pass additional parameters */ + fadump_conf->param_area_supported = 0; /* * Firmware supports 32-bit field for size. Align it to PAGE_SIZE diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c index 59882da3e742..cc7b1dd54ac6 100644 --- a/arch/powerpc/platforms/powernv/pci-sriov.c +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -238,7 +238,7 @@ void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev) } else if (pdev->is_physfn) { /* * For PFs adjust their allocated IOV resources to match what - * the PHB can support using it's M64 BAR table. + * the PHB can support using its M64 BAR table. */ pnv_pci_ioda_fixup_iov_resources(pdev); } @@ -658,7 +658,7 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) list_add_tail(&pe->list, &phb->ioda.pe_list); mutex_unlock(&phb->ioda.pe_list_mutex); - /* associate this pe to it's pdn */ + /* associate this pe to its pdn */ list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) { if (vf_pdn->busno == vf_bus && vf_pdn->devfn == vf_devfn) { diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index b664838008c1..5147df3a18ac 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -1059,7 +1059,7 @@ struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop, } } else { /* - * Interrupt hanlder or fault window setup failed. Means + * Interrupt handler or fault window setup failed. Means * NX can not generate fault for page fault. So not * opening for user space tx window. */ diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c index 878bc160246e..b18e1c92e554 100644 --- a/arch/powerpc/platforms/ps3/device-init.c +++ b/arch/powerpc/platforms/ps3/device-init.c @@ -770,49 +770,51 @@ static struct task_struct *probe_task; static int ps3_probe_thread(void *data) { - struct ps3_notification_device dev; + struct { + struct ps3_notification_device dev; + u8 buf[512]; + } *local; + struct ps3_notify_cmd *notify_cmd; + struct ps3_notify_event *notify_event; int res; unsigned int irq; u64 lpar; - void *buf; - struct ps3_notify_cmd *notify_cmd; - struct ps3_notify_event *notify_event; pr_debug(" -> %s:%u: kthread started\n", __func__, __LINE__); - buf = kzalloc(512, GFP_KERNEL); - if (!buf) + local = kzalloc(sizeof(*local), GFP_KERNEL); + if (!local) return -ENOMEM; - lpar = ps3_mm_phys_to_lpar(__pa(buf)); - notify_cmd = buf; - notify_event = buf; + lpar = ps3_mm_phys_to_lpar(__pa(&local->buf)); + notify_cmd = (struct ps3_notify_cmd *)&local->buf; + notify_event = (struct ps3_notify_event *)&local->buf; /* dummy system bus device */ - dev.sbd.bus_id = (u64)data; - dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID; - dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID; + local->dev.sbd.bus_id = (u64)data; + local->dev.sbd.dev_id = PS3_NOTIFICATION_DEV_ID; + local->dev.sbd.interrupt_id = PS3_NOTIFICATION_INTERRUPT_ID; - res = lv1_open_device(dev.sbd.bus_id, dev.sbd.dev_id, 0); + res = lv1_open_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id, 0); if (res) { pr_err("%s:%u: lv1_open_device failed %s\n", __func__, __LINE__, ps3_result(res)); goto fail_free; } - res = ps3_sb_event_receive_port_setup(&dev.sbd, PS3_BINDING_CPU_ANY, - &irq); + res = ps3_sb_event_receive_port_setup(&local->dev.sbd, + PS3_BINDING_CPU_ANY, &irq); if (res) { pr_err("%s:%u: ps3_sb_event_receive_port_setup failed %d\n", __func__, __LINE__, res); goto fail_close_device; } - spin_lock_init(&dev.lock); - rcuwait_init(&dev.wait); + spin_lock_init(&local->dev.lock); + rcuwait_init(&local->dev.wait); res = request_irq(irq, ps3_notification_interrupt, 0, - "ps3_notification", &dev); + "ps3_notification", &local->dev); if (res) { pr_err("%s:%u: request_irq failed %d\n", __func__, __LINE__, res); @@ -823,7 +825,7 @@ static int ps3_probe_thread(void *data) notify_cmd->operation_code = 0; /* must be zero */ notify_cmd->event_mask = 1UL << notify_region_probe; - res = ps3_notification_read_write(&dev, lpar, 1); + res = ps3_notification_read_write(&local->dev, lpar, 1); if (res) goto fail_free_irq; @@ -834,36 +836,37 @@ static int ps3_probe_thread(void *data) memset(notify_event, 0, sizeof(*notify_event)); - res = ps3_notification_read_write(&dev, lpar, 0); + res = ps3_notification_read_write(&local->dev, lpar, 0); if (res) break; pr_debug("%s:%u: notify event type 0x%llx bus id %llu dev id %llu" " type %llu port %llu\n", __func__, __LINE__, - notify_event->event_type, notify_event->bus_id, - notify_event->dev_id, notify_event->dev_type, - notify_event->dev_port); + notify_event->event_type, notify_event->bus_id, + notify_event->dev_id, notify_event->dev_type, + notify_event->dev_port); if (notify_event->event_type != notify_region_probe || - notify_event->bus_id != dev.sbd.bus_id) { + notify_event->bus_id != local->dev.sbd.bus_id) { pr_warn("%s:%u: bad notify_event: event %llu, dev_id %llu, dev_type %llu\n", __func__, __LINE__, notify_event->event_type, notify_event->dev_id, notify_event->dev_type); continue; } - ps3_find_and_add_device(dev.sbd.bus_id, notify_event->dev_id); + ps3_find_and_add_device(local->dev.sbd.bus_id, + notify_event->dev_id); } while (!kthread_should_stop()); fail_free_irq: - free_irq(irq, &dev); + free_irq(irq, &local->dev); fail_sb_event_receive_port_destroy: - ps3_sb_event_receive_port_destroy(&dev.sbd, irq); + ps3_sb_event_receive_port_destroy(&local->dev.sbd, irq); fail_close_device: - lv1_close_device(dev.sbd.bus_id, dev.sbd.dev_id); + lv1_close_device(local->dev.sbd.bus_id, local->dev.sbd.dev_id); fail_free: - kfree(buf); + kfree(local); probe_task = NULL; diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index f936962a2946..7bf506f6b8c8 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) ccflags-$(CONFIG_PPC_PSERIES_DEBUG) += -DDEBUG obj-y := lpar.o hvCall.o nvram.o reconfig.o \ diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 4e9916bb03d7..c1d8bee8f701 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1886,10 +1886,10 @@ out: * h_get_mpp * H_GET_MPP hcall returns info in 7 parms */ -int h_get_mpp(struct hvcall_mpp_data *mpp_data) +long h_get_mpp(struct hvcall_mpp_data *mpp_data) { - int rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_MPP, retbuf); diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index f73c4d1c26af..6e7029640c0c 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -113,8 +113,8 @@ struct hvcall_ppp_data { */ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) { - unsigned long rc; - unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; + long rc; rc = plpar_hcall9(H_GET_PPP, retbuf); @@ -170,20 +170,24 @@ out: kfree(buf); } -static unsigned h_pic(unsigned long *pool_idle_time, - unsigned long *num_procs) +static long h_pic(unsigned long *pool_idle_time, + unsigned long *num_procs) { - unsigned long rc; - unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = {0}; rc = plpar_hcall(H_PIC, retbuf); - *pool_idle_time = retbuf[0]; - *num_procs = retbuf[1]; + if (pool_idle_time) + *pool_idle_time = retbuf[0]; + if (num_procs) + *num_procs = retbuf[1]; return rc; } +unsigned long boot_pool_idle_time; + /* * parse_ppp_data * Parse out the data returned from h_get_ppp and h_pic @@ -193,7 +197,7 @@ static void parse_ppp_data(struct seq_file *m) struct hvcall_ppp_data ppp_data; struct device_node *root; const __be32 *perf_level; - int rc; + long rc; rc = h_get_ppp(&ppp_data); if (rc) @@ -215,9 +219,15 @@ static void parse_ppp_data(struct seq_file *m) seq_printf(m, "pool_capacity=%d\n", ppp_data.active_procs_in_pool * 100); - h_pic(&pool_idle_time, &pool_procs); - seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time); - seq_printf(m, "pool_num_procs=%ld\n", pool_procs); + /* In case h_pic call is not successful, this would result in + * APP values being wrong in tools like lparstat. + */ + + if (h_pic(&pool_idle_time, &pool_procs) == H_SUCCESS) { + seq_printf(m, "pool_idle_time=%ld\n", pool_idle_time); + seq_printf(m, "pool_num_procs=%ld\n", pool_procs); + seq_printf(m, "boot_pool_idle_time=%ld\n", boot_pool_idle_time); + } } seq_printf(m, "unallocated_capacity_weight=%d\n", @@ -792,6 +802,7 @@ static const struct proc_ops lparcfg_proc_ops = { static int __init lparcfg_init(void) { umode_t mode = 0444; + long retval; /* Allow writing if we have FW_FEATURE_SPLPAR */ if (firmware_has_feature(FW_FEATURE_SPLPAR)) @@ -801,6 +812,16 @@ static int __init lparcfg_init(void) printk(KERN_ERR "Failed to create powerpc/lparcfg\n"); return -EIO; } + + /* If this call fails, it would result in APP values + * being wrong for since boot reports of lparstat + */ + retval = h_pic(&boot_pool_idle_time, NULL); + + if (retval != H_SUCCESS) + pr_debug("H_PIC failed during lparcfg init retval: %ld\n", + retval); + return 0; } machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c index 1772ae3d193d..6dbc73eb2ca2 100644 --- a/arch/powerpc/platforms/pseries/pci.c +++ b/arch/powerpc/platforms/pseries/pci.c @@ -18,33 +18,6 @@ #include <asm/pci.h> #include "pseries.h" -#if 0 -void pcibios_name_device(struct pci_dev *dev) -{ - struct device_node *dn; - - /* - * Add IBM loc code (slot) as a prefix to the device names for service - */ - dn = pci_device_to_OF_node(dev); - if (dn) { - const char *loc_code = of_get_property(dn, "ibm,loc-code", - NULL); - if (loc_code) { - int loc_len = strlen(loc_code); - if (loc_len < sizeof(dev->dev.name)) { - memmove(dev->dev.name+loc_len+1, dev->dev.name, - sizeof(dev->dev.name)-loc_len-1); - memcpy(dev->dev.name, loc_code, loc_len); - dev->dev.name[loc_len] = ' '; - dev->dev.name[sizeof(dev->dev.name)-1] = '\0'; - } - } - } -} -DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_name_device); -#endif - #ifdef CONFIG_PCI_IOV #define MAX_VFS_FOR_MAP_PE 256 struct pe_map_bar_entry { diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c index b5853e9fcc3c..eceb3289383e 100644 --- a/arch/powerpc/platforms/pseries/rtas-fadump.c +++ b/arch/powerpc/platforms/pseries/rtas-fadump.c @@ -18,6 +18,7 @@ #include <asm/page.h> #include <asm/rtas.h> +#include <asm/setup.h> #include <asm/fadump.h> #include <asm/fadump-internal.h> @@ -29,9 +30,6 @@ static const struct rtas_fadump_mem_struct *fdm_active; static void rtas_fadump_update_config(struct fw_dump *fadump_conf, const struct rtas_fadump_mem_struct *fdm) { - fadump_conf->boot_mem_dest_addr = - be64_to_cpu(fdm->rmr_region.destination_address); - fadump_conf->fadumphdr_addr = (fadump_conf->boot_mem_dest_addr + fadump_conf->boot_memory_size); } @@ -43,20 +41,56 @@ static void rtas_fadump_update_config(struct fw_dump *fadump_conf, static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf, const struct rtas_fadump_mem_struct *fdm) { - fadump_conf->boot_mem_addr[0] = - be64_to_cpu(fdm->rmr_region.source_address); - fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len); - fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0]; + unsigned long base, size, last_end, hole_size; - fadump_conf->boot_mem_top = fadump_conf->boot_memory_size; - fadump_conf->boot_mem_regs_cnt = 1; + last_end = 0; + hole_size = 0; + fadump_conf->boot_memory_size = 0; + fadump_conf->boot_mem_regs_cnt = 0; + pr_debug("Boot memory regions:\n"); + for (int i = 0; i < be16_to_cpu(fdm->header.dump_num_sections); i++) { + int type = be16_to_cpu(fdm->rgn[i].source_data_type); + u64 addr; - /* - * Start address of reserve dump area (permanent reservation) for - * re-registering FADump after dump capture. - */ - fadump_conf->reserve_dump_area_start = - be64_to_cpu(fdm->cpu_state_data.destination_address); + switch (type) { + case RTAS_FADUMP_CPU_STATE_DATA: + addr = be64_to_cpu(fdm->rgn[i].destination_address); + + fadump_conf->cpu_state_dest_vaddr = (u64)__va(addr); + /* + * Start address of reserve dump area (permanent reservation) for + * re-registering FADump after dump capture. + */ + fadump_conf->reserve_dump_area_start = addr; + break; + case RTAS_FADUMP_HPTE_REGION: + /* Not processed currently. */ + break; + case RTAS_FADUMP_REAL_MODE_REGION: + base = be64_to_cpu(fdm->rgn[i].source_address); + size = be64_to_cpu(fdm->rgn[i].source_len); + pr_debug("\t[%03d] base: 0x%lx, size: 0x%lx\n", i, base, size); + if (!base) { + fadump_conf->boot_mem_dest_addr = + be64_to_cpu(fdm->rgn[i].destination_address); + } + + fadump_conf->boot_mem_addr[fadump_conf->boot_mem_regs_cnt] = base; + fadump_conf->boot_mem_sz[fadump_conf->boot_mem_regs_cnt] = size; + fadump_conf->boot_memory_size += size; + hole_size += (base - last_end); + last_end = base + size; + fadump_conf->boot_mem_regs_cnt++; + break; + case RTAS_FADUMP_PARAM_AREA: + fadump_conf->param_area = be64_to_cpu(fdm->rgn[i].destination_address); + break; + default: + pr_warn("Section type %d unsupported on this kernel. Ignoring!\n", type); + break; + } + } + fadump_conf->boot_mem_top = fadump_conf->boot_memory_size + hole_size; rtas_fadump_update_config(fadump_conf, fdm); } @@ -64,16 +98,15 @@ static void __init rtas_fadump_get_config(struct fw_dump *fadump_conf, static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf) { u64 addr = fadump_conf->reserve_dump_area_start; + u16 sec_cnt = 0; memset(&fdm, 0, sizeof(struct rtas_fadump_mem_struct)); addr = addr & PAGE_MASK; fdm.header.dump_format_version = cpu_to_be32(0x00000001); - fdm.header.dump_num_sections = cpu_to_be16(3); fdm.header.dump_status_flag = 0; fdm.header.offset_first_dump_section = - cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, - cpu_state_data)); + cpu_to_be32((u32)offsetof(struct rtas_fadump_mem_struct, rgn)); /* * Fields for disk dump option. @@ -89,25 +122,22 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf) /* Kernel dump sections */ /* cpu state data section. */ - fdm.cpu_state_data.request_flag = - cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); - fdm.cpu_state_data.source_data_type = - cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA); - fdm.cpu_state_data.source_address = 0; - fdm.cpu_state_data.source_len = - cpu_to_be64(fadump_conf->cpu_state_data_size); - fdm.cpu_state_data.destination_address = cpu_to_be64(addr); + fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_CPU_STATE_DATA); + fdm.rgn[sec_cnt].source_address = 0; + fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->cpu_state_data_size); + fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr); addr += fadump_conf->cpu_state_data_size; + sec_cnt++; /* hpte region section */ - fdm.hpte_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); - fdm.hpte_region.source_data_type = - cpu_to_be16(RTAS_FADUMP_HPTE_REGION); - fdm.hpte_region.source_address = 0; - fdm.hpte_region.source_len = - cpu_to_be64(fadump_conf->hpte_region_size); - fdm.hpte_region.destination_address = cpu_to_be64(addr); + fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_HPTE_REGION); + fdm.rgn[sec_cnt].source_address = 0; + fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->hpte_region_size); + fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr); addr += fadump_conf->hpte_region_size; + sec_cnt++; /* * Align boot memory area destination address to page boundary to @@ -115,14 +145,29 @@ static u64 rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf) */ addr = PAGE_ALIGN(addr); - /* RMA region section */ - fdm.rmr_region.request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); - fdm.rmr_region.source_data_type = - cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION); - fdm.rmr_region.source_address = cpu_to_be64(0); - fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size); - fdm.rmr_region.destination_address = cpu_to_be64(addr); - addr += fadump_conf->boot_memory_size; + /* First boot memory region destination address */ + fadump_conf->boot_mem_dest_addr = addr; + for (int i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) { + /* Boot memory regions */ + fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION); + fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->boot_mem_addr[i]); + fdm.rgn[sec_cnt].source_len = cpu_to_be64(fadump_conf->boot_mem_sz[i]); + fdm.rgn[sec_cnt].destination_address = cpu_to_be64(addr); + addr += fadump_conf->boot_mem_sz[i]; + sec_cnt++; + } + + /* Parameters area */ + if (fadump_conf->param_area) { + fdm.rgn[sec_cnt].request_flag = cpu_to_be32(RTAS_FADUMP_REQUEST_FLAG); + fdm.rgn[sec_cnt].source_data_type = cpu_to_be16(RTAS_FADUMP_PARAM_AREA); + fdm.rgn[sec_cnt].source_address = cpu_to_be64(fadump_conf->param_area); + fdm.rgn[sec_cnt].source_len = cpu_to_be64(COMMAND_LINE_SIZE); + fdm.rgn[sec_cnt].destination_address = cpu_to_be64(fadump_conf->param_area); + sec_cnt++; + } + fdm.header.dump_num_sections = cpu_to_be16(sec_cnt); rtas_fadump_update_config(fadump_conf, &fdm); @@ -136,14 +181,21 @@ static u64 rtas_fadump_get_bootmem_min(void) static int rtas_fadump_register(struct fw_dump *fadump_conf) { - unsigned int wait_time; + unsigned int wait_time, fdm_size; int rc, err = -EIO; + /* + * Platform requires the exact size of the Dump Memory Structure. + * Avoid including any unused rgns in the calculation, as this + * could result in a parameter error (-3) from the platform. + */ + fdm_size = sizeof(struct rtas_fadump_section_header); + fdm_size += be16_to_cpu(fdm.header.dump_num_sections) * sizeof(struct rtas_fadump_section); + /* TODO: Add upper time limit for the delay */ do { rc = rtas_call(fadump_conf->ibm_configure_kernel_dump, 3, 1, - NULL, FADUMP_REGISTER, &fdm, - sizeof(struct rtas_fadump_mem_struct)); + NULL, FADUMP_REGISTER, &fdm, fdm_size); wait_time = rtas_busy_delay_time(rc); if (wait_time) @@ -161,9 +213,7 @@ static int rtas_fadump_register(struct fw_dump *fadump_conf) pr_err("Failed to register. Hardware Error(%d).\n", rc); break; case -3: - if (!is_fadump_boot_mem_contiguous()) - pr_err("Can't have holes in boot memory area.\n"); - else if (!is_fadump_reserved_mem_contiguous()) + if (!is_fadump_reserved_mem_contiguous()) pr_err("Can't have holes in reserved memory area.\n"); pr_err("Failed to register. Parameter Error(%d).\n", rc); @@ -316,11 +366,9 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf) u32 num_cpus, *note_buf; int i, rc = 0, cpu = 0; struct pt_regs regs; - unsigned long addr; void *vaddr; - addr = be64_to_cpu(fdm_active->cpu_state_data.destination_address); - vaddr = __va(addr); + vaddr = (void *)fadump_conf->cpu_state_dest_vaddr; reg_header = vaddr; if (be64_to_cpu(reg_header->magic_number) != @@ -375,11 +423,8 @@ static int __init rtas_fadump_build_cpu_notes(struct fw_dump *fadump_conf) } final_note(note_buf); - if (fdh) { - pr_debug("Updating elfcore header (%llx) with cpu notes\n", - fdh->elfcorehdr_addr); - fadump_update_elfcore_header(__va(fdh->elfcorehdr_addr)); - } + pr_debug("Updating elfcore header (%llx) with cpu notes\n", fadump_conf->elfcorehdr_addr); + fadump_update_elfcore_header((char *)fadump_conf->elfcorehdr_addr); return 0; error_out: @@ -389,57 +434,66 @@ error_out: } /* - * Validate and process the dump data stored by firmware before exporting - * it through '/proc/vmcore'. + * Validate and process the dump data stored by the firmware, and update + * the CPU notes of elfcorehdr. */ static int __init rtas_fadump_process(struct fw_dump *fadump_conf) { - struct fadump_crash_info_header *fdh; - int rc = 0; - if (!fdm_active || !fadump_conf->fadumphdr_addr) return -EINVAL; /* Check if the dump data is valid. */ - if ((be16_to_cpu(fdm_active->header.dump_status_flag) == - RTAS_FADUMP_ERROR_FLAG) || - (fdm_active->cpu_state_data.error_flags != 0) || - (fdm_active->rmr_region.error_flags != 0)) { - pr_err("Dump taken by platform is not valid\n"); - return -EINVAL; - } - if ((fdm_active->rmr_region.bytes_dumped != - fdm_active->rmr_region.source_len) || - !fdm_active->cpu_state_data.bytes_dumped) { - pr_err("Dump taken by platform is incomplete\n"); - return -EINVAL; - } + for (int i = 0; i < be16_to_cpu(fdm_active->header.dump_num_sections); i++) { + int type = be16_to_cpu(fdm_active->rgn[i].source_data_type); + int rc = 0; - /* Validate the fadump crash info header */ - fdh = __va(fadump_conf->fadumphdr_addr); - if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) { - pr_err("Crash info header is not valid.\n"); - return -EINVAL; + switch (type) { + case RTAS_FADUMP_CPU_STATE_DATA: + case RTAS_FADUMP_HPTE_REGION: + case RTAS_FADUMP_REAL_MODE_REGION: + if (fdm_active->rgn[i].error_flags != 0) { + pr_err("Dump taken by platform is not valid (%d)\n", i); + rc = -EINVAL; + } + if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len) { + pr_err("Dump taken by platform is incomplete (%d)\n", i); + rc = -EINVAL; + } + if (rc) { + pr_warn("Region type: %u src addr: 0x%llx dest addr: 0x%llx\n", + be16_to_cpu(fdm_active->rgn[i].source_data_type), + be64_to_cpu(fdm_active->rgn[i].source_address), + be64_to_cpu(fdm_active->rgn[i].destination_address)); + return rc; + } + break; + case RTAS_FADUMP_PARAM_AREA: + if (fdm_active->rgn[i].bytes_dumped != fdm_active->rgn[i].source_len || + fdm_active->rgn[i].error_flags != 0) { + pr_warn("Failed to process additional parameters! Proceeding anyway..\n"); + fadump_conf->param_area = 0; + } + break; + default: + /* + * If the first/crashed kernel added a new region type that the + * second/fadump kernel doesn't recognize, skip it and process + * assuming backward compatibility. + */ + pr_warn("Unknown region found: type: %u src addr: 0x%llx dest addr: 0x%llx\n", + be16_to_cpu(fdm_active->rgn[i].source_data_type), + be64_to_cpu(fdm_active->rgn[i].source_address), + be64_to_cpu(fdm_active->rgn[i].destination_address)); + break; + } } - rc = rtas_fadump_build_cpu_notes(fadump_conf); - if (rc) - return rc; - - /* - * We are done validating dump info and elfcore header is now ready - * to be exported. set elfcorehdr_addr so that vmcore module will - * export the elfcore header through '/proc/vmcore'. - */ - elfcorehdr_addr = fdh->elfcorehdr_addr; - - return 0; + return rtas_fadump_build_cpu_notes(fadump_conf); } static void rtas_fadump_region_show(struct fw_dump *fadump_conf, struct seq_file *m) { - const struct rtas_fadump_section *cpu_data_section; const struct rtas_fadump_mem_struct *fdm_ptr; if (fdm_active) @@ -447,27 +501,49 @@ static void rtas_fadump_region_show(struct fw_dump *fadump_conf, else fdm_ptr = &fdm; - cpu_data_section = &(fdm_ptr->cpu_state_data); - seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", - be64_to_cpu(cpu_data_section->destination_address), - be64_to_cpu(cpu_data_section->destination_address) + - be64_to_cpu(cpu_data_section->source_len) - 1, - be64_to_cpu(cpu_data_section->source_len), - be64_to_cpu(cpu_data_section->bytes_dumped)); - - seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", - be64_to_cpu(fdm_ptr->hpte_region.destination_address), - be64_to_cpu(fdm_ptr->hpte_region.destination_address) + - be64_to_cpu(fdm_ptr->hpte_region.source_len) - 1, - be64_to_cpu(fdm_ptr->hpte_region.source_len), - be64_to_cpu(fdm_ptr->hpte_region.bytes_dumped)); - - seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ", - be64_to_cpu(fdm_ptr->rmr_region.source_address), - be64_to_cpu(fdm_ptr->rmr_region.destination_address)); - seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n", - be64_to_cpu(fdm_ptr->rmr_region.source_len), - be64_to_cpu(fdm_ptr->rmr_region.bytes_dumped)); + + for (int i = 0; i < be16_to_cpu(fdm_ptr->header.dump_num_sections); i++) { + int type = be16_to_cpu(fdm_ptr->rgn[i].source_data_type); + + switch (type) { + case RTAS_FADUMP_CPU_STATE_DATA: + seq_printf(m, "CPU :[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", + be64_to_cpu(fdm_ptr->rgn[i].destination_address), + be64_to_cpu(fdm_ptr->rgn[i].destination_address) + + be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1, + be64_to_cpu(fdm_ptr->rgn[i].source_len), + be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped)); + break; + case RTAS_FADUMP_HPTE_REGION: + seq_printf(m, "HPTE:[%#016llx-%#016llx] %#llx bytes, Dumped: %#llx\n", + be64_to_cpu(fdm_ptr->rgn[i].destination_address), + be64_to_cpu(fdm_ptr->rgn[i].destination_address) + + be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1, + be64_to_cpu(fdm_ptr->rgn[i].source_len), + be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped)); + break; + case RTAS_FADUMP_REAL_MODE_REGION: + seq_printf(m, "DUMP: Src: %#016llx, Dest: %#016llx, ", + be64_to_cpu(fdm_ptr->rgn[i].source_address), + be64_to_cpu(fdm_ptr->rgn[i].destination_address)); + seq_printf(m, "Size: %#llx, Dumped: %#llx bytes\n", + be64_to_cpu(fdm_ptr->rgn[i].source_len), + be64_to_cpu(fdm_ptr->rgn[i].bytes_dumped)); + break; + case RTAS_FADUMP_PARAM_AREA: + seq_printf(m, "\n[%#016llx-%#016llx]: cmdline append: '%s'\n", + be64_to_cpu(fdm_ptr->rgn[i].destination_address), + be64_to_cpu(fdm_ptr->rgn[i].destination_address) + + be64_to_cpu(fdm_ptr->rgn[i].source_len) - 1, + (char *)__va(be64_to_cpu(fdm_ptr->rgn[i].destination_address))); + break; + default: + seq_printf(m, "Unknown region type %d : Src: %#016llx, Dest: %#016llx, ", + type, be64_to_cpu(fdm_ptr->rgn[i].source_address), + be64_to_cpu(fdm_ptr->rgn[i].destination_address)); + break; + } + } /* Dump is active. Show preserved area start address. */ if (fdm_active) { @@ -483,6 +559,20 @@ static void rtas_fadump_trigger(struct fadump_crash_info_header *fdh, rtas_os_term((char *)msg); } +/* FADUMP_MAX_MEM_REGS or lower */ +static int rtas_fadump_max_boot_mem_rgns(void) +{ + /* + * Version 1 of Kernel Assisted Dump Memory Structure (PAPR) supports 10 sections. + * With one each section taken for CPU state data & HPTE respectively, 8 sections + * can be used for boot memory regions. + * + * If new region(s) is(are) defined, maximum boot memory regions will decrease + * proportionally. + */ + return RTAS_FADUMP_MAX_BOOT_MEM_REGS; +} + static struct fadump_ops rtas_fadump_ops = { .fadump_init_mem_struct = rtas_fadump_init_mem_struct, .fadump_get_bootmem_min = rtas_fadump_get_bootmem_min, @@ -492,6 +582,7 @@ static struct fadump_ops rtas_fadump_ops = { .fadump_process = rtas_fadump_process, .fadump_region_show = rtas_fadump_region_show, .fadump_trigger = rtas_fadump_trigger, + .fadump_max_boot_mem_rgns = rtas_fadump_max_boot_mem_rgns, }; void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) @@ -508,9 +599,10 @@ void __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) if (!token) return; - fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token); - fadump_conf->ops = &rtas_fadump_ops; - fadump_conf->fadump_supported = 1; + fadump_conf->ibm_configure_kernel_dump = be32_to_cpu(*token); + fadump_conf->ops = &rtas_fadump_ops; + fadump_conf->fadump_supported = 1; + fadump_conf->param_area_supported = 1; /* Firmware supports 64-bit value for size, align it to pagesize. */ fadump_conf->max_copy_size = ALIGN_DOWN(U64_MAX, PAGE_SIZE); diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h index fd59bd7ca9c3..c109abf6befd 100644 --- a/arch/powerpc/platforms/pseries/rtas-fadump.h +++ b/arch/powerpc/platforms/pseries/rtas-fadump.h @@ -23,12 +23,24 @@ #define RTAS_FADUMP_HPTE_REGION 0x0002 #define RTAS_FADUMP_REAL_MODE_REGION 0x0011 +/* OS defined sections */ +#define RTAS_FADUMP_PARAM_AREA 0x0100 + /* Dump request flag */ #define RTAS_FADUMP_REQUEST_FLAG 0x00000001 /* Dump status flag */ #define RTAS_FADUMP_ERROR_FLAG 0x2000 +/* + * The Firmware Assisted Dump Memory structure supports a maximum of 10 sections + * in the dump memory structure. Presently, three sections are used for + * CPU state data, HPTE & Parameters area, while the remaining seven sections + * can be used for boot memory regions. + */ +#define MAX_SECTIONS 10 +#define RTAS_FADUMP_MAX_BOOT_MEM_REGS 7 + /* Kernel Dump section info */ struct rtas_fadump_section { __be32 request_flag; @@ -61,20 +73,15 @@ struct rtas_fadump_section_header { * Firmware Assisted dump memory structure. This structure is required for * registering future kernel dump with power firmware through rtas call. * - * No disk dump option. Hence disk dump path string section is not included. + * In version 1, the platform permits one section header, dump-disk path + * and ten sections. + * + * Note: No disk dump option. Hence disk dump path string section is not + * included. */ struct rtas_fadump_mem_struct { struct rtas_fadump_section_header header; - - /* Kernel dump sections */ - struct rtas_fadump_section cpu_state_data; - struct rtas_fadump_section hpte_region; - - /* - * TODO: Extend multiple boot memory regions support in the kernel - * for this platform. - */ - struct rtas_fadump_section rmr_region; + struct rtas_fadump_section rgn[MAX_SECTIONS]; }; /* diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index 71d52a670d95..ba3fb7a7f2ea 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -228,7 +228,7 @@ static irqreturn_t pseries_vas_irq_handler(int irq, void *data) struct pseries_vas_window *txwin = data; /* - * The thread hanlder will process this interrupt if it is + * The thread handler will process this interrupt if it is * already running. */ atomic_inc(&txwin->pending_faults); diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 90ff85c879bf..b2babfdbc40b 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1592,13 +1592,9 @@ static int vio_hotplug(const struct device *dev, struct kobj_uevent_env *env) const char *cp; dn = dev->of_node; - if (!dn) - return -ENODEV; - cp = of_get_property(dn, "compatible", NULL); - if (!cp) - return -ENODEV; + if (dn && (cp = of_get_property(dn, "compatible", NULL))) + add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp); - add_uevent_var(env, "MODALIAS=vio:T%sS%s", vio_dev->type, cp); return 0; } diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 9cb1d029511a..24a177d164f1 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -1,7 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) - mpic-msi-obj-$(CONFIG_PCI_MSI) += mpic_msi.o mpic_u3msi.o obj-$(CONFIG_MPIC) += mpic.o $(mpic-msi-obj-y) obj-$(CONFIG_MPIC_TIMER) += mpic_timer.o diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 98096bbfd62e..c0d10c149661 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -24,7 +24,6 @@ #include <linux/suspend.h> #include <linux/memblock.h> #include <linux/gfp.h> -#include <linux/kmemleak.h> #include <linux/of_address.h> #include <asm/io.h> #include <asm/iommu.h> @@ -243,9 +242,6 @@ static void __init allocate_dart(void) if (!dart_tablebase) panic("Failed to allocate 16MB below 2GB for DART table\n"); - /* There is no point scanning the DART space for leaks*/ - kmemleak_no_scan((void *)dart_tablebase); - /* Allocate a spare page to map all invalid DART pages. We need to do * that to work around what looks like a problem with the HT bridge * prefetching into invalid pages and corrupting data diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index 39186ad6b3c3..3dabc9621810 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -77,7 +77,7 @@ struct gtm { static LIST_HEAD(gtms); /** - * gtm_get_timer - request GTM timer to use it with the rest of GTM API + * gtm_get_timer16 - request GTM timer to use it with the rest of GTM API * Context: non-IRQ * * This function reserves GTM timer for later use. It returns gtm_timer @@ -110,7 +110,7 @@ struct gtm_timer *gtm_get_timer16(void) EXPORT_SYMBOL(gtm_get_timer16); /** - * gtm_get_specific_timer - request specific GTM timer + * gtm_get_specific_timer16 - request specific GTM timer * @gtm: specific GTM, pass here GTM's device_node->data * @timer: specific timer number, Timer1 is 0. * Context: non-IRQ @@ -260,7 +260,7 @@ int gtm_set_timer16(struct gtm_timer *tmr, unsigned long usec, bool reload) EXPORT_SYMBOL(gtm_set_timer16); /** - * gtm_set_exact_utimer16 - (re)set 16 bits timer + * gtm_set_exact_timer16 - (re)set 16 bits timer * @tmr: pointer to the gtm_timer structure obtained from gtm_get_timer * @usec: timer interval in microseconds * @reload: if set, the timer will reset upon expiry rather than diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 8e6c84df4ca1..e205135ae1fe 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -564,10 +564,12 @@ static const struct fsl_msi_feature ipic_msi_feature = { .msiir_offset = 0x38, }; +#ifdef CONFIG_EPAPR_PARAVIRT static const struct fsl_msi_feature vmpic_msi_feature = { .fsl_pic_ip = FSL_PIC_IP_VMPIC, .msiir_offset = 0, }; +#endif static const struct of_device_id fsl_of_msi_ids[] = { { diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index a289cb97c1d7..fa01818c1972 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -383,7 +383,7 @@ static unsigned int xive_get_irq(void) * CPU. * * If we find that there is indeed more in there, we call - * force_external_irq_replay() to make Linux synthetize an + * force_external_irq_replay() to make Linux synthesize an * external interrupt on the next call to local_irq_restore(). */ static void xive_do_queue_eoi(struct xive_cpu *xc) @@ -874,7 +874,7 @@ static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state) * * This also tells us that it's in flight to a host queue * or has already been fetched but hasn't been EOIed yet - * by the host. This it's potentially using up a host + * by the host. Thus it's potentially using up a host * queue slot. This is important to know because as long * as this is the case, we must not hard-unmask it when * "returning" that interrupt to the host. diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index f1c0fa6ece21..517b963e3e6a 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -415,7 +415,7 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc) return; } - /* Grab it's CAM value */ + /* Grab its CAM value */ rc = opal_xive_get_vp_info(vp, NULL, &vp_cam_be, NULL, NULL); if (rc) { pr_err("Failed to get pool VP info CPU %d\n", cpu); diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 682c7c0a6f77..d778011060a8 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -10,8 +10,6 @@ KCSAN_SANITIZE := n # Disable ftrace for the entire directory ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE) -ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) - # Clang stores addresses on the stack causing the frame size to blow # out. See https://github.com/ClangBuiltLinux/linux/issues/252 ccflags-$(CONFIG_CC_IS_CLANG) += -Wframe-larger-than=4096 diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index d79d6633f333..bd4813bad317 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -1350,7 +1350,7 @@ static int cpu_cmd(void) } termch = cpu; - if (!scanhex(&cpu)) { + if (!scanhex(&cpu) || cpu >= num_possible_cpus()) { /* print cpus waiting or in xmon */ printf("cpus stopped:"); last_cpu = first_cpu = NR_CPUS; @@ -2772,7 +2772,7 @@ static void dump_pacas(void) termch = c; /* Put c back, it wasn't 'a' */ - if (scanhex(&num)) + if (scanhex(&num) && num < num_possible_cpus()) dump_one_paca(num); else dump_one_paca(xmon_owner); @@ -2845,7 +2845,7 @@ static void dump_xives(void) termch = c; /* Put c back, it wasn't 'a' */ - if (scanhex(&num)) + if (scanhex(&num) && num < num_possible_cpus()) dump_one_xive(num); else dump_one_xive(xmon_owner); |