* Re: [PATCH v5 08/27] irq_domain: Move irq_domain code from powerpc to kernel/irq
From: Grant Likely @ 2012-02-16 13:23 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-9-git-send-email-grant.likely@secretlab.ca>
On Thu, Feb 16, 2012 at 2:09 AM, Grant Likely <grant.likely@secretlab.ca> w=
rote:
> This patch only moves the code. =A0It doesn't make any changes, and the
> code is still only compiled for powerpc. =A0Follow-on patches will genera=
lize
> the code for other architectures.
>
> Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Milton Miller <miltonm@bga.com>
> Tested-by: Olof Johansson <olof@lixom.net>
> ---
> +unsigned int irq_find_mapping(struct irq_domain *host,
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 irq_hw_number_t=
hwirq)
> +{
> + =A0 =A0 =A0 unsigned int i;
> + =A0 =A0 =A0 unsigned int hint =3D hwirq % irq_virq_count;
> +
> + =A0 =A0 =A0 /* Look for default host if nececssary */
> + =A0 =A0 =A0 if (host =3D=3D NULL)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 host =3D irq_default_host;
> + =A0 =A0 =A0 if (host =3D=3D NULL)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return NO_IRQ;
> +
> + =A0 =A0 =A0 /* legacy -> bail early */
> + =A0 =A0 =A0 if (host->revmap_type =3D=3D IRQ_DOMAIN_MAP_LEGACY)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 return hwirq;
> +
> + =A0 =A0 =A0 /* Slow path does a linear search of the map */
> + =A0 =A0 =A0 if (hint =3D=3D 0)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 hint =3D 1;
> + =A0 =A0 =A0 i =3D hint;
> + =A0 =A0 =A0 do {
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 struct irq_data *data =3D irq_get_irq_data(=
i);
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 if (data && (data->domain =3D=3D host) && (=
data->hwirq =3D=3D hwirq))
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 return i;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 i++;
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 if (i >=3D irq_virq_count)
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 i =3D 1
Typo on this line; missing semicolon. Fixed in my tree now.
g.
^ permalink raw reply
* [PATCH 2/2] powerpc/85xx: add a 36-bit corenet default config
From: Li Yang @ 2012-02-16 12:10 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <1329394210-1014-1-git-send-email-leoli@freescale.com>
This default config should be used by platforms that only
provides 36-bit software support in tree, such as P3041DS,
P3060QDS, P4080DS, P5020DS, and etc.
Signed-off-by: Li Yang <leoli@freescale.com>
---
arch/powerpc/configs/corenet36_smp_defconfig | 185 ++++++++++++++++++++++++++
1 files changed, 185 insertions(+), 0 deletions(-)
create mode 100644 arch/powerpc/configs/corenet36_smp_defconfig
diff --git a/arch/powerpc/configs/corenet36_smp_defconfig b/arch/powerpc/configs/corenet36_smp_defconfig
new file mode 100644
index 0000000..9765b4d
--- /dev/null
+++ b/arch/powerpc/configs/corenet36_smp_defconfig
@@ -0,0 +1,185 @@
+CONFIG_PPC_85xx=y
+CONFIG_PHYS_64BIT=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=8
+CONFIG_EXPERIMENTAL=y
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_AUDIT=y
+CONFIG_SPARSE_IRQ=y
+CONFIG_RCU_TRACE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=14
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_EMBEDDED=y
+CONFIG_PERF_EVENTS=y
+CONFIG_SLAB=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+# CONFIG_BLK_DEV_BSG is not set
+CONFIG_P2041_RDB=y
+CONFIG_P3041_DS=y
+CONFIG_P3060_QDS=y
+CONFIG_P4080_DS=y
+CONFIG_P5020_DS=y
+CONFIG_HIGHMEM=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_BINFMT_MISC=m
+CONFIG_KEXEC=y
+CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_FSL_LBC=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+# CONFIG_PCIEASPM is not set
+CONFIG_RAPIDIO=y
+CONFIG_FSL_RIO=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_XFRM_USER=y
+CONFIG_XFRM_SUB_POLICY=y
+CONFIG_XFRM_STATISTICS=y
+CONFIG_NET_KEY=y
+CONFIG_NET_KEY_MIGRATE=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_ROUTE_MULTIPATH=y
+CONFIG_IP_ROUTE_VERBOSE=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NET_IPIP=y
+CONFIG_IP_MROUTE=y
+CONFIG_IP_PIMSM_V1=y
+CONFIG_IP_PIMSM_V2=y
+CONFIG_ARPD=y
+CONFIG_INET_AH=y
+CONFIG_INET_ESP=y
+CONFIG_INET_IPCOMP=y
+# CONFIG_INET_LRO is not set
+CONFIG_IPV6=y
+CONFIG_IP_SCTP=m
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLOCK=y
+CONFIG_MTD_CFI=y
+CONFIG_MTD_CFI_AMDSTD=y
+CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_M25P80=y
+CONFIG_PROC_DEVICETREE=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_SIZE=131072
+CONFIG_MISC_DEVICES=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_CHR_DEV_ST=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_CHR_DEV_SG=y
+CONFIG_SCSI_MULTI_LUN=y
+CONFIG_SCSI_LOGGING=y
+CONFIG_SCSI_SYM53C8XX_2=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_FSL=y
+CONFIG_SATA_SIL24=y
+CONFIG_SATA_SIL=y
+CONFIG_PATA_SIL680=y
+CONFIG_NETDEVICES=y
+CONFIG_FSL_PQ_MDIO=y
+CONFIG_E1000=y
+CONFIG_E1000E=y
+CONFIG_VITESSE_PHY=y
+CONFIG_FIXED_PHY=y
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_LEGACY_PTYS is not set
+CONFIG_PPC_EPAPR_HV_BYTECHAN=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_EXTENDED=y
+CONFIG_SERIAL_8250_MANY_PORTS=y
+CONFIG_SERIAL_8250_DETECT_IRQ=y
+CONFIG_SERIAL_8250_RSA=y
+CONFIG_HW_RANDOM=y
+CONFIG_NVRAM=y
+CONFIG_I2C=y
+CONFIG_I2C_MPC=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
+CONFIG_SPI_FSL_SPI=y
+CONFIG_SPI_FSL_ESPI=y
+# CONFIG_HWMON is not set
+CONFIG_VIDEO_OUTPUT_CONTROL=y
+CONFIG_USB_HID=m
+CONFIG_USB=y
+CONFIG_USB_DEVICEFS=y
+CONFIG_USB_MON=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_FSL=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
+CONFIG_USB_OHCI_HCD_PPC_OF_LE=y
+CONFIG_USB_STORAGE=y
+CONFIG_MMC=y
+CONFIG_MMC_SDHCI=y
+CONFIG_EDAC=y
+CONFIG_EDAC_MM_EDAC=y
+CONFIG_EDAC_MPC85XX=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS3232=y
+CONFIG_RTC_DRV_CMOS=y
+CONFIG_UIO=y
+CONFIG_STAGING=y
+CONFIG_VIRT_DRIVERS=y
+CONFIG_FSL_HV_MANAGER=y
+CONFIG_EXT2_FS=y
+CONFIG_EXT3_FS=y
+# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set
+CONFIG_ISO9660_FS=m
+CONFIG_JOLIET=y
+CONFIG_ZISOFS=y
+CONFIG_UDF_FS=m
+CONFIG_MSDOS_FS=m
+CONFIG_VFAT_FS=y
+CONFIG_NTFS_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_HUGETLBFS=y
+CONFIG_JFFS2_FS=y
+CONFIG_CRAMFS=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V3=y
+CONFIG_NFS_V4=y
+CONFIG_ROOT_NFS=y
+CONFIG_NFSD=m
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
+CONFIG_NLS_ISO8859_1=y
+CONFIG_NLS_UTF8=m
+CONFIG_MAGIC_SYSRQ=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEBUG_INFO=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_CRYPTO_NULL=y
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_MD4=y
+CONFIG_CRYPTO_SHA256=y
+CONFIG_CRYPTO_SHA512=y
+CONFIG_CRYPTO_AES=y
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+CONFIG_CRYPTO_DEV_FSL_CAAM=y
--
1.5.4.3
^ permalink raw reply related
* [PATCH 1/2] powerpc/85xx: fix problem that prevents PHYS_64BIT from configurable
From: Li Yang @ 2012-02-16 12:10 UTC (permalink / raw)
To: linuxppc-dev
Fix the problem that large physical address support cannot be
disabled when some platforms which only provides 36-bit support
are selected. According to the philosophy of kernel config
enabling a platform support doesn't mean the kernel is only
running on that platform. Remove the auto selection of PHYS_64BIT
option for these platforms. They will need to use a 36bit default
config that selects PHYS_64BIT explicitly.
The reason why we need to keep PHYS_64BIT option configurable is
that enabling it cause negative performance impact on various
aspects like TLB miss and physical address manipulating. We should
not enable it unless really needed, e.g. use large memory of 4GB
or bigger.
Signed-off-by: Li Yang <leoli@freescale.com>
---
arch/powerpc/platforms/85xx/Kconfig | 6 ------
1 files changed, 0 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index d7946be..d9bc0bd 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -80,7 +80,6 @@ config P1010_RDB
config P1022_DS
bool "Freescale P1022 DS"
select DEFAULT_UIMAGE
- select PHYS_64BIT # The DTS has 36-bit addresses
select SWIOTLB
help
This option enables support for the Freescale P1022DS reference board.
@@ -175,7 +174,6 @@ config P2041_RDB
bool "Freescale P2041 RDB"
select DEFAULT_UIMAGE
select PPC_E500MC
- select PHYS_64BIT
select SWIOTLB
select ARCH_REQUIRE_GPIOLIB
select GPIO_MPC8XXX
@@ -188,7 +186,6 @@ config P3041_DS
bool "Freescale P3041 DS"
select DEFAULT_UIMAGE
select PPC_E500MC
- select PHYS_64BIT
select SWIOTLB
select ARCH_REQUIRE_GPIOLIB
select GPIO_MPC8XXX
@@ -201,7 +198,6 @@ config P3060_QDS
bool "Freescale P3060 QDS"
select DEFAULT_UIMAGE
select PPC_E500MC
- select PHYS_64BIT
select SWIOTLB
select GPIO_MPC8XXX
select HAS_RAPIDIO
@@ -213,7 +209,6 @@ config P4080_DS
bool "Freescale P4080 DS"
select DEFAULT_UIMAGE
select PPC_E500MC
- select PHYS_64BIT
select SWIOTLB
select ARCH_REQUIRE_GPIOLIB
select GPIO_MPC8XXX
@@ -229,7 +224,6 @@ config P5020_DS
select DEFAULT_UIMAGE
select E500
select PPC_E500MC
- select PHYS_64BIT
select SWIOTLB
select ARCH_REQUIRE_GPIOLIB
select GPIO_MPC8XXX
--
1.5.4.3
^ permalink raw reply related
* [RFC PATCH v7 10/10] fadump: Remove the phyp assisted dump code.
From: Mahesh J Salgaonkar @ 2012-02-16 11:15 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Remove the phyp assisted dump implementation which is not is use.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
Documentation/powerpc/phyp-assisted-dump.txt | 127 ------
arch/powerpc/Kconfig | 10 -
arch/powerpc/include/asm/phyp_dump.h | 47 --
arch/powerpc/kernel/prom.c | 87 ----
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/phyp_dump.c | 513 --------------------------
6 files changed, 0 insertions(+), 785 deletions(-)
delete mode 100644 Documentation/powerpc/phyp-assisted-dump.txt
delete mode 100644 arch/powerpc/include/asm/phyp_dump.h
delete mode 100644 arch/powerpc/platforms/pseries/phyp_dump.c
diff --git a/Documentation/powerpc/phyp-assisted-dump.txt b/Documentation/powerpc/phyp-assisted-dump.txt
deleted file mode 100644
index ad34020..0000000
--- a/Documentation/powerpc/phyp-assisted-dump.txt
+++ /dev/null
@@ -1,127 +0,0 @@
-
- Hypervisor-Assisted Dump
- ------------------------
- November 2007
-
-The goal of hypervisor-assisted dump is to enable the dump of
-a crashed system, and to do so from a fully-reset system, and
-to minimize the total elapsed time until the system is back
-in production use.
-
-As compared to kdump or other strategies, hypervisor-assisted
-dump offers several strong, practical advantages:
-
--- Unlike kdump, the system has been reset, and loaded
- with a fresh copy of the kernel. In particular,
- PCI and I/O devices have been reinitialized and are
- in a clean, consistent state.
--- As the dump is performed, the dumped memory becomes
- immediately available to the system for normal use.
--- After the dump is completed, no further reboots are
- required; the system will be fully usable, and running
- in its normal, production mode on its normal kernel.
-
-The above can only be accomplished by coordination with,
-and assistance from the hypervisor. The procedure is
-as follows:
-
--- When a system crashes, the hypervisor will save
- the low 256MB of RAM to a previously registered
- save region. It will also save system state, system
- registers, and hardware PTE's.
-
--- After the low 256MB area has been saved, the
- hypervisor will reset PCI and other hardware state.
- It will *not* clear RAM. It will then launch the
- bootloader, as normal.
-
--- The freshly booted kernel will notice that there
- is a new node (ibm,dump-kernel) in the device tree,
- indicating that there is crash data available from
- a previous boot. It will boot into only 256MB of RAM,
- reserving the rest of system memory.
-
--- Userspace tools will parse /sys/kernel/release_region
- and read /proc/vmcore to obtain the contents of memory,
- which holds the previous crashed kernel. The userspace
- tools may copy this info to disk, or network, nas, san,
- iscsi, etc. as desired.
-
- For Example: the values in /sys/kernel/release-region
- would look something like this (address-range pairs).
- CPU:0x177fee000-0x10000: HPTE:0x177ffe020-0x1000: /
- DUMP:0x177fff020-0x10000000, 0x10000000-0x16F1D370A
-
--- As the userspace tools complete saving a portion of
- dump, they echo an offset and size to
- /sys/kernel/release_region to release the reserved
- memory back to general use.
-
- An example of this is:
- "echo 0x40000000 0x10000000 > /sys/kernel/release_region"
- which will release 256MB at the 1GB boundary.
-
-Please note that the hypervisor-assisted dump feature
-is only available on Power6-based systems with recent
-firmware versions.
-
-Implementation details:
-----------------------
-
-During boot, a check is made to see if firmware supports
-this feature on this particular machine. If it does, then
-we check to see if a active dump is waiting for us. If yes
-then everything but 256 MB of RAM is reserved during early
-boot. This area is released once we collect a dump from user
-land scripts that are run. If there is dump data, then
-the /sys/kernel/release_region file is created, and
-the reserved memory is held.
-
-If there is no waiting dump data, then only the highest
-256MB of the ram is reserved as a scratch area. This area
-is *not* released: this region will be kept permanently
-reserved, so that it can act as a receptacle for a copy
-of the low 256MB in the case a crash does occur. See,
-however, "open issues" below, as to whether
-such a reserved region is really needed.
-
-Currently the dump will be copied from /proc/vmcore to a
-a new file upon user intervention. The starting address
-to be read and the range for each data point in provided
-in /sys/kernel/release_region.
-
-The tools to examine the dump will be same as the ones
-used for kdump.
-
-General notes:
---------------
-Security: please note that there are potential security issues
-with any sort of dump mechanism. In particular, plaintext
-(unencrypted) data, and possibly passwords, may be present in
-the dump data. Userspace tools must take adequate precautions to
-preserve security.
-
-Open issues/ToDo:
-------------
- o The various code paths that tell the hypervisor that a crash
- occurred, vs. it simply being a normal reboot, should be
- reviewed, and possibly clarified/fixed.
-
- o Instead of using /sys/kernel, should there be a /sys/dump
- instead? There is a dump_subsys being created by the s390 code,
- perhaps the pseries code should use a similar layout as well.
-
- o Is reserving a 256MB region really required? The goal of
- reserving a 256MB scratch area is to make sure that no
- important crash data is clobbered when the hypervisor
- save low mem to the scratch area. But, if one could assure
- that nothing important is located in some 256MB area, then
- it would not need to be reserved. Something that can be
- improved in subsequent versions.
-
- o Still working the kdump team to integrate this with kdump,
- some work remains but this would not affect the current
- patches.
-
- o Still need to write a shell script, to copy the dump away.
- Currently I am parsing it manually.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index afa4dab..c713111 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -376,16 +376,6 @@ config CRASH_DUMP
The same kernel binary can be used as production kernel and dump
capture kernel.
-config PHYP_DUMP
- bool "Hypervisor-assisted dump (EXPERIMENTAL)"
- depends on PPC_PSERIES && EXPERIMENTAL
- help
- Hypervisor-assisted dump is meant to be a kdump replacement
- offering robustness and speed not possible without system
- hypervisor assistance.
-
- If unsure, say "N"
-
config FA_DUMP
bool "Firmware-assisted dump"
depends on PPC64 && PPC_RTAS && CRASH_DUMP
diff --git a/arch/powerpc/include/asm/phyp_dump.h b/arch/powerpc/include/asm/phyp_dump.h
deleted file mode 100644
index fa74c6c..0000000
--- a/arch/powerpc/include/asm/phyp_dump.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * Hypervisor-assisted dump
- *
- * Linas Vepstas, Manish Ahuja 2008
- * Copyright 2008 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef _PPC64_PHYP_DUMP_H
-#define _PPC64_PHYP_DUMP_H
-
-#ifdef CONFIG_PHYP_DUMP
-
-/* The RMR region will be saved for later dumping
- * whenever the kernel crashes. Set this to 256MB. */
-#define PHYP_DUMP_RMR_START 0x0
-#define PHYP_DUMP_RMR_END (1UL<<28)
-
-struct phyp_dump {
- /* Memory that is reserved during very early boot. */
- unsigned long init_reserve_start;
- unsigned long init_reserve_size;
- /* cmd line options during boot */
- unsigned long reserve_bootvar;
- unsigned long phyp_dump_at_boot;
- /* Check status during boot if dump supported, active & present*/
- unsigned long phyp_dump_configured;
- unsigned long phyp_dump_is_active;
- /* store cpu & hpte size */
- unsigned long cpu_state_size;
- unsigned long hpte_region_size;
- /* previous scratch area values */
- unsigned long reserved_scratch_addr;
- unsigned long reserved_scratch_size;
-};
-
-extern struct phyp_dump *phyp_dump_info;
-
-int early_init_dt_scan_phyp_dump(unsigned long node,
- const char *uname, int depth, void *data);
-
-#endif /* CONFIG_PHYP_DUMP */
-#endif /* _PPC64_PHYP_DUMP_H */
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 70222b3..89e850a 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -52,7 +52,6 @@
#include <asm/machdep.h>
#include <asm/pSeries_reconfig.h>
#include <asm/pci-bridge.h>
-#include <asm/phyp_dump.h>
#include <asm/kexec.h>
#include <asm/opal.h>
#include <asm/fadump.h>
@@ -616,86 +615,6 @@ static void __init early_reserve_mem(void)
}
}
-#ifdef CONFIG_PHYP_DUMP
-/**
- * phyp_dump_calculate_reserve_size() - reserve variable boot area 5% or arg
- *
- * Function to find the largest size we need to reserve
- * during early boot process.
- *
- * It either looks for boot param and returns that OR
- * returns larger of 256 or 5% rounded down to multiples of 256MB.
- *
- */
-static inline unsigned long phyp_dump_calculate_reserve_size(void)
-{
- unsigned long tmp;
-
- if (phyp_dump_info->reserve_bootvar)
- return phyp_dump_info->reserve_bootvar;
-
- /* divide by 20 to get 5% of value */
- tmp = memblock_end_of_DRAM();
- do_div(tmp, 20);
-
- /* round it down in multiples of 256 */
- tmp = tmp & ~0x0FFFFFFFUL;
-
- return (tmp > PHYP_DUMP_RMR_END ? tmp : PHYP_DUMP_RMR_END);
-}
-
-/**
- * phyp_dump_reserve_mem() - reserve all not-yet-dumped mmemory
- *
- * This routine may reserve memory regions in the kernel only
- * if the system is supported and a dump was taken in last
- * boot instance or if the hardware is supported and the
- * scratch area needs to be setup. In other instances it returns
- * without reserving anything. The memory in case of dump being
- * active is freed when the dump is collected (by userland tools).
- */
-static void __init phyp_dump_reserve_mem(void)
-{
- unsigned long base, size;
- unsigned long variable_reserve_size;
-
- if (!phyp_dump_info->phyp_dump_configured) {
- printk(KERN_ERR "Phyp-dump not supported on this hardware\n");
- return;
- }
-
- if (!phyp_dump_info->phyp_dump_at_boot) {
- printk(KERN_INFO "Phyp-dump disabled at boot time\n");
- return;
- }
-
- variable_reserve_size = phyp_dump_calculate_reserve_size();
-
- if (phyp_dump_info->phyp_dump_is_active) {
- /* Reserve *everything* above RMR.Area freed by userland tools*/
- base = variable_reserve_size;
- size = memblock_end_of_DRAM() - base;
-
- /* XXX crashed_ram_end is wrong, since it may be beyond
- * the memory_limit, it will need to be adjusted. */
- memblock_reserve(base, size);
-
- phyp_dump_info->init_reserve_start = base;
- phyp_dump_info->init_reserve_size = size;
- } else {
- size = phyp_dump_info->cpu_state_size +
- phyp_dump_info->hpte_region_size +
- variable_reserve_size;
- base = memblock_end_of_DRAM() - size;
- memblock_reserve(base, size);
- phyp_dump_info->init_reserve_start = base;
- phyp_dump_info->init_reserve_size = size;
- }
-}
-#else
-static inline void __init phyp_dump_reserve_mem(void) {}
-#endif /* CONFIG_PHYP_DUMP && CONFIG_PPC_RTAS */
-
void __init early_init_devtree(void *params)
{
phys_addr_t limit;
@@ -715,11 +634,6 @@ void __init early_init_devtree(void *params)
of_scan_flat_dt(early_init_dt_scan_opal, NULL);
#endif
-#ifdef CONFIG_PHYP_DUMP
- /* scan tree to see if dump occurred during last boot */
- of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
-#endif
-
#ifdef CONFIG_FA_DUMP
/* scan tree to see if dump is active during last boot */
of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
@@ -765,7 +679,6 @@ void __init early_init_devtree(void *params)
#endif
reserve_crashkernel();
early_reserve_mem();
- phyp_dump_reserve_mem();
/*
* Ensure that total memory size is page-aligned, because otherwise
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index 236db46..67b3e6e 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += hotplug-memory.o
obj-$(CONFIG_HVC_CONSOLE) += hvconsole.o
obj-$(CONFIG_HVCS) += hvcserver.o
obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o
-obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o
obj-$(CONFIG_CMM) += cmm.o
obj-$(CONFIG_DTL) += dtl.o
obj-$(CONFIG_IO_EVENT_IRQ) += io_event_irq.o
diff --git a/arch/powerpc/platforms/pseries/phyp_dump.c b/arch/powerpc/platforms/pseries/phyp_dump.c
deleted file mode 100644
index 6e7742d..0000000
--- a/arch/powerpc/platforms/pseries/phyp_dump.c
+++ /dev/null
@@ -1,513 +0,0 @@
-/*
- * Hypervisor-assisted dump
- *
- * Linas Vepstas, Manish Ahuja 2008
- * Copyright 2008 IBM Corp.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- */
-
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/kobject.h>
-#include <linux/mm.h>
-#include <linux/of.h>
-#include <linux/pfn.h>
-#include <linux/swap.h>
-#include <linux/sysfs.h>
-
-#include <asm/page.h>
-#include <asm/phyp_dump.h>
-#include <asm/machdep.h>
-#include <asm/prom.h>
-#include <asm/rtas.h>
-
-/* Variables, used to communicate data between early boot and late boot */
-static struct phyp_dump phyp_dump_vars;
-struct phyp_dump *phyp_dump_info = &phyp_dump_vars;
-
-static int ibm_configure_kernel_dump;
-/* ------------------------------------------------- */
-/* RTAS interfaces to declare the dump regions */
-
-struct dump_section {
- u32 dump_flags;
- u16 source_type;
- u16 error_flags;
- u64 source_address;
- u64 source_length;
- u64 length_copied;
- u64 destination_address;
-};
-
-struct phyp_dump_header {
- u32 version;
- u16 num_of_sections;
- u16 status;
-
- u32 first_offset_section;
- u32 dump_disk_section;
- u64 block_num_dd;
- u64 num_of_blocks_dd;
- u32 offset_dd;
- u32 maxtime_to_auto;
- /* No dump disk path string used */
-
- struct dump_section cpu_data;
- struct dump_section hpte_data;
- struct dump_section kernel_data;
-};
-
-/* The dump header *must be* in low memory, so .bss it */
-static struct phyp_dump_header phdr;
-
-#define NUM_DUMP_SECTIONS 3
-#define DUMP_HEADER_VERSION 0x1
-#define DUMP_REQUEST_FLAG 0x1
-#define DUMP_SOURCE_CPU 0x0001
-#define DUMP_SOURCE_HPTE 0x0002
-#define DUMP_SOURCE_RMO 0x0011
-#define DUMP_ERROR_FLAG 0x2000
-#define DUMP_TRIGGERED 0x4000
-#define DUMP_PERFORMED 0x8000
-
-
-/**
- * init_dump_header() - initialize the header declaring a dump
- * Returns: length of dump save area.
- *
- * When the hypervisor saves crashed state, it needs to put
- * it somewhere. The dump header tells the hypervisor where
- * the data can be saved.
- */
-static unsigned long init_dump_header(struct phyp_dump_header *ph)
-{
- unsigned long addr_offset = 0;
-
- /* Set up the dump header */
- ph->version = DUMP_HEADER_VERSION;
- ph->num_of_sections = NUM_DUMP_SECTIONS;
- ph->status = 0;
-
- ph->first_offset_section =
- (u32)offsetof(struct phyp_dump_header, cpu_data);
- ph->dump_disk_section = 0;
- ph->block_num_dd = 0;
- ph->num_of_blocks_dd = 0;
- ph->offset_dd = 0;
-
- ph->maxtime_to_auto = 0; /* disabled */
-
- /* The first two sections are mandatory */
- ph->cpu_data.dump_flags = DUMP_REQUEST_FLAG;
- ph->cpu_data.source_type = DUMP_SOURCE_CPU;
- ph->cpu_data.source_address = 0;
- ph->cpu_data.source_length = phyp_dump_info->cpu_state_size;
- ph->cpu_data.destination_address = addr_offset;
- addr_offset += phyp_dump_info->cpu_state_size;
-
- ph->hpte_data.dump_flags = DUMP_REQUEST_FLAG;
- ph->hpte_data.source_type = DUMP_SOURCE_HPTE;
- ph->hpte_data.source_address = 0;
- ph->hpte_data.source_length = phyp_dump_info->hpte_region_size;
- ph->hpte_data.destination_address = addr_offset;
- addr_offset += phyp_dump_info->hpte_region_size;
-
- /* This section describes the low kernel region */
- ph->kernel_data.dump_flags = DUMP_REQUEST_FLAG;
- ph->kernel_data.source_type = DUMP_SOURCE_RMO;
- ph->kernel_data.source_address = PHYP_DUMP_RMR_START;
- ph->kernel_data.source_length = PHYP_DUMP_RMR_END;
- ph->kernel_data.destination_address = addr_offset;
- addr_offset += ph->kernel_data.source_length;
-
- return addr_offset;
-}
-
-static void print_dump_header(const struct phyp_dump_header *ph)
-{
-#ifdef DEBUG
- if (ph == NULL)
- return;
-
- printk(KERN_INFO "dump header:\n");
- /* setup some ph->sections required */
- printk(KERN_INFO "version = %d\n", ph->version);
- printk(KERN_INFO "Sections = %d\n", ph->num_of_sections);
- printk(KERN_INFO "Status = 0x%x\n", ph->status);
-
- /* No ph->disk, so all should be set to 0 */
- printk(KERN_INFO "Offset to first section 0x%x\n",
- ph->first_offset_section);
- printk(KERN_INFO "dump disk sections should be zero\n");
- printk(KERN_INFO "dump disk section = %d\n", ph->dump_disk_section);
- printk(KERN_INFO "block num = %lld\n", ph->block_num_dd);
- printk(KERN_INFO "number of blocks = %lld\n", ph->num_of_blocks_dd);
- printk(KERN_INFO "dump disk offset = %d\n", ph->offset_dd);
- printk(KERN_INFO "Max auto time= %d\n", ph->maxtime_to_auto);
-
- /*set cpu state and hpte states as well scratch pad area */
- printk(KERN_INFO " CPU AREA\n");
- printk(KERN_INFO "cpu dump_flags =%d\n", ph->cpu_data.dump_flags);
- printk(KERN_INFO "cpu source_type =%d\n", ph->cpu_data.source_type);
- printk(KERN_INFO "cpu error_flags =%d\n", ph->cpu_data.error_flags);
- printk(KERN_INFO "cpu source_address =%llx\n",
- ph->cpu_data.source_address);
- printk(KERN_INFO "cpu source_length =%llx\n",
- ph->cpu_data.source_length);
- printk(KERN_INFO "cpu length_copied =%llx\n",
- ph->cpu_data.length_copied);
-
- printk(KERN_INFO " HPTE AREA\n");
- printk(KERN_INFO "HPTE dump_flags =%d\n", ph->hpte_data.dump_flags);
- printk(KERN_INFO "HPTE source_type =%d\n", ph->hpte_data.source_type);
- printk(KERN_INFO "HPTE error_flags =%d\n", ph->hpte_data.error_flags);
- printk(KERN_INFO "HPTE source_address =%llx\n",
- ph->hpte_data.source_address);
- printk(KERN_INFO "HPTE source_length =%llx\n",
- ph->hpte_data.source_length);
- printk(KERN_INFO "HPTE length_copied =%llx\n",
- ph->hpte_data.length_copied);
-
- printk(KERN_INFO " SRSD AREA\n");
- printk(KERN_INFO "SRSD dump_flags =%d\n", ph->kernel_data.dump_flags);
- printk(KERN_INFO "SRSD source_type =%d\n", ph->kernel_data.source_type);
- printk(KERN_INFO "SRSD error_flags =%d\n", ph->kernel_data.error_flags);
- printk(KERN_INFO "SRSD source_address =%llx\n",
- ph->kernel_data.source_address);
- printk(KERN_INFO "SRSD source_length =%llx\n",
- ph->kernel_data.source_length);
- printk(KERN_INFO "SRSD length_copied =%llx\n",
- ph->kernel_data.length_copied);
-#endif
-}
-
-static ssize_t show_phyp_dump_active(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
-
- /* create filesystem entry so kdump is phyp-dump aware */
- return sprintf(buf, "%lx\n", phyp_dump_info->phyp_dump_at_boot);
-}
-
-static struct kobj_attribute pdl = __ATTR(phyp_dump_active, 0600,
- show_phyp_dump_active,
- NULL);
-
-static void register_dump_area(struct phyp_dump_header *ph, unsigned long addr)
-{
- int rc;
-
- /* Add addr value if not initialized before */
- if (ph->cpu_data.destination_address == 0) {
- ph->cpu_data.destination_address += addr;
- ph->hpte_data.destination_address += addr;
- ph->kernel_data.destination_address += addr;
- }
-
- /* ToDo Invalidate kdump and free memory range. */
-
- do {
- rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
- 1, ph, sizeof(struct phyp_dump_header));
- } while (rtas_busy_delay(rc));
-
- if (rc) {
- printk(KERN_ERR "phyp-dump: unexpected error (%d) on "
- "register\n", rc);
- print_dump_header(ph);
- return;
- }
-
- rc = sysfs_create_file(kernel_kobj, &pdl.attr);
- if (rc)
- printk(KERN_ERR "phyp-dump: unable to create sysfs"
- " file (%d)\n", rc);
-}
-
-static
-void invalidate_last_dump(struct phyp_dump_header *ph, unsigned long addr)
-{
- int rc;
-
- /* Add addr value if not initialized before */
- if (ph->cpu_data.destination_address == 0) {
- ph->cpu_data.destination_address += addr;
- ph->hpte_data.destination_address += addr;
- ph->kernel_data.destination_address += addr;
- }
-
- do {
- rc = rtas_call(ibm_configure_kernel_dump, 3, 1, NULL,
- 2, ph, sizeof(struct phyp_dump_header));
- } while (rtas_busy_delay(rc));
-
- if (rc) {
- printk(KERN_ERR "phyp-dump: unexpected error (%d) "
- "on invalidate\n", rc);
- print_dump_header(ph);
- }
-}
-
-/* ------------------------------------------------- */
-/**
- * release_memory_range -- release memory previously memblock_reserved
- * @start_pfn: starting physical frame number
- * @nr_pages: number of pages to free.
- *
- * This routine will release memory that had been previously
- * memblock_reserved in early boot. The released memory becomes
- * available for genreal use.
- */
-static void release_memory_range(unsigned long start_pfn,
- unsigned long nr_pages)
-{
- struct page *rpage;
- unsigned long end_pfn;
- long i;
-
- end_pfn = start_pfn + nr_pages;
-
- for (i = start_pfn; i <= end_pfn; i++) {
- rpage = pfn_to_page(i);
- if (PageReserved(rpage)) {
- ClearPageReserved(rpage);
- init_page_count(rpage);
- __free_page(rpage);
- totalram_pages++;
- }
- }
-}
-
-/**
- * track_freed_range -- Counts the range being freed.
- * Once the counter goes to zero, it re-registers dump for
- * future use.
- */
-static void
-track_freed_range(unsigned long addr, unsigned long length)
-{
- static unsigned long scratch_area_size, reserved_area_size;
-
- if (addr < phyp_dump_info->init_reserve_start)
- return;
-
- if ((addr >= phyp_dump_info->init_reserve_start) &&
- (addr <= phyp_dump_info->init_reserve_start +
- phyp_dump_info->init_reserve_size))
- reserved_area_size += length;
-
- if ((addr >= phyp_dump_info->reserved_scratch_addr) &&
- (addr <= phyp_dump_info->reserved_scratch_addr +
- phyp_dump_info->reserved_scratch_size))
- scratch_area_size += length;
-
- if ((reserved_area_size == phyp_dump_info->init_reserve_size) &&
- (scratch_area_size == phyp_dump_info->reserved_scratch_size)) {
-
- invalidate_last_dump(&phdr,
- phyp_dump_info->reserved_scratch_addr);
- register_dump_area(&phdr,
- phyp_dump_info->reserved_scratch_addr);
- }
-}
-
-/* ------------------------------------------------- */
-/**
- * sysfs_release_region -- sysfs interface to release memory range.
- *
- * Usage:
- * "echo <start addr> <length> > /sys/kernel/release_region"
- *
- * Example:
- * "echo 0x40000000 0x10000000 > /sys/kernel/release_region"
- *
- * will release 256MB starting at 1GB.
- */
-static ssize_t store_release_region(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
-{
- unsigned long start_addr, length, end_addr;
- unsigned long start_pfn, nr_pages;
- ssize_t ret;
-
- ret = sscanf(buf, "%lx %lx", &start_addr, &length);
- if (ret != 2)
- return -EINVAL;
-
- track_freed_range(start_addr, length);
-
- /* Range-check - don't free any reserved memory that
- * wasn't reserved for phyp-dump */
- if (start_addr < phyp_dump_info->init_reserve_start)
- start_addr = phyp_dump_info->init_reserve_start;
-
- end_addr = phyp_dump_info->init_reserve_start +
- phyp_dump_info->init_reserve_size;
- if (start_addr+length > end_addr)
- length = end_addr - start_addr;
-
- /* Release the region of memory assed in by user */
- start_pfn = PFN_DOWN(start_addr);
- nr_pages = PFN_DOWN(length);
- release_memory_range(start_pfn, nr_pages);
-
- return count;
-}
-
-static ssize_t show_release_region(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- u64 second_addr_range;
-
- /* total reserved size - start of scratch area */
- second_addr_range = phyp_dump_info->init_reserve_size -
- phyp_dump_info->reserved_scratch_size;
- return sprintf(buf, "CPU:0x%llx-0x%llx: HPTE:0x%llx-0x%llx:"
- " DUMP:0x%llx-0x%llx, 0x%lx-0x%llx:\n",
- phdr.cpu_data.destination_address,
- phdr.cpu_data.length_copied,
- phdr.hpte_data.destination_address,
- phdr.hpte_data.length_copied,
- phdr.kernel_data.destination_address,
- phdr.kernel_data.length_copied,
- phyp_dump_info->init_reserve_start,
- second_addr_range);
-}
-
-static struct kobj_attribute rr = __ATTR(release_region, 0600,
- show_release_region,
- store_release_region);
-
-static int __init phyp_dump_setup(void)
-{
- struct device_node *rtas;
- const struct phyp_dump_header *dump_header = NULL;
- unsigned long dump_area_start;
- unsigned long dump_area_length;
- int header_len = 0;
- int rc;
-
- /* If no memory was reserved in early boot, there is nothing to do */
- if (phyp_dump_info->init_reserve_size == 0)
- return 0;
-
- /* Return if phyp dump not supported */
- if (!phyp_dump_info->phyp_dump_configured)
- return -ENOSYS;
-
- /* Is there dump data waiting for us? If there isn't,
- * then register a new dump area, and release all of
- * the rest of the reserved ram.
- *
- * The /rtas/ibm,kernel-dump rtas node is present only
- * if there is dump data waiting for us.
- */
- rtas = of_find_node_by_path("/rtas");
- if (rtas) {
- dump_header = of_get_property(rtas, "ibm,kernel-dump",
- &header_len);
- of_node_put(rtas);
- }
-
- ibm_configure_kernel_dump = rtas_token("ibm,configure-kernel-dump");
-
- print_dump_header(dump_header);
- dump_area_length = init_dump_header(&phdr);
- /* align down */
- dump_area_start = phyp_dump_info->init_reserve_start & PAGE_MASK;
-
- if (dump_header == NULL) {
- register_dump_area(&phdr, dump_area_start);
- return 0;
- }
-
- /* re-register the dump area, if old dump was invalid */
- if ((dump_header) && (dump_header->status & DUMP_ERROR_FLAG)) {
- invalidate_last_dump(&phdr, dump_area_start);
- register_dump_area(&phdr, dump_area_start);
- return 0;
- }
-
- if (dump_header) {
- phyp_dump_info->reserved_scratch_addr =
- dump_header->cpu_data.destination_address;
- phyp_dump_info->reserved_scratch_size =
- dump_header->cpu_data.source_length +
- dump_header->hpte_data.source_length +
- dump_header->kernel_data.source_length;
- }
-
- /* Should we create a dump_subsys, analogous to s390/ipl.c ? */
- rc = sysfs_create_file(kernel_kobj, &rr.attr);
- if (rc)
- printk(KERN_ERR "phyp-dump: unable to create sysfs file (%d)\n",
- rc);
-
- /* ToDo: re-register the dump area, for next time. */
- return 0;
-}
-machine_subsys_initcall(pseries, phyp_dump_setup);
-
-int __init early_init_dt_scan_phyp_dump(unsigned long node,
- const char *uname, int depth, void *data)
-{
- const unsigned int *sizes;
-
- phyp_dump_info->phyp_dump_configured = 0;
- phyp_dump_info->phyp_dump_is_active = 0;
-
- if (depth != 1 || strcmp(uname, "rtas") != 0)
- return 0;
-
- if (of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL))
- phyp_dump_info->phyp_dump_configured++;
-
- if (of_get_flat_dt_prop(node, "ibm,dump-kernel", NULL))
- phyp_dump_info->phyp_dump_is_active++;
-
- sizes = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
- NULL);
- if (!sizes)
- return 0;
-
- if (sizes[0] == 1)
- phyp_dump_info->cpu_state_size = *((unsigned long *)&sizes[1]);
-
- if (sizes[3] == 2)
- phyp_dump_info->hpte_region_size =
- *((unsigned long *)&sizes[4]);
- return 1;
-}
-
-/* Look for phyp_dump= cmdline option */
-static int __init early_phyp_dump_enabled(char *p)
-{
- phyp_dump_info->phyp_dump_at_boot = 1;
-
- if (!p)
- return 0;
-
- if (strncmp(p, "1", 1) == 0)
- phyp_dump_info->phyp_dump_at_boot = 1;
- else if (strncmp(p, "0", 1) == 0)
- phyp_dump_info->phyp_dump_at_boot = 0;
-
- return 0;
-}
-early_param("phyp_dump", early_phyp_dump_enabled);
-
-/* Look for phyp_dump_reserve_size= cmdline option */
-static int __init early_phyp_dump_reserve_size(char *p)
-{
- if (p)
- phyp_dump_info->reserve_bootvar = memparse(p, &p);
-
- return 0;
-}
-early_param("phyp_dump_reserve_size", early_phyp_dump_reserve_size);
^ permalink raw reply related
* [RFC PATCH v7 07/10] fadump: Introduce cleanup routine to invalidate /proc/vmcore.
From: Mahesh J Salgaonkar @ 2012-02-16 11:15 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
With the firmware-assisted dump support we don't require a reboot when we
are in second kernel after crash. The second kernel after crash is a normal
kernel boot and has knowledge about entire system RAM with the page tables
initialized for entire system RAM. Hence once the dump is saved to disk, we
can just release the reserved memory area for general use and continue
with second kernel as production kernel.
Hence when we release the reserved memory that contains dump data, the
'/proc/vmcore' will not be valid anymore. Hence this patch introduces
a cleanup routine that invalidates and removes the /proc/vmcore file. This
routine will be invoked before we release the reserved dump memory area.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
fs/proc/vmcore.c | 23 +++++++++++++++++++++++
1 files changed, 23 insertions(+), 0 deletions(-)
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index b0f450a..0d5071d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -700,3 +700,26 @@ static int __init vmcore_init(void)
return 0;
}
module_init(vmcore_init)
+
+/* Cleanup function for vmcore module. */
+void vmcore_cleanup(void)
+{
+ struct list_head *pos, *next;
+
+ if (proc_vmcore) {
+ remove_proc_entry(proc_vmcore->name, proc_vmcore->parent);
+ proc_vmcore = NULL;
+ }
+
+ /* clear the vmcore list. */
+ list_for_each_safe(pos, next, &vmcore_list) {
+ struct vmcore *m;
+
+ m = list_entry(pos, struct vmcore, list);
+ list_del(&m->list);
+ kfree(m);
+ }
+ kfree(elfcorebuf);
+ elfcorebuf = NULL;
+}
+EXPORT_SYMBOL_GPL(vmcore_cleanup);
^ permalink raw reply related
* [RFC PATCH v7 06/10] fadump: Add PT_NOTE program header for vmcoreinfo
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Introduce a PT_NOTE program header that points to physical address of
vmcoreinfo_note buffer declared in kernel/kexec.c. The vmcoreinfo
note buffer is populated during crash_fadump() at the time of system
crash.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kernel/fadump.c | 29 +++++++++++++++++++++++++++++
1 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index cab56e7..5689954 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -814,6 +814,19 @@ static void fadump_setup_crash_memory_ranges(void)
}
}
+/*
+ * 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.
+ */
+static inline unsigned long fadump_relocate(unsigned long paddr)
+{
+ if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
+ return fdm.rmr_region.destination_address + paddr;
+ else
+ return paddr;
+}
+
static int fadump_create_elfcore_headers(char *bufp)
{
struct elfhdr *elf;
@@ -845,6 +858,22 @@ static int fadump_create_elfcore_headers(char *bufp)
(elf->e_phnum)++;
+ /* setup ELF PT_NOTE for vmcoreinfo */
+ 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_paddr = fadump_relocate(paddr_vmcoreinfo_note());
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_memsz = vmcoreinfo_max_size;
+ phdr->p_filesz = vmcoreinfo_max_size;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+
/* setup PT_LOAD sections. */
for (i = 0; i < crash_mem_ranges; i++) {
^ permalink raw reply related
* [RFC PATCH v7 09/10] fadump: Invalidate the fadump registration during machine shutdown.
From: Mahesh J Salgaonkar @ 2012-02-16 11:15 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
If dump is active during system reboot, shutdown or halt then invalidate
the fadump registration as it does not get invalidated automatically.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/kernel/setup-common.c | 8 ++++++++
1 files changed, 8 insertions(+), 0 deletions(-)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 4e62a56..b0ebdea 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -110,6 +110,14 @@ EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
/* also used by kexec */
void machine_shutdown(void)
{
+#ifdef CONFIG_FA_DUMP
+ /*
+ * if fadump is active, cleanup the fadump registration before we
+ * shutdown.
+ */
+ fadump_cleanup();
+#endif
+
if (ppc_md.machine_shutdown)
ppc_md.machine_shutdown();
}
^ permalink raw reply related
* [RFC PATCH v7 08/10] fadump: Invalidate registration and release reserved memory for general use.
From: Mahesh J Salgaonkar @ 2012-02-16 11:15 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch introduces an sysfs interface '/sys/kernel/fadump_release_mem' to
invalidate the last fadump registration, invalidate '/proc/vmcore', release
the reserved memory for general use and re-register for future kernel dump.
Once the dump is copied to the disk, unlike phyp dump, the userspace tool
can release all the memory reserved for dump with one single operation of
echo 1 to '/sys/kernel/fadump_release_mem'.
Release the reserved memory region excluding the size of the memory required
for future kernel dump registration. And therefore, unlike kdump, Fadump
doesn't need a 2nd reboot to get back the system to the production
configuration.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 3 +
arch/powerpc/kernel/fadump.c | 158 ++++++++++++++++++++++++++++++++++++-
2 files changed, 157 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 6768195..88dbf96 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -208,6 +208,9 @@ extern int fadump_reserve_mem(void);
extern int setup_fadump(void);
extern int is_fadump_active(void);
extern void crash_fadump(struct pt_regs *, const char *);
+extern void fadump_cleanup(void);
+
+extern void vmcore_cleanup(void);
#else /* CONFIG_FA_DUMP */
static inline int is_fadump_active(void) { return 0; }
static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 5689954..8874d6b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -33,6 +33,8 @@
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/crash_dump.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -984,6 +986,132 @@ static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
return 0;
}
+static int fadump_invalidate_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Invalidating firmware-assisted dump registration\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_INVALIDATE, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+ } while (wait_time);
+
+ if (rc) {
+ printk(KERN_ERR "Failed to invalidate firmware-assisted dump "
+ "rgistration. unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_active = 0;
+ fdm_active = NULL;
+ return 0;
+}
+
+void fadump_cleanup(void)
+{
+ /* Invalidate the registration only if dump is active. */
+ if (fw_dump.dump_active) {
+ init_fadump_mem_struct(&fdm,
+ fdm_active->cpu_state_data.destination_address);
+ fadump_invalidate_dump(&fdm);
+ }
+}
+
+/*
+ * Release the memory that was reserved in early boot to preserve the memory
+ * contents. The released memory will be available for general use.
+ */
+static void fadump_release_memory(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+ unsigned long ra_start, ra_end;
+
+ ra_start = fw_dump.reserve_dump_area_start;
+ ra_end = ra_start + fw_dump.reserve_dump_area_size;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ /*
+ * exclude the dump reserve area. Will reuse it for next
+ * fadump registration.
+ */
+ if (addr <= ra_end && ((addr + PAGE_SIZE) > ra_start))
+ continue;
+
+ ClearPageReserved(pfn_to_page(addr >> PAGE_SHIFT));
+ init_page_count(pfn_to_page(addr >> PAGE_SHIFT));
+ free_page((unsigned long)__va(addr));
+ totalram_pages++;
+ }
+}
+
+static void fadump_invalidate_release_mem(void)
+{
+ unsigned long reserved_area_start, reserved_area_end;
+ unsigned long destination_address;
+
+ mutex_lock(&fadump_mutex);
+ if (!fw_dump.dump_active) {
+ mutex_unlock(&fadump_mutex);
+ return;
+ }
+
+ destination_address = fdm_active->cpu_state_data.destination_address;
+ fadump_cleanup();
+ mutex_unlock(&fadump_mutex);
+
+ /*
+ * Save the current reserved memory bounds we will require them
+ * later for releasing the memory for general use.
+ */
+ reserved_area_start = fw_dump.reserve_dump_area_start;
+ reserved_area_end = reserved_area_start +
+ fw_dump.reserve_dump_area_size;
+ /*
+ * Setup reserve_dump_area_start and its size so that we can
+ * reuse this reserved memory for Re-registration.
+ */
+ fw_dump.reserve_dump_area_start = destination_address;
+ fw_dump.reserve_dump_area_size = get_fadump_area_size();
+
+ fadump_release_memory(reserved_area_start, reserved_area_end);
+ if (fw_dump.cpu_notes_buf) {
+ fadump_cpu_notes_buf_free(
+ (unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ }
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+}
+
+static ssize_t fadump_release_memory_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ if (!fw_dump.dump_active)
+ return -EPERM;
+
+ if (buf[0] == '1') {
+ /*
+ * Take away the '/proc/vmcore'. We are releasing the dump
+ * memory, hence it will not be valid anymore.
+ */
+ vmcore_cleanup();
+ fadump_invalidate_release_mem();
+
+ } else
+ return -EINVAL;
+ return count;
+}
+
static ssize_t fadump_enabled_show(struct kobject *kobj,
struct kobj_attribute *attr,
char *buf)
@@ -1043,10 +1171,13 @@ static int fadump_region_show(struct seq_file *m, void *private)
if (!fw_dump.fadump_enabled)
return 0;
+ mutex_lock(&fadump_mutex);
if (fdm_active)
fdm_ptr = fdm_active;
- else
+ else {
+ mutex_unlock(&fadump_mutex);
fdm_ptr = &fdm;
+ }
seq_printf(m,
"CPU : [%#016llx-%#016llx] %#llx bytes, "
@@ -1076,7 +1207,7 @@ static int fadump_region_show(struct seq_file *m, void *private)
if (!fdm_active ||
(fw_dump.reserve_dump_area_start ==
fdm_ptr->cpu_state_data.destination_address))
- return 0;
+ goto out;
/* Dump is active. Show reserved memory region. */
seq_printf(m,
@@ -1088,9 +1219,15 @@ static int fadump_region_show(struct seq_file *m, void *private)
fw_dump.reserve_dump_area_start,
fdm_ptr->cpu_state_data.destination_address -
fw_dump.reserve_dump_area_start);
+out:
+ if (fdm_active)
+ mutex_unlock(&fadump_mutex);
return 0;
}
+static struct kobj_attribute fadump_release_attr = __ATTR(fadump_release_mem,
+ 0200, NULL,
+ fadump_release_memory_store);
static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
0444, fadump_enabled_show,
NULL);
@@ -1131,6 +1268,13 @@ static void fadump_init_files(void)
if (!debugfs_file)
printk(KERN_ERR "fadump: unable to create debugfs file"
" fadump_region\n");
+
+ if (fw_dump.dump_active) {
+ rc = sysfs_create_file(kernel_kobj, &fadump_release_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_release_mem (%d)\n", rc);
+ }
return;
}
@@ -1150,8 +1294,14 @@ int __init setup_fadump(void)
* If dump data is available then see if it is valid and prepare for
* saving it to the disk.
*/
- if (fw_dump.dump_active)
- process_fadump(fdm_active);
+ if (fw_dump.dump_active) {
+ /*
+ * if dump process fails then invalidate the registration
+ * and release memory before proceeding for re-registration.
+ */
+ if (process_fadump(fdm_active) < 0)
+ fadump_invalidate_release_mem();
+ }
/* Initialize the kernel dump memory structure for FAD registration. */
else if (fw_dump.reserve_dump_area_size)
init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
^ permalink raw reply related
* [RFC PATCH v7 03/10] fadump: Register for firmware assisted dump.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
This patch registers for firmware-assisted dump using rtas token
ibm,configure-kernel-dump. During registration firmware is informed about
the reserved area where it saves the CPU state data, HPTE table and contents
of RMR region at the time of kernel crash. Apart from this, firmware also
preserves the contents of entire partition memory even if it is not specified
during registration.
This patch also populates sysfs files under /sys/kernel to display
fadump status and reserved memory regions.
This patch introduces fadump_registered sysfs control file which will be
used by kdump init scripts to start/stop firmware assisted dump. echo 1 to
/sys/kernel/fadump_registered file for fadump registration and
echo 0 to /sys/kernel/fadump_registered file for fadump un-registration.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 57 ++++++
arch/powerpc/kernel/fadump.c | 352 +++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/iommu.c | 8 +
arch/powerpc/mm/hash_utils_64.c | 11 +
4 files changed, 424 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 7be25d3..bbaf278 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -48,6 +48,58 @@
#define FADUMP_HPTE_REGION 0x0002
#define FADUMP_REAL_MODE_REGION 0x0011
+/* Dump request flag */
+#define FADUMP_REQUEST_FLAG 0x00000001
+
+/* FAD commands */
+#define FADUMP_REGISTER 1
+#define FADUMP_UNREGISTER 2
+#define FADUMP_INVALIDATE 3
+
+/* Kernel Dump section info */
+struct fadump_section {
+ u32 request_flag;
+ u16 source_data_type;
+ u16 error_flags;
+ u64 source_address;
+ u64 source_len;
+ u64 bytes_dumped;
+ u64 destination_address;
+};
+
+/* ibm,configure-kernel-dump header. */
+struct fadump_section_header {
+ u32 dump_format_version;
+ u16 dump_num_sections;
+ u16 dump_status_flag;
+ u32 offset_first_dump_section;
+
+ /* Fields for disk dump option. */
+ u32 dd_block_size;
+ u64 dd_block_offset;
+ u64 dd_num_blocks;
+ u32 dd_offset_disk_path;
+
+ /* Maximum time allowed to prevent an automatic dump-reboot. */
+ u32 max_time_auto;
+};
+
+/*
+ * 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.
+ */
+struct fadump_mem_struct {
+ struct fadump_section_header header;
+
+ /* Kernel dump sections */
+ struct fadump_section cpu_state_data;
+ struct fadump_section hpte_region;
+ struct fadump_section rmr_region;
+};
+
+/* Firmware-assisted dump configuration details. */
struct fw_dump {
unsigned long cpu_state_data_size;
unsigned long hpte_region_size;
@@ -62,10 +114,15 @@ struct fw_dump {
unsigned long fadump_enabled:1;
unsigned long fadump_supported:1;
unsigned long dump_active:1;
+ unsigned long dump_registered:1;
};
extern int early_init_dt_scan_fw_dump(unsigned long node,
const char *uname, int depth, void *data);
extern int fadump_reserve_mem(void);
+extern int setup_fadump(void);
+extern int is_fadump_active(void);
+#else /* CONFIG_FA_DUMP */
+static inline int is_fadump_active(void) { return 0; }
#endif
#endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index deb276a..13c22cd 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -29,6 +29,9 @@
#include <linux/string.h>
#include <linux/memblock.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -36,6 +39,10 @@
#include <asm/fadump.h>
static struct fw_dump fw_dump;
+static struct fadump_mem_struct fdm;
+static const struct fadump_mem_struct *fdm_active;
+
+static DEFINE_MUTEX(fadump_mutex);
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node,
@@ -64,7 +71,8 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
* The 'ibm,kernel-dump' rtas node is present only if there is
* dump data waiting for us.
*/
- if (of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL))
+ fdm_active = of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL);
+ if (fdm_active)
fw_dump.dump_active = 1;
/* Get the sizes required to store dump data for the firmware provided
@@ -98,6 +106,85 @@ int __init early_init_dt_scan_fw_dump(unsigned long node,
return 1;
}
+int is_fadump_active(void)
+{
+ return fw_dump.dump_active;
+}
+
+/* Print firmware assisted dump configurations for debugging purpose. */
+static void fadump_show_config(void)
+{
+ pr_debug("Support for firmware-assisted dump (fadump): %s\n",
+ (fw_dump.fadump_supported ? "present" : "no support"));
+
+ if (!fw_dump.fadump_supported)
+ return;
+
+ pr_debug("Fadump enabled : %s\n",
+ (fw_dump.fadump_enabled ? "yes" : "no"));
+ pr_debug("Dump Active : %s\n",
+ (fw_dump.dump_active ? "yes" : "no"));
+ pr_debug("Dump section sizes:\n");
+ pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
+ pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
+ pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size);
+}
+
+static unsigned long init_fadump_mem_struct(struct fadump_mem_struct *fdm,
+ unsigned long addr)
+{
+ if (!fdm)
+ return 0;
+
+ memset(fdm, 0, sizeof(struct fadump_mem_struct));
+ addr = addr & PAGE_MASK;
+
+ fdm->header.dump_format_version = 0x00000001;
+ fdm->header.dump_num_sections = 3;
+ fdm->header.dump_status_flag = 0;
+ fdm->header.offset_first_dump_section =
+ (u32)offsetof(struct fadump_mem_struct, cpu_state_data);
+
+ /*
+ * Fields for disk dump option.
+ * We are not using disk dump option, hence set these fields to 0.
+ */
+ fdm->header.dd_block_size = 0;
+ fdm->header.dd_block_offset = 0;
+ fdm->header.dd_num_blocks = 0;
+ fdm->header.dd_offset_disk_path = 0;
+
+ /* set 0 to disable an automatic dump-reboot. */
+ fdm->header.max_time_auto = 0;
+
+ /* Kernel dump sections */
+ /* cpu state data section. */
+ fdm->cpu_state_data.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->cpu_state_data.source_data_type = FADUMP_CPU_STATE_DATA;
+ fdm->cpu_state_data.source_address = 0;
+ fdm->cpu_state_data.source_len = fw_dump.cpu_state_data_size;
+ fdm->cpu_state_data.destination_address = addr;
+ addr += fw_dump.cpu_state_data_size;
+
+ /* hpte region section */
+ fdm->hpte_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->hpte_region.source_data_type = FADUMP_HPTE_REGION;
+ fdm->hpte_region.source_address = 0;
+ fdm->hpte_region.source_len = fw_dump.hpte_region_size;
+ fdm->hpte_region.destination_address = addr;
+ addr += fw_dump.hpte_region_size;
+
+ /* RMA region section */
+ fdm->rmr_region.request_flag = FADUMP_REQUEST_FLAG;
+ fdm->rmr_region.source_data_type = FADUMP_REAL_MODE_REGION;
+ fdm->rmr_region.source_address = RMA_START;
+ fdm->rmr_region.source_len = fw_dump.boot_memory_size;
+ fdm->rmr_region.destination_address = addr;
+ addr += fw_dump.boot_memory_size;
+
+ return addr;
+}
+
/**
* fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
*
@@ -166,8 +253,15 @@ int __init fadump_reserve_mem(void)
fw_dump.fadump_enabled = 0;
return 0;
}
- /* Initialize boot memory size */
- fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+ /*
+ * Initialize boot memory size
+ * If dump is active then we have already calculated the size during
+ * first kernel.
+ */
+ if (fdm_active)
+ fw_dump.boot_memory_size = fdm_active->rmr_region.source_len;
+ else
+ fw_dump.boot_memory_size = fadump_calculate_reserve_size();
/*
* Calculate the memory boundary.
@@ -244,3 +338,255 @@ static int __init early_fadump_reserve_mem(char *p)
return 0;
}
early_param("fadump_reserve_mem", early_fadump_reserve_mem);
+
+static void register_fw_dump(struct fadump_mem_struct *fdm)
+{
+ int rc;
+ unsigned int wait_time;
+
+ pr_debug("Registering for firmware-assisted kernel dump...\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_REGISTER, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+
+ } while (wait_time);
+
+ switch (rc) {
+ case -1:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Hardware Error(%d).\n", rc);
+ break;
+ case -3:
+ printk(KERN_ERR "Failed to register firmware-assisted kernel"
+ " dump. Parameter Error(%d).\n", rc);
+ break;
+ case -9:
+ printk(KERN_ERR "firmware-assisted kernel dump is already "
+ " registered.");
+ fw_dump.dump_registered = 1;
+ break;
+ case 0:
+ printk(KERN_INFO "firmware-assisted kernel dump registration"
+ " is successful\n");
+ fw_dump.dump_registered = 1;
+ break;
+ }
+}
+
+static void register_fadump(void)
+{
+ /*
+ * If no memory is reserved then we can not register for firmware-
+ * assisted dump.
+ */
+ if (!fw_dump.reserve_dump_area_size)
+ return;
+
+ /* register the future kernel dump with firmware. */
+ register_fw_dump(&fdm);
+}
+
+static int fadump_unregister_dump(struct fadump_mem_struct *fdm)
+{
+ int rc = 0;
+ unsigned int wait_time;
+
+ pr_debug("Un-register firmware-assisted dump\n");
+
+ /* TODO: Add upper time limit for the delay */
+ do {
+ rc = rtas_call(fw_dump.ibm_configure_kernel_dump, 3, 1, NULL,
+ FADUMP_UNREGISTER, fdm,
+ sizeof(struct fadump_mem_struct));
+
+ wait_time = rtas_busy_delay_time(rc);
+ if (wait_time)
+ mdelay(wait_time);
+ } while (wait_time);
+
+ if (rc) {
+ printk(KERN_ERR "Failed to un-register firmware-assisted dump."
+ " unexpected error(%d).\n", rc);
+ return rc;
+ }
+ fw_dump.dump_registered = 0;
+ return 0;
+}
+
+static ssize_t fadump_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.fadump_enabled);
+}
+
+static ssize_t fadump_register_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", fw_dump.dump_registered);
+}
+
+static ssize_t fadump_register_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int ret = 0;
+
+ if (!fw_dump.fadump_enabled || fdm_active)
+ return -EPERM;
+
+ mutex_lock(&fadump_mutex);
+
+ switch (buf[0]) {
+ case '0':
+ if (fw_dump.dump_registered == 0) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Un-register Firmware-assisted dump */
+ fadump_unregister_dump(&fdm);
+ break;
+ case '1':
+ if (fw_dump.dump_registered == 1) {
+ ret = -EINVAL;
+ goto unlock_out;
+ }
+ /* Register Firmware-assisted dump */
+ register_fadump();
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+unlock_out:
+ mutex_unlock(&fadump_mutex);
+ return ret < 0 ? ret : count;
+}
+
+static int fadump_region_show(struct seq_file *m, void *private)
+{
+ const struct fadump_mem_struct *fdm_ptr;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else
+ fdm_ptr = &fdm;
+
+ seq_printf(m,
+ "CPU : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->cpu_state_data.destination_address,
+ fdm_ptr->cpu_state_data.destination_address +
+ fdm_ptr->cpu_state_data.source_len - 1,
+ fdm_ptr->cpu_state_data.source_len,
+ fdm_ptr->cpu_state_data.bytes_dumped);
+ seq_printf(m,
+ "HPTE: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->hpte_region.destination_address,
+ fdm_ptr->hpte_region.destination_address +
+ fdm_ptr->hpte_region.source_len - 1,
+ fdm_ptr->hpte_region.source_len,
+ fdm_ptr->hpte_region.bytes_dumped);
+ seq_printf(m,
+ "DUMP: [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ fdm_ptr->rmr_region.destination_address,
+ fdm_ptr->rmr_region.destination_address +
+ fdm_ptr->rmr_region.source_len - 1,
+ fdm_ptr->rmr_region.source_len,
+ fdm_ptr->rmr_region.bytes_dumped);
+
+ if (!fdm_active ||
+ (fw_dump.reserve_dump_area_start ==
+ fdm_ptr->cpu_state_data.destination_address))
+ return 0;
+
+ /* Dump is active. Show reserved memory region. */
+ seq_printf(m,
+ " : [%#016llx-%#016llx] %#llx bytes, "
+ "Dumped: %#llx\n",
+ (unsigned long long)fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address - 1,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start,
+ fdm_ptr->cpu_state_data.destination_address -
+ fw_dump.reserve_dump_area_start);
+ return 0;
+}
+
+static struct kobj_attribute fadump_attr = __ATTR(fadump_enabled,
+ 0444, fadump_enabled_show,
+ NULL);
+static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered,
+ 0644, fadump_register_show,
+ fadump_register_store);
+
+static int fadump_region_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, fadump_region_show, inode->i_private);
+}
+
+static const struct file_operations fadump_region_fops = {
+ .open = fadump_region_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void fadump_init_files(void)
+{
+ struct dentry *debugfs_file;
+ int rc = 0;
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_enabled (%d)\n", rc);
+
+ rc = sysfs_create_file(kernel_kobj, &fadump_register_attr.attr);
+ if (rc)
+ printk(KERN_ERR "fadump: unable to create sysfs file"
+ " fadump_registered (%d)\n", rc);
+
+ debugfs_file = debugfs_create_file("fadump_region", 0444,
+ powerpc_debugfs_root, NULL,
+ &fadump_region_fops);
+ if (!debugfs_file)
+ printk(KERN_ERR "fadump: unable to create debugfs file"
+ " fadump_region\n");
+ return;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_ERR "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ return 0;
+ }
+
+ fadump_show_config();
+ /* Initialize the kernel dump memory structure for FAD registration. */
+ if (fw_dump.reserve_dump_area_size)
+ init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
+ fadump_init_files();
+
+ return 1;
+}
+subsys_initcall(setup_fadump);
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 0cfcf98..359f078 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -39,6 +39,7 @@
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/kdump.h>
+#include <asm/fadump.h>
#define DBG(...)
@@ -445,7 +446,12 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
static void iommu_table_clear(struct iommu_table *tbl)
{
- if (!is_kdump_kernel()) {
+ /*
+ * In case of firmware assisted dump system goes through clean
+ * reboot process at the time of system crash. Hence it's safe to
+ * clear the TCE entries if firmware assisted dump is active.
+ */
+ if (!is_kdump_kernel() || is_fadump_active()) {
/* Clear the table in case firmware left allocations in it */
ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
return;
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 2d28218..b534bba 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -55,6 +55,7 @@
#include <asm/spu.h>
#include <asm/udbg.h>
#include <asm/code-patching.h>
+#include <asm/fadump.h>
#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
@@ -625,6 +626,16 @@ static void __init htab_initialize(void)
/* Using a hypervisor which owns the htab */
htab_address = NULL;
_SDR1 = 0;
+#ifdef CONFIG_FA_DUMP
+ /*
+ * If firmware assisted dump is active firmware preserves
+ * the contents of htab along with entire partition memory.
+ * Clear the htab if firmware assisted dump is active so
+ * that we dont end up using old mappings.
+ */
+ if (is_fadump_active() && ppc_md.hpte_clear_all)
+ ppc_md.hpte_clear_all();
+#endif
} else {
/* Find storage for the HPT. Must be contiguous in
* the absolute address space. On cell we want it to be
^ permalink raw reply related
* [RFC PATCH v7 01/10] fadump: Add documentation for firmware-assisted dump.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Documentation for firmware-assisted dump. This document is based on the
original documentation written for phyp assisted dump by Linas Vepstas
and Manish Ahuja, with few changes to reflect the current implementation.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.txt | 270 ++++++++++++++++++++++
1 files changed, 270 insertions(+), 0 deletions(-)
create mode 100644 Documentation/powerpc/firmware-assisted-dump.txt
diff --git a/Documentation/powerpc/firmware-assisted-dump.txt b/Documentation/powerpc/firmware-assisted-dump.txt
new file mode 100644
index 0000000..3007bc9
--- /dev/null
+++ b/Documentation/powerpc/firmware-assisted-dump.txt
@@ -0,0 +1,270 @@
+
+ Firmware-Assisted Dump
+ ------------------------
+ July 2011
+
+The goal of firmware-assisted dump is to enable the dump of
+a crashed system, and to do so from a fully-reset system, and
+to minimize the total elapsed time until the system is back
+in production use.
+
+- Firmware assisted dump (fadump) infrastructure is intended to replace
+ the existing phyp assisted dump.
+- Fadump uses the same firmware interfaces and memory reservation model
+ as phyp assisted dump.
+- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
+ in the ELF format in the same way as kdump. This helps us reuse the
+ kdump infrastructure for dump capture and filtering.
+- Unlike phyp dump, userspace tool does not need to refer any sysfs
+ interface while reading /proc/vmcore.
+- Unlike phyp dump, fadump allows user to release all the memory reserved
+ for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
+- Once enabled through kernel boot parameter, fadump can be
+ started/stopped through /sys/kernel/fadump_registered interface (see
+ sysfs files section below) and can be easily integrated with kdump
+ service start/stop init scripts.
+
+Comparing with kdump or other strategies, firmware-assisted
+dump offers several strong, practical advantages:
+
+-- Unlike kdump, the system has been reset, and loaded
+ with a fresh copy of the kernel. In particular,
+ PCI and I/O devices have been reinitialized and are
+ in a clean, consistent state.
+-- Once the dump is copied out, the memory that held the dump
+ is immediately available to the running kernel. And therefore,
+ unlike kdump, fadump doesn't need a 2nd reboot to get back
+ the system to the production configuration.
+
+The above can only be accomplished by coordination with,
+and assistance from the Power firmware. The procedure is
+as follows:
+
+-- The first kernel registers the sections of memory with the
+ Power firmware for dump preservation during OS initialization.
+ These registered sections of memory are reserved by the first
+ kernel during early boot.
+
+-- When a system crashes, the Power firmware will save
+ the low memory (boot memory of size larger of 5% of system RAM
+ or 256MB) of RAM to the previous registered region. It will
+ also save system registers, and hardware PTE's.
+
+ NOTE: The term 'boot memory' means size of the low memory chunk
+ that is required for a kernel to boot successfully when
+ booted with restricted memory. By default, the boot memory
+ size will be the larger of 5% of system RAM or 256MB.
+ Alternatively, user can also specify boot memory size
+ through boot parameter 'fadump_reserve_mem=' which will
+ override the default calculated size. Use this option
+ if default boot memory size is not sufficient for second
+ kernel to boot successfully.
+
+-- After the low memory (boot memory) area has been saved, the
+ firmware will reset PCI and other hardware state. It will
+ *not* clear the RAM. It will then launch the bootloader, as
+ normal.
+
+-- The freshly booted kernel will notice that there is a new
+ node (ibm,dump-kernel) in the device tree, indicating that
+ there is crash data available from a previous boot. During
+ the early boot OS will reserve rest of the memory above
+ boot memory size effectively booting with restricted memory
+ size. This will make sure that the second kernel will not
+ touch any of the dump memory area.
+
+-- User-space tools will read /proc/vmcore to obtain the contents
+ of memory, which holds the previous crashed kernel dump in ELF
+ format. The userspace tools may copy this info to disk, or
+ network, nas, san, iscsi, etc. as desired.
+
+-- Once the userspace tool is done saving dump, it will echo
+ '1' to /sys/kernel/fadump_release_mem to release the reserved
+ memory back to general use, except the memory required for
+ next firmware-assisted dump registration.
+
+ e.g.
+ # echo 1 > /sys/kernel/fadump_release_mem
+
+Please note that the firmware-assisted dump feature
+is only available on Power6 and above systems with recent
+firmware versions.
+
+Implementation details:
+----------------------
+
+During boot, a check is made to see if firmware supports
+this feature on that particular machine. If it does, then
+we check to see if an active dump is waiting for us. If yes
+then everything but boot memory size of RAM is reserved during
+early boot (See Fig. 2). This area is released once we finish
+collecting the dump from user land scripts (e.g. kdump scripts)
+that are run. If there is dump data, then the
+/sys/kernel/fadump_release_mem file is created, and the reserved
+memory is held.
+
+If there is no waiting dump data, then only the memory required
+to hold CPU state, HPTE region, boot memory dump and elfcore
+header, is reserved at the top of memory (see Fig. 1). This area
+is *not* released: this region will be kept permanently reserved,
+so that it can act as a receptacle for a copy of the boot memory
+content in addition to CPU state and HPTE region, in the case a
+crash does occur.
+
+ o Memory Reservation during first kernel
+
+ Low memory Top of memory
+ 0 boot memory size |
+ | | |<--Reserved dump area -->|
+ V V | Permanent Reservation V
+ +-----------+----------/ /----------+---+----+-----------+----+
+ | | |CPU|HPTE| DUMP |ELF |
+ +-----------+----------/ /----------+---+----+-----------+----+
+ | ^
+ | |
+ \ /
+ -------------------------------------------
+ Boot memory content gets transferred to
+ reserved area by firmware at the time of
+ crash
+ Fig. 1
+
+ o Memory Reservation during second kernel after crash
+
+ Low memory Top of memory
+ 0 boot memory size |
+ | |<------------- Reserved dump area ----------- -->|
+ V V V
+ +-----------+----------/ /----------+---+----+-----------+----+
+ | | |CPU|HPTE| DUMP |ELF |
+ +-----------+----------/ /----------+---+----+-----------+----+
+ | |
+ V V
+ Used by second /proc/vmcore
+ kernel to boot
+ Fig. 2
+
+Currently the dump will be copied from /proc/vmcore to a
+a new file upon user intervention. The dump data available through
+/proc/vmcore will be in ELF format. Hence the existing kdump
+infrastructure (kdump scripts) to save the dump works fine with
+minor modifications.
+
+The tools to examine the dump will be same as the ones
+used for kdump.
+
+How to enable firmware-assisted dump (fadump):
+-------------------------------------
+
+1. Set config option CONFIG_FA_DUMP=y and build kernel.
+2. Boot into linux kernel with 'fadump=on' kernel cmdline option.
+3. Optionally, user can also set 'fadump_reserve_mem=' kernel cmdline
+ to specify size of the memory to reserve for boot memory dump
+ preservation.
+
+NOTE: If firmware-assisted dump fails to reserve memory then it will
+ fallback to existing kdump mechanism if 'crashkernel=' option
+ is set at kernel cmdline.
+
+Sysfs/debugfs files:
+------------
+
+Firmware-assisted dump feature uses sysfs file system to hold
+the control files and debugfs file to display memory reserved region.
+
+Here is the list of files under kernel sysfs:
+
+ /sys/kernel/fadump_enabled
+
+ This is used to display the fadump status.
+ 0 = fadump is disabled
+ 1 = fadump is enabled
+
+ This interface can be used by kdump init scripts to identify if
+ fadump is enabled in the kernel and act accordingly.
+
+ /sys/kernel/fadump_registered
+
+ This is used to display the fadump registration status as well
+ as to control (start/stop) the fadump registration.
+ 0 = fadump is not registered.
+ 1 = fadump is registered and ready to handle system crash.
+
+ To register fadump echo 1 > /sys/kernel/fadump_registered and
+ echo 0 > /sys/kernel/fadump_registered for un-register and stop the
+ fadump. Once the fadump is un-registered, the system crash will not
+ be handled and vmcore will not be captured. This interface can be
+ easily integrated with kdump service start/stop.
+
+ /sys/kernel/fadump_release_mem
+
+ This file is available only when fadump is active during
+ second kernel. This is used to release the reserved memory
+ region that are held for saving crash dump. To release the
+ reserved memory echo 1 to it:
+
+ echo 1 > /sys/kernel/fadump_release_mem
+
+ After echo 1, the content of the /sys/kernel/debug/powerpc/fadump_region
+ file will change to reflect the new memory reservations.
+
+ The existing userspace tools (kdump infrastructure) can be easily
+ enhanced to use this interface to release the memory reserved for
+ dump and continue without 2nd reboot.
+
+Here is the list of files under powerpc debugfs:
+(Assuming debugfs is mounted on /sys/kernel/debug directory.)
+
+ /sys/kernel/debug/powerpc/fadump_region
+
+ This file shows the reserved memory regions if fadump is
+ enabled otherwise this file is empty. The output format
+ is:
+ <region>: [<start>-<end>] <reserved-size> bytes, Dumped: <dump-size>
+
+ e.g.
+ Contents when fadump is registered during first kernel
+
+ # cat /sys/kernel/debug/powerpc/fadump_region
+ CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x0
+ HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x0
+ DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x0
+
+ Contents when fadump is active during second kernel
+
+ # cat /sys/kernel/debug/powerpc/fadump_region
+ CPU : [0x0000006ffb0000-0x0000006fff001f] 0x40020 bytes, Dumped: 0x40020
+ HPTE: [0x0000006fff0020-0x0000006fff101f] 0x1000 bytes, Dumped: 0x1000
+ DUMP: [0x0000006fff1020-0x0000007fff101f] 0x10000000 bytes, Dumped: 0x10000000
+ : [0x00000010000000-0x0000006ffaffff] 0x5ffb0000 bytes, Dumped: 0x5ffb0000
+
+NOTE: Please refer to Documentation/filesystems/debugfs.txt on
+ how to mount the debugfs filesystem.
+
+
+TODO:
+-----
+ o Need to come up with the better approach to find out more
+ accurate boot memory size that is required for a kernel to
+ boot successfully when booted with restricted memory.
+ o The fadump implementation introduces a fadump crash info structure
+ in the scratch area before the ELF core header. The idea of introducing
+ this structure is to pass some important crash info data to the second
+ kernel which will help second kernel to populate ELF core header with
+ correct data before it gets exported through /proc/vmcore. The current
+ design implementation does not address a possibility of introducing
+ additional fields (in future) to this structure without affecting
+ compatibility. Need to come up with the better approach to address this.
+ The possible approaches are:
+ 1. Introduce version field for version tracking, bump up the version
+ whenever a new field is added to the structure in future. The version
+ field can be used to find out what fields are valid for the current
+ version of the structure.
+ 2. Reserve the area of predefined size (say PAGE_SIZE) for this
+ structure and have unused area as reserved (initialized to zero)
+ for future field additions.
+ The advantage of approach 1 over 2 is we don't need to reserve extra space.
+---
+Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+This document is based on the original documentation written for phyp
+assisted dump by Linas Vepstas and Manish Ahuja.
^ permalink raw reply related
* [RFC PATCH v7 05/10] fadump: Convert firmware-assisted cpu state dump data into elf notes.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
When registered for firmware assisted dump on powerpc, firmware preserves
the registers for the active CPUs during a system crash. This patch reads
the cpu register data stored in Firmware-assisted dump format (except for
crashing cpu) and converts it into elf notes and updates the PT_NOTE program
header accordingly. The exact register state for crashing cpu is saved to
fadump crash info structure in scratch area during crash_fadump() and read
during second kernel boot.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 44 +++++
arch/powerpc/kernel/fadump.c | 314 ++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/setup-common.c | 6 +
arch/powerpc/kernel/traps.c | 3
4 files changed, 365 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index 9e172a5..6768195 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -65,6 +65,18 @@
/* Dump status flag */
#define FADUMP_ERROR_FLAG 0x2000
+#define FADUMP_CPU_ID_MASK ((1UL << 32) - 1)
+
+#define CPU_UNKNOWN (~((u32)0))
+
+/* Utility macros */
+#define SKIP_TO_NEXT_CPU(reg_entry) \
+({ \
+ while (reg_entry->reg_id != REG_ID("CPUEND")) \
+ reg_entry++; \
+ reg_entry++; \
+})
+
/* Kernel Dump section info */
struct fadump_section {
u32 request_flag;
@@ -119,6 +131,9 @@ struct fw_dump {
unsigned long reserve_bootvar;
unsigned long fadumphdr_addr;
+ unsigned long cpu_notes_buf;
+ unsigned long cpu_notes_buf_size;
+
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -143,13 +158,40 @@ static inline u64 str_to_u64(const char *str)
return val;
}
#define STR_TO_HEX(x) str_to_u64(x)
+#define REG_ID(x) str_to_u64(x)
#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF")
+#define REGSAVE_AREA_MAGIC STR_TO_HEX("REGSAVE")
+
+/* The firmware-assisted dump format.
+ *
+ * The register save area is an area in the partition's memory used to preserve
+ * the register contents (CPU state data) for the active CPUs during a firmware
+ * assisted dump. The dump format contains register save area header followed
+ * by register entries. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND".
+ */
+
+/* Register save area header. */
+struct fadump_reg_save_area_header {
+ u64 magic_number;
+ u32 version;
+ u32 num_cpu_offset;
+};
+
+/* Register entry. */
+struct fadump_reg_entry {
+ u64 reg_id;
+ u64 reg_value;
+};
/* fadump crash info structure */
struct fadump_crash_info_header {
u64 magic_number;
u64 elfcorehdr_addr;
+ u32 crashing_cpu;
+ struct pt_regs regs;
+ struct cpumask cpu_online_mask;
};
/* Crash memory ranges */
@@ -165,7 +207,9 @@ extern int early_init_dt_scan_fw_dump(unsigned long node,
extern int fadump_reserve_mem(void);
extern int setup_fadump(void);
extern int is_fadump_active(void);
+extern void crash_fadump(struct pt_regs *, const char *);
#else /* CONFIG_FA_DUMP */
static inline int is_fadump_active(void) { return 0; }
+static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
#endif
#endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index f85a63f..cab56e7 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -240,6 +240,7 @@ static unsigned long get_fadump_area_size(void)
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);
@@ -393,6 +394,285 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
}
}
+void crash_fadump(struct pt_regs *regs, const char *str)
+{
+ struct fadump_crash_info_header *fdh = NULL;
+
+ if (!fw_dump.dump_registered || !fw_dump.fadumphdr_addr)
+ return;
+
+ fdh = __va(fw_dump.fadumphdr_addr);
+ crashing_cpu = smp_processor_id();
+ fdh->crashing_cpu = crashing_cpu;
+ crash_save_vmcoreinfo();
+
+ if (regs)
+ fdh->regs = *regs;
+ else
+ ppc_save_regs(&fdh->regs);
+
+ fdh->cpu_online_mask = *cpu_online_mask;
+
+ /* Call ibm,os-term rtas call to trigger firmware assisted dump */
+ rtas_os_term((char *)str);
+}
+
+#define GPR_MASK 0xffffff0000000000
+static inline int fadump_gpr_index(u64 id)
+{
+ int i = -1;
+ char str[3];
+
+ if ((id & GPR_MASK) == REG_ID("GPR")) {
+ /* get the digits at the end */
+ id &= ~GPR_MASK;
+ id >>= 24;
+ str[2] = '\0';
+ str[1] = id & 0xff;
+ str[0] = (id >> 8) & 0xff;
+ sscanf(str, "%d", &i);
+ if (i > 31)
+ i = -1;
+ }
+ return i;
+}
+
+static inline void fadump_set_regval(struct pt_regs *regs, u64 reg_id,
+ u64 reg_val)
+{
+ int i;
+
+ i = fadump_gpr_index(reg_id);
+ if (i >= 0)
+ regs->gpr[i] = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("NIA"))
+ regs->nip = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("MSR"))
+ regs->msr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CTR"))
+ regs->ctr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("LR"))
+ regs->link = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("XER"))
+ regs->xer = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("CR"))
+ regs->ccr = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DAR"))
+ regs->dar = (unsigned long)reg_val;
+ else if (reg_id == REG_ID("DSISR"))
+ regs->dsisr = (unsigned long)reg_val;
+}
+
+static struct fadump_reg_entry*
+fadump_read_registers(struct fadump_reg_entry *reg_entry, struct pt_regs *regs)
+{
+ memset(regs, 0, sizeof(struct pt_regs));
+
+ while (reg_entry->reg_id != REG_ID("CPUEND")) {
+ fadump_set_regval(regs, reg_entry->reg_id,
+ reg_entry->reg_value);
+ reg_entry++;
+ }
+ reg_entry++;
+ return reg_entry;
+}
+
+static u32 *fadump_append_elf_note(u32 *buf, char *name, unsigned type,
+ void *data, size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, ¬e, sizeof(note));
+ buf += (sizeof(note) + 3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+static void fadump_final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, ¬e, sizeof(note));
+}
+
+static u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs)
+{
+ struct elf_prstatus prstatus;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ /*
+ * FIXME: How do i get PID? Do I really need it?
+ * prstatus.pr_pid = ????
+ */
+ elf_core_copy_kernel_regs(&prstatus.pr_reg, regs);
+ buf = fadump_append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS,
+ &prstatus, sizeof(prstatus));
+ return buf;
+}
+
+static void fadump_update_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /* First note is a place holder for cpu notes info. */
+ phdr = (struct elf_phdr *)bufp;
+
+ if (phdr->p_type == PT_NOTE) {
+ phdr->p_paddr = fw_dump.cpu_notes_buf;
+ phdr->p_offset = phdr->p_paddr;
+ phdr->p_filesz = fw_dump.cpu_notes_buf_size;
+ phdr->p_memsz = fw_dump.cpu_notes_buf_size;
+ }
+ return;
+}
+
+static void *fadump_cpu_notes_buf_alloc(unsigned long size)
+{
+ void *vaddr;
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ vaddr = (void *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, order);
+ if (!vaddr)
+ return NULL;
+
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ SetPageReserved(page + i);
+ return vaddr;
+}
+
+static void fadump_cpu_notes_buf_free(unsigned long vaddr, unsigned long size)
+{
+ struct page *page;
+ unsigned long order, count, i;
+
+ order = get_order(size);
+ count = 1 << order;
+ page = virt_to_page(vaddr);
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+}
+
+/*
+ * Read CPU state dump data and convert it into ELF notes.
+ * The CPU dump starts with magic number "REGSAVE". NumCpusOffset should be
+ * used to access the data to allow for additional fields to be added without
+ * affecting compatibility. Each list of registers for a CPU starts with
+ * "CPUSTRT" and ends with "CPUEND". Each register entry is of 16 bytes,
+ * 8 Byte ASCII identifier and 8 Byte register value. The register entry
+ * with identifier "CPUSTRT" and "CPUEND" contains 4 byte cpu id as part
+ * of register value. For more details refer to PAPR document.
+ *
+ * Only for the crashing cpu we ignore the CPU dump data and get exact
+ * state from fadump crash info structure populated by first kernel at the
+ * time of crash.
+ */
+static int __init fadump_build_cpu_notes(const struct fadump_mem_struct *fdm)
+{
+ struct fadump_reg_save_area_header *reg_header;
+ struct fadump_reg_entry *reg_entry;
+ struct fadump_crash_info_header *fdh = NULL;
+ void *vaddr;
+ unsigned long addr;
+ u32 num_cpus, *note_buf;
+ struct pt_regs regs;
+ int i, rc = 0, cpu = 0;
+
+ if (!fdm->cpu_state_data.bytes_dumped)
+ return -EINVAL;
+
+ addr = fdm->cpu_state_data.destination_address;
+ vaddr = __va(addr);
+
+ reg_header = vaddr;
+ if (reg_header->magic_number != REGSAVE_AREA_MAGIC) {
+ printk(KERN_ERR "Unable to read register save area.\n");
+ return -ENOENT;
+ }
+ pr_debug("--------CPU State Data------------\n");
+ pr_debug("Magic Number: %llx\n", reg_header->magic_number);
+ pr_debug("NumCpuOffset: %x\n", reg_header->num_cpu_offset);
+
+ vaddr += reg_header->num_cpu_offset;
+ num_cpus = *((u32 *)(vaddr));
+ pr_debug("NumCpus : %u\n", num_cpus);
+ vaddr += sizeof(u32);
+ reg_entry = (struct fadump_reg_entry *)vaddr;
+
+ /* Allocate buffer to hold cpu crash notes. */
+ fw_dump.cpu_notes_buf_size = num_cpus * sizeof(note_buf_t);
+ fw_dump.cpu_notes_buf_size = PAGE_ALIGN(fw_dump.cpu_notes_buf_size);
+ note_buf = fadump_cpu_notes_buf_alloc(fw_dump.cpu_notes_buf_size);
+ if (!note_buf) {
+ printk(KERN_ERR "Failed to allocate 0x%lx bytes for "
+ "cpu notes buffer\n", fw_dump.cpu_notes_buf_size);
+ return -ENOMEM;
+ }
+ fw_dump.cpu_notes_buf = __pa(note_buf);
+
+ pr_debug("Allocated buffer for cpu notes of size %ld at %p\n",
+ (num_cpus * sizeof(note_buf_t)), note_buf);
+
+ if (fw_dump.fadumphdr_addr)
+ fdh = __va(fw_dump.fadumphdr_addr);
+
+ for (i = 0; i < num_cpus; i++) {
+ if (reg_entry->reg_id != REG_ID("CPUSTRT")) {
+ printk(KERN_ERR "Unable to read CPU state data\n");
+ rc = -ENOENT;
+ goto error_out;
+ }
+ /* Lower 4 bytes of reg_value contains logical cpu id */
+ cpu = reg_entry->reg_value & FADUMP_CPU_ID_MASK;
+ if (!cpumask_test_cpu(cpu, &fdh->cpu_online_mask)) {
+ SKIP_TO_NEXT_CPU(reg_entry);
+ continue;
+ }
+ pr_debug("Reading register data for cpu %d...\n", cpu);
+ if (fdh && fdh->crashing_cpu == cpu) {
+ regs = fdh->regs;
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ SKIP_TO_NEXT_CPU(reg_entry);
+ } else {
+ reg_entry++;
+ reg_entry = fadump_read_registers(reg_entry, ®s);
+ note_buf = fadump_regs_to_elf_notes(note_buf, ®s);
+ }
+ }
+ fadump_final_note(note_buf);
+
+ pr_debug("Updating elfcore header (%llx) with cpu notes\n",
+ fdh->elfcorehdr_addr);
+ fadump_update_elfcore_header((char *)__va(fdh->elfcorehdr_addr));
+ return 0;
+
+error_out:
+ fadump_cpu_notes_buf_free((unsigned long)__va(fw_dump.cpu_notes_buf),
+ fw_dump.cpu_notes_buf_size);
+ fw_dump.cpu_notes_buf = 0;
+ fw_dump.cpu_notes_buf_size = 0;
+ return rc;
+
+}
+
/*
* Validate and process the dump data stored by firmware before exporting
* it through '/proc/vmcore'.
@@ -400,18 +680,21 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
{
struct fadump_crash_info_header *fdh;
+ int rc = 0;
if (!fdm_active || !fw_dump.fadumphdr_addr)
return -EINVAL;
/* Check if the dump data is valid. */
if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+ (fdm_active->cpu_state_data.error_flags != 0) ||
(fdm_active->rmr_region.error_flags != 0)) {
printk(KERN_ERR "Dump taken by platform is not valid\n");
return -EINVAL;
}
- if (fdm_active->rmr_region.bytes_dumped !=
- fdm_active->rmr_region.source_len) {
+ if ((fdm_active->rmr_region.bytes_dumped !=
+ fdm_active->rmr_region.source_len) ||
+ !fdm_active->cpu_state_data.bytes_dumped) {
printk(KERN_ERR "Dump taken by platform is incomplete\n");
return -EINVAL;
}
@@ -423,6 +706,10 @@ static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
return -EINVAL;
}
+ rc = fadump_build_cpu_notes(fdm_active);
+ 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
@@ -537,6 +824,27 @@ static int fadump_create_elfcore_headers(char *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.
+ *
+ * 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;
+
+ (elf->e_phnum)++;
+
/* setup PT_LOAD sections. */
for (i = 0; i < crash_mem_ranges; i++) {
@@ -588,6 +896,8 @@ 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;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = CPU_UNKNOWN;
return addr;
}
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 77bb77d..4e62a56 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -61,6 +61,7 @@
#include <asm/xmon.h>
#include <asm/cputhreads.h>
#include <mm/mmu_decl.h>
+#include <asm/fadump.h>
#include "setup.h"
@@ -639,6 +640,11 @@ EXPORT_SYMBOL(check_legacy_ioport);
static int ppc_panic_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
+ /*
+ * If firmware-assisted dump has been registered then trigger
+ * firmware-assisted dump and let firmware handle everything else.
+ */
+ crash_fadump(NULL, ptr);
ppc_md.panic(ptr); /* May not return */
return NOTIFY_DONE;
}
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c091527..5d40e59 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -57,6 +57,7 @@
#include <asm/kexec.h>
#include <asm/ppc-opcode.h>
#include <asm/rio.h>
+#include <asm/fadump.h>
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
int (*__debugger)(struct pt_regs *regs) __read_mostly;
@@ -145,6 +146,8 @@ static void __kprobes oops_end(unsigned long flags, struct pt_regs *regs,
arch_spin_unlock(&die_lock);
raw_local_irq_restore(flags);
+ crash_fadump(regs, "die oops");
+
/*
* A system reset (0x100) is a request to dump, so we always send
* it through the crashdump code.
^ permalink raw reply related
* [RFC PATCH v7 04/10] fadump: Initialize elfcore header and add PT_LOAD program headers.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Build the crash memory range list by traversing through system memory during
the first kernel before we register for firmware-assisted dump. After the
successful dump registration, initialize the elfcore header and populate
PT_LOAD program headers with crash memory ranges. The elfcore header is
saved in the scratch area within the reserved memory. The scratch area starts
at the end of the memory reserved for saving RMR region contents. The
scratch area contains fadump crash info structure that contains magic number
for fadump validation and physical address where the eflcore header can be
found. This structure will also be used to pass some important crash info
data to the second kernel which will help second kernel to populate ELF core
header with correct data before it gets exported through /proc/vmcore. Since
the firmware preserves the entire partition memory at the time of crash the
contents of the scratch area will be preserved till second kernel boot.
Since the memory dump exported through /proc/vmcore is in ELF format similar
to kdump, it will help us to reuse the kdump infrastructure for dump capture
and filtering. Unlike phyp dump, userspace tool does not need to refer any
sysfs interface while reading /proc/vmcore.
NOTE: The current design implementation does not address a possibility of
introducing additional fields (in future) to this structure without affecting
compatibility. It's on TODO list to come up with better approach to
address this.
Reserved dump area start => +-------------------------------------+
| CPU state dump data |
+-------------------------------------+
| HPTE region data |
+-------------------------------------+
| RMR region data |
Scratch area start => +-------------------------------------+
| fadump crash info structure { |
| magic nummber |
+------|---- elfcorehdr_addr |
| | } |
+----> +-------------------------------------+
| ELF core header |
Reserved dump area end => +-------------------------------------+
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/fadump.h | 43 +++++++
arch/powerpc/kernel/fadump.c | 233 +++++++++++++++++++++++++++++++++++++
2 files changed, 275 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
index bbaf278..9e172a5 100644
--- a/arch/powerpc/include/asm/fadump.h
+++ b/arch/powerpc/include/asm/fadump.h
@@ -43,6 +43,12 @@
#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+ (0x1UL << 26))
+#define memblock_num_regions(memblock_type) (memblock.memblock_type.cnt)
+
+#ifndef ELF_CORE_EFLAGS
+#define ELF_CORE_EFLAGS 0
+#endif
+
/* Firmware provided dump sections */
#define FADUMP_CPU_STATE_DATA 0x0001
#define FADUMP_HPTE_REGION 0x0002
@@ -56,6 +62,9 @@
#define FADUMP_UNREGISTER 2
#define FADUMP_INVALIDATE 3
+/* Dump status flag */
+#define FADUMP_ERROR_FLAG 0x2000
+
/* Kernel Dump section info */
struct fadump_section {
u32 request_flag;
@@ -109,6 +118,7 @@ struct fw_dump {
/* cmd line option during boot */
unsigned long reserve_bootvar;
+ unsigned long fadumphdr_addr;
int ibm_configure_kernel_dump;
unsigned long fadump_enabled:1;
@@ -117,6 +127,39 @@ struct fw_dump {
unsigned long dump_registered:1;
};
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ * The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 str_to_u64(const char *str)
+{
+ u64 val = 0;
+ int i;
+
+ for (i = 0; i < sizeof(val); i++)
+ val = (*str) ? (val << 8) | *str++ : val << 8;
+ return val;
+}
+#define STR_TO_HEX(x) str_to_u64(x)
+
+#define FADUMP_CRASH_INFO_MAGIC STR_TO_HEX("FADMPINF")
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+ u64 magic_number;
+ u64 elfcorehdr_addr;
+};
+
+/* Crash memory ranges */
+#define INIT_CRASHMEM_RANGES (INIT_MEMBLOCK_REGIONS + 2)
+
+struct fad_crash_memory_ranges {
+ unsigned long long base;
+ unsigned long long size;
+};
+
extern int early_init_dt_scan_fw_dump(unsigned long node,
const char *uname, int depth, void *data);
extern int fadump_reserve_mem(void);
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 13c22cd..f85a63f 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -32,6 +32,7 @@
#include <linux/delay.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
+#include <linux/crash_dump.h>
#include <asm/page.h>
#include <asm/prom.h>
@@ -43,6 +44,8 @@ static struct fadump_mem_struct fdm;
static const struct fadump_mem_struct *fdm_active;
static DEFINE_MUTEX(fadump_mutex);
+struct fad_crash_memory_ranges crash_memory_ranges[INIT_CRASHMEM_RANGES];
+int crash_mem_ranges;
/* Scan the Firmware Assisted dump configuration details. */
int __init early_init_dt_scan_fw_dump(unsigned long node,
@@ -235,6 +238,10 @@ static unsigned long get_fadump_area_size(void)
size += fw_dump.cpu_state_data_size;
size += fw_dump.hpte_region_size;
size += fw_dump.boot_memory_size;
+ size += sizeof(struct fadump_crash_info_header);
+ size += sizeof(struct elfhdr); /* ELF core header.*/
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
size = PAGE_ALIGN(size);
return size;
@@ -300,6 +307,12 @@ int __init fadump_reserve_mem(void)
"for saving crash dump\n",
(unsigned long)(size >> 20),
(unsigned long)(base >> 20));
+
+ fw_dump.fadumphdr_addr =
+ fdm_active->rmr_region.destination_address +
+ fdm_active->rmr_region.source_len;
+ pr_debug("fadumphdr_addr = %p\n",
+ (void *) fw_dump.fadumphdr_addr);
} else {
/* Reserve the memory at the top of memory. */
size = get_fadump_area_size();
@@ -380,8 +393,210 @@ static void register_fw_dump(struct fadump_mem_struct *fdm)
}
}
+/*
+ * Validate and process the dump data stored by firmware before exporting
+ * it through '/proc/vmcore'.
+ */
+static int __init process_fadump(const struct fadump_mem_struct *fdm_active)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!fdm_active || !fw_dump.fadumphdr_addr)
+ return -EINVAL;
+
+ /* Check if the dump data is valid. */
+ if ((fdm_active->header.dump_status_flag == FADUMP_ERROR_FLAG) ||
+ (fdm_active->rmr_region.error_flags != 0)) {
+ printk(KERN_ERR "Dump taken by platform is not valid\n");
+ return -EINVAL;
+ }
+ if (fdm_active->rmr_region.bytes_dumped !=
+ fdm_active->rmr_region.source_len) {
+ printk(KERN_ERR "Dump taken by platform is incomplete\n");
+ return -EINVAL;
+ }
+
+ /* Validate the fadump crash info header */
+ fdh = __va(fw_dump.fadumphdr_addr);
+ if (fdh->magic_number != FADUMP_CRASH_INFO_MAGIC) {
+ printk(KERN_ERR "Crash info header is not valid.\n");
+ return -EINVAL;
+ }
+
+ /*
+ * 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;
+}
+
+static inline void fadump_add_crash_memory(unsigned long long base,
+ unsigned long long end)
+{
+ if (base == end)
+ return;
+
+ pr_debug("crash_memory_range[%d] [%#016llx-%#016llx], %#llx bytes\n",
+ crash_mem_ranges, base, end - 1, (end - base));
+ crash_memory_ranges[crash_mem_ranges].base = base;
+ crash_memory_ranges[crash_mem_ranges].size = end - base;
+ crash_mem_ranges++;
+}
+
+static void fadump_exclude_reserved_area(unsigned long long start,
+ unsigned long long end)
+{
+ unsigned long long ra_start, ra_end;
+
+ 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)) {
+ fadump_add_crash_memory(start, ra_start);
+ fadump_add_crash_memory(ra_end, end);
+ } else if (start < ra_start) {
+ fadump_add_crash_memory(start, ra_start);
+ } else if (ra_end < end) {
+ fadump_add_crash_memory(ra_end, end);
+ }
+ } else
+ fadump_add_crash_memory(start, end);
+}
+
+static int fadump_init_elfcore_header(char *bufp)
+{
+ struct elfhdr *elf;
+
+ elf = (struct elfhdr *) bufp;
+ bufp += sizeof(struct elfhdr);
+ memcpy(elf->e_ident, ELFMAG, SELFMAG);
+ elf->e_ident[EI_CLASS] = ELF_CLASS;
+ elf->e_ident[EI_DATA] = ELF_DATA;
+ elf->e_ident[EI_VERSION] = EV_CURRENT;
+ elf->e_ident[EI_OSABI] = ELF_OSABI;
+ memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
+ elf->e_type = ET_CORE;
+ elf->e_machine = ELF_ARCH;
+ elf->e_version = EV_CURRENT;
+ elf->e_entry = 0;
+ elf->e_phoff = sizeof(struct elfhdr);
+ elf->e_shoff = 0;
+ elf->e_flags = ELF_CORE_EFLAGS;
+ elf->e_ehsize = sizeof(struct elfhdr);
+ elf->e_phentsize = sizeof(struct elf_phdr);
+ elf->e_phnum = 0;
+ elf->e_shentsize = 0;
+ elf->e_shnum = 0;
+ elf->e_shstrndx = 0;
+
+ return 0;
+}
+
+/*
+ * Traverse through memblock structure and setup crash memory ranges. These
+ * ranges will be used create PT_LOAD program headers in elfcore header.
+ */
+static void fadump_setup_crash_memory_ranges(void)
+{
+ struct memblock_region *reg;
+ unsigned long long start, end;
+
+ pr_debug("Setup crash memory ranges.\n");
+ crash_mem_ranges = 0;
+ /*
+ * add the first memory chunk (RMA_START through boot_memory_size) as
+ * a separate memory chunk. The reason is, at the time crash firmware
+ * will move the content of this memory chunk to different location
+ * specified during fadump registration. We need to create a separate
+ * program header for this chunk with the correct offset.
+ */
+ fadump_add_crash_memory(RMA_START, fw_dump.boot_memory_size);
+
+ for_each_memblock(memory, reg) {
+ start = (unsigned long long)reg->base;
+ end = start + (unsigned long long)reg->size;
+ if (start == RMA_START && end >= fw_dump.boot_memory_size)
+ start = fw_dump.boot_memory_size;
+
+ /* add this range excluding the reserved dump area. */
+ fadump_exclude_reserved_area(start, end);
+ }
+}
+
+static int fadump_create_elfcore_headers(char *bufp)
+{
+ struct elfhdr *elf;
+ struct elf_phdr *phdr;
+ int i;
+
+ fadump_init_elfcore_header(bufp);
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /* setup PT_LOAD sections. */
+
+ for (i = 0; i < crash_mem_ranges; i++) {
+ unsigned long long mbase, msize;
+ mbase = crash_memory_ranges[i].base;
+ msize = crash_memory_ranges[i].size;
+
+ if (!msize)
+ continue;
+
+ 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 == RMA_START) {
+ /*
+ * The entire RMA region will be moved by firmware
+ * to the specified destination_address. Hence set
+ * the correct offset.
+ */
+ phdr->p_offset = fdm.rmr_region.destination_address;
+ }
+
+ phdr->p_paddr = mbase;
+ phdr->p_vaddr = (unsigned long)__va(mbase);
+ phdr->p_filesz = msize;
+ phdr->p_memsz = msize;
+ phdr->p_align = 0;
+
+ /* Increment number of program headers. */
+ (elf->e_phnum)++;
+ }
+ return 0;
+}
+
+static unsigned long init_fadump_header(unsigned long addr)
+{
+ struct fadump_crash_info_header *fdh;
+
+ if (!addr)
+ return 0;
+
+ fw_dump.fadumphdr_addr = addr;
+ fdh = __va(addr);
+ addr += sizeof(struct fadump_crash_info_header);
+
+ memset(fdh, 0, sizeof(struct fadump_crash_info_header));
+ fdh->magic_number = FADUMP_CRASH_INFO_MAGIC;
+ fdh->elfcorehdr_addr = addr;
+
+ return addr;
+}
+
static void register_fadump(void)
{
+ unsigned long addr;
+ void *vaddr;
+
/*
* If no memory is reserved then we can not register for firmware-
* assisted dump.
@@ -389,6 +604,16 @@ static void register_fadump(void)
if (!fw_dump.reserve_dump_area_size)
return;
+ fadump_setup_crash_memory_ranges();
+
+ addr = fdm.rmr_region.destination_address + fdm.rmr_region.source_len;
+ /* 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. */
register_fw_dump(&fdm);
}
@@ -582,8 +807,14 @@ int __init setup_fadump(void)
}
fadump_show_config();
+ /*
+ * If dump data is available then see if it is valid and prepare for
+ * saving it to the disk.
+ */
+ if (fw_dump.dump_active)
+ process_fadump(fdm_active);
/* Initialize the kernel dump memory structure for FAD registration. */
- if (fw_dump.reserve_dump_area_size)
+ else if (fw_dump.reserve_dump_area_size)
init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
fadump_init_files();
^ permalink raw reply related
* [RFC PATCH v7 02/10] fadump: Reserve the memory for firmware assisted dump.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
In-Reply-To: <20120216111050.4733.38034.stgit@mars>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reserve the memory during early boot to preserve CPU state data, HPTE region
and RMA (real mode area) region data in case of kernel crash. At the time of
crash, powerpc firmware will store CPU state data, HPTE region data and move
RMA region data to the reserved memory area.
If the firmware-assisted dump fails to reserve the memory, then fallback
to existing kexec-based kdump.
Most of the code implementation to reserve memory has been
adapted from phyp assisted dump implementation written by Linas Vepstas
and Manish Ahuja
This patch also introduces a config option CONFIG_FA_DUMP for firmware
assisted dump feature on Powerpc (ppc64) architecture.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
---
arch/powerpc/Kconfig | 13 ++
arch/powerpc/include/asm/fadump.h | 71 +++++++++++
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/fadump.c | 246 +++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/prom.c | 15 ++
5 files changed, 345 insertions(+), 1 deletions(-)
create mode 100644 arch/powerpc/include/asm/fadump.h
create mode 100644 arch/powerpc/kernel/fadump.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1919634..afa4dab 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -386,6 +386,19 @@ config PHYP_DUMP
If unsure, say "N"
+config FA_DUMP
+ bool "Firmware-assisted dump"
+ depends on PPC64 && PPC_RTAS && CRASH_DUMP
+ help
+ A robust mechanism to get reliable kernel crash dump with
+ assistance from firmware. This approach does not use kexec,
+ instead firmware assists in booting the kdump kernel
+ while preserving memory contents. Firmware-assisted dump
+ is meant to be a kdump replacement offering robustness and
+ speed not possible without system firmware assistance.
+
+ If unsure, say "N"
+
config IRQ_ALL_CPUS
bool "Distribute interrupts on all CPUs by default"
depends on SMP && !MV64360
diff --git a/arch/powerpc/include/asm/fadump.h b/arch/powerpc/include/asm/fadump.h
new file mode 100644
index 0000000..7be25d3
--- /dev/null
+++ b/arch/powerpc/include/asm/fadump.h
@@ -0,0 +1,71 @@
+/*
+ * Firmware Assisted dump header file.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef __PPC64_FA_DUMP_H__
+#define __PPC64_FA_DUMP_H__
+
+#ifdef CONFIG_FA_DUMP
+
+/*
+ * The RMA region will be saved for later dumping when kernel crashes.
+ * RMA is Real Mode Area, the first block of logical memory address owned
+ * by logical partition, containing the storage that may be accessed with
+ * translate off.
+ */
+#define RMA_START 0x0
+#define RMA_END (ppc64_rma_size)
+
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need aditional 64M
+ * of memory to avoid OOM issue.
+ */
+#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
+ + (0x1UL << 26))
+
+/* Firmware provided dump sections */
+#define FADUMP_CPU_STATE_DATA 0x0001
+#define FADUMP_HPTE_REGION 0x0002
+#define FADUMP_REAL_MODE_REGION 0x0011
+
+struct fw_dump {
+ unsigned long cpu_state_data_size;
+ unsigned long hpte_region_size;
+ unsigned long boot_memory_size;
+ unsigned long reserve_dump_area_start;
+ unsigned long reserve_dump_area_size;
+ /* cmd line option during boot */
+ unsigned long reserve_bootvar;
+
+ int ibm_configure_kernel_dump;
+
+ unsigned long fadump_enabled:1;
+ unsigned long fadump_supported:1;
+ unsigned long dump_active:1;
+};
+
+extern int early_init_dt_scan_fw_dump(unsigned long node,
+ const char *uname, int depth, void *data);
+extern int fadump_reserve_mem(void);
+#endif
+#endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e4..391bf7e 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -60,6 +60,7 @@ obj-$(CONFIG_IBMVIO) += vio.o
obj-$(CONFIG_IBMEBUS) += ibmebus.o
obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+obj-$(CONFIG_FA_DUMP) += fadump.o
ifeq ($(CONFIG_PPC32),y)
obj-$(CONFIG_E500) += idle_e500.o
endif
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
new file mode 100644
index 0000000..deb276a
--- /dev/null
+++ b/arch/powerpc/kernel/fadump.c
@@ -0,0 +1,246 @@
+/*
+ * Firmware Assisted dump: A robust mechanism to get reliable kernel crash
+ * dump with assistance from firmware. This approach does not use kexec,
+ * instead firmware assists in booting the kdump kernel while preserving
+ * memory contents. The most of the code implementation has been adapted
+ * from phyp assisted dump implementation written by Linas Vepstas and
+ * Manish Ahuja
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#undef DEBUG
+#define pr_fmt(fmt) "fadump: " fmt
+
+#include <linux/string.h>
+#include <linux/memblock.h>
+
+#include <asm/page.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+#include <asm/fadump.h>
+
+static struct fw_dump fw_dump;
+
+/* 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)
+{
+ __be32 *sections;
+ int i, num_sections;
+ unsigned long size;
+ const int *token;
+
+ if (depth != 1 || strcmp(uname, "rtas") != 0)
+ return 0;
+
+ /*
+ * Check if Firmware Assisted dump is supported. if yes, check
+ * if dump has been initiated on last reboot.
+ */
+ token = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump", NULL);
+ if (!token)
+ return 0;
+
+ fw_dump.fadump_supported = 1;
+ fw_dump.ibm_configure_kernel_dump = *token;
+
+ /*
+ * The 'ibm,kernel-dump' rtas node is present only if there is
+ * dump data waiting for us.
+ */
+ if (of_get_flat_dt_prop(node, "ibm,kernel-dump", NULL))
+ fw_dump.dump_active = 1;
+
+ /* Get the sizes required to store dump data for the firmware provided
+ * dump sections.
+ * For each dump section type supported, a 32bit cell which defines
+ * the ID of a supported section followed by two 32 bit cells which
+ * gives teh size of the section in bytes.
+ */
+ sections = of_get_flat_dt_prop(node, "ibm,configure-kernel-dump-sizes",
+ &size);
+
+ if (!sections)
+ return 0;
+
+ num_sections = size / (3 * sizeof(u32));
+
+ for (i = 0; i < num_sections; i++, sections += 3) {
+ u32 type = (u32)of_read_number(sections, 1);
+
+ switch (type) {
+ case FADUMP_CPU_STATE_DATA:
+ fw_dump.cpu_state_data_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ case FADUMP_HPTE_REGION:
+ fw_dump.hpte_region_size =
+ of_read_ulong(§ions[1], 2);
+ break;
+ }
+ }
+ return 1;
+}
+
+/**
+ * fadump_calculate_reserve_size(): reserve variable boot area 5% of System RAM
+ *
+ * Function to find the largest memory size we need to reserve during early
+ * boot process. This will be the size of the memory that is required for a
+ * kernel to boot successfully.
+ *
+ * This function has been taken from phyp-assisted dump feature implementation.
+ *
+ * returns larger of 256MB or 5% rounded down to multiples of 256MB.
+ *
+ * TODO: Come up with better approach to find out more accurate memory size
+ * that is required for a kernel to boot successfully.
+ *
+ */
+static inline unsigned long fadump_calculate_reserve_size(void)
+{
+ unsigned long size;
+
+ /*
+ * Check if the size is specified through fadump_reserve_mem= cmdline
+ * option. If yes, then use that.
+ */
+ if (fw_dump.reserve_bootvar)
+ return fw_dump.reserve_bootvar;
+
+ /* divide by 20 to get 5% of value */
+ size = memblock_end_of_DRAM() / 20;
+
+ /* round it down in multiples of 256 */
+ size = size & ~0x0FFFFFFFUL;
+
+ /* Truncate to memory_limit. We don't want to over reserve the memory.*/
+ if (memory_limit && size > memory_limit)
+ size = memory_limit;
+
+ return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+}
+
+/*
+ * Calculate the total memory size required to be reserved for
+ * firmware-assisted dump registration.
+ */
+static unsigned long get_fadump_area_size(void)
+{
+ unsigned long size = 0;
+
+ size += fw_dump.cpu_state_data_size;
+ size += fw_dump.hpte_region_size;
+ size += fw_dump.boot_memory_size;
+
+ size = PAGE_ALIGN(size);
+ return size;
+}
+
+int __init fadump_reserve_mem(void)
+{
+ unsigned long base, size, memory_boundary;
+
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_INFO "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ fw_dump.fadump_enabled = 0;
+ return 0;
+ }
+ /* Initialize boot memory size */
+ fw_dump.boot_memory_size = fadump_calculate_reserve_size();
+
+ /*
+ * 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",
+ (unsigned long long)memory_limit);
+ }
+ if (memory_limit)
+ memory_boundary = memory_limit;
+ else
+ memory_boundary = memblock_end_of_DRAM();
+
+ if (fw_dump.dump_active) {
+ printk(KERN_INFO "Firmware-assisted dump is active.\n");
+ /*
+ * If last boot has crashed then reserve all the memory
+ * above boot_memory_size so that we don't touch it until
+ * dump is written to disk by userspace tool. This memory
+ * will be released for general use once the dump is saved.
+ */
+ base = fw_dump.boot_memory_size;
+ size = memory_boundary - base;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for saving crash dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+ } else {
+ /* Reserve the memory at the top of memory. */
+ size = get_fadump_area_size();
+ base = memory_boundary - size;
+ memblock_reserve(base, size);
+ printk(KERN_INFO "Reserved %ldMB of memory at %ldMB "
+ "for firmware-assisted dump\n",
+ (unsigned long)(size >> 20),
+ (unsigned long)(base >> 20));
+ }
+ fw_dump.reserve_dump_area_start = base;
+ fw_dump.reserve_dump_area_size = size;
+ return 1;
+}
+
+/* Look for fadump= cmdline option. */
+static int __init early_fadump_param(char *p)
+{
+ if (!p)
+ return 1;
+
+ if (strncmp(p, "on", 2) == 0)
+ fw_dump.fadump_enabled = 1;
+ else if (strncmp(p, "off", 3) == 0)
+ fw_dump.fadump_enabled = 0;
+
+ return 0;
+}
+early_param("fadump", early_fadump_param);
+
+/* Look for fadump_reserve_mem= cmdline option */
+static int __init early_fadump_reserve_mem(char *p)
+{
+ if (p)
+ fw_dump.reserve_bootvar = memparse(p, &p);
+ return 0;
+}
+early_param("fadump_reserve_mem", early_fadump_reserve_mem);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index abe405d..70222b3 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -55,6 +55,7 @@
#include <asm/phyp_dump.h>
#include <asm/kexec.h>
#include <asm/opal.h>
+#include <asm/fadump.h>
#include <mm/mmu_decl.h>
@@ -719,6 +720,11 @@ void __init early_init_devtree(void *params)
of_scan_flat_dt(early_init_dt_scan_phyp_dump, NULL);
#endif
+#ifdef CONFIG_FA_DUMP
+ /* scan tree to see if dump is active during last boot */
+ of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
+#endif
+
/* Pre-initialize the cmd_line with the content of boot_commmand_line,
* which will be empty except when the content of the variable has
* been overriden by a bootloading mechanism. This happens typically
@@ -750,7 +756,14 @@ void __init early_init_devtree(void *params)
if (PHYSICAL_START > MEMORY_START)
memblock_reserve(MEMORY_START, 0x8000);
reserve_kdump_trampoline();
- reserve_crashkernel();
+#ifdef CONFIG_FA_DUMP
+ /*
+ * If we fail to reserve memory for firmware-assisted dump then
+ * fallback to kexec based kdump.
+ */
+ if (fadump_reserve_mem() == 0)
+#endif
+ reserve_crashkernel();
early_reserve_mem();
phyp_dump_reserve_mem();
^ permalink raw reply related
* [RFC PATCH v7 00/10] fadump: Firmware-assisted dump support for Powerpc.
From: Mahesh J Salgaonkar @ 2012-02-16 11:14 UTC (permalink / raw)
To: linuxppc-dev, Linux Kernel, Benjamin Herrenschmidt
Cc: Anton Blanchard, Amerigo Wang, Kexec-ml, Milton Miller,
Randy Dunlap, Paul Mackerras, Eric W. Biederman, Vivek Goyal
Hi All,
Please find the version 7 of the patchset that implements firmware-assisted
dump mechanism to capture kernel crash dump for Powerpc architecture.
Firmware-assisted dump is a robust mechanism to get reliable kernel crash
dump with the assistance of firmware. This approach does not use kexec,
instead firmware assists in booting the kdump kernel while preserving memory
contents.
- Firmware assisted dump (fadump) infrastructure is intended to replace
the existing phyp assisted dump.
- Fadump uses the same firmware interfaces and memory reservation model
as phyp assisted dump.
- Unlike phyp dump, fadump exports the memory dump through /proc/vmcore
in the ELF format in the same way as kdump. This helps us reuse the
kdump infrastructure for dump capture and filtering.
- Unlike phyp dump, userspace tool does not need to refer any sysfs
interface while reading /proc/vmcore.
- Unlike phyp dump, fadump allows user to release all the memory reserved
for dump, with a single operation of echo 1 > /sys/kernel/fadump_release_mem.
- Once enabled through kernel boot parameter, fadump can be
started/stopped through /sys/kernel/fadump_registered interface and
can be easily integrated with kdump service start/stop init scripts.
- Once the dump is copied out, the memory that held the dump is
immediately available to the running kernel. And therefore, unlike
kdump, fadump doesn't need a 2nd reboot to get back the system to
the production configuration.
Fadump reuses much of the code written by Manish Ahuja and Linas Vepstas
for the phyp assisted dump.
I have tested the patches on following system configuration:
1. LPAR on Power6 with 4GB RAM and 8 CPUs
2. LPAR on Power7 with 2GB RAM and 20 CPUs
3. LPAR on Power7 with 1TB RAM and 896 CPUs
Please review the patchset and let me know your comments.
ChangeLog:
Change in v7:
-------------
- Updated the documentation explaining the enhancement in fadump over old
phyp dump.
- Re-based patches to commit d65b4e98d7 (v3.3-rc3)
Change in v6:
-------------
- Use of_read_number and of_read_ulong while reading the dump sizes
from rtas node ibm,configure-kernel-kdump-sizes and few minor changes.
- Kernel command line option 'fadump' now uses on/off values to
enable/disable fadump.
- Added the last patch in this series 10/10 to remove phyp dump code.
Change in v5:
-------------
- Added 'fadump_' prefix to all static functions defined.
patch 02/10:
- Merged patch 10/10 which introduces a config option CONFIG_FA_DUMP
for firmware assisted dump feature on Powerpc (ppc64) architecture.
- Increased MIN_BOOT_MEM by 64M to avoid OOM issue during network
dump capture. When kdump infrastructure is configured to save vmcore
over network, we run into OOM issue while loading modules related to
network setup.
Changes in v4:
--------------
patch 04/10:
- Move the init_elfcore_header() function and 'memblock_num_regions' macro
from generic code to power specific code as these are used only by
firmware assisted dump implementation which is power specific feature.
patch 05/10:
- Fixes a issue where memblock_free() is invoked from build_cpu_notes()
function during error_out path. Invoke cpu_notes_buf_free() in error_out
path instead of memblock_free().
Changes in v3:
-------------
- Re-factored the implementation to work with kdump service start/stop.
Introduce fadump_registered sysfs control file which will be used by
kdump init scripts to start/stop firmware assisted dump. echo 1 to
/sys/kernel/fadump_registered file for fadump registration and
echo 0 to /sys/kernel/fadump_registered file for fadump un-registration.
- Introduced the locking mechanism to handle simultaneous writes to
sysfs control files fadump_registered and fadump_release_mem
Affected patches are: 01/10, 03/10, 08/10.
Changes in v2:
-------------
patch 01/10:
- Modified the documentation to reflect the change of fadump_region
file under debugfs filesystem.
patch 02/10:
- Modified to use standard pr_debug() macro.
- Modified early_init_dt_scan_fw_dump() to get the size of
"ibm,configure-kernel-dump-sizes" property and use it to iterate through
an array of dump sections.
- Introduced boot option 'fadump_reserve_mem=' to let user specify the
fadump boot memory to be reserved.
patch 03/10:
- Removed few debug print statements.
- Moved the setup_fadump() call from setup_system() and now calling it
subsys_initcall.
- Moved fadump_region attribute under debugfs.
- Clear the TCE entries if firmware assisted dump is active.
patch 05/10:
- Moved the crash_fadump() invocation from generic code to panic notifier.
- Introduced cpu_notes_buf_alloc() function to allocate cpu notes buffer
using get_free_pages().
patch 08/10:
- Introduced cpu_notes_buf_free() function to free memory allocated for
cpu notes buffer.
Thanks,
-Mahesh.
---
Mahesh Salgaonkar (10):
fadump: Add documentation for firmware-assisted dump.
fadump: Reserve the memory for firmware assisted dump.
fadump: Register for firmware assisted dump.
fadump: Initialize elfcore header and add PT_LOAD program headers.
fadump: Convert firmware-assisted cpu state dump data into elf notes.
fadump: Add PT_NOTE program header for vmcoreinfo
fadump: Introduce cleanup routine to invalidate /proc/vmcore.
fadump: Invalidate registration and release reserved memory for general use.
fadump: Invalidate the fadump registration during machine shutdown.
fadump: Remove the phyp assisted dump code.
Documentation/powerpc/firmware-assisted-dump.txt | 270 +++++
Documentation/powerpc/phyp-assisted-dump.txt | 127 --
arch/powerpc/Kconfig | 17
arch/powerpc/include/asm/fadump.h | 218 ++++
arch/powerpc/include/asm/phyp_dump.h | 47 -
arch/powerpc/kernel/Makefile | 1
arch/powerpc/kernel/fadump.c | 1312 ++++++++++++++++++++++
arch/powerpc/kernel/iommu.c | 8
arch/powerpc/kernel/prom.c | 98 --
arch/powerpc/kernel/setup-common.c | 14
arch/powerpc/kernel/traps.c | 3
arch/powerpc/mm/hash_utils_64.c | 11
arch/powerpc/platforms/pseries/Makefile | 1
arch/powerpc/platforms/pseries/phyp_dump.c | 513 ---------
fs/proc/vmcore.c | 23
15 files changed, 1881 insertions(+), 782 deletions(-)
create mode 100644 Documentation/powerpc/firmware-assisted-dump.txt
delete mode 100644 Documentation/powerpc/phyp-assisted-dump.txt
create mode 100644 arch/powerpc/include/asm/fadump.h
delete mode 100644 arch/powerpc/include/asm/phyp_dump.h
create mode 100644 arch/powerpc/kernel/fadump.c
delete mode 100644 arch/powerpc/platforms/pseries/phyp_dump.c
--
-Mahesh
^ permalink raw reply
* Re: [PATCH] powerpc/usb: fix bug of kernel hang when initializing usb
From: Benjamin Herrenschmidt @ 2012-02-16 10:39 UTC (permalink / raw)
To: Shengzhou Liu; +Cc: linux-usb, linuxppc-dev
In-Reply-To: <1329386540-12341-1-git-send-email-Shengzhou.Liu@freescale.com>
On Thu, 2012-02-16 at 18:02 +0800, Shengzhou Liu wrote:
> If USB UTMI PHY is not enable, writing to portsc register will lead to
> kernel hang during boot up.
Thanks, I'll try that tomorrow.
Greg, you're picking that up or should I ?
Cheers,
Ben.
> Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
> ---
> Apply for master branch of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
> Tested on P5020DS, the issue was reported by Benjamin Herrenschmidt.
>
> drivers/usb/host/ehci-fsl.c | 4 ++++
> drivers/usb/host/ehci-fsl.h | 1 +
> 2 files changed, 5 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
> index c26a82e..0090ed2 100644
> --- a/drivers/usb/host/ehci-fsl.c
> +++ b/drivers/usb/host/ehci-fsl.c
> @@ -216,6 +216,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
> unsigned int port_offset)
> {
> u32 portsc;
> + struct usb_hcd *hcd = ehci_to_hcd(ehci);
> + void __iomem *non_ehci = hcd->regs;
>
> portsc = ehci_readl(ehci, &ehci->regs->port_status[port_offset]);
> portsc &= ~(PORT_PTS_MSK | PORT_PTS_PTW);
> @@ -231,6 +233,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
> portsc |= PORT_PTS_PTW;
> /* fall through */
> case FSL_USB2_PHY_UTMI:
> + /* enable UTMI PHY */
> + setbits32(non_ehci + FSL_SOC_USB_CTRL, CTRL_UTMI_PHY_EN);
> portsc |= PORT_PTS_UTMI;
> break;
> case FSL_USB2_PHY_NONE:
> diff --git a/drivers/usb/host/ehci-fsl.h b/drivers/usb/host/ehci-fsl.h
> index bdf43e2..0e400c2 100644
> --- a/drivers/usb/host/ehci-fsl.h
> +++ b/drivers/usb/host/ehci-fsl.h
> @@ -45,6 +45,7 @@
> #define FSL_SOC_USB_PRICTRL 0x40c /* NOTE: big-endian */
> #define FSL_SOC_USB_SICTRL 0x410 /* NOTE: big-endian */
> #define FSL_SOC_USB_CTRL 0x500 /* NOTE: big-endian */
> +#define CTRL_UTMI_PHY_EN (1<<9)
> #define CTRL_PHY_CLK_VALID (1 << 17)
> #define SNOOP_SIZE_2GB 0x1e
> #endif /* _EHCI_FSL_H */
^ permalink raw reply
* Re: [PATCH v4 3/3] KVM: PPC: epapr: install ev_idle hcall for e500 guest
From: Alexander Graf @ 2012-02-16 10:24 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-3-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> If the guest hypervisor node contains "has-idle" property.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> 1. discard the CONFIG_E500 to make code for all powerpc platform
> 2. code cleanup
>=20
> arch/powerpc/kernel/epapr.S | 29 +++++++++++++++++++++++++++++
> arch/powerpc/kernel/epapr_para.c | 13 ++++++++++++-
> 2 files changed, 41 insertions(+), 1 deletions(-)
>=20
> diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
> index 697b390..f06d636 100644
> --- a/arch/powerpc/kernel/epapr.S
> +++ b/arch/powerpc/kernel/epapr.S
> @@ -15,6 +15,35 @@
> #include <asm/ppc_asm.h>
> #include <asm/asm-offsets.h>
>=20
> +#define HC_VENDOR_EPAPR (1 << 16)
> +#define HC_EV_IDLE 16
> +
> +_GLOBAL(epapr_ev_idle)
> +epapr_ev_idle:
> + rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */
> + lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
> + ori r4,r4,_TLF_NAPPING /* so when we take an exception */
> + stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
> +
> + wrteei 1
> +
> +idle_loop:
> + LOAD_REG_IMMEDIATE(r11, HC_VENDOR_EPAPR | HC_EV_IDLE)
> +
> +.global epapr_ev_idle_start
> +epapr_ev_idle_start:
> + li r3, -1
> + nop
> + nop
> + nop
Can't you just bl into epapr_hypercall_start? You don't even have to save th=
e old lr. because we never return anyways :)
Alex
> +
> + /*
> + * Guard against spurious wakeups (e.g. from a hypervisor) --
> + * any real interrupt will cause us to return to LR due to
> + * _TLF_NAPPING.
> + */
> + b idle_loop
> +
> /* Hypercall entry point. Will be patched with device tree instructions. *=
/
> .global epapr_hypercall_start
> epapr_hypercall_start:
> diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_=
para.c
> index ea13cac..adee4f1 100644
> --- a/arch/powerpc/kernel/epapr_para.c
> +++ b/arch/powerpc/kernel/epapr_para.c
> @@ -20,6 +20,10 @@
> #include <linux/of.h>
> #include <asm/epapr_hcalls.h>
> #include <asm/cacheflush.h>
> +#include <asm/machdep.h>
> +
> +extern void epapr_ev_idle(void);
> +extern u32 epapr_ev_idle_start[];
>=20
> bool epapr_para_enabled =3D false;
>=20
> @@ -35,10 +39,17 @@ static int __init epapr_para_init(void)
>=20
> insts =3D of_get_property(hyper_node, "hcall-instructions", &len);
> if (!(len % 4) && (len >=3D (4 * 4))) {
> - for (i =3D 0; i < (len / 4); i++)
> + for (i =3D 0; i < (len / 4); i++) {
> epapr_hypercall_start[i] =3D insts[i];
> + epapr_ev_idle_start[i] =3D insts[i];
> + }
> flush_icache_range((ulong)epapr_hypercall_start,
> (ulong)epapr_hypercall_start + len);
> + flush_icache_range((ulong)epapr_ev_idle_start,
> + (ulong)epapr_ev_idle_start + len);
> +
> + if (of_get_property(hyper_node, "has-idle", NULL))
> + ppc_md.power_save =3D epapr_ev_idle;
>=20
> epapr_para_enabled =3D true;
> }
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 2/3] KVM: PPC: epapr: Add idle hcall support for host
From: Alexander Graf @ 2012-02-16 10:20 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-2-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> And add a new flag definition in kvm_ppc_pvinfo to indicate
> whether host support EV_IDLE hcall.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> no change
>=20
> arch/powerpc/include/asm/kvm_para.h | 14 ++++++++++++--
> arch/powerpc/kvm/powerpc.c | 8 ++++++++
> include/linux/kvm.h | 2 ++
> 3 files changed, 22 insertions(+), 2 deletions(-)
>=20
> diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/as=
m/kvm_para.h
> index 7b754e7..81a34c9 100644
> --- a/arch/powerpc/include/asm/kvm_para.h
> +++ b/arch/powerpc/include/asm/kvm_para.h
> @@ -75,9 +75,19 @@ struct kvm_vcpu_arch_shared {
> };
>=20
> #define KVM_SC_MAGIC_R0 0x4b564d21 /* "KVM!" */
> -#define HC_VENDOR_KVM (42 << 16)
> +
> +#include <asm/epapr_hcalls.h>
> +
> +/* ePAPR Hypercall Vendor ID */
> +#define HC_VENDOR_EPAPR (EV_EPAPR_VENDOR_ID << 16)
> +#define HC_VENDOR_KVM (EV_KVM_VENDOR_ID << 16)
> +
> +/* ePAPR Hypercall Token */
> +#define HC_EV_IDLE EV_IDLE
> +
> +/* ePAPR Hypercall Return Codes */
> #define HC_EV_SUCCESS 0
> -#define HC_EV_UNIMPLEMENTED 12
> +#define HC_EV_UNIMPLEMENTED EV_UNIMPLEMENTED
>=20
> #define KVM_FEATURE_MAGIC_PAGE 1
>=20
> diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
> index 0e21d15..03ebd5d 100644
> --- a/arch/powerpc/kvm/powerpc.c
> +++ b/arch/powerpc/kvm/powerpc.c
> @@ -81,6 +81,10 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
>=20
> /* Second return value is in r4 */
> break;
> + case HC_VENDOR_EPAPR | HC_EV_IDLE:
> + r =3D HC_EV_SUCCESS;
> + kvm_vcpu_block(vcpu);
> + break;
> default:
> r =3D HC_EV_UNIMPLEMENTED;
> break;
> @@ -746,6 +750,10 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvi=
nfo *pvinfo)
> pvinfo->hcall[2] =3D inst_sc;
> pvinfo->hcall[3] =3D inst_nop;
>=20
> +#ifdef CONFIG_BOOKE
Why limit it to booke? The less ifdefs our code has, the better :)
Alex
> + pvinfo->flags |=3D KVM_PPC_PVINFO_FLAGS_EV_IDLE;
> +#endif
> +
> return 0;
> }
>=20
> diff --git a/include/linux/kvm.h b/include/linux/kvm.h
> index acbe429..6b2c70e 100644
> --- a/include/linux/kvm.h
> +++ b/include/linux/kvm.h
> @@ -449,6 +449,8 @@ struct kvm_ppc_pvinfo {
> __u8 pad[108];
> };
>=20
> +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
> +
> #define KVMIO 0xAE
>=20
> /* machine type bits, to be used as argument to KVM_CREATE_VM */
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [PATCH] powerpc/usb: fix issue of CPU halt when missing USB PHY clock
From: Liu Shengzhou-B36685 @ 2012-02-16 10:16 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: linuxppc-dev@lists.ozlabs.org, linux-usb@vger.kernel.org,
Pavan Kondeti
In-Reply-To: <1329273064.3772.18.camel@pasglop>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^ permalink raw reply
* Re: [PATCH v4 1/3] KVM: PPC: epapr: Factor out the epapr init
From: Alexander Graf @ 2012-02-16 10:17 UTC (permalink / raw)
To: Liu Yu
Cc: <linuxppc-dev@ozlabs.org>, Liu Yu,
<kvm@vger.kernel.org>, <kvm-ppc@vger.kernel.org>,
<B07421@freescale.com>
In-Reply-To: <1329384365-4028-1-git-send-email-yu.liu@freescale.com>
On 16.02.2012, at 10:26, Liu Yu <yu.liu@freescale.com> wrote:
> from the kvm guest paravirt init code.
>=20
> Signed-off-by: Liu Yu <yu.liu@freescale.com>
> ---
> v4:
> 1. code cleanup
> 2. move kvm_hypercall_start() to epapr_hypercall_start()
>=20
> arch/powerpc/Kconfig | 4 ++
> arch/powerpc/include/asm/epapr_hcalls.h | 2 +
> arch/powerpc/kernel/Makefile | 1 +
> arch/powerpc/kernel/epapr.S | 25 ++++++++++++++++
> arch/powerpc/kernel/epapr_para.c | 49 +++++++++++++++++++++++++++=
++++
> arch/powerpc/kernel/kvm.c | 28 ++----------------
> arch/powerpc/kernel/kvm_emul.S | 10 ------
> arch/powerpc/kvm/Kconfig | 1 +
> 8 files changed, 85 insertions(+), 35 deletions(-)
> create mode 100644 arch/powerpc/kernel/epapr.S
> create mode 100644 arch/powerpc/kernel/epapr_para.c
>=20
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 1919634..1262b43 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -202,6 +202,10 @@ config EPAPR_BOOT
> Used to allow a board to specify it wants an ePAPR compliant wrapper.=
> default n
>=20
> +config EPAPR_PARAVIRT
> + bool
> + default n
> +
> config DEFAULT_UIMAGE
> bool
> help
> diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/includ=
e/asm/epapr_hcalls.h
> index f3b0c2c..0ff3f24 100644
> --- a/arch/powerpc/include/asm/epapr_hcalls.h
> +++ b/arch/powerpc/include/asm/epapr_hcalls.h
> @@ -148,6 +148,8 @@
> #define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
> #define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
>=20
> +extern bool epapr_para_enabled;
> +extern u32 epapr_hypercall_start[];
>=20
> /*
> * We use "uintptr_t" to define a register because it's guaranteed to be a=
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index ee728e4..9e807f3 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -136,6 +136,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
> obj-y +=3D ppc_save_regs.o
> endif
>=20
> +obj-$(CONFIG_EPAPR_PARAVIRT) +=3D epapr_para.o epapr.o
> obj-$(CONFIG_KVM_GUEST) +=3D kvm.o kvm_emul.o
>=20
> # Disable GCOV in odd or sensitive code
> diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
> new file mode 100644
> index 0000000..697b390
> --- /dev/null
> +++ b/arch/powerpc/kernel/epapr.S
> @@ -0,0 +1,25 @@
> +/*
> + * Copyright (C) 2012 Freescale Semiconductor, Inc.
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU General Public License
> + * as published by the Free Software Foundation; either version
> + * 2 of the License, or (at your option) any later version.
> + */
> +
> +#include <linux/threads.h>
> +#include <asm/reg.h>
> +#include <asm/page.h>
> +#include <asm/cputable.h>
> +#include <asm/thread_info.h>
> +#include <asm/ppc_asm.h>
> +#include <asm/asm-offsets.h>
> +
> +/* Hypercall entry point. Will be patched with device tree instructions. *=
/
> +.global epapr_hypercall_start
> +epapr_hypercall_start:
> + li r3, -1
> + nop
> + nop
> + nop
> + blr
> diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_=
para.c
> new file mode 100644
> index 0000000..ea13cac
> --- /dev/null
> +++ b/arch/powerpc/kernel/epapr_para.c
> @@ -0,0 +1,49 @@
> +/*
> + * ePAPR para-virtualization support.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License, version 2, as
> + * published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program; if not, write to the Free Software
> + * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, U=
SA.
> + *
> + * Copyright (C) 2012 Freescale Semiconductor, Inc.
> + */
> +
> +#include <linux/of.h>
> +#include <asm/epapr_hcalls.h>
> +#include <asm/cacheflush.h>
> +
> +bool epapr_para_enabled =3D false;
> +
> +static int __init epapr_para_init(void)
> +{
> + struct device_node *hyper_node;
> + const u32 *insts;
> + int len, i;
> +
> + hyper_node =3D of_find_node_by_path("/hypervisor");
> + if (!hyper_node)
> + return -ENODEV;
> +
> + insts =3D of_get_property(hyper_node, "hcall-instructions", &len);
> + if (!(len % 4) && (len >=3D (4 * 4))) {
> + for (i =3D 0; i < (len / 4); i++)
So if the dt passes in less than 4 ops, you bail out, and for more you overw=
rite the buffer? Not good :)
> + epapr_hypercall_start[i] =3D insts[i];
> + flush_icache_range((ulong)epapr_hypercall_start,
> + (ulong)epapr_hypercall_start + len);
> +
> + epapr_para_enabled =3D true;
> + }
> +
> + return 0;
> +}
> +
> +early_initcall(epapr_para_init);
> diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
> index 62bdf23..9dfc24a 100644
> --- a/arch/powerpc/kernel/kvm.c
> +++ b/arch/powerpc/kernel/kvm.c
> @@ -31,6 +31,7 @@
> #include <asm/cacheflush.h>
> #include <asm/disassemble.h>
> #include <asm/ppc-opcode.h>
> +#include <asm/epapr_hcalls.h>
>=20
> #define KVM_MAGIC_PAGE (-4096L)
> #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared=
, x)
> @@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
> unsigned long register r11 asm("r11") =3D nr;
> unsigned long register r12 asm("r12");
>=20
> - asm volatile("bl kvm_hypercall_start"
> + asm volatile("bl epapr_hypercall_start"
> : "=3Dr"(r0), "=3Dr"(r3), "=3Dr"(r4), "=3Dr"(r5), "=3Dr"(r6),
> "=3Dr"(r7), "=3Dr"(r8), "=3Dr"(r9), "=3Dr"(r10), "=3Dr"(r11)=
,
> "=3Dr"(r12)
> @@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
> }
> EXPORT_SYMBOL_GPL(kvm_hypercall);
>=20
> -static int kvm_para_setup(void)
> -{
> - extern u32 kvm_hypercall_start;
> - struct device_node *hyper_node;
> - u32 *insts;
> - int len, i;
> -
> - hyper_node =3D of_find_node_by_path("/hypervisor");
> - if (!hyper_node)
> - return -1;
> -
> - insts =3D (u32*)of_get_property(hyper_node, "hcall-instructions", &le=
n);
> - if (len % 4)
> - return -1;
> - if (len > (4 * 4))
As you can see, the previous code allowed for less than 4 instructions, but n=
ot more.
Alex
> - return -1;
> -
> - for (i =3D 0; i < (len / 4); i++)
> - kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
> -
> - return 0;
> -}
> -
> static __init void kvm_free_tmp(void)
> {
> unsigned long start, end;
> @@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
> if (!kvm_para_available())
> goto free_tmp;
>=20
> - if (kvm_para_setup())
> + if (!epapr_para_enabled)
> goto free_tmp;
>=20
> if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
> diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul=
.S
> index e291cf3..62ceb2a 100644
> --- a/arch/powerpc/kernel/kvm_emul.S
> +++ b/arch/powerpc/kernel/kvm_emul.S
> @@ -24,16 +24,6 @@
> #include <asm/page.h>
> #include <asm/asm-offsets.h>
>=20
> -/* Hypercall entry point. Will be patched with device tree instructions. *=
/
> -
> -.global kvm_hypercall_start
> -kvm_hypercall_start:
> - li r3, -1
> - nop
> - nop
> - nop
> - blr
> -
> #define KVM_MAGIC_PAGE (-4096)
>=20
> #ifdef CONFIG_64BIT
> diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
> index 8f64709..9bb9d18 100644
> --- a/arch/powerpc/kvm/Kconfig
> +++ b/arch/powerpc/kvm/Kconfig
> @@ -20,6 +20,7 @@ config KVM
> bool
> select PREEMPT_NOTIFIERS
> select ANON_INODES
> + select EPAPR_PARAVIRT
>=20
> config KVM_BOOK3S_HANDLER
> bool
> --=20
> 1.7.0.4
>=20
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH] powerpc/usb: fix bug of kernel hang when initializing usb
From: Shengzhou Liu @ 2012-02-16 10:02 UTC (permalink / raw)
To: linux-usb; +Cc: linuxppc-dev, Shengzhou Liu
If USB UTMI PHY is not enable, writing to portsc register will lead to
kernel hang during boot up.
Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
---
Apply for master branch of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
Tested on P5020DS, the issue was reported by Benjamin Herrenschmidt.
drivers/usb/host/ehci-fsl.c | 4 ++++
drivers/usb/host/ehci-fsl.h | 1 +
2 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c
index c26a82e..0090ed2 100644
--- a/drivers/usb/host/ehci-fsl.c
+++ b/drivers/usb/host/ehci-fsl.c
@@ -216,6 +216,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
unsigned int port_offset)
{
u32 portsc;
+ struct usb_hcd *hcd = ehci_to_hcd(ehci);
+ void __iomem *non_ehci = hcd->regs;
portsc = ehci_readl(ehci, &ehci->regs->port_status[port_offset]);
portsc &= ~(PORT_PTS_MSK | PORT_PTS_PTW);
@@ -231,6 +233,8 @@ static void ehci_fsl_setup_phy(struct ehci_hcd *ehci,
portsc |= PORT_PTS_PTW;
/* fall through */
case FSL_USB2_PHY_UTMI:
+ /* enable UTMI PHY */
+ setbits32(non_ehci + FSL_SOC_USB_CTRL, CTRL_UTMI_PHY_EN);
portsc |= PORT_PTS_UTMI;
break;
case FSL_USB2_PHY_NONE:
diff --git a/drivers/usb/host/ehci-fsl.h b/drivers/usb/host/ehci-fsl.h
index bdf43e2..0e400c2 100644
--- a/drivers/usb/host/ehci-fsl.h
+++ b/drivers/usb/host/ehci-fsl.h
@@ -45,6 +45,7 @@
#define FSL_SOC_USB_PRICTRL 0x40c /* NOTE: big-endian */
#define FSL_SOC_USB_SICTRL 0x410 /* NOTE: big-endian */
#define FSL_SOC_USB_CTRL 0x500 /* NOTE: big-endian */
+#define CTRL_UTMI_PHY_EN (1<<9)
#define CTRL_PHY_CLK_VALID (1 << 17)
#define SNOOP_SIZE_2GB 0x1e
#endif /* _EHCI_FSL_H */
--
1.6.4
^ permalink raw reply related
* [PATCH v4 2/3] KVM: PPC: epapr: Add idle hcall support for host
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
In-Reply-To: <1329384365-4028-1-git-send-email-yu.liu@freescale.com>
And add a new flag definition in kvm_ppc_pvinfo to indicate
whether host support EV_IDLE hcall.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
no change
arch/powerpc/include/asm/kvm_para.h | 14 ++++++++++++--
arch/powerpc/kvm/powerpc.c | 8 ++++++++
include/linux/kvm.h | 2 ++
3 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 7b754e7..81a34c9 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -75,9 +75,19 @@ struct kvm_vcpu_arch_shared {
};
#define KVM_SC_MAGIC_R0 0x4b564d21 /* "KVM!" */
-#define HC_VENDOR_KVM (42 << 16)
+
+#include <asm/epapr_hcalls.h>
+
+/* ePAPR Hypercall Vendor ID */
+#define HC_VENDOR_EPAPR (EV_EPAPR_VENDOR_ID << 16)
+#define HC_VENDOR_KVM (EV_KVM_VENDOR_ID << 16)
+
+/* ePAPR Hypercall Token */
+#define HC_EV_IDLE EV_IDLE
+
+/* ePAPR Hypercall Return Codes */
#define HC_EV_SUCCESS 0
-#define HC_EV_UNIMPLEMENTED 12
+#define HC_EV_UNIMPLEMENTED EV_UNIMPLEMENTED
#define KVM_FEATURE_MAGIC_PAGE 1
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 0e21d15..03ebd5d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -81,6 +81,10 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
/* Second return value is in r4 */
break;
+ case HC_VENDOR_EPAPR | HC_EV_IDLE:
+ r = HC_EV_SUCCESS;
+ kvm_vcpu_block(vcpu);
+ break;
default:
r = HC_EV_UNIMPLEMENTED;
break;
@@ -746,6 +750,10 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
pvinfo->hcall[2] = inst_sc;
pvinfo->hcall[3] = inst_nop;
+#ifdef CONFIG_BOOKE
+ pvinfo->flags |= KVM_PPC_PVINFO_FLAGS_EV_IDLE;
+#endif
+
return 0;
}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index acbe429..6b2c70e 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -449,6 +449,8 @@ struct kvm_ppc_pvinfo {
__u8 pad[108];
};
+#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0)
+
#define KVMIO 0xAE
/* machine type bits, to be used as argument to KVM_CREATE_VM */
--
1.7.0.4
^ permalink raw reply related
* [PATCH v4 1/3] KVM: PPC: epapr: Factor out the epapr init
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
from the kvm guest paravirt init code.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
1. code cleanup
2. move kvm_hypercall_start() to epapr_hypercall_start()
arch/powerpc/Kconfig | 4 ++
arch/powerpc/include/asm/epapr_hcalls.h | 2 +
arch/powerpc/kernel/Makefile | 1 +
arch/powerpc/kernel/epapr.S | 25 ++++++++++++++++
arch/powerpc/kernel/epapr_para.c | 49 +++++++++++++++++++++++++++++++
arch/powerpc/kernel/kvm.c | 28 ++----------------
arch/powerpc/kernel/kvm_emul.S | 10 ------
arch/powerpc/kvm/Kconfig | 1 +
8 files changed, 85 insertions(+), 35 deletions(-)
create mode 100644 arch/powerpc/kernel/epapr.S
create mode 100644 arch/powerpc/kernel/epapr_para.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1919634..1262b43 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -202,6 +202,10 @@ config EPAPR_BOOT
Used to allow a board to specify it wants an ePAPR compliant wrapper.
default n
+config EPAPR_PARAVIRT
+ bool
+ default n
+
config DEFAULT_UIMAGE
bool
help
diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h
index f3b0c2c..0ff3f24 100644
--- a/arch/powerpc/include/asm/epapr_hcalls.h
+++ b/arch/powerpc/include/asm/epapr_hcalls.h
@@ -148,6 +148,8 @@
#define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
#define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
+extern bool epapr_para_enabled;
+extern u32 epapr_hypercall_start[];
/*
* We use "uintptr_t" to define a register because it's guaranteed to be a
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index ee728e4..9e807f3 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -136,6 +136,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
obj-y += ppc_save_regs.o
endif
+obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_para.o epapr.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
# Disable GCOV in odd or sensitive code
diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
new file mode 100644
index 0000000..697b390
--- /dev/null
+++ b/arch/powerpc/kernel/epapr.S
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/threads.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/cputable.h>
+#include <asm/thread_info.h>
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+.global epapr_hypercall_start
+epapr_hypercall_start:
+ li r3, -1
+ nop
+ nop
+ nop
+ blr
diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_para.c
new file mode 100644
index 0000000..ea13cac
--- /dev/null
+++ b/arch/powerpc/kernel/epapr_para.c
@@ -0,0 +1,49 @@
+/*
+ * ePAPR para-virtualization support.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/of.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/cacheflush.h>
+
+bool epapr_para_enabled = false;
+
+static int __init epapr_para_init(void)
+{
+ struct device_node *hyper_node;
+ const u32 *insts;
+ int len, i;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return -ENODEV;
+
+ insts = of_get_property(hyper_node, "hcall-instructions", &len);
+ if (!(len % 4) && (len >= (4 * 4))) {
+ for (i = 0; i < (len / 4); i++)
+ epapr_hypercall_start[i] = insts[i];
+ flush_icache_range((ulong)epapr_hypercall_start,
+ (ulong)epapr_hypercall_start + len);
+
+ epapr_para_enabled = true;
+ }
+
+ return 0;
+}
+
+early_initcall(epapr_para_init);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 62bdf23..9dfc24a 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -31,6 +31,7 @@
#include <asm/cacheflush.h>
#include <asm/disassemble.h>
#include <asm/ppc-opcode.h>
+#include <asm/epapr_hcalls.h>
#define KVM_MAGIC_PAGE (-4096L)
#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
@@ -726,7 +727,7 @@ unsigned long kvm_hypercall(unsigned long *in,
unsigned long register r11 asm("r11") = nr;
unsigned long register r12 asm("r12");
- asm volatile("bl kvm_hypercall_start"
+ asm volatile("bl epapr_hypercall_start"
: "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
"=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
"=r"(r12)
@@ -747,29 +748,6 @@ unsigned long kvm_hypercall(unsigned long *in,
}
EXPORT_SYMBOL_GPL(kvm_hypercall);
-static int kvm_para_setup(void)
-{
- extern u32 kvm_hypercall_start;
- struct device_node *hyper_node;
- u32 *insts;
- int len, i;
-
- hyper_node = of_find_node_by_path("/hypervisor");
- if (!hyper_node)
- return -1;
-
- insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
- if (len % 4)
- return -1;
- if (len > (4 * 4))
- return -1;
-
- for (i = 0; i < (len / 4); i++)
- kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
-
- return 0;
-}
-
static __init void kvm_free_tmp(void)
{
unsigned long start, end;
@@ -791,7 +769,7 @@ static int __init kvm_guest_init(void)
if (!kvm_para_available())
goto free_tmp;
- if (kvm_para_setup())
+ if (!epapr_para_enabled)
goto free_tmp;
if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index e291cf3..62ceb2a 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -24,16 +24,6 @@
#include <asm/page.h>
#include <asm/asm-offsets.h>
-/* Hypercall entry point. Will be patched with device tree instructions. */
-
-.global kvm_hypercall_start
-kvm_hypercall_start:
- li r3, -1
- nop
- nop
- nop
- blr
-
#define KVM_MAGIC_PAGE (-4096)
#ifdef CONFIG_64BIT
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 8f64709..9bb9d18 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,6 +20,7 @@ config KVM
bool
select PREEMPT_NOTIFIERS
select ANON_INODES
+ select EPAPR_PARAVIRT
config KVM_BOOK3S_HANDLER
bool
--
1.7.0.4
^ permalink raw reply related
* [PATCH v4 3/3] KVM: PPC: epapr: install ev_idle hcall for e500 guest
From: Liu Yu @ 2012-02-16 9:26 UTC (permalink / raw)
To: agraf, kvm-ppc, kvm; +Cc: linuxppc-dev, Liu Yu, B07421
In-Reply-To: <1329384365-4028-2-git-send-email-yu.liu@freescale.com>
If the guest hypervisor node contains "has-idle" property.
Signed-off-by: Liu Yu <yu.liu@freescale.com>
---
v4:
1. discard the CONFIG_E500 to make code for all powerpc platform
2. code cleanup
arch/powerpc/kernel/epapr.S | 29 +++++++++++++++++++++++++++++
arch/powerpc/kernel/epapr_para.c | 13 ++++++++++++-
2 files changed, 41 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/kernel/epapr.S b/arch/powerpc/kernel/epapr.S
index 697b390..f06d636 100644
--- a/arch/powerpc/kernel/epapr.S
+++ b/arch/powerpc/kernel/epapr.S
@@ -15,6 +15,35 @@
#include <asm/ppc_asm.h>
#include <asm/asm-offsets.h>
+#define HC_VENDOR_EPAPR (1 << 16)
+#define HC_EV_IDLE 16
+
+_GLOBAL(epapr_ev_idle)
+epapr_ev_idle:
+ rlwinm r3,r1,0,0,31-THREAD_SHIFT /* current thread_info */
+ lwz r4,TI_LOCAL_FLAGS(r3) /* set napping bit */
+ ori r4,r4,_TLF_NAPPING /* so when we take an exception */
+ stw r4,TI_LOCAL_FLAGS(r3) /* it will return to our caller */
+
+ wrteei 1
+
+idle_loop:
+ LOAD_REG_IMMEDIATE(r11, HC_VENDOR_EPAPR | HC_EV_IDLE)
+
+.global epapr_ev_idle_start
+epapr_ev_idle_start:
+ li r3, -1
+ nop
+ nop
+ nop
+
+ /*
+ * Guard against spurious wakeups (e.g. from a hypervisor) --
+ * any real interrupt will cause us to return to LR due to
+ * _TLF_NAPPING.
+ */
+ b idle_loop
+
/* Hypercall entry point. Will be patched with device tree instructions. */
.global epapr_hypercall_start
epapr_hypercall_start:
diff --git a/arch/powerpc/kernel/epapr_para.c b/arch/powerpc/kernel/epapr_para.c
index ea13cac..adee4f1 100644
--- a/arch/powerpc/kernel/epapr_para.c
+++ b/arch/powerpc/kernel/epapr_para.c
@@ -20,6 +20,10 @@
#include <linux/of.h>
#include <asm/epapr_hcalls.h>
#include <asm/cacheflush.h>
+#include <asm/machdep.h>
+
+extern void epapr_ev_idle(void);
+extern u32 epapr_ev_idle_start[];
bool epapr_para_enabled = false;
@@ -35,10 +39,17 @@ static int __init epapr_para_init(void)
insts = of_get_property(hyper_node, "hcall-instructions", &len);
if (!(len % 4) && (len >= (4 * 4))) {
- for (i = 0; i < (len / 4); i++)
+ for (i = 0; i < (len / 4); i++) {
epapr_hypercall_start[i] = insts[i];
+ epapr_ev_idle_start[i] = insts[i];
+ }
flush_icache_range((ulong)epapr_hypercall_start,
(ulong)epapr_hypercall_start + len);
+ flush_icache_range((ulong)epapr_ev_idle_start,
+ (ulong)epapr_ev_idle_start + len);
+
+ if (of_get_property(hyper_node, "has-idle", NULL))
+ ppc_md.power_save = epapr_ev_idle;
epapr_para_enabled = true;
}
--
1.7.0.4
^ permalink raw reply related
* [PATCH v5 27/27] irq_domain: For NOMAP revmap, allow users to specify the largest usable virq
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
This patch replaces the old global setting of irq_virq_count that is only
used by the NOMAP mapping and instead uses a revmap_data property so that
the maximum NOMAP allocation can be set per NOMAP irq_domain.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
---
arch/powerpc/platforms/cell/axon_msi.c | 2 +-
arch/powerpc/platforms/cell/beat_interrupt.c | 2 +-
arch/powerpc/platforms/iseries/irq.c | 8 +------
arch/powerpc/platforms/powermac/smp.c | 2 +-
arch/powerpc/platforms/ps3/interrupt.c | 3 +-
include/linux/irqdomain.h | 7 ++---
kernel/irq/irqdomain.c | 29 ++++++-------------------
7 files changed, 15 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index db360fc..369df06 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -392,7 +392,7 @@ static int axon_msi_probe(struct platform_device *device)
}
memset(msic->fifo_virt, 0xff, MSIC_FIFO_SIZE_BYTES);
- msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic);
+ msic->irq_domain = irq_domain_add_nomap(dn, &msic_host_ops, msic, ~0);
if (!msic->irq_domain) {
printk(KERN_ERR "axon_msi: couldn't allocate irq_domain for %s\n",
dn->full_name);
diff --git a/arch/powerpc/platforms/cell/beat_interrupt.c b/arch/powerpc/platforms/cell/beat_interrupt.c
index e5c3a2c..4315349 100644
--- a/arch/powerpc/platforms/cell/beat_interrupt.c
+++ b/arch/powerpc/platforms/cell/beat_interrupt.c
@@ -239,7 +239,7 @@ void __init beatic_init_IRQ(void)
ppc_md.get_irq = beatic_get_irq;
/* Allocate an irq host */
- beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL);
+ beatic_host = irq_domain_add_nomap(NULL, &beatic_pic_host_ops, NULL, ~0);
BUG_ON(beatic_host == NULL);
irq_set_default_host(beatic_host);
}
diff --git a/arch/powerpc/platforms/iseries/irq.c b/arch/powerpc/platforms/iseries/irq.c
index 05ce516..db48abe 100644
--- a/arch/powerpc/platforms/iseries/irq.c
+++ b/arch/powerpc/platforms/iseries/irq.c
@@ -371,16 +371,10 @@ void __init iSeries_init_IRQ(void)
struct irq_domain *host;
int ret;
- /*
- * The Hypervisor only allows us up to 256 interrupt
- * sources (the irq number is passed in a u8).
- */
- irq_set_virq_count(256);
-
/* Create irq host. No need for a revmap since HV will give us
* back our virtual irq number
*/
- host = irq_domain_add_nomap(NULL, &iseries_irq_domain_ops, NULL);
+ host = irq_domain_add_nomap(NULL, &iseries_irq_domain_ops, NULL, 256);
BUG_ON(host == NULL);
irq_set_default_host(host);
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index a81e5a8..40f12af 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -192,7 +192,7 @@ static int psurge_secondary_ipi_init(void)
{
int rc = -ENOMEM;
- psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL);
+ psurge_host = irq_domain_add_nomap(NULL, &psurge_host_ops, NULL, ~0);
if (psurge_host)
psurge_secondary_virq = irq_create_direct_mapping(psurge_host);
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 2a4ff86..0700a98 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -753,9 +753,8 @@ void __init ps3_init_IRQ(void)
unsigned cpu;
struct irq_domain *host;
- host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL);
+ host = irq_domain_add_nomap(NULL, &ps3_host_ops, NULL, PS3_PLUG_MAX + 1);
irq_set_default_host(host);
- irq_set_virq_count(PS3_PLUG_MAX + 1);
for_each_possible_cpu(cpu) {
struct ps3_private *pd = &per_cpu(ps3_private, cpu);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 47af458..80bb917 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -105,6 +105,7 @@ struct irq_domain {
unsigned int *revmap;
} linear;
struct radix_tree_root tree;
+ unsigned int nomap_max_virq;
} revmap_data;
const struct irq_domain_ops *ops;
void *host_data;
@@ -126,15 +127,14 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
const struct irq_domain_ops *ops,
void *host_data);
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
- const struct irq_domain_ops *ops,
- void *host_data);
+ const struct irq_domain_ops *ops,
+ void *host_data, unsigned int max_virq);
struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
const struct irq_domain_ops *ops,
void *host_data);
extern struct irq_domain *irq_find_host(struct device_node *node);
extern void irq_set_default_host(struct irq_domain *host);
-extern void irq_set_virq_count(unsigned int count);
static inline struct irq_domain *irq_domain_add_legacy_isa(
struct device_node *of_node,
@@ -146,7 +146,6 @@ static inline struct irq_domain *irq_domain_add_legacy_isa(
}
extern struct irq_domain *irq_find_host(struct device_node *node);
extern void irq_set_default_host(struct irq_domain *host);
-extern void irq_set_virq_count(unsigned int count);
extern unsigned int irq_create_mapping(struct irq_domain *host,
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index e7d8e96..e820b53 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -23,7 +23,6 @@ static LIST_HEAD(irq_domain_list);
static DEFINE_MUTEX(irq_domain_mutex);
static DEFINE_MUTEX(revmap_trees_mutex);
-static unsigned int irq_virq_count = NR_IRQS;
static struct irq_domain *irq_default_domain;
/**
@@ -185,12 +184,14 @@ struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
const struct irq_domain_ops *ops,
- void *host_data)
+ void *host_data, unsigned int max_virq)
{
struct irq_domain *domain = irq_domain_alloc(of_node,
IRQ_DOMAIN_MAP_NOMAP, ops, host_data);
- if (domain)
+ if (domain) {
+ domain->revmap_data.nomap_max_virq = max_virq;
irq_domain_add(domain);
+ }
return domain;
}
@@ -262,22 +263,6 @@ void irq_set_default_host(struct irq_domain *domain)
irq_default_domain = domain;
}
-/**
- * irq_set_virq_count() - Set the maximum number of linux irqs
- * @count: number of linux irqs, capped with NR_IRQS
- *
- * This is mainly for use by platforms like iSeries who want to program
- * the virtual irq number in the controller to avoid the reverse mapping
- */
-void irq_set_virq_count(unsigned int count)
-{
- pr_debug("irq: Trying to set virq count to %d\n", count);
-
- BUG_ON(count < NUM_ISA_INTERRUPTS);
- if (count < NR_IRQS)
- irq_virq_count = count;
-}
-
static int irq_setup_virq(struct irq_domain *domain, unsigned int virq,
irq_hw_number_t hwirq)
{
@@ -321,9 +306,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
pr_debug("irq: create_direct virq allocation failed\n");
return 0;
}
- if (virq >= irq_virq_count) {
+ if (virq > domain->revmap_data.nomap_max_virq) {
pr_err("ERROR: no free irqs available below %i maximum\n",
- irq_virq_count);
+ domain->revmap_data.nomap_max_virq);
irq_free_desc(virq);
return 0;
}
@@ -549,7 +534,7 @@ static unsigned int irq_find_mapping_slow(struct irq_domain *domain,
unsigned int i;
/* Slow path does a linear search of the map */
- for (i = 0; i < irq_virq_count; i++) {
+ for (i = 0; i < nr_irqs; i++) {
struct irq_data *data = irq_get_irq_data(i);
if (data && (data->domain == domain) && (data->hwirq == hwirq))
return i;
--
1.7.9
^ permalink raw reply related
* [PATCH v5 26/27] irq_domain: mostly eliminate slow-path revmap lookups
From: Grant Likely @ 2012-02-16 9:09 UTC (permalink / raw)
To: linux-kernel, linuxppc-dev, devicetree-discuss, linux-arm-kernel,
Benjamin Herrenschmidt, Thomas Gleixner, Milton Miller,
Rob Herring
In-Reply-To: <1329383368-12122-1-git-send-email-grant.likely@secretlab.ca>
With the current state of irq_domain, the reverse map is always updated
when new IRQs get mapped. This means that the irq_find_mapping() function
can be simplified to always execute the revmap-specific lookup function.
This patch adds lookup functions for the revmaps that don't yet have one
and removes the slow path lookup from most of the code paths. The only
place where the slow path legitimately remains is where the linear map
is used with a hwirq number larger than the revmap size.
v5: rewrite to not use a ->revmap() callback. It is simpler, smaller,
safer and faster to open code each of the revmap lookups directly into
irq_find_mapping() via a switch statement.
v4: Fix build failure on incorrect variable reference.
Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Milton Miller <miltonm@bga.com>
---
arch/powerpc/sysdev/xics/icp-hv.c | 2 +-
arch/powerpc/sysdev/xics/icp-native.c | 2 +-
arch/powerpc/sysdev/xics/xics-common.c | 3 -
include/linux/irqdomain.h | 4 -
kernel/irq/irqdomain.c | 121 ++++++++++++--------------------
5 files changed, 48 insertions(+), 84 deletions(-)
diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c
index 253dce9..14469cf 100644
--- a/arch/powerpc/sysdev/xics/icp-hv.c
+++ b/arch/powerpc/sysdev/xics/icp-hv.c
@@ -111,7 +111,7 @@ static unsigned int icp_hv_get_irq(void)
if (vec == XICS_IRQ_SPURIOUS)
return NO_IRQ;
- irq = irq_radix_revmap_lookup(xics_host, vec);
+ irq = irq_find_mapping(xics_host, vec);
if (likely(irq != NO_IRQ)) {
xics_push_cppr(vec);
return irq;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 4c79b6f..48861d3 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -119,7 +119,7 @@ static unsigned int icp_native_get_irq(void)
if (vec == XICS_IRQ_SPURIOUS)
return NO_IRQ;
- irq = irq_radix_revmap_lookup(xics_host, vec);
+ irq = irq_find_mapping(xics_host, vec);
if (likely(irq != NO_IRQ)) {
xics_push_cppr(vec);
return irq;
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index ea5e204..1d7067d 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -330,9 +330,6 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq,
pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);
- /* Insert the interrupt mapping into the radix tree for fast lookup */
- irq_radix_revmap_insert(xics_host, virq, hw);
-
/* They aren't all level sensitive but we just don't really know */
irq_set_status_flags(virq, IRQ_LEVEL);
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 5245488..47af458 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -155,10 +155,6 @@ extern void irq_dispose_mapping(unsigned int virq);
extern unsigned int irq_find_mapping(struct irq_domain *host,
irq_hw_number_t hwirq);
extern unsigned int irq_create_direct_mapping(struct irq_domain *host);
-extern void irq_radix_revmap_insert(struct irq_domain *host, unsigned int virq,
- irq_hw_number_t hwirq);
-extern unsigned int irq_radix_revmap_lookup(struct irq_domain *host,
- irq_hw_number_t hwirq);
extern unsigned int irq_linear_revmap(struct irq_domain *host,
irq_hw_number_t hwirq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index db7adb2..e7d8e96 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -313,7 +313,8 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
domain = irq_default_domain;
BUG_ON(domain == NULL);
- WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP);
+ if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_NOMAP))
+ return 0;
virq = irq_alloc_desc_from(1, 0);
if (!virq) {
@@ -389,6 +390,18 @@ unsigned int irq_create_mapping(struct irq_domain *domain,
return 0;
}
+ switch(domain->revmap_type) {
+ case IRQ_DOMAIN_MAP_LINEAR:
+ if (hwirq < domain->revmap_data.linear.size)
+ domain->revmap_data.linear.revmap[hwirq] = virq;
+ break;
+ case IRQ_DOMAIN_MAP_TREE:
+ mutex_lock(&revmap_trees_mutex);
+ radix_tree_insert(&domain->revmap_data.tree, hwirq,
+ irq_get_irq_data(virq));
+ mutex_unlock(&revmap_trees_mutex);
+ break;
+ }
pr_debug("irq: irq %lu on domain %s mapped to virtual irq %u\n",
hwirq, domain->of_node ? domain->of_node->full_name : "null", virq);
@@ -497,7 +510,7 @@ EXPORT_SYMBOL_GPL(irq_dispose_mapping);
unsigned int irq_find_mapping(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int i;
+ struct irq_data *data;
/* Look for default domain if nececssary */
if (domain == NULL)
@@ -505,74 +518,43 @@ unsigned int irq_find_mapping(struct irq_domain *domain,
if (domain == NULL)
return 0;
- /* legacy -> bail early */
- if (domain->revmap_type == IRQ_DOMAIN_MAP_LEGACY)
+ switch (domain->revmap_type) {
+ case IRQ_DOMAIN_MAP_LEGACY:
return irq_domain_legacy_revmap(domain, hwirq);
-
- /* Slow path does a linear search of the map */
- for (i = 0; i < irq_virq_count; i++) {
- struct irq_data *data = irq_get_irq_data(i);
+ case IRQ_DOMAIN_MAP_LINEAR:
+ return irq_linear_revmap(domain, hwirq);
+ case IRQ_DOMAIN_MAP_TREE:
+ rcu_read_lock();
+ data = radix_tree_lookup(&domain->revmap_data.tree, hwirq);
+ rcu_read_unlock();
+ if (data)
+ return data->irq;
+ break;
+ case IRQ_DOMAIN_MAP_NOMAP:
+ data = irq_get_irq_data(hwirq);
if (data && (data->domain == domain) && (data->hwirq == hwirq))
- return i;
+ return hwirq;
+ break;
}
+
+ WARN(1, "ERROR: irq revmap went horribly wrong. revmap_type=%i\n",
+ domain->revmap_type);
return 0;
}
EXPORT_SYMBOL_GPL(irq_find_mapping);
-/**
- * irq_radix_revmap_lookup() - Find a linux irq from a hw irq number.
- * @domain: domain owning this hardware interrupt
- * @hwirq: hardware irq number in that domain space
- *
- * This is a fast path, for use by irq controller code that uses radix tree
- * revmaps
- */
-unsigned int irq_radix_revmap_lookup(struct irq_domain *domain,
- irq_hw_number_t hwirq)
+static unsigned int irq_find_mapping_slow(struct irq_domain *domain,
+ irq_hw_number_t hwirq)
{
- struct irq_data *irq_data;
-
- if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
- return irq_find_mapping(domain, hwirq);
-
- /*
- * Freeing an irq can delete nodes along the path to
- * do the lookup via call_rcu.
- */
- rcu_read_lock();
- irq_data = radix_tree_lookup(&domain->revmap_data.tree, hwirq);
- rcu_read_unlock();
-
- /*
- * If found in radix tree, then fine.
- * Else fallback to linear lookup - this should not happen in practice
- * as it means that we failed to insert the node in the radix tree.
- */
- return irq_data ? irq_data->irq : irq_find_mapping(domain, hwirq);
-}
-
-/**
- * irq_radix_revmap_insert() - Insert a hw irq to linux irq number mapping.
- * @domain: domain owning this hardware interrupt
- * @virq: linux irq number
- * @hwirq: hardware irq number in that domain space
- *
- * This is for use by irq controllers that use a radix tree reverse
- * mapping for fast lookup.
- */
-void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
- irq_hw_number_t hwirq)
-{
- struct irq_data *irq_data = irq_get_irq_data(virq);
-
- if (WARN_ON(domain->revmap_type != IRQ_DOMAIN_MAP_TREE))
- return;
+ unsigned int i;
- if (virq) {
- mutex_lock(&revmap_trees_mutex);
- radix_tree_insert(&domain->revmap_data.tree, hwirq, irq_data);
- mutex_unlock(&revmap_trees_mutex);
+ /* Slow path does a linear search of the map */
+ for (i = 0; i < irq_virq_count; i++) {
+ struct irq_data *data = irq_get_irq_data(i);
+ if (data && (data->domain == domain) && (data->hwirq == hwirq))
+ return i;
}
+ return 0;
}
/**
@@ -581,31 +563,20 @@ void irq_radix_revmap_insert(struct irq_domain *domain, unsigned int virq,
* @hwirq: hardware irq number in that domain space
*
* This is a fast path, for use by irq controller code that uses linear
- * revmaps. It does fallback to the slow path if the revmap doesn't exist
- * yet and will create the revmap entry with appropriate locking
+ * revmaps. It does fallback to the slow path if the hwirq number is outside
+ * the range of the hwirq numbers.
*/
unsigned int irq_linear_revmap(struct irq_domain *domain,
irq_hw_number_t hwirq)
{
- unsigned int *revmap;
-
if (WARN_ON_ONCE(domain->revmap_type != IRQ_DOMAIN_MAP_LINEAR))
return irq_find_mapping(domain, hwirq);
/* Check revmap bounds */
if (unlikely(hwirq >= domain->revmap_data.linear.size))
- return irq_find_mapping(domain, hwirq);
-
- /* Check if revmap was allocated */
- revmap = domain->revmap_data.linear.revmap;
- if (unlikely(revmap == NULL))
- return irq_find_mapping(domain, hwirq);
-
- /* Fill up revmap with slow path if no mapping found */
- if (unlikely(!revmap[hwirq]))
- revmap[hwirq] = irq_find_mapping(domain, hwirq);
+ return irq_find_mapping_slow(domain, hwirq);
- return revmap[hwirq];
+ return domain->revmap_data.linear.revmap[hwirq];
}
#ifdef CONFIG_VIRQ_DEBUG
--
1.7.9
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox