to the client. The presence of this property also mandates
that any initialization related to interrupt sources shall
be limited to sources explicitly referenced in the device tree.
-
+
+ - big-endian
+ Usage: optional
+ Value type: <empty>
+ If present the MPIC will be assumed to be big-endian. Some
+ device-trees omit this property on MPIC nodes even when the MPIC is
+ in fact big-endian, so certain boards override this property.
+
+ - single-cpu-affinity
+ Usage: optional
+ Value type: <empty>
+ If present the MPIC will be assumed to only be able to route
+ non-IPI interrupts to a single CPU at a time (EG: Freescale MPIC).
+
+ - last-interrupt-source
+ Usage: optional
+ Value type: <u32>
+ Some MPICs do not correctly report the number of hardware sources
+ in the global feature registers. If specified, this field will
+ override the value read from MPIC_GREG_FEATURE_LAST_SRC.
+
INTERRUPT SPECIFIER DEFINITION
Interrupt specifiers consists of 4 cells encoded as
--- /dev/null
+
+ 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.
+++ /dev/null
-
- 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.
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.
+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"
arch/powerpc/net/
core-$(CONFIG_XMON) += arch/powerpc/xmon/
core-$(CONFIG_KVM) += arch/powerpc/kvm/
+core-$(CONFIG_PERF_EVENTS) += arch/powerpc/perf/
drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/
reg = <0x40000 0x40000>;
compatible = "fsl,mpic";
device_type = "open-pic";
+ big-endian;
+ single-cpu-affinity;
+ last-interrupt-source = <255>;
};
timer@41100 {
--- /dev/null
+/*
+ * 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))
+
+#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
+#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
+
+/* 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;
+ 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;
+ 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;
+
+ 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;
+ unsigned long fadump_supported:1;
+ unsigned long dump_active:1;
+ 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 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 */
+#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);
+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) { }
+#endif
+#endif
unsigned int isu_size;
unsigned int isu_shift;
unsigned int isu_mask;
- unsigned int irq_count;
/* Number of sources */
unsigned int num_sources;
/* default senses array */
#define MPIC_U3_HT_IRQS 0x00000004
/* Broken IPI registers (autodetected) */
#define MPIC_BROKEN_IPI 0x00000008
-/* MPIC wants a reset */
-#define MPIC_WANTS_RESET 0x00000010
/* Spurious vector requires EOI */
#define MPIC_SPV_EOI 0x00000020
/* No passthrough disable */
#define MPIC_ENABLE_MCK 0x00000200
/* Disable bias among target selection, spread interrupts evenly */
#define MPIC_NO_BIAS 0x00000400
-/* Ignore NIRQS as reported by FRR */
-#define MPIC_BROKEN_FRR_NIRQS 0x00000800
/* Destination only supports a single CPU at a time */
#define MPIC_SINGLE_DEST_CPU 0x00001000
/* Enable CoreInt delivery of interrupts */
#define MPIC_ENABLE_COREINT 0x00002000
-/* Disable resetting of the MPIC.
- * NOTE: This flag trumps MPIC_WANTS_RESET.
- */
+/* Do not reset the MPIC during initialization */
#define MPIC_NO_RESET 0x00004000
/* Freescale MPIC (compatible includes "fsl,mpic") */
#define MPIC_FSL 0x00008000
+++ /dev/null
-/*
- * 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 */
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
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o
-obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o
-
-obj-$(CONFIG_PPC_PERF_CTRS) += perf_event.o
-obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \
- power5+-pmu.o power6-pmu.o power7-pmu.o
-obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
-
-obj-$(CONFIG_FSL_EMB_PERF_EVENT) += perf_event_fsl_emb.o
-obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
--- /dev/null
+/*
+ * 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 <linux/delay.h>
+#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>
+#include <asm/rtas.h>
+#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);
+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,
+ 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.
+ */
+ 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
+ * 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;
+}
+
+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
+ *
+ * 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 += sizeof(struct fadump_crash_info_header);
+ size += sizeof(struct elfhdr); /* ELF core header.*/
+ size += sizeof(struct elf_phdr); /* place holder for cpu notes */
+ /* Program headers for crash memory regions. */
+ size += sizeof(struct elf_phdr) * (memblock_num_regions(memory) + 2);
+
+ size = PAGE_ALIGN(size);
+ 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
+ * 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.
+ * 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));
+
+ 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();
+ 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);
+
+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;
+ }
+}
+
+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'.
+ */
+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) ||
+ !fdm_active->cpu_state_data.bytes_dumped) {
+ 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;
+ }
+
+ 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
+ * 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);
+ }
+}
+
+/*
+ * 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;
+ struct elf_phdr *phdr;
+ int i;
+
+ fadump_init_elfcore_header(bufp);
+ elf = (struct elfhdr *)bufp;
+ bufp += sizeof(struct elfhdr);
+
+ /*
+ * setup ELF PT_NOTE, place holder for cpu notes info. The notes info
+ * will be populated during second kernel boot after crash. Hence
+ * this PT_NOTE will always be the first elf note.
+ *
+ * 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 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++) {
+ 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;
+ /* We will set the crashing cpu id in crash_fadump() during crash. */
+ fdh->crashing_cpu = CPU_UNKNOWN;
+
+ 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.
+ */
+ 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);
+}
+
+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 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)
+{
+ 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;
+
+ mutex_lock(&fadump_mutex);
+ if (fdm_active)
+ fdm_ptr = fdm_active;
+ else {
+ mutex_unlock(&fadump_mutex);
+ 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))
+ goto out;
+
+ /* 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);
+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);
+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");
+
+ 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;
+}
+
+/*
+ * Prepare for firmware-assisted dump.
+ */
+int __init setup_fadump(void)
+{
+ if (!fw_dump.fadump_enabled)
+ return 0;
+
+ if (!fw_dump.fadump_supported) {
+ printk(KERN_ERR "Firmware-assisted dump is not supported on"
+ " this hardware\n");
+ return 0;
+ }
+
+ 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) {
+ /*
+ * 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);
+ fadump_init_files();
+
+ return 1;
+}
+subsys_initcall(setup_fadump);
#include <asm/pci-bridge.h>
#include <asm/machdep.h>
#include <asm/kdump.h>
+#include <asm/fadump.h>
#define DBG(...)
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;
#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>
#include <mm/mmu_decl.h>
}
}
-#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;
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);
+#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,
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();
/*
* Ensure that total memory size is page-aligned, because otherwise
#include <asm/xmon.h>
#include <asm/cputhreads.h>
#include <mm/mmu_decl.h>
+#include <asm/fadump.h>
#include "setup.h"
/* 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();
}
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;
}
#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;
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.
#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)
/* 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
--- /dev/null
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
+obj-$(CONFIG_PERF_EVENTS) += callchain.o
+
+obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o
+obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \
+ power5+-pmu.o power6-pmu.o power7-pmu.o
+obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
+
+obj-$(CONFIG_FSL_EMB_PERF_EVENT) += core-fsl-emb.o
+obj-$(CONFIG_FSL_EMB_PERF_EVENT_E500) += e500-pmu.o
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
+obj-$(CONFIG_PPC32) += $(obj32-y)
#include <asm/ucontext.h>
#include <asm/vdso.h>
#ifdef CONFIG_PPC64
-#include "ppc32.h"
+#include "../kernel/ppc32.h"
#endif
0x00000022, /* BFP set 2: byte 0 bits 1, 5 */
0, 0
};
-
+
/*
* Returns 1 if event counts things relating to marked instructions
* and thus needs the MMCRA_SAMPLE_ENABLE bit set, or 0 if not.
alt[1] = event ^ 0x1000;
return 2;
}
-
+
return 1;
}
* device-tree, just pass 0 to all arguments
*/
struct mpic *mpic =
- mpic_alloc(np, 0, 0, 0, 0, " MPIC ");
+ mpic_alloc(np, 0, MPIC_NO_RESET, 0, 0, " MPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
ppc_md.get_irq = mpic_get_irq;
/* The MPIC driver will get everything it needs from the
* device-tree, just pass 0 to all arguments
*/
- struct mpic *mpic = mpic_alloc(np, 0, 0, 0, 0,
- " MPIC ");
+ struct mpic *mpic = mpic_alloc(np, 0, MPIC_NO_RESET, 0, 0, " MPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
ppc_md.get_irq = mpic_get_irq;
void __init corenet_ds_pic_init(void)
{
struct mpic *mpic;
- unsigned int flags = MPIC_BIG_ENDIAN |
- MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU;
+ unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU |
+ MPIC_NO_RESET;
if (ppc_md.get_irq == mpic_get_coreint_irq)
flags |= MPIC_ENABLE_COREINT;
static void __init ksi8560_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
void __init mpc8536_ds_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET |
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
static void __init mpc85xx_ads_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
static void __init mpc85xx_cds_pic_init(void)
{
struct mpic *mpic;
- mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
mpic = mpic_alloc(NULL, 0,
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+ MPIC_NO_RESET |
+ MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
} else {
mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET |
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+ MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
}
static void __init mpc85xx_mds_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
- MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+ MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
unsigned long root = of_get_flat_dt_root();
if (of_flat_dt_is_compatible(root, "fsl,MPC85XXRDB-CAMP")) {
- mpic = mpic_alloc(NULL, 0,
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+ mpic = mpic_alloc(NULL, 0, MPIC_NO_RESET |
+ MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
} else {
mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET |
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+ MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
}
void __init p1010_rdb_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
- MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+ MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
void __init p1022_ds_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET |
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
static void __init mpc85xx_rds_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
- MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+ MPIC_SINGLE_DEST_CPU,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
static void __init sbc8548_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
static void __init sbc8560_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
{
struct device_node *np;
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
static void __init stx_gp3_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
static void __init tqm85xx_pic_init(void)
{
struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN,
+ MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
void __init xes_mpc85xx_pic_init(void)
{
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET |
- MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN,
0, 256, " OpenPIC ");
BUG_ON(mpic == NULL);
mpic_init(mpic);
int cascade_irq;
#endif
- struct mpic *mpic = mpic_alloc(NULL, 0,
- MPIC_WANTS_RESET | MPIC_BIG_ENDIAN |
- MPIC_BROKEN_FRR_NIRQS | MPIC_SINGLE_DEST_CPU,
+ struct mpic *mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
+ MPIC_SINGLE_DEST_CPU,
0, 256, " MPIC ");
BUG_ON(mpic == NULL);
/* The MPIC driver will get everything it needs from the
* device-tree, just pass 0 to all arguments
*/
- mpic = mpic_alloc(dn, 0, MPIC_SECONDARY, 0, 0, " MPIC ");
+ mpic = mpic_alloc(dn, 0, MPIC_SECONDARY | MPIC_NO_RESET,
+ 0, 0, " MPIC ");
if (mpic == NULL)
continue;
mpic_init(mpic);
if (len > 1)
isu_size = iranges[3];
- chrp_mpic = mpic_alloc(np, opaddr, 0, isu_size, 0, " MPIC ");
+ chrp_mpic = mpic_alloc(np, opaddr, MPIC_NO_RESET,
+ isu_size, 0, " MPIC ");
if (chrp_mpic == NULL) {
printk(KERN_ERR "Failed to allocate MPIC structure\n");
goto bail;
struct device_node *cascade_node = NULL;
#endif
- mpic = mpic_alloc(NULL, 0,
- MPIC_BIG_ENDIAN | MPIC_WANTS_RESET |
+ mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108,
- 24,
- NR_IRQS-4, /* num_sources used */
+ 24, 0,
"Tsi108_PIC");
BUG_ON(mpic == NULL);
{
struct mpic *mpic;
- mpic = mpic_alloc(NULL, 0, MPIC_WANTS_RESET,
- 4, 32, " EPIC ");
+ mpic = mpic_alloc(NULL, 0, 0, 4, 0, " EPIC ");
BUG_ON(mpic == NULL);
/* PCI IRQs */
struct device_node *cascade_node = NULL;
#endif
- mpic = mpic_alloc(NULL, 0,
- MPIC_BIG_ENDIAN | MPIC_WANTS_RESET |
+ mpic = mpic_alloc(NULL, 0, MPIC_BIG_ENDIAN |
MPIC_SPV_EOI | MPIC_NO_PTHROU_DIS | MPIC_REGSET_TSI108,
- 24,
- NR_IRQS-4, /* num_sources used */
+ 24, 0,
"Tsi108_PIC");
BUG_ON(mpic == NULL);
{
struct mpic *mpic;
- mpic = mpic_alloc(NULL, 0, MPIC_WANTS_RESET,
- 16, 32, " OpenPIC ");
+ mpic = mpic_alloc(NULL, 0, 0, 16, 0, " OpenPIC ");
BUG_ON(mpic == NULL);
/*
flags |= MPIC_BIG_ENDIAN;
/* XXX Maple specific bits */
- flags |= MPIC_U3_HT_IRQS | MPIC_WANTS_RESET;
+ flags |= MPIC_U3_HT_IRQS;
/* All U3/U4 are big-endian, older SLOF firmware doesn't encode this */
flags |= MPIC_BIG_ENDIAN;
openpic_addr = of_read_number(opprop, naddr);
printk(KERN_DEBUG "OpenPIC addr: %lx\n", openpic_addr);
- mpic_flags = MPIC_LARGE_VECTORS | MPIC_NO_BIAS;
+ mpic_flags = MPIC_LARGE_VECTORS | MPIC_NO_BIAS | MPIC_NO_RESET;
nmiprop = of_get_property(mpic_node, "nmi-source", NULL);
if (nmiprop)
pmac_call_feature(PMAC_FTR_ENABLE_MPIC, np, 0, 0);
- flags |= MPIC_WANTS_RESET;
if (of_get_property(np, "big-endian", NULL))
flags |= MPIC_BIG_ENDIAN;
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
+++ /dev/null
-/*
- * 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);
BUG_ON(openpic_addr == 0);
/* Setup the openpic driver */
- mpic = mpic_alloc(pSeries_mpic_node, openpic_addr, 0,
- 16, 250, /* isu size, irq count */
- " MPIC ");
+ mpic = mpic_alloc(pSeries_mpic_node, openpic_addr,
+ MPIC_NO_RESET, 16, 0, " MPIC ");
BUG_ON(mpic == NULL);
/* Add ISUs */
DBG("mpic: set_irq_type(mpic:@%p,virq:%d,src:0x%x,type:0x%x)\n",
mpic, d->irq, src, flow_type);
- if (src >= mpic->irq_count)
+ if (src >= mpic->num_sources)
return -EINVAL;
if (flow_type == IRQ_TYPE_NONE)
DBG("mpic: set_vector(mpic:@%p,virq:%d,src:%d,vector:0x%x)\n",
mpic, virq, src, vector);
- if (src >= mpic->irq_count)
+ if (src >= mpic->num_sources)
return;
vecpri = mpic_irq_read(src, MPIC_INFO(IRQ_VECTOR_PRI));
DBG("mpic: set_destination(mpic:@%p,virq:%d,src:%d,cpuid:0x%x)\n",
mpic, virq, src, cpuid);
- if (src >= mpic->irq_count)
+ if (src >= mpic->num_sources)
return;
mpic_irq_write(src, MPIC_INFO(IRQ_DESTINATION), 1 << cpuid);
return 0;
}
- if (hw >= mpic->irq_count)
+ if (hw >= mpic->num_sources)
return -EINVAL;
mpic_msi_reserve_hwirq(mpic, hw);
u32 greg_feature;
const char *vers;
const u32 *psrc;
+ u32 last_irq;
/* Default MPIC search parameters */
static const struct of_device_id __initconst mpic_device_id[] = {
}
}
+ /* Read extra device-tree properties into the flags variable */
+ if (of_get_property(node, "big-endian", NULL))
+ flags |= MPIC_BIG_ENDIAN;
+ if (of_get_property(node, "pic-no-reset", NULL))
+ flags |= MPIC_NO_RESET;
+ if (of_get_property(node, "single-cpu-affinity", NULL))
+ flags |= MPIC_SINGLE_DEST_CPU;
+ if (of_device_is_compatible(node, "fsl,mpic"))
+ flags |= MPIC_FSL;
+
mpic = kzalloc(sizeof(struct mpic), GFP_KERNEL);
if (mpic == NULL)
goto err_of_node_put;
mpic->name = name;
mpic->node = node;
mpic->paddr = phys_addr;
+ mpic->flags = flags;
mpic->hc_irq = mpic_irq_chip;
mpic->hc_irq.name = name;
- if (!(flags & MPIC_SECONDARY))
+ if (!(mpic->flags & MPIC_SECONDARY))
mpic->hc_irq.irq_set_affinity = mpic_set_affinity;
#ifdef CONFIG_MPIC_U3_HT_IRQS
mpic->hc_ht_irq = mpic_irq_ht_chip;
mpic->hc_ht_irq.name = name;
- if (!(flags & MPIC_SECONDARY))
+ if (!(mpic->flags & MPIC_SECONDARY))
mpic->hc_ht_irq.irq_set_affinity = mpic_set_affinity;
#endif /* CONFIG_MPIC_U3_HT_IRQS */
mpic->hc_tm = mpic_tm_chip;
mpic->hc_tm.name = name;
- mpic->flags = flags;
- mpic->isu_size = isu_size;
- mpic->irq_count = irq_count;
mpic->num_sources = 0; /* so far */
- if (flags & MPIC_LARGE_VECTORS)
+ if (mpic->flags & MPIC_LARGE_VECTORS)
intvec_top = 2047;
else
intvec_top = 255;
mpic->ipi_vecs[3] = intvec_top - 1;
mpic->spurious_vec = intvec_top;
- /* Check for "big-endian" in device-tree */
- if (of_get_property(mpic->node, "big-endian", NULL) != NULL)
- mpic->flags |= MPIC_BIG_ENDIAN;
- if (of_device_is_compatible(mpic->node, "fsl,mpic"))
- mpic->flags |= MPIC_FSL;
-
/* Look for protected sources */
psrc = of_get_property(mpic->node, "protected-sources", &psize);
if (psrc) {
}
#ifdef CONFIG_MPIC_WEIRD
- mpic->hw_set = mpic_infos[MPIC_GET_REGSET(flags)];
+ mpic->hw_set = mpic_infos[MPIC_GET_REGSET(mpic->flags)];
#endif
/* default register type */
- if (flags & MPIC_BIG_ENDIAN)
+ if (mpic->flags & MPIC_BIG_ENDIAN)
mpic->reg_type = mpic_access_mmio_be;
else
mpic->reg_type = mpic_access_mmio_le;
* only if the kernel includes DCR support.
*/
#ifdef CONFIG_PPC_DCR
- if (flags & MPIC_USES_DCR)
+ if (mpic->flags & MPIC_USES_DCR)
mpic->reg_type = mpic_access_dcr;
#else
- BUG_ON(flags & MPIC_USES_DCR);
+ BUG_ON(mpic->flags & MPIC_USES_DCR);
#endif
/* Map the global registers */
/* When using a device-node, reset requests are only honored if the MPIC
* is allowed to reset.
*/
- if (of_get_property(mpic->node, "pic-no-reset", NULL))
- mpic->flags |= MPIC_NO_RESET;
-
- if ((flags & MPIC_WANTS_RESET) && !(mpic->flags & MPIC_NO_RESET)) {
+ if (!(mpic->flags & MPIC_NO_RESET)) {
printk(KERN_DEBUG "mpic: Resetting\n");
mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
}
/* CoreInt */
- if (flags & MPIC_ENABLE_COREINT)
+ if (mpic->flags & MPIC_ENABLE_COREINT)
mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
| MPIC_GREG_GCONF_COREINT);
- if (flags & MPIC_ENABLE_MCK)
+ if (mpic->flags & MPIC_ENABLE_MCK)
mpic_write(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0),
mpic_read(mpic->gregs, MPIC_INFO(GREG_GLOBAL_CONF_0))
| MPIC_GREG_GCONF_MCK);
- /*
- * Read feature register. For non-ISU MPICs, num sources as well. On
- * ISU MPICs, sources are counted as ISUs are added
- */
- greg_feature = mpic_read(mpic->gregs, MPIC_INFO(GREG_FEATURE_0));
- if (isu_size == 0) {
- if (flags & MPIC_BROKEN_FRR_NIRQS)
- mpic->num_sources = mpic->irq_count;
- else
- mpic->num_sources =
- ((greg_feature & MPIC_GREG_FEATURE_LAST_SRC_MASK)
- >> MPIC_GREG_FEATURE_LAST_SRC_SHIFT) + 1;
- }
-
/*
* The MPIC driver will crash if there are more cores than we
* can initialize, so we may as well catch that problem here.
0x1000);
}
+ /*
+ * Read feature register. For non-ISU MPICs, num sources as well. On
+ * ISU MPICs, sources are counted as ISUs are added
+ */
+ greg_feature = mpic_read(mpic->gregs, MPIC_INFO(GREG_FEATURE_0));
+
+ /*
+ * By default, the last source number comes from the MPIC, but the
+ * device-tree and board support code can override it on buggy hw.
+ */
+ last_irq = (greg_feature & MPIC_GREG_FEATURE_LAST_SRC_MASK)
+ >> MPIC_GREG_FEATURE_LAST_SRC_SHIFT;
+ of_property_read_u32(mpic->node, "last-interrupt-source", &last_irq);
+ if (irq_count)
+ last_irq = irq_count - 1;
+
/* Initialize main ISU if none provided */
- if (mpic->isu_size == 0) {
- mpic->isu_size = mpic->num_sources;
+ if (!isu_size) {
+ isu_size = last_irq + 1;
+ mpic->num_sources = isu_size;
mpic_map(mpic, mpic->paddr, &mpic->isus[0],
- MPIC_INFO(IRQ_BASE), MPIC_INFO(IRQ_STRIDE) * mpic->isu_size);
+ MPIC_INFO(IRQ_BASE),
+ MPIC_INFO(IRQ_STRIDE) * isu_size);
}
+
+ mpic->isu_size = isu_size;
mpic->isu_shift = 1 + __ilog2(mpic->isu_size - 1);
mpic->isu_mask = (1 << mpic->isu_shift) - 1;
mpic->irqhost = irq_alloc_host(mpic->node, IRQ_HOST_MAP_LINEAR,
- isu_size ? isu_size : mpic->num_sources,
- &mpic_host_ops,
- flags & MPIC_LARGE_VECTORS ? 2048 : 256);
+ mpic->isu_size, &mpic_host_ops,
+ intvec_top + 1);
/*
* FIXME: The code leaks the MPIC object and mappings here; this
mpic->next = mpics;
mpics = mpic;
- if (!(flags & MPIC_SECONDARY)) {
+ if (!(mpic->flags & MPIC_SECONDARY)) {
mpic_primary = mpic;
irq_set_default_host(mpic->irqhost);
}
(mpic->ipi_vecs[0] + i));
}
- /* Initialize interrupt sources */
- if (mpic->irq_count == 0)
- mpic->irq_count = mpic->num_sources;
-
/* Do the HT PIC fixups on U3 broken mpic */
DBG("MPIC flags: %x\n", mpic->flags);
if ((mpic->flags & MPIC_U3_HT_IRQS) && !(mpic->flags & MPIC_SECONDARY)) {
for (i = 100; i < 105; i++)
msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, i);
- for (i = 124; i < mpic->irq_count; i++)
+ for (i = 124; i < mpic->num_sources; i++)
msi_bitmap_reserve_hwirq(&mpic->msi_bitmap, i);
{
int rc;
- rc = msi_bitmap_alloc(&mpic->msi_bitmap, mpic->irq_count,
+ rc = msi_bitmap_alloc(&mpic->msi_bitmap, mpic->num_sources,
mpic->irqhost->of_node);
if (rc)
return rc;
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);