blob: 26b9f31cf65aeb84110361751e9d1cba488fec65
1 | Ramoops oops/panic logger |
2 | ========================= |
3 | |
4 | Sergiu Iordache <sergiu@chromium.org> |
5 | |
6 | Updated: 17 November 2011 |
7 | |
8 | 0. Introduction |
9 | |
10 | Ramoops is an oops/panic logger that writes its logs to RAM before the system |
11 | crashes. It works by logging oopses and panics in a circular buffer. Ramoops |
12 | needs a system with persistent RAM so that the content of that area can |
13 | survive after a restart. |
14 | |
15 | 1. Ramoops concepts |
16 | |
17 | Ramoops uses a predefined memory area to store the dump. The start and size |
18 | and type of the memory area are set using three variables: |
19 | * "mem_address" for the start |
20 | * "mem_size" for the size. The memory size will be rounded down to a |
21 | power of two. |
22 | * "mem_type" to specifiy if the memory type (default is pgprot_writecombine). |
23 | |
24 | Typically the default value of mem_type=0 should be used as that sets the pstore |
25 | mapping to pgprot_writecombine. Setting mem_type=1 attempts to use |
26 | pgprot_noncached, which only works on some platforms. This is because pstore |
27 | depends on atomic operations. At least on ARM, pgprot_noncached causes the |
28 | memory to be mapped strongly ordered, and atomic operations on strongly ordered |
29 | memory are implementation defined, and won't work on many ARMs such as omaps. |
30 | |
31 | The memory area is divided into "record_size" chunks (also rounded down to |
32 | power of two) and each oops/panic writes a "record_size" chunk of |
33 | information. |
34 | |
35 | Dumping both oopses and panics can be done by setting 1 in the "dump_oops" |
36 | variable while setting 0 in that variable dumps only the panics. |
37 | |
38 | The module uses a counter to record multiple dumps but the counter gets reset |
39 | on restart (i.e. new dumps after the restart will overwrite old ones). |
40 | |
41 | Ramoops also supports software ECC protection of persistent memory regions. |
42 | This might be useful when a hardware reset was used to bring the machine back |
43 | to life (i.e. a watchdog triggered). In such cases, RAM may be somewhat |
44 | corrupt, but usually it is restorable. |
45 | |
46 | 2. Setting the parameters |
47 | |
48 | Setting the ramoops parameters can be done in several different manners: |
49 | |
50 | A. Use the module parameters (which have the names of the variables described |
51 | as before). For quick debugging, you can also reserve parts of memory during |
52 | boot and then use the reserved memory for ramoops. For example, assuming a |
53 | machine with > 128 MB of memory, the following kernel command line will tell |
54 | the kernel to use only the first 128 MB of memory, and place ECC-protected |
55 | ramoops region at 128 MB boundary: |
56 | "mem=128M ramoops.mem_address=0x8000000 ramoops.ecc=1" |
57 | |
58 | B. Use Device Tree bindings, as described in |
59 | Documentation/device-tree/bindings/reserved-memory/ramoops.txt. |
60 | For example: |
61 | |
62 | reserved-memory { |
63 | #address-cells = <2>; |
64 | #size-cells = <2>; |
65 | ranges; |
66 | |
67 | ramoops@8f000000 { |
68 | compatible = "ramoops"; |
69 | reg = <0 0x8f000000 0 0x100000>; |
70 | record-size = <0x4000>; |
71 | console-size = <0x4000>; |
72 | }; |
73 | }; |
74 | |
75 | C. Use a platform device and set the platform data. The parameters can then |
76 | be set through that platform data. An example of doing that is: |
77 | |
78 | #include <linux/pstore_ram.h> |
79 | [...] |
80 | |
81 | static struct ramoops_platform_data ramoops_data = { |
82 | .mem_size = <...>, |
83 | .mem_address = <...>, |
84 | .mem_type = <...>, |
85 | .record_size = <...>, |
86 | .dump_oops = <...>, |
87 | .ecc = <...>, |
88 | }; |
89 | |
90 | static struct platform_device ramoops_dev = { |
91 | .name = "ramoops", |
92 | .dev = { |
93 | .platform_data = &ramoops_data, |
94 | }, |
95 | }; |
96 | |
97 | [... inside a function ...] |
98 | int ret; |
99 | |
100 | ret = platform_device_register(&ramoops_dev); |
101 | if (ret) { |
102 | printk(KERN_ERR "unable to register platform device\n"); |
103 | return ret; |
104 | } |
105 | |
106 | You can specify either RAM memory or peripheral devices' memory. However, when |
107 | specifying RAM, be sure to reserve the memory by issuing memblock_reserve() |
108 | very early in the architecture code, e.g.: |
109 | |
110 | #include <linux/memblock.h> |
111 | |
112 | memblock_reserve(ramoops_data.mem_address, ramoops_data.mem_size); |
113 | |
114 | 3. Dump format |
115 | |
116 | The data dump begins with a header, currently defined as "====" followed by a |
117 | timestamp and a new line. The dump then continues with the actual data. |
118 | |
119 | 4. Reading the data |
120 | |
121 | The dump data can be read from the pstore filesystem. The format for these |
122 | files is "dmesg-ramoops-N", where N is the record number in memory. To delete |
123 | a stored record from RAM, simply unlink the respective pstore file. |
124 | |
125 | 5. Persistent function tracing |
126 | |
127 | Persistent function tracing might be useful for debugging software or hardware |
128 | related hangs. The functions call chain log is stored in a "ftrace-ramoops" |
129 | file. Here is an example of usage: |
130 | |
131 | # mount -t debugfs debugfs /sys/kernel/debug/ |
132 | # echo 1 > /sys/kernel/debug/pstore/record_ftrace |
133 | # reboot -f |
134 | [...] |
135 | # mount -t pstore pstore /mnt/ |
136 | # tail /mnt/ftrace-ramoops |
137 | 0 ffffffff8101ea64 ffffffff8101bcda native_apic_mem_read <- disconnect_bsp_APIC+0x6a/0xc0 |
138 | 0 ffffffff8101ea44 ffffffff8101bcf6 native_apic_mem_write <- disconnect_bsp_APIC+0x86/0xc0 |
139 | 0 ffffffff81020084 ffffffff8101a4b5 hpet_disable <- native_machine_shutdown+0x75/0x90 |
140 | 0 ffffffff81005f94 ffffffff8101a4bb iommu_shutdown_noop <- native_machine_shutdown+0x7b/0x90 |
141 | 0 ffffffff8101a6a1 ffffffff8101a437 native_machine_emergency_restart <- native_machine_restart+0x37/0x40 |
142 | 0 ffffffff811f9876 ffffffff8101a73a acpi_reboot <- native_machine_emergency_restart+0xaa/0x1e0 |
143 | 0 ffffffff8101a514 ffffffff8101a772 mach_reboot_fixups <- native_machine_emergency_restart+0xe2/0x1e0 |
144 | 0 ffffffff811d9c54 ffffffff8101a7a0 __const_udelay <- native_machine_emergency_restart+0x110/0x1e0 |
145 | 0 ffffffff811d9c34 ffffffff811d9c80 __delay <- __const_udelay+0x30/0x40 |
146 | 0 ffffffff811d9d14 ffffffff811d9c3f delay_tsc <- __delay+0xf/0x20 |
147 |