diff options
Diffstat (limited to 'Documentation/hwmon/adm1021')
-rw-r--r-- | Documentation/hwmon/adm1021 | 36 |
1 files changed, 19 insertions, 17 deletions
diff --git a/Documentation/hwmon/adm1021 b/Documentation/hwmon/adm1021 index 03d02bfb3df1..02ad96cf9b2b 100644 --- a/Documentation/hwmon/adm1021 +++ b/Documentation/hwmon/adm1021 | |||
@@ -14,10 +14,6 @@ Supported chips: | |||
14 | Prefix: 'gl523sm' | 14 | Prefix: 'gl523sm' |
15 | Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e | 15 | Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e |
16 | Datasheet: | 16 | Datasheet: |
17 | * Intel Xeon Processor | ||
18 | Prefix: - any other - may require 'force_adm1021' parameter | ||
19 | Addresses scanned: none | ||
20 | Datasheet: Publicly available at Intel website | ||
21 | * Maxim MAX1617 | 17 | * Maxim MAX1617 |
22 | Prefix: 'max1617' | 18 | Prefix: 'max1617' |
23 | Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e | 19 | Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e |
@@ -91,21 +87,27 @@ will do no harm, but will return 'old' values. It is possible to make | |||
91 | ADM1021-clones do faster measurements, but there is really no good reason | 87 | ADM1021-clones do faster measurements, but there is really no good reason |
92 | for that. | 88 | for that. |
93 | 89 | ||
94 | Xeon support | ||
95 | ------------ | ||
96 | 90 | ||
97 | Some Xeon processors have real max1617, adm1021, or compatible chips | 91 | Netburst-based Xeon support |
98 | within them, with two temperature sensors. | 92 | --------------------------- |
99 | 93 | ||
100 | Other Xeons have chips with only one sensor. | 94 | Some Xeon processors based on the Netburst (early Pentium 4, from 2001 to |
95 | 2003) microarchitecture had real MAX1617, ADM1021, or compatible chips | ||
96 | within them, with two temperature sensors. Other Xeon processors of this | ||
97 | era (with 400 MHz FSB) had chips with only one temperature sensor. | ||
101 | 98 | ||
102 | If you have a Xeon, and the adm1021 module loads, and both temperatures | 99 | If you have such an old Xeon, and you get two valid temperatures when |
103 | appear valid, then things are good. | 100 | loading the adm1021 module, then things are good. |
104 | 101 | ||
105 | If the adm1021 module doesn't load, you should try this: | 102 | If nothing happens when loading the adm1021 module, and you are certain |
106 | modprobe adm1021 force_adm1021=BUS,ADDRESS | 103 | that your specific Xeon processor model includes compatible sensors, you |
107 | ADDRESS can only be 0x18, 0x1a, 0x29, 0x2b, 0x4c, or 0x4e. | 104 | will have to explicitly instantiate the sensor chips from user-space. See |
105 | method 4 in Documentation/i2c/instantiating-devices. Possible slave | ||
106 | addresses are 0x18, 0x1a, 0x29, 0x2b, 0x4c, or 0x4e. It is likely that | ||
107 | only temp2 will be correct and temp1 will have to be ignored. | ||
108 | 108 | ||
109 | If you have dual Xeons you may have appear to have two separate | 109 | Previous generations of the Xeon processor (based on Pentium II/III) |
110 | adm1021-compatible chips, or two single-temperature sensors, at distinct | 110 | didn't have these sensors. Next generations of Xeon processors (533 MHz |
111 | addresses. | 111 | FSB and faster) lost them, until the Core-based generation which |
112 | introduced integrated digital thermal sensors. These are supported by | ||
113 | the coretemp driver. | ||