Gwendal Grignou | d902747 | 2010-05-25 12:31:38 -0700 | [diff] [blame] | 1 | What: /sys/class/ata_... |
| 2 | Date: August 2008 |
| 3 | Contact: Gwendal Grignou<gwendal@google.com> |
| 4 | Description: |
| 5 | |
| 6 | Provide a place in sysfs for storing the ATA topology of the system. This allows |
| 7 | retrieving various information about ATA objects. |
| 8 | |
| 9 | Files under /sys/class/ata_port |
| 10 | ------------------------------- |
| 11 | |
| 12 | For each port, a directory ataX is created where X is the ata_port_id of |
| 13 | the port. The device parent is the ata host device. |
| 14 | |
| 15 | idle_irq (read) |
| 16 | |
| 17 | Number of IRQ received by the port while idle [some ata HBA only]. |
| 18 | |
| 19 | nr_pmp_links (read) |
| 20 | |
| 21 | If a SATA Port Multiplier (PM) is connected, number of link behind it. |
| 22 | |
| 23 | Files under /sys/class/ata_link |
| 24 | ------------------------------- |
| 25 | |
| 26 | Behind each port, there is a ata_link. If there is a SATA PM in the |
| 27 | topology, 15 ata_link objects are created. |
| 28 | |
| 29 | If a link is behind a port, the directory name is linkX, where X is |
| 30 | ata_port_id of the port. |
| 31 | If a link is behind a PM, its name is linkX.Y where X is ata_port_id |
| 32 | of the parent port and Y the PM port. |
| 33 | |
| 34 | hw_sata_spd_limit |
| 35 | |
| 36 | Maximum speed supported by the connected SATA device. |
| 37 | |
| 38 | sata_spd_limit |
| 39 | |
| 40 | Maximum speed imposed by libata. |
| 41 | |
| 42 | sata_spd |
| 43 | |
| 44 | Current speed of the link [1.5, 3Gps,...]. |
| 45 | |
| 46 | Files under /sys/class/ata_device |
| 47 | --------------------------------- |
| 48 | |
| 49 | Behind each link, up to two ata device are created. |
| 50 | The name of the directory is devX[.Y].Z where: |
| 51 | - X is ata_port_id of the port where the device is connected, |
| 52 | - Y the port of the PM if any, and |
| 53 | - Z the device id: for PATA, there is usually 2 devices [0,1], |
| 54 | only 1 for SATA. |
| 55 | |
| 56 | class |
| 57 | Device class. Can be "ata" for disk, "atapi" for packet device, |
| 58 | "pmp" for PM, or "none" if no device was found behind the link. |
| 59 | |
| 60 | dma_mode |
| 61 | |
| 62 | Transfer modes supported by the device when in DMA mode. |
| 63 | Mostly used by PATA device. |
| 64 | |
| 65 | pio_mode |
| 66 | |
| 67 | Transfer modes supported by the device when in PIO mode. |
| 68 | Mostly used by PATA device. |
| 69 | |
| 70 | xfer_mode |
| 71 | |
| 72 | Current transfer mode. |
| 73 | |
| 74 | id |
| 75 | |
| 76 | Cached result of IDENTIFY command, as described in ATA8 7.16 and 7.17. |
| 77 | Only valid if the device is not a PM. |
| 78 | |
| 79 | gscr |
| 80 | |
| 81 | Cached result of the dump of PM GSCR register. |
| 82 | Valid registers are: |
| 83 | 0: SATA_PMP_GSCR_PROD_ID, |
| 84 | 1: SATA_PMP_GSCR_REV, |
| 85 | 2: SATA_PMP_GSCR_PORT_INFO, |
| 86 | 32: SATA_PMP_GSCR_ERROR, |
| 87 | 33: SATA_PMP_GSCR_ERROR_EN, |
| 88 | 64: SATA_PMP_GSCR_FEAT, |
| 89 | 96: SATA_PMP_GSCR_FEAT_EN, |
| 90 | 130: SATA_PMP_GSCR_SII_GPIO |
| 91 | Only valid if the device is a PM. |
| 92 | |
Martin K. Petersen | f303074 | 2015-05-04 21:54:19 -0400 | [diff] [blame] | 93 | trim |
| 94 | |
| 95 | Shows the DSM TRIM mode currently used by the device. Valid |
| 96 | values are: |
| 97 | unsupported: Drive does not support DSM TRIM |
| 98 | unqueued: Drive supports unqueued DSM TRIM only |
| 99 | queued: Drive supports queued DSM TRIM |
Martin K. Petersen | 4b9d64e | 2015-05-05 17:53:48 -0400 | [diff] [blame] | 100 | forced_unqueued: Drive's queued DSM support is known to be |
Martin K. Petersen | f303074 | 2015-05-04 21:54:19 -0400 | [diff] [blame] | 101 | buggy and only unqueued TRIM commands |
| 102 | are sent |
| 103 | |
Gwendal Grignou | d902747 | 2010-05-25 12:31:38 -0700 | [diff] [blame] | 104 | spdn_cnt |
| 105 | |
| 106 | Number of time libata decided to lower the speed of link due to errors. |
| 107 | |
| 108 | ering |
| 109 | |
| 110 | Formatted output of the error ring of the device. |