From 4310c6b8e75d6a47f7548e5948fbe6318aa4440a Mon Sep 17 00:00:00 2001 From: Fedor Pchelkin Date: Mon, 31 Aug 2026 10:58:09 +0300 Subject: thunderbolt: Fix NULL dereference in tb_remove_work() There is a slight race between tb_remove_work() and tb_domain_remove() which leads to dereferencing a NULL tb->root_switch pointer inside tb_free_unplugged_xdomains(): Thread A Thread B tb_remove_work() tb_domain_remove() mutex_lock(&tb->lock) tb_stop() /* doesn't cancel a running callback */ cancel_delayed_work(&tcm->remove_work) ... tb_switch_remove(tb->root_switch) tb->root_switch = NULL mutex_unlock(&tb->lock) mutex_lock(&tb->lock) ... /* without checking ->root_switch */ tb_free_unplugged_xdomains(tb->root_switch) mutex_unlock(&tb->lock) Commit a8937f35cf39 ("thunderbolt: Remove XDomain from the bus without holding tb->lock") doesn't seem right to move tb_free_unplugged_xdomains() out of the &tb->lock section and the check for tb->root_switch, in particular. It states: For this reason separate removing the XDomain from the topology data structures (where we need the lock) from unregistering the device from the bus (where remove callbacks of the drivers are being called). tb_free_unplugged_xdomains() belongs to the former group of functions requiring the lock. And it also calls tb_xdomain_remove() which should only be called with &tb->lock held. Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool. Fixes: a8937f35cf39 ("thunderbolt: Remove XDomain from the bus without holding tb->lock") Cc: stable@vger.kernel.org Signed-off-by: Fedor Pchelkin Signed-off-by: Mika Westerberg --- .../blockdev/drbd/DRBD-8.3-data-packets.svg | 588 ++++++++++++++++++++ .../blockdev/drbd/DRBD-data-packets.svg | 459 ++++++++++++++++ .../admin-guide/blockdev/drbd/conn-states-8.dot | 18 + .../blockdev/drbd/data-structure-v9.rst | 42 ++ .../admin-guide/blockdev/drbd/disk-states-8.dot | 16 + .../drbd/drbd-connection-state-overview.dot | 85 +++ .../admin-guide/blockdev/drbd/figures.rst | 30 + Documentation/admin-guide/blockdev/drbd/index.rst | 19 + .../admin-guide/blockdev/drbd/peer-states-8.dot | 8 + Documentation/admin-guide/blockdev/floppy.rst | 255 +++++++++ Documentation/admin-guide/blockdev/index.rst | 17 + Documentation/admin-guide/blockdev/nbd.rst | 31 ++ Documentation/admin-guide/blockdev/paride.rst | 207 +++++++ Documentation/admin-guide/blockdev/ramdisk.rst | 153 ++++++ Documentation/admin-guide/blockdev/zoned_loop.rst | 191 +++++++ Documentation/admin-guide/blockdev/zram.rst | 610 +++++++++++++++++++++ 16 files changed, 2729 insertions(+) create mode 100644 Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg create mode 100644 Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg create mode 100644 Documentation/admin-guide/blockdev/drbd/conn-states-8.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/disk-states-8.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/figures.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/index.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/peer-states-8.dot create mode 100644 Documentation/admin-guide/blockdev/floppy.rst create mode 100644 Documentation/admin-guide/blockdev/index.rst create mode 100644 Documentation/admin-guide/blockdev/nbd.rst create mode 100644 Documentation/admin-guide/blockdev/paride.rst create mode 100644 Documentation/admin-guide/blockdev/ramdisk.rst create mode 100644 Documentation/admin-guide/blockdev/zoned_loop.rst create mode 100644 Documentation/admin-guide/blockdev/zram.rst (limited to 'Documentation/admin-guide/blockdev') diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg new file mode 100644 index 000000000..f87cfa0dc --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg @@ -0,0 +1,588 @@ + + + + + + Master slide + + + + + + + + + + RSDataReply + + + + + + + CsumRSRequest + + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + + WriteAck + + + + got_BlockAck() + + + Checksum based Resync, case not in sync + + + DRBD-8.3 data flow + + + w_e_send_csum() + + + + + + + + RSIsInSync + + + + + + + CsumRSRequest + + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + got_IsInSync() + + + Checksum based Resync, case in sync + + + + + + + + + + OVReply + + + + + + + OVRequest + + + + receive_OVRequest() + + + drbd_endio_read_sec() + + + w_e_end_ov_req() + + + receive_OVReply() + + + drbd_endio_read_sec() + + + w_e_end_ov_reply() + + + + + + OVResult + + + + got_OVResult() + + + Online verify + + + w_make_ov_request() + + + + + + + + drbd_endio_read_sec() + + + w_make_resync_request() + + + w_e_send_csum() + + + + + drbd_endio_read_sec() + + + + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg new file mode 100644 index 000000000..48a1e2165 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg @@ -0,0 +1,459 @@ + + + + + + Master slide + + + + + + + + + RSDataReply + + + + + RSDataRequest + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_rsdata_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + WriteAck + + + got_BlockAck() + + + Resync blocks, 4-32K + + + + + + + WriteAck + + + + + Data + + + drbd_make_request() + + + receive_Data() + + + drbd_endio_write_sec() + + + e_end_block() + + + got_BlockAck() + + + Regular mirrored write, 512-32K + + + w_send_dblock() + + + + + drbd_endio_write_pri() + + + + + + + DataReply + + + + + DataRequest + + + drbd_make_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_data_req() + + + Drawing + + receive_DataReply() + + + + Diskless read, 512-32K + + + w_send_read_req() + + + DRBD 8 data flow + + + + + + al_begin_io() + + + al_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + diff --git a/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot new file mode 100644 index 000000000..025e8cf5e --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot @@ -0,0 +1,18 @@ +digraph conn_states { + StandAllone -> WFConnection [ label = "ioctl_set_net()" ] + WFConnection -> Unconnected [ label = "unable to bind()" ] + WFConnection -> WFReportParams [ label = "in connect() after accept" ] + WFReportParams -> StandAllone [ label = "checks in receive_param()" ] + WFReportParams -> Connected [ label = "in receive_param()" ] + WFReportParams -> WFBitMapS [ label = "sync_handshake()" ] + WFReportParams -> WFBitMapT [ label = "sync_handshake()" ] + WFBitMapS -> SyncSource [ label = "receive_bitmap()" ] + WFBitMapT -> SyncTarget [ label = "receive_bitmap()" ] + SyncSource -> Connected + SyncTarget -> Connected + SyncSource -> PausedSyncS + SyncTarget -> PausedSyncT + PausedSyncS -> SyncSource + PausedSyncT -> SyncTarget + Connected -> WFConnection [ label = "* on network error" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst new file mode 100644 index 000000000..66036b901 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst @@ -0,0 +1,42 @@ +================================ +kernel data structure for DRBD-9 +================================ + +This describes the in kernel data structure for DRBD-9. Starting with +Linux v3.14 we are reorganizing DRBD to use this data structure. + +Basic Data Structure +==================== + +A node has a number of DRBD resources. Each such resource has a number of +devices (aka volumes) and connections to other nodes ("peer nodes"). Each DRBD +device is represented by a block device locally. + +The DRBD objects are interconnected to form a matrix as depicted below; a +drbd_peer_device object sits at each intersection between a drbd_device and a +drbd_connection:: + + /--------------+---------------+.....+---------------\ + | resource | device | | device | + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + +--------------+---------------+.....+---------------+ + : : : : : + : : : : : + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + \--------------+---------------+.....+---------------/ + +In this table, horizontally, devices can be accessed from resources by their +volume number. Likewise, peer_devices can be accessed from connections by +their volume number. Objects in the vertical direction are connected by double +linked lists. There are back pointers from peer_devices to their connections a +devices, and from connections and devices to their resource. + +All resources are in the drbd_resources double-linked list. In addition, all +devices can be accessed by their minor device number via the drbd_devices idr. + +The drbd_resource, drbd_connection, and drbd_device objects are reference +counted. The peer_device objects only serve to establish the links between +devices and connections; their lifetime is determined by the lifetime of the +device and connection which they reference. diff --git a/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot new file mode 100644 index 000000000..d06cfb46f --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot @@ -0,0 +1,16 @@ +digraph disk_states { + Diskless -> Inconsistent [ label = "ioctl_set_disk()" ] + Diskless -> Consistent [ label = "ioctl_set_disk()" ] + Diskless -> Outdated [ label = "ioctl_set_disk()" ] + Consistent -> Outdated [ label = "receive_param()" ] + Consistent -> UpToDate [ label = "receive_param()" ] + Consistent -> Inconsistent [ label = "start resync" ] + Outdated -> Inconsistent [ label = "start resync" ] + UpToDate -> Inconsistent [ label = "ioctl_replicate" ] + Inconsistent -> UpToDate [ label = "resync completed" ] + Consistent -> Failed [ label = "io completion error" ] + Outdated -> Failed [ label = "io completion error" ] + UpToDate -> Failed [ label = "io completion error" ] + Inconsistent -> Failed [ label = "io completion error" ] + Failed -> Diskless [ label = "sending notify to peer" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot new file mode 100644 index 000000000..6d9cf0a7b --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot @@ -0,0 +1,85 @@ +// vim: set sw=2 sts=2 : +digraph { + rankdir=BT + bgcolor=white + + node [shape=plaintext] + node [fontcolor=black] + + StandAlone [ style=filled,fillcolor=gray,label=StandAlone ] + + node [fontcolor=lightgray] + + Unconnected [ label=Unconnected ] + + CommTrouble [ shape=record, + label="{communication loss|{Timeout|BrokenPipe|NetworkFailure}}" ] + + node [fontcolor=gray] + + subgraph cluster_try_connect { + label="try to connect, handshake" + rank=max + WFConnection [ label=WFConnection ] + WFReportParams [ label=WFReportParams ] + } + + TearDown [ label=TearDown ] + + Connected [ label=Connected,style=filled,fillcolor=green,fontcolor=black ] + + node [fontcolor=lightblue] + + StartingSyncS [ label=StartingSyncS ] + StartingSyncT [ label=StartingSyncT ] + + subgraph cluster_bitmap_exchange { + node [fontcolor=red] + fontcolor=red + label="new application (WRITE?) requests blocked\lwhile bitmap is exchanged" + + WFBitMapT [ label=WFBitMapT ] + WFSyncUUID [ label=WFSyncUUID ] + WFBitMapS [ label=WFBitMapS ] + } + + node [fontcolor=blue] + + cluster_resync [ shape=record,label="{resynchronisation process running\l'concurrent' application requests allowed|{{PausedSyncT\nSyncTarget}|{PausedSyncS\nSyncSource}}}" ] + + node [shape=box,fontcolor=black] + + // drbdadm [label="drbdadm connect"] + // handshake [label="drbd_connect()\ndrbd_do_handshake\ndrbd_sync_handshake() etc."] + // comm_error [label="communication trouble"] + + // + // edges + // -------------------------------------- + + StandAlone -> Unconnected [ label="drbdadm connect" ] + Unconnected -> StandAlone [ label="drbdadm disconnect\lor serious communication trouble" ] + Unconnected -> WFConnection [ label="receiver thread is started" ] + WFConnection -> WFReportParams [ headlabel="accept()\land/or \lconnect()\l" ] + + WFReportParams -> StandAlone [ label="during handshake\lpeers do not agree\labout something essential" ] + WFReportParams -> Connected [ label="data identical\lno sync needed",color=green,fontcolor=green ] + + WFReportParams -> WFBitMapS + WFReportParams -> WFBitMapT + WFBitMapT -> WFSyncUUID [minlen=0.1,constraint=false] + + WFBitMapS -> cluster_resync:S + WFSyncUUID -> cluster_resync:T + + edge [color=green] + cluster_resync:any -> Connected [ label="resnyc done",fontcolor=green ] + + edge [color=red] + WFReportParams -> CommTrouble + Connected -> CommTrouble + cluster_resync:any -> CommTrouble + edge [color=black] + CommTrouble -> Unconnected [label="receiver thread is stopped" ] + +} diff --git a/Documentation/admin-guide/blockdev/drbd/figures.rst b/Documentation/admin-guide/blockdev/drbd/figures.rst new file mode 100644 index 000000000..9f73253ea --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/figures.rst @@ -0,0 +1,30 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. The here included files are intended to help understand the implementation + +Data flows that Relate some functions, and write packets +======================================================== + +.. kernel-figure:: DRBD-8.3-data-packets.svg + :alt: DRBD-8.3-data-packets.svg + :align: center + +.. kernel-figure:: DRBD-data-packets.svg + :alt: DRBD-data-packets.svg + :align: center + + +Sub graphs of DRBD's state transitions +====================================== + +.. kernel-figure:: conn-states-8.dot + :alt: conn-states-8.dot + :align: center + +.. kernel-figure:: disk-states-8.dot + :alt: disk-states-8.dot + :align: center + +.. kernel-figure:: peer-states-8.dot + :alt: peer-states-8.dot + :align: center diff --git a/Documentation/admin-guide/blockdev/drbd/index.rst b/Documentation/admin-guide/blockdev/drbd/index.rst new file mode 100644 index 000000000..561fd1e35 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/index.rst @@ -0,0 +1,19 @@ +========================================== +Distributed Replicated Block Device - DRBD +========================================== + +Description +=========== + + DRBD is a shared-nothing, synchronously replicated block device. It + is designed to serve as a building block for high availability + clusters and in this context, is a "drop-in" replacement for shared + storage. Simplistically, you could see it as a network RAID 1. + + Please visit https://www.drbd.org to find out more. + +.. toctree:: + :maxdepth: 1 + + data-structure-v9 + figures diff --git a/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot new file mode 100644 index 000000000..6dc395495 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot @@ -0,0 +1,8 @@ +digraph peer_states { + Secondary -> Primary [ label = "recv state packet" ] + Primary -> Secondary [ label = "recv state packet" ] + Primary -> Unknown [ label = "connection lost" ] + Secondary -> Unknown [ label = "connection lost" ] + Unknown -> Primary [ label = "connected" ] + Unknown -> Secondary [ label = "connected" ] +} diff --git a/Documentation/admin-guide/blockdev/floppy.rst b/Documentation/admin-guide/blockdev/floppy.rst new file mode 100644 index 000000000..0328438eb --- /dev/null +++ b/Documentation/admin-guide/blockdev/floppy.rst @@ -0,0 +1,255 @@ +============= +Floppy Driver +============= + +FAQ list: +========= + +A FAQ list may be found in the fdutils package (see below), and also +at . + + +LILO configuration options (Thinkpad users, read this) +====================================================== + +The floppy driver is configured using the 'floppy=' option in +lilo. This option can be typed at the boot prompt, or entered in the +lilo configuration file. + +Example: If your kernel is called linux-2.6.9, type the following line +at the lilo boot prompt (if you have a thinkpad):: + + linux-2.6.9 floppy=thinkpad + +You may also enter the following line in /etc/lilo.conf, in the description +of linux-2.6.9:: + + append = "floppy=thinkpad" + +Several floppy related options may be given, example:: + + linux-2.6.9 floppy=daring floppy=two_fdc + append = "floppy=daring floppy=two_fdc" + +If you give options both in the lilo config file and on the boot +prompt, the option strings of both places are concatenated, the boot +prompt options coming last. That's why there are also options to +restore the default behavior. + + +Module configuration options +============================ + +If you use the floppy driver as a module, use the following syntax:: + + modprobe floppy floppy="" + +Example:: + + modprobe floppy floppy="omnibook messages" + +If you need certain options enabled every time you load the floppy driver, +you can put:: + + options floppy floppy="omnibook messages" + +in a configuration file in /etc/modprobe.d/. + + +The floppy driver related options are: + + floppy=asus_pci + Sets the bit mask to allow only units 0 and 1. (default) + + floppy=daring + Tells the floppy driver that you have a well behaved floppy controller. + This allows more efficient and smoother operation, but may fail on + certain controllers. This may speed up certain operations. + + floppy=0,daring + Tells the floppy driver that your floppy controller should be used + with caution. + + floppy=one_fdc + Tells the floppy driver that you have only one floppy controller. + (default) + + floppy=two_fdc / floppy=
,two_fdc + Tells the floppy driver that you have two floppy controllers. + The second floppy controller is assumed to be at
. + This option is not needed if the second controller is at address + 0x370, and if you use the 'cmos' option. + + floppy=thinkpad + Tells the floppy driver that you have a Thinkpad. Thinkpads use an + inverted convention for the disk change line. + + floppy=0,thinkpad + Tells the floppy driver that you don't have a Thinkpad. + + floppy=omnibook / floppy=nodma + Tells the floppy driver not to use Dma for data transfers. + This is needed on HP Omnibooks, which don't have a workable + DMA channel for the floppy driver. This option is also useful + if you frequently get "Unable to allocate DMA memory" messages. + Indeed, dma memory needs to be continuous in physical memory, + and is thus harder to find, whereas non-dma buffers may be + allocated in virtual memory. However, I advise against this if + you have an FDC without a FIFO (8272A or 82072). 82072A and + later are OK. You also need at least a 486 to use nodma. + If you use nodma mode, I suggest you also set the FIFO + threshold to 10 or lower, in order to limit the number of data + transfer interrupts. + + If you have a FIFO-able FDC, the floppy driver automatically + falls back on non DMA mode if no DMA-able memory can be found. + If you want to avoid this, explicitly ask for 'yesdma'. + + floppy=yesdma + Tells the floppy driver that a workable DMA channel is available. + (default) + + floppy=nofifo + Disables the FIFO entirely. This is needed if you get "Bus + master arbitration error" messages from your Ethernet card (or + from other devices) while accessing the floppy. + + floppy=usefifo + Enables the FIFO. (default) + + floppy=,fifo_depth + Sets the FIFO threshold. This is mostly relevant in DMA + mode. If this is higher, the floppy driver tolerates more + interrupt latency, but it triggers more interrupts (i.e. it + imposes more load on the rest of the system). If this is + lower, the interrupt latency should be lower too (faster + processor). The benefit of a lower threshold is less + interrupts. + + To tune the fifo threshold, switch on over/underrun messages + using 'floppycontrol --messages'. Then access a floppy + disk. If you get a huge amount of "Over/Underrun - retrying" + messages, then the fifo threshold is too low. Try with a + higher value, until you only get an occasional Over/Underrun. + It is a good idea to compile the floppy driver as a module + when doing this tuning. Indeed, it allows to try different + fifo values without rebooting the machine for each test. Note + that you need to do 'floppycontrol --messages' every time you + re-insert the module. + + Usually, tuning the fifo threshold should not be needed, as + the default (0xa) is reasonable. + + floppy=,,cmos + Sets the CMOS type of to . This is mandatory if + you have more than two floppy drives (only two can be + described in the physical CMOS), or if your BIOS uses + non-standard CMOS types. The CMOS types are: + + == ================================== + 0 Use the value of the physical CMOS + 1 5 1/4 DD + 2 5 1/4 HD + 3 3 1/2 DD + 4 3 1/2 HD + 5 3 1/2 ED + 6 3 1/2 ED + 16 unknown or not installed + == ================================== + + (Note: there are two valid types for ED drives. This is because 5 was + initially chosen to represent floppy *tapes*, and 6 for ED drives. + AMI ignored this, and used 5 for ED drives. That's why the floppy + driver handles both.) + + floppy=unexpected_interrupts + Print a warning message when an unexpected interrupt is received. + (default) + + floppy=no_unexpected_interrupts / floppy=L40SX + Don't print a message when an unexpected interrupt is received. This + is needed on IBM L40SX laptops in certain video modes. (There seems + to be an interaction between video and floppy. The unexpected + interrupts affect only performance, and can be safely ignored.) + + floppy=broken_dcl + Don't use the disk change line, but assume that the disk was + changed whenever the device node is reopened. Needed on some + boxes where the disk change line is broken or unsupported. + This should be regarded as a stopgap measure, indeed it makes + floppy operation less efficient due to unneeded cache + flushings, and slightly more unreliable. Please verify your + cable, connection and jumper settings if you have any DCL + problems. However, some older drives, and also some laptops + are known not to have a DCL. + + floppy=debug + Print debugging messages. + + floppy=messages + Print informational messages for some operations (disk change + notifications, warnings about over and underruns, and about + autodetection). + + floppy=silent_dcl_clear + Uses a less noisy way to clear the disk change line (which + doesn't involve seeks). Implied by 'daring' option. + + floppy=,irq + Sets the floppy IRQ to instead of 6. + + floppy=,dma + Sets the floppy DMA channel to instead of 2. + + floppy=slow + Use PS/2 stepping rate:: + + PS/2 floppies have much slower step rates than regular floppies. + It's been recommended that take about 1/4 of the default speed + in some more extreme cases. + + +Supporting utilities and additional documentation: +================================================== + +Additional parameters of the floppy driver can be configured at +runtime. Utilities which do this can be found in the fdutils package. +This package also contains a new version of mtools which allows to +access high capacity disks (up to 1992K on a high density 3 1/2 disk!). +It also contains additional documentation about the floppy driver. + +The latest version can be found at fdutils homepage: + + https://fdutils.linux.lu + +The fdutils releases can be found at: + + https://fdutils.linux.lu/download.html + + http://www.tux.org/pub/knaff/fdutils/ + + ftp://metalab.unc.edu/pub/Linux/utils/disk-management/ + +Reporting problems about the floppy driver +========================================== + +If you have a question or a bug report about the floppy driver, mail +me at Alain.Knaff@poboxes.com . If you post to Usenet, preferably use +comp.os.linux.hardware. As the volume in these groups is rather high, +be sure to include the word "floppy" (or "FLOPPY") in the subject +line. If the reported problem happens when mounting floppy disks, be +sure to mention also the type of the filesystem in the subject line. + +Be sure to read the FAQ before mailing/posting any bug reports! + +Alain + +Changelog +========= + +10-30-2004 : + Cleanup, updating, add reference to module configuration. + James Nelson + +6-3-2000 : + Original Document diff --git a/Documentation/admin-guide/blockdev/index.rst b/Documentation/admin-guide/blockdev/index.rst new file mode 100644 index 000000000..3262397eb --- /dev/null +++ b/Documentation/admin-guide/blockdev/index.rst @@ -0,0 +1,17 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============= +Block Devices +============= + +.. toctree:: + :maxdepth: 1 + + floppy + nbd + paride + ramdisk + zoned_loop + zram + + drbd/index diff --git a/Documentation/admin-guide/blockdev/nbd.rst b/Documentation/admin-guide/blockdev/nbd.rst new file mode 100644 index 000000000..faf2ac4b1 --- /dev/null +++ b/Documentation/admin-guide/blockdev/nbd.rst @@ -0,0 +1,31 @@ +================================== +Network Block Device (TCP version) +================================== + +1) Overview +----------- + +What is it: With this compiled in the kernel (or as a module), Linux +can use a remote server as one of its block devices. So every time +the client computer wants to read, e.g., /dev/nb0, it sends a +request over TCP to the server, which will reply with the data read. +This can be used for stations with low disk space (or even diskless) +to borrow disk space from another computer. +Unlike NFS, it is possible to put any filesystem on it, etc. + +For more information, or to download the nbd-client and nbd-server +tools, go to https://github.com/NetworkBlockDevice/nbd. + +The nbd kernel module need only be installed on the client +system, as the nbd-server is completely in userspace. In fact, +the nbd-server has been successfully ported to other operating +systems, including Windows. + +A) NBD parameters +----------------- + +max_part + Number of partitions per device (default: 0). + +nbds_max + Number of block devices that should be initialized (default: 16). diff --git a/Documentation/admin-guide/blockdev/paride.rst b/Documentation/admin-guide/blockdev/paride.rst new file mode 100644 index 000000000..b2f627d4c --- /dev/null +++ b/Documentation/admin-guide/blockdev/paride.rst @@ -0,0 +1,207 @@ +=================================== +Linux and parallel port IDE devices +=================================== + +PARIDE v1.03 (c) 1997-8 Grant Guenther +PATA_PARPORT (c) 2023 Ondrej Zary + +1. Introduction +=============== + +Owing to the simplicity and near universality of the parallel port interface +to personal computers, many external devices such as portable hard-disk, +CD-ROM, LS-120 and tape drives use the parallel port to connect to their +host computer. While some devices (notably scanners) use ad-hoc methods +to pass commands and data through the parallel port interface, most +external devices are actually identical to an internal model, but with +a parallel-port adapter chip added in. Some of the original parallel port +adapters were little more than mechanisms for multiplexing a SCSI bus. +(The Iomega PPA-3 adapter used in the ZIP drives is an example of this +approach). Most current designs, however, take a different approach. +The adapter chip reproduces a small ISA or IDE bus in the external device +and the communication protocol provides operations for reading and writing +device registers, as well as data block transfer functions. Sometimes, +the device being addressed via the parallel cable is a standard SCSI +controller like an NCR 5380. The "ditto" family of external tape +drives use the ISA replicator to interface a floppy disk controller, +which is then connected to a floppy-tape mechanism. The vast majority +of external parallel port devices, however, are now based on standard +IDE type devices, which require no intermediate controller. If one +were to open up a parallel port CD-ROM drive, for instance, one would +find a standard ATAPI CD-ROM drive, a power supply, and a single adapter +that interconnected a standard PC parallel port cable and a standard +IDE cable. It is usually possible to exchange the CD-ROM device with +any other device using the IDE interface. + +The document describes the support in Linux for parallel port IDE +devices. It does not cover parallel port SCSI devices, "ditto" tape +drives or scanners. Many different devices are supported by the +parallel port IDE subsystem, including: + + - MicroSolutions backpack CD-ROM + - MicroSolutions backpack PD/CD + - MicroSolutions backpack hard-drives + - MicroSolutions backpack 8000t tape drive + - SyQuest EZ-135, EZ-230 & SparQ drives + - Avatar Shark + - Imation Superdisk LS-120 + - Maxell Superdisk LS-120 + - FreeCom Power CD + - Hewlett-Packard 5GB and 8GB tape drives + - Hewlett-Packard 7100 and 7200 CD-RW drives + +as well as most of the clone and no-name products on the market. + +To support such a wide range of devices, pata_parport is actually structured +in two parts. There is a base pata_parport module which provides an interface +to kernel libata subsystem, registry and some common methods for accessing +the parallel ports. + +The second component is a set of low-level protocol drivers for each of the +parallel port IDE adapter chips. Thanks to the interest and encouragement of +Linux users from many parts of the world, support is available for almost all +known adapter protocols: + + ==== ====================================== ==== + aten ATEN EH-100 (HK) + bpck Microsolutions backpack (US) + comm DataStor (old-type) "commuter" adapter (TW) + dstr DataStor EP-2000 (TW) + epat Shuttle EPAT (UK) + epia Shuttle EPIA (UK) + fit2 FIT TD-2000 (US) + fit3 FIT TD-3000 (US) + friq Freecom IQ cable (DE) + frpw Freecom Power (DE) + kbic KingByte KBIC-951A and KBIC-971A (TW) + ktti KT Technology PHd adapter (SG) + on20 OnSpec 90c20 (US) + on26 OnSpec 90c26 (US) + ==== ====================================== ==== + + +2. Using pata_parport subsystem +=============================== + +While configuring the Linux kernel, you may choose either to build +the pata_parport drivers into your kernel, or to build them as modules. + +In either case, you will need to select "Parallel port IDE device support" +and at least one of the parallel port communication protocols. +If you do not know what kind of parallel port adapter is used in your drive, +you could begin by checking the file names and any text files on your DOS +installation floppy. Alternatively, you can look at the markings on +the adapter chip itself. That's usually sufficient to identify the +correct device. + +You can actually select all the protocol modules, and allow the pata_parport +subsystem to try them all for you. + +For the "brand-name" products listed above, here are the protocol +and high-level drivers that you would use: + + ================ ============ ======== + Manufacturer Model Protocol + ================ ============ ======== + MicroSolutions CD-ROM bpck + MicroSolutions PD drive bpck + MicroSolutions hard-drive bpck + MicroSolutions 8000t tape bpck + SyQuest EZ, SparQ epat + Imation Superdisk epat + Maxell Superdisk friq + Avatar Shark epat + FreeCom CD-ROM frpw + Hewlett-Packard 5GB Tape epat + Hewlett-Packard 7200e (CD) epat + Hewlett-Packard 7200e (CD-R) epat + ================ ============ ======== + +All parports and all protocol drivers are probed automatically unless probe=0 +parameter is used. So just "modprobe epat" is enough for an Imation SuperDisk +drive to work. + +Manual device creation:: + + # echo "port protocol mode unit delay" >/sys/bus/pata_parport/new_device + +where: + + ======== ================================================ + port parport name (or "auto" for all parports) + protocol protocol name (or "auto" for all protocols) + mode mode number (protocol-specific) or -1 for probe + unit unit number (for backpack only, see below) + delay I/O delay (see troubleshooting section below) + ======== ================================================ + +If you happen to be using a MicroSolutions backpack device, you will +also need to know the unit ID number for each drive. This is usually +the last two digits of the drive's serial number (but read MicroSolutions' +documentation about this). + +If you omit the parameters from the end, defaults will be used, e.g.: + +Probe all parports with all protocols:: + + # echo auto >/sys/bus/pata_parport/new_device + +Probe parport0 using protocol epat and mode 4 (EPP-16):: + + # echo "parport0 epat 4" >/sys/bus/pata_parport/new_device + +Probe parport0 using all protocols:: + + # echo "parport0 auto" >/sys/bus/pata_parport/new_device + +Probe all parports using protoocol epat:: + + # echo "auto epat" >/sys/bus/pata_parport/new_device + +Deleting devices:: + + # echo pata_parport.0 >/sys/bus/pata_parport/delete_device + + +3. Troubleshooting +================== + +3.1 Use EPP mode if you can +---------------------------- + +The most common problems that people report with the pata_parport drivers +concern the parallel port CMOS settings. At this time, none of the +protocol modules support ECP mode, or any ECP combination modes. +If you are able to do so, please set your parallel port into EPP mode +using your CMOS setup procedure. + +3.2 Check the port delay +------------------------- + +Some parallel ports cannot reliably transfer data at full speed. To +offset the errors, the protocol modules introduce a "port +delay" between each access to the i/o ports. Each protocol sets +a default value for this delay. In most cases, the user can override +the default and set it to 0 - resulting in somewhat higher transfer +rates. In some rare cases (especially with older 486 systems) the +default delays are not long enough. if you experience corrupt data +transfers, or unexpected failures, you may wish to increase the +port delay. + +3.3 Some drives need a printer reset +------------------------------------- + +There appear to be a number of "noname" external drives on the market +that do not always power up correctly. We have noticed this with some +drives based on OnSpec and older Freecom adapters. In these rare cases, +the adapter can often be reinitialised by issuing a "printer reset" on +the parallel port. As the reset operation is potentially disruptive in +multiple device environments, the pata_parport drivers will not do it +automatically. You can however, force a printer reset by doing:: + + insmod lp reset=1 + rmmod lp + +If you have one of these marginal cases, you should probably build +your pata_parport drivers as modules, and arrange to do the printer reset +before loading the pata_parport drivers. diff --git a/Documentation/admin-guide/blockdev/ramdisk.rst b/Documentation/admin-guide/blockdev/ramdisk.rst new file mode 100644 index 000000000..9ce6101e8 --- /dev/null +++ b/Documentation/admin-guide/blockdev/ramdisk.rst @@ -0,0 +1,153 @@ +========================================== +Using the RAM disk block device with Linux +========================================== + +.. Contents: + + 1) Overview + 2) Kernel Command Line Parameters + 3) Using "rdev" + 4) An Example of Creating a Compressed RAM Disk + + +1) Overview +----------- + +The RAM disk driver is a way to use main system memory as a block device. It +is required for initrd, an initial filesystem used if you need to load modules +in order to access the root filesystem (see Documentation/admin-guide/initrd.rst). It can +also be used for a temporary filesystem for crypto work, since the contents +are erased on reboot. + +The RAM disk dynamically grows as more space is required. It does this by using +RAM from the buffer cache. The driver marks the buffers it is using as dirty +so that the VM subsystem does not try to reclaim them later. + +The RAM disk supports up to 16 RAM disks by default, and can be reconfigured +to support an unlimited number of RAM disks (at your own risk). Just change +the configuration symbol BLK_DEV_RAM_COUNT in the Block drivers config menu +and (re)build the kernel. + +To use RAM disk support with your system, run './MAKEDEV ram' from the /dev +directory. RAM disks are all major number 1, and start with minor number 0 +for /dev/ram0, etc. If used, modern kernels use /dev/ram0 for an initrd. + +The new RAM disk also has the ability to load compressed RAM disk images, +allowing one to squeeze more programs onto an average installation or +rescue floppy disk. + + +2) Parameters +--------------------------------- + +2a) Kernel Command Line Parameters + + ramdisk_size=N + Size of the ramdisk. + +This parameter tells the RAM disk driver to set up RAM disks of N k size. The +default is 4096 (4 MB). + +2b) Module parameters + + rd_nr + /dev/ramX devices created. + + max_part + Maximum partition number. + + rd_size + See ramdisk_size. + +3) Using "rdev" +--------------- + +"rdev" is an obsolete, deprecated, antiquated utility that could be used +to set the boot device in a Linux kernel image. + +Instead of using rdev, just place the boot device information on the +kernel command line and pass it to the kernel from the bootloader. + +You can also pass arguments to the kernel by setting FDARGS in +arch/x86/boot/Makefile and specify in initrd image by setting FDINITRD in +arch/x86/boot/Makefile. + +Some of the kernel command line boot options that may apply here are:: + + ramdisk_start=N + ramdisk_size=M + +If you make a boot disk that has LILO, then for the above, you would use:: + + append = "ramdisk_start=N ramdisk_size=M" + +4) An Example of Creating a Compressed RAM Disk +----------------------------------------------- + +To create a RAM disk image, you will need a spare block device to +construct it on. This can be the RAM disk device itself, or an +unused disk partition (such as an unmounted swap partition). For this +example, we will use the RAM disk device, "/dev/ram0". + +Note: This technique should not be done on a machine with less than 8 MB +of RAM. If using a spare disk partition instead of /dev/ram0, then this +restriction does not apply. + +a) Decide on the RAM disk size that you want. Say 2 MB for this example. + Create it by writing to the RAM disk device. (This step is not currently + required, but may be in the future.) It is wise to zero out the + area (esp. for disks) so that maximal compression is achieved for + the unused blocks of the image that you are about to create:: + + dd if=/dev/zero of=/dev/ram0 bs=1k count=2048 + +b) Make a filesystem on it. Say ext2fs for this example:: + + mke2fs -vm0 /dev/ram0 2048 + +c) Mount it, copy the files you want to it (eg: /etc/* /dev/* ...) + and unmount it again. + +d) Compress the contents of the RAM disk. The level of compression + will be approximately 50% of the space used by the files. Unused + space on the RAM disk will compress to almost nothing:: + + dd if=/dev/ram0 bs=1k count=2048 | gzip -v9 > /tmp/ram_image.gz + +e) Put the kernel onto the floppy:: + + dd if=zImage of=/dev/fd0 bs=1k + +f) Put the RAM disk image onto the floppy, after the kernel. Use an offset + that is slightly larger than the kernel, so that you can put another + (possibly larger) kernel onto the same floppy later without overlapping + the RAM disk image. An offset of 400 kB for kernels about 350 kB in + size would be reasonable. Make sure offset+size of ram_image.gz is + not larger than the total space on your floppy (usually 1440 kB):: + + dd if=/tmp/ram_image.gz of=/dev/fd0 bs=1k seek=400 + +g) Make sure that you have already specified the boot information in + FDARGS and FDINITRD or that you use a bootloader to pass kernel + command line boot options to the kernel. + +That is it. You now have your boot/root compressed RAM disk floppy. Some +users may wish to combine steps (d) and (f) by using a pipe. + + + Paul Gortmaker 12/95 + +Changelog: +---------- + +SEPT-2020 : + + Removed usage of "rdev" + +10-22-04 : + Updated to reflect changes in command line options, remove + obsolete references, general cleanup. + James Nelson (james4765@gmail.com) + +12-95 : + Original Document diff --git a/Documentation/admin-guide/blockdev/zoned_loop.rst b/Documentation/admin-guide/blockdev/zoned_loop.rst new file mode 100644 index 000000000..64277494f --- /dev/null +++ b/Documentation/admin-guide/blockdev/zoned_loop.rst @@ -0,0 +1,191 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================= +Zoned Loop Block Device +======================= + +.. Contents: + + 1) Overview + 2) Creating a Zoned Device + 3) Deleting a Zoned Device + 4) Example + + +1) Overview +----------- + +The zoned loop block device driver (zloop) allows a user to create a zoned block +device using one regular file per zone as backing storage. This driver does not +directly control any hardware and uses read, write and truncate operations to +regular files of a file system to emulate a zoned block device. + +Using zloop, zoned block devices with a configurable capacity, zone size and +number of conventional zones can be created. The storage for each zone of the +device is implemented using a regular file with a maximum size equal to the zone +size. The size of a file backing a conventional zone is always equal to the zone +size. The size of a file backing a sequential zone indicates the amount of data +sequentially written to the file, that is, the size of the file directly +indicates the position of the write pointer of the zone. + +When resetting a sequential zone, its backing file size is truncated to zero. +Conversely, for a zone finish operation, the backing file is truncated to the +zone capacity. With this, a zloop zoned block device can be configured with a +larger capacity than the storage space available on the backing file system. Of +course, for such configuration, writing more data than the storage space +available on the backing file system will result in write errors. + +The zoned loop block device driver implements a complete zone transition state +machine. That is, zones can be empty, implicitly opened, explicitly opened, +closed or full. The current implementation does not support any limits on the +maximum number of open and active zones. + +No user tools are necessary to create and delete zloop devices. + +2) Creating a Zoned Device +-------------------------- + +Once the zloop module is loaded (or if zloop is compiled in the kernel), the +character device file /dev/zloop-control can be used to add a zloop device. +This is done by writing an "add" command directly to the /dev/zloop-control +device:: + + $ modprobe zloop + $ ls -l /dev/zloop* + crw-------. 1 root root 10, 123 Jan 6 19:18 /dev/zloop-control + + $ mkdir -p + $ echo "add [options]" > /dev/zloop-control + +The options available for the add command can be listed by reading the +/dev/zloop-control device:: + + $ cat /dev/zloop-control + add id=%d,capacity_mb=%u,zone_size_mb=%u,zone_capacity_mb=%u,conv_zones=%u,max_open_zones=%u,base_dir=%s,nr_queues=%u,queue_depth=%u,buffered_io,zone_append=%u,ordered_zone_append,discard_write_cache + remove id=%d + +In more details, the options that can be used with the "add" command are as +follows. + +=================== ========================================================= +id Device number (the X in /dev/zloopX). + Default: automatically assigned. +capacity_mb Device total capacity in MiB. A smaller last zone is not + supported, so a capacity value that is not a multiple of + the zone size is rounded down to the closest multiple of + the zone size. + Default: 16384 MiB (16 GiB). +zone_size_mb Device zone size in MiB. Default: 256 MiB. +zone_capacity_mb Device zone capacity (must always be equal to or lower + than the zone size. Default: zone size. +conv_zones Total number of conventioanl zones starting from + sector 0 + Default: 8 +max_open_zones Maximum number of open sequential write required zones + (0 for no limit). + Default: 0 +base_dir Path to the base directory where to create the directory + containing the zone files of the device. + Default=/var/local/zloop. + The device directory containing the zone files is always + named with the device ID. E.g. the default zone file + directory for /dev/zloop0 is /var/local/zloop/0. +nr_queues Number of I/O queues of the zoned block device. This + value is always capped by the number of online CPUs + Default: 1 +queue_depth Maximum I/O queue depth per I/O queue. + Default: 64 +buffered_io Do buffered IOs instead of direct IOs (default: false) +zone_append Enable or disable a zloop device native zone append + support. + Default: 1 (enabled). + If native zone append support is disabled, the block layer + will emulate this operation using regular write + operations. +ordered_zone_append Enable zloop mitigation of zone append reordering. + Default: disabled. + This is useful for testing file systems file data mapping + (extents), as when enabled, this can significantly reduce + the number of data extents needed to for a file data + mapping. +discard_write_cache Discard all data that was not explicitly persisted using a + flush operation when the device is removed by truncating + each zone file to the size recorded during the last flush + operation. This simulates power fail events where + uncommitted data is lost. +=================== ========================================================= + +3) Deleting a Zoned Device +-------------------------- + +Deleting an unused zoned loop block device is done by issuing the "remove" +command to /dev/zloop-control, specifying the ID of the device to remove:: + + $ echo "remove id=X" > /dev/zloop-control + +The remove command does not have any option. + +A zoned device that was removed can be re-added again without any change to the +state of the device zones: the device zones are restored to their last state +before the device was removed. Adding again a zoned device after it was removed +must always be done using the same configuration as when the device was first +added. If a zone configuration change is detected, an error will be returned and +the zoned device will not be created. + +To fully delete a zoned device, after executing the remove operation, the device +base directory containing the backing files of the device zones must be deleted. + +4) Example +---------- + +The following sequence of commands creates a 2GB zoned device with zones of 64 +MB and a zone capacity of 63 MB:: + + $ modprobe zloop + $ mkdir -p /var/local/zloop/0 + $ echo "add capacity_mb=2048,zone_size_mb=64,zone_capacity_mb=63" > /dev/zloop-control + +For the device created (/dev/zloop0), the zone backing files are all created +under the default base directory (/var/local/zloop):: + + $ ls -l /var/local/zloop/0 + total 0 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000000 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000001 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000002 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000003 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000004 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000005 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000006 + -rw-------. 1 root root 67108864 Jan 6 22:23 cnv-000007 + -rw-------. 1 root root 0 Jan 6 22:23 seq-000008 + -rw-------. 1 root root 0 Jan 6 22:23 seq-000009 + ... + +The zoned device created (/dev/zloop0) can then be used normally:: + + $ lsblk -z + NAME ZONED ZONE-SZ ZONE-NR ZONE-AMAX ZONE-OMAX ZONE-APP ZONE-WGRAN + zloop0 host-managed 64M 32 0 0 1M 4K + $ blkzone report /dev/zloop0 + start: 0x000000000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x000020000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x000040000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x000060000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x000080000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x0000a0000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x0000c0000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x0000e0000, len 0x020000, cap 0x020000, wptr 0x000000 reset:0 non-seq:0, zcond: 0(nw) [type: 1(CONVENTIONAL)] + start: 0x000100000, len 0x020000, cap 0x01f800, wptr 0x000000 reset:0 non-seq:0, zcond: 1(em) [type: 2(SEQ_WRITE_REQUIRED)] + start: 0x000120000, len 0x020000, cap 0x01f800, wptr 0x000000 reset:0 non-seq:0, zcond: 1(em) [type: 2(SEQ_WRITE_REQUIRED)] + ... + +Deleting this device is done using the command:: + + $ echo "remove id=0" > /dev/zloop-control + +The removed device can be re-added again using the same "add" command as when +the device was first created. To fully delete a zoned device, its backing files +should also be deleted after executing the remove command:: + + $ rm -r /var/local/zloop/0 diff --git a/Documentation/admin-guide/blockdev/zram.rst b/Documentation/admin-guide/blockdev/zram.rst new file mode 100644 index 000000000..148b7cf3b --- /dev/null +++ b/Documentation/admin-guide/blockdev/zram.rst @@ -0,0 +1,610 @@ +======================================== +zram: Compressed RAM-based block devices +======================================== + +Introduction +============ + +The zram module creates RAM-based block devices named /dev/zram +( = 0, 1, ...). Pages written to these disks are compressed and stored +in memory itself. These disks allow very fast I/O and compression provides +good amounts of memory savings. Some of the use cases include /tmp storage, +use as swap disks, various caches under /var and maybe many more. :) + +Statistics for individual zram devices are exported through sysfs nodes at +/sys/block/zram/ + +Usage +===== + +There are several ways to configure and manage zram device(-s): + +a) using zram and zram_control sysfs attributes +b) using zramctl utility, provided by util-linux (util-linux@vger.kernel.org). + +In this document we will describe only 'manual' zram configuration steps, +IOW, zram and zram_control sysfs attributes. + +In order to get a better idea about zramctl please consult util-linux +documentation, zramctl man-page or `zramctl --help`. Please be informed +that zram maintainers do not develop/maintain util-linux or zramctl, should +you have any questions please contact util-linux@vger.kernel.org + +Following shows a typical sequence of steps for using zram. + +WARNING +======= + +For the sake of simplicity we skip error checking parts in most of the +examples below. However, it is your sole responsibility to handle errors. + +zram sysfs attributes always return negative values in case of errors. +The list of possible return codes: + +======== ============================================================= +-EBUSY an attempt to modify an attribute that cannot be changed once + the device has been initialised. Please reset device first. +-ENOMEM zram was not able to allocate enough memory to fulfil your + needs. +-EINVAL invalid input has been provided. +-EAGAIN re-try operation later (e.g. when attempting to run recompress + and writeback simultaneously). +======== ============================================================= + +If you use 'echo', the returned value is set by the 'echo' utility, +and, in general case, something like:: + + echo foo > /sys/block/zram0/comp_algorithm + if [ $? -ne 0 ]; then + handle_error + fi + +should suffice. + +Load Module +=========== + +:: + + modprobe zram num_devices=4 + +This creates 4 devices: /dev/zram{0,1,2,3} + +num_devices parameter is optional and tells zram how many devices should be +pre-created. Default: 1. + +Select compression algorithm +============================ + +Using comp_algorithm device attribute one can see available and +currently selected (shown in square brackets) compression algorithms, +or change the selected compression algorithm (once the device is initialised +there is no way to change compression algorithm). + +Examples:: + + #show supported compression algorithms + cat /sys/block/zram0/comp_algorithm + lzo [lz4] + + #select lzo compression algorithm + echo lzo > /sys/block/zram0/comp_algorithm + +For the time being, the `comp_algorithm` content shows only compression +algorithms that are supported by zram. + +Set compression algorithm parameters: Optional +============================================== + +Compression algorithms may support specific parameters which can be +tweaked for particular dataset. ZRAM has an `algorithm_params` device +attribute which provides a per-algorithm params configuration. + +For example, several compression algorithms support `level` parameter. +In addition, certain compression algorithms support pre-trained dictionaries, +which significantly change algorithms' characteristics. In order to configure +compression algorithm to use external pre-trained dictionary, pass full +path to the `dict` along with other parameters:: + + #pass path to pre-trained zstd dictionary + echo "algo=zstd dict=/etc/dictionary" > /sys/block/zram0/algorithm_params + + #pass path to pre-trained zstd dictionary and compression level + echo "algo=zstd level=8 dict=/etc/dictionary" > \ + /sys/block/zram0/algorithm_params + + #same, but using algorithm priority + echo "algo=zstd priority=1" > /sys/block/zram0/recomp_algorithm + echo "priority=1 dict=/etc/dictionary" > \ + /sys/block/zram0/algorithm_params + +Each write to `algorithm_params` replaces the entire set of parameters of +the corresponding algorithm, parameters that are not listed in the write +are reset to their default values. Configure all of the parameters of an +algorithm in one write:: + + #WRONG: the second write resets level back to its default value + echo "algo=zstd level=8" > /sys/block/zram0/algorithm_params + echo "algo=zstd dict=/etc/dictionary" > /sys/block/zram0/algorithm_params + + #RIGHT + echo "algo=zstd level=8 dict=/etc/dictionary" > \ + /sys/block/zram0/algorithm_params + +Select the compression algorithm before configuring its parameters. The +parameters of one algorithm are not necessarily valid for another one, so +changing the algorithm of a particular priority resets that priority's +parameters:: + + #WRONG: comp_algorithm write resets the previously configured level + echo "level=8" > /sys/block/zram0/algorithm_params + echo zstd > /sys/block/zram0/comp_algorithm + + #RIGHT + echo zstd > /sys/block/zram0/comp_algorithm + echo "algo=zstd level=8" > /sys/block/zram0/algorithm_params + +Parameters are algorithm specific: not all algorithms support pre-trained +dictionaries, not all algorithms support `level`. Furthermore, for certain +algorithms `level` controls the compression level (the higher the value the +better the compression ratio, it even can take negatives values for some +algorithms), for other algorithms `level` is acceleration level (the higher +the value the lower the compression ratio). + +Parameters are handed over to the compression algorithm when the device is +initialised, hence invalid parameters (or parameters that the selected +algorithm does not support) are reported by the `disksize` write, and not +by the `algorithm_params` write that has configured them. + +Set Disksize +============ + +Set disk size by writing the value to sysfs node 'disksize'. +The value can be either in bytes or you can use mem suffixes. +Examples:: + + # Initialize /dev/zram0 with 50MB disksize + echo $((50*1024*1024)) > /sys/block/zram0/disksize + + # Using mem suffixes + echo 256K > /sys/block/zram0/disksize + echo 512M > /sys/block/zram0/disksize + echo 1G > /sys/block/zram0/disksize + +Note: +There is little point creating a zram of greater than twice the size of memory +since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the +size of the disk when not in use so a huge zram is wasteful. + +Set memory limit: Optional +========================== + +Set memory limit by writing the value to sysfs node 'mem_limit'. +The value can be either in bytes or you can use mem suffixes. +In addition, you could change the value in runtime. +Examples:: + + # limit /dev/zram0 with 50MB memory + echo $((50*1024*1024)) > /sys/block/zram0/mem_limit + + # Using mem suffixes + echo 256K > /sys/block/zram0/mem_limit + echo 512M > /sys/block/zram0/mem_limit + echo 1G > /sys/block/zram0/mem_limit + + # To disable memory limit + echo 0 > /sys/block/zram0/mem_limit + +Activate +======== + +:: + + mkswap /dev/zram0 + swapon /dev/zram0 + + mkfs.ext4 /dev/zram1 + mount /dev/zram1 /tmp + +Add/remove zram devices +======================= + +zram provides a control interface, which enables dynamic (on-demand) device +addition and removal. + +In order to add a new /dev/zramX device, perform a read operation on the hot_add +attribute. This will return either the new device's device id (meaning that you +can use /dev/zram) or an error code. + +Example:: + + cat /sys/class/zram-control/hot_add + 1 + +To remove the existing /dev/zramX device (where X is a device id) +execute:: + + echo X > /sys/class/zram-control/hot_remove + +Stats +===== + +Per-device statistics are exported as various nodes under /sys/block/zram/ + +A brief description of exported device attributes follows. For more details +please read Documentation/ABI/testing/sysfs-block-zram. + +====================== ====== =============================================== +Name access description +====================== ====== =============================================== +disksize RW show and set the device's disk size +initstate RO shows the initialization state of the device +reset WO trigger device reset +mem_used_max WO reset the `mem_used_max` counter (see later) +mem_limit WO specifies the maximum amount of memory ZRAM can + use to store the compressed data +writeback_limit WO specifies the maximum amount of write IO zram + can write out to backing device as 4KB unit +writeback_limit_enable RW show and set writeback_limit feature +writeback_batch_size RW show and set maximum number of in-flight + writeback operations +compressed_writeback RW show and set compressed writeback feature +comp_algorithm RW show and change the compression algorithm +algorithm_params WO setup compression algorithm parameters +compact WO trigger memory compaction +debug_stat RO this file is used for zram debugging purposes +backing_dev RW set up backend storage for zram to write out +idle WO mark allocated slot as idle +====================== ====== =============================================== + +User space is advised to use the following files to read the device statistics. + +File /sys/block/zram/stat + +Represents block layer statistics. Read Documentation/block/stat.rst for +details. + +File /sys/block/zram/io_stat + +The stat file represents device's I/O statistics not accounted by block +layer and, thus, not available in zram/stat file. It consists of a +single line of text and contains the following stats separated by +whitespace: + + ============= ============================================================= + failed_reads The number of failed reads + failed_writes The number of failed writes + invalid_io The number of non-page-size-aligned I/O requests + notify_free Depending on device usage scenario it may account + + a) the number of pages freed because of swap slot free + notifications + b) the number of pages freed because of + REQ_OP_DISCARD requests sent by bio. The former ones are + sent to a swap block device when a swap slot is freed, + which implies that this disk is being used as a swap disk. + + The latter ones are sent by filesystem mounted with + discard option, whenever some data blocks are getting + discarded. + ============= ============================================================= + +File /sys/block/zram/mm_stat + +The mm_stat file represents the device's mm statistics. It consists of a single +line of text and contains the following stats separated by whitespace: + + ================ ============================================================= + orig_data_size uncompressed size of data stored in this disk. + Unit: bytes + compr_data_size compressed size of data stored in this disk + mem_used_total the amount of memory allocated for this disk. This + includes allocator fragmentation and metadata overhead, + allocated for this disk. So, allocator space efficiency + can be calculated using compr_data_size and this statistic. + Unit: bytes + mem_limit the maximum amount of memory ZRAM can use to store + the compressed data + mem_used_max the maximum amount of memory zram has consumed to + store the data + same_pages the number of same element filled pages written to this disk. + No memory is allocated for such pages. + pages_compacted the number of pages freed during compaction + huge_pages the number of incompressible pages + huge_pages_since the number of incompressible pages since zram set up + ================ ============================================================= + +File /sys/block/zram/bd_stat + +The bd_stat file represents a device's backing device statistics. It consists of +a single line of text and contains the following stats separated by whitespace: + + ============== ============================================================= + bd_count size of data written in backing device. + Unit: 4K bytes + bd_reads the number of reads from backing device + Unit: 4K bytes + bd_writes the number of writes to backing device + Unit: 4K bytes + ============== ============================================================= + +Deactivate +========== + +:: + + swapoff /dev/zram0 + umount /dev/zram1 + +Reset +===== + + Write any positive value to 'reset' sysfs node:: + + echo 1 > /sys/block/zram0/reset + echo 1 > /sys/block/zram1/reset + + This frees all the memory allocated for the given device and + resets the disksize to zero. You must set the disksize again + before reusing the device. + +Optional Feature +================ + +IDLE pages tracking +------------------- + +zram has built-in support for idle pages tracking (that is, allocated but +not used pages). This feature is useful for e.g. zram writeback and +recompression. In order to mark pages as idle, execute the following command:: + + echo all > /sys/block/zramX/idle + +This will mark all allocated zram pages as idle. The idle mark will be +removed only when the page (block) is accessed (e.g. overwritten or freed). +Additionally, when CONFIG_ZRAM_TRACK_ENTRY_ACTIME is enabled, pages can be +marked as idle based on how many seconds have passed since the last access to +a particular zram page:: + + echo 86400 > /sys/block/zramX/idle + +In this example, all pages which haven't been accessed in more than 86400 +seconds (one day) will be marked idle. + +writeback +--------- + +With CONFIG_ZRAM_WRITEBACK, zram can write idle/incompressible page +to backing storage rather than keeping it in memory. +To use the feature, admin should set up backing device via:: + + echo /dev/sda5 > /sys/block/zramX/backing_dev + +before disksize setting. It supports only partitions at this moment. +If admin wants to use incompressible page writeback, they could do it via:: + + echo huge > /sys/block/zramX/writeback + +Admin can request writeback of idle pages at right timing via:: + + echo idle > /sys/block/zramX/writeback + +With the command, zram will writeback idle pages from memory to the storage. + +Additionally, if a user choose to writeback only huge and idle pages +this can be accomplished with:: + + echo huge_idle > /sys/block/zramX/writeback + +If a user chooses to writeback only incompressible pages (pages that none of +algorithms can compress) this can be accomplished with:: + + echo incompressible > /sys/block/zramX/writeback + +If an admin wants to write a specific page in zram device to the backing device, +they could write a page index into the interface:: + + echo "page_index=1251" > /sys/block/zramX/writeback + +In Linux 6.16 this interface underwent some rework. First, the interface +now supports `key=value` format for all of its parameters (`type=huge_idle`, +etc.) Second, the support for `page_indexes` was introduced, which specify +`LOW-HIGH` range (or ranges) of pages to be written-back. This reduces the +number of syscalls, but more importantly this enables optimal post-processing +target selection strategy. Usage example:: + + echo "type=idle" > /sys/block/zramX/writeback + echo "page_indexes=1-100 page_indexes=200-300" > \ + /sys/block/zramX/writeback + +We also now permit multiple page_index params per call and a mix of +single pages and page ranges:: + + echo page_index=42 page_index=99 page_indexes=100-200 \ + page_indexes=500-700 > /sys/block/zramX/writeback + +If there are lots of write IO with flash device, potentially, it has +flash wearout problem so that admin needs to design write limitation +to guarantee storage health for entire product life. + +To overcome the concern, zram supports "writeback_limit" feature. +The "writeback_limit_enable"'s default value is 0 so that it doesn't limit +any writeback. IOW, if admin wants to apply writeback budget, they should +enable writeback_limit_enable via:: + + $ echo 1 > /sys/block/zramX/writeback_limit_enable + +Once writeback_limit_enable is set, zram doesn't allow any writeback +until admin sets the budget via /sys/block/zramX/writeback_limit. + +(If admin doesn't enable writeback_limit_enable, writeback_limit's value +assigned via /sys/block/zramX/writeback_limit is meaningless.) + +If admin wants to limit writeback as per-day 400M, they could do it +like below:: + + $ MB_SHIFT=20 + $ 4K_SHIFT=12 + $ echo $((400<>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit. + $ echo 1 > /sys/block/zram0/writeback_limit_enable + +If admins want to allow further write again once the budget is exhausted, +they could do it like below:: + + $ echo $((400<>4K_SHIFT)) > \ + /sys/block/zram0/writeback_limit + +If an admin wants to see the remaining writeback budget since last set:: + + $ cat /sys/block/zramX/writeback_limit + +If an admin wants to disable writeback limit, they could do:: + + $ echo 0 > /sys/block/zramX/writeback_limit_enable + +The writeback_limit count will reset whenever you reset zram (e.g., +system reboot, echo 1 > /sys/block/zramX/reset) so keeping how many of +writeback happened until you reset the zram to allocate extra writeback +budget in next setting is user's job. + +By default zram stores written back pages in decompressed (raw) form, which +means that writeback operation involves decompression of the page before +writing it to the backing device. This behavior can be changed by enabling +`compressed_writeback` feature, which causes zram to write compressed pages +to the backing device, thus avoiding decompression overhead. To enable +this feature, execute:: + + $ echo yes > /sys/block/zramX/compressed_writeback + +Note that this feature should be configured before the `zramX` device is +initialized. + +Depending on backing device storage type, writeback operation may benefit +from a higher number of in-flight write requests (batched writes). The +number of maximum in-flight writeback operations can be configured via +`writeback_batch_size` attribute. To change the default value (which is 32), +execute:: + + $ echo 64 > /sys/block/zramX/writeback_batch_size + +If admin wants to measure writeback count in a certain period, they could +know it via /sys/block/zram0/bd_stat's 3rd column. + +recompression +------------- + +With `CONFIG_ZRAM_MULTI_COMP`, zram can recompress pages using alternative +(secondary) compression algorithms. The basic idea is that alternative +compression algorithm can provide better compression ratio at a price of +(potentially) slower compression/decompression speeds. Alternative compression +algorithm can, for example, be more successful compressing huge pages (those +that default algorithm failed to compress). Another application is idle pages +recompression - pages that are cold and sit in the memory can be recompressed +using more effective algorithm and, hence, reduce zsmalloc memory usage. + +With `CONFIG_ZRAM_MULTI_COMP`, zram supports up to 4 compression algorithms: +one primary and up to 3 secondary ones. Primary zram compressor is explained +in "3) Select compression algorithm", secondary algorithms are configured +using recomp_algorithm device attribute. + +Example::: + + #show supported recompression algorithms + cat /sys/block/zramX/recomp_algorithm + #1: lzo lzo-rle lz4 lz4hc [zstd] + #2: lzo lzo-rle lz4 [lz4hc] zstd + +Alternative compression algorithms are sorted by priority. In the example +above, zstd is used as the first alternative algorithm, which has priority +of 1, while lz4hc is configured as a compression algorithm with priority 2. +Alternative compression algorithm's priority is provided during algorithms +configuration::: + + #select zstd recompression algorithm, priority 1 + echo "algo=zstd priority=1" > /sys/block/zramX/recomp_algorithm + + #select deflate recompression algorithm, priority 2 + echo "algo=deflate priority=2" > /sys/block/zramX/recomp_algorithm + +Another device attribute that `CONFIG_ZRAM_MULTI_COMP` enables is `recompress`, +which controls recompression. + +Examples::: + + #IDLE pages recompression is activated by `idle` mode + echo "type=idle priority=1" > /sys/block/zramX/recompress + + #HUGE pages recompression is activated by `huge` mode + echo "type=huge priority=2" > /sys/block/zram0/recompress + + #HUGE_IDLE pages recompression is activated by `huge_idle` mode + echo "type=huge_idle priority=1" > /sys/block/zramX/recompress + +The number of idle pages can be significant, so user-space can pass a size +threshold (in bytes) to the recompress knob: zram will recompress only pages +of equal or greater size::: + + #recompress all pages larger than 3000 bytes + echo "threshold=3000 priority=1" > /sys/block/zramX/recompress + + #recompress idle pages larger than 2000 bytes + echo "type=idle threshold=2000 priority=1" > \ + /sys/block/zramX/recompress + +It is also possible to limit the number of pages zram re-compression will +attempt to recompress::: + + echo "type=huge_idle priority=1 max_pages=42" > \ + /sys/block/zramX/recompress + +It is advised to always specify `priority` parameter. While it is also +possible to specify `algo` parameter, so that `zram` will use algorithm's +name to determine the priority, it is not recommended, since it can lead to +unexpected results when the same algorithm is configured with different +priorities (e.g. different parameters). `priority` is the only way to +guarantee that the expected algorithm will be used. + +memory tracking +=============== + +With CONFIG_ZRAM_MEMORY_TRACKING, user can know information of the +zram block. It could be useful to catch cold or incompressible +pages of the process with*pagemap. + +If you enable the feature, you could see block state via +/sys/kernel/debug/zram/zram0/block_state". The output is as follows:: + + 300 75.033841 .wh... + 301 63.806904 s..... + 302 63.806919 ..hi.. + 303 62.801919 ....r. + 304 146.781902 ..hi.n + +First column + zram's block index. +Second column + access time since the system was booted +Third column + state of the block: + + s: + same page + w: + written page to backing store + h: + huge page + i: + idle page + r: + recompressed page (secondary compression algorithm) + n: + none (including secondary) of algorithms could compress it + +First line of above example says 300th block is accessed at 75.033841sec +and the block's state is huge so it is written back to the backing +storage. It's a debugging feature so anyone shouldn't rely on it to work +properly. + +Nitin Gupta +ngupta@vflare.org -- cgit v1.3.1