diff options
294 files changed, 6382 insertions, 1786 deletions
@@ -159,6 +159,7 @@ Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com> Praveen BP <praveenbp@ti.com> +Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> Qais Yousef <qsyousef@gmail.com> <qais.yousef@imgtec.com> Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net> Oleksij Rempel <linux@rempel-privat.de> <external.Oleksij.Rempel@de.bosch.com> diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern index fb3d1e03b881..1e5d172e0646 100644 --- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern +++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern @@ -37,8 +37,8 @@ Description: 0-| / \/ \/ +---0----1----2----3----4----5----6------------> time (s) - 2. To make the LED go instantly from one brigntess value to another, - we should use use zero-time lengths (the brightness must be same as + 2. To make the LED go instantly from one brightness value to another, + we should use zero-time lengths (the brightness must be same as the previous tuple's). So the format should be: "brightness_1 duration_1 brightness_1 0 brightness_2 duration_2 brightness_2 0 ...". For example: diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt index f5e0f82fd503..58c4256d37a3 100644 --- a/Documentation/devicetree/bindings/arm/shmobile.txt +++ b/Documentation/devicetree/bindings/arm/shmobile.txt @@ -27,7 +27,7 @@ SoCs: compatible = "renesas,r8a77470" - RZ/G2M (R8A774A1) compatible = "renesas,r8a774a1" - - RZ/G2E (RA8774C0) + - RZ/G2E (R8A774C0) compatible = "renesas,r8a774c0" - R-Car M1A (R8A77781) compatible = "renesas,r8a7778" diff --git a/Documentation/devicetree/bindings/i2c/i2c-omap.txt b/Documentation/devicetree/bindings/i2c/i2c-omap.txt index 7e49839d4124..4b90ba9f31b7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-omap.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-omap.txt @@ -1,8 +1,12 @@ I2C for OMAP platforms Required properties : -- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c" - or "ti,omap4-i2c" +- compatible : Must be + "ti,omap2420-i2c" for OMAP2420 SoCs + "ti,omap2430-i2c" for OMAP2430 SoCs + "ti,omap3-i2c" for OMAP3 SoCs + "ti,omap4-i2c" for OMAP4+ SoCs + "ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs - ti,hwmods : Must be "i2c<n>", n being the instance number (1-based) - #address-cells = <1>; - #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/timer/csky,gx6605s-timer.txt b/Documentation/devicetree/bindings/timer/csky,gx6605s-timer.txt new file mode 100644 index 000000000000..6b04344f4bea --- /dev/null +++ b/Documentation/devicetree/bindings/timer/csky,gx6605s-timer.txt @@ -0,0 +1,42 @@ +================= +gx6605s SOC Timer +================= + +The timer is used in gx6605s soc as system timer and the driver +contain clk event and clk source. + +============================== +timer node bindings definition +============================== + + Description: Describes gx6605s SOC timer + + PROPERTIES + + - compatible + Usage: required + Value type: <string> + Definition: must be "csky,gx6605s-timer" + - reg + Usage: required + Value type: <u32 u32> + Definition: <phyaddr size> in soc from cpu view + - clocks + Usage: required + Value type: phandle + clock specifier cells + Definition: must be input clk node + - interrupt + Usage: required + Value type: <u32> + Definition: must be timer irq num defined by soc + +Examples: +--------- + + timer0: timer@20a000 { + compatible = "csky,gx6605s-timer"; + reg = <0x0020a000 0x400>; + clocks = <&dummy_apb_clk>; + interrupts = <10>; + interrupt-parent = <&intc>; + }; diff --git a/Documentation/devicetree/bindings/timer/csky,mptimer.txt b/Documentation/devicetree/bindings/timer/csky,mptimer.txt new file mode 100644 index 000000000000..15cfec08fbb8 --- /dev/null +++ b/Documentation/devicetree/bindings/timer/csky,mptimer.txt @@ -0,0 +1,42 @@ +============================ +C-SKY Multi-processors Timer +============================ + +C-SKY multi-processors timer is designed for C-SKY SMP system and the +regs is accessed by cpu co-processor 4 registers with mtcr/mfcr. + + - PTIM_CTLR "cr<0, 14>" Control reg to start reset timer. + - PTIM_TSR "cr<1, 14>" Interrupt cleanup status reg. + - PTIM_CCVR "cr<3, 14>" Current counter value reg. + - PTIM_LVR "cr<6, 14>" Window value reg to triger next event. + +============================== +timer node bindings definition +============================== + + Description: Describes SMP timer + + PROPERTIES + + - compatible + Usage: required + Value type: <string> + Definition: must be "csky,mptimer" + - clocks + Usage: required + Value type: <node> + Definition: must be input clk node + - interrupts + Usage: required + Value type: <u32> + Definition: must be timer irq num defined by soc + +Examples: +--------- + + timer: timer { + compatible = "csky,mptimer"; + clocks = <&dummy_apb_clk>; + interrupts = <16>; + interrupt-parent = <&intc>; + }; diff --git a/Documentation/filesystems/ubifs-authentication.md b/Documentation/filesystems/ubifs-authentication.md new file mode 100644 index 000000000000..028b3e2e25f9 --- /dev/null +++ b/Documentation/filesystems/ubifs-authentication.md @@ -0,0 +1,426 @@ +% UBIFS Authentication +% sigma star gmbh +% 2018 + +# Introduction + +UBIFS utilizes the fscrypt framework to provide confidentiality for file +contents and file names. This prevents attacks where an attacker is able to +read contents of the filesystem on a single point in time. A classic example +is a lost smartphone where the attacker is unable to read personal data stored +on the device without the filesystem decryption key. + +At the current state, UBIFS encryption however does not prevent attacks where +the attacker is able to modify the filesystem contents and the user uses the +device afterwards. In such a scenario an attacker can modify filesystem +contents arbitrarily without the user noticing. One example is to modify a +binary to perform a malicious action when executed [DMC-CBC-ATTACK]. Since +most of the filesystem metadata of UBIFS is stored in plain, this makes it +fairly easy to swap files and replace their contents. + +Other full disk encryption systems like dm-crypt cover all filesystem metadata, +which makes such kinds of attacks more complicated, but not impossible. +Especially, if the attacker is given access to the device multiple points in +time. For dm-crypt and other filesystems that build upon the Linux block IO +layer, the dm-integrity or dm-verity subsystems [DM-INTEGRITY, DM-VERITY] +can be used to get full data authentication at the block layer. +These can also be combined with dm-crypt [CRYPTSETUP2]. + +This document describes an approach to get file contents _and_ full metadata +authentication for UBIFS. Since UBIFS uses fscrypt for file contents and file +name encryption, the authentication system could be tied into fscrypt such that +existing features like key derivation can be utilized. It should however also +be possible to use UBIFS authentication without using encryption. + + +## MTD, UBI & UBIFS + +On Linux, the MTD (Memory Technology Devices) subsystem provides a uniform +interface to access raw flash devices. One of the more prominent subsystems that +work on top of MTD is UBI (Unsorted Block Images). It provides volume management +for flash devices and is thus somewhat similar to LVM for block devices. In +addition, it deals with flash-specific wear-leveling and transparent I/O error +handling. UBI offers logical erase blocks (LEBs) to the layers on top of it +and maps them transparently to physical erase blocks (PEBs) on the flash. + +UBIFS is a filesystem for raw flash which operates on top of UBI. Thus, wear +leveling and some flash specifics are left to UBI, while UBIFS focuses on +scalability, performance and recoverability. + + + + +------------+ +*******+ +-----------+ +-----+ + | | * UBIFS * | UBI-BLOCK | | ... | + | JFFS/JFFS2 | +*******+ +-----------+ +-----+ + | | +-----------------------------+ +-----------+ +-----+ + | | | UBI | | MTD-BLOCK | | ... | + +------------+ +-----------------------------+ +-----------+ +-----+ + +------------------------------------------------------------------+ + | MEMORY TECHNOLOGY DEVICES (MTD) | + +------------------------------------------------------------------+ + +-----------------------------+ +--------------------------+ +-----+ + | NAND DRIVERS | | NOR DRIVERS | | ... | + +-----------------------------+ +--------------------------+ +-----+ + + Figure 1: Linux kernel subsystems for dealing with raw flash + + + +Internally, UBIFS maintains multiple data structures which are persisted on +the flash: + +- *Index*: an on-flash B+ tree where the leaf nodes contain filesystem data +- *Journal*: an additional data structure to collect FS changes before updating + the on-flash index and reduce flash wear. +- *Tree Node Cache (TNC)*: an in-memory B+ tree that reflects the current FS + state to avoid frequent flash reads. It is basically the in-memory + representation of the index, but contains additional attributes. +- *LEB property tree (LPT)*: an on-flash B+ tree for free space accounting per + UBI LEB. + +In the remainder of this section we will cover the on-flash UBIFS data +structures in more detail. The TNC is of less importance here since it is never +persisted onto the flash directly. More details on UBIFS can also be found in +[UBIFS-WP]. + + +### UBIFS Index & Tree Node Cache + +Basic on-flash UBIFS entities are called *nodes*. UBIFS knows different types +of nodes. Eg. data nodes (`struct ubifs_data_node`) which store chunks of file +contents or inode nodes (`struct ubifs_ino_node`) which represent VFS inodes. +Almost all types of nodes share a common header (`ubifs_ch`) containing basic +information like node type, node length, a sequence number, etc. (see +`fs/ubifs/ubifs-media.h`in kernel source). Exceptions are entries of the LPT +and some less important node types like padding nodes which are used to pad +unusable content at the end of LEBs. + +To avoid re-writing the whole B+ tree on every single change, it is implemented +as *wandering tree*, where only the changed nodes are re-written and previous +versions of them are obsoleted without erasing them right away. As a result, +the index is not stored in a single place on the flash, but *wanders* around +and there are obsolete parts on the flash as long as the LEB containing them is +not reused by UBIFS. To find the most recent version of the index, UBIFS stores +a special node called *master node* into UBI LEB 1 which always points to the +most recent root node of the UBIFS index. For recoverability, the master node +is additionally duplicated to LEB 2. Mounting UBIFS is thus a simple read of +LEB 1 and 2 to get the current master node and from there get the location of +the most recent on-flash index. + +The TNC is the in-memory representation of the on-flash index. It contains some +additional runtime attributes per node which are not persisted. One of these is +a dirty-flag which marks nodes that have to be persisted the next time the +index is written onto the flash. The TNC acts as a write-back cache and all +modifications of the on-flash index are done through the TNC. Like other caches, +the TNC does not have to mirror the full index into memory, but reads parts of +it from flash whenever needed. A *commit* is the UBIFS operation of updating the +on-flash filesystem structures like the index. On every commit, the TNC nodes +marked as dirty are written to the flash to update the persisted index. + + +### Journal + +To avoid wearing out the flash, the index is only persisted (*commited*) when +certain conditions are met (eg. `fsync(2)`). The journal is used to record +any changes (in form of inode nodes, data nodes etc.) between commits +of the index. During mount, the journal is read from the flash and replayed +onto the TNC (which will be created on-demand from the on-flash index). + +UBIFS reserves a bunch of LEBs just for the journal called *log area*. The +amount of log area LEBs is configured on filesystem creation (using +`mkfs.ubifs`) and stored in the superblock node. The log area contains only +two types of nodes: *reference nodes* and *commit start nodes*. A commit start +node is written whenever an index commit is performed. Reference nodes are +written on every journal update. Each reference node points to the position of +other nodes (inode nodes, data nodes etc.) on the flash that are part of this +journal entry. These nodes are called *buds* and describe the actual filesystem +changes including their data. + +The log area is maintained as a ring. Whenever the journal is almost full, +a commit is initiated. This also writes a commit start node so that during +mount, UBIFS will seek for the most recent commit start node and just replay +every reference node after that. Every reference node before the commit start +node will be ignored as they are already part of the on-flash index. + +When writing a journal entry, UBIFS first ensures that enough space is +available to write the reference node and buds part of this entry. Then, the +reference node is written and afterwards the buds describing the file changes. +On replay, UBIFS will record every reference node and inspect the location of +the referenced LEBs to discover the buds. If these are corrupt or missing, +UBIFS will attempt to recover them by re-reading the LEB. This is however only +done for the last referenced LEB of the journal. Only this can become corrupt +because of a power cut. If the recovery fails, UBIFS will not mount. An error +for every other LEB will directly cause UBIFS to fail the mount operation. + + + | ---- LOG AREA ---- | ---------- MAIN AREA ------------ | + + -----+------+-----+--------+---- ------+-----+-----+--------------- + \ | | | | / / | | | \ + / CS | REF | REF | | \ \ DENT | INO | INO | / + \ | | | | / / | | | \ + ----+------+-----+--------+--- -------+-----+-----+---------------- + | | ^ ^ + | | | | + +------------------------+ | + | | + +-------------------------------+ + + + Figure 2: UBIFS flash layout of log area with commit start nodes + (CS) and reference nodes (REF) pointing to main area + containing their buds + + +### LEB Property Tree/Table + +The LEB property tree is used to store per-LEB information. This includes the +LEB type and amount of free and *dirty* (old, obsolete content) space [1] on +the LEB. The type is important, because UBIFS never mixes index nodes with data +nodes on a single LEB and thus each LEB has a specific purpose. This again is +useful for free space calculations. See [UBIFS-WP] for more details. + +The LEB property tree again is a B+ tree, but it is much smaller than the +index. Due to its smaller size it is always written as one chunk on every +commit. Thus, saving the LPT is an atomic operation. + + +[1] Since LEBs can only be appended and never overwritten, there is a +difference between free space ie. the remaining space left on the LEB to be +written to without erasing it and previously written content that is obsolete +but can't be overwritten without erasing the full LEB. + + +# UBIFS Authentication + +This chapter introduces UBIFS authentication which enables UBIFS to verify +the authenticity and integrity of metadata and file contents stored on flash. + + +## Threat Model + +UBIFS authentication enables detection of offline data modification. While it +does not prevent it, it enables (trusted) code to check the integrity and +authenticity of on-flash file contents and filesystem metadata. This covers +attacks where file contents are swapped. + +UBIFS authentication will not protect against rollback of full flash contents. +Ie. an attacker can still dump the flash and restore it at a later time without +detection. It will also not protect against partial rollback of individual +index commits. That means that an attacker is able to partially undo changes. +This is possible because UBIFS does not immediately overwrites obsolete +versions of the index tree or the journal, but instead marks them as obsolete +and garbage collection erases them at a later time. An attacker can use this by +erasing parts of the current tree and restoring old versions that are still on +the flash and have not yet been erased. This is possible, because every commit +will always write a new version of the index root node and the master node +without overwriting the previous version. This is further helped by the +wear-leveling operations of UBI which copies contents from one physical +eraseblock to another and does not atomically erase the first eraseblock. + +UBIFS authentication does not cover attacks where an attacker is able to +execute code on the device after the authentication key was provided. +Additional measures like secure boot and trusted boot have to be taken to +ensure that only trusted code is executed on a device. + + +## Authentication + +To be able to fully trust data read from flash, all UBIFS data structures +stored on flash are authenticated. That is: + +- The index which includes file contents, file metadata like extended + attributes, file length etc. +- The journal which also contains file contents and metadata by recording changes + to the filesystem +- The LPT which stores UBI LEB metadata which UBIFS uses for free space accounting + + +### Index Authentication + +Through UBIFS' concept of a wandering tree, it already takes care of only +updating and persisting changed parts from leaf node up to the root node +of the full B+ tree. This enables us to augment the index nodes of the tree +with a hash over each node's child nodes. As a result, the index basically also +a Merkle tree. Since the leaf nodes of the index contain the actual filesystem +data, the hashes of their parent index nodes thus cover all the file contents +and file metadata. When a file changes, the UBIFS index is updated accordingly +from the leaf nodes up to the root node including the master node. This process +can be hooked to recompute the hash only for each changed node at the same time. +Whenever a file is read, UBIFS can verify the hashes from each leaf node up to +the root node to ensure the node's integrity. + +To ensure the authenticity of the whole index, the UBIFS master node stores a +keyed hash (HMAC) over its own contents and a hash of the root node of the index +tree. As mentioned above, the master node is always written to the flash whenever +the index is persisted (ie. on index commit). + +Using this approach only UBIFS index nodes and the master node are changed to +include a hash. All other types of nodes will remain unchanged. This reduces +the storage overhead which is precious for users of UBIFS (ie. embedded +devices). + + + +---------------+ + | Master Node | + | (hash) | + +---------------+ + | + v + +-------------------+ + | Index Node #1 | + | | + | branch0 branchn | + | (hash) (hash) | + +-------------------+ + | ... | (fanout: 8) + | | + +-------+ +------+ + | | + v v + +-------------------+ +-------------------+ + | Index Node #2 | | Index Node #3 | + | | | | + | branch0 branchn | | branch0 branchn | + | (hash) (hash) | | (hash) (hash) | + +-------------------+ +-------------------+ + | ... | ... | + v v v + +-----------+ +----------+ +-----------+ + | Data Node | | INO Node | | DENT Node | + +-----------+ +----------+ +-----------+ + + + Figure 3: Coverage areas of index node hash and master node HMAC + + + +The most important part for robustness and power-cut safety is to atomically +persist the hash and file contents. Here the existing UBIFS logic for how +changed nodes are persisted is already designed for this purpose such that +UBIFS can safely recover if a power-cut occurs while persisting. Adding +hashes to index nodes does not change this since each hash will be persisted +atomically together with its respective node. + + +### Journal Authentication + +The journal is authenticated too. Since the journal is continuously written +it is necessary to also add authentication information frequently to the +journal so that in case of a powercut not too much data can't be authenticated. +This is done by creating a continuous hash beginning from the commit start node +over the previous reference nodes, the current reference node, and the bud +nodes. From time to time whenever it is suitable authentication nodes are added +between the bud nodes. This new node type contains a HMAC over the current state +of the hash chain. That way a journal can be authenticated up to the last +authentication node. The tail of the journal which may not have a authentication +node cannot be authenticated and is skipped during journal replay. + +We get this picture for journal authentication: + + ,,,,,,,, + ,......,........................................... + ,. CS , hash1.----. hash2.----. + ,. | , . |hmac . |hmac + ,. v , . v . v + ,.REF#0,-> bud -> bud -> bud.-> auth -> bud -> bud.-> auth ... + ,..|...,........................................... + , | , + , | ,,,,,,,,,,,,,,, + . | hash3,----. + , | , |hmac + , v , v + , REF#1 -> bud -> bud,-> auth ... + ,,,|,,,,,,,,,,,,,,,,,, + v + REF#2 -> ... + | + V + ... + +Since the hash also includes the reference nodes an attacker cannot reorder or +skip any journal heads for replay. An attacker can only remove bud nodes or +reference nodes from the end of the journal, effectively rewinding the +filesystem at maximum back to the last commit. + +The location of the log area is stored in the master node. Since the master +node is authenticated with a HMAC as described above, it is not possible to +tamper with that without detection. The size of the log area is specified when +the filesystem is created using `mkfs.ubifs` and stored in the superblock node. +To avoid tampering with this and other values stored there, a HMAC is added to +the superblock struct. The superblock node is stored in LEB 0 and is only +modified on feature flag or similar changes, but never on file changes. + + +### LPT Authentication + +The location of the LPT root node on the flash is stored in the UBIFS master +node. Since the LPT is written and read atomically on every commit, there is +no need to authenticate individual nodes of the tree. It suffices to +protect the integrity of the full LPT by a simple hash stored in the master +node. Since the master node itself is authenticated, the LPTs authenticity can +be verified by verifying the authenticity of the master node and comparing the +LTP hash stored there with the hash computed from the read on-flash LPT. + + +## Key Management + +For simplicity, UBIFS authentication uses a single key to compute the HMACs +of superblock, master, commit start and reference nodes. This key has to be +available on creation of the filesystem (`mkfs.ubifs`) to authenticate the +superblock node. Further, it has to be available on mount of the filesystem +to verify authenticated nodes and generate new HMACs for changes. + +UBIFS authentication is intended to operate side-by-side with UBIFS encryption +(fscrypt) to provide confidentiality and authenticity. Since UBIFS encryption +has a different approach of encryption policies per directory, there can be +multiple fscrypt master keys and there might be folders without encryption. +UBIFS authentication on the other hand has an all-or-nothing approach in the +sense that it either authenticates everything of the filesystem or nothing. +Because of this and because UBIFS authentication should also be usable without +encryption, it does not share the same master key with fscrypt, but manages +a dedicated authentication key. + +The API for providing the authentication key has yet to be defined, but the +key can eg. be provided by userspace through a keyring similar to the way it +is currently done in fscrypt. It should however be noted that the current +fscrypt approach has shown its flaws and the userspace API will eventually +change [FSCRYPT-POLICY2]. + +Nevertheless, it will be possible for a user to provide a single passphrase +or key in userspace that covers UBIFS authentication and encryption. This can +be solved by the corresponding userspace tools which derive a second key for +authentication in addition to the derived fscrypt master key used for +encryption. + +To be able to check if the proper key is available on mount, the UBIFS +superblock node will additionally store a hash of the authentication key. This +approach is similar to the approach proposed for fscrypt encryption policy v2 +[FSCRYPT-POLICY2]. + + +# Future Extensions + +In certain cases where a vendor wants to provide an authenticated filesystem +image to customers, it should be possible to do so without sharing the secret +UBIFS authentication key. Instead, in addition the each HMAC a digital +signature could be stored where the vendor shares the public key alongside the +filesystem image. In case this filesystem has to be modified afterwards, +UBIFS can exchange all digital signatures with HMACs on first mount similar +to the way the IMA/EVM subsystem deals with such situations. The HMAC key +will then have to be provided beforehand in the normal way. + + +# References + +[CRYPTSETUP2] http://www.saout.de/pipermail/dm-crypt/2017-November/005745.html + +[DMC-CBC-ATTACK] http://www.jakoblell.com/blog/2013/12/22/practical-malleability-attack-against-cbc-encrypted-luks-partitions/ + +[DM-INTEGRITY] https://www.kernel.org/doc/Documentation/device-mapper/dm-integrity.txt + +[DM-VERITY] https://www.kernel.org/doc/Documentation/device-mapper/verity.txt + +[FSCRYPT-POLICY2] https://www.spinics.net/lists/linux-ext4/msg58710.html + +[UBIFS-WP] http://www.linux-mtd.infradead.org/doc/ubifs_whitepaper.pdf diff --git a/Documentation/filesystems/ubifs.txt b/Documentation/filesystems/ubifs.txt index a0a61d2f389f..acc80442a3bb 100644 --- a/Documentation/filesystems/ubifs.txt +++ b/Documentation/filesystems/ubifs.txt @@ -91,6 +91,13 @@ chk_data_crc do not skip checking CRCs on data nodes compr=none override default compressor and set it to "none" compr=lzo override default compressor and set it to "lzo" compr=zlib override default compressor and set it to "zlib" +auth_key= specify the key used for authenticating the filesystem. + Passing this option makes authentication mandatory. + The passed key must be present in the kernel keyring + and must be of type 'logon' +auth_hash_name= The hash algorithm used for authentication. Used for + both hashing and for creating HMACs. Typical values + include "sha256" or "sha512" Quick usage instructions diff --git a/Documentation/i2c/busses/i2c-nvidia-gpu b/Documentation/i2c/busses/i2c-nvidia-gpu new file mode 100644 index 000000000000..31884d2b2eb5 --- /dev/null +++ b/Documentation/i2c/busses/i2c-nvidia-gpu @@ -0,0 +1,18 @@ +Kernel driver i2c-nvidia-gpu + +Datasheet: not publicly available. + +Authors: + Ajay Gupta <ajayg@nvidia.com> + +Description +----------- + +i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing +and later GPUs and it is used to communicate with Type-C controller on GPUs. + +If your 'lspci -v' listing shows something like the following, + +01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1) + +then this driver should support the I2C controller of your GPU. diff --git a/MAINTAINERS b/MAINTAINERS index f4855974f325..0abecc528dac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6607,9 +6607,9 @@ F: arch/*/include/asm/suspend*.h HID CORE LAYER M: Jiri Kosina <jikos@kernel.org> -R: Benjamin Tissoires <benjamin.tissoires@redhat.com> +M: Benjamin Tissoires <benjamin.tissoires@redhat.com> L: linux-input@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: drivers/hid/ F: include/linux/hid* @@ -6861,6 +6861,13 @@ L: linux-acpi@vger.kernel.org S: Maintained F: drivers/i2c/i2c-core-acpi.c +I2C CONTROLLER DRIVER FOR NVIDIA GPU +M: Ajay Gupta <ajayg@nvidia.com> +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/i2c/busses/i2c-nvidia-gpu +F: drivers/i2c/busses/i2c-nvidia-gpu.c + I2C MUXES M: Peter Rosin <peda@axentia.se> L: linux-i2c@vger.kernel.org @@ -8367,7 +8374,7 @@ F: drivers/media/dvb-frontends/lgdt3305.* LIBATA PATA ARASAN COMPACT FLASH CONTROLLER M: Viresh Kumar <vireshk@kernel.org> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: include/linux/pata_arasan_cf_data.h F: drivers/ata/pata_arasan_cf.c @@ -8384,7 +8391,7 @@ F: drivers/ata/ata_generic.c LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS M: Linus Walleij <linus.walleij@linaro.org> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/pata_ftide010.c F: drivers/ata/sata_gemini.c @@ -8403,7 +8410,7 @@ F: include/linux/ahci_platform.h LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER M: Mikael Pettersson <mikpelinux@gmail.com> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/sata_promise.* @@ -10784,6 +10791,14 @@ L: linux-omap@vger.kernel.org S: Maintained F: arch/arm/mach-omap2/omap_hwmod.* +OMAP I2C DRIVER +M: Vignesh R <vigneshr@ti.com> +L: linux-omap@vger.kernel.org +L: linux-i2c@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/i2c-omap.txt +F: drivers/i2c/busses/i2c-omap.c + OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS) M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> L: linux-media@vger.kernel.org @@ -15436,9 +15451,9 @@ F: include/linux/usb/gadget* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina <jikos@kernel.org> -R: Benjamin Tissoires <benjamin.tissoires@redhat.com> +M: Benjamin Tissoires <benjamin.tissoires@redhat.com> L: linux-usb@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: Documentation/hid/hiddev.txt F: drivers/hid/usbhid/ @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 -PATCHLEVEL = 19 +PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = "People's Front" # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h index 6a8c53dec57e..b7c77bb1bfd2 100644 --- a/arch/alpha/include/asm/termios.h +++ b/arch/alpha/include/asm/termios.h @@ -73,9 +73,15 @@ }) #define user_termios_to_kernel_termios(k, u) \ - copy_from_user(k, u, sizeof(struct termios)) + copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios2)) + +#define user_termios_to_kernel_termios_1(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios_1(u, k) \ copy_to_user(u, k, sizeof(struct termios)) #endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 1e9121c9b3c7..971311605288 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -32,6 +32,11 @@ #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) +#define TCGETS2 _IOR('T', 42, struct termios2) +#define TCSETS2 _IOW('T', 43, struct termios2) +#define TCSETSW2 _IOW('T', 44, struct termios2) +#define TCSETSF2 _IOW('T', 45, struct termios2) + #define TIOCSWINSZ _IOW('t', 103, struct winsize) #define TIOCGWINSZ _IOR('t', 104, struct winsize) #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index de6c8360fbe3..4575ba34a0ea 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -26,6 +26,19 @@ struct termios { speed_t c_ospeed; /* output speed */ }; +/* Alpha has identical termios and termios2 */ + +struct termios2 { + tcflag_t c_iflag; /* input mode flags */ + tcflag_t c_oflag; /* output mode flags */ + tcflag_t c_cflag; /* control mode flags */ + tcflag_t c_lflag; /* local mode flags */ + cc_t c_cc[NCCS]; /* control characters */ + cc_t c_line; /* line discipline (== c_cc[19]) */ + speed_t c_ispeed; /* input speed */ + speed_t c_ospeed; /* output speed */ +}; + /* Alpha has matching termios and ktermios */ struct ktermios { @@ -152,6 +165,7 @@ struct ktermios { #define B3000000 00034 #define B3500000 00035 #define B4000000 00036 +#define BOTHER 00037 #define CSIZE 00001400 #define CS5 00000000 @@ -169,6 +183,9 @@ struct ktermios { #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define CIBAUD 07600000 +#define IBSHIFT 16 + /* c_lflag bits */ #define ISIG 0x00000080 #define ICANON 0x00000100 diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index b560ff88459b..5ff9a179c83c 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -55,7 +55,7 @@ }; chosen { - stdout-path = "&uart1:115200n8"; + stdout-path = "serial0:115200n8"; }; memory@70000000 { diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index ed9a980bce85..beefa1b2049d 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -740,7 +740,7 @@ i2c1: i2c@21a0000 { #address-cells = <1>; #size-cells = <0>; - compatible = "fs,imx6sll-i2c", "fsl,imx21-i2c"; + compatible = "fsl,imx6sll-i2c", "fsl,imx21-i2c"; reg = <0x021a0000 0x4000>; interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SLL_CLK_I2C1>; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index 53b3408b5fab..7d7d679945d2 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -117,7 +117,9 @@ regulator-name = "enet_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; + gpio = <&gpio2 6 GPIO_ACTIVE_LOW>; + regulator-boot-on; + regulator-always-on; }; reg_pcie_gpio: regulator-pcie-gpio { @@ -180,6 +182,7 @@ phy-supply = <®_enet_3v3>; phy-mode = "rgmii"; phy-handle = <ðphy1>; + phy-reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>; status = "okay"; mdio { @@ -373,6 +376,8 @@ MX6SX_PAD_RGMII1_RD3__ENET1_RX_DATA_3 0x3081 MX6SX_PAD_RGMII1_RX_CTL__ENET1_RX_EN 0x3081 MX6SX_PAD_ENET2_RX_CLK__ENET2_REF_CLK_25M 0x91 + /* phy reset */ + MX6SX_PAD_ENET2_CRS__GPIO2_IO_7 0x10b0 >; }; diff --git a/arch/arm/boot/dts/vf610m4-colibri.dts b/arch/arm/boot/dts/vf610m4-colibri.dts index 41ec66a96990..ca6249558760 100644 --- a/arch/arm/boot/dts/vf610m4-colibri.dts +++ b/arch/arm/boot/dts/vf610m4-colibri.dts @@ -50,8 +50,8 @@ compatible = "fsl,vf610m4"; chosen { - bootargs = "console=ttyLP2,115200 clk_ignore_unused init=/linuxrc rw"; - stdout-path = "&uart2"; + bootargs = "clk_ignore_unused init=/linuxrc rw"; + stdout-path = "serial2:115200"; }; memory@8c000000 { diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 1c7616815a86..63af6234c1b6 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y CONFIG_CGROUPS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EMBEDDED=y diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 92fd2c8a9af0..12659ce5c1f3 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -10,7 +10,7 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Hardware-wise, we have a two level page table structure, where the first diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6fe52819e014..339eb17c9808 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -112,7 +112,7 @@ ENTRY(cpu_v7_hvc_switch_mm) hvc #0 ldmfd sp!, {r0 - r3} b cpu_v7_switch_mm -ENDPROC(cpu_v7_smc_switch_mm) +ENDPROC(cpu_v7_hvc_switch_mm) #endif ENTRY(cpu_v7_iciallu_switch_mm) mov r3, #0 diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 8253a1a9e985..fef7351e9f67 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -139,6 +139,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -154,6 +155,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -169,6 +171,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index b5f2273caca4..a79c8d369e0b 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -652,7 +652,7 @@ clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac1 0x35>, <&dmac1 0x34>, <&dmac2 0x35>, <&dmac2 0x34>; - dma-names = "tx", "rx"; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; resets = <&cpg 518>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts index fe2e2c051cc9..5a7012be0d6a 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts @@ -15,7 +15,7 @@ aliases { serial0 = &scif0; - ethernet0 = &avb; + ethernet0 = &gether; }; chosen { @@ -97,23 +97,6 @@ }; }; -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - - phy-mode = "rgmii-id"; - phy-handle = <&phy0>; - renesas,no-ether-link; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio1>; - interrupts = <17 IRQ_TYPE_LEVEL_LOW>; - }; -}; - &canfd { pinctrl-0 = <&canfd0_pins>; pinctrl-names = "default"; @@ -139,6 +122,23 @@ clock-frequency = <32768>; }; +&gether { + pinctrl-0 = <&gether_pins>; + pinctrl-names = "default"; + + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + renesas,no-ether-link; + status = "okay"; + + phy0: ethernet-phy@0 { + rxc-skew-ps = <1500>; + reg = <0>; + interrupt-parent = <&gpio4>; + interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + }; +}; + &i2c0 { pinctrl-0 = <&i2c0_pins>; pinctrl-names = "default"; @@ -236,16 +236,17 @@ }; &pfc { - avb_pins: avb { - groups = "avb_mdio", "avb_rgmii"; - function = "avb"; - }; - canfd0_pins: canfd0 { groups = "canfd0_data_a"; function = "canfd0"; }; + gether_pins: gether { + groups = "gether_mdio_a", "gether_rgmii", + "gether_txcrefclk", "gether_txcrefclk_mega"; + function = "gether"; + }; + i2c0_pins: i2c0 { groups = "i2c0"; function = "i2c0"; diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 3e2091708b8e..6b0d4dff5012 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -24,6 +24,14 @@ #define KERNEL_DS UL(-1) #define USER_DS (TASK_SIZE_64 - 1) +/* + * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is + * no point in shifting all network buffers by 2 bytes just to make some IP + * header fields appear aligned in memory, potentially sacrificing some DMA + * performance on some platforms. + */ +#define NET_IP_ALIGN 0 + #ifndef __ASSEMBLY__ #ifdef __KERNEL__ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9d9582cac6c4..9b432d9fcada 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -483,8 +483,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma_phys_limit); - - memblock_allow_resize(); } void __init bootmem_init(void) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 394b8d554def..d1d6601b385d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -659,6 +659,8 @@ void __init paging_init(void) memblock_free(__pa_symbol(init_pg_dir), __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + + memblock_allow_resize(); } /* diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 6181e4134483..fe3ddd73a0cc 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -55,12 +55,12 @@ */ #ifdef CONFIG_SUN3 #define PTRS_PER_PTE 16 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 2048 #elif defined(CONFIG_COLDFIRE) #define PTRS_PER_PTE 512 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index f64ebb9c9a41..e14b6621c933 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -63,7 +63,7 @@ extern int mem_init_done; #include <asm-generic/4level-fixup.h> -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #ifdef __KERNEL__ #ifndef __ASSEMBLY__ diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 75108ec669eb..6c79e8a16a26 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port, void (*cvmx_override_ipd_port_setup) (int ipd_port); /* Port count per interface */ -static int interface_port_count[5]; +static int interface_port_count[9]; /** * Return the number of interfaces the chip has. Each interface diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index e6c9485cadcf..cb38461391cb 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, void *ret; ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); - if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { + if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { dma_cache_wback_inv((unsigned long) ret, size); ret = (void *)UNCAC_ADDR(ret); } diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h index d3e19a55cf53..9f52db930c00 100644 --- a/arch/nds32/include/asm/pgtable.h +++ b/arch/nds32/include/asm/pgtable.h @@ -4,7 +4,7 @@ #ifndef _ASMNDS32_PGTABLE_H #define _ASMNDS32_PGTABLE_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #include <asm-generic/4level-fixup.h> #include <asm-generic/sizes.h> diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index b941ac7d4e70..c7bb74e22436 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #if CONFIG_PGTABLE_LEVELS == 3 #define BITS_PER_PMD (PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY) #else -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define BITS_PER_PMD 0 #endif #define PTRS_PER_PMD (1UL << BITS_PER_PMD) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 0b33577932c3..e21053e5e0da 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) UTS_MACHINE := s390x -STACK_SIZE := $(if $(CONFIG_KASAN),32768,16384) +STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ export LD_BFD diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 593039620487..b1bdd15e3429 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -22,10 +22,10 @@ OBJCOPYFLAGS := OBJECTS := $(addprefix $(obj)/,$(obj-y)) LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) +$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE $(call if_changed,ld) -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load $(obj)/info.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -46,17 +46,17 @@ suffix-$(CONFIG_KERNEL_LZMA) := .lzma suffix-$(CONFIG_KERNEL_LZO) := .lzo suffix-$(CONFIG_KERNEL_XZ) := .xz -$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE $(call if_changed,gzip) -$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) -$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE $(call if_changed,lz4) -$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) -$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) -$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE $(call if_changed,xzkern) OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 259d1698ac50..c69cb04b7a59 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -64,6 +64,8 @@ CONFIG_NUMA=y CONFIG_PREEMPT=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -84,9 +86,11 @@ CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -161,8 +165,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -365,6 +367,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -461,6 +465,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -486,9 +491,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -615,7 +623,6 @@ CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 CONFIG_NOTIFIER_ERROR_INJECTION=m -CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y @@ -727,3 +734,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 37fd60c20e22..32f539dc9c19 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -65,6 +65,8 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,9 +84,11 @@ CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -159,8 +163,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -362,6 +364,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -458,6 +462,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -483,9 +488,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -666,3 +674,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 7cb6a52f727d..4d58a92b5d97 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -26,14 +26,23 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_NR_CPUS=256 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m CONFIG_OPROFILE=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -44,11 +53,7 @@ CONFIG_BLK_DEV_INTEGRITY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_NR_CPUS=256 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -60,9 +65,6 @@ CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -98,6 +100,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_VIRTIO_BLK=y CONFIG_SCSI=y +# CONFIG_SCSI_MQ_DEFAULT is not set CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -131,6 +134,7 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y # CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_AURORA is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set @@ -157,33 +161,6 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -CONFIG_UNUSED_SYMBOLS=y -CONFIG_DEBUG_SECTION_MISMATCH=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_PAGEALLOC=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_SG=y -CONFIG_DEBUG_NOTIFIERS=y -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -# CONFIG_RUNTIME_TESTING_MENU is not set -CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -193,6 +170,7 @@ CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_CMAC=m @@ -231,7 +209,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_ZCRYPT=m -CONFIG_ZCRYPT_MULTIDEVNODES=y CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m @@ -247,4 +224,30 @@ CONFIG_CRC7=m # CONFIG_XZ_DEC_ARM is not set # CONFIG_XZ_DEC_ARMTHUMB is not set # CONFIG_XZ_DEC_SPARC is not set -CONFIG_CMM=m +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FUNCTION_PROFILER=y +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index dbd689d556ce..ccbb53e22024 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; - /* pgd_alloc() did not account this pud */ - mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not account this pmd */ - mm_inc_nr_pmds(mm); - mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index f0f9bcf94c03..5ee733720a57 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry) static inline unsigned long pgd_entry_type(struct mm_struct *mm) { - if (mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(mm)) return _SEGMENT_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(mm)) return _REGION3_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(mm)) return _REGION2_ENTRY_EMPTY; return _REGION1_ENTRY_EMPTY; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 411d435e7a7d..063732414dfb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr) _REGION_ENTRY_PROTECT | \ _REGION_ENTRY_NOEXEC) +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION1_SIZE; +} +#define mm_p4d_folded(mm) mm_p4d_folded(mm) + +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION2_SIZE; +} +#define mm_pud_folded(mm) mm_pud_folded(mm) + +static inline bool mm_pmd_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION3_SIZE; +} +#define mm_pmd_folded(mm) mm_pmd_folded(mm) + static inline int mm_has_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 302795c47c06..81038ab357ce 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -236,7 +236,7 @@ static inline unsigned long current_stack_pointer(void) return sp; } -static __no_sanitize_address_or_inline unsigned short stap(void) +static __no_kasan_or_inline unsigned short stap(void) { unsigned short cpu_address; @@ -330,7 +330,7 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ -static __no_sanitize_address_or_inline void __load_psw_mask(unsigned long mask) +static __no_kasan_or_inline void __load_psw_mask(unsigned long mask) { unsigned long addr; psw_t psw; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 27248f42a03c..ce4e17c9aad6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,7 +14,7 @@ * General size of kernel stacks */ #ifdef CONFIG_KASAN -#define THREAD_SIZE_ORDER 3 +#define THREAD_SIZE_ORDER 4 #else #define THREAD_SIZE_ORDER 2 #endif diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..b31c779cf581 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); @@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(tlb->mm)) return; tlb_remove_table(tlb, p4d); } @@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(tlb->mm)) return; tlb_remove_table(tlb, pud); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 724fba4d09d2..39191a0feed1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -236,10 +236,10 @@ ENTRY(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread - lg %r5,0(%r4,%r3) # start of kernel stack of next + llill %r5,STACK_INIT stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev - lgr %r15,%r5 - aghi %r15,STACK_INIT # end of kernel stack of next + lg %r15,0(%r4,%r3) # start of kernel stack of next + agr %r15,%r5 # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index cc085e2d2ce9..74091fd3101e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event) return -ENOENT; if (ev > PERF_CPUM_CF_MAX_CTR) - return -EINVAL; + return -ENOENT; /* Obtain the counter set to which the specified counter belongs */ set = get_counter_set(ev); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 7bf604ff50a1..bfabeb1889cc 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags) CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF); CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); -static struct attribute *cpumsf_pmu_events_attr[] = { - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - NULL, - NULL, +/* Attribute list for CPU_SF. + * + * The availablitiy depends on the CPU_MF sampling facility authorization + * for basic + diagnositic samples. This is determined at initialization + * time by the sampling facility device driver. + * If the authorization for basic samples is turned off, it should be + * also turned off for diagnostic sampling. + * + * During initialization of the device driver, check the authorization + * level for diagnostic sampling and installs the attribute + * file for diagnostic sampling if necessary. + * + * For now install a placeholder to reference all possible attributes: + * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG. + * Add another entry for the final NULL pointer. + */ +enum { + SF_CYCLES_BASIC_ATTR_IDX = 0, + SF_CYCLES_BASIC_DIAG_ATTR_IDX, + SF_CYCLES_ATTR_MAX +}; + +static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = { + [SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC) }; PMU_FORMAT_ATTR(event, "config:0-63"); @@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void) if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); - cpumsf_pmu_events_attr[1] = + /* Sampling of diagnostic data authorized, + * install event into attribute list of PMU device. + */ + cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index eb8aebea3ea7..e76309fbbcb3 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index a22b2cf86eec..f849ac61c5da 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 21eb7407d51b..8429ab079715 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -154,14 +154,14 @@ SECTIONS * uncompressed image info used by the decompressor * it should match struct vmlinux_info */ - .vmlinux.info 0 : { + .vmlinux.info 0 (INFO) : { QUAD(_stext) /* default_lma */ QUAD(startup_continue) /* entry */ QUAD(__bss_start - _stext) /* image_size */ QUAD(__bss_stop - __bss_start) /* bss_size */ QUAD(__boot_data_start) /* bootdata_off */ QUAD(__boot_data_end - __boot_data_start) /* bootdata_size */ - } + } :NONE /* Debugging sections. */ STABS_DEBUG diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 76d89ee8b428..814f26520aa2 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) mm->context.asce_limit = _REGION1_SIZE; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); } else { crst_table_init(table, _REGION1_ENTRY_EMPTY); pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index ae0d9e889534..d31bde0870d8 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -53,6 +53,7 @@ int __node_distance(int a, int b) { return mode->distance ? mode->distance(a, b) : 0; } +EXPORT_SYMBOL(__node_distance); int numa_debug_enabled; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 74c002ddc0ce..28c40624bcb6 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->fds[0] = dev->cow.fd; else io_req->fds[0] = dev->fd; + io_req->error = 0; if (req_op(req) == REQ_OP_FLUSH) { io_req->op = UBD_FLUSH; @@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->cow_offset = -1; io_req->offset = off; io_req->length = bvec->bv_len; - io_req->error = 0; io_req->sector_mask = 0; - io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset; @@ -1341,11 +1340,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { + struct ubd *ubd_dev = hctx->queue->queuedata; struct request *req = bd->rq; int ret = 0; blk_mq_start_request(req); + spin_lock_irq(&ubd_dev->lock); + if (req_op(req) == REQ_OP_FLUSH) { ret = ubd_queue_one_vec(hctx, req, 0, NULL); } else { @@ -1361,9 +1363,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, } } out: - if (ret < 0) { + spin_unlock_irq(&ubd_dev->lock); + + if (ret < 0) blk_mq_requeue_request(req, true); - } + return BLK_STS_OK; } diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 87623c6b13db..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -13,12 +13,15 @@ #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) { - u32 val = 0; - - if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, - "I", _Q_PENDING_OFFSET)) - val |= _Q_PENDING_VAL; + u32 val; + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; return val; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include <linux/mm.h> #include <linux/device.h> -#include <linux/uaccess.h> +#include <asm/extable.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b06731705529..055e37e43541 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include <linux/log2.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/atomic.h> #include <asm/paravirt.h> #include <asm/qspinlock.h> @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) diff --git a/block/bio.c b/block/bio.c index d5368a445561..a50d59236b19 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1260,6 +1260,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } diff --git a/block/blk-lib.c b/block/blk-lib.c index 76f867ea9a9b..e8b3bb9bf375 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -51,16 +51,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; - while (nr_sects) { - unsigned int req_sects = nr_sects; - sector_t end_sect; - - if (!req_sects) - goto fail; - if (req_sects > UINT_MAX >> 9) - req_sects = UINT_MAX >> 9; + if (!nr_sects) + return -EINVAL; - end_sect = sector + req_sects; + while (nr_sects) { + unsigned int req_sects = min_t(unsigned int, nr_sects, + bio_allowed_max_sectors(q)); bio = blk_next_bio(bio, 0, gfp_mask); bio->bi_iter.bi_sector = sector; @@ -68,8 +64,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_set_op_attrs(bio, op, 0); bio->bi_iter.bi_size = req_sects << 9; + sector += req_sects; nr_sects -= req_sects; - sector = end_sect; /* * We can loop for a long time in here, if someone does @@ -82,14 +78,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, *biop = bio; return 0; - -fail: - if (bio) { - submit_bio_wait(bio); - bio_put(bio); - } - *biop = NULL; - return -EOPNOTSUPP; } EXPORT_SYMBOL(__blkdev_issue_discard); @@ -161,7 +149,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; /* Ensure that max_write_same_sectors doesn't overflow bi_size */ - max_write_same_sectors = UINT_MAX >> 9; + max_write_same_sectors = bio_allowed_max_sectors(q); while (nr_sects) { bio = blk_next_bio(bio, 1, gfp_mask); diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..e7696c47489a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) + if (pb.bv_offset & queue_virt_boundary(q)) return true; /* @@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = min(q->limits.max_discard_sectors, + bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { diff --git a/block/blk.h b/block/blk.h index a1841b8ff129..0089fefdf771 100644 --- a/block/blk.h +++ b/block/blk.h @@ -169,7 +169,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { - return offset || + return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } @@ -396,6 +396,16 @@ static inline unsigned long blk_rq_deadline(struct request *rq) } /* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to aligned to with logical + * block size which is the minimum accepted unit by hardware. + */ +static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) +{ + return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; +} + +/* * Internal io_context interface */ void get_io_context(struct io_context *ioc); diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 10ecb232245d..4b1ff5bc256a 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Renesas R-Car SATA driver * * Author: Vladimir Barinov <source@cogentembedded.com> * Copyright (C) 2013-2015 Cogent Embedded, Inc. * Copyright (C) 2013-2015 Renesas Solutions 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/kernel.h> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 56452cabce5b..0ed4b200fa58 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1919,6 +1919,7 @@ static int negotiate_mq(struct blkfront_info *info) GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); + info->nr_rings = 0; return -ENOMEM; } diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index ef0ca9414f37..ff83e899df71 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -210,6 +210,7 @@ static int of_fixed_factor_clk_remove(struct platform_device *pdev) { struct clk *clk = platform_get_drvdata(pdev); + of_clk_del_provider(pdev->dev.of_node); clk_unregister_fixed_factor(clk); return 0; diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c981159b02c0..792735d7e46e 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -325,6 +325,7 @@ static struct clk_regmap axg_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; @@ -349,6 +350,18 @@ static struct clk_regmap axg_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 9309cfaaa464..4ada9668fd49 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -506,6 +506,18 @@ static struct clk_regmap gxbb_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index e4ca6a45f313..ef1b267cb058 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -265,7 +265,7 @@ static struct clk_fixed_factor cxo = { .div = 1, .hw.init = &(struct clk_init_data){ .name = "cxo", - .parent_names = (const char *[]){ "xo_board" }, + .parent_names = (const char *[]){ "xo-board" }, .num_parents = 1, .ops = &clk_fixed_factor_ops, }, diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index a11f4ba98b05..55c77e44bb2d 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -620,4 +620,22 @@ config RISCV_TIMER is accessed via both the SBI and the rdcycle instruction. This is required for all RISC-V systems. +config CSKY_MP_TIMER + bool "SMP Timer for the C-SKY platform" if COMPILE_TEST + depends on CSKY + select TIMER_OF + help + Say yes here to enable C-SKY SMP timer driver used for C-SKY SMP + system. + csky,mptimer is not only used in SMP system, it also could be used + single core system. It's not a mmio reg and it use mtcr/mfcr instruction. + +config GX6605S_TIMER + bool "Gx6605s SOC system timer driver" if COMPILE_TEST + depends on CSKY + select CLKSRC_MMIO + select TIMER_OF + help + This option enables support for gx6605s SOC's timer. + endmenu diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index e33b21d3f9d8..dd9138104568 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -79,3 +79,5 @@ obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += riscv_timer.o +obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o +obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o diff --git a/drivers/clocksource/timer-gx6605s.c b/drivers/clocksource/timer-gx6605s.c new file mode 100644 index 000000000000..80d0939d040b --- /dev/null +++ b/drivers/clocksource/timer-gx6605s.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/sched_clock.h> + +#include "timer-of.h" + +#define CLKSRC_OFFSET 0x40 + +#define TIMER_STATUS 0x00 +#define TIMER_VALUE 0x04 +#define TIMER_CONTRL 0x10 +#define TIMER_CONFIG 0x20 +#define TIMER_DIV 0x24 +#define TIMER_INI 0x28 + +#define GX6605S_STATUS_CLR BIT(0) +#define GX6605S_CONTRL_RST BIT(0) +#define GX6605S_CONTRL_START BIT(1) +#define GX6605S_CONFIG_EN BIT(0) +#define GX6605S_CONFIG_IRQ_EN BIT(1) + +static irqreturn_t gx6605s_timer_interrupt(int irq, void *dev) +{ + struct clock_event_device *ce = dev; + void __iomem *base = timer_of_base(to_timer_of(ce)); + + writel_relaxed(GX6605S_STATUS_CLR, base + TIMER_STATUS); + + ce->event_handler(ce); + + return IRQ_HANDLED; +} + +static int gx6605s_timer_set_oneshot(struct clock_event_device *ce) +{ + void __iomem *base = timer_of_base(to_timer_of(ce)); + + /* reset and stop counter */ + writel_relaxed(GX6605S_CONTRL_RST, base + TIMER_CONTRL); + + /* enable with irq and start */ + writel_relaxed(GX6605S_CONFIG_EN | GX6605S_CONFIG_IRQ_EN, + base + TIMER_CONFIG); + + return 0; +} + +static int gx6605s_timer_set_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + void __iomem *base = timer_of_base(to_timer_of(ce)); + + /* use reset to pause timer */ + writel_relaxed(GX6605S_CONTRL_RST, base + TIMER_CONTRL); + + /* config next timeout value */ + writel_relaxed(ULONG_MAX - delta, base + TIMER_INI); + writel_relaxed(GX6605S_CONTRL_START, base + TIMER_CONTRL); + + return 0; +} + +static int gx6605s_timer_shutdown(struct clock_event_device *ce) +{ + void __iomem *base = timer_of_base(to_timer_of(ce)); + + writel_relaxed(0, base + TIMER_CONTRL); + writel_relaxed(0, base + TIMER_CONFIG); + + return 0; +} + +static struct timer_of to = { + .flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK, + .clkevt = { + .rating = 300, + .features = CLOCK_EVT_FEAT_DYNIRQ | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_shutdown = gx6605s_timer_shutdown, + .set_state_oneshot = gx6605s_timer_set_oneshot, + .set_next_event = gx6605s_timer_set_next_event, + .cpumask = cpu_possible_mask, + }, + .of_irq = { + .handler = gx6605s_timer_interrupt, + .flags = IRQF_TIMER | IRQF_IRQPOLL, + }, +}; + +static u64 notrace gx6605s_sched_clock_read(void) +{ + void __iomem *base; + + base = timer_of_base(&to) + CLKSRC_OFFSET; + + return (u64)readl_relaxed(base + TIMER_VALUE); +} + +static void gx6605s_clkevt_init(void __iomem *base) +{ + writel_relaxed(0, base + TIMER_DIV); + writel_relaxed(0, base + TIMER_CONFIG); + + clockevents_config_and_register(&to.clkevt, timer_of_rate(&to), 2, + ULONG_MAX); +} + +static int gx6605s_clksrc_init(void __iomem *base) +{ + writel_relaxed(0, base + TIMER_DIV); + writel_relaxed(0, base + TIMER_INI); + + writel_relaxed(GX6605S_CONTRL_RST, base + TIMER_CONTRL); + + writel_relaxed(GX6605S_CONFIG_EN, base + TIMER_CONFIG); + + writel_relaxed(GX6605S_CONTRL_START, base + TIMER_CONTRL); + + sched_clock_register(gx6605s_sched_clock_read, 32, timer_of_rate(&to)); + + return clocksource_mmio_init(base + TIMER_VALUE, "gx6605s", + timer_of_rate(&to), 200, 32, clocksource_mmio_readl_up); +} + +static int __init gx6605s_timer_init(struct device_node *np) +{ + int ret; + + /* + * The timer driver is for nationalchip gx6605s SOC and there are two + * same timer in gx6605s. We use one for clkevt and another for clksrc. + * + * The timer is mmio map to access, so we need give mmio address in dts. + * + * It provides a 32bit countup timer and interrupt will be caused by + * count-overflow. + * So we need set-next-event by ULONG_MAX - delta in TIMER_INI reg. + * + * The counter at 0x0 offset is clock event. + * The counter at 0x40 offset is clock source. + * They are the same in hardware, just different used by driver. + */ + ret = timer_of_init(np, &to); + if (ret) + return ret; + + gx6605s_clkevt_init(timer_of_base(&to)); + + return gx6605s_clksrc_init(timer_of_base(&to) + CLKSRC_OFFSET); +} +TIMER_OF_DECLARE(csky_gx6605s_timer, "csky,gx6605s-timer", gx6605s_timer_init); diff --git a/drivers/clocksource/timer-mp-csky.c b/drivers/clocksource/timer-mp-csky.c new file mode 100644 index 000000000000..a8acc431a774 --- /dev/null +++ b/drivers/clocksource/timer-mp-csky.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/sched_clock.h> +#include <linux/cpu.h> +#include <linux/of_irq.h> +#include <asm/reg_ops.h> + +#include "timer-of.h" + +#define PTIM_CCVR "cr<3, 14>" +#define PTIM_CTLR "cr<0, 14>" +#define PTIM_LVR "cr<6, 14>" +#define PTIM_TSR "cr<1, 14>" + +static int csky_mptimer_irq; + +static int csky_mptimer_set_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + mtcr(PTIM_LVR, delta); + + return 0; +} + +static int csky_mptimer_shutdown(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 0); + + return 0; +} + +static int csky_mptimer_oneshot(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 1); + + return 0; +} + +static int csky_mptimer_oneshot_stopped(struct clock_event_device *ce) +{ + mtcr(PTIM_CTLR, 0); + + return 0; +} + +static DEFINE_PER_CPU(struct timer_of, csky_to) = { + .flags = TIMER_OF_CLOCK, + .clkevt = { + .rating = 300, + .features = CLOCK_EVT_FEAT_PERCPU | + CLOCK_EVT_FEAT_ONESHOT, + .set_state_shutdown = csky_mptimer_shutdown, + .set_state_oneshot = csky_mptimer_oneshot, + .set_state_oneshot_stopped = csky_mptimer_oneshot_stopped, + .set_next_event = csky_mptimer_set_next_event, + }, +}; + +static irqreturn_t csky_timer_interrupt(int irq, void *dev) +{ + struct timer_of *to = this_cpu_ptr(&csky_to); + + mtcr(PTIM_TSR, 0); + + to->clkevt.event_handler(&to->clkevt); + + return IRQ_HANDLED; +} + +/* + * clock event for percpu + */ +static int csky_mptimer_starting_cpu(unsigned int cpu) +{ + struct timer_of *to = per_cpu_ptr(&csky_to, cpu); + + to->clkevt.cpumask = cpumask_of(cpu); + + clockevents_config_and_register(&to->clkevt, timer_of_rate(to), + 2, ULONG_MAX); + + enable_percpu_irq(csky_mptimer_irq, 0); + + return 0; +} + +static int csky_mptimer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(csky_mptimer_irq); + + return 0; +} + +/* + * clock source + */ +static u64 sched_clock_read(void) +{ + return (u64)mfcr(PTIM_CCVR); +} + +static u64 clksrc_read(struct clocksource *c) +{ + return (u64)mfcr(PTIM_CCVR); +} + +struct clocksource csky_clocksource = { + .name = "csky", + .rating = 400, + .mask = CLOCKSOURCE_MASK(32), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clksrc_read, +}; + +static int __init csky_mptimer_init(struct device_node *np) +{ + int ret, cpu, cpu_rollback; + struct timer_of *to = NULL; + + /* + * Csky_mptimer is designed for C-SKY SMP multi-processors and + * every core has it's own private irq and regs for clkevt and + * clksrc. + * + * The regs is accessed by cpu instruction: mfcr/mtcr instead of + * mmio map style. So we needn't mmio-address in dts, but we still + * need to give clk and irq number. + * + * We use private irq for the mptimer and irq number is the same + * for every core. So we use request_percpu_irq() in timer_of_init. + */ + csky_mptimer_irq = irq_of_parse_and_map(np, 0); + if (csky_mptimer_irq <= 0) + return -EINVAL; + + ret = request_percpu_irq(csky_mptimer_irq, csky_timer_interrupt, + "csky_mp_timer", &csky_to); + if (ret) + return -EINVAL; + + for_each_possible_cpu(cpu) { + to = per_cpu_ptr(&csky_to, cpu); + ret = timer_of_init(np, to); + if (ret) + goto rollback; + } + + clocksource_register_hz(&csky_clocksource, timer_of_rate(to)); + sched_clock_register(sched_clock_read, 32, timer_of_rate(to)); + + ret = cpuhp_setup_state(CPUHP_AP_CSKY_TIMER_STARTING, + "clockevents/csky/timer:starting", + csky_mptimer_starting_cpu, + csky_mptimer_dying_cpu); + if (ret) + return -EINVAL; + + return 0; + +rollback: + for_each_possible_cpu(cpu_rollback) { + if (cpu_rollback == cpu) + break; + + to = per_cpu_ptr(&csky_to, cpu_rollback); + timer_of_cleanup(to); + } + return -EINVAL; +} +TIMER_OF_DECLARE(csky_mptimer, "csky,mptimer", csky_mptimer_init); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d0102cfc8efb..104b2e0d893b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -151,6 +151,7 @@ extern int amdgpu_compute_multipipe; extern int amdgpu_gpu_recovery; extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; +extern uint amdgpu_dc_feature_mask; extern struct amdgpu_mgpu_info mgpu_info; #ifdef CONFIG_DRM_AMDGPU_SI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 943dbf3c5da1..8de55f7f1a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1; int amdgpu_gpu_recovery = -1; /* auto */ int amdgpu_emu_mode = 0; uint amdgpu_smu_memory_pool_size = 0; +/* FBC (bit 0) disabled by default*/ +uint amdgpu_dc_feature_mask = 0; + struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; @@ -631,6 +634,14 @@ module_param(halt_if_hws_hang, int, 0644); MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); #endif +/** + * DOC: dcfeaturemask (uint) + * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h. + * The default is the current set of stable display features. + */ +MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))"); +module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444); + static const struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_SI {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI}, diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c index 2d4473557b0d..d13fc4fcb517 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c @@ -49,6 +49,7 @@ int vega20_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); + adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); } return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b0df6dc9a775..c1262f62cd9f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -429,6 +429,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; + if (amdgpu_dc_feature_mask & DC_FBC_MASK) + init_data.flags.fbc_support = true; + /* Display Core create. */ adev->dm.dc = dc_create(&init_data); @@ -1524,13 +1527,6 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - /* - * PWM interperts 0 as 100% rather than 0% because of HW - * limitation for level 0.So limiting minimum brightness level - * to 1. - */ - if (bd->props.brightness < 1) - return 1; if (dc_link_set_backlight_level(dm->backlight_link, bd->props.brightness, 0, 0)) return 0; @@ -2707,18 +2703,11 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector = &aconnector->base; if (!aconnector->dc_sink) { - /* - * Create dc_sink when necessary to MST - * Don't apply fake_sink to MST - */ - if (aconnector->mst_port) { - dm_dp_mst_dc_sink_create(drm_connector); - return stream; + if (!aconnector->mst_port) { + sink = create_fake_sink(aconnector); + if (!sink) + return stream; } - - sink = create_fake_sink(aconnector); - if (!sink) - return stream; } else { sink = aconnector->dc_sink; } @@ -3308,7 +3297,7 @@ void dm_drm_plane_destroy_state(struct drm_plane *plane, static const struct drm_plane_funcs dm_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = drm_plane_cleanup, + .destroy = drm_primary_helper_destroy, .reset = dm_drm_plane_reset, .atomic_duplicate_state = dm_drm_plane_duplicate_state, .atomic_destroy_state = dm_drm_plane_destroy_state, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 978b34a5011c..924a38a1fc44 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -160,8 +160,6 @@ struct amdgpu_dm_connector { struct mutex hpd_lock; bool fake_enable; - - bool mst_connected; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 03601d717fed..d02c32a1039c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -205,40 +205,6 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { .atomic_get_property = amdgpu_dm_connector_atomic_get_property }; -void dm_dp_mst_dc_sink_create(struct drm_connector *connector) -{ - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - struct dc_sink *dc_sink; - struct dc_sink_init_data init_params = { - .link = aconnector->dc_link, - .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; - - /* FIXME none of this is safe. we shouldn't touch aconnector here in - * atomic_check - */ - - /* - * TODO: Need to further figure out why ddc.algo is NULL while MST port exists - */ - if (!aconnector->port || !aconnector->port->aux.ddc.algo) - return; - - ASSERT(aconnector->edid); - - dc_sink = dc_link_add_remote_sink( - aconnector->dc_link, - (uint8_t *)aconnector->edid, - (aconnector->edid->extensions + 1) * EDID_LENGTH, - &init_params); - - dc_sink->priv = aconnector; - aconnector->dc_sink = dc_sink; - - if (aconnector->dc_sink) - amdgpu_dm_update_freesync_caps( - connector, aconnector->edid); -} - static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); @@ -319,12 +285,7 @@ dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector) struct amdgpu_device *adev = dev->dev_private; struct amdgpu_encoder *amdgpu_encoder; struct drm_encoder *encoder; - const struct drm_connector_helper_funcs *connector_funcs = - connector->base.helper_private; - struct drm_encoder *enc_master = - connector_funcs->best_encoder(&connector->base); - DRM_DEBUG_KMS("enc master is %p\n", enc_master); amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL); if (!amdgpu_encoder) return NULL; @@ -354,25 +315,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; - - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - aconnector = to_amdgpu_dm_connector(connector); - if (aconnector->mst_port == master - && !aconnector->port) { - DRM_INFO("DM_MST: reusing connector: %p [id: %d] [master: %p]\n", - aconnector, connector->base.id, aconnector->mst_port); - - aconnector->port = port; - drm_connector_set_path_property(connector, pathprop); - - drm_connector_list_iter_end(&conn_iter); - aconnector->mst_connected = true; - return &aconnector->base; - } - } - drm_connector_list_iter_end(&conn_iter); aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL); if (!aconnector) @@ -421,8 +363,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, */ amdgpu_dm_connector_funcs_reset(connector); - aconnector->mst_connected = true; - DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n", aconnector, connector->base.id, aconnector->mst_port); @@ -434,6 +374,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_connector *connector) { + struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr); + struct drm_device *dev = master->base.dev; + struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); DRM_INFO("DM_MST: Disabling connector: %p [id: %d] [master: %p]\n", @@ -447,7 +390,10 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector->dc_sink = NULL; } - aconnector->mst_connected = false; + drm_connector_unregister(connector); + if (adev->mode_info.rfbdev) + drm_fb_helper_remove_one_connector(&adev->mode_info.rfbdev->helper, connector); + drm_connector_put(connector); } static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) @@ -458,18 +404,10 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) drm_kms_helper_hotplug_event(dev); } -static void dm_dp_mst_link_status_reset(struct drm_connector *connector) -{ - mutex_lock(&connector->dev->mode_config.mutex); - drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); - mutex_unlock(&connector->dev->mode_config.mutex); -} - static void dm_dp_mst_register_connector(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = dev->dev_private; - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); if (adev->mode_info.rfbdev) drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector); @@ -477,9 +415,6 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector) DRM_ERROR("adev->mode_info.rfbdev is NULL\n"); drm_connector_register(connector); - - if (aconnector->mst_connected) - dm_dp_mst_link_status_reset(connector); } static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 8cf51da26657..2da851b40042 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -31,6 +31,5 @@ struct amdgpu_dm_connector; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); -void dm_dp_mst_dc_sink_create(struct drm_connector *connector); #endif diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fb04a4ad141f..5da2186b3615 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1722,7 +1722,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ @@ -1734,7 +1734,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 199527171100..b57fa61b3034 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -169,6 +169,7 @@ struct link_training_settings; struct dc_config { bool gpu_vm_support; bool disable_disp_pll_sharing; + bool fbc_support; }; enum visual_confirm { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index b75ede5f84f7..b459867a05b2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1736,7 +1736,12 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx, if (events->force_trigger) value |= 0x1; - value |= 0x84; + if (num_pipes) { + struct dc *dc = pipe_ctx[0]->stream->ctx->dc; + + if (dc->fbc_compressor) + value |= 0x84; + } for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index e3624ca24574..7c9fd9052ee2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -1362,7 +1362,8 @@ static bool construct( pool->base.sw_i2cs[i] = NULL; } - dc->fbc_compressor = dce110_compressor_create(ctx); + if (dc->config.fbc_support) + dc->fbc_compressor = dce110_compressor_create(ctx); if (!underlay_create(ctx, &pool->base)) goto res_create_fail; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 2083c308007c..470d7b89071a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -133,6 +133,10 @@ enum PP_FEATURE_MASK { PP_AVFS_MASK = 0x40000, }; +enum DC_FEATURE_MASK { + DC_FBC_MASK = 0x1, +}; + /** * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks */ diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index d2e7c0fa96c2..8eb0bb241210 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1325,7 +1325,7 @@ struct atom_smu_info_v3_3 { struct atom_common_table_header table_header; uint8_t smuip_min_ver; uint8_t smuip_max_ver; - uint8_t smu_rsd1; + uint8_t waflclk_ss_mode; uint8_t gpuclk_ss_mode; uint16_t sclk_ss_percentage; uint16_t sclk_ss_rate_10hz; @@ -1355,7 +1355,10 @@ struct atom_smu_info_v3_3 { uint32_t syspll3_1_vco_freq_10khz; uint32_t bootup_fclk_10khz; uint32_t bootup_waflclk_10khz; - uint32_t reserved[3]; + uint32_t smu_info_caps; + uint16_t waflclk_ss_percentage; // in unit of 0.001% + uint16_t smuinitoffset; + uint32_t reserved; }; /* diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 57143d51e3ee..99861f32b1f9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -120,6 +120,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; + data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; @@ -829,6 +830,28 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr) return 0; } +static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); + + if (data->smu_features[GNLD_DPM_UCLK].enabled) + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetUclkFastSwitch, + 1); + + return 0; +} + +static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetFclkGfxClkRatio, + data->registry_data.fclk_gfxclk_ratio); +} + static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = @@ -1532,6 +1555,16 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to enable all smu features!", return result); + result = vega20_notify_smc_display_change(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to notify smc display change!", + return result); + + result = vega20_send_clock_ratio(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to send clock ratio!", + return result); + /* Initialize UVD/VCE powergating state */ vega20_init_powergate_state(hwmgr); @@ -1972,19 +2005,6 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx, return ret; } -static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr, - bool has_disp) -{ - struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DPM_UCLK].enabled) - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_SetUclkFastSwitch, - has_disp ? 1 : 0); - - return 0; -} - int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, struct pp_display_clock_request *clock_req) { @@ -2044,13 +2064,6 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( struct pp_display_clock_request clock_req; int ret = 0; - if ((hwmgr->display_config->num_display > 1) && - !hwmgr->display_config->multi_monitor_in_sync && - !hwmgr->display_config->nb_pstate_switch_disable) - vega20_notify_smc_display_change(hwmgr, false); - else - vega20_notify_smc_display_change(hwmgr, true); - min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk; min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk; min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h index 56fe6a0d42e8..25faaa5c5b10 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h @@ -328,6 +328,7 @@ struct vega20_registry_data { uint8_t disable_auto_wattman; uint32_t auto_wattman_debug; uint32_t auto_wattman_sample_period; + uint32_t fclk_gfxclk_ratio; uint8_t auto_wattman_threshold; uint8_t log_avfs_param; uint8_t enable_enginess; diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h index 45d64a81e945..4f63a736ea0e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h @@ -105,7 +105,8 @@ #define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x4B #define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x4C #define PPSMC_MSG_WaflTest 0x4D -// Unused ID 0x4E to 0x50 +#define PPSMC_MSG_SetFclkGfxClkRatio 0x4E +// Unused ID 0x4F to 0x50 #define PPSMC_MSG_AllowGfxOff 0x51 #define PPSMC_MSG_DisallowGfxOff 0x52 #define PPSMC_MSG_GetPptLimit 0x53 diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index e7c3ed6c9a2e..9b476368aa31 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -93,7 +93,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ - if (fence_completed(gpu, submit->out_fence->seqno)) + if (dma_fence_is_signaled(submit->out_fence)) return; /* diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 94529aa82339..aef487dd8731 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -164,13 +164,6 @@ static u32 decon_get_frame_count(struct decon_context *ctx, bool end) return frm; } -static u32 decon_get_vblank_counter(struct exynos_drm_crtc *crtc) -{ - struct decon_context *ctx = crtc->ctx; - - return decon_get_frame_count(ctx, false); -} - static void decon_setup_trigger(struct decon_context *ctx) { if (!ctx->crtc->i80_mode && !(ctx->out_type & I80_HW_TRG)) @@ -536,7 +529,6 @@ static const struct exynos_drm_crtc_ops decon_crtc_ops = { .disable = decon_disable, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, - .get_vblank_counter = decon_get_vblank_counter, .atomic_begin = decon_atomic_begin, .update_plane = decon_update_plane, .disable_plane = decon_disable_plane, @@ -554,7 +546,6 @@ static int decon_bind(struct device *dev, struct device *master, void *data) int ret; ctx->drm_dev = drm_dev; - drm_dev->max_vblank_count = 0xffffffff; for (win = ctx->first_win; win < WINDOWS_NR; win++) { ctx->configs[win].pixel_formats = decon_formats; diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index eea90251808f..2696289ecc78 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -162,16 +162,6 @@ static void exynos_drm_crtc_disable_vblank(struct drm_crtc *crtc) exynos_crtc->ops->disable_vblank(exynos_crtc); } -static u32 exynos_drm_crtc_get_vblank_counter(struct drm_crtc *crtc) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->get_vblank_counter) - return exynos_crtc->ops->get_vblank_counter(exynos_crtc); - - return 0; -} - static const struct drm_crtc_funcs exynos_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -181,7 +171,6 @@ static const struct drm_crtc_funcs exynos_crtc_funcs = { .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .enable_vblank = exynos_drm_crtc_enable_vblank, .disable_vblank = exynos_drm_crtc_disable_vblank, - .get_vblank_counter = exynos_drm_crtc_get_vblank_counter, }; struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index ec9604f1272b..5e61e707f955 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -135,7 +135,6 @@ struct exynos_drm_crtc_ops { void (*disable)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); - u32 (*get_vblank_counter)(struct exynos_drm_crtc *crtc); enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc, const struct drm_display_mode *mode); bool (*mode_fixup)(struct exynos_drm_crtc *crtc, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 07af7758066d..d81e62ae286a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -14,6 +14,7 @@ #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_panel.h> #include <drm/drm_atomic_helper.h> @@ -1474,12 +1475,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) { struct exynos_dsi *dsi = encoder_to_dsi(encoder); struct drm_connector *connector = &dsi->connector; + struct drm_device *drm = encoder->dev; int ret; connector->polled = DRM_CONNECTOR_POLL_HPD; - ret = drm_connector_init(encoder->dev, connector, - &exynos_dsi_connector_funcs, + ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); if (ret) { DRM_ERROR("Failed to initialize connector with drm\n"); @@ -1489,7 +1490,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) connector->status = connector_status_disconnected; drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); drm_connector_attach_encoder(connector, encoder); + if (!drm->registered) + return 0; + connector->funcs->reset(connector); + drm_fb_helper_add_one_connector(drm->fb_helper, connector); + drm_connector_register(connector); return 0; } @@ -1527,7 +1533,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, } dsi->panel = of_drm_find_panel(device->dev.of_node); - if (dsi->panel) { + if (IS_ERR(dsi->panel)) { + dsi->panel = NULL; + } else { drm_panel_attach(dsi->panel, &dsi->connector); dsi->connector.status = connector_status_connected; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 918dd2c82209..01d182289efa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -192,7 +192,7 @@ int exynos_drm_fbdev_init(struct drm_device *dev) struct drm_fb_helper *helper; int ret; - if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector) + if (!dev->mode_config.num_crtc) return 0; fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 2402395a068d..58e166effa45 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1905,7 +1905,6 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu) vgpu_free_mm(mm); return ERR_PTR(-ENOMEM); } - mm->ggtt_mm.last_partial_off = -1UL; return mm; } @@ -1930,7 +1929,6 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); - mm->ggtt_mm.last_partial_off = -1UL; } vgpu_free_mm(mm); @@ -2168,6 +2166,8 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, struct intel_gvt_gtt_entry e, m; dma_addr_t dma_addr; int ret; + struct intel_gvt_partial_pte *partial_pte, *pos, *n; + bool partial_update = false; if (bytes != 4 && bytes != 8) return -EINVAL; @@ -2178,68 +2178,57 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, if (!vgpu_gmadr_is_valid(vgpu, gma)) return 0; - ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index); - + e.type = GTT_TYPE_GGTT_PTE; memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes - * write, we assume the two 4 bytes writes are consecutive. - * Otherwise, we abort and report error + * write, save the first 4 bytes in a list and update virtual + * PTE. Only update shadow PTE when the second 4 bytes comes. */ if (bytes < info->gtt_entry_size) { - if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) { - /* the first partial part*/ - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; - return 0; - } else if ((g_gtt_index == - (ggtt_mm->ggtt_mm.last_partial_off >> - info->gtt_entry_size_shift)) && - (off != ggtt_mm->ggtt_mm.last_partial_off)) { - /* the second partial part */ - - int last_off = ggtt_mm->ggtt_mm.last_partial_off & - (info->gtt_entry_size - 1); - - memcpy((void *)&e.val64 + last_off, - (void *)&ggtt_mm->ggtt_mm.last_partial_data + - last_off, bytes); - - ggtt_mm->ggtt_mm.last_partial_off = -1UL; - } else { - int last_offset; - - gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n", - ggtt_mm->ggtt_mm.last_partial_off, off, - bytes, info->gtt_entry_size); - - /* set host ggtt entry to scratch page and clear - * virtual ggtt entry as not present for last - * partially write offset - */ - last_offset = ggtt_mm->ggtt_mm.last_partial_off & - (~(info->gtt_entry_size - 1)); - - ggtt_get_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate_pte(vgpu, &m); - ops->set_pfn(&m, gvt->gtt.scratch_mfn); - ops->clear_present(&m); - ggtt_set_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate(gvt->dev_priv); - - ggtt_get_guest_entry(ggtt_mm, &e, last_offset); - ops->clear_present(&e); - ggtt_set_guest_entry(ggtt_mm, &e, last_offset); - - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; + bool found = false; + + list_for_each_entry_safe(pos, n, + &ggtt_mm->ggtt_mm.partial_pte_list, list) { + if (g_gtt_index == pos->offset >> + info->gtt_entry_size_shift) { + if (off != pos->offset) { + /* the second partial part*/ + int last_off = pos->offset & + (info->gtt_entry_size - 1); + + memcpy((void *)&e.val64 + last_off, + (void *)&pos->data + last_off, + bytes); + + list_del(&pos->list); + kfree(pos); + found = true; + break; + } + + /* update of the first partial part */ + pos->data = e.val64; + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + return 0; + } + } - return 0; + if (!found) { + /* the first partial part */ + partial_pte = kzalloc(sizeof(*partial_pte), GFP_KERNEL); + if (!partial_pte) + return -ENOMEM; + partial_pte->offset = off; + partial_pte->data = e.val64; + list_add_tail(&partial_pte->list, + &ggtt_mm->ggtt_mm.partial_pte_list); + partial_update = true; } } - if (ops->test_present(&e)) { + if (!partial_update && (ops->test_present(&e))) { gfn = ops->get_pfn(&e); m = e; @@ -2263,16 +2252,18 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, } else ops->set_pfn(&m, dma_addr >> PAGE_SHIFT); } else { - ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index); - ggtt_invalidate_pte(vgpu, &m); ops->set_pfn(&m, gvt->gtt.scratch_mfn); ops->clear_present(&m); } out: + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + + ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index); + ggtt_invalidate_pte(vgpu, &e); + ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index); ggtt_invalidate(gvt->dev_priv); - ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); return 0; } @@ -2430,6 +2421,8 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) intel_vgpu_reset_ggtt(vgpu, false); + INIT_LIST_HEAD(>t->ggtt_mm->ggtt_mm.partial_pte_list); + return create_scratch_page_tree(vgpu); } @@ -2454,6 +2447,14 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu) { + struct intel_gvt_partial_pte *pos; + + list_for_each_entry(pos, + &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) { + gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n", + pos->offset, pos->data); + kfree(pos); + } intel_vgpu_destroy_mm(vgpu->gtt.ggtt_mm); vgpu->gtt.ggtt_mm = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 7a9b36176efb..d8cb04cc946d 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -35,7 +35,6 @@ #define _GVT_GTT_H_ #define I915_GTT_PAGE_SHIFT 12 -#define I915_GTT_PAGE_MASK (~(I915_GTT_PAGE_SIZE - 1)) struct intel_vgpu_mm; @@ -133,6 +132,12 @@ enum intel_gvt_mm_type { #define GVT_RING_CTX_NR_PDPS GEN8_3LVL_PDPES +struct intel_gvt_partial_pte { + unsigned long offset; + u64 data; + struct list_head list; +}; + struct intel_vgpu_mm { enum intel_gvt_mm_type type; struct intel_vgpu *vgpu; @@ -157,8 +162,7 @@ struct intel_vgpu_mm { } ppgtt_mm; struct { void *virtual_ggtt; - unsigned long last_partial_off; - u64 last_partial_data; + struct list_head partial_pte_list; } ggtt_mm; }; }; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 90f50f67909a..aa280bb07125 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1609,7 +1609,7 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu, return 0; } -static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu, +static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { vgpu_vreg(vgpu, offset) = 0; @@ -2607,6 +2607,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x1a178), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x1a17c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x2217c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + + MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); + MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); return 0; } @@ -3205,9 +3208,6 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT); - MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_D(RC6_CTX_BASE, D_BXT); MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 10e63eea5492..36a5147cd01e 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -131,7 +131,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GAMT_CHKN_BIT_REG, 0x0, false}, /* 0x4ab8 */ {RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */ - {RCS, GEN9_CSFE_CHICKEN1_RCS, 0x0, false}, /* 0x20d4 */ + {RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */ {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 44e2c0f5ec50..ffdbbac4400e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1175,8 +1175,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; - /* * If any of the channel is single rank channel, worst case output * will be same as if single rank memory, so consider single rank @@ -1193,8 +1191,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - if (ch0.is_16gb_dimm || ch1.is_16gb_dimm) - dram_info->is_16gb_dimm = true; + dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm; dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0, val_ch1, @@ -1314,7 +1311,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; dram_info->valid = true; return 0; } @@ -1327,12 +1323,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv) int ret; dram_info->valid = false; - dram_info->valid_dimm = false; - dram_info->is_16gb_dimm = false; dram_info->rank = I915_DRAM_RANK_INVALID; dram_info->bandwidth_kbps = 0; dram_info->num_channels = 0; + /* + * Assume 16Gb DIMMs are present until proven otherwise. + * This is only used for the level 0 watermark latency + * w/a which does not apply to bxt/glk. + */ + dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv); + if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8624b4bdc242..9102571e9692 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1948,7 +1948,6 @@ struct drm_i915_private { struct dram_info { bool valid; - bool valid_dimm; bool is_16gb_dimm; u8 num_channels; enum dram_rank { diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 09187286d346..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -460,7 +460,7 @@ eb_validate_vma(struct i915_execbuffer *eb, * any non-page-aligned or non-canonical addresses. */ if (unlikely(entry->flags & EXEC_OBJECT_PINNED && - entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK))) + entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK))) return -EINVAL; /* pad_to_size was once a reserved field, so sanitize it */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56c7f8637311..47c302543799 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1757,7 +1757,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m) if (i == 4) continue; - seq_printf(m, "\t\t(%03d, %04d) %08lx: ", + seq_printf(m, "\t\t(%03d, %04d) %08llx: ", pde, pte, (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE); for (i = 0; i < 4; i++) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 7e2af5f4f39b..28039290655c 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -42,13 +42,15 @@ #include "i915_selftest.h" #include "i915_timeline.h" -#define I915_GTT_PAGE_SIZE_4K BIT(12) -#define I915_GTT_PAGE_SIZE_64K BIT(16) -#define I915_GTT_PAGE_SIZE_2M BIT(21) +#define I915_GTT_PAGE_SIZE_4K BIT_ULL(12) +#define I915_GTT_PAGE_SIZE_64K BIT_ULL(16) +#define I915_GTT_PAGE_SIZE_2M BIT_ULL(21) #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M +#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE + #define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE #define I915_FENCE_REG_NONE -1 @@ -659,20 +661,20 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, u64 start, u64 end, unsigned int flags); /* Flags used by pin/bind&friends. */ -#define PIN_NONBLOCK BIT(0) -#define PIN_MAPPABLE BIT(1) -#define PIN_ZONE_4G BIT(2) -#define PIN_NONFAULT BIT(3) -#define PIN_NOEVICT BIT(4) - -#define PIN_MBZ BIT(5) /* I915_VMA_PIN_OVERFLOW */ -#define PIN_GLOBAL BIT(6) /* I915_VMA_GLOBAL_BIND */ -#define PIN_USER BIT(7) /* I915_VMA_LOCAL_BIND */ -#define PIN_UPDATE BIT(8) - -#define PIN_HIGH BIT(9) -#define PIN_OFFSET_BIAS BIT(10) -#define PIN_OFFSET_FIXED BIT(11) +#define PIN_NONBLOCK BIT_ULL(0) +#define PIN_MAPPABLE BIT_ULL(1) +#define PIN_ZONE_4G BIT_ULL(2) +#define PIN_NONFAULT BIT_ULL(3) +#define PIN_NOEVICT BIT_ULL(4) + +#define PIN_MBZ BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */ +#define PIN_GLOBAL BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */ +#define PIN_USER BIT_ULL(7) /* I915_VMA_LOCAL_BIND */ +#define PIN_UPDATE BIT_ULL(8) + +#define PIN_HIGH BIT_ULL(9) +#define PIN_OFFSET_BIAS BIT_ULL(10) +#define PIN_OFFSET_FIXED BIT_ULL(11) #define PIN_OFFSET_MASK (-I915_GTT_PAGE_SIZE) #endif diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7c491ea3d052..e31c27e45734 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2095,8 +2095,12 @@ enum i915_power_well_id { /* ICL PHY DFLEX registers */ #define PORT_TX_DFLEXDPMLE1 _MMIO(0x1638C0) -#define DFLEXDPMLE1_DPMLETC_MASK(n) (0xf << (4 * (n))) -#define DFLEXDPMLE1_DPMLETC(n, x) ((x) << (4 * (n))) +#define DFLEXDPMLE1_DPMLETC_MASK(tc_port) (0xf << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML0(tc_port) (1 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML1_0(tc_port) (3 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3(tc_port) (8 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_2(tc_port) (12 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_0(tc_port) (15 << (4 * (tc_port))) /* BXT PHY Ref registers */ #define _PORT_REF_DW3_A 0x16218C @@ -4593,12 +4597,12 @@ enum { #define DRM_DIP_ENABLE (1 << 28) #define PSR_VSC_BIT_7_SET (1 << 27) -#define VSC_SELECT_MASK (0x3 << 26) -#define VSC_SELECT_SHIFT 26 -#define VSC_DIP_HW_HEA_DATA (0 << 26) -#define VSC_DIP_HW_HEA_SW_DATA (1 << 26) -#define VSC_DIP_HW_DATA_SW_HEA (2 << 26) -#define VSC_DIP_SW_HEA_DATA (3 << 26) +#define VSC_SELECT_MASK (0x3 << 25) +#define VSC_SELECT_SHIFT 25 +#define VSC_DIP_HW_HEA_DATA (0 << 25) +#define VSC_DIP_HW_HEA_SW_DATA (1 << 25) +#define VSC_DIP_HW_DATA_SW_HEA (2 << 25) +#define VSC_DIP_SW_HEA_DATA (3 << 25) #define VDIP_ENABLE_PPS (1 << 24) /* Panel power sequencing */ diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 769f3f586661..ee3ca2de983b 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -144,6 +144,9 @@ static const struct { /* HDMI N/CTS table */ #define TMDS_297M 297000 #define TMDS_296M 296703 +#define TMDS_594M 594000 +#define TMDS_593M 593407 + static const struct { int sample_rate; int clock; @@ -164,6 +167,20 @@ static const struct { { 176400, TMDS_297M, 18816, 247500 }, { 192000, TMDS_296M, 23296, 281250 }, { 192000, TMDS_297M, 20480, 247500 }, + { 44100, TMDS_593M, 8918, 937500 }, + { 44100, TMDS_594M, 9408, 990000 }, + { 48000, TMDS_593M, 5824, 562500 }, + { 48000, TMDS_594M, 6144, 594000 }, + { 32000, TMDS_593M, 5824, 843750 }, + { 32000, TMDS_594M, 3072, 445500 }, + { 88200, TMDS_593M, 17836, 937500 }, + { 88200, TMDS_594M, 18816, 990000 }, + { 96000, TMDS_593M, 11648, 562500 }, + { 96000, TMDS_594M, 12288, 594000 }, + { 176400, TMDS_593M, 35672, 937500 }, + { 176400, TMDS_594M, 37632, 990000 }, + { 192000, TMDS_593M, 23296, 562500 }, + { 192000, TMDS_594M, 24576, 594000 }, }; /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 29075c763428..8d74276029e6 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2138,16 +2138,8 @@ void intel_set_cdclk(struct drm_i915_private *dev_priv, static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv, int pixel_rate) { - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return DIV_ROUND_UP(pixel_rate, 2); - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk - * as a temporary workaround. Use a higher cdclk instead. (Note that - * intel_compute_max_dotclk() limits the max pixel clock to 99% of max - * cdclk.) - */ - return DIV_ROUND_UP(pixel_rate * 100, 2 * 99); else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return pixel_rate; @@ -2543,14 +2535,8 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) { int max_cdclk_freq = dev_priv->max_cdclk_freq; - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 2 * max_cdclk_freq; - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Limiting to 99% as a temporary workaround. See - * intel_min_cdclk() for details. - */ - return 2 * max_cdclk_freq * 99 / 100; else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return max_cdclk_freq; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9741cc419e1b..23d8008a93bb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12768,17 +12768,12 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_check_cpu_fifo_underruns(dev_priv); intel_check_pch_fifo_underruns(dev_priv); - if (!new_crtc_state->active) { - /* - * Make sure we don't call initial_watermarks - * for ILK-style watermark updates. - * - * No clue what this is supposed to achieve. - */ - if (INTEL_GEN(dev_priv) >= 9) - dev_priv->display.initial_watermarks(intel_state, - to_intel_crtc_state(new_crtc_state)); - } + /* FIXME unify this for all platforms */ + if (!new_crtc_state->active && + !HAS_GMCH_DISPLAY(dev_priv) && + dev_priv->display.initial_watermarks) + dev_priv->display.initial_watermarks(intel_state, + to_intel_crtc_state(new_crtc_state)); } } @@ -14646,7 +14641,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, fb->height < SKL_MIN_YUV_420_SRC_H || (fb->width % 4) != 0 || (fb->height % 4) != 0)) { DRM_DEBUG_KMS("src dimensions not correct for NV12\n"); - return -EINVAL; + goto err; } for (i = 0; i < fb->format->num_planes; i++) { diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index cdf19553ffac..5d5336fbe7b0 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -297,8 +297,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); irq_free_desc(dev_priv->lpe_audio.irq); -} + dev_priv->lpe_audio.irq = -1; + dev_priv->lpe_audio.platdev = NULL; +} /** * intel_lpe_audio_notify() - notify lpe audio event diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1db9b8328275..245f0022bcfd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv, * any underrun. If not able to get Dimm info assume 16GB dimm * to avoid any underrun. */ - if (!dev_priv->dram_info.valid_dimm || - dev_priv->dram_info.is_16gb_dimm) + if (dev_priv->dram_info.is_16gb_dimm) wm[0] += 1; } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 8d03f64eabd7..5c22f2c8d4cf 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -551,7 +551,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) { - pr_err("page_sizes.gtt=%u, expected %lu\n", + pr_err("page_sizes.gtt=%u, expected %llu\n", vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K); err = -EINVAL; } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 8e2e269db97e..127d81513671 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1337,7 +1337,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1386,7 +1386,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1430,7 +1430,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != offset || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, offset, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index af7dcb6da351..e7eb0d1e17be 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -75,7 +75,7 @@ static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -88,7 +88,7 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index bf068da6b12e..f4a22689eb54 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -135,7 +135,7 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -148,7 +148,7 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index c78cd35a1294..f949287d926c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -491,7 +491,8 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, sun4i_tcon0_mode_set_common(tcon, mode); /* Set dithering if needed */ - sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); + if (tcon->panel) + sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); /* Adjust clock delay */ clk_delay = sun4i_tcon_get_clk_delay(mode, 0); @@ -555,7 +556,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, * Following code is a way to avoid quirks all around TCON * and DOTCLOCK drivers. */ - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { struct drm_panel *panel = tcon->panel; struct drm_connector *connector = panel->connector; struct drm_display_info display_info = connector->display_info; diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index cf2a18571d48..a132c37d7334 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -380,6 +380,9 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, mutex_unlock(&vgasr_mutex); return -EINVAL; } + /* notify if GPU has been already bound */ + if (ops->gpu_bound) + ops->gpu_bound(pdev, id); } mutex_unlock(&vgasr_mutex); diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index aec253b44156..3cd7229b6e54 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -660,6 +660,20 @@ exit: return ret; } +static int alps_sp_open(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + return hid_hw_open(hid); +} + +static void alps_sp_close(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + hid_hw_close(hid); +} + static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) { struct alps_dev *data = hid_get_drvdata(hdev); @@ -733,6 +747,10 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) input2->id.version = input->id.version; input2->dev.parent = input->dev.parent; + input_set_drvdata(input2, hdev); + input2->open = alps_sp_open; + input2->close = alps_sp_close; + __set_bit(EV_KEY, input2->evbit); data->sp_btn_cnt = (data->sp_btn_info & 0x0F); for (i = 0; i < data->sp_btn_cnt; i++) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index dc6d6477e961..a1fa2fc8c9b5 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -359,6 +359,9 @@ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev) u32 value; int ret; + if (!IS_ENABLED(CONFIG_ASUS_WMI)) + return false; + ret = asus_wmi_evaluate_method(ASUS_WMI_METHODID_DSTS2, ASUS_WMI_DEVID_KBD_BACKLIGHT, 0, &value); hid_dbg(hdev, "WMI backlight check: rc %d value %x", ret, value); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index f63489c882bb..c0d668944dbe 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -927,6 +927,9 @@ #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003 0x3003 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008 0x3008 +#define I2C_VENDOR_ID_RAYDIUM 0x2386 +#define I2C_PRODUCT_ID_RAYDIUM_4B33 0x4b33 + #define USB_VENDOR_ID_RAZER 0x1532 #define USB_DEVICE_ID_RAZER_BLADE_14 0x011D diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 52c3b01917e7..8237dd86fb17 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -107,7 +107,6 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 4aab96cf0818..3cde7c1b9c33 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -49,6 +49,7 @@ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) #define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2) +#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP BIT(3) /* flags */ #define I2C_HID_STARTED 0 @@ -158,6 +159,8 @@ struct i2c_hid { bool irq_wake_enabled; struct mutex reset_lock; + + unsigned long sleep_delay; }; static const struct i2c_hid_quirks { @@ -172,6 +175,8 @@ static const struct i2c_hid_quirks { { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET | I2C_HID_QUIRK_NO_RUNTIME_PM }, + { I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33, + I2C_HID_QUIRK_DELAY_AFTER_SLEEP }, { 0, 0 } }; @@ -387,6 +392,7 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) { struct i2c_hid *ihid = i2c_get_clientdata(client); int ret; + unsigned long now, delay; i2c_hid_dbg(ihid, "%s\n", __func__); @@ -404,9 +410,22 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) goto set_pwr_exit; } + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_ON) { + now = jiffies; + if (time_after(ihid->sleep_delay, now)) { + delay = jiffies_to_usecs(ihid->sleep_delay - now); + usleep_range(delay, delay + 1); + } + } + ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state, 0, NULL, 0, NULL, 0); + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_SLEEP) + ihid->sleep_delay = jiffies + msecs_to_jiffies(20); + if (ret) dev_err(&client->dev, "failed to change power setting.\n"); diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index cac262a912c1..89f2976f9c53 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -331,6 +331,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + .ident = "Direkt-Tek DTLAPY133-1", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY133-1"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Mediacom Flexbook Edge 11", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"), diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 23872d08308c..a746017fac17 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -512,14 +512,24 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, if (cmd == HIDIOCGCOLLECTIONINDEX) { if (uref->usage_index >= field->maxusage) goto inval; + uref->usage_index = + array_index_nospec(uref->usage_index, + field->maxusage); } else if (uref->usage_index >= field->report_count) goto inval; } - if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) && - (uref_multi->num_values > HID_MAX_MULTI_USAGES || - uref->usage_index + uref_multi->num_values > field->report_count)) - goto inval; + if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { + if (uref_multi->num_values > HID_MAX_MULTI_USAGES || + uref->usage_index + uref_multi->num_values > + field->report_count) + goto inval; + + uref->usage_index = + array_index_nospec(uref->usage_index, + field->report_count - + uref_multi->num_values); + } switch (cmd) { case HIDIOCGUSAGE: diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 975c95169884..84f61cec6319 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -649,8 +649,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, if (info[i]->config[j] & HWMON_T_INPUT) { err = hwmon_thermal_add_sensor(dev, hwdev, j); - if (err) - goto free_device; + if (err) { + device_unregister(hdev); + goto ida_remove; + } } } } @@ -658,8 +660,6 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; -free_device: - device_unregister(hdev); free_hwmon: kfree(hwdev); ida_remove: diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c index 0ccca87f5271..293dd1c6c7b3 100644 --- a/drivers/hwmon/ibmpowernv.c +++ b/drivers/hwmon/ibmpowernv.c @@ -181,7 +181,7 @@ static ssize_t show_label(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%s\n", sdata->label); } -static int __init get_logical_cpu(int hwcpu) +static int get_logical_cpu(int hwcpu) { int cpu; @@ -192,9 +192,8 @@ static int __init get_logical_cpu(int hwcpu) return -ENOENT; } -static void __init make_sensor_label(struct device_node *np, - struct sensor_data *sdata, - const char *label) +static void make_sensor_label(struct device_node *np, + struct sensor_data *sdata, const char *label) { u32 id; size_t n; diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 56ccb1ea7da5..f2c681971201 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -224,6 +224,15 @@ config I2C_NFORCE2_S4985 This driver can also be built as a module. If so, the module will be called i2c-nforce2-s4985. +config I2C_NVIDIA_GPU + tristate "NVIDIA GPU I2C controller" + depends on PCI + help + If you say yes to this option, support will be included for the + NVIDIA GPU I2C controller which is used to communicate with the GPU's + Type-C controller. This driver can also be built as a module called + i2c-nvidia-gpu. + config I2C_SIS5595 tristate "SiS 5595" depends on PCI @@ -752,7 +761,7 @@ config I2C_OCORES config I2C_OMAP tristate "OMAP I2C adapter" - depends on ARCH_OMAP + depends on ARCH_OMAP || ARCH_K3 default y if MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes to this option, support will be included for the diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 18b26af82b1c..5f0cb6915969 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_I2C_ISCH) += i2c-isch.o obj-$(CONFIG_I2C_ISMT) += i2c-ismt.o obj-$(CONFIG_I2C_NFORCE2) += i2c-nforce2.o obj-$(CONFIG_I2C_NFORCE2_S4985) += i2c-nforce2-s4985.o +obj-$(CONFIG_I2C_NVIDIA_GPU) += i2c-nvidia-gpu.o obj-$(CONFIG_I2C_PIIX4) += i2c-piix4.o obj-$(CONFIG_I2C_SIS5595) += i2c-sis5595.o obj-$(CONFIG_I2C_SIS630) += i2c-sis630.o diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c new file mode 100644 index 000000000000..8822357bca0c --- /dev/null +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Nvidia GPU I2C controller Driver + * + * Copyright (C) 2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <ajayg@nvidia.com> + */ +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> + +#include <asm/unaligned.h> + +/* I2C definitions */ +#define I2C_MST_CNTL 0x00 +#define I2C_MST_CNTL_GEN_START BIT(0) +#define I2C_MST_CNTL_GEN_STOP BIT(1) +#define I2C_MST_CNTL_CMD_READ (1 << 2) +#define I2C_MST_CNTL_CMD_WRITE (2 << 2) +#define I2C_MST_CNTL_BURST_SIZE_SHIFT 6 +#define I2C_MST_CNTL_GEN_NACK BIT(28) +#define I2C_MST_CNTL_STATUS GENMASK(30, 29) +#define I2C_MST_CNTL_STATUS_OKAY (0 << 29) +#define I2C_MST_CNTL_STATUS_NO_ACK (1 << 29) +#define I2C_MST_CNTL_STATUS_TIMEOUT (2 << 29) +#define I2C_MST_CNTL_STATUS_BUS_BUSY (3 << 29) +#define I2C_MST_CNTL_CYCLE_TRIGGER BIT(31) + +#define I2C_MST_ADDR 0x04 + +#define I2C_MST_I2C0_TIMING 0x08 +#define I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ 0x10e +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT 16 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX 255 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CHECK BIT(24) + +#define I2C_MST_DATA 0x0c + +#define I2C_MST_HYBRID_PADCTL 0x20 +#define I2C_MST_HYBRID_PADCTL_MODE_I2C BIT(0) +#define I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV BIT(14) +#define I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV BIT(15) + +struct gpu_i2c_dev { + struct device *dev; + void __iomem *regs; + struct i2c_adapter adapter; + struct i2c_board_info *gpu_ccgx_ucsi; +}; + +static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd) +{ + u32 val; + + /* enable I2C */ + val = readl(i2cd->regs + I2C_MST_HYBRID_PADCTL); + val |= I2C_MST_HYBRID_PADCTL_MODE_I2C | + I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV | + I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV; + writel(val, i2cd->regs + I2C_MST_HYBRID_PADCTL); + + /* enable 100KHZ mode */ + val = I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ; + val |= (I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX + << I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT); + val |= I2C_MST_I2C0_TIMING_TIMEOUT_CHECK; + writel(val, i2cd->regs + I2C_MST_I2C0_TIMING); +} + +static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd) +{ + unsigned long target = jiffies + msecs_to_jiffies(1000); + u32 val; + + do { + val = readl(i2cd->regs + I2C_MST_CNTL); + if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER)) + break; + if ((val & I2C_MST_CNTL_STATUS) != + I2C_MST_CNTL_STATUS_BUS_BUSY) + break; + usleep_range(500, 600); + } while (time_is_after_jiffies(target)); + + if (time_is_before_jiffies(target)) { + dev_err(i2cd->dev, "i2c timeout error %x\n", val); + return -ETIME; + } + + val = readl(i2cd->regs + I2C_MST_CNTL); + switch (val & I2C_MST_CNTL_STATUS) { + case I2C_MST_CNTL_STATUS_OKAY: + return 0; + case I2C_MST_CNTL_STATUS_NO_ACK: + return -EIO; + case I2C_MST_CNTL_STATUS_TIMEOUT: + return -ETIME; + default: + return 0; + } +} + +static int gpu_i2c_read(struct gpu_i2c_dev *i2cd, u8 *data, u16 len) +{ + int status; + u32 val; + + val = I2C_MST_CNTL_GEN_START | I2C_MST_CNTL_CMD_READ | + (len << I2C_MST_CNTL_BURST_SIZE_SHIFT) | + I2C_MST_CNTL_CYCLE_TRIGGER | I2C_MST_CNTL_GEN_NACK; + writel(val, i2cd->regs + I2C_MST_CNTL); + + status = gpu_i2c_check_status(i2cd); + if (status < 0) + return status; + + val = readl(i2cd->regs + I2C_MST_DATA); + switch (len) { + case 1: + data[0] = val; + break; + case 2: + put_unaligned_be16(val, data); + break; + case 3: + put_unaligned_be16(val >> 8, data); + data[2] = val; + break; + case 4: + put_unaligned_be32(val, data); + break; + default: + break; + } + return status; +} + +static int gpu_i2c_start(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_START, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_stop(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_STOP, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_write(struct gpu_i2c_dev *i2cd, u8 data) +{ + u32 val; + + writel(data, i2cd->regs + I2C_MST_DATA); + + val = I2C_MST_CNTL_CMD_WRITE | (1 << I2C_MST_CNTL_BURST_SIZE_SHIFT); + writel(val, i2cd->regs + I2C_MST_CNTL); + + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_master_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct gpu_i2c_dev *i2cd = i2c_get_adapdata(adap); + int status, status2; + int i, j; + + /* + * The controller supports maximum 4 byte read due to known + * limitation of sending STOP after every read. + */ + for (i = 0; i < num; i++) { + if (msgs[i].flags & I2C_M_RD) { + /* program client address before starting read */ + writel(msgs[i].addr, i2cd->regs + I2C_MST_ADDR); + /* gpu_i2c_read has implicit start */ + status = gpu_i2c_read(i2cd, msgs[i].buf, msgs[i].len); + if (status < 0) + goto stop; + } else { + u8 addr = i2c_8bit_addr_from_msg(msgs + i); + + status = gpu_i2c_start(i2cd); + if (status < 0) { + if (i == 0) + return status; + goto stop; + } + + status = gpu_i2c_write(i2cd, addr); + if (status < 0) + goto stop; + + for (j = 0; j < msgs[i].len; j++) { + status = gpu_i2c_write(i2cd, msgs[i].buf[j]); + if (status < 0) + goto stop; + } + } + } + status = gpu_i2c_stop(i2cd); + if (status < 0) + return status; + + return i; +stop: + status2 = gpu_i2c_stop(i2cd); + if (status2 < 0) + dev_err(i2cd->dev, "i2c stop failed %d\n", status2); + return status; +} + +static const struct i2c_adapter_quirks gpu_i2c_quirks = { + .max_read_len = 4, + .flags = I2C_AQ_COMB_WRITE_THEN_READ, +}; + +static u32 gpu_i2c_functionality(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm gpu_i2c_algorithm = { + .master_xfer = gpu_i2c_master_xfer, + .functionality = gpu_i2c_functionality, +}; + +/* + * This driver is for Nvidia GPU cards with USB Type-C interface. + * We want to identify the cards using vendor ID and class code only + * to avoid dependency of adding product id for any new card which + * requires this driver. + * Currently there is no class code defined for UCSI device over PCI + * so using UNKNOWN class for now and it will be updated when UCSI + * over PCI gets a class code. + * There is no other NVIDIA cards with UNKNOWN class code. Even if the + * driver gets loaded for an undesired card then eventually i2c_read() + * (initiated from UCSI i2c_client) will timeout or UCSI commands will + * timeout. + */ +#define PCI_CLASS_SERIAL_UNKNOWN 0x0c80 +static const struct pci_device_id gpu_i2c_ids[] = { + { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_SERIAL_UNKNOWN << 8, 0xffffff00}, + { } +}; +MODULE_DEVICE_TABLE(pci, gpu_i2c_ids); + +static int gpu_populate_client(struct gpu_i2c_dev *i2cd, int irq) +{ + struct i2c_client *ccgx_client; + + i2cd->gpu_ccgx_ucsi = devm_kzalloc(i2cd->dev, + sizeof(*i2cd->gpu_ccgx_ucsi), + GFP_KERNEL); + if (!i2cd->gpu_ccgx_ucsi) + return -ENOMEM; + + strlcpy(i2cd->gpu_ccgx_ucsi->type, "ccgx-ucsi", + sizeof(i2cd->gpu_ccgx_ucsi->type)); + i2cd->gpu_ccgx_ucsi->addr = 0x8; + i2cd->gpu_ccgx_ucsi->irq = irq; + ccgx_client = i2c_new_device(&i2cd->adapter, i2cd->gpu_ccgx_ucsi); + if (!ccgx_client) + return -ENODEV; + + return 0; +} + +static int gpu_i2c_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct gpu_i2c_dev *i2cd; + int status; + + i2cd = devm_kzalloc(&pdev->dev, sizeof(*i2cd), GFP_KERNEL); + if (!i2cd) + return -ENOMEM; + + i2cd->dev = &pdev->dev; + dev_set_drvdata(&pdev->dev, i2cd); + + status = pcim_enable_device(pdev); + if (status < 0) { + dev_err(&pdev->dev, "pcim_enable_device failed %d\n", status); + return status; + } + + pci_set_master(pdev); + + i2cd->regs = pcim_iomap(pdev, 0, 0); + if (!i2cd->regs) { + dev_err(&pdev->dev, "pcim_iomap failed\n"); + return -ENOMEM; + } + + status = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (status < 0) { + dev_err(&pdev->dev, "pci_alloc_irq_vectors err %d\n", status); + return status; + } + + gpu_enable_i2c_bus(i2cd); + + i2c_set_adapdata(&i2cd->adapter, i2cd); + i2cd->adapter.owner = THIS_MODULE; + strlcpy(i2cd->adapter.name, "NVIDIA GPU I2C adapter", + sizeof(i2cd->adapter.name)); + i2cd->adapter.algo = &gpu_i2c_algorithm; + i2cd->adapter.quirks = &gpu_i2c_quirks; + i2cd->adapter.dev.parent = &pdev->dev; + status = i2c_add_adapter(&i2cd->adapter); + if (status < 0) + goto free_irq_vectors; + + status = gpu_populate_client(i2cd, pdev->irq); + if (status < 0) { + dev_err(&pdev->dev, "gpu_populate_client failed %d\n", status); + goto del_adapter; + } + + return 0; + +del_adapter: + i2c_del_adapter(&i2cd->adapter); +free_irq_vectors: + pci_free_irq_vectors(pdev); + return status; +} + +static void gpu_i2c_remove(struct pci_dev *pdev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(&pdev->dev); + + i2c_del_adapter(&i2cd->adapter); + pci_free_irq_vectors(pdev); +} + +static int gpu_i2c_resume(struct device *dev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(dev); + + gpu_enable_i2c_bus(i2cd); + return 0; +} + +static UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); + +static struct pci_driver gpu_i2c_driver = { + .name = "nvidia-gpu", + .id_table = gpu_i2c_ids, + .probe = gpu_i2c_probe, + .remove = gpu_i2c_remove, + .driver = { + .pm = &gpu_i2c_driver_pm, + }, +}; + +module_pci_driver(gpu_i2c_driver); + +MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>"); +MODULE_DESCRIPTION("Nvidia GPU I2C controller Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 527f55c8c4c7..db075bc0d952 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -571,18 +571,19 @@ static int geni_i2c_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "i2c fifo/se-dma mode. fifo depth:%d\n", tx_depth); - ret = i2c_add_adapter(&gi2c->adap); - if (ret) { - dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); - return ret; - } - gi2c->suspended = 1; pm_runtime_set_suspended(gi2c->se.dev); pm_runtime_set_autosuspend_delay(gi2c->se.dev, I2C_AUTO_SUSPEND_DELAY); pm_runtime_use_autosuspend(gi2c->se.dev); pm_runtime_enable(gi2c->se.dev); + ret = i2c_add_adapter(&gi2c->adap); + if (ret) { + dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); + pm_runtime_disable(gi2c->se.dev); + return ret; + } + return 0; } @@ -590,8 +591,8 @@ static int geni_i2c_remove(struct platform_device *pdev) { struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); - pm_runtime_disable(gi2c->se.dev); i2c_del_adapter(&gi2c->adap); + pm_runtime_disable(gi2c->se.dev); return 0; } diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index ce7acd115dd8..1870cf87afe1 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -75,8 +75,6 @@ static void pattern_trig_timer_function(struct timer_list *t) { struct pattern_trig_data *data = from_timer(data, t, timer); - mutex_lock(&data->lock); - for (;;) { if (!data->is_indefinite && !data->repeat) break; @@ -87,9 +85,10 @@ static void pattern_trig_timer_function(struct timer_list *t) data->curr->brightness); mod_timer(&data->timer, jiffies + msecs_to_jiffies(data->curr->delta_t)); - - /* Skip the tuple with zero duration */ - pattern_trig_update_patterns(data); + if (!data->next->delta_t) { + /* Skip the tuple with zero duration */ + pattern_trig_update_patterns(data); + } /* Select next tuple */ pattern_trig_update_patterns(data); } else { @@ -116,8 +115,6 @@ static void pattern_trig_timer_function(struct timer_list *t) break; } - - mutex_unlock(&data->lock); } static int pattern_trig_start_pattern(struct led_classdev *led_cdev) @@ -176,14 +173,10 @@ static ssize_t repeat_store(struct device *dev, struct device_attribute *attr, if (res < -1 || res == 0) return -EINVAL; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); @@ -234,14 +227,10 @@ static ssize_t pattern_trig_store_patterns(struct led_classdev *led_cdev, struct pattern_trig_data *data = led_cdev->trigger_data; int ccount, cr, offset = 0, err = 0; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index e514d57a0419..aa983422aa97 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -207,7 +207,7 @@ comment "Disk-On-Chip Device Drivers" config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH - select BCH_CONST_PARAMS + select BCH_CONST_PARAMS if !MTD_NAND_BCH select BITREVERSE help This provides an MTD device driver for the M-Systems DiskOnChip diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c index 784c6e1a0391..fd5fe12d7461 100644 --- a/drivers/mtd/maps/sa1100-flash.c +++ b/drivers/mtd/maps/sa1100-flash.c @@ -221,7 +221,14 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = info->subdev[0].mtd; ret = 0; } else if (info->num_subdev > 1) { - struct mtd_info *cdev[nr]; + struct mtd_info **cdev; + + cdev = kmalloc_array(nr, sizeof(*cdev), GFP_KERNEL); + if (!cdev) { + ret = -ENOMEM; + goto err; + } + /* * We detected multiple devices. Concatenate them together. */ @@ -230,6 +237,7 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = mtd_concat_create(cdev, info->num_subdev, plat->name); + kfree(cdev); if (info->mtd == NULL) { ret = -ENXIO; goto err; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 05bd0779fe9b..71050a0b31df 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -590,7 +590,6 @@ retry: /** * panic_nand_wait - [GENERIC] wait until the command is done - * @mtd: MTD device structure * @chip: NAND chip structure * @timeo: timeout * diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index e24db817154e..d846428ef038 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -996,7 +996,7 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf, err_unmap: dma_unmap_single(nor->dev, dma_dst, len, DMA_FROM_DEVICE); - return 0; + return ret; } static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 9407ca5f9443..3e54e31889c7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -3250,12 +3250,14 @@ static int spi_nor_init_params(struct spi_nor *nor, memcpy(&sfdp_params, params, sizeof(sfdp_params)); memcpy(&prev_map, &nor->erase_map, sizeof(prev_map)); - if (spi_nor_parse_sfdp(nor, &sfdp_params)) + if (spi_nor_parse_sfdp(nor, &sfdp_params)) { + nor->addr_width = 0; /* restore previous erase map */ memcpy(&nor->erase_map, &prev_map, sizeof(nor->erase_map)); - else + } else { memcpy(params, &sfdp_params, sizeof(*params)); + } } return 0; diff --git a/drivers/mtd/ubi/attach.c b/drivers/mtd/ubi/attach.c index 93ceea4f27d5..e294d3986ba9 100644 --- a/drivers/mtd/ubi/attach.c +++ b/drivers/mtd/ubi/attach.c @@ -1072,6 +1072,7 @@ static int scan_peb(struct ubi_device *ubi, struct ubi_attach_info *ai, * be a result of power cut during erasure. */ ai->maybe_bad_peb_count += 1; + /* fall through */ case UBI_IO_BAD_HDR: /* * If we're facing a bad VID header we have to drop *all* diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index d2a726654ff1..a4e3454133a4 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1334,8 +1334,10 @@ static int bytes_str_to_int(const char *str) switch (*endp) { case 'G': result *= 1024; + /* fall through */ case 'M': result *= 1024; + /* fall through */ case 'K': result *= 1024; if (endp[1] == 'i' && endp[2] == 'B') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ffa37adb7681..333387f1f1fe 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3112,13 +3112,13 @@ static int bond_slave_netdev_event(unsigned long event, case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave - * in weird state. So mark it as link-down for the time + * in weird state. So mark it as link-fail for the time * being and let link-monitoring (miimon) set it right when * correct speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) - slave->link = BOND_LINK_DOWN; + slave->link = BOND_LINK_FAIL; if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 54e0ca6ed730..86b6464b4525 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1117,11 +1117,6 @@ static int ksz_switch_init(struct ksz_device *dev) { int i; - mutex_init(&dev->reg_mutex); - mutex_init(&dev->stats_mutex); - mutex_init(&dev->alu_mutex); - mutex_init(&dev->vlan_mutex); - dev->ds->ops = &ksz_switch_ops; for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) { @@ -1206,6 +1201,11 @@ int ksz_switch_register(struct ksz_device *dev) if (dev->pdata) dev->chip_id = dev->pdata->chip_id; + mutex_init(&dev->reg_mutex); + mutex_init(&dev->stats_mutex); + mutex_init(&dev->alu_mutex); + mutex_init(&dev->vlan_mutex); + if (ksz_switch_detect(dev)) return -EINVAL; diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index 78c5de467426..9d0e74f6b089 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -140,6 +140,5 @@ struct alx_priv { }; extern const struct ethtool_ops alx_ethtool_ops; -extern const char alx_drv_name[]; #endif diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 7968c644ad86..c131cfc1b79d 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -49,7 +49,7 @@ #include "hw.h" #include "reg.h" -const char alx_drv_name[] = "alx"; +static const char alx_drv_name[] = "alx"; static void alx_free_txbuf(struct alx_tx_queue *txq, int entry) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 4122553e224b..0e2d99c737e3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1902,9 +1902,6 @@ static void bcm_sysport_netif_start(struct net_device *dev) intrl2_1_mask_clear(priv, 0xffffffff); else intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK); - - /* Last call before we start the real business */ - netif_tx_start_all_queues(dev); } static void rbuf_init(struct bcm_sysport_priv *priv) @@ -2048,6 +2045,8 @@ static int bcm_sysport_open(struct net_device *dev) bcm_sysport_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; out_clear_rx_int: @@ -2071,7 +2070,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev) struct bcm_sysport_priv *priv = netdev_priv(dev); /* stop all software from updating hardware */ - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); napi_disable(&priv->napi); cancel_work_sync(&priv->dim.dim.work); phy_stop(dev->phydev); @@ -2658,12 +2657,12 @@ static int __maybe_unused bcm_sysport_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcm_sysport_netif_stop(dev); phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Disable UniMAC RX */ umac_enable_set(priv, CMD_RX_EN, 0); @@ -2746,8 +2745,6 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) goto out_free_rx_ring; } - netif_device_attach(dev); - /* RX pipe enable */ topctrl_writel(priv, 0, RX_FLUSH_CNTL); @@ -2788,6 +2785,8 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) bcm_sysport_netif_start(dev); + netif_device_attach(dev); + return 0; out_free_rx_ring: diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 20c1681bb1af..2d6f090bf644 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct net_device *dev) umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); - netif_tx_start_all_queues(dev); bcmgenet_enable_tx_napi(priv); /* Monitor link interrupts now */ @@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; err_irq1: @@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); bcmgenet_disable_tx_napi(priv); - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); /* Disable MAC receive */ umac_enable_set(priv, CMD_RX_EN, false); @@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcmgenet_netif_stop(dev); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Prepare the device for Wake-on-LAN and switch to the slow clock */ if (device_may_wakeup(d) && priv->wolopts) { ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); @@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device *d) /* Always enable ring 16 - descriptor ring */ bcmgenet_enable_dma(priv, dma_ctrl); - netif_device_attach(dev); - if (!device_may_wakeup(d)) phy_resume(dev->phydev); @@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device *d) bcmgenet_netif_start(dev); + netif_device_attach(dev); + return 0; out_clk_disable: diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index aa5cb9834d73..494e562fe8c7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1168,14 +1168,14 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev) */ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) { - struct hclge_vport *vport = hdev->vport; - u32 i, k, qs_bitmap; - int ret; + int i; for (i = 0; i < HCLGE_BP_GRP_NUM; i++) { - qs_bitmap = 0; + u32 qs_bitmap = 0; + int k, ret; for (k = 0; k < hdev->num_alloc_vport; k++) { + struct hclge_vport *vport = &hdev->vport[k]; u16 qs_id = vport->qs_offset + tc; u8 grp, sub_grp; @@ -1185,8 +1185,6 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) HCLGE_BP_SUB_GRP_ID_S); if (i == grp) qs_bitmap |= (1 << sub_grp); - - vport++; } ret = hclge_tm_qs_bp_cfg(hdev, tc, i, qs_bitmap); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1857ee0f0871..6f5153afcab4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1006,7 +1006,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->packets++; } ring->bytes += tx_info->nr_bytes; - netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes); AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len); if (tx_info->inl) @@ -1044,7 +1043,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(ring->tx_queue); ring->queue_stopped++; } - send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue); + + send_doorbell = __netdev_tx_sent_queue(ring->tx_queue, + tx_info->nr_bytes, + skb->xmit_more); real_size = (real_size / 16) & 0x3f; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a2df12b79f8e..9bec940330a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3568,7 +3568,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) burst_size = 7; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME: - is_bytes = true; rate = 4 * 1024; burst_size = 4; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index f40f654398a0..a96364df4320 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1944,9 +1944,12 @@ int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_speed_mask) { u32 transceiver_type, transceiver_state; + int ret; - qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, - &transceiver_type); + ret = qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, + &transceiver_type); + if (ret) + return ret; if (qed_is_transceiver_ready(transceiver_state, transceiver_type) == false) diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c index b12023bc2cab..a5bab614ff84 100644 --- a/drivers/net/ntb_netdev.c +++ b/drivers/net/ntb_netdev.c @@ -71,7 +71,6 @@ static unsigned int tx_start = 10; static unsigned int tx_stop = 5; struct ntb_netdev { - struct list_head list; struct pci_dev *pdev; struct net_device *ndev; struct ntb_transport_qp *qp; @@ -81,8 +80,6 @@ struct ntb_netdev { #define NTB_TX_TIMEOUT_MS 1000 #define NTB_RXQ_SIZE 100 -static LIST_HEAD(dev_list); - static void ntb_netdev_event_handler(void *data, int link_is_up) { struct net_device *ndev = data; @@ -236,7 +233,7 @@ static void ntb_netdev_tx_timer(struct timer_list *t) struct net_device *ndev = dev->ndev; if (ntb_transport_tx_free_entry(dev->qp) < tx_stop) { - mod_timer(&dev->tx_timer, jiffies + msecs_to_jiffies(tx_time)); + mod_timer(&dev->tx_timer, jiffies + usecs_to_jiffies(tx_time)); } else { /* Make sure anybody stopping the queue after this sees the new * value of ntb_transport_tx_free_entry() @@ -452,7 +449,7 @@ static int ntb_netdev_probe(struct device *client_dev) if (rc) goto err1; - list_add(&dev->list, &dev_list); + dev_set_drvdata(client_dev, ndev); dev_info(&pdev->dev, "%s created\n", ndev->name); return 0; @@ -465,27 +462,8 @@ err: static void ntb_netdev_remove(struct device *client_dev) { - struct ntb_dev *ntb; - struct net_device *ndev; - struct pci_dev *pdev; - struct ntb_netdev *dev; - bool found = false; - - ntb = dev_ntb(client_dev->parent); - pdev = ntb->pdev; - - list_for_each_entry(dev, &dev_list, list) { - if (dev->pdev == pdev) { - found = true; - break; - } - } - if (!found) - return; - - list_del(&dev->list); - - ndev = dev->ndev; + struct net_device *ndev = dev_get_drvdata(client_dev); + struct ntb_netdev *dev = netdev_priv(ndev); unregister_netdev(ndev); ntb_transport_free_queue(dev->qp); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 7fc8508b5231..271e8adc39f1 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -220,7 +220,7 @@ static struct phy_driver realtek_drvs[] = { .flags = PHY_HAS_INTERRUPT, }, { .phy_id = 0x001cc816, - .name = "RTL8201F 10/100Mbps Ethernet", + .name = "RTL8201F Fast Ethernet", .phy_id_mask = 0x001fffff, .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 262e7a3c23cb..2d17f3b9bb16 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1598,6 +1598,8 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) return ret; } + cancel_delayed_work_sync(&pdata->carrier_check); + if (pdata->suspend_flags) { netdev_warn(dev->net, "error during last resume\n"); pdata->suspend_flags = 0; @@ -1840,6 +1842,11 @@ done: */ if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); + + if (ret) + schedule_delayed_work(&pdata->carrier_check, + CARRIER_CHECK_DELAY); + return ret; } diff --git a/drivers/ntb/hw/idt/Kconfig b/drivers/ntb/hw/idt/Kconfig index b360e5613b9f..f8948cf515ce 100644 --- a/drivers/ntb/hw/idt/Kconfig +++ b/drivers/ntb/hw/idt/Kconfig @@ -1,6 +1,7 @@ config NTB_IDT tristate "IDT PCIe-switch Non-Transparent Bridge support" depends on PCI + select HWMON help This driver supports NTB of cappable IDT PCIe-switches. @@ -23,9 +24,7 @@ config NTB_IDT BAR settings of peer NT-functions, the BAR setups can't be done over kernel PCI fixups. That's why the alternative pre-initialization techniques like BIOS using SMBus interface or EEPROM should be - utilized. Additionally if one needs to have temperature sensor - information printed to system log, the corresponding registers must - be initialized within BIOS/EEPROM as well. + utilized. If unsure, say N. diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c index dbe72f116017..1dede87dd54f 100644 --- a/drivers/ntb/hw/idt/ntb_hw_idt.c +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -4,7 +4,7 @@ * * GPL LICENSE SUMMARY * - * Copyright (C) 2016 T-Platforms All Rights Reserved. + * Copyright (C) 2016-2018 T-Platforms JSC All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -49,11 +49,14 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/pci.h> #include <linux/aer.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/debugfs.h> +#include <linux/hwmon.h> +#include <linux/hwmon-sysfs.h> #include <linux/ntb.h> #include "ntb_hw_idt.h" @@ -1105,9 +1108,9 @@ static struct idt_mw_cfg *idt_scan_mws(struct idt_ntb_dev *ndev, int port, } /* Allocate memory for memory window descriptors */ - ret_mws = devm_kcalloc(&ndev->ntb.pdev->dev, *mw_cnt, - sizeof(*ret_mws), GFP_KERNEL); - if (IS_ERR_OR_NULL(ret_mws)) + ret_mws = devm_kcalloc(&ndev->ntb.pdev->dev, *mw_cnt, sizeof(*ret_mws), + GFP_KERNEL); + if (!ret_mws) return ERR_PTR(-ENOMEM); /* Copy the info of detected memory windows */ @@ -1320,7 +1323,7 @@ static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, idt_nt_write(ndev, bar->ltbase, (u32)addr); idt_nt_write(ndev, bar->utbase, (u32)(addr >> 32)); /* Set the custom BAR aperture limit */ - limit = pci_resource_start(ntb->pdev, mw_cfg->bar) + size; + limit = pci_bus_address(ntb->pdev, mw_cfg->bar) + size; idt_nt_write(ndev, bar->limit, (u32)limit); if (IS_FLD_SET(BARSETUP_TYPE, data, 64)) idt_nt_write(ndev, (bar + 1)->limit, (limit >> 32)); @@ -1821,61 +1824,284 @@ static int idt_ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx, * 7. Temperature sensor operations * * IDT PCIe-switch has an embedded temperature sensor, which can be used to - * warn a user-space of possible chip overheating. Since workload temperature - * can be different on different platforms, temperature thresholds as well as - * general sensor settings must be setup in the framework of BIOS/EEPROM - * initializations. It includes the actual sensor enabling as well. + * check current chip core temperature. Since a workload environment can be + * different on different platforms, an offset and ADC/filter settings can be + * specified. Although the offset configuration is only exposed to the sysfs + * hwmon interface at the moment. The rest of the settings can be adjusted + * for instance by the BIOS/EEPROM firmware. *============================================================================= */ /* + * idt_get_deg() - convert millidegree Celsius value to just degree + * @mdegC: IN - millidegree Celsius value + * + * Return: Degree corresponding to the passed millidegree value + */ +static inline s8 idt_get_deg(long mdegC) +{ + return mdegC / 1000; +} + +/* + * idt_get_frac() - retrieve 0/0.5 fraction of the millidegree Celsius value + * @mdegC: IN - millidegree Celsius value + * + * Return: 0/0.5 degree fraction of the passed millidegree value + */ +static inline u8 idt_get_deg_frac(long mdegC) +{ + return (mdegC % 1000) >= 500 ? 5 : 0; +} + +/* + * idt_get_temp_fmt() - convert millidegree Celsius value to 0:7:1 format + * @mdegC: IN - millidegree Celsius value + * + * Return: 0:7:1 format acceptable by the IDT temperature sensor + */ +static inline u8 idt_temp_get_fmt(long mdegC) +{ + return (idt_get_deg(mdegC) << 1) | (idt_get_deg_frac(mdegC) ? 1 : 0); +} + +/* + * idt_get_temp_sval() - convert temp sample to signed millidegree Celsius + * @data: IN - shifted to LSB 8-bits temperature sample + * + * Return: signed millidegree Celsius + */ +static inline long idt_get_temp_sval(u32 data) +{ + return ((s8)data / 2) * 1000 + (data & 0x1 ? 500 : 0); +} + +/* + * idt_get_temp_sval() - convert temp sample to unsigned millidegree Celsius + * @data: IN - shifted to LSB 8-bits temperature sample + * + * Return: unsigned millidegree Celsius + */ +static inline long idt_get_temp_uval(u32 data) +{ + return (data / 2) * 1000 + (data & 0x1 ? 500 : 0); +} + +/* * idt_read_temp() - read temperature from chip sensor * @ntb: NTB device context. - * @val: OUT - integer value of temperature - * @frac: OUT - fraction + * @type: IN - type of the temperature value to read + * @val: OUT - integer value of temperature in millidegree Celsius */ -static void idt_read_temp(struct idt_ntb_dev *ndev, unsigned char *val, - unsigned char *frac) +static void idt_read_temp(struct idt_ntb_dev *ndev, + const enum idt_temp_val type, long *val) { u32 data; - /* Read the data from TEMP field of the TMPSTS register */ - data = idt_sw_read(ndev, IDT_SW_TMPSTS); - data = GET_FIELD(TMPSTS_TEMP, data); - /* TEMP field has one fractional bit and seven integer bits */ - *val = data >> 1; - *frac = ((data & 0x1) ? 5 : 0); + /* Alter the temperature field in accordance with the passed type */ + switch (type) { + case IDT_TEMP_CUR: + data = GET_FIELD(TMPSTS_TEMP, + idt_sw_read(ndev, IDT_SW_TMPSTS)); + break; + case IDT_TEMP_LOW: + data = GET_FIELD(TMPSTS_LTEMP, + idt_sw_read(ndev, IDT_SW_TMPSTS)); + break; + case IDT_TEMP_HIGH: + data = GET_FIELD(TMPSTS_HTEMP, + idt_sw_read(ndev, IDT_SW_TMPSTS)); + break; + case IDT_TEMP_OFFSET: + /* This is the only field with signed 0:7:1 format */ + data = GET_FIELD(TMPADJ_OFFSET, + idt_sw_read(ndev, IDT_SW_TMPADJ)); + *val = idt_get_temp_sval(data); + return; + default: + data = GET_FIELD(TMPSTS_TEMP, + idt_sw_read(ndev, IDT_SW_TMPSTS)); + break; + } + + /* The rest of the fields accept unsigned 0:7:1 format */ + *val = idt_get_temp_uval(data); } /* - * idt_temp_isr() - temperature sensor alarm events ISR - * @ndev: IDT NTB hardware driver descriptor - * @ntint_sts: NT-function interrupt status + * idt_write_temp() - write temperature to the chip sensor register + * @ntb: NTB device context. + * @type: IN - type of the temperature value to change + * @val: IN - integer value of temperature in millidegree Celsius + */ +static void idt_write_temp(struct idt_ntb_dev *ndev, + const enum idt_temp_val type, const long val) +{ + unsigned int reg; + u32 data; + u8 fmt; + + /* Retrieve the properly formatted temperature value */ + fmt = idt_temp_get_fmt(val); + + mutex_lock(&ndev->hwmon_mtx); + switch (type) { + case IDT_TEMP_LOW: + reg = IDT_SW_TMPALARM; + data = SET_FIELD(TMPALARM_LTEMP, idt_sw_read(ndev, reg), fmt) & + ~IDT_TMPALARM_IRQ_MASK; + break; + case IDT_TEMP_HIGH: + reg = IDT_SW_TMPALARM; + data = SET_FIELD(TMPALARM_HTEMP, idt_sw_read(ndev, reg), fmt) & + ~IDT_TMPALARM_IRQ_MASK; + break; + case IDT_TEMP_OFFSET: + reg = IDT_SW_TMPADJ; + data = SET_FIELD(TMPADJ_OFFSET, idt_sw_read(ndev, reg), fmt); + break; + default: + goto inval_spin_unlock; + } + + idt_sw_write(ndev, reg, data); + +inval_spin_unlock: + mutex_unlock(&ndev->hwmon_mtx); +} + +/* + * idt_sysfs_show_temp() - printout corresponding temperature value + * @dev: Pointer to the NTB device structure + * @da: Sensor device attribute structure + * @buf: Buffer to print temperature out * - * It handles events of temperature crossing alarm thresholds. Since reading - * of TMPALARM register clears it up, the function doesn't analyze the - * read value, instead the current temperature value just warningly printed to - * log. - * The method is called from PCIe ISR bottom-half routine. + * Return: Number of written symbols or negative error */ -static void idt_temp_isr(struct idt_ntb_dev *ndev, u32 ntint_sts) +static ssize_t idt_sysfs_show_temp(struct device *dev, + struct device_attribute *da, char *buf) { - unsigned char val, frac; + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + struct idt_ntb_dev *ndev = dev_get_drvdata(dev); + enum idt_temp_val type = attr->index; + long mdeg; - /* Read the current temperature value */ - idt_read_temp(ndev, &val, &frac); + idt_read_temp(ndev, type, &mdeg); + return sprintf(buf, "%ld\n", mdeg); +} - /* Read the temperature alarm to clean the alarm status out */ - /*(void)idt_sw_read(ndev, IDT_SW_TMPALARM);*/ +/* + * idt_sysfs_set_temp() - set corresponding temperature value + * @dev: Pointer to the NTB device structure + * @da: Sensor device attribute structure + * @buf: Buffer to print temperature out + * @count: Size of the passed buffer + * + * Return: Number of written symbols or negative error + */ +static ssize_t idt_sysfs_set_temp(struct device *dev, + struct device_attribute *da, const char *buf, + size_t count) +{ + struct sensor_device_attribute *attr = to_sensor_dev_attr(da); + struct idt_ntb_dev *ndev = dev_get_drvdata(dev); + enum idt_temp_val type = attr->index; + long mdeg; + int ret; - /* Clean the corresponding interrupt bit */ - idt_nt_write(ndev, IDT_NT_NTINTSTS, IDT_NTINTSTS_TMPSENSOR); + ret = kstrtol(buf, 10, &mdeg); + if (ret) + return ret; + + /* Clamp the passed value in accordance with the type */ + if (type == IDT_TEMP_OFFSET) + mdeg = clamp_val(mdeg, IDT_TEMP_MIN_OFFSET, + IDT_TEMP_MAX_OFFSET); + else + mdeg = clamp_val(mdeg, IDT_TEMP_MIN_MDEG, IDT_TEMP_MAX_MDEG); + + idt_write_temp(ndev, type, mdeg); + + return count; +} + +/* + * idt_sysfs_reset_hist() - reset temperature history + * @dev: Pointer to the NTB device structure + * @da: Sensor device attribute structure + * @buf: Buffer to print temperature out + * @count: Size of the passed buffer + * + * Return: Number of written symbols or negative error + */ +static ssize_t idt_sysfs_reset_hist(struct device *dev, + struct device_attribute *da, + const char *buf, size_t count) +{ + struct idt_ntb_dev *ndev = dev_get_drvdata(dev); + + /* Just set the maximal value to the lowest temperature field and + * minimal value to the highest temperature field + */ + idt_write_temp(ndev, IDT_TEMP_LOW, IDT_TEMP_MAX_MDEG); + idt_write_temp(ndev, IDT_TEMP_HIGH, IDT_TEMP_MIN_MDEG); - dev_dbg(&ndev->ntb.pdev->dev, - "Temp sensor IRQ detected %#08x", ntint_sts); + return count; +} + +/* + * Hwmon IDT sysfs attributes + */ +static SENSOR_DEVICE_ATTR(temp1_input, 0444, idt_sysfs_show_temp, NULL, + IDT_TEMP_CUR); +static SENSOR_DEVICE_ATTR(temp1_lowest, 0444, idt_sysfs_show_temp, NULL, + IDT_TEMP_LOW); +static SENSOR_DEVICE_ATTR(temp1_highest, 0444, idt_sysfs_show_temp, NULL, + IDT_TEMP_HIGH); +static SENSOR_DEVICE_ATTR(temp1_offset, 0644, idt_sysfs_show_temp, + idt_sysfs_set_temp, IDT_TEMP_OFFSET); +static DEVICE_ATTR(temp1_reset_history, 0200, NULL, idt_sysfs_reset_hist); - /* Print temperature value to log */ - dev_warn(&ndev->ntb.pdev->dev, "Temperature %hhu.%hhu", val, frac); +/* + * Hwmon IDT sysfs attributes group + */ +static struct attribute *idt_temp_attrs[] = { + &sensor_dev_attr_temp1_input.dev_attr.attr, + &sensor_dev_attr_temp1_lowest.dev_attr.attr, + &sensor_dev_attr_temp1_highest.dev_attr.attr, + &sensor_dev_attr_temp1_offset.dev_attr.attr, + &dev_attr_temp1_reset_history.attr, + NULL +}; +ATTRIBUTE_GROUPS(idt_temp); + +/* + * idt_init_temp() - initialize temperature sensor interface + * @ndev: IDT NTB hardware driver descriptor + * + * Simple sensor initializarion method is responsible for device switching + * on and resource management based hwmon interface registration. Note, that + * since the device is shared we won't disable it on remove, but leave it + * working until the system is powered off. + */ +static void idt_init_temp(struct idt_ntb_dev *ndev) +{ + struct device *hwmon; + + /* Enable sensor if it hasn't been already */ + idt_sw_write(ndev, IDT_SW_TMPCTL, 0x0); + + /* Initialize hwmon interface fields */ + mutex_init(&ndev->hwmon_mtx); + + hwmon = devm_hwmon_device_register_with_groups(&ndev->ntb.pdev->dev, + ndev->swcfg->name, ndev, idt_temp_groups); + if (IS_ERR(hwmon)) { + dev_err(&ndev->ntb.pdev->dev, "Couldn't create hwmon device"); + return; + } + + dev_dbg(&ndev->ntb.pdev->dev, "Temperature HWmon interface registered"); } /*============================================================================= @@ -1931,7 +2157,7 @@ static int idt_init_isr(struct idt_ntb_dev *ndev) goto err_free_vectors; } - /* Unmask Message/Doorbell/SE/Temperature interrupts */ + /* Unmask Message/Doorbell/SE interrupts */ ntint_mask = idt_nt_read(ndev, IDT_NT_NTINTMSK) & ~IDT_NTINTMSK_ALL; idt_nt_write(ndev, IDT_NT_NTINTMSK, ntint_mask); @@ -1946,7 +2172,6 @@ err_free_vectors: return ret; } - /* * idt_deinit_ist() - deinitialize PCIe interrupt handler * @ndev: IDT NTB hardware driver descriptor @@ -2007,12 +2232,6 @@ static irqreturn_t idt_thread_isr(int irq, void *devid) handled = true; } - /* Handle temperature sensor interrupt */ - if (ntint_sts & IDT_NTINTSTS_TMPSENSOR) { - idt_temp_isr(ndev, ntint_sts); - handled = true; - } - dev_dbg(&ndev->ntb.pdev->dev, "IDT IRQs 0x%08x handled", ntint_sts); return handled ? IRQ_HANDLED : IRQ_NONE; @@ -2123,9 +2342,9 @@ static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, size_t count, loff_t *offp) { struct idt_ntb_dev *ndev = filp->private_data; - unsigned char temp, frac, idx, pidx, cnt; + unsigned char idx, pidx, cnt; + unsigned long irqflags, mdeg; ssize_t ret = 0, off = 0; - unsigned long irqflags; enum ntb_speed speed; enum ntb_width width; char *strbuf; @@ -2274,9 +2493,10 @@ static ssize_t idt_dbgfs_info_read(struct file *filp, char __user *ubuf, off += scnprintf(strbuf + off, size - off, "\n"); /* Current temperature */ - idt_read_temp(ndev, &temp, &frac); + idt_read_temp(ndev, IDT_TEMP_CUR, &mdeg); off += scnprintf(strbuf + off, size - off, - "Switch temperature\t\t- %hhu.%hhuC\n", temp, frac); + "Switch temperature\t\t- %hhd.%hhuC\n", + idt_get_deg(mdeg), idt_get_deg_frac(mdeg)); /* Copy the buffer to the User Space */ ret = simple_read_from_buffer(ubuf, count, offp, strbuf, off); @@ -2390,7 +2610,7 @@ static struct idt_ntb_dev *idt_create_dev(struct pci_dev *pdev, /* Allocate memory for the IDT PCIe-device descriptor */ ndev = devm_kzalloc(&pdev->dev, sizeof(*ndev), GFP_KERNEL); - if (IS_ERR_OR_NULL(ndev)) { + if (!ndev) { dev_err(&pdev->dev, "Memory allocation failed for descriptor"); return ERR_PTR(-ENOMEM); } @@ -2571,6 +2791,9 @@ static int idt_pci_probe(struct pci_dev *pdev, /* Initialize Messaging subsystem */ idt_init_msg(ndev); + /* Initialize hwmon interface */ + idt_init_temp(ndev); + /* Initialize IDT interrupts handler */ ret = idt_init_isr(ndev); if (ret != 0) diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.h b/drivers/ntb/hw/idt/ntb_hw_idt.h index 856fd182f6f4..2f1aa121b0cf 100644 --- a/drivers/ntb/hw/idt/ntb_hw_idt.h +++ b/drivers/ntb/hw/idt/ntb_hw_idt.h @@ -4,7 +4,7 @@ * * GPL LICENSE SUMMARY * - * Copyright (C) 2016 T-Platforms All Rights Reserved. + * Copyright (C) 2016-2018 T-Platforms JSC All Rights Reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -47,9 +47,9 @@ #include <linux/pci_ids.h> #include <linux/interrupt.h> #include <linux/spinlock.h> +#include <linux/mutex.h> #include <linux/ntb.h> - /* * Macro is used to create the struct pci_device_id that matches * the supported IDT PCIe-switches @@ -688,15 +688,14 @@ * @IDT_NTINTMSK_DBELL: Doorbell interrupt mask bit * @IDT_NTINTMSK_SEVENT: Switch Event interrupt mask bit * @IDT_NTINTMSK_TMPSENSOR: Temperature sensor interrupt mask bit - * @IDT_NTINTMSK_ALL: All the useful interrupts mask + * @IDT_NTINTMSK_ALL: NTB-related interrupts mask */ #define IDT_NTINTMSK_MSG 0x00000001U #define IDT_NTINTMSK_DBELL 0x00000002U #define IDT_NTINTMSK_SEVENT 0x00000008U #define IDT_NTINTMSK_TMPSENSOR 0x00000080U #define IDT_NTINTMSK_ALL \ - (IDT_NTINTMSK_MSG | IDT_NTINTMSK_DBELL | \ - IDT_NTINTMSK_SEVENT | IDT_NTINTMSK_TMPSENSOR) + (IDT_NTINTMSK_MSG | IDT_NTINTMSK_DBELL | IDT_NTINTMSK_SEVENT) /* * NTGSIGNAL register fields related constants @@ -886,12 +885,60 @@ #define IDT_SWPxMSGCTL_PART_FLD 4 /* + * TMPCTL register fields related constants + * @IDT_TMPCTL_LTH_MASK: Low temperature threshold field mask + * @IDT_TMPCTL_LTH_FLD: Low temperature threshold field offset + * @IDT_TMPCTL_MTH_MASK: Middle temperature threshold field mask + * @IDT_TMPCTL_MTH_FLD: Middle temperature threshold field offset + * @IDT_TMPCTL_HTH_MASK: High temperature threshold field mask + * @IDT_TMPCTL_HTH_FLD: High temperature threshold field offset + * @IDT_TMPCTL_PDOWN: Temperature sensor power down + */ +#define IDT_TMPCTL_LTH_MASK 0x000000FFU +#define IDT_TMPCTL_LTH_FLD 0 +#define IDT_TMPCTL_MTH_MASK 0x0000FF00U +#define IDT_TMPCTL_MTH_FLD 8 +#define IDT_TMPCTL_HTH_MASK 0x00FF0000U +#define IDT_TMPCTL_HTH_FLD 16 +#define IDT_TMPCTL_PDOWN 0x80000000U + +/* * TMPSTS register fields related constants * @IDT_TMPSTS_TEMP_MASK: Current temperature field mask * @IDT_TMPSTS_TEMP_FLD: Current temperature field offset + * @IDT_TMPSTS_LTEMP_MASK: Lowest temperature field mask + * @IDT_TMPSTS_LTEMP_FLD: Lowest temperature field offset + * @IDT_TMPSTS_HTEMP_MASK: Highest temperature field mask + * @IDT_TMPSTS_HTEMP_FLD: Highest temperature field offset */ #define IDT_TMPSTS_TEMP_MASK 0x000000FFU #define IDT_TMPSTS_TEMP_FLD 0 +#define IDT_TMPSTS_LTEMP_MASK 0x0000FF00U +#define IDT_TMPSTS_LTEMP_FLD 8 +#define IDT_TMPSTS_HTEMP_MASK 0x00FF0000U +#define IDT_TMPSTS_HTEMP_FLD 16 + +/* + * TMPALARM register fields related constants + * @IDT_TMPALARM_LTEMP_MASK: Lowest temperature field mask + * @IDT_TMPALARM_LTEMP_FLD: Lowest temperature field offset + * @IDT_TMPALARM_HTEMP_MASK: Highest temperature field mask + * @IDT_TMPALARM_HTEMP_FLD: Highest temperature field offset + * @IDT_TMPALARM_IRQ_MASK: Alarm IRQ status mask + */ +#define IDT_TMPALARM_LTEMP_MASK 0x0000FF00U +#define IDT_TMPALARM_LTEMP_FLD 8 +#define IDT_TMPALARM_HTEMP_MASK 0x00FF0000U +#define IDT_TMPALARM_HTEMP_FLD 16 +#define IDT_TMPALARM_IRQ_MASK 0x3F000000U + +/* + * TMPADJ register fields related constants + * @IDT_TMPADJ_OFFSET_MASK: Temperature value offset field mask + * @IDT_TMPADJ_OFFSET_FLD: Temperature value offset field offset + */ +#define IDT_TMPADJ_OFFSET_MASK 0x000000FFU +#define IDT_TMPADJ_OFFSET_FLD 0 /* * Helper macro to get/set the corresponding field value @@ -951,6 +998,32 @@ #define IDT_DIR_SIZE_ALIGN 1 /* + * IDT PCIe-switch temperature sensor value limits + * @IDT_TEMP_MIN_MDEG: Minimal integer value of temperature + * @IDT_TEMP_MAX_MDEG: Maximal integer value of temperature + * @IDT_TEMP_MIN_OFFSET:Minimal integer value of temperature offset + * @IDT_TEMP_MAX_OFFSET:Maximal integer value of temperature offset + */ +#define IDT_TEMP_MIN_MDEG 0 +#define IDT_TEMP_MAX_MDEG 127500 +#define IDT_TEMP_MIN_OFFSET -64000 +#define IDT_TEMP_MAX_OFFSET 63500 + +/* + * Temperature sensor values enumeration + * @IDT_TEMP_CUR: Current temperature + * @IDT_TEMP_LOW: Lowest historical temperature + * @IDT_TEMP_HIGH: Highest historical temperature + * @IDT_TEMP_OFFSET: Current temperature offset + */ +enum idt_temp_val { + IDT_TEMP_CUR, + IDT_TEMP_LOW, + IDT_TEMP_HIGH, + IDT_TEMP_OFFSET +}; + +/* * IDT Memory Windows type. Depending on the device settings, IDT supports * Direct Address Translation MW registers and Lookup Table registers * @IDT_MW_DIR: Direct address translation @@ -1044,6 +1117,8 @@ struct idt_ntb_peer { * @msg_mask_lock: Message mask register lock * @gasa_lock: GASA registers access lock * + * @hwmon_mtx: Temperature sensor interface update mutex + * * @dbgfs_info: DebugFS info node */ struct idt_ntb_dev { @@ -1071,6 +1146,8 @@ struct idt_ntb_dev { spinlock_t msg_mask_lock; spinlock_t gasa_lock; + struct mutex hwmon_mtx; + struct dentry *dbgfs_info; }; #define to_ndev_ntb(__ntb) container_of(__ntb, struct idt_ntb_dev, ntb) diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c index 6aa573227279..2ad263f708da 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen1.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c @@ -265,7 +265,7 @@ static inline int ndev_db_clear_mask(struct intel_ntb_dev *ndev, u64 db_bits, return 0; } -static inline int ndev_vec_mask(struct intel_ntb_dev *ndev, int db_vector) +static inline u64 ndev_vec_mask(struct intel_ntb_dev *ndev, int db_vector) { u64 shift, mask; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 939895966476..3bfdb4562408 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -194,6 +194,8 @@ struct ntb_transport_mw { void __iomem *vbase; size_t xlat_size; size_t buff_size; + size_t alloc_size; + void *alloc_addr; void *virt_addr; dma_addr_t dma_addr; }; @@ -672,13 +674,59 @@ static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw) return; ntb_mw_clear_trans(nt->ndev, PIDX, num_mw); - dma_free_coherent(&pdev->dev, mw->buff_size, - mw->virt_addr, mw->dma_addr); + dma_free_coherent(&pdev->dev, mw->alloc_size, + mw->alloc_addr, mw->dma_addr); mw->xlat_size = 0; mw->buff_size = 0; + mw->alloc_size = 0; + mw->alloc_addr = NULL; mw->virt_addr = NULL; } +static int ntb_alloc_mw_buffer(struct ntb_transport_mw *mw, + struct device *dma_dev, size_t align) +{ + dma_addr_t dma_addr; + void *alloc_addr, *virt_addr; + int rc; + + alloc_addr = dma_alloc_coherent(dma_dev, mw->alloc_size, + &dma_addr, GFP_KERNEL); + if (!alloc_addr) { + dev_err(dma_dev, "Unable to alloc MW buff of size %zu\n", + mw->alloc_size); + return -ENOMEM; + } + virt_addr = alloc_addr; + + /* + * we must ensure that the memory address allocated is BAR size + * aligned in order for the XLAT register to take the value. This + * is a requirement of the hardware. It is recommended to setup CMA + * for BAR sizes equal or greater than 4MB. + */ + if (!IS_ALIGNED(dma_addr, align)) { + if (mw->alloc_size > mw->buff_size) { + virt_addr = PTR_ALIGN(alloc_addr, align); + dma_addr = ALIGN(dma_addr, align); + } else { + rc = -ENOMEM; + goto err; + } + } + + mw->alloc_addr = alloc_addr; + mw->virt_addr = virt_addr; + mw->dma_addr = dma_addr; + + return 0; + +err: + dma_free_coherent(dma_dev, mw->alloc_size, alloc_addr, dma_addr); + + return rc; +} + static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, resource_size_t size) { @@ -710,28 +758,20 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw, /* Alloc memory for receiving data. Must be aligned */ mw->xlat_size = xlat_size; mw->buff_size = buff_size; + mw->alloc_size = buff_size; - mw->virt_addr = dma_alloc_coherent(&pdev->dev, buff_size, - &mw->dma_addr, GFP_KERNEL); - if (!mw->virt_addr) { - mw->xlat_size = 0; - mw->buff_size = 0; - dev_err(&pdev->dev, "Unable to alloc MW buff of size %zu\n", - buff_size); - return -ENOMEM; - } - - /* - * we must ensure that the memory address allocated is BAR size - * aligned in order for the XLAT register to take the value. This - * is a requirement of the hardware. It is recommended to setup CMA - * for BAR sizes equal or greater than 4MB. - */ - if (!IS_ALIGNED(mw->dma_addr, xlat_align)) { - dev_err(&pdev->dev, "DMA memory %pad is not aligned\n", - &mw->dma_addr); - ntb_free_mw(nt, num_mw); - return -ENOMEM; + rc = ntb_alloc_mw_buffer(mw, &pdev->dev, xlat_align); + if (rc) { + mw->alloc_size *= 2; + rc = ntb_alloc_mw_buffer(mw, &pdev->dev, xlat_align); + if (rc) { + dev_err(&pdev->dev, + "Unable to alloc aligned MW buff\n"); + mw->xlat_size = 0; + mw->buff_size = 0; + mw->alloc_size = 0; + return rc; + } } /* Notify HW the memory location of the receive buffer */ @@ -1278,6 +1318,7 @@ static void ntb_rx_copy_callback(void *data, case DMA_TRANS_READ_FAILED: case DMA_TRANS_WRITE_FAILED: entry->errors++; + /* fall through */ case DMA_TRANS_ABORTED: { struct ntb_transport_qp *qp = entry->qp; @@ -1533,6 +1574,7 @@ static void ntb_tx_copy_callback(void *data, case DMA_TRANS_READ_FAILED: case DMA_TRANS_WRITE_FAILED: entry->errors++; + /* fall through */ case DMA_TRANS_ABORTED: { void __iomem *offset = diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2e65be8b1387..559d567693b8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1519,8 +1519,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->ndev) nvme_nvm_update_nvm_info(ns); #ifdef CONFIG_NVME_MULTIPATH - if (ns->head->disk) + if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); + blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + } #endif } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5e3cc8c59a39..9901afd804ce 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -285,6 +285,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* set to a default value for 512 until disk is validated */ blk_queue_logical_block_size(q, 512); + blk_set_stacking_limits(&q->limits); /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f4efe289dc7b..a5f9bbce863f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -420,7 +420,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, struct pci_dev *p2p_dev; int ret; - if (!ctrl->p2p_client) + if (!ctrl->p2p_client || !ns->use_p2pmem) return; if (ns->p2p_dev) { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ddce100be57a..3f7971d3706d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -122,7 +122,6 @@ struct nvmet_rdma_device { int inline_page_count; }; -static struct workqueue_struct *nvmet_rdma_delete_wq; static bool nvmet_rdma_use_srq; module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444); MODULE_PARM_DESC(use_srq, "Use shared receive queue."); @@ -1274,12 +1273,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_rdma_delete_wq); + flush_scheduled_work(); } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); /* Destroying rdma_cm id is not needed here */ return 0; } @@ -1344,7 +1343,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } } @@ -1374,7 +1373,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); pr_err("failed to connect queue %d\n", queue->idx); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } /** @@ -1656,17 +1655,8 @@ static int __init nvmet_rdma_init(void) if (ret) goto err_ib_client; - nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); - if (!nvmet_rdma_delete_wq) { - ret = -ENOMEM; - goto err_unreg_transport; - } - return 0; -err_unreg_transport: - nvmet_unregister_transport(&nvmet_rdma_ops); err_ib_client: ib_unregister_client(&nvmet_rdma_ib_client); return ret; @@ -1674,7 +1664,6 @@ err_ib_client: static void __exit nvmet_rdma_exit(void) { - destroy_workqueue(nvmet_rdma_delete_wq); nvmet_unregister_transport(&nvmet_rdma_ops); ib_unregister_client(&nvmet_rdma_ib_client); WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list)); diff --git a/drivers/of/device.c b/drivers/of/device.c index 0f27fad9fe94..5592437bb3d1 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -149,9 +149,11 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) * set by the driver. */ mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); - dev->bus_dma_mask = mask; dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; + /* ...but only set bus mask if we found valid dma-ranges earlier */ + if (!ret) + dev->bus_dma_mask = mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 35c64a4295e0..fe6b13608e51 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -104,9 +104,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map) distance = of_read_number(matrix, 1); matrix++; + if ((nodea == nodeb && distance != LOCAL_DISTANCE) || + (nodea != nodeb && distance <= LOCAL_DISTANCE)) { + pr_err("Invalid distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + return -EINVAL; + } + numa_set_distance(nodea, nodeb, distance); - pr_debug("distance[node%d -> node%d] = %d\n", - nodea, nodeb, distance); /* Set default distance of node B->A same as A->B */ if (nodeb > nodea) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 6843bc7ee9f2..04e294d1d16d 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -87,6 +87,18 @@ struct qeth_dbf_info { #define SENSE_RESETTING_EVENT_BYTE 1 #define SENSE_RESETTING_EVENT_FLAG 0x80 +static inline u32 qeth_get_device_id(struct ccw_device *cdev) +{ + struct ccw_dev_id dev_id; + u32 id; + + ccw_device_get_id(cdev, &dev_id); + id = dev_id.devno; + id |= (u32) (dev_id.ssid << 16); + + return id; +} + /* * Common IO related definitions */ @@ -97,7 +109,8 @@ struct qeth_dbf_info { #define CARD_RDEV_ID(card) dev_name(&card->read.ccwdev->dev) #define CARD_WDEV_ID(card) dev_name(&card->write.ccwdev->dev) #define CARD_DDEV_ID(card) dev_name(&card->data.ccwdev->dev) -#define CHANNEL_ID(channel) dev_name(&channel->ccwdev->dev) +#define CCW_DEVID(cdev) (qeth_get_device_id(cdev)) +#define CARD_DEVID(card) (CCW_DEVID(CARD_RDEV(card))) /** * card stuff @@ -830,6 +843,11 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline bool qeth_netdev_is_registered(struct net_device *dev) +{ + return dev->netdev_ops != NULL; +} + static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, unsigned int elements) { @@ -973,7 +991,7 @@ int qeth_wait_for_threads(struct qeth_card *, unsigned long); int qeth_do_run_thread(struct qeth_card *, unsigned long); void qeth_clear_thread_start_bit(struct qeth_card *, unsigned long); void qeth_clear_thread_running_bit(struct qeth_card *, unsigned long); -int qeth_core_hardsetup_card(struct qeth_card *); +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok); void qeth_print_status_message(struct qeth_card *); int qeth_init_qdio_queues(struct qeth_card *); int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, @@ -1028,11 +1046,6 @@ int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); void qeth_close_dev(struct qeth_card *); -int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, - long, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *); int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long); struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, enum qeth_ipa_funcs, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 3274f13aad57..4bce5ae65a55 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -167,6 +167,8 @@ const char *qeth_get_cardname_short(struct qeth_card *card) return "OSD_1000"; case QETH_LINK_TYPE_10GBIT_ETH: return "OSD_10GIG"; + case QETH_LINK_TYPE_25GBIT_ETH: + return "OSD_25GIG"; case QETH_LINK_TYPE_LANE_ETH100: return "OSD_FE_LANE"; case QETH_LINK_TYPE_LANE_TR: @@ -554,8 +556,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) if (!iob) { dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s issue_next_read failed: no iob " - "available\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "issue_next_read on device %x failed: no iob available\n", + CARD_DEVID(card)); return -ENOMEM; } qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data); @@ -563,8 +565,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) rc = ccw_device_start(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0); if (rc) { - QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! " - "rc=%i\n", dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", + rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); card->read_or_write_problem = 1; qeth_schedule_recovery(card); @@ -613,16 +615,14 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, const char *ipa_name; int com = cmd->hdr.command; ipa_name = qeth_get_ipa_cmd_name(com); + if (rc) - QETH_DBF_MESSAGE(2, "IPA: %s(x%X) for %s/%s returned " - "x%X \"%s\"\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card), rc, - qeth_get_ipa_msg(rc)); + QETH_DBF_MESSAGE(2, "IPA: %s(%#x) for device %x returned %#x \"%s\"\n", + ipa_name, com, CARD_DEVID(card), rc, + qeth_get_ipa_msg(rc)); else - QETH_DBF_MESSAGE(5, "IPA: %s(x%X) for %s/%s succeeded\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(5, "IPA: %s(%#x) for device %x succeeded\n", + ipa_name, com, CARD_DEVID(card)); } static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card, @@ -711,7 +711,7 @@ static int qeth_check_idx_response(struct qeth_card *card, QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); if ((buffer[2] & 0xc0) == 0xc0) { - QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#02x\n", + QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); @@ -972,8 +972,8 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, QETH_CARD_TEXT(card, 2, "CGENCHK"); dev_warn(&cdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s check on device dstat=x%x, cstat=x%x\n", - dev_name(&cdev->dev), dstat, cstat); + QETH_DBF_MESSAGE(2, "check on channel %x with dstat=%#x, cstat=%#x\n", + CCW_DEVID(cdev), dstat, cstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 64, 1); return 1; @@ -1013,8 +1013,8 @@ static long qeth_check_irb_error(struct qeth_card *card, switch (PTR_ERR(irb)) { case -EIO: - QETH_DBF_MESSAGE(2, "%s i/o-error on device\n", - dev_name(&cdev->dev)); + QETH_DBF_MESSAGE(2, "i/o-error on channel %x\n", + CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); break; @@ -1031,8 +1031,8 @@ static long qeth_check_irb_error(struct qeth_card *card, } break; default: - QETH_DBF_MESSAGE(2, "%s unknown error %ld on device\n", - dev_name(&cdev->dev), PTR_ERR(irb)); + QETH_DBF_MESSAGE(2, "unknown error %ld on channel %x\n", + PTR_ERR(irb), CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT(card, 2, " rc???"); } @@ -1114,9 +1114,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, dev_warn(&channel->ccwdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s sense data available. cstat " - "0x%X dstat 0x%X\n", - dev_name(&channel->ccwdev->dev), cstat, dstat); + QETH_DBF_MESSAGE(2, "sense data available on channel %x: cstat %#X dstat %#X\n", + CCW_DEVID(channel->ccwdev), cstat, + dstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 32, 1); print_hex_dump(KERN_WARNING, "qeth: sense data ", @@ -1890,8 +1890,8 @@ static int qeth_idx_activate_channel(struct qeth_card *card, if (channel->state != CH_STATE_ACTIVATING) { dev_warn(&channel->ccwdev->dev, "The qeth device driver" " failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX activate timed out on channel %x\n", + CCW_DEVID(channel->ccwdev)); QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME); return -ETIME; } @@ -1926,17 +1926,15 @@ static void qeth_idx_write_cb(struct qeth_card *card, "The adapter is used exclusively by another " "host\n"); else - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); goto out; } memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: " - "function level mismatch (sent: 0x%x, received: " - "0x%x)\n", dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } channel->state = CH_STATE_UP; @@ -1973,9 +1971,8 @@ static void qeth_idx_read_cb(struct qeth_card *card, "insufficient authorization\n"); break; default: - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); } QETH_CARD_TEXT_(card, 2, "idxread%c", QETH_IDX_ACT_CAUSE_CODE(iob->data)); @@ -1984,10 +1981,9 @@ static void qeth_idx_read_cb(struct qeth_card *card, memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if (temp != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function " - "level mismatch (sent: 0x%x, received: 0x%x)\n", - dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } memcpy(&card->token.issuer_rm_r, @@ -2096,9 +2092,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, (addr_t) iob, 0, 0, event_timeout); spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " - "ccw_device_start rc = %i\n", - dev_name(&channel->ccwdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", + CARD_DEVID(card), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); spin_lock_irq(&card->lock); list_del_init(&reply->list); @@ -2853,8 +2848,8 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, } else { dev_warn(&card->gdev->dev, "The qeth driver ran out of channel command buffers\n"); - QETH_DBF_MESSAGE(1, "%s The qeth driver ran out of channel command buffers", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "device %x ran out of channel command buffers", + CARD_DEVID(card)); } return iob; @@ -2989,10 +2984,9 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, return 0; default: if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Unhandled " - "rc=%d\n", - dev_name(&card->gdev->dev), - cmd->hdr.return_code); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Unhandled rc=%#x\n", + CARD_DEVID(card), + cmd->hdr.return_code); return 0; } } @@ -3004,8 +2998,8 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, card->options.ipa6.supported_funcs = cmd->hdr.ipa_supported; card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; } else - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Flawed LIC detected" - "\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Flawed LIC detected\n", + CARD_DEVID(card)); return 0; } @@ -4297,10 +4291,9 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, cmd->data.setadapterparms.hdr.return_code); if (cmd->data.setadapterparms.hdr.return_code != SET_ACCESS_CTRL_RC_SUCCESS) - QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%s,%d)==%d\n", - card->gdev->dev.kobj.name, - access_ctrl_req->subcmd_code, - cmd->data.setadapterparms.hdr.return_code); + QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n", + access_ctrl_req->subcmd_code, CARD_DEVID(card), + cmd->data.setadapterparms.hdr.return_code); switch (cmd->data.setadapterparms.hdr.return_code) { case SET_ACCESS_CTRL_RC_SUCCESS: if (card->options.isolation == ISOLATION_MODE_NONE) { @@ -4312,14 +4305,14 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, } break; case SET_ACCESS_CTRL_RC_ALREADY_NOT_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already " - "deactivated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already deactivated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; case SET_ACCESS_CTRL_RC_ALREADY_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already" - " activated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already activated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; @@ -4405,10 +4398,8 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback) rc = qeth_setadpparms_set_access_ctrl(card, card->options.isolation, fallback); if (rc) { - QETH_DBF_MESSAGE(3, - "IPA(SET_ACCESS_CTRL,%s,%d) sent failed\n", - card->gdev->dev.kobj.name, - rc); + QETH_DBF_MESSAGE(3, "IPA(SET_ACCESS_CTRL(%d) on device %x: sent failed\n", + rc, CARD_DEVID(card)); rc = -EOPNOTSUPP; } } else if (card->options.isolation != ISOLATION_MODE_NONE) { @@ -4443,7 +4434,8 @@ static int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum) rc = BMCR_FULLDPLX; if ((card->info.link_type != QETH_LINK_TYPE_GBIT_ETH) && (card->info.link_type != QETH_LINK_TYPE_OSN) && - (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH)) + (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH) && + (card->info.link_type != QETH_LINK_TYPE_25GBIT_ETH)) rc |= BMCR_SPEED100; break; case MII_BMSR: /* Basic mode status register */ @@ -4634,8 +4626,8 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len, qeth_snmp_command_cb, (void *)&qinfo); if (rc) - QETH_DBF_MESSAGE(2, "SNMP command failed on %s: (0x%x)\n", - QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "SNMP command failed on device %x: (%#x)\n", + CARD_DEVID(card), rc); else { if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) rc = -EFAULT; @@ -4869,8 +4861,8 @@ static void qeth_determine_capabilities(struct qeth_card *card) rc = qeth_read_conf_data(card, (void **) &prcd, &length); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_read_conf_data on device %x returned %i\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); goto out_offline; } @@ -5086,7 +5078,7 @@ static struct ccw_driver qeth_ccw_driver = { .remove = ccwgroup_remove_ccwdev, }; -int qeth_core_hardsetup_card(struct qeth_card *card) +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok) { int retries = 3; int rc; @@ -5096,8 +5088,8 @@ int qeth_core_hardsetup_card(struct qeth_card *card) qeth_update_from_chp_desc(card); retry: if (retries < 3) - QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "Retrying to do IDX activates on device %x.\n", + CARD_DEVID(card)); rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); @@ -5161,13 +5153,20 @@ retriable: if (rc == IPA_RC_LAN_OFFLINE) { dev_warn(&card->gdev->dev, "The LAN is offline\n"); - netif_carrier_off(card->dev); + *carrier_ok = false; } else { rc = -ENODEV; goto out; } } else { - netif_carrier_on(card->dev); + *carrier_ok = true; + } + + if (qeth_netdev_is_registered(card->dev)) { + if (*carrier_ok) + netif_carrier_on(card->dev); + else + netif_carrier_off(card->dev); } card->options.ipa4.supported_funcs = 0; @@ -5201,8 +5200,8 @@ retriable: out: dev_warn(&card->gdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s Initialization in hardsetup failed! rc=%d\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "Initialization for device %x failed in hardsetup! rc=%d\n", + CARD_DEVID(card), rc); return rc; } EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card); @@ -5481,11 +5480,12 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, } EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd); -int qeth_send_setassparms(struct qeth_card *card, - struct qeth_cmd_buffer *iob, __u16 len, long data, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *reply_param) +static int qeth_send_setassparms(struct qeth_card *card, + struct qeth_cmd_buffer *iob, u16 len, + long data, int (*reply_cb)(struct qeth_card *, + struct qeth_reply *, + unsigned long), + void *reply_param) { int rc; struct qeth_ipa_cmd *cmd; @@ -5501,7 +5501,6 @@ int qeth_send_setassparms(struct qeth_card *card, rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param); return rc; } -EXPORT_SYMBOL_GPL(qeth_send_setassparms); int qeth_send_simple_setassparms_prot(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, @@ -6170,8 +6169,14 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, WARN_ON_ONCE(1); } - /* fallthrough from high to low, to select all legal speeds: */ + /* partially does fall through, to also select lower speeds */ switch (maxspeed) { + case SPEED_25000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 25000baseSR_Full); + break; case SPEED_10000: ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); @@ -6254,6 +6259,10 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.speed = SPEED_10000; cmd->base.port = PORT_FIBRE; break; + case QETH_LINK_TYPE_25GBIT_ETH: + cmd->base.speed = SPEED_25000; + cmd->base.port = PORT_FIBRE; + break; default: cmd->base.speed = SPEED_10; cmd->base.port = PORT_TP; @@ -6320,6 +6329,9 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, case CARD_INFO_PORTS_10G: cmd->base.speed = SPEED_10000; break; + case CARD_INFO_PORTS_25G: + cmd->base.speed = SPEED_25000; + break; } return 0; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index e85090467afe..3e54be201b27 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -90,6 +90,7 @@ enum qeth_link_types { QETH_LINK_TYPE_GBIT_ETH = 0x03, QETH_LINK_TYPE_OSN = 0x04, QETH_LINK_TYPE_10GBIT_ETH = 0x10, + QETH_LINK_TYPE_25GBIT_ETH = 0x12, QETH_LINK_TYPE_LANE_ETH100 = 0x81, QETH_LINK_TYPE_LANE_TR = 0x82, QETH_LINK_TYPE_LANE_ETH1000 = 0x83, @@ -347,6 +348,7 @@ enum qeth_card_info_port_speed { CARD_INFO_PORTS_100M = 0x00000006, CARD_INFO_PORTS_1G = 0x00000007, CARD_INFO_PORTS_10G = 0x00000008, + CARD_INFO_PORTS_25G = 0x0000000A, }; /* (SET)DELIP(M) IPA stuff ***************************************************/ @@ -436,7 +438,7 @@ struct qeth_ipacmd_setassparms { __u32 flags_32bit; struct qeth_ipa_caps caps; struct qeth_checksum_cmd chksum; - struct qeth_arp_cache_entry add_arp_entry; + struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; __u8 ip[16]; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 23aaf373f631..2914a1a69f83 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -146,11 +146,11 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Wmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc == -EEXIST) - QETH_DBF_MESSAGE(2, "MAC %pM already registered on %s\n", - mac, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "MAC already registered on device %x\n", + CARD_DEVID(card)); else if (rc) - QETH_DBF_MESSAGE(2, "Failed to register MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to register MAC on device %x: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -163,8 +163,8 @@ static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Rmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc) - QETH_DBF_MESSAGE(2, "Failed to delete MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to delete MAC on device %u: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -260,9 +260,9 @@ static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "L2sdvcb"); if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(2, "Error in processing VLAN %i on %s: 0x%x.\n", + QETH_DBF_MESSAGE(2, "Error in processing VLAN %u on device %x: %#x.\n", cmd->data.setdelvlan.vlan_id, - QETH_CARD_IFNAME(card), cmd->hdr.return_code); + CARD_DEVID(card), cmd->hdr.return_code); QETH_CARD_TEXT_(card, 2, "L2VL%4x", cmd->hdr.command); QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code); } @@ -455,8 +455,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_vm_request_mac(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "err%04x", rc); /* fall back to alternative mechanism: */ } @@ -468,8 +468,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_setadpparms_change_macaddr(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); /* fall back once more: */ } @@ -826,7 +826,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); } static const struct ethtool_ops qeth_l2_ethtool_ops = { @@ -862,11 +863,11 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_set_features = qeth_set_features }; -static int qeth_l2_setup_netdev(struct qeth_card *card) +static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) { int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; card->dev->priv_flags |= IFF_UNICAST_FLT; @@ -919,6 +920,9 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) qeth_l2_request_initial_mac(card); netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + if (rc) card->dev->netdev_ops = NULL; return rc; @@ -949,6 +953,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -956,7 +961,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; @@ -967,7 +972,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) dev_info(&card->gdev->dev, "The device represents a Bridge Capable Port\n"); - rc = qeth_l2_setup_netdev(card); + rc = qeth_l2_setup_netdev(card, carrier_ok); if (rc) goto out_remove; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 0b161cc1fd2e..f08b745c2007 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -278,9 +278,6 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) QETH_CARD_TEXT(card, 4, "clearip"); - if (recover && card->options.sniffer) - return; - spin_lock_bh(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { @@ -494,9 +491,8 @@ int qeth_l3_setrouting_v4(struct qeth_card *card) QETH_PROT_IPV4); if (rc) { card->options.route4.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -518,9 +514,8 @@ int qeth_l3_setrouting_v6(struct qeth_card *card) QETH_PROT_IPV6); if (rc) { card->options.route6.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -663,6 +658,8 @@ static int qeth_l3_register_addr_entry(struct qeth_card *card, int rc = 0; int cnt = 3; + if (card->options.sniffer) + return 0; if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "setaddr4"); @@ -697,6 +694,9 @@ static int qeth_l3_deregister_addr_entry(struct qeth_card *card, { int rc = 0; + if (card->options.sniffer) + return 0; + if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "deladdr4"); QETH_CARD_HEX(card, 3, &addr->u.a4.addr, sizeof(int)); @@ -1070,8 +1070,8 @@ qeth_diags_trace_cb(struct qeth_card *card, struct qeth_reply *reply, } break; default: - QETH_DBF_MESSAGE(2, "Unknown sniffer action (0x%04x) on %s\n", - cmd->data.diagass.action, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Unknown sniffer action (%#06x) on device %x\n", + cmd->data.diagass.action, CARD_DEVID(card)); } return 0; @@ -1517,32 +1517,25 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) qeth_l3_handle_promisc_mode(card); } -static const char *qeth_l3_arp_get_error_cause(int *rc) +static int qeth_l3_arp_makerc(int rc) { - switch (*rc) { - case QETH_IPA_ARP_RC_FAILED: - *rc = -EIO; - return "operation failed"; + switch (rc) { + case IPA_RC_SUCCESS: + return 0; case QETH_IPA_ARP_RC_NOTSUPP: - *rc = -EOPNOTSUPP; - return "operation not supported"; - case QETH_IPA_ARP_RC_OUT_OF_RANGE: - *rc = -EINVAL; - return "argument out of range"; case QETH_IPA_ARP_RC_Q_NOTSUPP: - *rc = -EOPNOTSUPP; - return "query operation not supported"; + return -EOPNOTSUPP; + case QETH_IPA_ARP_RC_OUT_OF_RANGE: + return -EINVAL; case QETH_IPA_ARP_RC_Q_NO_DATA: - *rc = -ENOENT; - return "no query data available"; + return -ENOENT; default: - return "unknown error"; + return -EIO; } } static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) { - int tmp; int rc; QETH_CARD_TEXT(card, 3, "arpstnoe"); @@ -1560,13 +1553,10 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_SET_NO_ENTRIES, no_entries); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on " - "%s: %s (0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static __u32 get_arp_entry_size(struct qeth_card *card, @@ -1716,7 +1706,6 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - int tmp; int rc; QETH_CARD_TEXT_(card, 3, "qarpipv%i", prot); @@ -1735,15 +1724,10 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, rc = qeth_l3_send_ipa_arp_cmd(card, iob, QETH_SETASS_BASE_LEN+QETH_ARP_CMD_LEN, qeth_l3_arp_query_cb, (void *)qinfo); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, - "Error while querying ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Error while querying ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata) @@ -1793,15 +1777,18 @@ out: return rc; } -static int qeth_l3_arp_add_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) +static int qeth_l3_arp_modify_entry(struct qeth_card *card, + struct qeth_arp_cache_entry *entry, + enum qeth_arp_process_subcmds arp_cmd) { + struct qeth_arp_cache_entry *cmd_entry; struct qeth_cmd_buffer *iob; - char buf[16]; - int tmp; int rc; - QETH_CARD_TEXT(card, 3, "arpadent"); + if (arp_cmd == IPA_CMD_ASS_ARP_ADD_ENTRY) + QETH_CARD_TEXT(card, 3, "arpadd"); + else + QETH_CARD_TEXT(card, 3, "arpdel"); /* * currently GuestLAN only supports the ARP assist function @@ -1814,71 +1801,25 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, return -EOPNOTSUPP; } - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_ADD_ENTRY, - sizeof(struct qeth_arp_cache_entry), - QETH_PROT_IPV4); + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, arp_cmd, + sizeof(*cmd_entry), QETH_PROT_IPV4); if (!iob) return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - sizeof(struct qeth_arp_cache_entry), - (unsigned long) entry, - qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not add ARP entry for address %s " - "on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; -} - -static int qeth_l3_arp_remove_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) -{ - struct qeth_cmd_buffer *iob; - char buf[16] = {0, }; - int tmp; - int rc; - QETH_CARD_TEXT(card, 3, "arprment"); + cmd_entry = &__ipa_cmd(iob)->data.setassparms.data.arp_entry; + ether_addr_copy(cmd_entry->macaddr, entry->macaddr); + memcpy(cmd_entry->ipaddr, entry->ipaddr, 4); + rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL); + if (rc) + QETH_DBF_MESSAGE(2, "Could not modify (cmd: %#x) ARP entry on device %x: %#x\n", + arp_cmd, CARD_DEVID(card), rc); - /* - * currently GuestLAN only supports the ARP assist function - * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_REMOVE_ENTRY; - * thus we say EOPNOTSUPP for this ARP function - */ - if (card->info.guestlan) - return -EOPNOTSUPP; - if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { - return -EOPNOTSUPP; - } - memcpy(buf, entry, 12); - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_REMOVE_ENTRY, - 12, - QETH_PROT_IPV4); - if (!iob) - return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - 12, (unsigned long)buf, - qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - memset(buf, 0, 16); - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not delete ARP entry for address %s" - " on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_flush_cache(struct qeth_card *card) { int rc; - int tmp; QETH_CARD_TEXT(card, 3, "arpflush"); @@ -1894,19 +1835,17 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_FLUSH_CACHE, 0); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not flush ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not flush ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct qeth_card *card = dev->ml_priv; struct qeth_arp_cache_entry arp_entry; + enum qeth_arp_process_subcmds arp_cmd; int rc = 0; switch (cmd) { @@ -1925,27 +1864,16 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) rc = qeth_l3_arp_query(card, rq->ifr_ifru.ifru_data); break; case SIOC_QETH_ARP_ADD_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_add_entry(card, &arp_entry); - break; case SIOC_QETH_ARP_REMOVE_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_remove_entry(card, &arp_entry); - break; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (copy_from_user(&arp_entry, rq->ifr_data, sizeof(arp_entry))) + return -EFAULT; + + arp_cmd = (cmd == SIOC_QETH_ARP_ADD_ENTRY) ? + IPA_CMD_ASS_ARP_ADD_ENTRY : + IPA_CMD_ASS_ARP_REMOVE_ENTRY; + return qeth_l3_arp_modify_entry(card, &arp_entry, arp_cmd); case SIOC_QETH_ARP_FLUSH_CACHE: if (!capable(CAP_NET_ADMIN)) { rc = -EPERM; @@ -2383,12 +2311,12 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_neigh_setup = qeth_l3_neigh_setup, }; -static int qeth_l3_setup_netdev(struct qeth_card *card) +static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) { unsigned int headroom; int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; if (card->info.type == QETH_CARD_TYPE_OSD || @@ -2457,6 +2385,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + out: if (rc) card->dev->netdev_ops = NULL; @@ -2497,7 +2428,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); qeth_l3_clear_ipato_list(card); } @@ -2507,6 +2439,7 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -2514,14 +2447,14 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; goto out_remove; } - rc = qeth_l3_setup_netdev(card); + rc = qeth_l3_setup_netdev(card, carrier_ok); if (rc) goto out_remove; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ff6ba6d86cd8..cc56cb3b3eca 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1614,10 +1614,10 @@ static void sci_request_dma(struct uart_port *port) hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); s->rx_timer.function = rx_timer_fn; + s->chan_rx_saved = s->chan_rx = chan; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) sci_submit_rx(s); - - s->chan_rx_saved = s->chan_rx = chan; } } @@ -3102,6 +3102,7 @@ static struct uart_driver sci_uart_driver = { static int sci_remove(struct platform_device *dev) { struct sci_port *port = platform_get_drvdata(dev); + unsigned int type = port->port.type; /* uart_remove_... clears it */ sci_ports_in_use &= ~BIT(port->port.line); uart_remove_one_port(&sci_uart_driver, &port->port); @@ -3112,8 +3113,7 @@ static int sci_remove(struct platform_device *dev) sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_trigger.attr); } - if (port->port.type == PORT_SCIFA || port->port.type == PORT_SCIFB || - port->port.type == PORT_HSCIF) { + if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) { sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_timeout.attr); } diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c index 7576ceace571..f438eaa68246 100644 --- a/drivers/tty/tty_baudrate.c +++ b/drivers/tty/tty_baudrate.c @@ -77,7 +77,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); @@ -113,7 +113,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; #else /* IBSHIFT */ return tty_termios_baud_rate(termios); #endif /* IBSHIFT */ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 55370e651db3..41ec8e5010f3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1548,7 +1548,7 @@ static void csi_K(struct vc_data *vc, int vpar) scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count); vc->vc_need_wrap = 0; if (con_should_update(vc)) - do_update_region(vc, (unsigned long) start, count); + do_update_region(vc, (unsigned long)(start + offset), count); } static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar positions */ diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index e36d6c73c4a4..78118883f96c 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -23,6 +23,16 @@ config TYPEC_UCSI if TYPEC_UCSI +config UCSI_CCG + tristate "UCSI Interface Driver for Cypress CCGx" + depends on I2C + help + This driver enables UCSI support on platforms that expose a + Cypress CCGx Type-C controller over I2C interface. + + To compile the driver as a module, choose M here: the module will be + called ucsi_ccg. + config UCSI_ACPI tristate "UCSI ACPI Interface Driver" depends on ACPI diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index 7afbea512207..2f4900b26210 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -8,3 +8,5 @@ typec_ucsi-y := ucsi.o typec_ucsi-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o + +obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c new file mode 100644 index 000000000000..de8a43bdff68 --- /dev/null +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UCSI driver for Cypress CCGx Type-C controller + * + * Copyright (C) 2017-2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <ajayg@nvidia.com> + * + * Some code borrowed from drivers/usb/typec/ucsi/ucsi_acpi.c + */ +#include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include <asm/unaligned.h> +#include "ucsi.h" + +struct ucsi_ccg { + struct device *dev; + struct ucsi *ucsi; + struct ucsi_ppm ppm; + struct i2c_client *client; +}; + +#define CCGX_RAB_INTR_REG 0x06 +#define CCGX_RAB_UCSI_CONTROL 0x39 +#define CCGX_RAB_UCSI_CONTROL_START BIT(0) +#define CCGX_RAB_UCSI_CONTROL_STOP BIT(1) +#define CCGX_RAB_UCSI_DATA_BLOCK(offset) (0xf000 | ((offset) & 0xff)) + +static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + const struct i2c_adapter_quirks *quirks = client->adapter->quirks; + unsigned char buf[2]; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + .len = sizeof(buf), + .buf = buf, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .buf = data, + }, + }; + u32 rlen, rem_len = len, max_read_len = len; + int status; + + /* check any max_read_len limitation on i2c adapter */ + if (quirks && quirks->max_read_len) + max_read_len = quirks->max_read_len; + + while (rem_len > 0) { + msgs[1].buf = &data[len - rem_len]; + rlen = min_t(u16, rem_len, max_read_len); + msgs[1].len = rlen; + put_unaligned_le16(rab, buf); + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + return status; + } + rab += rlen; + rem_len -= rlen; + } + + return 0; +} + +static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + unsigned char *buf; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + } + }; + int status; + + buf = kzalloc(len + sizeof(rab), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + put_unaligned_le16(rab, buf); + memcpy(buf + sizeof(rab), data, len); + + msgs[0].len = len + sizeof(rab); + msgs[0].buf = buf; + + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + kfree(buf); + return status; + } + + kfree(buf); + return 0; +} + +static int ucsi_ccg_init(struct ucsi_ccg *uc) +{ + unsigned int count = 10; + u8 data; + int status; + + data = CCGX_RAB_UCSI_CONTROL_STOP; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + data = CCGX_RAB_UCSI_CONTROL_START; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + /* + * Flush CCGx RESPONSE queue by acking interrupts. Above ucsi control + * register write will push response which must be cleared. + */ + do { + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + if (!data) + return 0; + + status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + usleep_range(10000, 11000); + } while (--count); + + return -ETIMEDOUT; +} + +static int ucsi_ccg_send_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_out)); + status = ccg_write(uc, rab, ppm + + offsetof(struct ucsi_data, message_out), + sizeof(uc->ppm.data->message_out)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, ctrl)); + return ccg_write(uc, rab, ppm + offsetof(struct ucsi_data, ctrl), + sizeof(uc->ppm.data->ctrl)); +} + +static int ucsi_ccg_recv_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, cci)); + status = ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, cci), + sizeof(uc->ppm.data->cci)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_in)); + return ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, message_in), + sizeof(uc->ppm.data->message_in)); +} + +static int ucsi_ccg_ack_interrupt(struct ucsi_ccg *uc) +{ + int status; + unsigned char data; + + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + return ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); +} + +static int ucsi_ccg_sync(struct ucsi_ppm *ppm) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + int status; + + status = ucsi_ccg_recv_data(uc); + if (status < 0) + return status; + + /* ack interrupt to allow next command to run */ + return ucsi_ccg_ack_interrupt(uc); +} + +static int ucsi_ccg_cmd(struct ucsi_ppm *ppm, struct ucsi_control *ctrl) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + + ppm->data->ctrl.raw_cmd = ctrl->raw_cmd; + return ucsi_ccg_send_data(uc); +} + +static irqreturn_t ccg_irq_handler(int irq, void *data) +{ + struct ucsi_ccg *uc = data; + + ucsi_notify(uc->ucsi); + + return IRQ_HANDLED; +} + +static int ucsi_ccg_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct ucsi_ccg *uc; + int status; + u16 rab; + + uc = devm_kzalloc(dev, sizeof(*uc), GFP_KERNEL); + if (!uc) + return -ENOMEM; + + uc->ppm.data = devm_kzalloc(dev, sizeof(struct ucsi_data), GFP_KERNEL); + if (!uc->ppm.data) + return -ENOMEM; + + uc->ppm.cmd = ucsi_ccg_cmd; + uc->ppm.sync = ucsi_ccg_sync; + uc->dev = dev; + uc->client = client; + + /* reset ccg device and initialize ucsi */ + status = ucsi_ccg_init(uc); + if (status < 0) { + dev_err(uc->dev, "ucsi_ccg_init failed - %d\n", status); + return status; + } + + status = devm_request_threaded_irq(dev, client->irq, NULL, + ccg_irq_handler, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), uc); + if (status < 0) { + dev_err(uc->dev, "request_threaded_irq failed - %d\n", status); + return status; + } + + uc->ucsi = ucsi_register_ppm(dev, &uc->ppm); + if (IS_ERR(uc->ucsi)) { + dev_err(uc->dev, "ucsi_register_ppm failed\n"); + return PTR_ERR(uc->ucsi); + } + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, version)); + status = ccg_read(uc, rab, (u8 *)(uc->ppm.data) + + offsetof(struct ucsi_data, version), + sizeof(uc->ppm.data->version)); + if (status < 0) { + ucsi_unregister_ppm(uc->ucsi); + return status; + } + + i2c_set_clientdata(client, uc); + return 0; +} + +static int ucsi_ccg_remove(struct i2c_client *client) +{ + struct ucsi_ccg *uc = i2c_get_clientdata(client); + + ucsi_unregister_ppm(uc->ucsi); + + return 0; +} + +static const struct i2c_device_id ucsi_ccg_device_id[] = { + {"ccgx-ucsi", 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, ucsi_ccg_device_id); + +static struct i2c_driver ucsi_ccg_driver = { + .driver = { + .name = "ucsi_ccg", + }, + .probe = ucsi_ccg_probe, + .remove = ucsi_ccg_remove, + .id_table = ucsi_ccg_device_id, +}; + +module_i2c_driver(ucsi_ccg_driver); + +MODULE_AUTHOR("Ajay Gupta <ajayg@nvidia.com>"); +MODULE_DESCRIPTION("UCSI driver for Cypress CCGx Type-C controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f15f89df1f36..7ea6fb6a2e5d 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -914,7 +914,7 @@ int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args) ret = xenmem_reservation_increase(args->nr_pages, args->frames); if (ret != args->nr_pages) { - pr_debug("Failed to decrease reservation for DMA buffer\n"); + pr_debug("Failed to increase reservation for DMA buffer\n"); ret = -EFAULT; } else { ret = 0; diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index df1ed37c3269..de01a6d0059d 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -21,15 +21,9 @@ MODULE_LICENSE("GPL"); -static unsigned int limit = 64; -module_param(limit, uint, 0644); -MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by " - "the privcmd-buf device per open file"); - struct privcmd_buf_private { struct mutex lock; struct list_head list; - unsigned int allocated; }; struct privcmd_buf_vma_private { @@ -60,13 +54,10 @@ static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv) { unsigned int i; - vma_priv->file_priv->allocated -= vma_priv->n_pages; - list_del(&vma_priv->list); for (i = 0; i < vma_priv->n_pages; i++) - if (vma_priv->pages[i]) - __free_page(vma_priv->pages[i]); + __free_page(vma_priv->pages[i]); kfree(vma_priv); } @@ -146,8 +137,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) unsigned int i; int ret = 0; - if (!(vma->vm_flags & VM_SHARED) || count > limit || - file_priv->allocated + count > limit) + if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), @@ -155,19 +145,15 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) if (!vma_priv) return -ENOMEM; - vma_priv->n_pages = count; - count = 0; - for (i = 0; i < vma_priv->n_pages; i++) { + for (i = 0; i < count; i++) { vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!vma_priv->pages[i]) break; - count++; + vma_priv->n_pages++; } mutex_lock(&file_priv->lock); - file_priv->allocated += count; - vma_priv->file_priv = file_priv; vma_priv->users = 1; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 27cad84dab23..189df668b6a0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1931,10 +1931,17 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, if (!prealloc_cf) return -ENOMEM; - /* Start by sync'ing the source file */ + /* Start by sync'ing the source and destination files */ ret = file_write_and_wait_range(src_file, src_off, (src_off + len)); - if (ret < 0) + if (ret < 0) { + dout("failed to write src file (%zd)\n", ret); + goto out; + } + ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len)); + if (ret < 0) { + dout("failed to write dst file (%zd)\n", ret); goto out; + } /* * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 67a9aeb2f4ec..bd13a3267ae0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end, info->symlink = *p; *p += info->symlink_len; - if (features & CEPH_FEATURE_DIRLAYOUTHASH) - ceph_decode_copy_safe(p, end, &info->dir_layout, - sizeof(info->dir_layout), bad); - else - memset(&info->dir_layout, 0, sizeof(info->dir_layout)); - + ceph_decode_copy_safe(p, end, &info->dir_layout, + sizeof(info->dir_layout), bad); ceph_decode_32_safe(p, end, info->xattr_len, bad); ceph_decode_need(p, end, info->xattr_len, bad); info->xattr_data = *p; @@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.pagelist = pagelist; if (session->s_con.peer_features & CEPH_FEATURE_MDSENC) recon_state.msg_version = 3; - else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK) - recon_state.msg_version = 2; else - recon_state.msg_version = 1; + recon_state.msg_version = 2; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 32d4f13784ba..03f4d24db8fe 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -237,7 +237,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, ceph_put_snap_realm(mdsc, realm); realm = next; } - ceph_put_snap_realm(mdsc, realm); + if (realm) + ceph_put_snap_realm(mdsc, realm); up_read(&mdsc->snap_rwsem); return exceeded; diff --git a/fs/namespace.c b/fs/namespace.c index 98d27da43304..74f64294a410 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1728,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1782,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index db84b4adbc49..867457d6dfbe 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3788,7 +3788,7 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, } /* - * -EACCESS could mean that the user doesn't have correct permissions + * -EACCES could mean that the user doesn't have correct permissions * to access the mount. It could also mean that we tried to mount * with a gss auth flavor, but rpc.gssd isn't running. Either way, * existing mount programs don't handle -EACCES very well so it should diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig index bbc78549be4c..529856fbccd0 100644 --- a/fs/ubifs/Kconfig +++ b/fs/ubifs/Kconfig @@ -7,6 +7,7 @@ config UBIFS_FS select CRYPTO if UBIFS_FS_ZLIB select CRYPTO_LZO if UBIFS_FS_LZO select CRYPTO_DEFLATE if UBIFS_FS_ZLIB + select CRYPTO_HASH_INFO depends on MTD_UBI help UBIFS is a file system for flash devices which works on top of UBI. @@ -85,3 +86,13 @@ config UBIFS_FS_SECURITY the extended attribute support in advance. If you are not using a security module, say N. + +config UBIFS_FS_AUTHENTICATION + bool "UBIFS authentication support" + select CRYPTO_HMAC + help + Enable authentication support for UBIFS. This feature offers protection + against offline changes for both data and metadata of the filesystem. + If you say yes here you should also select a hashing algorithm such as + sha256, these are not selected automatically since there are many + different options. diff --git a/fs/ubifs/Makefile b/fs/ubifs/Makefile index 6197d7e539e4..5f838319c8d5 100644 --- a/fs/ubifs/Makefile +++ b/fs/ubifs/Makefile @@ -8,3 +8,4 @@ ubifs-y += recovery.o ioctl.o lpt_commit.o tnc_misc.o debug.o ubifs-y += misc.o ubifs-$(CONFIG_UBIFS_FS_ENCRYPTION) += crypto.o ubifs-$(CONFIG_UBIFS_FS_XATTR) += xattr.o +ubifs-$(CONFIG_UBIFS_FS_AUTHENTICATION) += auth.o diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c new file mode 100644 index 000000000000..124e965a28b3 --- /dev/null +++ b/fs/ubifs/auth.c @@ -0,0 +1,502 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file is part of UBIFS. + * + * Copyright (C) 2018 Pengutronix, Sascha Hauer <s.hauer@pengutronix.de> + */ + +/* + * This file implements various helper functions for UBIFS authentication support + */ + +#include <linux/crypto.h> +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <crypto/algapi.h> +#include <keys/user-type.h> + +#include "ubifs.h" + +/** + * ubifs_node_calc_hash - calculate the hash of a UBIFS node + * @c: UBIFS file-system description object + * @node: the node to calculate a hash for + * @hash: the returned hash + * + * Returns 0 for success or a negative error code otherwise. + */ +int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *node, + u8 *hash) +{ + const struct ubifs_ch *ch = node; + SHASH_DESC_ON_STACK(shash, c->hash_tfm); + int err; + + shash->tfm = c->hash_tfm; + shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + err = crypto_shash_digest(shash, node, le32_to_cpu(ch->len), hash); + if (err < 0) + return err; + return 0; +} + +/** + * ubifs_hash_calc_hmac - calculate a HMAC from a hash + * @c: UBIFS file-system description object + * @hash: the node to calculate a HMAC for + * @hmac: the returned HMAC + * + * Returns 0 for success or a negative error code otherwise. + */ +static int ubifs_hash_calc_hmac(const struct ubifs_info *c, const u8 *hash, + u8 *hmac) +{ + SHASH_DESC_ON_STACK(shash, c->hmac_tfm); + int err; + + shash->tfm = c->hmac_tfm; + shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + err = crypto_shash_digest(shash, hash, c->hash_len, hmac); + if (err < 0) + return err; + return 0; +} + +/** + * ubifs_prepare_auth_node - Prepare an authentication node + * @c: UBIFS file-system description object + * @node: the node to calculate a hash for + * @hash: input hash of previous nodes + * + * This function prepares an authentication node for writing onto flash. + * It creates a HMAC from the given input hash and writes it to the node. + * + * Returns 0 for success or a negative error code otherwise. + */ +int ubifs_prepare_auth_node(struct ubifs_info *c, void *node, + struct shash_desc *inhash) +{ + SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); + struct ubifs_auth_node *auth = node; + u8 *hash; + int err; + + hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS); + if (!hash) + return -ENOMEM; + + hash_desc->tfm = c->hash_tfm; + hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + ubifs_shash_copy_state(c, inhash, hash_desc); + + err = crypto_shash_final(hash_desc, hash); + if (err) + goto out; + + err = ubifs_hash_calc_hmac(c, hash, auth->hmac); + if (err) + goto out; + + auth->ch.node_type = UBIFS_AUTH_NODE; + ubifs_prepare_node(c, auth, ubifs_auth_node_sz(c), 0); + + err = 0; +out: + kfree(hash); + + return err; +} + +static struct shash_desc *ubifs_get_desc(const struct ubifs_info *c, + struct crypto_shash *tfm) +{ + struct shash_desc *desc; + int err; + + if (!ubifs_authenticated(c)) + return NULL; + + desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(tfm), GFP_KERNEL); + if (!desc) + return ERR_PTR(-ENOMEM); + + desc->tfm = tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + err = crypto_shash_init(desc); + if (err) { + kfree(desc); + return ERR_PTR(err); + } + + return desc; +} + +/** + * __ubifs_hash_get_desc - get a descriptor suitable for hashing a node + * @c: UBIFS file-system description object + * + * This function returns a descriptor suitable for hashing a node. Free after use + * with kfree. + */ +struct shash_desc *__ubifs_hash_get_desc(const struct ubifs_info *c) +{ + return ubifs_get_desc(c, c->hash_tfm); +} + +/** + * __ubifs_shash_final - finalize shash + * @c: UBIFS file-system description object + * @desc: the descriptor + * @out: the output hash + * + * Simple wrapper around crypto_shash_final(), safe to be called with + * disabled authentication. + */ +int __ubifs_shash_final(const struct ubifs_info *c, struct shash_desc *desc, + u8 *out) +{ + if (ubifs_authenticated(c)) + return crypto_shash_final(desc, out); + + return 0; +} + +/** + * ubifs_bad_hash - Report hash mismatches + * @c: UBIFS file-system description object + * @node: the node + * @hash: the expected hash + * @lnum: the LEB @node was read from + * @offs: offset in LEB @node was read from + * + * This function reports a hash mismatch when a node has a different hash than + * expected. + */ +void ubifs_bad_hash(const struct ubifs_info *c, const void *node, const u8 *hash, + int lnum, int offs) +{ + int len = min(c->hash_len, 20); + int cropped = len != c->hash_len; + const char *cont = cropped ? "..." : ""; + + u8 calc[UBIFS_HASH_ARR_SZ]; + + __ubifs_node_calc_hash(c, node, calc); + + ubifs_err(c, "hash mismatch on node at LEB %d:%d", lnum, offs); + ubifs_err(c, "hash expected: %*ph%s", len, hash, cont); + ubifs_err(c, "hash calculated: %*ph%s", len, calc, cont); +} + +/** + * __ubifs_node_check_hash - check the hash of a node against given hash + * @c: UBIFS file-system description object + * @node: the node + * @expected: the expected hash + * + * This function calculates a hash over a node and compares it to the given hash. + * Returns 0 if both hashes are equal or authentication is disabled, otherwise a + * negative error code is returned. + */ +int __ubifs_node_check_hash(const struct ubifs_info *c, const void *node, + const u8 *expected) +{ + u8 calc[UBIFS_HASH_ARR_SZ]; + int err; + + err = __ubifs_node_calc_hash(c, node, calc); + if (err) + return err; + + if (ubifs_check_hash(c, expected, calc)) + return -EPERM; + + return 0; +} + +/** + * ubifs_init_authentication - initialize UBIFS authentication support + * @c: UBIFS file-system description object + * + * This function returns 0 for success or a negative error code otherwise. + */ +int ubifs_init_authentication(struct ubifs_info *c) +{ + struct key *keyring_key; + const struct user_key_payload *ukp; + int err; + char hmac_name[CRYPTO_MAX_ALG_NAME]; + + if (!c->auth_hash_name) { + ubifs_err(c, "authentication hash name needed with authentication"); + return -EINVAL; + } + + c->auth_hash_algo = match_string(hash_algo_name, HASH_ALGO__LAST, + c->auth_hash_name); + if ((int)c->auth_hash_algo < 0) { + ubifs_err(c, "Unknown hash algo %s specified", + c->auth_hash_name); + return -EINVAL; + } + + snprintf(hmac_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)", + c->auth_hash_name); + + keyring_key = request_key(&key_type_logon, c->auth_key_name, NULL); + + if (IS_ERR(keyring_key)) { + ubifs_err(c, "Failed to request key: %ld", + PTR_ERR(keyring_key)); + return PTR_ERR(keyring_key); + } + + down_read(&keyring_key->sem); + + if (keyring_key->type != &key_type_logon) { + ubifs_err(c, "key type must be logon"); + err = -ENOKEY; + goto out; + } + + ukp = user_key_payload_locked(keyring_key); + if (!ukp) { + /* key was revoked before we acquired its semaphore */ + err = -EKEYREVOKED; + goto out; + } + + c->hash_tfm = crypto_alloc_shash(c->auth_hash_name, 0, + CRYPTO_ALG_ASYNC); + if (IS_ERR(c->hash_tfm)) { + err = PTR_ERR(c->hash_tfm); + ubifs_err(c, "Can not allocate %s: %d", + c->auth_hash_name, err); + goto out; + } + + c->hash_len = crypto_shash_digestsize(c->hash_tfm); + if (c->hash_len > UBIFS_HASH_ARR_SZ) { + ubifs_err(c, "hash %s is bigger than maximum allowed hash size (%d > %d)", + c->auth_hash_name, c->hash_len, UBIFS_HASH_ARR_SZ); + err = -EINVAL; + goto out_free_hash; + } + + c->hmac_tfm = crypto_alloc_shash(hmac_name, 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(c->hmac_tfm)) { + err = PTR_ERR(c->hmac_tfm); + ubifs_err(c, "Can not allocate %s: %d", hmac_name, err); + goto out_free_hash; + } + + c->hmac_desc_len = crypto_shash_digestsize(c->hmac_tfm); + if (c->hmac_desc_len > UBIFS_HMAC_ARR_SZ) { + ubifs_err(c, "hmac %s is bigger than maximum allowed hmac size (%d > %d)", + hmac_name, c->hmac_desc_len, UBIFS_HMAC_ARR_SZ); + err = -EINVAL; + goto out_free_hash; + } + + err = crypto_shash_setkey(c->hmac_tfm, ukp->data, ukp->datalen); + if (err) + goto out_free_hmac; + + c->authenticated = true; + + c->log_hash = ubifs_hash_get_desc(c); + if (IS_ERR(c->log_hash)) + goto out_free_hmac; + + err = 0; + +out_free_hmac: + if (err) + crypto_free_shash(c->hmac_tfm); +out_free_hash: + if (err) + crypto_free_shash(c->hash_tfm); +out: + up_read(&keyring_key->sem); + key_put(keyring_key); + + return err; +} + +/** + * __ubifs_exit_authentication - release resource + * @c: UBIFS file-system description object + * + * This function releases the authentication related resources. + */ +void __ubifs_exit_authentication(struct ubifs_info *c) +{ + if (!ubifs_authenticated(c)) + return; + + crypto_free_shash(c->hmac_tfm); + crypto_free_shash(c->hash_tfm); + kfree(c->log_hash); +} + +/** + * ubifs_node_calc_hmac - calculate the HMAC of a UBIFS node + * @c: UBIFS file-system description object + * @node: the node to insert a HMAC into. + * @len: the length of the node + * @ofs_hmac: the offset in the node where the HMAC is inserted + * @hmac: returned HMAC + * + * This function calculates a HMAC of a UBIFS node. The HMAC is expected to be + * embedded into the node, so this area is not covered by the HMAC. Also not + * covered is the UBIFS_NODE_MAGIC and the CRC of the node. + */ +static int ubifs_node_calc_hmac(const struct ubifs_info *c, const void *node, + int len, int ofs_hmac, void *hmac) +{ + SHASH_DESC_ON_STACK(shash, c->hmac_tfm); + int hmac_len = c->hmac_desc_len; + int err; + + ubifs_assert(c, ofs_hmac > 8); + ubifs_assert(c, ofs_hmac + hmac_len < len); + + shash->tfm = c->hmac_tfm; + shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + err = crypto_shash_init(shash); + if (err) + return err; + + /* behind common node header CRC up to HMAC begin */ + err = crypto_shash_update(shash, node + 8, ofs_hmac - 8); + if (err < 0) + return err; + + /* behind HMAC, if any */ + if (len - ofs_hmac - hmac_len > 0) { + err = crypto_shash_update(shash, node + ofs_hmac + hmac_len, + len - ofs_hmac - hmac_len); + if (err < 0) + return err; + } + + return crypto_shash_final(shash, hmac); +} + +/** + * __ubifs_node_insert_hmac - insert a HMAC into a UBIFS node + * @c: UBIFS file-system description object + * @node: the node to insert a HMAC into. + * @len: the length of the node + * @ofs_hmac: the offset in the node where the HMAC is inserted + * + * This function inserts a HMAC at offset @ofs_hmac into the node given in + * @node. + * + * This function returns 0 for success or a negative error code otherwise. + */ +int __ubifs_node_insert_hmac(const struct ubifs_info *c, void *node, int len, + int ofs_hmac) +{ + return ubifs_node_calc_hmac(c, node, len, ofs_hmac, node + ofs_hmac); +} + +/** + * __ubifs_node_verify_hmac - verify the HMAC of UBIFS node + * @c: UBIFS file-system description object + * @node: the node to insert a HMAC into. + * @len: the length of the node + * @ofs_hmac: the offset in the node where the HMAC is inserted + * + * This function verifies the HMAC at offset @ofs_hmac of the node given in + * @node. Returns 0 if successful or a negative error code otherwise. + */ +int __ubifs_node_verify_hmac(const struct ubifs_info *c, const void *node, + int len, int ofs_hmac) +{ + int hmac_len = c->hmac_desc_len; + u8 *hmac; + int err; + + hmac = kmalloc(hmac_len, GFP_NOFS); + if (!hmac) + return -ENOMEM; + + err = ubifs_node_calc_hmac(c, node, len, ofs_hmac, hmac); + if (err) + return err; + + err = crypto_memneq(hmac, node + ofs_hmac, hmac_len); + + kfree(hmac); + + if (!err) + return 0; + + return -EPERM; +} + +int __ubifs_shash_copy_state(const struct ubifs_info *c, struct shash_desc *src, + struct shash_desc *target) +{ + u8 *state; + int err; + + state = kmalloc(crypto_shash_descsize(src->tfm), GFP_NOFS); + if (!state) + return -ENOMEM; + + err = crypto_shash_export(src, state); + if (err) + goto out; + + err = crypto_shash_import(target, state); + +out: + kfree(state); + + return err; +} + +/** + * ubifs_hmac_wkm - Create a HMAC of the well known message + * @c: UBIFS file-system description object + * @hmac: The HMAC of the well known message + * + * This function creates a HMAC of a well known message. This is used + * to check if the provided key is suitable to authenticate a UBIFS + * image. This is only a convenience to the user to provide a better + * error message when the wrong key is provided. + * + * This function returns 0 for success or a negative error code otherwise. + */ +int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac) +{ + SHASH_DESC_ON_STACK(shash, c->hmac_tfm); + int err; + const char well_known_message[] = "UBIFS"; + + if (!ubifs_authenticated(c)) + return 0; + + shash->tfm = c->hmac_tfm; + shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + err = crypto_shash_init(shash); + if (err) + return err; + + err = crypto_shash_update(shash, well_known_message, + sizeof(well_known_message) - 1); + if (err < 0) + return err; + + err = crypto_shash_final(shash, hmac); + if (err) + return err; + return 0; +} diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 564e330d05b1..c49ff50fdceb 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -165,6 +165,8 @@ const char *dbg_ntype(int type) return "commit start node"; case UBIFS_ORPH_NODE: return "orphan node"; + case UBIFS_AUTH_NODE: + return "auth node"; default: return "unknown node"; } @@ -542,6 +544,10 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node) (unsigned long long)le64_to_cpu(orph->inos[i])); break; } + case UBIFS_AUTH_NODE: + { + break; + } default: pr_err("node type %d was not recognized\n", (int)ch->node_type); diff --git a/fs/ubifs/gc.c b/fs/ubifs/gc.c index d2680e0b4a36..bf75fdc76fc3 100644 --- a/fs/ubifs/gc.c +++ b/fs/ubifs/gc.c @@ -254,7 +254,8 @@ static int sort_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb, snod->type == UBIFS_DATA_NODE || snod->type == UBIFS_DENT_NODE || snod->type == UBIFS_XENT_NODE || - snod->type == UBIFS_TRUN_NODE); + snod->type == UBIFS_TRUN_NODE || + snod->type == UBIFS_AUTH_NODE); if (snod->type != UBIFS_INO_NODE && snod->type != UBIFS_DATA_NODE && @@ -364,12 +365,13 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) /* Write nodes to their new location. Use the first-fit strategy */ while (1) { - int avail; + int avail, moved = 0; struct ubifs_scan_node *snod, *tmp; /* Move data nodes */ list_for_each_entry_safe(snod, tmp, &sleb->nodes, list) { - avail = c->leb_size - wbuf->offs - wbuf->used; + avail = c->leb_size - wbuf->offs - wbuf->used - + ubifs_auth_node_sz(c); if (snod->len > avail) /* * Do not skip data nodes in order to optimize @@ -377,14 +379,21 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) */ break; + err = ubifs_shash_update(c, c->jheads[GCHD].log_hash, + snod->node, snod->len); + if (err) + goto out; + err = move_node(c, sleb, snod, wbuf); if (err) goto out; + moved = 1; } /* Move non-data nodes */ list_for_each_entry_safe(snod, tmp, &nondata, list) { - avail = c->leb_size - wbuf->offs - wbuf->used; + avail = c->leb_size - wbuf->offs - wbuf->used - + ubifs_auth_node_sz(c); if (avail < min) break; @@ -402,9 +411,41 @@ static int move_nodes(struct ubifs_info *c, struct ubifs_scan_leb *sleb) continue; } + err = ubifs_shash_update(c, c->jheads[GCHD].log_hash, + snod->node, snod->len); + if (err) + goto out; + err = move_node(c, sleb, snod, wbuf); if (err) goto out; + moved = 1; + } + + if (ubifs_authenticated(c) && moved) { + struct ubifs_auth_node *auth; + + auth = kmalloc(ubifs_auth_node_sz(c), GFP_NOFS); + if (!auth) { + err = -ENOMEM; + goto out; + } + + err = ubifs_prepare_auth_node(c, auth, + c->jheads[GCHD].log_hash); + if (err) { + kfree(auth); + goto out; + } + + err = ubifs_wbuf_write_nolock(wbuf, auth, + ubifs_auth_node_sz(c)); + if (err) { + kfree(auth); + goto out; + } + + ubifs_add_dirt(c, wbuf->lnum, ubifs_auth_node_sz(c)); } if (list_empty(&sleb->nodes) && list_empty(&nondata)) diff --git a/fs/ubifs/io.c b/fs/ubifs/io.c index 099bec94b820..d124117efd42 100644 --- a/fs/ubifs/io.c +++ b/fs/ubifs/io.c @@ -365,20 +365,8 @@ static unsigned long long next_sqnum(struct ubifs_info *c) return sqnum; } -/** - * ubifs_prepare_node - prepare node to be written to flash. - * @c: UBIFS file-system description object - * @node: the node to pad - * @len: node length - * @pad: if the buffer has to be padded - * - * This function prepares node at @node to be written to the media - it - * calculates node CRC, fills the common header, and adds proper padding up to - * the next minimum I/O unit if @pad is not zero. - */ -void ubifs_prepare_node(struct ubifs_info *c, void *node, int len, int pad) +void ubifs_init_node(struct ubifs_info *c, void *node, int len, int pad) { - uint32_t crc; struct ubifs_ch *ch = node; unsigned long long sqnum = next_sqnum(c); @@ -389,8 +377,6 @@ void ubifs_prepare_node(struct ubifs_info *c, void *node, int len, int pad) ch->group_type = UBIFS_NO_NODE_GROUP; ch->sqnum = cpu_to_le64(sqnum); ch->padding[0] = ch->padding[1] = 0; - crc = crc32(UBIFS_CRC32_INIT, node + 8, len - 8); - ch->crc = cpu_to_le32(crc); if (pad) { len = ALIGN(len, 8); @@ -399,6 +385,68 @@ void ubifs_prepare_node(struct ubifs_info *c, void *node, int len, int pad) } } +void ubifs_crc_node(struct ubifs_info *c, void *node, int len) +{ + struct ubifs_ch *ch = node; + uint32_t crc; + + crc = crc32(UBIFS_CRC32_INIT, node + 8, len - 8); + ch->crc = cpu_to_le32(crc); +} + +/** + * ubifs_prepare_node_hmac - prepare node to be written to flash. + * @c: UBIFS file-system description object + * @node: the node to pad + * @len: node length + * @hmac_offs: offset of the HMAC in the node + * @pad: if the buffer has to be padded + * + * This function prepares node at @node to be written to the media - it + * calculates node CRC, fills the common header, and adds proper padding up to + * the next minimum I/O unit if @pad is not zero. if @hmac_offs is positive then + * a HMAC is inserted into the node at the given offset. + * + * This function returns 0 for success or a negative error code otherwise. + */ +int ubifs_prepare_node_hmac(struct ubifs_info *c, void *node, int len, + int hmac_offs, int pad) +{ + int err; + + ubifs_init_node(c, node, len, pad); + + if (hmac_offs > 0) { + err = ubifs_node_insert_hmac(c, node, len, hmac_offs); + if (err) + return err; + } + + ubifs_crc_node(c, node, len); + + return 0; +} + +/** + * ubifs_prepare_node - prepare node to be written to flash. + * @c: UBIFS file-system description object + * @node: the node to pad + * @len: node length + * @pad: if the buffer has to be padded + * + * This function prepares node at @node to be written to the media - it + * calculates node CRC, fills the common header, and adds proper padding up to + * the next minimum I/O unit if @pad is not zero. + */ +void ubifs_prepare_node(struct ubifs_info *c, void *node, int len, int pad) +{ + /* + * Deliberately ignore return value since this function can only fail + * when a hmac offset is given. + */ + ubifs_prepare_node_hmac(c, node, len, 0, pad); +} + /** * ubifs_prep_grp_node - prepare node of a group to be written to flash. * @c: UBIFS file-system description object @@ -849,12 +897,13 @@ out: } /** - * ubifs_write_node - write node to the media. + * ubifs_write_node_hmac - write node to the media. * @c: UBIFS file-system description object * @buf: the node to write * @len: node length * @lnum: logical eraseblock number * @offs: offset within the logical eraseblock + * @hmac_offs: offset of the HMAC within the node * * This function automatically fills node magic number, assigns sequence * number, and calculates node CRC checksum. The length of the @buf buffer has @@ -862,8 +911,8 @@ out: * appends padding node and padding bytes if needed. Returns zero in case of * success and a negative error code in case of failure. */ -int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, - int offs) +int ubifs_write_node_hmac(struct ubifs_info *c, void *buf, int len, int lnum, + int offs, int hmac_offs) { int err, buf_len = ALIGN(len, c->min_io_size); @@ -878,7 +927,10 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, if (c->ro_error) return -EROFS; - ubifs_prepare_node(c, buf, len, 1); + err = ubifs_prepare_node_hmac(c, buf, len, hmac_offs, 1); + if (err) + return err; + err = ubifs_leb_write(c, lnum, buf, offs, buf_len); if (err) ubifs_dump_node(c, buf); @@ -887,6 +939,26 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, } /** + * ubifs_write_node - write node to the media. + * @c: UBIFS file-system description object + * @buf: the node to write + * @len: node length + * @lnum: logical eraseblock number + * @offs: offset within the logical eraseblock + * + * This function automatically fills node magic number, assigns sequence + * number, and calculates node CRC checksum. The length of the @buf buffer has + * to be aligned to the minimal I/O unit size. This function automatically + * appends padding node and padding bytes if needed. Returns zero in case of + * success and a negative error code in case of failure. + */ +int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum, + int offs) +{ + return ubifs_write_node_hmac(c, buf, len, lnum, offs, -1); +} + +/** * ubifs_read_node_wbuf - read node from the media or write-buffer. * @wbuf: wbuf to check for un-written data * @buf: buffer to read to diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 802565a17733..729dc76c83df 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -90,6 +90,12 @@ static inline void zero_trun_node_unused(struct ubifs_trun_node *trun) memset(trun->padding, 0, 12); } +static void ubifs_add_auth_dirt(struct ubifs_info *c, int lnum) +{ + if (ubifs_authenticated(c)) + ubifs_add_dirt(c, lnum, ubifs_auth_node_sz(c)); +} + /** * reserve_space - reserve space in the journal. * @c: UBIFS file-system description object @@ -228,34 +234,33 @@ out_return: return err; } -/** - * write_node - write node to a journal head. - * @c: UBIFS file-system description object - * @jhead: journal head - * @node: node to write - * @len: node length - * @lnum: LEB number written is returned here - * @offs: offset written is returned here - * - * This function writes a node to reserved space of journal head @jhead. - * Returns zero in case of success and a negative error code in case of - * failure. - */ -static int write_node(struct ubifs_info *c, int jhead, void *node, int len, - int *lnum, int *offs) +static int ubifs_hash_nodes(struct ubifs_info *c, void *node, + int len, struct shash_desc *hash) { - struct ubifs_wbuf *wbuf = &c->jheads[jhead].wbuf; + int auth_node_size = ubifs_auth_node_sz(c); + int err; - ubifs_assert(c, jhead != GCHD); + while (1) { + const struct ubifs_ch *ch = node; + int nodelen = le32_to_cpu(ch->len); - *lnum = c->jheads[jhead].wbuf.lnum; - *offs = c->jheads[jhead].wbuf.offs + c->jheads[jhead].wbuf.used; + ubifs_assert(c, len >= auth_node_size); - dbg_jnl("jhead %s, LEB %d:%d, len %d", - dbg_jhead(jhead), *lnum, *offs, len); - ubifs_prepare_node(c, node, len, 0); + if (len == auth_node_size) + break; + + ubifs_assert(c, len > nodelen); + ubifs_assert(c, ch->magic == cpu_to_le32(UBIFS_NODE_MAGIC)); - return ubifs_wbuf_write_nolock(wbuf, node, len); + err = ubifs_shash_update(c, hash, (void *)node, nodelen); + if (err) + return err; + + node += ALIGN(nodelen, 8); + len -= ALIGN(nodelen, 8); + } + + return ubifs_prepare_auth_node(c, node, hash); } /** @@ -268,9 +273,9 @@ static int write_node(struct ubifs_info *c, int jhead, void *node, int len, * @offs: offset written is returned here * @sync: non-zero if the write-buffer has to by synchronized * - * This function is the same as 'write_node()' but it does not assume the - * buffer it is writing is a node, so it does not prepare it (which means - * initializing common header and calculating CRC). + * This function writes data to the reserved space of journal head @jhead. + * Returns zero in case of success and a negative error code in case of + * failure. */ static int write_head(struct ubifs_info *c, int jhead, void *buf, int len, int *lnum, int *offs, int sync) @@ -285,6 +290,12 @@ static int write_head(struct ubifs_info *c, int jhead, void *buf, int len, dbg_jnl("jhead %s, LEB %d:%d, len %d", dbg_jhead(jhead), *lnum, *offs, len); + if (ubifs_authenticated(c)) { + err = ubifs_hash_nodes(c, buf, len, c->jheads[jhead].log_hash); + if (err) + return err; + } + err = ubifs_wbuf_write_nolock(wbuf, buf, len); if (err) return err; @@ -548,6 +559,9 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, struct ubifs_dent_node *dent; struct ubifs_ino_node *ino; union ubifs_key dent_key, ino_key; + u8 hash_dent[UBIFS_HASH_ARR_SZ]; + u8 hash_ino[UBIFS_HASH_ARR_SZ]; + u8 hash_ino_host[UBIFS_HASH_ARR_SZ]; ubifs_assert(c, mutex_is_locked(&host_ui->ui_mutex)); @@ -570,7 +584,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, len = aligned_dlen + aligned_ilen + UBIFS_INO_NODE_SZ; /* Make sure to also account for extended attributes */ - len += host_ui->data_len; + if (ubifs_authenticated(c)) + len += ALIGN(host_ui->data_len, 8) + ubifs_auth_node_sz(c); + else + len += host_ui->data_len; dent = kzalloc(len, GFP_NOFS); if (!dent) @@ -602,11 +619,21 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, zero_dent_node_unused(dent); ubifs_prep_grp_node(c, dent, dlen, 0); + err = ubifs_node_calc_hash(c, dent, hash_dent); + if (err) + goto out_release; ino = (void *)dent + aligned_dlen; pack_inode(c, ino, inode, 0); + err = ubifs_node_calc_hash(c, ino, hash_ino); + if (err) + goto out_release; + ino = (void *)ino + aligned_ilen; pack_inode(c, ino, dir, 1); + err = ubifs_node_calc_hash(c, ino, hash_ino_host); + if (err) + goto out_release; if (last_reference) { err = ubifs_add_orphan(c, inode->i_ino); @@ -628,6 +655,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, } release_head(c, BASEHD); kfree(dent); + ubifs_add_auth_dirt(c, lnum); if (deletion) { if (nm->hash) @@ -638,7 +666,8 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, goto out_ro; err = ubifs_add_dirt(c, lnum, dlen); } else - err = ubifs_tnc_add_nm(c, &dent_key, lnum, dent_offs, dlen, nm); + err = ubifs_tnc_add_nm(c, &dent_key, lnum, dent_offs, dlen, + hash_dent, nm); if (err) goto out_ro; @@ -650,14 +679,14 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, */ ino_key_init(c, &ino_key, inode->i_ino); ino_offs = dent_offs + aligned_dlen; - err = ubifs_tnc_add(c, &ino_key, lnum, ino_offs, ilen); + err = ubifs_tnc_add(c, &ino_key, lnum, ino_offs, ilen, hash_ino); if (err) goto out_ro; ino_key_init(c, &ino_key, dir->i_ino); ino_offs += aligned_ilen; err = ubifs_tnc_add(c, &ino_key, lnum, ino_offs, - UBIFS_INO_NODE_SZ + host_ui->data_len); + UBIFS_INO_NODE_SZ + host_ui->data_len, hash_ino_host); if (err) goto out_ro; @@ -706,10 +735,12 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode, const union ubifs_key *key, const void *buf, int len) { struct ubifs_data_node *data; - int err, lnum, offs, compr_type, out_len, compr_len; + int err, lnum, offs, compr_type, out_len, compr_len, auth_len; int dlen = COMPRESSED_DATA_NODE_BUF_SZ, allocated = 1; + int write_len; struct ubifs_inode *ui = ubifs_inode(inode); bool encrypted = ubifs_crypt_is_encrypted(inode); + u8 hash[UBIFS_HASH_ARR_SZ]; dbg_jnlk(key, "ino %lu, blk %u, len %d, key ", (unsigned long)key_inum(c, key), key_block(c, key), len); @@ -718,7 +749,9 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode, if (encrypted) dlen += UBIFS_CIPHER_BLOCK_SIZE; - data = kmalloc(dlen, GFP_NOFS | __GFP_NOWARN); + auth_len = ubifs_auth_node_sz(c); + + data = kmalloc(dlen + auth_len, GFP_NOFS | __GFP_NOWARN); if (!data) { /* * Fall-back to the write reserve buffer. Note, we might be @@ -757,20 +790,33 @@ int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode, } dlen = UBIFS_DATA_NODE_SZ + out_len; + if (ubifs_authenticated(c)) + write_len = ALIGN(dlen, 8) + auth_len; + else + write_len = dlen; + data->compr_type = cpu_to_le16(compr_type); /* Make reservation before allocating sequence numbers */ - err = make_reservation(c, DATAHD, dlen); + err = make_reservation(c, DATAHD, write_len); if (err) goto out_free; - err = write_node(c, DATAHD, data, dlen, &lnum, &offs); + ubifs_prepare_node(c, data, dlen, 0); + err = write_head(c, DATAHD, data, write_len, &lnum, &offs, 0); + if (err) + goto out_release; + + err = ubifs_node_calc_hash(c, data, hash); if (err) goto out_release; + ubifs_wbuf_add_ino_nolock(&c->jheads[DATAHD].wbuf, key_inum(c, key)); release_head(c, DATAHD); - err = ubifs_tnc_add(c, key, lnum, offs, dlen); + ubifs_add_auth_dirt(c, lnum); + + err = ubifs_tnc_add(c, key, lnum, offs, dlen, hash); if (err) goto out_ro; @@ -808,7 +854,9 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) int err, lnum, offs; struct ubifs_ino_node *ino; struct ubifs_inode *ui = ubifs_inode(inode); - int sync = 0, len = UBIFS_INO_NODE_SZ, last_reference = !inode->i_nlink; + int sync = 0, write_len, ilen = UBIFS_INO_NODE_SZ; + int last_reference = !inode->i_nlink; + u8 hash[UBIFS_HASH_ARR_SZ]; dbg_jnl("ino %lu, nlink %u", inode->i_ino, inode->i_nlink); @@ -817,20 +865,30 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) * need to synchronize the write-buffer either. */ if (!last_reference) { - len += ui->data_len; + ilen += ui->data_len; sync = IS_SYNC(inode); } - ino = kmalloc(len, GFP_NOFS); + + if (ubifs_authenticated(c)) + write_len = ALIGN(ilen, 8) + ubifs_auth_node_sz(c); + else + write_len = ilen; + + ino = kmalloc(write_len, GFP_NOFS); if (!ino) return -ENOMEM; /* Make reservation before allocating sequence numbers */ - err = make_reservation(c, BASEHD, len); + err = make_reservation(c, BASEHD, write_len); if (err) goto out_free; pack_inode(c, ino, inode, 1); - err = write_head(c, BASEHD, ino, len, &lnum, &offs, sync); + err = ubifs_node_calc_hash(c, ino, hash); + if (err) + goto out_release; + + err = write_head(c, BASEHD, ino, write_len, &lnum, &offs, sync); if (err) goto out_release; if (!sync) @@ -838,17 +896,19 @@ int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode) inode->i_ino); release_head(c, BASEHD); + ubifs_add_auth_dirt(c, lnum); + if (last_reference) { err = ubifs_tnc_remove_ino(c, inode->i_ino); if (err) goto out_ro; ubifs_delete_orphan(c, inode->i_ino); - err = ubifs_add_dirt(c, lnum, len); + err = ubifs_add_dirt(c, lnum, ilen); } else { union ubifs_key key; ino_key_init(c, &key, inode->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, len); + err = ubifs_tnc_add(c, &key, lnum, offs, ilen, hash); } if (err) goto out_ro; @@ -958,6 +1018,10 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, int aligned_dlen1, aligned_dlen2; int twoparents = (fst_dir != snd_dir); void *p; + u8 hash_dent1[UBIFS_HASH_ARR_SZ]; + u8 hash_dent2[UBIFS_HASH_ARR_SZ]; + u8 hash_p1[UBIFS_HASH_ARR_SZ]; + u8 hash_p2[UBIFS_HASH_ARR_SZ]; ubifs_assert(c, ubifs_inode(fst_dir)->data_len == 0); ubifs_assert(c, ubifs_inode(snd_dir)->data_len == 0); @@ -973,6 +1037,8 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, if (twoparents) len += plen; + len += ubifs_auth_node_sz(c); + dent1 = kzalloc(len, GFP_NOFS); if (!dent1) return -ENOMEM; @@ -993,6 +1059,9 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, set_dent_cookie(c, dent1); zero_dent_node_unused(dent1); ubifs_prep_grp_node(c, dent1, dlen1, 0); + err = ubifs_node_calc_hash(c, dent1, hash_dent1); + if (err) + goto out_release; /* Make new dent for 2nd entry */ dent2 = (void *)dent1 + aligned_dlen1; @@ -1006,14 +1075,26 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, set_dent_cookie(c, dent2); zero_dent_node_unused(dent2); ubifs_prep_grp_node(c, dent2, dlen2, 0); + err = ubifs_node_calc_hash(c, dent2, hash_dent2); + if (err) + goto out_release; p = (void *)dent2 + aligned_dlen2; - if (!twoparents) + if (!twoparents) { pack_inode(c, p, fst_dir, 1); - else { + err = ubifs_node_calc_hash(c, p, hash_p1); + if (err) + goto out_release; + } else { pack_inode(c, p, fst_dir, 0); + err = ubifs_node_calc_hash(c, p, hash_p1); + if (err) + goto out_release; p += ALIGN(plen, 8); pack_inode(c, p, snd_dir, 1); + err = ubifs_node_calc_hash(c, p, hash_p2); + if (err) + goto out_release; } err = write_head(c, BASEHD, dent1, len, &lnum, &offs, sync); @@ -1027,28 +1108,30 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, } release_head(c, BASEHD); + ubifs_add_auth_dirt(c, lnum); + dent_key_init(c, &key, snd_dir->i_ino, snd_nm); - err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, snd_nm); + err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, hash_dent1, snd_nm); if (err) goto out_ro; offs += aligned_dlen1; dent_key_init(c, &key, fst_dir->i_ino, fst_nm); - err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, fst_nm); + err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, fst_nm); if (err) goto out_ro; offs += aligned_dlen2; ino_key_init(c, &key, fst_dir->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, plen); + err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_p1); if (err) goto out_ro; if (twoparents) { offs += ALIGN(plen, 8); ino_key_init(c, &key, snd_dir->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, plen); + err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_p2); if (err) goto out_ro; } @@ -1101,6 +1184,11 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, int last_reference = !!(new_inode && new_inode->i_nlink == 0); int move = (old_dir != new_dir); struct ubifs_inode *uninitialized_var(new_ui); + u8 hash_old_dir[UBIFS_HASH_ARR_SZ]; + u8 hash_new_dir[UBIFS_HASH_ARR_SZ]; + u8 hash_new_inode[UBIFS_HASH_ARR_SZ]; + u8 hash_dent1[UBIFS_HASH_ARR_SZ]; + u8 hash_dent2[UBIFS_HASH_ARR_SZ]; ubifs_assert(c, ubifs_inode(old_dir)->data_len == 0); ubifs_assert(c, ubifs_inode(new_dir)->data_len == 0); @@ -1123,6 +1211,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); if (move) len += plen; + + len += ubifs_auth_node_sz(c); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -1143,6 +1234,9 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, set_dent_cookie(c, dent); zero_dent_node_unused(dent); ubifs_prep_grp_node(c, dent, dlen1, 0); + err = ubifs_node_calc_hash(c, dent, hash_dent1); + if (err) + goto out_release; dent2 = (void *)dent + aligned_dlen1; dent2->ch.node_type = UBIFS_DENT_NODE; @@ -1162,19 +1256,36 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, set_dent_cookie(c, dent2); zero_dent_node_unused(dent2); ubifs_prep_grp_node(c, dent2, dlen2, 0); + err = ubifs_node_calc_hash(c, dent2, hash_dent2); + if (err) + goto out_release; p = (void *)dent2 + aligned_dlen2; if (new_inode) { pack_inode(c, p, new_inode, 0); + err = ubifs_node_calc_hash(c, p, hash_new_inode); + if (err) + goto out_release; + p += ALIGN(ilen, 8); } - if (!move) + if (!move) { pack_inode(c, p, old_dir, 1); - else { + err = ubifs_node_calc_hash(c, p, hash_old_dir); + if (err) + goto out_release; + } else { pack_inode(c, p, old_dir, 0); + err = ubifs_node_calc_hash(c, p, hash_old_dir); + if (err) + goto out_release; + p += ALIGN(plen, 8); pack_inode(c, p, new_dir, 1); + err = ubifs_node_calc_hash(c, p, hash_new_dir); + if (err) + goto out_release; } if (last_reference) { @@ -1200,15 +1311,17 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, } release_head(c, BASEHD); + ubifs_add_auth_dirt(c, lnum); + dent_key_init(c, &key, new_dir->i_ino, new_nm); - err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, new_nm); + err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen1, hash_dent1, new_nm); if (err) goto out_ro; offs += aligned_dlen1; if (whiteout) { dent_key_init(c, &key, old_dir->i_ino, old_nm); - err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, old_nm); + err = ubifs_tnc_add_nm(c, &key, lnum, offs, dlen2, hash_dent2, old_nm); if (err) goto out_ro; @@ -1227,21 +1340,21 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, offs += aligned_dlen2; if (new_inode) { ino_key_init(c, &key, new_inode->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, ilen); + err = ubifs_tnc_add(c, &key, lnum, offs, ilen, hash_new_inode); if (err) goto out_ro; offs += ALIGN(ilen, 8); } ino_key_init(c, &key, old_dir->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, plen); + err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_old_dir); if (err) goto out_ro; if (move) { offs += ALIGN(plen, 8); ino_key_init(c, &key, new_dir->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, plen); + err = ubifs_tnc_add(c, &key, lnum, offs, plen, hash_new_dir); if (err) goto out_ro; } @@ -1360,6 +1473,8 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, struct ubifs_inode *ui = ubifs_inode(inode); ino_t inum = inode->i_ino; unsigned int blk; + u8 hash_ino[UBIFS_HASH_ARR_SZ]; + u8 hash_dn[UBIFS_HASH_ARR_SZ]; dbg_jnl("ino %lu, size %lld -> %lld", (unsigned long)inum, old_size, new_size); @@ -1369,6 +1484,9 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, sz = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ + UBIFS_MAX_DATA_NODE_SZ * WORST_COMPR_FACTOR; + + sz += ubifs_auth_node_sz(c); + ino = kmalloc(sz, GFP_NOFS); if (!ino) return -ENOMEM; @@ -1414,16 +1532,28 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, /* Must make reservation before allocating sequence numbers */ len = UBIFS_TRUN_NODE_SZ + UBIFS_INO_NODE_SZ; - if (dlen) + + if (ubifs_authenticated(c)) + len += ALIGN(dlen, 8) + ubifs_auth_node_sz(c); + else len += dlen; + err = make_reservation(c, BASEHD, len); if (err) goto out_free; pack_inode(c, ino, inode, 0); + err = ubifs_node_calc_hash(c, ino, hash_ino); + if (err) + goto out_release; + ubifs_prep_grp_node(c, trun, UBIFS_TRUN_NODE_SZ, dlen ? 0 : 1); - if (dlen) + if (dlen) { ubifs_prep_grp_node(c, dn, dlen, 1); + err = ubifs_node_calc_hash(c, dn, hash_dn); + if (err) + goto out_release; + } err = write_head(c, BASEHD, ino, len, &lnum, &offs, sync); if (err) @@ -1432,15 +1562,17 @@ int ubifs_jnl_truncate(struct ubifs_info *c, const struct inode *inode, ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, inum); release_head(c, BASEHD); + ubifs_add_auth_dirt(c, lnum); + if (dlen) { sz = offs + UBIFS_INO_NODE_SZ + UBIFS_TRUN_NODE_SZ; - err = ubifs_tnc_add(c, &key, lnum, sz, dlen); + err = ubifs_tnc_add(c, &key, lnum, sz, dlen, hash_dn); if (err) goto out_ro; } ino_key_init(c, &key, inum); - err = ubifs_tnc_add(c, &key, lnum, offs, UBIFS_INO_NODE_SZ); + err = ubifs_tnc_add(c, &key, lnum, offs, UBIFS_INO_NODE_SZ, hash_ino); if (err) goto out_ro; @@ -1495,12 +1627,13 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, const struct inode *inode, const struct fscrypt_name *nm) { - int err, xlen, hlen, len, lnum, xent_offs, aligned_xlen; + int err, xlen, hlen, len, lnum, xent_offs, aligned_xlen, write_len; struct ubifs_dent_node *xent; struct ubifs_ino_node *ino; union ubifs_key xent_key, key1, key2; int sync = IS_DIRSYNC(host); struct ubifs_inode *host_ui = ubifs_inode(host); + u8 hash[UBIFS_HASH_ARR_SZ]; ubifs_assert(c, inode->i_nlink == 0); ubifs_assert(c, mutex_is_locked(&host_ui->ui_mutex)); @@ -1514,12 +1647,14 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, hlen = host_ui->data_len + UBIFS_INO_NODE_SZ; len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8); - xent = kzalloc(len, GFP_NOFS); + write_len = len + ubifs_auth_node_sz(c); + + xent = kzalloc(write_len, GFP_NOFS); if (!xent) return -ENOMEM; /* Make reservation before allocating sequence numbers */ - err = make_reservation(c, BASEHD, len); + err = make_reservation(c, BASEHD, write_len); if (err) { kfree(xent); return err; @@ -1540,11 +1675,16 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, pack_inode(c, ino, inode, 0); ino = (void *)ino + UBIFS_INO_NODE_SZ; pack_inode(c, ino, host, 1); + err = ubifs_node_calc_hash(c, ino, hash); + if (err) + goto out_release; - err = write_head(c, BASEHD, xent, len, &lnum, &xent_offs, sync); + err = write_head(c, BASEHD, xent, write_len, &lnum, &xent_offs, sync); if (!sync && !err) ubifs_wbuf_add_ino_nolock(&c->jheads[BASEHD].wbuf, host->i_ino); release_head(c, BASEHD); + + ubifs_add_auth_dirt(c, lnum); kfree(xent); if (err) goto out_ro; @@ -1572,7 +1712,7 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, /* And update TNC with the new host inode position */ ino_key_init(c, &key1, host->i_ino); - err = ubifs_tnc_add(c, &key1, lnum, xent_offs + len - hlen, hlen); + err = ubifs_tnc_add(c, &key1, lnum, xent_offs + len - hlen, hlen, hash); if (err) goto out_ro; @@ -1583,6 +1723,9 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, mark_inode_clean(c, host_ui); return 0; +out_release: + kfree(xent); + release_head(c, BASEHD); out_ro: ubifs_ro_mode(c, err); finish_reservation(c); @@ -1610,6 +1753,8 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, struct ubifs_ino_node *ino; union ubifs_key key; int sync = IS_DIRSYNC(host); + u8 hash_host[UBIFS_HASH_ARR_SZ]; + u8 hash[UBIFS_HASH_ARR_SZ]; dbg_jnl("ino %lu, ino %lu", host->i_ino, inode->i_ino); ubifs_assert(c, host->i_nlink > 0); @@ -1621,6 +1766,8 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, aligned_len1 = ALIGN(len1, 8); aligned_len = aligned_len1 + ALIGN(len2, 8); + aligned_len += ubifs_auth_node_sz(c); + ino = kzalloc(aligned_len, GFP_NOFS); if (!ino) return -ENOMEM; @@ -1631,7 +1778,13 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, goto out_free; pack_inode(c, ino, host, 0); + err = ubifs_node_calc_hash(c, ino, hash_host); + if (err) + goto out_release; pack_inode(c, (void *)ino + aligned_len1, inode, 1); + err = ubifs_node_calc_hash(c, (void *)ino + aligned_len1, hash); + if (err) + goto out_release; err = write_head(c, BASEHD, ino, aligned_len, &lnum, &offs, 0); if (!sync && !err) { @@ -1644,13 +1797,15 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, if (err) goto out_ro; + ubifs_add_auth_dirt(c, lnum); + ino_key_init(c, &key, host->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs, len1); + err = ubifs_tnc_add(c, &key, lnum, offs, len1, hash_host); if (err) goto out_ro; ino_key_init(c, &key, inode->i_ino); - err = ubifs_tnc_add(c, &key, lnum, offs + aligned_len1, len2); + err = ubifs_tnc_add(c, &key, lnum, offs + aligned_len1, len2, hash); if (err) goto out_ro; @@ -1662,6 +1817,8 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, kfree(ino); return 0; +out_release: + release_head(c, BASEHD); out_ro: ubifs_ro_mode(c, err); finish_reservation(c); diff --git a/fs/ubifs/log.c b/fs/ubifs/log.c index 86b0828f5499..15fd854149bb 100644 --- a/fs/ubifs/log.c +++ b/fs/ubifs/log.c @@ -236,6 +236,7 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) bud->lnum = lnum; bud->start = offs; bud->jhead = jhead; + bud->log_hash = NULL; ref->ch.node_type = UBIFS_REF_NODE; ref->lnum = cpu_to_le32(bud->lnum); @@ -275,6 +276,14 @@ int ubifs_add_bud_to_log(struct ubifs_info *c, int jhead, int lnum, int offs) if (err) goto out_unlock; + err = ubifs_shash_update(c, c->log_hash, ref, UBIFS_REF_NODE_SZ); + if (err) + goto out_unlock; + + err = ubifs_shash_copy_state(c, c->log_hash, c->jheads[jhead].log_hash); + if (err) + goto out_unlock; + c->lhead_offs += c->ref_node_alsz; ubifs_add_bud(c, bud); @@ -377,6 +386,14 @@ int ubifs_log_start_commit(struct ubifs_info *c, int *ltail_lnum) cs->cmt_no = cpu_to_le64(c->cmt_no); ubifs_prepare_node(c, cs, UBIFS_CS_NODE_SZ, 0); + err = ubifs_shash_init(c, c->log_hash); + if (err) + goto out; + + err = ubifs_shash_update(c, c->log_hash, cs, UBIFS_CS_NODE_SZ); + if (err < 0) + goto out; + /* * Note, we do not lock 'c->log_mutex' because this is the commit start * phase and we are exclusively using the log. And we do not lock @@ -402,6 +419,12 @@ int ubifs_log_start_commit(struct ubifs_info *c, int *ltail_lnum) ubifs_prepare_node(c, ref, UBIFS_REF_NODE_SZ, 0); len += UBIFS_REF_NODE_SZ; + + err = ubifs_shash_update(c, c->log_hash, ref, + UBIFS_REF_NODE_SZ); + if (err) + goto out; + ubifs_shash_copy_state(c, c->log_hash, c->jheads[i].log_hash); } ubifs_pad(c, buf + len, ALIGN(len, c->min_io_size) - len); @@ -516,6 +539,7 @@ int ubifs_log_post_commit(struct ubifs_info *c, int old_ltail_lnum) if (err) return err; list_del(&bud->list); + kfree(bud->log_hash); kfree(bud); } mutex_lock(&c->log_mutex); diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index 31393370e334..d1d5e96350dd 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -604,11 +604,12 @@ static int calc_pnode_num_from_parent(const struct ubifs_info *c, * @lpt_first: LEB number of first LPT LEB * @lpt_lebs: number of LEBs for LPT is passed and returned here * @big_lpt: use big LPT model is passed and returned here + * @hash: hash of the LPT is returned here * * This function returns %0 on success and a negative error code on failure. */ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, - int *lpt_lebs, int *big_lpt) + int *lpt_lebs, int *big_lpt, u8 *hash) { int lnum, err = 0, node_sz, iopos, i, j, cnt, len, alen, row; int blnum, boffs, bsz, bcnt; @@ -617,6 +618,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, void *buf = NULL, *p; struct ubifs_lpt_lprops *ltab = NULL; int *lsave = NULL; + struct shash_desc *desc; err = calc_dflt_lpt_geom(c, main_lebs, big_lpt); if (err) @@ -630,6 +632,10 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, /* Needed by 'ubifs_pack_lsave()' */ c->main_first = c->leb_cnt - *main_lebs; + desc = ubifs_hash_get_desc(c); + if (IS_ERR(desc)) + return PTR_ERR(desc); + lsave = kmalloc_array(c->lsave_cnt, sizeof(int), GFP_KERNEL); pnode = kzalloc(sizeof(struct ubifs_pnode), GFP_KERNEL); nnode = kzalloc(sizeof(struct ubifs_nnode), GFP_KERNEL); @@ -677,6 +683,10 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, /* Add first pnode */ ubifs_pack_pnode(c, p, pnode); + err = ubifs_shash_update(c, desc, p, c->pnode_sz); + if (err) + goto out; + p += c->pnode_sz; len = c->pnode_sz; pnode->num += 1; @@ -711,6 +721,10 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, len = 0; } ubifs_pack_pnode(c, p, pnode); + err = ubifs_shash_update(c, desc, p, c->pnode_sz); + if (err) + goto out; + p += c->pnode_sz; len += c->pnode_sz; /* @@ -830,6 +844,10 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, if (err) goto out; + err = ubifs_shash_final(c, desc, hash); + if (err) + goto out; + c->nhead_lnum = lnum; c->nhead_offs = ALIGN(len, c->min_io_size); @@ -853,6 +871,7 @@ int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, dbg_lp("LPT lsave is at %d:%d", c->lsave_lnum, c->lsave_offs); out: c->ltab = NULL; + kfree(desc); kfree(lsave); vfree(ltab); vfree(buf); @@ -1439,26 +1458,25 @@ struct ubifs_pnode *ubifs_get_pnode(struct ubifs_info *c, } /** - * ubifs_lpt_lookup - lookup LEB properties in the LPT. + * ubifs_pnode_lookup - lookup a pnode in the LPT. * @c: UBIFS file-system description object - * @lnum: LEB number to lookup + * @i: pnode number (0 to (main_lebs - 1) / UBIFS_LPT_FANOUT) * - * This function returns a pointer to the LEB properties on success or a - * negative error code on failure. + * This function returns a pointer to the pnode on success or a negative + * error code on failure. */ -struct ubifs_lprops *ubifs_lpt_lookup(struct ubifs_info *c, int lnum) +struct ubifs_pnode *ubifs_pnode_lookup(struct ubifs_info *c, int i) { - int err, i, h, iip, shft; + int err, h, iip, shft; struct ubifs_nnode *nnode; - struct ubifs_pnode *pnode; if (!c->nroot) { err = ubifs_read_nnode(c, NULL, 0); if (err) return ERR_PTR(err); } + i <<= UBIFS_LPT_FANOUT_SHIFT; nnode = c->nroot; - i = lnum - c->main_first; shft = c->lpt_hght * UBIFS_LPT_FANOUT_SHIFT; for (h = 1; h < c->lpt_hght; h++) { iip = ((i >> shft) & (UBIFS_LPT_FANOUT - 1)); @@ -1468,7 +1486,24 @@ struct ubifs_lprops *ubifs_lpt_lookup(struct ubifs_info *c, int lnum) return ERR_CAST(nnode); } iip = ((i >> shft) & (UBIFS_LPT_FANOUT - 1)); - pnode = ubifs_get_pnode(c, nnode, iip); + return ubifs_get_pnode(c, nnode, iip); +} + +/** + * ubifs_lpt_lookup - lookup LEB properties in the LPT. + * @c: UBIFS file-system description object + * @lnum: LEB number to lookup + * + * This function returns a pointer to the LEB properties on success or a + * negative error code on failure. + */ +struct ubifs_lprops *ubifs_lpt_lookup(struct ubifs_info *c, int lnum) +{ + int i, iip; + struct ubifs_pnode *pnode; + + i = lnum - c->main_first; + pnode = ubifs_pnode_lookup(c, i >> UBIFS_LPT_FANOUT_SHIFT); if (IS_ERR(pnode)) return ERR_CAST(pnode); iip = (i & (UBIFS_LPT_FANOUT - 1)); @@ -1620,6 +1655,131 @@ struct ubifs_lprops *ubifs_lpt_lookup_dirty(struct ubifs_info *c, int lnum) } /** + * ubifs_lpt_calc_hash - Calculate hash of the LPT pnodes + * @c: UBIFS file-system description object + * @hash: the returned hash of the LPT pnodes + * + * This function iterates over the LPT pnodes and creates a hash over them. + * Returns 0 for success or a negative error code otherwise. + */ +int ubifs_lpt_calc_hash(struct ubifs_info *c, u8 *hash) +{ + struct ubifs_nnode *nnode, *nn; + struct ubifs_cnode *cnode; + struct shash_desc *desc; + int iip = 0, i; + int bufsiz = max_t(int, c->nnode_sz, c->pnode_sz); + void *buf; + int err; + + if (!ubifs_authenticated(c)) + return 0; + + desc = ubifs_hash_get_desc(c); + if (IS_ERR(desc)) + return PTR_ERR(desc); + + buf = kmalloc(bufsiz, GFP_NOFS); + if (!buf) { + err = -ENOMEM; + goto out; + } + + if (!c->nroot) { + err = ubifs_read_nnode(c, NULL, 0); + if (err) + return err; + } + + cnode = (struct ubifs_cnode *)c->nroot; + + while (cnode) { + nnode = cnode->parent; + nn = (struct ubifs_nnode *)cnode; + if (cnode->level > 1) { + while (iip < UBIFS_LPT_FANOUT) { + if (nn->nbranch[iip].lnum == 0) { + /* Go right */ + iip++; + continue; + } + + nnode = ubifs_get_nnode(c, nn, iip); + if (IS_ERR(nnode)) { + err = PTR_ERR(nnode); + goto out; + } + + /* Go down */ + iip = 0; + cnode = (struct ubifs_cnode *)nnode; + break; + } + if (iip < UBIFS_LPT_FANOUT) + continue; + } else { + struct ubifs_pnode *pnode; + + for (i = 0; i < UBIFS_LPT_FANOUT; i++) { + if (nn->nbranch[i].lnum == 0) + continue; + pnode = ubifs_get_pnode(c, nn, i); + if (IS_ERR(pnode)) { + err = PTR_ERR(pnode); + goto out; + } + + ubifs_pack_pnode(c, buf, pnode); + err = ubifs_shash_update(c, desc, buf, + c->pnode_sz); + if (err) + goto out; + } + } + /* Go up and to the right */ + iip = cnode->iip + 1; + cnode = (struct ubifs_cnode *)nnode; + } + + err = ubifs_shash_final(c, desc, hash); +out: + kfree(desc); + kfree(buf); + + return err; +} + +/** + * lpt_check_hash - check the hash of the LPT. + * @c: UBIFS file-system description object + * + * This function calculates a hash over all pnodes in the LPT and compares it with + * the hash stored in the master node. Returns %0 on success and a negative error + * code on failure. + */ +static int lpt_check_hash(struct ubifs_info *c) +{ + int err; + u8 hash[UBIFS_HASH_ARR_SZ]; + + if (!ubifs_authenticated(c)) + return 0; + + err = ubifs_lpt_calc_hash(c, hash); + if (err) + return err; + + if (ubifs_check_hash(c, c->mst_node->hash_lpt, hash)) { + err = -EPERM; + ubifs_err(c, "Failed to authenticate LPT"); + } else { + err = 0; + } + + return err; +} + +/** * lpt_init_rd - initialize the LPT for reading. * @c: UBIFS file-system description object * @@ -1660,6 +1820,10 @@ static int lpt_init_rd(struct ubifs_info *c) if (err) return err; + err = lpt_check_hash(c); + if (err) + return err; + dbg_lp("space_bits %d", c->space_bits); dbg_lp("lpt_lnum_bits %d", c->lpt_lnum_bits); dbg_lp("lpt_offs_bits %d", c->lpt_offs_bits); diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index 7ce30994bbba..1f88caffdf2a 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -619,38 +619,6 @@ static struct ubifs_pnode *next_pnode_to_dirty(struct ubifs_info *c, } /** - * pnode_lookup - lookup a pnode in the LPT. - * @c: UBIFS file-system description object - * @i: pnode number (0 to (main_lebs - 1) / UBIFS_LPT_FANOUT)) - * - * This function returns a pointer to the pnode on success or a negative - * error code on failure. - */ -static struct ubifs_pnode *pnode_lookup(struct ubifs_info *c, int i) -{ - int err, h, iip, shft; - struct ubifs_nnode *nnode; - - if (!c->nroot) { - err = ubifs_read_nnode(c, NULL, 0); - if (err) - return ERR_PTR(err); - } - i <<= UBIFS_LPT_FANOUT_SHIFT; - nnode = c->nroot; - shft = c->lpt_hght * UBIFS_LPT_FANOUT_SHIFT; - for (h = 1; h < c->lpt_hght; h++) { - iip = ((i >> shft) & (UBIFS_LPT_FANOUT - 1)); - shft -= UBIFS_LPT_FANOUT_SHIFT; - nnode = ubifs_get_nnode(c, nnode, iip); - if (IS_ERR(nnode)) - return ERR_CAST(nnode); - } - iip = ((i >> shft) & (UBIFS_LPT_FANOUT - 1)); - return ubifs_get_pnode(c, nnode, iip); -} - -/** * add_pnode_dirt - add dirty space to LPT LEB properties. * @c: UBIFS file-system description object * @pnode: pnode for which to add dirt @@ -702,7 +670,7 @@ static int make_tree_dirty(struct ubifs_info *c) { struct ubifs_pnode *pnode; - pnode = pnode_lookup(c, 0); + pnode = ubifs_pnode_lookup(c, 0); if (IS_ERR(pnode)) return PTR_ERR(pnode); @@ -956,7 +924,7 @@ static int make_pnode_dirty(struct ubifs_info *c, int node_num, int lnum, struct ubifs_pnode *pnode; struct ubifs_nbranch *branch; - pnode = pnode_lookup(c, node_num); + pnode = ubifs_pnode_lookup(c, node_num); if (IS_ERR(pnode)) return PTR_ERR(pnode); branch = &pnode->parent->nbranch[pnode->iip]; @@ -1279,6 +1247,10 @@ int ubifs_lpt_start_commit(struct ubifs_info *c) if (err) goto out; + err = ubifs_lpt_calc_hash(c, c->mst_node->hash_lpt); + if (err) + goto out; + /* Copy the LPT's own lprops for end commit to write */ memcpy(c->ltab_cmt, c->ltab, sizeof(struct ubifs_lpt_lprops) * c->lpt_lebs); @@ -1558,7 +1530,7 @@ static int dbg_is_pnode_dirty(struct ubifs_info *c, int lnum, int offs) struct ubifs_nbranch *branch; cond_resched(); - pnode = pnode_lookup(c, i); + pnode = ubifs_pnode_lookup(c, i); if (IS_ERR(pnode)) return PTR_ERR(pnode); branch = &pnode->parent->nbranch[pnode->iip]; @@ -1710,7 +1682,7 @@ int dbg_check_ltab(struct ubifs_info *c) for (i = 0; i < cnt; i++) { struct ubifs_pnode *pnode; - pnode = pnode_lookup(c, i); + pnode = ubifs_pnode_lookup(c, i); if (IS_ERR(pnode)) return PTR_ERR(pnode); cond_resched(); diff --git a/fs/ubifs/master.c b/fs/ubifs/master.c index 9df4a41bba52..5ea51bbd14c7 100644 --- a/fs/ubifs/master.c +++ b/fs/ubifs/master.c @@ -25,6 +25,42 @@ #include "ubifs.h" /** + * ubifs_compare_master_node - compare two UBIFS master nodes + * @c: UBIFS file-system description object + * @m1: the first node + * @m2: the second node + * + * This function compares two UBIFS master nodes. Returns 0 if they are equal + * and nonzero if not. + */ +int ubifs_compare_master_node(struct ubifs_info *c, void *m1, void *m2) +{ + int ret; + int behind; + int hmac_offs = offsetof(struct ubifs_mst_node, hmac); + + /* + * Do not compare the common node header since the sequence number and + * hence the CRC are different. + */ + ret = memcmp(m1 + UBIFS_CH_SZ, m2 + UBIFS_CH_SZ, + hmac_offs - UBIFS_CH_SZ); + if (ret) + return ret; + + /* + * Do not compare the embedded HMAC aswell which also must be different + * due to the different common node header. + */ + behind = hmac_offs + UBIFS_MAX_HMAC_LEN; + + if (UBIFS_MST_NODE_SZ > behind) + return memcmp(m1 + behind, m2 + behind, UBIFS_MST_NODE_SZ - behind); + + return 0; +} + +/** * scan_for_master - search the valid master node. * @c: UBIFS file-system description object * @@ -37,7 +73,7 @@ static int scan_for_master(struct ubifs_info *c) { struct ubifs_scan_leb *sleb; struct ubifs_scan_node *snod; - int lnum, offs = 0, nodes_cnt; + int lnum, offs = 0, nodes_cnt, err; lnum = UBIFS_MST_LNUM; @@ -69,12 +105,23 @@ static int scan_for_master(struct ubifs_info *c) goto out_dump; if (snod->offs != offs) goto out; - if (memcmp((void *)c->mst_node + UBIFS_CH_SZ, - (void *)snod->node + UBIFS_CH_SZ, - UBIFS_MST_NODE_SZ - UBIFS_CH_SZ)) + if (ubifs_compare_master_node(c, c->mst_node, snod->node)) goto out; + c->mst_offs = offs; ubifs_scan_destroy(sleb); + + if (!ubifs_authenticated(c)) + return 0; + + err = ubifs_node_verify_hmac(c, c->mst_node, + sizeof(struct ubifs_mst_node), + offsetof(struct ubifs_mst_node, hmac)); + if (err) { + ubifs_err(c, "Failed to verify master node HMAC"); + return -EPERM; + } + return 0; out: @@ -305,6 +352,8 @@ int ubifs_read_master(struct ubifs_info *c) c->lst.total_dead = le64_to_cpu(c->mst_node->total_dead); c->lst.total_dark = le64_to_cpu(c->mst_node->total_dark); + ubifs_copy_hash(c, c->mst_node->hash_root_idx, c->zroot.hash); + c->calc_idx_sz = c->bi.old_idx_sz; if (c->mst_node->flags & cpu_to_le32(UBIFS_MST_NO_ORPHS)) @@ -378,7 +427,9 @@ int ubifs_write_master(struct ubifs_info *c) c->mst_offs = offs; c->mst_node->highest_inum = cpu_to_le64(c->highest_inum); - err = ubifs_write_node(c, c->mst_node, len, lnum, offs); + ubifs_copy_hash(c, c->zroot.hash, c->mst_node->hash_root_idx); + err = ubifs_write_node_hmac(c, c->mst_node, len, lnum, offs, + offsetof(struct ubifs_mst_node, hmac)); if (err) return err; @@ -389,7 +440,8 @@ int ubifs_write_master(struct ubifs_info *c) if (err) return err; } - err = ubifs_write_node(c, c->mst_node, len, lnum, offs); + err = ubifs_write_node_hmac(c, c->mst_node, len, lnum, offs, + offsetof(struct ubifs_mst_node, hmac)); return err; } diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h index 21d35d7dd975..6f87237fdbf4 100644 --- a/fs/ubifs/misc.h +++ b/fs/ubifs/misc.h @@ -197,7 +197,8 @@ static inline int ubifs_return_leb(struct ubifs_info *c, int lnum) */ static inline int ubifs_idx_node_sz(const struct ubifs_info *c, int child_cnt) { - return UBIFS_IDX_NODE_SZ + (UBIFS_BRANCH_SZ + c->key_len) * child_cnt; + return UBIFS_IDX_NODE_SZ + (UBIFS_BRANCH_SZ + c->key_len + c->hash_len) + * child_cnt; } /** @@ -212,7 +213,7 @@ struct ubifs_branch *ubifs_idx_branch(const struct ubifs_info *c, int bnum) { return (struct ubifs_branch *)((void *)idx->branches + - (UBIFS_BRANCH_SZ + c->key_len) * bnum); + (UBIFS_BRANCH_SZ + c->key_len + c->hash_len) * bnum); } /** diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index 984e30e83c0b..8526b7ec4707 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -212,7 +212,10 @@ static int write_rcvrd_mst_node(struct ubifs_info *c, save_flags = mst->flags; mst->flags |= cpu_to_le32(UBIFS_MST_RCVRY); - ubifs_prepare_node(c, mst, UBIFS_MST_NODE_SZ, 1); + err = ubifs_prepare_node_hmac(c, mst, UBIFS_MST_NODE_SZ, + offsetof(struct ubifs_mst_node, hmac), 1); + if (err) + goto out; err = ubifs_leb_change(c, lnum, mst, sz); if (err) goto out; @@ -264,9 +267,7 @@ int ubifs_recover_master_node(struct ubifs_info *c) offs2 = (void *)mst2 - buf2; if (offs1 == offs2) { /* Same offset, so must be the same */ - if (memcmp((void *)mst1 + UBIFS_CH_SZ, - (void *)mst2 + UBIFS_CH_SZ, - UBIFS_MST_NODE_SZ - UBIFS_CH_SZ)) + if (ubifs_compare_master_node(c, mst1, mst2)) goto out_err; mst = mst1; } else if (offs2 + sz == offs1) { @@ -1462,15 +1463,81 @@ out: } /** + * inode_fix_size - fix inode size + * @c: UBIFS file-system description object + * @e: inode size information for recovery + */ +static int inode_fix_size(struct ubifs_info *c, struct size_entry *e) +{ + struct inode *inode; + struct ubifs_inode *ui; + int err; + + if (c->ro_mount) + ubifs_assert(c, !e->inode); + + if (e->inode) { + /* Remounting rw, pick up inode we stored earlier */ + inode = e->inode; + } else { + inode = ubifs_iget(c->vfs_sb, e->inum); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + if (inode->i_size >= e->d_size) { + /* + * The original inode in the index already has a size + * big enough, nothing to do + */ + iput(inode); + return 0; + } + + dbg_rcvry("ino %lu size %lld -> %lld", + (unsigned long)e->inum, + inode->i_size, e->d_size); + + ui = ubifs_inode(inode); + + inode->i_size = e->d_size; + ui->ui_size = e->d_size; + ui->synced_i_size = e->d_size; + + e->inode = inode; + } + + /* + * In readonly mode just keep the inode pinned in memory until we go + * readwrite. In readwrite mode write the inode to the journal with the + * fixed size. + */ + if (c->ro_mount) + return 0; + + err = ubifs_jnl_write_inode(c, inode); + + iput(inode); + + if (err) + return err; + + rb_erase(&e->rb, &c->size_tree); + kfree(e); + + return 0; +} + +/** * ubifs_recover_size - recover inode size. * @c: UBIFS file-system description object + * @in_place: If true, do a in-place size fixup * * This function attempts to fix inode size discrepancies identified by the * 'ubifs_recover_size_accum()' function. * * This functions returns %0 on success and a negative error code on failure. */ -int ubifs_recover_size(struct ubifs_info *c) +int ubifs_recover_size(struct ubifs_info *c, bool in_place) { struct rb_node *this = rb_first(&c->size_tree); @@ -1479,6 +1546,9 @@ int ubifs_recover_size(struct ubifs_info *c) int err; e = rb_entry(this, struct size_entry, rb); + + this = rb_next(this); + if (!e->exists) { union ubifs_key key; @@ -1502,40 +1572,26 @@ int ubifs_recover_size(struct ubifs_info *c) } if (e->exists && e->i_size < e->d_size) { - if (c->ro_mount) { - /* Fix the inode size and pin it in memory */ - struct inode *inode; - struct ubifs_inode *ui; - - ubifs_assert(c, !e->inode); - - inode = ubifs_iget(c->vfs_sb, e->inum); - if (IS_ERR(inode)) - return PTR_ERR(inode); - - ui = ubifs_inode(inode); - if (inode->i_size < e->d_size) { - dbg_rcvry("ino %lu size %lld -> %lld", - (unsigned long)e->inum, - inode->i_size, e->d_size); - inode->i_size = e->d_size; - ui->ui_size = e->d_size; - ui->synced_i_size = e->d_size; - e->inode = inode; - this = rb_next(this); - continue; - } - iput(inode); - } else { - /* Fix the size in place */ + ubifs_assert(c, !(c->ro_mount && in_place)); + + /* + * We found data that is outside the found inode size, + * fixup the inode size + */ + + if (in_place) { err = fix_size_in_place(c, e); if (err) return err; iput(e->inode); + } else { + err = inode_fix_size(c, e); + if (err) + return err; + continue; } } - this = rb_next(this); rb_erase(&e->rb, &c->size_tree); kfree(e); } diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index 4844538eb926..75f961c4c044 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -34,6 +34,8 @@ #include "ubifs.h" #include <linux/list_sort.h> +#include <crypto/hash.h> +#include <crypto/algapi.h> /** * struct replay_entry - replay list entry. @@ -56,6 +58,7 @@ struct replay_entry { int lnum; int offs; int len; + u8 hash[UBIFS_HASH_ARR_SZ]; unsigned int deletion:1; unsigned long long sqnum; struct list_head list; @@ -228,7 +231,7 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r) err = ubifs_tnc_remove_nm(c, &r->key, &r->nm); else err = ubifs_tnc_add_nm(c, &r->key, r->lnum, r->offs, - r->len, &r->nm); + r->len, r->hash, &r->nm); } else { if (r->deletion) switch (key_type(c, &r->key)) { @@ -248,7 +251,7 @@ static int apply_replay_entry(struct ubifs_info *c, struct replay_entry *r) } else err = ubifs_tnc_add(c, &r->key, r->lnum, r->offs, - r->len); + r->len, r->hash); if (err) return err; @@ -352,9 +355,9 @@ static void destroy_replay_list(struct ubifs_info *c) * in case of success and a negative error code in case of failure. */ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len, - union ubifs_key *key, unsigned long long sqnum, - int deletion, int *used, loff_t old_size, - loff_t new_size) + const u8 *hash, union ubifs_key *key, + unsigned long long sqnum, int deletion, int *used, + loff_t old_size, loff_t new_size) { struct replay_entry *r; @@ -372,6 +375,7 @@ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len, r->lnum = lnum; r->offs = offs; r->len = len; + ubifs_copy_hash(c, hash, r->hash); r->deletion = !!deletion; r->sqnum = sqnum; key_copy(c, key, &r->key); @@ -400,8 +404,9 @@ static int insert_node(struct ubifs_info *c, int lnum, int offs, int len, * negative error code in case of failure. */ static int insert_dent(struct ubifs_info *c, int lnum, int offs, int len, - union ubifs_key *key, const char *name, int nlen, - unsigned long long sqnum, int deletion, int *used) + const u8 *hash, union ubifs_key *key, + const char *name, int nlen, unsigned long long sqnum, + int deletion, int *used) { struct replay_entry *r; char *nbuf; @@ -425,6 +430,7 @@ static int insert_dent(struct ubifs_info *c, int lnum, int offs, int len, r->lnum = lnum; r->offs = offs; r->len = len; + ubifs_copy_hash(c, hash, r->hash); r->deletion = !!deletion; r->sqnum = sqnum; key_copy(c, key, &r->key); @@ -528,6 +534,105 @@ static int is_last_bud(struct ubifs_info *c, struct ubifs_bud *bud) } /** + * authenticate_sleb - authenticate one scan LEB + * @c: UBIFS file-system description object + * @sleb: the scan LEB to authenticate + * @log_hash: + * @is_last: if true, this is is the last LEB + * + * This function iterates over the buds of a single LEB authenticating all buds + * with the authentication nodes on this LEB. Authentication nodes are written + * after some buds and contain a HMAC covering the authentication node itself + * and the buds between the last authentication node and the current + * authentication node. It can happen that the last buds cannot be authenticated + * because a powercut happened when some nodes were written but not the + * corresponding authentication node. This function returns the number of nodes + * that could be authenticated or a negative error code. + */ +static int authenticate_sleb(struct ubifs_info *c, struct ubifs_scan_leb *sleb, + struct shash_desc *log_hash, int is_last) +{ + int n_not_auth = 0; + struct ubifs_scan_node *snod; + int n_nodes = 0; + int err; + u8 *hash, *hmac; + + if (!ubifs_authenticated(c)) + return sleb->nodes_cnt; + + hash = kmalloc(crypto_shash_descsize(c->hash_tfm), GFP_NOFS); + hmac = kmalloc(c->hmac_desc_len, GFP_NOFS); + if (!hash || !hmac) { + err = -ENOMEM; + goto out; + } + + list_for_each_entry(snod, &sleb->nodes, list) { + + n_nodes++; + + if (snod->type == UBIFS_AUTH_NODE) { + struct ubifs_auth_node *auth = snod->node; + SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm); + SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm); + + hash_desc->tfm = c->hash_tfm; + hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ubifs_shash_copy_state(c, log_hash, hash_desc); + err = crypto_shash_final(hash_desc, hash); + if (err) + goto out; + + hmac_desc->tfm = c->hmac_tfm; + hmac_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + err = crypto_shash_digest(hmac_desc, hash, c->hash_len, + hmac); + if (err) + goto out; + + err = ubifs_check_hmac(c, auth->hmac, hmac); + if (err) { + err = -EPERM; + goto out; + } + n_not_auth = 0; + } else { + err = crypto_shash_update(log_hash, snod->node, + snod->len); + if (err) + goto out; + n_not_auth++; + } + } + + /* + * A powercut can happen when some nodes were written, but not yet + * the corresponding authentication node. This may only happen on + * the last bud though. + */ + if (n_not_auth) { + if (is_last) { + dbg_mnt("%d unauthenticated nodes found on LEB %d, Ignoring them", + n_not_auth, sleb->lnum); + err = 0; + } else { + dbg_mnt("%d unauthenticated nodes found on non-last LEB %d", + n_not_auth, sleb->lnum); + err = -EPERM; + } + } else { + err = 0; + } +out: + kfree(hash); + kfree(hmac); + + return err ? err : n_nodes - n_not_auth; +} + +/** * replay_bud - replay a bud logical eraseblock. * @c: UBIFS file-system description object * @b: bud entry which describes the bud @@ -540,6 +645,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) { int is_last = is_last_bud(c, b->bud); int err = 0, used = 0, lnum = b->bud->lnum, offs = b->bud->start; + int n_nodes, n = 0; struct ubifs_scan_leb *sleb; struct ubifs_scan_node *snod; @@ -559,6 +665,15 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) if (IS_ERR(sleb)) return PTR_ERR(sleb); + n_nodes = authenticate_sleb(c, sleb, b->bud->log_hash, is_last); + if (n_nodes < 0) { + err = n_nodes; + goto out; + } + + ubifs_shash_copy_state(c, b->bud->log_hash, + c->jheads[b->bud->jhead].log_hash); + /* * The bud does not have to start from offset zero - the beginning of * the 'lnum' LEB may contain previously committed data. One of the @@ -582,6 +697,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) */ list_for_each_entry(snod, &sleb->nodes, list) { + u8 hash[UBIFS_HASH_ARR_SZ]; int deletion = 0; cond_resched(); @@ -591,6 +707,8 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) goto out_dump; } + ubifs_node_calc_hash(c, snod->node, hash); + if (snod->sqnum > c->max_sqnum) c->max_sqnum = snod->sqnum; @@ -602,7 +720,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) if (le32_to_cpu(ino->nlink) == 0) deletion = 1; - err = insert_node(c, lnum, snod->offs, snod->len, + err = insert_node(c, lnum, snod->offs, snod->len, hash, &snod->key, snod->sqnum, deletion, &used, 0, new_size); break; @@ -614,7 +732,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) key_block(c, &snod->key) * UBIFS_BLOCK_SIZE; - err = insert_node(c, lnum, snod->offs, snod->len, + err = insert_node(c, lnum, snod->offs, snod->len, hash, &snod->key, snod->sqnum, deletion, &used, 0, new_size); break; @@ -628,7 +746,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) if (err) goto out_dump; - err = insert_dent(c, lnum, snod->offs, snod->len, + err = insert_dent(c, lnum, snod->offs, snod->len, hash, &snod->key, dent->name, le16_to_cpu(dent->nlen), snod->sqnum, !le64_to_cpu(dent->inum), &used); @@ -654,11 +772,13 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) * functions which expect nodes to have keys. */ trun_key_init(c, &key, le32_to_cpu(trun->inum)); - err = insert_node(c, lnum, snod->offs, snod->len, + err = insert_node(c, lnum, snod->offs, snod->len, hash, &key, snod->sqnum, 1, &used, old_size, new_size); break; } + case UBIFS_AUTH_NODE: + break; default: ubifs_err(c, "unexpected node type %d in bud LEB %d:%d", snod->type, lnum, snod->offs); @@ -667,6 +787,10 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b) } if (err) goto out; + + n++; + if (n == n_nodes) + break; } ubifs_assert(c, ubifs_search_bud(c, lnum)); @@ -745,6 +869,7 @@ static int add_replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead, { struct ubifs_bud *bud; struct bud_entry *b; + int err; dbg_mnt("add replay bud LEB %d:%d, head %d", lnum, offs, jhead); @@ -754,13 +879,21 @@ static int add_replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead, b = kmalloc(sizeof(struct bud_entry), GFP_KERNEL); if (!b) { - kfree(bud); - return -ENOMEM; + err = -ENOMEM; + goto out; } bud->lnum = lnum; bud->start = offs; bud->jhead = jhead; + bud->log_hash = ubifs_hash_get_desc(c); + if (IS_ERR(bud->log_hash)) { + err = PTR_ERR(bud->log_hash); + goto out; + } + + ubifs_shash_copy_state(c, c->log_hash, bud->log_hash); + ubifs_add_bud(c, bud); b->bud = bud; @@ -768,6 +901,11 @@ static int add_replay_bud(struct ubifs_info *c, int lnum, int offs, int jhead, list_add_tail(&b->list, &c->replay_buds); return 0; +out: + kfree(bud); + kfree(b); + + return err; } /** @@ -873,6 +1011,14 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) c->cs_sqnum = le64_to_cpu(node->ch.sqnum); dbg_mnt("commit start sqnum %llu", c->cs_sqnum); + + err = ubifs_shash_init(c, c->log_hash); + if (err) + goto out; + + err = ubifs_shash_update(c, c->log_hash, node, UBIFS_CS_NODE_SZ); + if (err < 0) + goto out; } if (snod->sqnum < c->cs_sqnum) { @@ -920,6 +1066,11 @@ static int replay_log_leb(struct ubifs_info *c, int lnum, int offs, void *sbuf) if (err) goto out_dump; + err = ubifs_shash_update(c, c->log_hash, ref, + UBIFS_REF_NODE_SZ); + if (err) + goto out; + err = add_replay_bud(c, le32_to_cpu(ref->lnum), le32_to_cpu(ref->offs), le32_to_cpu(ref->jhead), diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c index bf17f58908ff..75a69dd26d6e 100644 --- a/fs/ubifs/sb.c +++ b/fs/ubifs/sb.c @@ -82,10 +82,13 @@ static int create_default_filesystem(struct ubifs_info *c) int err, tmp, jnl_lebs, log_lebs, max_buds, main_lebs, main_first; int lpt_lebs, lpt_first, orph_lebs, big_lpt, ino_waste, sup_flags = 0; int min_leb_cnt = UBIFS_MIN_LEB_CNT; + int idx_node_size; long long tmp64, main_bytes; __le64 tmp_le64; __le32 tmp_le32; struct timespec64 ts; + u8 hash[UBIFS_HASH_ARR_SZ]; + u8 hash_lpt[UBIFS_HASH_ARR_SZ]; /* Some functions called from here depend on the @c->key_len filed */ c->key_len = UBIFS_SK_LEN; @@ -147,7 +150,7 @@ static int create_default_filesystem(struct ubifs_info *c) c->lsave_cnt = DEFAULT_LSAVE_CNT; c->max_leb_cnt = c->leb_cnt; err = ubifs_create_dflt_lpt(c, &main_lebs, lpt_first, &lpt_lebs, - &big_lpt); + &big_lpt, hash_lpt); if (err) return err; @@ -156,17 +159,35 @@ static int create_default_filesystem(struct ubifs_info *c) main_first = c->leb_cnt - main_lebs; + sup = kzalloc(ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size), GFP_KERNEL); + mst = kzalloc(c->mst_node_alsz, GFP_KERNEL); + idx_node_size = ubifs_idx_node_sz(c, 1); + idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL); + ino = kzalloc(ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size), GFP_KERNEL); + cs = kzalloc(ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size), GFP_KERNEL); + + if (!sup || !mst || !idx || !ino || !cs) { + err = -ENOMEM; + goto out; + } + /* Create default superblock */ - tmp = ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size); - sup = kzalloc(tmp, GFP_KERNEL); - if (!sup) - return -ENOMEM; tmp64 = (long long)max_buds * c->leb_size; if (big_lpt) sup_flags |= UBIFS_FLG_BIGLPT; sup_flags |= UBIFS_FLG_DOUBLE_HASH; + if (ubifs_authenticated(c)) { + sup_flags |= UBIFS_FLG_AUTHENTICATION; + sup->hash_algo = cpu_to_le16(c->auth_hash_algo); + err = ubifs_hmac_wkm(c, sup->hmac_wkm); + if (err) + goto out; + } else { + sup->hash_algo = 0xffff; + } + sup->ch.node_type = UBIFS_SB_NODE; sup->key_hash = UBIFS_KEY_HASH_R5; sup->flags = cpu_to_le32(sup_flags); @@ -197,17 +218,9 @@ static int create_default_filesystem(struct ubifs_info *c) sup->rp_size = cpu_to_le64(tmp64); sup->ro_compat_version = cpu_to_le32(UBIFS_RO_COMPAT_VERSION); - err = ubifs_write_node(c, sup, UBIFS_SB_NODE_SZ, 0, 0); - kfree(sup); - if (err) - return err; - dbg_gen("default superblock created at LEB 0:0"); /* Create default master node */ - mst = kzalloc(c->mst_node_alsz, GFP_KERNEL); - if (!mst) - return -ENOMEM; mst->ch.node_type = UBIFS_MST_NODE; mst->log_lnum = cpu_to_le32(UBIFS_LOG_LNUM); @@ -233,6 +246,7 @@ static int create_default_filesystem(struct ubifs_info *c) mst->empty_lebs = cpu_to_le32(main_lebs - 2); mst->idx_lebs = cpu_to_le32(1); mst->leb_cnt = cpu_to_le32(c->leb_cnt); + ubifs_copy_hash(c, hash_lpt, mst->hash_lpt); /* Calculate lprops statistics */ tmp64 = main_bytes; @@ -253,24 +267,9 @@ static int create_default_filesystem(struct ubifs_info *c) mst->total_used = cpu_to_le64(UBIFS_INO_NODE_SZ); - err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM, 0); - if (err) { - kfree(mst); - return err; - } - err = ubifs_write_node(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM + 1, - 0); - kfree(mst); - if (err) - return err; - dbg_gen("default master node created at LEB %d:0", UBIFS_MST_LNUM); /* Create the root indexing node */ - tmp = ubifs_idx_node_sz(c, 1); - idx = kzalloc(ALIGN(tmp, c->min_io_size), GFP_KERNEL); - if (!idx) - return -ENOMEM; c->key_fmt = UBIFS_SIMPLE_KEY_FMT; c->key_hash = key_r5_hash; @@ -282,19 +281,11 @@ static int create_default_filesystem(struct ubifs_info *c) key_write_idx(c, &key, &br->key); br->lnum = cpu_to_le32(main_first + DEFAULT_DATA_LEB); br->len = cpu_to_le32(UBIFS_INO_NODE_SZ); - err = ubifs_write_node(c, idx, tmp, main_first + DEFAULT_IDX_LEB, 0); - kfree(idx); - if (err) - return err; dbg_gen("default root indexing node created LEB %d:0", main_first + DEFAULT_IDX_LEB); /* Create default root inode */ - tmp = ALIGN(UBIFS_INO_NODE_SZ, c->min_io_size); - ino = kzalloc(tmp, GFP_KERNEL); - if (!ino) - return -ENOMEM; ino_key_init_flash(c, &ino->key, UBIFS_ROOT_INO); ino->ch.node_type = UBIFS_INO_NODE; @@ -317,12 +308,6 @@ static int create_default_filesystem(struct ubifs_info *c) /* Set compression enabled by default */ ino->flags = cpu_to_le32(UBIFS_COMPR_FL); - err = ubifs_write_node(c, ino, UBIFS_INO_NODE_SZ, - main_first + DEFAULT_DATA_LEB, 0); - kfree(ino); - if (err) - return err; - dbg_gen("root inode created at LEB %d:0", main_first + DEFAULT_DATA_LEB); @@ -331,19 +316,54 @@ static int create_default_filesystem(struct ubifs_info *c) * always the case during normal file-system operation. Write a fake * commit start node to the log. */ - tmp = ALIGN(UBIFS_CS_NODE_SZ, c->min_io_size); - cs = kzalloc(tmp, GFP_KERNEL); - if (!cs) - return -ENOMEM; cs->ch.node_type = UBIFS_CS_NODE; + + err = ubifs_write_node_hmac(c, sup, UBIFS_SB_NODE_SZ, 0, 0, + offsetof(struct ubifs_sb_node, hmac)); + if (err) + goto out; + + err = ubifs_write_node(c, ino, UBIFS_INO_NODE_SZ, + main_first + DEFAULT_DATA_LEB, 0); + if (err) + goto out; + + ubifs_node_calc_hash(c, ino, hash); + ubifs_copy_hash(c, hash, ubifs_branch_hash(c, br)); + + err = ubifs_write_node(c, idx, idx_node_size, main_first + DEFAULT_IDX_LEB, 0); + if (err) + goto out; + + ubifs_node_calc_hash(c, idx, hash); + ubifs_copy_hash(c, hash, mst->hash_root_idx); + + err = ubifs_write_node_hmac(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM, 0, + offsetof(struct ubifs_mst_node, hmac)); + if (err) + goto out; + + err = ubifs_write_node_hmac(c, mst, UBIFS_MST_NODE_SZ, UBIFS_MST_LNUM + 1, + 0, offsetof(struct ubifs_mst_node, hmac)); + if (err) + goto out; + err = ubifs_write_node(c, cs, UBIFS_CS_NODE_SZ, UBIFS_LOG_LNUM, 0); - kfree(cs); if (err) - return err; + goto out; ubifs_msg(c, "default file-system created"); - return 0; + + err = 0; +out: + kfree(sup); + kfree(mst); + kfree(idx); + kfree(ino); + kfree(cs); + + return err; } /** @@ -498,7 +518,7 @@ failed: * code. Note, the user of this function is responsible of kfree()'ing the * returned superblock buffer. */ -struct ubifs_sb_node *ubifs_read_sb_node(struct ubifs_info *c) +static struct ubifs_sb_node *ubifs_read_sb_node(struct ubifs_info *c) { struct ubifs_sb_node *sup; int err; @@ -517,6 +537,65 @@ struct ubifs_sb_node *ubifs_read_sb_node(struct ubifs_info *c) return sup; } +static int authenticate_sb_node(struct ubifs_info *c, + const struct ubifs_sb_node *sup) +{ + unsigned int sup_flags = le32_to_cpu(sup->flags); + u8 hmac_wkm[UBIFS_HMAC_ARR_SZ]; + int authenticated = !!(sup_flags & UBIFS_FLG_AUTHENTICATION); + int hash_algo; + int err; + + if (c->authenticated && !authenticated) { + ubifs_err(c, "authenticated FS forced, but found FS without authentication"); + return -EINVAL; + } + + if (!c->authenticated && authenticated) { + ubifs_err(c, "authenticated FS found, but no key given"); + return -EINVAL; + } + + ubifs_msg(c, "Mounting in %sauthenticated mode", + c->authenticated ? "" : "un"); + + if (!c->authenticated) + return 0; + + if (!IS_ENABLED(CONFIG_UBIFS_FS_AUTHENTICATION)) + return -EOPNOTSUPP; + + hash_algo = le16_to_cpu(sup->hash_algo); + if (hash_algo >= HASH_ALGO__LAST) { + ubifs_err(c, "superblock uses unknown hash algo %d", + hash_algo); + return -EINVAL; + } + + if (strcmp(hash_algo_name[hash_algo], c->auth_hash_name)) { + ubifs_err(c, "This filesystem uses %s for hashing," + " but %s is specified", hash_algo_name[hash_algo], + c->auth_hash_name); + return -EINVAL; + } + + err = ubifs_hmac_wkm(c, hmac_wkm); + if (err) + return err; + + if (ubifs_check_hmac(c, hmac_wkm, sup->hmac_wkm)) { + ubifs_err(c, "provided key does not fit"); + return -ENOKEY; + } + + err = ubifs_node_verify_hmac(c, sup, sizeof(*sup), + offsetof(struct ubifs_sb_node, hmac)); + if (err) + ubifs_err(c, "Failed to authenticate superblock: %d", err); + + return err; +} + /** * ubifs_write_sb_node - write superblock node. * @c: UBIFS file-system description object @@ -527,8 +606,13 @@ struct ubifs_sb_node *ubifs_read_sb_node(struct ubifs_info *c) int ubifs_write_sb_node(struct ubifs_info *c, struct ubifs_sb_node *sup) { int len = ALIGN(UBIFS_SB_NODE_SZ, c->min_io_size); + int err; + + err = ubifs_prepare_node_hmac(c, sup, UBIFS_SB_NODE_SZ, + offsetof(struct ubifs_sb_node, hmac), 1); + if (err) + return err; - ubifs_prepare_node(c, sup, UBIFS_SB_NODE_SZ, 1); return ubifs_leb_change(c, UBIFS_SB_LNUM, sup, len); } @@ -555,6 +639,8 @@ int ubifs_read_superblock(struct ubifs_info *c) if (IS_ERR(sup)) return PTR_ERR(sup); + c->sup_node = sup; + c->fmt_version = le32_to_cpu(sup->fmt_version); c->ro_compat_version = le32_to_cpu(sup->ro_compat_version); @@ -603,7 +689,7 @@ int ubifs_read_superblock(struct ubifs_info *c) c->key_hash = key_test_hash; c->key_hash_type = UBIFS_KEY_HASH_TEST; break; - }; + } c->key_fmt = sup->key_fmt; @@ -640,6 +726,10 @@ int ubifs_read_superblock(struct ubifs_info *c) c->double_hash = !!(sup_flags & UBIFS_FLG_DOUBLE_HASH); c->encrypted = !!(sup_flags & UBIFS_FLG_ENCRYPTION); + err = authenticate_sb_node(c, sup); + if (err) + goto out; + if ((sup_flags & ~UBIFS_FLG_MASK) != 0) { ubifs_err(c, "Unknown feature flags found: %#x", sup_flags & ~UBIFS_FLG_MASK); @@ -686,7 +776,6 @@ int ubifs_read_superblock(struct ubifs_info *c) err = validate_sb(c, sup); out: - kfree(sup); return err; } @@ -815,7 +904,7 @@ out: int ubifs_fixup_free_space(struct ubifs_info *c) { int err; - struct ubifs_sb_node *sup; + struct ubifs_sb_node *sup = c->sup_node; ubifs_assert(c, c->space_fixup); ubifs_assert(c, !c->ro_mount); @@ -826,16 +915,11 @@ int ubifs_fixup_free_space(struct ubifs_info *c) if (err) return err; - sup = ubifs_read_sb_node(c); - if (IS_ERR(sup)) - return PTR_ERR(sup); - /* Free-space fixup is no longer required */ c->space_fixup = 0; sup->flags &= cpu_to_le32(~UBIFS_FLG_SPACE_FIXUP); err = ubifs_write_sb_node(c, sup); - kfree(sup); if (err) return err; @@ -846,7 +930,7 @@ int ubifs_fixup_free_space(struct ubifs_info *c) int ubifs_enable_encryption(struct ubifs_info *c) { int err; - struct ubifs_sb_node *sup; + struct ubifs_sb_node *sup = c->sup_node; if (c->encrypted) return 0; @@ -859,16 +943,11 @@ int ubifs_enable_encryption(struct ubifs_info *c) return -EINVAL; } - sup = ubifs_read_sb_node(c); - if (IS_ERR(sup)) - return PTR_ERR(sup); - sup->flags |= cpu_to_le32(UBIFS_FLG_ENCRYPTION); err = ubifs_write_sb_node(c, sup); if (!err) c->encrypted = 1; - kfree(sup); return err; } diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index fec62e9dfbe6..1fac1133dadd 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -579,6 +579,9 @@ static int init_constants_early(struct ubifs_info *c) c->ranges[UBIFS_REF_NODE].len = UBIFS_REF_NODE_SZ; c->ranges[UBIFS_TRUN_NODE].len = UBIFS_TRUN_NODE_SZ; c->ranges[UBIFS_CS_NODE].len = UBIFS_CS_NODE_SZ; + c->ranges[UBIFS_AUTH_NODE].min_len = UBIFS_AUTH_NODE_SZ; + c->ranges[UBIFS_AUTH_NODE].max_len = UBIFS_AUTH_NODE_SZ + + UBIFS_MAX_HMAC_LEN; c->ranges[UBIFS_INO_NODE].min_len = UBIFS_INO_NODE_SZ; c->ranges[UBIFS_INO_NODE].max_len = UBIFS_MAX_INO_NODE_SZ; @@ -816,6 +819,9 @@ static int alloc_wbufs(struct ubifs_info *c) c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback; c->jheads[i].wbuf.jhead = i; c->jheads[i].grouped = 1; + c->jheads[i].log_hash = ubifs_hash_get_desc(c); + if (IS_ERR(c->jheads[i].log_hash)) + goto out; } /* @@ -826,6 +832,12 @@ static int alloc_wbufs(struct ubifs_info *c) c->jheads[GCHD].grouped = 0; return 0; + +out: + while (i--) + kfree(c->jheads[i].log_hash); + + return err; } /** @@ -840,6 +852,7 @@ static void free_wbufs(struct ubifs_info *c) for (i = 0; i < c->jhead_cnt; i++) { kfree(c->jheads[i].wbuf.buf); kfree(c->jheads[i].wbuf.inodes); + kfree(c->jheads[i].log_hash); } kfree(c->jheads); c->jheads = NULL; @@ -924,6 +937,8 @@ static int check_volume_empty(struct ubifs_info *c) * Opt_no_chk_data_crc: do not check CRCs when reading data nodes * Opt_override_compr: override default compressor * Opt_assert: set ubifs_assert() action + * Opt_auth_key: The key name used for authentication + * Opt_auth_hash_name: The hash type used for authentication * Opt_err: just end of array marker */ enum { @@ -935,6 +950,8 @@ enum { Opt_no_chk_data_crc, Opt_override_compr, Opt_assert, + Opt_auth_key, + Opt_auth_hash_name, Opt_ignore, Opt_err, }; @@ -947,6 +964,8 @@ static const match_table_t tokens = { {Opt_chk_data_crc, "chk_data_crc"}, {Opt_no_chk_data_crc, "no_chk_data_crc"}, {Opt_override_compr, "compr=%s"}, + {Opt_auth_key, "auth_key=%s"}, + {Opt_auth_hash_name, "auth_hash_name=%s"}, {Opt_ignore, "ubi=%s"}, {Opt_ignore, "vol=%s"}, {Opt_assert, "assert=%s"}, @@ -1070,6 +1089,16 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options, kfree(act); break; } + case Opt_auth_key: + c->auth_key_name = kstrdup(args[0].from, GFP_KERNEL); + if (!c->auth_key_name) + return -ENOMEM; + break; + case Opt_auth_hash_name: + c->auth_hash_name = kstrdup(args[0].from, GFP_KERNEL); + if (!c->auth_hash_name) + return -ENOMEM; + break; case Opt_ignore: break; default: @@ -1249,6 +1278,19 @@ static int mount_ubifs(struct ubifs_info *c) c->mounting = 1; + if (c->auth_key_name) { + if (IS_ENABLED(CONFIG_UBIFS_FS_AUTHENTICATION)) { + err = ubifs_init_authentication(c); + if (err) + goto out_free; + } else { + ubifs_err(c, "auth_key_name, but UBIFS is built without" + " authentication support"); + err = -EINVAL; + goto out_free; + } + } + err = ubifs_read_superblock(c); if (err) goto out_free; @@ -1367,12 +1409,21 @@ static int mount_ubifs(struct ubifs_info *c) } if (c->need_recovery) { - err = ubifs_recover_size(c); - if (err) - goto out_orphans; + if (!ubifs_authenticated(c)) { + err = ubifs_recover_size(c, true); + if (err) + goto out_orphans; + } + err = ubifs_rcvry_gc_commit(c); if (err) goto out_orphans; + + if (ubifs_authenticated(c)) { + err = ubifs_recover_size(c, false); + if (err) + goto out_orphans; + } } else { err = take_gc_lnum(c); if (err) @@ -1391,7 +1442,7 @@ static int mount_ubifs(struct ubifs_info *c) if (err) goto out_orphans; } else if (c->need_recovery) { - err = ubifs_recover_size(c); + err = ubifs_recover_size(c, false); if (err) goto out_orphans; } else { @@ -1557,7 +1608,10 @@ static void ubifs_umount(struct ubifs_info *c) free_wbufs(c); free_orphans(c); ubifs_lpt_free(c, 0); + ubifs_exit_authentication(c); + kfree(c->auth_key_name); + kfree(c->auth_hash_name); kfree(c->cbuf); kfree(c->rcvrd_mst_node); kfree(c->mst_node); @@ -1605,16 +1659,10 @@ static int ubifs_remount_rw(struct ubifs_info *c) goto out; if (c->old_leb_cnt != c->leb_cnt) { - struct ubifs_sb_node *sup; + struct ubifs_sb_node *sup = c->sup_node; - sup = ubifs_read_sb_node(c); - if (IS_ERR(sup)) { - err = PTR_ERR(sup); - goto out; - } sup->leb_cnt = cpu_to_le32(c->leb_cnt); err = ubifs_write_sb_node(c, sup); - kfree(sup); if (err) goto out; } @@ -1624,9 +1672,11 @@ static int ubifs_remount_rw(struct ubifs_info *c) err = ubifs_write_rcvrd_mst_node(c); if (err) goto out; - err = ubifs_recover_size(c); - if (err) - goto out; + if (!ubifs_authenticated(c)) { + err = ubifs_recover_size(c, true); + if (err) + goto out; + } err = ubifs_clean_lebs(c, c->sbuf); if (err) goto out; @@ -1692,10 +1742,19 @@ static int ubifs_remount_rw(struct ubifs_info *c) goto out; } - if (c->need_recovery) + if (c->need_recovery) { err = ubifs_rcvry_gc_commit(c); - else + if (err) + goto out; + + if (ubifs_authenticated(c)) { + err = ubifs_recover_size(c, false); + if (err) + goto out; + } + } else { err = ubifs_leb_unmap(c, c->gc_lnum); + } if (err) goto out; diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c index bf416e512743..25572ffea163 100644 --- a/fs/ubifs/tnc.c +++ b/fs/ubifs/tnc.c @@ -35,7 +35,7 @@ #include "ubifs.h" static int try_read_node(const struct ubifs_info *c, void *buf, int type, - int len, int lnum, int offs); + struct ubifs_zbranch *zbr); static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key, struct ubifs_zbranch *zbr, void *node); @@ -433,9 +433,7 @@ static int tnc_read_hashed_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, * @c: UBIFS file-system description object * @buf: buffer to read to * @type: node type - * @len: node length (not aligned) - * @lnum: LEB number of node to read - * @offs: offset of node to read + * @zbr: the zbranch describing the node to read * * This function tries to read a node of known type and length, checks it and * stores it in @buf. This function returns %1 if a node is present and %0 if @@ -453,8 +451,11 @@ static int tnc_read_hashed_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, * journal nodes may potentially be corrupted, so checking is required. */ static int try_read_node(const struct ubifs_info *c, void *buf, int type, - int len, int lnum, int offs) + struct ubifs_zbranch *zbr) { + int len = zbr->len; + int lnum = zbr->lnum; + int offs = zbr->offs; int err, node_len; struct ubifs_ch *ch = buf; uint32_t crc, node_crc; @@ -487,6 +488,12 @@ static int try_read_node(const struct ubifs_info *c, void *buf, int type, if (crc != node_crc) return 0; + err = ubifs_node_check_hash(c, buf, zbr->hash); + if (err) { + ubifs_bad_hash(c, buf, zbr->hash, lnum, offs); + return 0; + } + return 1; } @@ -507,8 +514,7 @@ static int fallible_read_node(struct ubifs_info *c, const union ubifs_key *key, dbg_tnck(key, "LEB %d:%d, key ", zbr->lnum, zbr->offs); - ret = try_read_node(c, node, key_type(c, key), zbr->len, zbr->lnum, - zbr->offs); + ret = try_read_node(c, node, key_type(c, key), zbr); if (ret == 1) { union ubifs_key node_key; struct ubifs_dent_node *dent = node; @@ -1713,6 +1719,12 @@ static int validate_data_node(struct ubifs_info *c, void *buf, goto out; } + err = ubifs_node_check_hash(c, buf, zbr->hash); + if (err) { + ubifs_bad_hash(c, buf, zbr->hash, zbr->lnum, zbr->offs); + return err; + } + len = le32_to_cpu(ch->len); if (len != zbr->len) { ubifs_err(c, "bad node length %d, expected %d", len, zbr->len); @@ -2260,13 +2272,14 @@ do_split: * @lnum: LEB number of node * @offs: node offset * @len: node length + * @hash: The hash over the node * * This function adds a node with key @key to TNC. The node may be new or it may * obsolete some existing one. Returns %0 on success or negative error code on * failure. */ int ubifs_tnc_add(struct ubifs_info *c, const union ubifs_key *key, int lnum, - int offs, int len) + int offs, int len, const u8 *hash) { int found, n, err = 0; struct ubifs_znode *znode; @@ -2281,6 +2294,7 @@ int ubifs_tnc_add(struct ubifs_info *c, const union ubifs_key *key, int lnum, zbr.lnum = lnum; zbr.offs = offs; zbr.len = len; + ubifs_copy_hash(c, hash, zbr.hash); key_copy(c, key, &zbr.key); err = tnc_insert(c, znode, &zbr, n + 1); } else if (found == 1) { @@ -2291,6 +2305,7 @@ int ubifs_tnc_add(struct ubifs_info *c, const union ubifs_key *key, int lnum, zbr->lnum = lnum; zbr->offs = offs; zbr->len = len; + ubifs_copy_hash(c, hash, zbr->hash); } else err = found; if (!err) @@ -2392,13 +2407,14 @@ out_unlock: * @lnum: LEB number of node * @offs: node offset * @len: node length + * @hash: The hash over the node * @nm: node name * * This is the same as 'ubifs_tnc_add()' but it should be used with keys which * may have collisions, like directory entry keys. */ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, - int lnum, int offs, int len, + int lnum, int offs, int len, const u8 *hash, const struct fscrypt_name *nm) { int found, n, err = 0; @@ -2441,6 +2457,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, zbr->lnum = lnum; zbr->offs = offs; zbr->len = len; + ubifs_copy_hash(c, hash, zbr->hash); goto out_unlock; } } @@ -2452,6 +2469,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, zbr.lnum = lnum; zbr.offs = offs; zbr.len = len; + ubifs_copy_hash(c, hash, zbr.hash); key_copy(c, key, &zbr.key); err = tnc_insert(c, znode, &zbr, n + 1); if (err) diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index dba87d09b989..dbcd2c350b65 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -38,6 +38,7 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, struct ubifs_znode *znode, int lnum, int offs, int len) { struct ubifs_znode *zp; + u8 hash[UBIFS_HASH_ARR_SZ]; int i, err; /* Make index node */ @@ -52,6 +53,7 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, br->lnum = cpu_to_le32(zbr->lnum); br->offs = cpu_to_le32(zbr->offs); br->len = cpu_to_le32(zbr->len); + ubifs_copy_hash(c, zbr->hash, ubifs_branch_hash(c, br)); if (!zbr->lnum || !zbr->len) { ubifs_err(c, "bad ref in znode"); ubifs_dump_znode(c, znode); @@ -62,6 +64,7 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, } } ubifs_prepare_node(c, idx, len, 0); + ubifs_node_calc_hash(c, idx, hash); znode->lnum = lnum; znode->offs = offs; @@ -78,10 +81,12 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx, zbr->lnum = lnum; zbr->offs = offs; zbr->len = len; + ubifs_copy_hash(c, hash, zbr->hash); } else { c->zroot.lnum = lnum; c->zroot.offs = offs; c->zroot.len = len; + ubifs_copy_hash(c, hash, c->zroot.hash); } c->calc_idx_sz += ALIGN(len, 8); @@ -647,6 +652,8 @@ static int get_znodes_to_commit(struct ubifs_info *c) znode->cnext = c->cnext; break; } + znode->cparent = znode->parent; + znode->ciip = znode->iip; znode->cnext = cnext; znode = cnext; cnt += 1; @@ -840,6 +847,8 @@ static int write_index(struct ubifs_info *c) } while (1) { + u8 hash[UBIFS_HASH_ARR_SZ]; + cond_resched(); znode = cnext; @@ -857,6 +866,7 @@ static int write_index(struct ubifs_info *c) br->lnum = cpu_to_le32(zbr->lnum); br->offs = cpu_to_le32(zbr->offs); br->len = cpu_to_le32(zbr->len); + ubifs_copy_hash(c, zbr->hash, ubifs_branch_hash(c, br)); if (!zbr->lnum || !zbr->len) { ubifs_err(c, "bad ref in znode"); ubifs_dump_znode(c, znode); @@ -868,6 +878,23 @@ static int write_index(struct ubifs_info *c) } len = ubifs_idx_node_sz(c, znode->child_cnt); ubifs_prepare_node(c, idx, len, 0); + ubifs_node_calc_hash(c, idx, hash); + + mutex_lock(&c->tnc_mutex); + + if (znode->cparent) + ubifs_copy_hash(c, hash, + znode->cparent->zbranch[znode->ciip].hash); + + if (znode->parent) { + if (!ubifs_zn_obsolete(znode)) + ubifs_copy_hash(c, hash, + znode->parent->zbranch[znode->iip].hash); + } else { + ubifs_copy_hash(c, hash, c->zroot.hash); + } + + mutex_unlock(&c->tnc_mutex); /* Determine the index node position */ if (lnum == -1) { diff --git a/fs/ubifs/tnc_misc.c b/fs/ubifs/tnc_misc.c index d90ee01076a9..d1815e959007 100644 --- a/fs/ubifs/tnc_misc.c +++ b/fs/ubifs/tnc_misc.c @@ -265,9 +265,7 @@ long ubifs_destroy_tnc_subtree(const struct ubifs_info *c, /** * read_znode - read an indexing node from flash and fill znode. * @c: UBIFS file-system description object - * @lnum: LEB of the indexing node to read - * @offs: node offset - * @len: node length + * @zzbr: the zbranch describing the node to read * @znode: znode to read to * * This function reads an indexing node from the flash media and fills znode @@ -276,9 +274,12 @@ long ubifs_destroy_tnc_subtree(const struct ubifs_info *c, * is wrong with it, this function prints complaint messages and returns * %-EINVAL. */ -static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, +static int read_znode(struct ubifs_info *c, struct ubifs_zbranch *zzbr, struct ubifs_znode *znode) { + int lnum = zzbr->lnum; + int offs = zzbr->offs; + int len = zzbr->len; int i, err, type, cmp; struct ubifs_idx_node *idx; @@ -292,6 +293,12 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, return err; } + err = ubifs_node_check_hash(c, idx, zzbr->hash); + if (err) { + ubifs_bad_hash(c, idx, zzbr->hash, lnum, offs); + return err; + } + znode->child_cnt = le16_to_cpu(idx->child_cnt); znode->level = le16_to_cpu(idx->level); @@ -308,13 +315,14 @@ static int read_znode(struct ubifs_info *c, int lnum, int offs, int len, } for (i = 0; i < znode->child_cnt; i++) { - const struct ubifs_branch *br = ubifs_idx_branch(c, idx, i); + struct ubifs_branch *br = ubifs_idx_branch(c, idx, i); struct ubifs_zbranch *zbr = &znode->zbranch[i]; key_read(c, &br->key, &zbr->key); zbr->lnum = le32_to_cpu(br->lnum); zbr->offs = le32_to_cpu(br->offs); zbr->len = le32_to_cpu(br->len); + ubifs_copy_hash(c, ubifs_branch_hash(c, br), zbr->hash); zbr->znode = NULL; /* Validate branch */ @@ -425,7 +433,7 @@ struct ubifs_znode *ubifs_load_znode(struct ubifs_info *c, if (!znode) return ERR_PTR(-ENOMEM); - err = read_znode(c, zbr->lnum, zbr->offs, zbr->len, znode); + err = read_znode(c, zbr, znode); if (err) goto out; @@ -496,5 +504,11 @@ int ubifs_tnc_read_node(struct ubifs_info *c, struct ubifs_zbranch *zbr, return -EINVAL; } + err = ubifs_node_check_hash(c, node, zbr->hash); + if (err) { + ubifs_bad_hash(c, node, zbr->hash, zbr->lnum, zbr->offs); + return err; + } + return 0; } diff --git a/fs/ubifs/ubifs-media.h b/fs/ubifs/ubifs-media.h index e8c23c9d4f4a..8b7c1844014f 100644 --- a/fs/ubifs/ubifs-media.h +++ b/fs/ubifs/ubifs-media.h @@ -286,6 +286,7 @@ enum { #define UBIFS_IDX_NODE_SZ sizeof(struct ubifs_idx_node) #define UBIFS_CS_NODE_SZ sizeof(struct ubifs_cs_node) #define UBIFS_ORPH_NODE_SZ sizeof(struct ubifs_orph_node) +#define UBIFS_AUTH_NODE_SZ sizeof(struct ubifs_auth_node) /* Extended attribute entry nodes are identical to directory entry nodes */ #define UBIFS_XENT_NODE_SZ UBIFS_DENT_NODE_SZ /* Only this does not have to be multiple of 8 bytes */ @@ -300,6 +301,12 @@ enum { /* The largest UBIFS node */ #define UBIFS_MAX_NODE_SZ UBIFS_MAX_INO_NODE_SZ +/* The maxmimum size of a hash, enough for sha512 */ +#define UBIFS_MAX_HASH_LEN 64 + +/* The maxmimum size of a hmac, enough for hmac(sha512) */ +#define UBIFS_MAX_HMAC_LEN 64 + /* * xattr name of UBIFS encryption context, we don't use a prefix * nor a long name to not waste space on the flash. @@ -365,6 +372,7 @@ enum { * UBIFS_IDX_NODE: index node * UBIFS_CS_NODE: commit start node * UBIFS_ORPH_NODE: orphan node + * UBIFS_AUTH_NODE: authentication node * UBIFS_NODE_TYPES_CNT: count of supported node types * * Note, we index arrays by these numbers, so keep them low and contiguous. @@ -384,6 +392,7 @@ enum { UBIFS_IDX_NODE, UBIFS_CS_NODE, UBIFS_ORPH_NODE, + UBIFS_AUTH_NODE, UBIFS_NODE_TYPES_CNT, }; @@ -421,15 +430,19 @@ enum { * UBIFS_FLG_DOUBLE_HASH: store a 32bit cookie in directory entry nodes to * support 64bit cookies for lookups by hash * UBIFS_FLG_ENCRYPTION: this filesystem contains encrypted files + * UBIFS_FLG_AUTHENTICATION: this filesystem contains hashes for authentication */ enum { UBIFS_FLG_BIGLPT = 0x02, UBIFS_FLG_SPACE_FIXUP = 0x04, UBIFS_FLG_DOUBLE_HASH = 0x08, UBIFS_FLG_ENCRYPTION = 0x10, + UBIFS_FLG_AUTHENTICATION = 0x20, }; -#define UBIFS_FLG_MASK (UBIFS_FLG_BIGLPT|UBIFS_FLG_SPACE_FIXUP|UBIFS_FLG_DOUBLE_HASH|UBIFS_FLG_ENCRYPTION) +#define UBIFS_FLG_MASK (UBIFS_FLG_BIGLPT | UBIFS_FLG_SPACE_FIXUP | \ + UBIFS_FLG_DOUBLE_HASH | UBIFS_FLG_ENCRYPTION | \ + UBIFS_FLG_AUTHENTICATION) /** * struct ubifs_ch - common header node. @@ -633,6 +646,10 @@ struct ubifs_pad_node { * @time_gran: time granularity in nanoseconds * @uuid: UUID generated when the file system image was created * @ro_compat_version: UBIFS R/O compatibility version + * @hmac: HMAC to authenticate the superblock node + * @hmac_wkm: HMAC of a well known message (the string "UBIFS") as a convenience + * to the user to check if the correct key is passed. + * @hash_algo: The hash algo used for this filesystem (one of enum hash_algo) */ struct ubifs_sb_node { struct ubifs_ch ch; @@ -660,7 +677,10 @@ struct ubifs_sb_node { __le32 time_gran; __u8 uuid[16]; __le32 ro_compat_version; - __u8 padding2[3968]; + __u8 hmac[UBIFS_MAX_HMAC_LEN]; + __u8 hmac_wkm[UBIFS_MAX_HMAC_LEN]; + __le16 hash_algo; + __u8 padding2[3838]; } __packed; /** @@ -695,6 +715,9 @@ struct ubifs_sb_node { * @empty_lebs: number of empty logical eraseblocks * @idx_lebs: number of indexing logical eraseblocks * @leb_cnt: count of LEBs used by file-system + * @hash_root_idx: the hash of the root index node + * @hash_lpt: the hash of the LPT + * @hmac: HMAC to authenticate the master node * @padding: reserved for future, zeroes */ struct ubifs_mst_node { @@ -727,7 +750,10 @@ struct ubifs_mst_node { __le32 empty_lebs; __le32 idx_lebs; __le32 leb_cnt; - __u8 padding[344]; + __u8 hash_root_idx[UBIFS_MAX_HASH_LEN]; + __u8 hash_lpt[UBIFS_MAX_HASH_LEN]; + __u8 hmac[UBIFS_MAX_HMAC_LEN]; + __u8 padding[152]; } __packed; /** @@ -747,11 +773,25 @@ struct ubifs_ref_node { } __packed; /** + * struct ubifs_auth_node - node for authenticating other nodes + * @ch: common header + * @hmac: The HMAC + */ +struct ubifs_auth_node { + struct ubifs_ch ch; + __u8 hmac[]; +} __packed; + +/** * struct ubifs_branch - key/reference/length branch * @lnum: LEB number of the target node * @offs: offset within @lnum * @len: target node length * @key: key + * + * In an authenticated UBIFS we have the hash of the referenced node after @key. + * This can't be added to the struct type definition because @key is a + * dynamically sized element already. */ struct ubifs_branch { __le32 lnum; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 4368cde476b0..38401adaa00d 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -39,6 +39,9 @@ #include <linux/security.h> #include <linux/xattr.h> #include <linux/random.h> +#include <crypto/hash_info.h> +#include <crypto/hash.h> +#include <crypto/algapi.h> #define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_UBIFS_FS_ENCRYPTION) #include <linux/fscrypt.h> @@ -157,6 +160,14 @@ /* Maximum number of data nodes to bulk-read */ #define UBIFS_MAX_BULK_READ 32 +#ifdef CONFIG_UBIFS_FS_AUTHENTICATION +#define UBIFS_HASH_ARR_SZ UBIFS_MAX_HASH_LEN +#define UBIFS_HMAC_ARR_SZ UBIFS_MAX_HMAC_LEN +#else +#define UBIFS_HASH_ARR_SZ 0 +#define UBIFS_HMAC_ARR_SZ 0 +#endif + /* * Lockdep classes for UBIFS inode @ui_mutex. */ @@ -706,6 +717,7 @@ struct ubifs_wbuf { * @jhead: journal head number this bud belongs to * @list: link in the list buds belonging to the same journal head * @rb: link in the tree of all buds + * @log_hash: the log hash from the commit start node up to this bud */ struct ubifs_bud { int lnum; @@ -713,6 +725,7 @@ struct ubifs_bud { int jhead; struct list_head list; struct rb_node rb; + struct shash_desc *log_hash; }; /** @@ -720,6 +733,7 @@ struct ubifs_bud { * @wbuf: head's write-buffer * @buds_list: list of bud LEBs belonging to this journal head * @grouped: non-zero if UBIFS groups nodes when writing to this journal head + * @log_hash: the log hash from the commit start node up to this journal head * * Note, the @buds list is protected by the @c->buds_lock. */ @@ -727,6 +741,7 @@ struct ubifs_jhead { struct ubifs_wbuf wbuf; struct list_head buds_list; unsigned int grouped:1; + struct shash_desc *log_hash; }; /** @@ -736,6 +751,7 @@ struct ubifs_jhead { * @lnum: LEB number of the target node (indexing node or data node) * @offs: target node offset within @lnum * @len: target node length + * @hash: the hash of the target node */ struct ubifs_zbranch { union ubifs_key key; @@ -746,12 +762,15 @@ struct ubifs_zbranch { int lnum; int offs; int len; + u8 hash[UBIFS_HASH_ARR_SZ]; }; /** * struct ubifs_znode - in-memory representation of an indexing node. * @parent: parent znode or NULL if it is the root * @cnext: next znode to commit + * @cparent: parent node for this commit + * @ciip: index in cparent's zbranch array * @flags: znode flags (%DIRTY_ZNODE, %COW_ZNODE or %OBSOLETE_ZNODE) * @time: last access time (seconds) * @level: level of the entry in the TNC tree @@ -769,6 +788,8 @@ struct ubifs_zbranch { struct ubifs_znode { struct ubifs_znode *parent; struct ubifs_znode *cnext; + struct ubifs_znode *cparent; + int ciip; unsigned long flags; time64_t time; int level; @@ -983,6 +1004,7 @@ struct ubifs_debug_info; * struct ubifs_info - UBIFS file-system description data structure * (per-superblock). * @vfs_sb: VFS @struct super_block object + * @sup_node: The super block node as read from the device * * @highest_inum: highest used inode number * @max_sqnum: current global sequence number @@ -1028,6 +1050,7 @@ struct ubifs_debug_info; * @default_compr: default compression algorithm (%UBIFS_COMPR_LZO, etc) * @rw_incompat: the media is not R/W compatible * @assert_action: action to take when a ubifs_assert() fails + * @authenticated: flag indigating the FS is mounted in authenticated mode * * @tnc_mutex: protects the Tree Node Cache (TNC), @zroot, @cnext, @enext, and * @calc_idx_sz @@ -1075,6 +1098,7 @@ struct ubifs_debug_info; * @key_hash: direntry key hash function * @key_fmt: key format * @key_len: key length + * @hash_len: The length of the index node hashes * @fanout: fanout of the index tree (number of links per indexing node) * * @min_io_size: minimal input/output unit size @@ -1210,6 +1234,15 @@ struct ubifs_debug_info; * @rp_uid: reserved pool user ID * @rp_gid: reserved pool group ID * + * @hash_tfm: the hash transformation used for hashing nodes + * @hmac_tfm: the HMAC transformation for this filesystem + * @hmac_desc_len: length of the HMAC used for authentication + * @auth_key_name: the authentication key name + * @auth_hash_name: the name of the hash algorithm used for authentication + * @auth_hash_algo: the authentication hash used for this fs + * @log_hash: the log hash from the commit start node up to the latest reference + * node. + * * @empty: %1 if the UBI device is empty * @need_recovery: %1 if the file-system needs recovery * @replaying: %1 during journal replay @@ -1230,6 +1263,7 @@ struct ubifs_debug_info; */ struct ubifs_info { struct super_block *vfs_sb; + struct ubifs_sb_node *sup_node; ino_t highest_inum; unsigned long long max_sqnum; @@ -1270,6 +1304,7 @@ struct ubifs_info { unsigned int default_compr:2; unsigned int rw_incompat:1; unsigned int assert_action:2; + unsigned int authenticated:1; struct mutex tnc_mutex; struct ubifs_zbranch zroot; @@ -1314,6 +1349,7 @@ struct ubifs_info { uint32_t (*key_hash)(const char *str, int len); int key_fmt; int key_len; + int hash_len; int fanout; int min_io_size; @@ -1441,6 +1477,15 @@ struct ubifs_info { kuid_t rp_uid; kgid_t rp_gid; + struct crypto_shash *hash_tfm; + struct crypto_shash *hmac_tfm; + int hmac_desc_len; + char *auth_key_name; + char *auth_hash_name; + enum hash_algo auth_hash_algo; + + struct shash_desc *log_hash; + /* The below fields are used only during mounting and re-mounting */ unsigned int empty:1; unsigned int need_recovery:1; @@ -1471,6 +1516,195 @@ extern const struct inode_operations ubifs_dir_inode_operations; extern const struct inode_operations ubifs_symlink_inode_operations; extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT]; +/* auth.c */ +static inline int ubifs_authenticated(const struct ubifs_info *c) +{ + return (IS_ENABLED(CONFIG_UBIFS_FS_AUTHENTICATION)) && c->authenticated; +} + +struct shash_desc *__ubifs_hash_get_desc(const struct ubifs_info *c); +static inline struct shash_desc *ubifs_hash_get_desc(const struct ubifs_info *c) +{ + return ubifs_authenticated(c) ? __ubifs_hash_get_desc(c) : NULL; +} + +static inline int ubifs_shash_init(const struct ubifs_info *c, + struct shash_desc *desc) +{ + if (ubifs_authenticated(c)) + return crypto_shash_init(desc); + else + return 0; +} + +static inline int ubifs_shash_update(const struct ubifs_info *c, + struct shash_desc *desc, const void *buf, + unsigned int len) +{ + int err = 0; + + if (ubifs_authenticated(c)) { + err = crypto_shash_update(desc, buf, len); + if (err < 0) + return err; + } + + return 0; +} + +static inline int ubifs_shash_final(const struct ubifs_info *c, + struct shash_desc *desc, u8 *out) +{ + return ubifs_authenticated(c) ? crypto_shash_final(desc, out) : 0; +} + +int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *buf, + u8 *hash); +static inline int ubifs_node_calc_hash(const struct ubifs_info *c, + const void *buf, u8 *hash) +{ + if (ubifs_authenticated(c)) + return __ubifs_node_calc_hash(c, buf, hash); + else + return 0; +} + +int ubifs_prepare_auth_node(struct ubifs_info *c, void *node, + struct shash_desc *inhash); + +/** + * ubifs_check_hash - compare two hashes + * @c: UBIFS file-system description object + * @expected: first hash + * @got: second hash + * + * Compare two hashes @expected and @got. Returns 0 when they are equal, a + * negative error code otherwise. + */ +static inline int ubifs_check_hash(const struct ubifs_info *c, + const u8 *expected, const u8 *got) +{ + return crypto_memneq(expected, got, c->hash_len); +} + +/** + * ubifs_check_hmac - compare two HMACs + * @c: UBIFS file-system description object + * @expected: first HMAC + * @got: second HMAC + * + * Compare two hashes @expected and @got. Returns 0 when they are equal, a + * negative error code otherwise. + */ +static inline int ubifs_check_hmac(const struct ubifs_info *c, + const u8 *expected, const u8 *got) +{ + return crypto_memneq(expected, got, c->hmac_desc_len); +} + +void ubifs_bad_hash(const struct ubifs_info *c, const void *node, + const u8 *hash, int lnum, int offs); + +int __ubifs_node_check_hash(const struct ubifs_info *c, const void *buf, + const u8 *expected); +static inline int ubifs_node_check_hash(const struct ubifs_info *c, + const void *buf, const u8 *expected) +{ + if (ubifs_authenticated(c)) + return __ubifs_node_check_hash(c, buf, expected); + else + return 0; +} + +int ubifs_init_authentication(struct ubifs_info *c); +void __ubifs_exit_authentication(struct ubifs_info *c); +static inline void ubifs_exit_authentication(struct ubifs_info *c) +{ + if (ubifs_authenticated(c)) + __ubifs_exit_authentication(c); +} + +/** + * ubifs_branch_hash - returns a pointer to the hash of a branch + * @c: UBIFS file-system description object + * @br: branch to get the hash from + * + * This returns a pointer to the hash of a branch. Since the key already is a + * dynamically sized object we cannot use a struct member here. + */ +static inline u8 *ubifs_branch_hash(struct ubifs_info *c, + struct ubifs_branch *br) +{ + return (void *)br + sizeof(*br) + c->key_len; +} + +/** + * ubifs_copy_hash - copy a hash + * @c: UBIFS file-system description object + * @from: source hash + * @to: destination hash + * + * With authentication this copies a hash, otherwise does nothing. + */ +static inline void ubifs_copy_hash(const struct ubifs_info *c, const u8 *from, + u8 *to) +{ + if (ubifs_authenticated(c)) + memcpy(to, from, c->hash_len); +} + +int __ubifs_node_insert_hmac(const struct ubifs_info *c, void *buf, + int len, int ofs_hmac); +static inline int ubifs_node_insert_hmac(const struct ubifs_info *c, void *buf, + int len, int ofs_hmac) +{ + if (ubifs_authenticated(c)) + return __ubifs_node_insert_hmac(c, buf, len, ofs_hmac); + else + return 0; +} + +int __ubifs_node_verify_hmac(const struct ubifs_info *c, const void *buf, + int len, int ofs_hmac); +static inline int ubifs_node_verify_hmac(const struct ubifs_info *c, + const void *buf, int len, int ofs_hmac) +{ + if (ubifs_authenticated(c)) + return __ubifs_node_verify_hmac(c, buf, len, ofs_hmac); + else + return 0; +} + +/** + * ubifs_auth_node_sz - returns the size of an authentication node + * @c: UBIFS file-system description object + * + * This function returns the size of an authentication node which can + * be 0 for unauthenticated filesystems or the real size of an auth node + * authentication is enabled. + */ +static inline int ubifs_auth_node_sz(const struct ubifs_info *c) +{ + if (ubifs_authenticated(c)) + return sizeof(struct ubifs_auth_node) + c->hmac_desc_len; + else + return 0; +} + +int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac); + +int __ubifs_shash_copy_state(const struct ubifs_info *c, struct shash_desc *src, + struct shash_desc *target); +static inline int ubifs_shash_copy_state(const struct ubifs_info *c, + struct shash_desc *src, + struct shash_desc *target) +{ + if (ubifs_authenticated(c)) + return __ubifs_shash_copy_state(c, src, target); + else + return 0; +} + /* io.c */ void ubifs_ro_mode(struct ubifs_info *c, int err); int ubifs_leb_read(const struct ubifs_info *c, int lnum, void *buf, int offs, @@ -1490,9 +1724,15 @@ int ubifs_read_node_wbuf(struct ubifs_wbuf *wbuf, void *buf, int type, int len, int lnum, int offs); int ubifs_write_node(struct ubifs_info *c, void *node, int len, int lnum, int offs); +int ubifs_write_node_hmac(struct ubifs_info *c, void *buf, int len, int lnum, + int offs, int hmac_offs); int ubifs_check_node(const struct ubifs_info *c, const void *buf, int lnum, int offs, int quiet, int must_chk_crc); +void ubifs_init_node(struct ubifs_info *c, void *buf, int len, int pad); +void ubifs_crc_node(struct ubifs_info *c, void *buf, int len); void ubifs_prepare_node(struct ubifs_info *c, void *buf, int len, int pad); +int ubifs_prepare_node_hmac(struct ubifs_info *c, void *node, int len, + int hmac_offs, int pad); void ubifs_prep_grp_node(struct ubifs_info *c, void *node, int len, int last); int ubifs_io_init(struct ubifs_info *c); void ubifs_pad(const struct ubifs_info *c, void *buf, int pad); @@ -1592,11 +1832,12 @@ int ubifs_tnc_lookup_dh(struct ubifs_info *c, const union ubifs_key *key, int ubifs_tnc_locate(struct ubifs_info *c, const union ubifs_key *key, void *node, int *lnum, int *offs); int ubifs_tnc_add(struct ubifs_info *c, const union ubifs_key *key, int lnum, - int offs, int len); + int offs, int len, const u8 *hash); int ubifs_tnc_replace(struct ubifs_info *c, const union ubifs_key *key, int old_lnum, int old_offs, int lnum, int offs, int len); int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key, - int lnum, int offs, int len, const struct fscrypt_name *nm); + int lnum, int offs, int len, const u8 *hash, + const struct fscrypt_name *nm); int ubifs_tnc_remove(struct ubifs_info *c, const union ubifs_key *key); int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key, const struct fscrypt_name *nm); @@ -1659,12 +1900,12 @@ int ubifs_gc_should_commit(struct ubifs_info *c); void ubifs_wait_for_commit(struct ubifs_info *c); /* master.c */ +int ubifs_compare_master_node(struct ubifs_info *c, void *m1, void *m2); int ubifs_read_master(struct ubifs_info *c); int ubifs_write_master(struct ubifs_info *c); /* sb.c */ int ubifs_read_superblock(struct ubifs_info *c); -struct ubifs_sb_node *ubifs_read_sb_node(struct ubifs_info *c); int ubifs_write_sb_node(struct ubifs_info *c, struct ubifs_sb_node *sup); int ubifs_fixup_free_space(struct ubifs_info *c); int ubifs_enable_encryption(struct ubifs_info *c); @@ -1693,7 +1934,7 @@ int ubifs_clear_orphans(struct ubifs_info *c); /* lpt.c */ int ubifs_calc_lpt_geom(struct ubifs_info *c); int ubifs_create_dflt_lpt(struct ubifs_info *c, int *main_lebs, int lpt_first, - int *lpt_lebs, int *big_lpt); + int *lpt_lebs, int *big_lpt, u8 *hash); int ubifs_lpt_init(struct ubifs_info *c, int rd, int wr); struct ubifs_lprops *ubifs_lpt_lookup(struct ubifs_info *c, int lnum); struct ubifs_lprops *ubifs_lpt_lookup_dirty(struct ubifs_info *c, int lnum); @@ -1712,6 +1953,7 @@ struct ubifs_pnode *ubifs_get_pnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip); struct ubifs_nnode *ubifs_get_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip); +struct ubifs_pnode *ubifs_pnode_lookup(struct ubifs_info *c, int i); int ubifs_read_nnode(struct ubifs_info *c, struct ubifs_nnode *parent, int iip); void ubifs_add_lpt_dirt(struct ubifs_info *c, int lnum, int dirty); void ubifs_add_nnode_dirt(struct ubifs_info *c, struct ubifs_nnode *nnode); @@ -1720,6 +1962,7 @@ struct ubifs_nnode *ubifs_first_nnode(struct ubifs_info *c, int *hght); /* Needed only in debugging code in lpt_commit.c */ int ubifs_unpack_nnode(const struct ubifs_info *c, void *buf, struct ubifs_nnode *nnode); +int ubifs_lpt_calc_hash(struct ubifs_info *c, u8 *hash); /* lpt_commit.c */ int ubifs_lpt_start_commit(struct ubifs_info *c); @@ -1807,7 +2050,7 @@ int ubifs_clean_lebs(struct ubifs_info *c, void *sbuf); int ubifs_rcvry_gc_commit(struct ubifs_info *c); int ubifs_recover_size_accum(struct ubifs_info *c, union ubifs_key *key, int deletion, loff_t new_size); -int ubifs_recover_size(struct ubifs_info *c); +int ubifs_recover_size(struct ubifs_info *c, bool in_place); void ubifs_destroy_size_tree(struct ubifs_info *c); /* ioctl.c */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 6fc5425b1474..2652d00842d6 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -243,7 +243,7 @@ xfs_attr3_leaf_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; - uint16_t end; + uint32_t end; /* must be 32bit - see below */ int i; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); @@ -293,6 +293,11 @@ xfs_attr3_leaf_verify( /* * Quickly check the freemap information. Attribute data has to be * aligned to 4-byte boundaries, and likewise for the free space. + * + * Note that for 64k block size filesystems, the freemap entries cannot + * overflow as they are only be16 fields. However, when checking end + * pointer of the freemap, we have to be careful to detect overflows and + * so use uint32_t for those checks. */ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr.freemap[i].base > mp->m_attr_geo->blksize) @@ -303,7 +308,9 @@ xfs_attr3_leaf_verify( return __this_address; if (ichdr.freemap[i].size & 0x3) return __this_address; - end = ichdr.freemap[i].base + ichdr.freemap[i].size; + + /* be care of 16 bit overflows here */ + end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) return __this_address; if (end > mp->m_attr_geo->blksize) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6e2c08f30f60..6ecdbb3af7de 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1608,7 +1608,7 @@ xfs_ioc_getbmap( error = 0; out_free_buf: kmem_free(buf); - return 0; + return error; } struct getfsmap_info { diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 576c375ce12a..6b736ea58d35 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -107,5 +107,5 @@ assfail(char *expr, char *file, int line) void xfs_hex_dump(void *p, int length) { - print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1); + print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1); } diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 89f3b03b1445..e3667c9a33a5 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -3,7 +3,7 @@ #define _4LEVEL_FIXUP_H #define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 #define PUD_SHIFT PGDIR_SHIFT #define PUD_SIZE PGDIR_SIZE diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index 9c2e0708eb82..73474bb52344 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -3,7 +3,7 @@ #define _5LEVEL_FIXUP_H #define __ARCH_HAS_5LEVEL_HACK -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 #define P4D_SHIFT PGDIR_SHIFT #define P4D_SIZE PGDIR_SIZE diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h index 0c34215263b8..1d6dd38c0e5e 100644 --- a/include/asm-generic/pgtable-nop4d-hack.h +++ b/include/asm-generic/pgtable-nop4d-hack.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLY__ #include <asm-generic/5level-fixup.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a pgd gets the size right, and allows diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index 1a29b2a0282b..04cb913797bc 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -4,7 +4,7 @@ #ifndef __ASSEMBLY__ -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 typedef struct { pgd_t pgd; } p4d_t; diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index f35f6e8149e4..b85b8271a73d 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -8,7 +8,7 @@ struct mm_struct; -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Having the pmd type consist of a pud gets the size right, and allows diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index e950b9c50f34..9bef475db6fe 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -9,7 +9,7 @@ #else #include <asm-generic/pgtable-nop4d.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a p4d gets the size right, and allows diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 5657a20e0c59..359fb935ded6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void) #endif #endif +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#endif - #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ -# define __no_kasan_or_inline __no_sanitize_address __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index caf40ad0bbc6..e0cd2baa8380 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -126,6 +126,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_KVM_STARTING, CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, CPUHP_AP_KVM_ARM_VGIC_STARTING, diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this diff --git a/include/linux/mm.h b/include/linux/mm.h index fcf9cc9d535f..5411de93a363 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1744,11 +1744,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1768,11 +1772,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** @@ -569,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index 131424cefc6a..02c0412e368c 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -107,8 +107,8 @@ struct krb5_ctx { u8 Ksess[GSS_KRB5_MAX_KEYLEN]; /* session key */ u8 cksum[GSS_KRB5_MAX_KEYLEN]; s32 endtime; - u32 seq_send; - u64 seq_send64; + atomic_t seq_send; + atomic64_t seq_send64; struct xdr_netobj mech_used; u8 initiator_sign[GSS_KRB5_MAX_KEYLEN]; u8 acceptor_sign[GSS_KRB5_MAX_KEYLEN]; @@ -118,9 +118,6 @@ struct krb5_ctx { u8 acceptor_integ[GSS_KRB5_MAX_KEYLEN]; }; -extern u32 gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx); -extern u64 gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx); - /* The length of the Kerberos GSS token header */ #define GSS_KRB5_TOK_HDR_LEN (16) diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 14b789a123e7..1656c5978498 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -317,6 +317,8 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); +int ipv6_anycast_init(void); +void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index d7578cf49c3a..c9c78c15bce0 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -146,10 +146,12 @@ struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; + struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; + struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index eed04af9b75e..ae7b86f587f2 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -153,4 +153,43 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ +static inline struct nf_generic_net *nf_generic_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.generic; +} + +static inline struct nf_tcp_net *nf_tcp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.tcp; +} + +static inline struct nf_udp_net *nf_udp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.udp; +} + +static inline struct nf_icmp_net *nf_icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + +static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +#ifdef CONFIG_NF_CT_PROTO_DCCP +static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.dccp; +} +#endif + +#ifdef CONFIG_NF_CT_PROTO_SCTP +static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.sctp; +} +#endif + #endif /*_NF_CONNTRACK_PROTOCOL_H*/ diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f5ff8a76e208..b01eb502d49c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -83,11 +83,11 @@ struct kfd_ioctl_set_cu_mask_args { }; struct kfd_ioctl_get_queue_wave_state_args { - uint64_t ctl_stack_address; /* to KFD */ - uint32_t ctl_stack_used_size; /* from KFD */ - uint32_t save_area_used_size; /* from KFD */ - uint32_t queue_id; /* to KFD */ - uint32_t pad; + __u64 ctl_stack_address; /* to KFD */ + __u32 ctl_stack_used_size; /* from KFD */ + __u32 save_area_used_size; /* from KFD */ + __u32 queue_id; /* to KFD */ + __u32 pad; }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ @@ -255,10 +255,10 @@ struct kfd_hsa_memory_exception_data { /* hw exception data */ struct kfd_hsa_hw_exception_data { - uint32_t reset_type; - uint32_t reset_cause; - uint32_t memory_lost; - uint32_t gpu_id; + __u32 reset_type; + __u32 reset_cause; + __u32 memory_lost; + __u32 gpu_id; }; /* Event data */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 579974b0bf0d..7de4f1bdaf06 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1635,8 +1635,8 @@ enum nft_ng_attributes { NFTA_NG_MODULUS, NFTA_NG_TYPE, NFTA_NG_OFFSET, - NFTA_NG_SET_NAME, - NFTA_NG_SET_ID, + NFTA_NG_SET_NAME, /* deprecated */ + NFTA_NG_SET_ID, /* deprecated */ __NFTA_NG_MAX }; #define NFTA_NG_MAX (__NFTA_NG_MAX - 1) diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 156ccd089df1..1610fdbab98d 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -11,6 +11,10 @@ #include <linux/if_vlan.h> #include <linux/if_pppox.h> +#ifndef __KERNEL__ +#include <limits.h> /* for INT_MIN, INT_MAX */ +#endif + /* Bridge Hooks */ /* After promisc drops, checksum checks. */ #define NF_BR_PRE_ROUTING 0 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 34dd3d497f2c..c81feb373d3e 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -568,6 +568,8 @@ struct sctp_assoc_reset_event { #define SCTP_ASSOC_CHANGE_DENIED 0x0004 #define SCTP_ASSOC_CHANGE_FAILED 0x0008 +#define SCTP_STREAM_CHANGE_DENIED SCTP_ASSOC_CHANGE_DENIED +#define SCTP_STREAM_CHANGE_FAILED SCTP_ASSOC_CHANGE_FAILED struct sctp_stream_change_event { __u16 strchange_type; __u16 strchange_flags; @@ -1151,6 +1153,7 @@ struct sctp_add_streams { /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, + SCTP_SS_DEFAULT = SCTP_SS_FCFS, SCTP_SS_PRIO, SCTP_SS_RR, SCTP_SS_MAX = SCTP_SS_RR diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 18803ff76e27..4969817124a8 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,16 +42,12 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#ifdef CONFIG_XEN_PV +#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); - -int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); #else static inline int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, @@ -63,7 +59,13 @@ static inline int xen_create_contiguous_region(phys_addr_t pstart, static inline void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { } +#endif +#if defined(CONFIG_XEN_PV) +int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, + unsigned int domid, bool no_translate, struct page **pages); +#else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6377225b2082..1a796e0799ec 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -553,7 +553,6 @@ bool is_bpf_text_address(unsigned long addr) int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - unsigned long symbol_start, symbol_end; struct bpf_prog_aux *aux; unsigned int it = 0; int ret = -ERANGE; @@ -566,10 +565,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); bpf_get_prog_name(aux->prog, sym); - *value = symbol_start; + *value = (unsigned long)aux->prog->bpf_func; *type = BPF_SYM_ELF_TYPE; ret = 0; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ccb93277aae2..cf5040fd5434 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; goto done; } @@ -2158,11 +2159,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (info.nr_jited_ksyms && ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2170,10 +2171,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2182,7 +2190,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (info.nr_jited_func_lens && ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; @@ -2191,9 +2199,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { diff --git a/kernel/resource.c b/kernel/resource.c index b3a3a1fc499e..b0fbf685c77a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -319,16 +319,23 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /** - * Finds the lowest iomem resource that covers part of [start..end]. The - * caller must specify start, end, flags, and desc (which may be + * Finds the lowest iomem resource that covers part of [@start..@end]. The + * caller must specify @start, @end, @flags, and @desc (which may be * IORES_DESC_NONE). * - * If a resource is found, returns 0 and *res is overwritten with the part - * of the resource that's within [start..end]; if none is found, returns - * -1. + * If a resource is found, returns 0 and @*res is overwritten with the part + * of the resource that's within [@start..@end]; if none is found, returns + * -1 or -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. + * + * @start: start address of the resource searched for + * @end: end address of same resource + * @flags: flags which the resource must have + * @desc: descriptor the resource must have + * @first_lvl: walk only the first level children, if set + * @res: return ptr, if resource found */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, @@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @flags: I/O resource flags * @start: start addr * @end: end addr + * @arg: function argument for the callback @func + * @func: callback function that is called for each qualifying resource area * * NOTE: For a new descriptor search, define a new IORES_DESC in * <linux/ioport.h> and set it in 'desc' of a target resource entry. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f12225f26b70..091e089063be 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5851,11 +5851,14 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. + * happen. The hotplug lock is nevertheless taken to satisfy lockdep, + * but there won't be any contention on it. */ + cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..3648d0300fdf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ce32cf741b25..8f0644af40be 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk, struct task_cputime cputime; unsigned long soft; - if (dl_task(tsk)) - check_dl_overrun(tsk); - /* * If cputimer is not running, then there are no active * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ef15a6683c0..bd30e9398d2a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -535,7 +535,7 @@ int traceprobe_update_arg(struct probe_arg *arg) if (code[1].op != FETCH_OP_IMM) return -EINVAL; - tmp = strpbrk("+-", code->data); + tmp = strpbrk(code->data, "+-"); if (tmp) c = *tmp; ret = traceprobe_split_symbol_offset(code->data, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e5222b5fb4fe..923414a246e9 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; - ret = sort_idmaps(&new_map); - if (ret < 0) - goto out; - ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. @@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf, e->lower_first = lower_first; } + /* + * If we want to use binary search for lookup, this clones the extent + * array and sorts both copies. + */ + ret = sort_idmaps(&new_map); + if (ret < 0) + goto out; + /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 5d73f5cb4d8a..79777645cac9 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -27,7 +27,7 @@ ifeq ($(ARCH),arm) CFLAGS += -I../../../arch/arm/include -mfpu=neon HAS_NEON = yes endif -ifeq ($(ARCH),arm64) +ifeq ($(ARCH),aarch64) CFLAGS += -I../../../arch/arm64/include HAS_NEON = yes endif @@ -41,7 +41,7 @@ ifeq ($(IS_X86),yes) gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX512=1) else ifeq ($(HAS_NEON),yes) - OBJS += neon.o neon1.o neon2.o neon4.o neon8.o + OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\ diff --git a/net/core/dev.c b/net/core/dev.c index 77d43ae2a7bb..0ffcbdd55fa9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5da9552b186b..2b9fdbc43205 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np) read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != + !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e01274bd5e3e..33d9227a8b80 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = 0; } ret = dumpit(skb, cb); - if (ret < 0) + if (ret) break; } cb->family = idx; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 946de0e24c87..b4ee5c8b928f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4944,6 +4944,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * + * @skb: GSO skb + * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * diff --git a/net/core/sock.c b/net/core/sock.c index 6fcc4bc07d19..080a880a1761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9b0158fa431f..d6ee343fdb86 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -722,10 +722,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) - return skb; - if (pskb_trim_rcsum(skb, netoff + len)) - return skb; + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { + kfree_skb(skb); + return NULL; + } + if (pskb_trim_rcsum(skb, netoff + len)) { + kfree_skb(skb); + return NULL; + } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..fffcc130900e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f4d61017a69..f0cd291034f0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1001,6 +1001,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1091,6 +1094,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4e0ff7031edd..94999058e110 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,8 +44,22 @@ #include <net/checksum.h> +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) +/* anycast address hash table + */ +static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(acaddr_hash_lock); + static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); +static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr) +{ + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + /* * socket join an anycast group */ @@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk) rtnl_unlock(); } +static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) +{ + unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); + + spin_lock(&acaddr_hash_lock); + hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); + spin_unlock(&acaddr_hash_lock); +} + +static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) +{ + spin_lock(&acaddr_hash_lock); + hlist_del_init_rcu(&aca->aca_addr_lst); + spin_unlock(&acaddr_hash_lock); +} + static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } +static void aca_free_rcu(struct rcu_head *h) +{ + struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); + + fib6_info_release(aca->aca_rt); + kfree(aca); +} + static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - fib6_info_release(ac->aca_rt); - kfree(ac); + call_rcu(&ac->rcu, aca_free_rcu); } } @@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; + INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); + ipv6_add_acaddr_hash(net, aca); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) else idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); + addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { + unsigned int hash = inet6_acaddr_hash(net, addr); + struct net_device *nh_dev; + struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { + hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], + aca_addr_lst) { + nh_dev = fib6_info_nh_dev(aca->aca_rt); + if (!nh_dev || !net_eq(dev_net(nh_dev), net)) + continue; + if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } + } rcu_read_unlock(); return found; } @@ -540,3 +591,24 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif + +/* Init / cleanup code + */ +int __init ipv6_anycast_init(void) +{ + int i; + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); + return 0; +} + +void ipv6_anycast_cleanup(void) +{ + int i; + + spin_lock(&acaddr_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); + spin_unlock(&acaddr_hash_lock); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b8bc008b53b..ae3786132c23 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* fib entries are never clones */ if (arg.filter.flags & RTM_F_CLONED) - return skb->len; + goto out; w = (void *)cb->args[2]; if (!w) { @@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (arg.filter.dump_all_families) - return skb->len; + goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b8ac369f98ad..d219979c3e52 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) */ ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - else + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + if (nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; + skb->_skb_refdst = orefdst; + } else { skb_dst_drop(skb); + } out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..1577f2f76060 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); -/* When the nfnl mutex is held: */ +/* When the nfnl mutex or ip_set_ref_lock is held: */ #define ip_set_dereference(p) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&ip_set_ref_lock)) #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] +#define ip_set_ref_netlink(inst,id) \ + rcu_dereference_raw((inst)->ip_set_list)[id] /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -693,21 +697,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -961,7 +964,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Wraparound */ goto cleanup; - list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -973,7 +976,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Use new list */ index = inst->ip_set_max; inst->ip_set_max = i; - kfree(tmp); + kvfree(tmp); ret = 0; } else if (ret) { goto cleanup; @@ -1153,7 +1156,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1173,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } @@ -1252,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; - struct ip_set *set = ip_set(inst, index); + struct ip_set *set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); @@ -1441,7 +1444,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - set = ip_set(inst, index); + set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); @@ -2059,7 +2062,7 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; inst->is_deleted = false; @@ -2087,7 +2090,7 @@ ip_set_net_exit(struct net *net) } } nfnl_unlock(NFNL_SUBSYS_IPSET); - kfree(rcu_dereference_protected(inst->ip_set_list, 1)); + kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index d391485a6acd..613e18e720a4 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..4eef55da0878 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ca1168d67fac..e92e749aff53 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 171e9e122e5f..023c1445bc39 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = }, }; -static inline struct nf_dccp_net *dccp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp; -} - static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh) @@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: - dn = dccp_pernet(net); + dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; @@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; + timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, static int dccp_init_net(struct net *net) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); struct nf_proto_net *pn = &dn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e10e867e0b55..5da19d5fbc76 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static inline struct nf_generic_net *generic_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.generic; -} - static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct, } if (!timeout) - timeout = &generic_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) @@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, static int generic_init_net(struct net *net) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 3598520bd19b..de64d8a5fdfd 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,11 +25,6 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { @@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, } if (!timeout) - timeout = &icmp_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) @@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmp_init_net(struct net *net) { - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 378618feed5d..a15eefb8e317 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,11 +30,6 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, @@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &icmpv6_pernet(net)->timeout; + return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); @@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmpv6_init_net(struct net *net) { - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3d719d3eb9a3..d53e3e78f605 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { } }; -static inline struct nf_sctp_net *sctp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); @@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; /* set default SCTP timeouts. */ @@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int sctp_init_net(struct net *net) { - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1bcf9984d45e..4dcbd51a8e97 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; -static inline struct nf_tcp_net *tcp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); - const struct nf_tcp_net *tn = tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; @@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; @@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int tcp_init_net(struct net *net) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a7aa70370913..c879d8d78cfd 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_REPLIED] = 180*HZ, }; -static inline struct nf_udp_net *udp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udp; -} - static unsigned int *udp_get_timeouts(struct net *net) { - return udp_pernet(net)->timeouts; + return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, @@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; @@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int udp_init_net(struct net *net) { - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); struct nf_proto_net *pn = &un->pn; if (!pn->users) { diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index e7a50af1b3d6..a518eb162344 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -382,7 +382,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -442,12 +444,44 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &nf_icmp_pernet(net)->timeout; + break; + case IPPROTO_TCP: + timeouts = nf_tcp_pernet(net)->timeouts; + break; + case IPPROTO_UDP: + timeouts = nf_udp_pernet(net)->timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = nf_dccp_pernet(net)->dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &nf_icmpv6_pernet(net)->timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case 255: + timeouts = &nf_generic_pernet(net)->timeout; + break; + default: + WARN_ON_ONCE(1); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -458,8 +492,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l3num, - l4proto); + l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 768292eac2a4..9d0ede474224 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt) return false; } -static int nft_compat_chain_validate_dependency(const char *tablename, - const struct nft_chain *chain) +static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, + const char *tablename) { + enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; + const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || @@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename, return 0; basechain = nft_base_chain(chain); - if (strcmp(tablename, "nat") == 0 && - basechain->type->type != NFT_CHAIN_T_NAT) - return -EINVAL; + if (strcmp(tablename, "nat") == 0) { + if (ctx->family != NFPROTO_BRIDGE) + type = NFT_CHAIN_T_NAT; + if (basechain->type->type != type) + return -EINVAL; + } return 0; } @@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(target->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } @@ -590,8 +594,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 649d1700ec5b..3cc1b3dc3c3c 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,7 +24,6 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; - struct nft_set *map; }; static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) @@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_inc_gen(priv); } -static void nft_ng_inc_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_inc_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, - [NFTA_NG_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_inc_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_inc_init(ctx, expr, tb); - - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_inc_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_inc *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_INCREMENTAL, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static u32 nft_ng_random_gen(struct nft_ng_random *priv) @@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_random_gen(priv); } -static void nft_ng_random_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_random_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static int nft_ng_random_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_random_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_random_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_random *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_RANDOM, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; -static const struct nft_expr_ops nft_ng_inc_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), - .eval = nft_ng_inc_map_eval, - .init = nft_ng_inc_map_init, - .dump = nft_ng_inc_map_dump, -}; - static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; -static const struct nft_expr_ops nft_ng_random_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), - .eval = nft_ng_random_map_eval, - .init = nft_ng_random_map_init, - .dump = nft_ng_random_map_dump, -}; - static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_random_map_ops; return &nft_ng_random_ops; } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ca5e5d8c5ef8..b13618c764ec 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; - if (nla_get_u8(tb[NFTA_OSF_TTL])) { + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) return -EINVAL; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index c6acfc2d9c84..eb4cbd244c3d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } +static int idletimer_check_sysfs_name(const char *name, unsigned int size) +{ + int ret; + + ret = xt_check_proc_name(name, size); + if (ret < 0) + return ret; + + if (!strcmp(name, "power") || + !strcmp(name, "subsystem") || + !strcmp(name, "uevent")) + return -EINVAL; + + return 0; +} + static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; @@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); + if (ret < 0) + goto out_free_timer; + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6bec37ab4472..a4660c48ff01 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 382196e57a26..bc628acf4f4f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -611,6 +611,7 @@ struct rxrpc_call { * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 8e7434e92097..468efc3660c0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; + ack_at += READ_ONCE(call->tx_backoff); ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); @@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work) container_of(work, struct rxrpc_call, processor); rxrpc_serial_t *send_ack; unsigned long now, next, t; + unsigned int iterations = 0; rxrpc_see_call(call); @@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + /* Limit the number of times we do this before returning to the manager */ + iterations++; + if (iterations > 5) + goto requeue; + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; @@ -447,13 +454,16 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) { - __rxrpc_queue_call(call); - goto out; - } + if (call->events && call->state < RXRPC_CALL_COMPLETE) + goto requeue; out_put: rxrpc_put_call(call, rxrpc_call_put); out: _leave(""); + return; + +requeue: + __rxrpc_queue_call(call); + goto out; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 189418888839..736aa9281100 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -35,6 +35,21 @@ struct rxrpc_abort_buffer { static const char rxrpc_keepalive_string[] = ""; /* + * Increase Tx backoff on transmission failure and clear it on success. + */ +static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) +{ + if (ret < 0) { + u16 tx_backoff = READ_ONCE(call->tx_backoff); + + if (tx_backoff < HZ) + WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + } else { + WRITE_ONCE(call->tx_backoff, 0); + } +} + +/* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep * the route through any intervening firewall open. @@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, else trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, rxrpc_tx_point_call_ack); + rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), - true, true, + false, true, rxrpc_propose_ack_retry_tx); } else { spin_lock_bh(&call->lock); @@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) else trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); - + rxrpc_tx_backoff(call, ret); rxrpc_put_connection(conn); return ret; @@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -445,9 +462,18 @@ done: rxrpc_reduce_call_timer(call, expect_rx_by, nowj, rxrpc_timer_set_for_normal); } - } - rxrpc_set_keepalive(call); + rxrpc_set_keepalive(call); + } else { + /* Cancel the call if the initial transmission fails, + * particularly if that's due to network routing issues that + * aren't going away anytime soon. The layer above can arrange + * the retransmission. + */ + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_USER_ABORT, ret); + } _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; @@ -506,6 +532,7 @@ send_fragmentable: else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); goto done; diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9cb854b05342..c37e1c2dec9d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_FCFS); + sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 7f0424dfa8f6..eab71fc7af3e 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -274,6 +274,7 @@ out_err: static int gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) { + u32 seq_send; int tmp; p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate)); @@ -315,9 +316,10 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); if (IS_ERR(p)) goto out_err; - p = simple_get_bytes(p, end, &ctx->seq_send, sizeof(ctx->seq_send)); + p = simple_get_bytes(p, end, &seq_send, sizeof(seq_send)); if (IS_ERR(p)) goto out_err; + atomic_set(&ctx->seq_send, seq_send); p = simple_get_netobj(p, end, &ctx->mech_used); if (IS_ERR(p)) goto out_err; @@ -607,6 +609,7 @@ static int gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, gfp_t gfp_mask) { + u64 seq_send64; int keylen; p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags)); @@ -617,14 +620,15 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); if (IS_ERR(p)) goto out_err; - p = simple_get_bytes(p, end, &ctx->seq_send64, sizeof(ctx->seq_send64)); + p = simple_get_bytes(p, end, &seq_send64, sizeof(seq_send64)); if (IS_ERR(p)) goto out_err; + atomic64_set(&ctx->seq_send64, seq_send64); /* set seq_send for use by "older" enctypes */ - ctx->seq_send = ctx->seq_send64; - if (ctx->seq_send64 != ctx->seq_send) { - dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__, - (unsigned long)ctx->seq_send64, ctx->seq_send); + atomic_set(&ctx->seq_send, seq_send64); + if (seq_send64 != atomic_read(&ctx->seq_send)) { + dprintk("%s: seq_send64 %llx, seq_send %x overflow?\n", __func__, + seq_send64, atomic_read(&ctx->seq_send)); p = ERR_PTR(-EINVAL); goto out_err; } diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index b4adeb06660b..48fe4a591b54 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -123,30 +123,6 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token) return krb5_hdr; } -u32 -gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx) -{ - u32 old, seq_send = READ_ONCE(ctx->seq_send); - - do { - old = seq_send; - seq_send = cmpxchg(&ctx->seq_send, old, old + 1); - } while (old != seq_send); - return seq_send; -} - -u64 -gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx) -{ - u64 old, seq_send = READ_ONCE(ctx->seq_send); - - do { - old = seq_send; - seq_send = cmpxchg64(&ctx->seq_send64, old, old + 1); - } while (old != seq_send); - return seq_send; -} - static u32 gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj *token) @@ -177,7 +153,7 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - seq_send = gss_seq_send_fetch_and_inc(ctx); + seq_send = atomic_fetch_inc(&ctx->seq_send); if (krb5_make_seq_num(ctx, ctx->seq, ctx->initiate ? 0 : 0xff, seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)) @@ -205,7 +181,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, /* Set up the sequence number. Now 64-bits in clear * text and w/o direction indicator */ - seq_send_be64 = cpu_to_be64(gss_seq_send64_fetch_and_inc(ctx)); + seq_send_be64 = cpu_to_be64(atomic64_fetch_inc(&ctx->seq_send64)); memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8); if (ctx->initiate) { diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 962fa84e6db1..5cdde6cb703a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -228,7 +228,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len); - seq_send = gss_seq_send_fetch_and_inc(kctx); + seq_send = atomic_fetch_inc(&kctx->seq_send); /* XXX would probably be more efficient to compute checksum * and encrypt at the same time: */ @@ -475,7 +475,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, *be16ptr++ = 0; be64ptr = (__be64 *)be16ptr; - *be64ptr = cpu_to_be64(gss_seq_send64_fetch_and_inc(kctx)); + *be64ptr = cpu_to_be64(atomic64_fetch_inc(&kctx->seq_send64)); err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages); if (err) diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 97f49b751e6e..568575b72f2f 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -58,8 +58,8 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 && - snd_hda_gen_add_micmute_led(codec, - update_tpacpi_micmute) > 0) + !snd_hda_gen_add_micmute_led(codec, + update_tpacpi_micmute)) removefunc = false; } diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 12835ea0e417..378c051fa177 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,74 +14,75 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") -#define smp_store_release(p, v) \ -do { \ - union { typeof(*p) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(*p)) (v) }; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u8 *)__u.__c) \ - : "memory"); \ - break; \ - case 2: \ - asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u16 *)__u.__c) \ - : "memory"); \ - break; \ - case 4: \ - asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u32 *)__u.__c) \ - : "memory"); \ - break; \ - case 8: \ - asm volatile ("stlr %1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u64 *)__u.__c) \ - : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ +#define smp_store_release(p, v) \ +do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (v) }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u8_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u16_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile ("stlr %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u32_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile ("stlr %1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u64_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ } while (0) -#define smp_load_acquire(p) \ -({ \ - union { typeof(*p) __val; char __c[1]; } __u; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("ldarb %w0, %1" \ - : "=r" (*(__u8 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 2: \ - asm volatile ("ldarh %w0, %1" \ - : "=r" (*(__u16 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 4: \ - asm volatile ("ldar %w0, %1" \ - : "=r" (*(__u32 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 8: \ - asm volatile ("ldar %0, %1" \ - : "=r" (*(__u64 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ - __u.__val; \ +#define smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (*(__u8_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (*(__u16_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 4: \ + asm volatile ("ldar %w0, %1" \ + : "=r" (*(__u32_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 8: \ + asm volatile ("ldar %0, %1" \ + : "=r" (*(__u64_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ + __u.__val; \ }) #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */ diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 236b9b97dfdb..667c14e56031 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -55,7 +55,6 @@ counted. The following modifiers exist: S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, - only supported in 'perf stat' for now. The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3ccb4f0bf088..d95655489f7e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH) linux_uapi_dir := $(srctree)/tools/include/uapi/linux asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic -arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/ +arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/ beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 10cf889c6d75..488779bc4c8d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -391,7 +391,12 @@ try_again: ui__warning("%s\n", msg); goto try_again; } - + if ((errno == EINVAL || errno == EBADF) && + pos->leader != pos && + pos->weak_group) { + pos = perf_evlist__reset_weak_group(evlist, pos); + goto try_again; + } rc = -errno; perf_evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg)); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d1028d7755bb..a635abfa77b6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter) return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; } -static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) -{ - struct perf_evsel *c2, *leader; - bool is_open = true; - - leader = evsel->leader; - pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); - - /* - * for_each_group_member doesn't work here because it doesn't - * include the first entry. - */ - evlist__for_each_entry(evsel_list, c2) { - if (c2 == evsel) - is_open = false; - if (c2->leader == leader) { - if (is_open) - perf_evsel__close(c2); - c2->leader = c2; - c2->nr_members = 0; - } - } - return leader; -} - static bool is_target_alive(struct target *_target, struct thread_map *threads) { @@ -477,7 +451,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - counter = perf_evsel__reset_weak_group(counter); + counter = perf_evlist__reset_weak_group(evsel_list, counter); goto try_again; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b2838de13de0..aa0c73e57924 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv) } } + if (opts->branch_stack && callchain_param.enabled) + symbol_conf.show_branchflag_count = true; + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ perf_hpp_list.need_collapse = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dc8a6c4986ce..835619476370 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -108,6 +108,7 @@ struct trace { } stats; unsigned int max_stack; unsigned int min_stack; + bool raw_augmented_syscalls; bool not_ev_qualifier; bool live; bool full_time; @@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } -static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size) +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented) { void *augmented_args = NULL; + /* + * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter + * and there we get all 6 syscall args plus the tracepoint common + * fields (sizeof(long)) and the syscall_nr (another long). So we check + * if that is the case and if so don't look after the sc->args_size, + * but always after the full raw_syscalls:sys_enter payload, which is + * fixed. + * + * We'll revisit this later to pass s->args_size to the BPF augmenter + * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it + * copies only what we need for each syscall, like what happens when we + * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace + * traffic to just what is needed for each syscall. + */ + int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size; - *augmented_args_size = sample->raw_size - sc->args_size; + *augmented_args_size = sample->raw_size - args_size; if (*augmented_args_size > 0) - augmented_args = sample->raw_data + sc->args_size; + augmented_args = sample->raw_data + args_size; return augmented_args; } @@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); @@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse goto out_put; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); fprintf(trace->output, "%s", msg); err = 0; @@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv) evsel->handler = trace__sys_enter; evlist__for_each_entry(trace.evlist, evsel) { + bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0; + + if (raw_syscalls_sys_exit) { + trace.raw_augmented_syscalls = true; + goto init_augmented_syscall_tp; + } + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { +init_augmented_syscall_tp: perf_evsel__init_augmented_syscall_tp(evsel); perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c new file mode 100644 index 000000000000..90a19336310b --- /dev/null +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null + * + * This exactly matches what is marshalled into the raw_syscall:sys_enter + * payload expected by the 'perf trace' beautifiers. + * + * For now it just uses the existing tracepoint augmentation code in 'perf + * trace', in the next csets we'll hook up these with the sys_enter/sys_exit + * code that will combine entry/exit in a strace like way. + */ + +#include <stdio.h> +#include <linux/socket.h> + +/* bpf-output associated map */ +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_args { + unsigned long long common_tp_fields; + long syscall_nr; + unsigned long args[6]; +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define SYS_OPEN 2 +#define SYS_OPENAT 257 + +SEC("raw_syscalls:sys_enter") +int sys_enter(struct syscall_enter_args *args) +{ + struct { + struct syscall_enter_args args; + struct augmented_filename filename; + } augmented_args; + unsigned int len = sizeof(augmented_args); + const void *filename_arg = NULL; + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + /* + * Yonghong and Edward Cree sayz: + * + * https://www.spinics.net/lists/netdev/msg531645.html + * + * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 + * >> 10: (bf) r1 = r6 + * >> 11: (07) r1 += 16 + * >> 12: (05) goto pc+2 + * >> 15: (79) r3 = *(u64 *)(r1 +0) + * >> dereference of modified ctx ptr R1 off=16 disallowed + * > Aha, we at least got a different error message this time. + * > And indeed llvm has done that optimisation, rather than the more obvious + * > 11: r3 = *(u64 *)(r1 +16) + * > because it wants to have lots of reads share a single insn. You may be able + * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone + * > with llvm knowledge can figure out how to stop it (ideally, llvm would know + * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ + * + * The optimization mostly likes below: + * + * br1: + * ... + * r1 += 16 + * goto merge + * br2: + * ... + * r1 += 20 + * goto merge + * merge: + * *(u64 *)(r1 + 0) + * + * The compiler tries to merge common loads. There is no easy way to + * stop this compiler optimization without turning off a lot of other + * optimizations. The easiest way is to add barriers: + * + * __asm__ __volatile__("": : :"memory") + * + * after the ctx memory access to prevent their down stream merging. + */ + switch (augmented_args.args.syscall_nr) { + case SYS_OPEN: filename_arg = (const void *)args->args[0]; + __asm__ __volatile__("": : :"memory"); + break; + case SYS_OPENAT: filename_arg = (const void *)args->args[1]; + break; + } + + if (filename_arg != NULL) { + augmented_args.filename.reserved = 0; + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, + sizeof(augmented_args.filename.value), + filename_arg); + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; + len &= sizeof(augmented_args.filename.value) - 1; + } + } else { + len = sizeof(augmented_args.args); + } + + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return 0; +} + +SEC("raw_syscalls:sys_exit") +int sys_exit(struct syscall_exit_args *args) +{ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ +} + +license(GPL); diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index ac1bcdc17dae..f7eb63cbbc65 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -125,7 +125,7 @@ perf_get_timestamp(void) } static int -debug_cache_init(void) +create_jit_cache_dir(void) { char str[32]; char *base, *p; @@ -144,8 +144,13 @@ debug_cache_init(void) strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm); - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because %s/.debug/" + " is too long, please check the cwd, JITDUMPDIR, and" + " HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { @@ -154,20 +159,32 @@ debug_cache_init(void) } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base); + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit/%s.XXXXXXXX is too long, please check" + " the cwd, JITDUMPDIR, and HOME variables", + base, str); + return -1; + } p = mkdtemp(jit_path); if (p != jit_path) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } @@ -228,7 +245,7 @@ void *jvmti_open(void) { char dump_path[PATH_MAX]; struct jitheader header; - int fd; + int fd, ret; FILE *fp; init_arch_timestamp(); @@ -245,12 +262,22 @@ void *jvmti_open(void) memset(&header, 0, sizeof(header)); - debug_cache_init(); + /* + * jitdump file dir + */ + if (create_jit_cache_dir() < 0) + return NULL; /* * jitdump file name */ - scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jitdump file full path because" + " %s/jit-%i.dump is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", jit_path, getpid()); + return NULL; + } fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 24cb0bd56afa..f278ce5ebab7 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -119,6 +119,14 @@ def dsoname(name): return "[kernel]" return name +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + # Percent to one decimal place def PercentToOneDP(n, d): @@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow): else: self.find_bar.NotFound() +# Dialog data item converted and validated using a SQL table + +class SQLTableDialogDataItem(): + + def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent): + self.glb = glb + self.label = label + self.placeholder_text = placeholder_text + self.table_name = table_name + self.match_column = match_column + self.column_name1 = column_name1 + self.column_name2 = column_name2 + self.parent = parent + + self.value = "" + + self.widget = QLineEdit() + self.widget.editingFinished.connect(self.Validate) + self.widget.textChanged.connect(self.Invalidate) + self.red = False + self.error = "" + self.validated = True + + self.last_id = 0 + self.first_time = 0 + self.last_time = 2 ** 64 + if self.table_name == "<timeranges>": + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1") + if query.next(): + self.last_id = int(query.value(0)) + self.last_time = int(query.value(1)) + QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1") + if query.next(): + self.first_time = int(query.value(0)) + if placeholder_text: + placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time) + + if placeholder_text: + self.widget.setPlaceholderText(placeholder_text) + + def ValueToIds(self, value): + ids = [] + query = QSqlQuery(self.glb.db) + stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'" + ret = query.exec_(stmt) + if ret: + while query.next(): + ids.append(str(query.value(0))) + return ids + + def IdBetween(self, query, lower_id, higher_id, order): + QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1") + if query.next(): + return True, int(query.value(0)) + else: + return False, 0 + + def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor): + query = QSqlQuery(self.glb.db) + while True: + next_id = int((lower_id + higher_id) / 2) + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + if not query.next(): + ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC") + if not ok: + ok, dbid = self.IdBetween(query, next_id, higher_id, "") + if not ok: + return str(higher_id) + next_id = dbid + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + next_time = int(query.value(0)) + if get_floor: + if target_time > next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(higher_id) + else: + if target_time >= next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(lower_id) + + def ConvertRelativeTime(self, val): + print "val ", val + mult = 1 + suffix = val[-2:] + if suffix == "ms": + mult = 1000000 + elif suffix == "us": + mult = 1000 + elif suffix == "ns": + mult = 1 + else: + return val + val = val[:-2].strip() + if not self.IsNumber(val): + return val + val = int(val) * mult + if val >= 0: + val += self.first_time + else: + val += self.last_time + return str(val) + + def ConvertTimeRange(self, vrange): + print "vrange ", vrange + if vrange[0] == "": + vrange[0] = str(self.first_time) + if vrange[1] == "": + vrange[1] = str(self.last_time) + vrange[0] = self.ConvertRelativeTime(vrange[0]) + vrange[1] = self.ConvertRelativeTime(vrange[1]) + print "vrange2 ", vrange + if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return False + print "ok1" + beg_range = max(int(vrange[0]), self.first_time) + end_range = min(int(vrange[1]), self.last_time) + if beg_range > self.last_time or end_range < self.first_time: + return False + print "ok2" + vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True) + vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False) + print "vrange3 ", vrange + return True + + def AddTimeRange(self, value, ranges): + print "value ", value + n = value.count("-") + if n == 1: + pass + elif n == 2: + if value.split("-")[1].strip() == "": + n = 1 + elif n == 3: + n = 2 + else: + return False + pos = findnth(value, "-", n) + vrange = [value[:pos].strip() ,value[pos+1:].strip()] + if self.ConvertTimeRange(vrange): + ranges.append(vrange) + return True + return False + + def InvalidValue(self, value): + self.value = "" + palette = QPalette() + palette.setColor(QPalette.Text,Qt.red) + self.widget.setPalette(palette) + self.red = True + self.error = self.label + " invalid value '" + value + "'" + self.parent.ShowMessage(self.error) + + def IsNumber(self, value): + try: + x = int(value) + except: + x = 0 + return str(x) == value + + def Invalidate(self): + self.validated = False + + def Validate(self): + input_string = self.widget.text() + self.validated = True + if self.red: + palette = QPalette() + self.widget.setPalette(palette) + self.red = False + if not len(input_string.strip()): + self.error = "" + self.value = "" + return + if self.table_name == "<timeranges>": + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if not self.AddTimeRange(value, ranges): + return self.InvalidValue(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + self.value = " OR ".join(ranges) + elif self.table_name == "<ranges>": + singles = [] + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if "-" in value: + vrange = value.split("-") + if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return self.InvalidValue(value) + ranges.append(vrange) + else: + if not self.IsNumber(value): + return self.InvalidValue(value) + singles.append(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + if len(singles): + ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")") + self.value = " OR ".join(ranges) + elif self.table_name: + all_ids = [] + for value in [x.strip() for x in input_string.split(",")]: + ids = self.ValueToIds(value) + if len(ids): + all_ids.extend(ids) + else: + return self.InvalidValue(value) + self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")" + if self.column_name2: + self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )" + else: + self.value = input_string.strip() + self.error = "" + self.parent.ClearMessage() + + def IsValid(self): + if not self.validated: + self.Validate() + if len(self.error): + self.parent.ShowMessage(self.error) + return False + return True + +# Selected branch report creation dialog + +class SelectedBranchDialog(QDialog): + + def __init__(self, glb, parent=None): + super(SelectedBranchDialog, self).__init__(parent) + + self.glb = glb + + self.name = "" + self.where_clause = "" + + self.setWindowTitle("Selected Branches") + self.setMinimumWidth(600) + + items = ( + ("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""), + ("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""), + ("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""), + ("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""), + ("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""), + ("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""), + ("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"), + ("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"), + ("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""), + ) + self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items] + + self.grid = QGridLayout() + + for row in xrange(len(self.data_items)): + self.grid.addWidget(QLabel(self.data_items[row].label), row, 0) + self.grid.addWidget(self.data_items[row].widget, row, 1) + + self.status = QLabel() + + self.ok_button = QPushButton("Ok", self) + self.ok_button.setDefault(True) + self.ok_button.released.connect(self.Ok) + self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.cancel_button = QPushButton("Cancel", self) + self.cancel_button.released.connect(self.reject) + self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.hbox = QHBoxLayout() + #self.hbox.addStretch() + self.hbox.addWidget(self.status) + self.hbox.addWidget(self.ok_button) + self.hbox.addWidget(self.cancel_button) + + self.vbox = QVBoxLayout() + self.vbox.addLayout(self.grid) + self.vbox.addLayout(self.hbox) + + self.setLayout(self.vbox); + + def Ok(self): + self.name = self.data_items[0].value + if not self.name: + self.ShowMessage("Report name is required") + return + for d in self.data_items: + if not d.IsValid(): + return + for d in self.data_items[1:]: + if len(d.value): + if len(self.where_clause): + self.where_clause += " AND " + self.where_clause += d.value + if len(self.where_clause): + self.where_clause = " AND ( " + self.where_clause + " ) " + else: + self.ShowMessage("No selection") + return + self.accept() + + def ShowMessage(self, msg): + self.status.setText("<font color=#FF0000>" + msg) + + def ClearMessage(self): + self.status.setText("") + # Event list def GetEventList(db): @@ -1656,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): def FindDone(self, row): self.find_bar.Idle() if row >= 0: - self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex()))) else: self.find_bar.NotFound() @@ -1765,6 +2084,149 @@ class WindowMenu(): def setActiveSubWindow(self, nr): self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1]) +# Help text + +glb_help_text = """ +<h1>Contents</h1> +<style> +p.c1 { + text-indent: 40px; +} +p.c2 { + text-indent: 80px; +} +} +</style> +<p class=c1><a href=#reports>1. Reports</a></p> +<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p> +<p class=c2><a href=#allbranches>1.2 All branches</a></p> +<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p> +<p class=c1><a href=#tables>2. Tables</a></p> +<h1 id=reports>1. Reports</h1> +<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2> +The result is a GUI window with a tree representing a context-sensitive +call-graph. Expanding a couple of levels of the tree and adjusting column +widths to suit will display something like: +<pre> + Call Graph: pt_example +Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +v- ls + v- 2638:2638 + v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 + |- unknown unknown 1 13198 0.1 1 0.0 + >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 + >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 + v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 + >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 + >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 + >- __libc_csu_init ls 1 10354 0.1 10 0.0 + |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 + v- main ls 1 8182043 99.6 180254 99.9 +</pre> +<h3>Points to note:</h3> +<ul> +<li>The top level is a command name (comm)</li> +<li>The next level is a thread (pid:tid)</li> +<li>Subsequent levels are functions</li> +<li>'Count' is the number of calls</li> +<li>'Time' is the elapsed time until the function returns</li> +<li>Percentages are relative to the level above</li> +<li>'Branch Count' is the total number of branches for that function and all functions that it calls +</ul> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match. +The pattern matching symbols are ? for any character and * for zero or more characters. +<h2 id=allbranches>1.2 All branches</h2> +The All branches report displays all branches in chronological order. +Not all data is fetched immediately. More records can be fetched using the Fetch bar provided. +<h3>Disassembly</h3> +Open a branch to display disassembly. This only works if: +<ol> +<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li> +<li>The object code is available. Currently, only the perf build ID cache is searched for object code. +The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR. +One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu), +or alternatively, set environment variable PERF_KCORE to the kcore file name.</li> +</ol> +<h4 id=xed>Intel XED Setup</h4> +To use Intel XED, libxed.so must be present. To build and install libxed.so: +<pre> +git clone https://github.com/intelxed/mbuild.git mbuild +git clone https://github.com/intelxed/xed +cd xed +./mfile.py --share +sudo ./mfile.py --prefix=/usr/local install +sudo ldconfig +</pre> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<h2 id=selectedbranches>1.3 Selected branches</h2> +This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced +by various selection criteria. A dialog box displays available criteria which are AND'ed together. +<h3>1.3.1 Time ranges</h3> +The time ranges hint text shows the total time range. Relative time ranges can also be entered in +ms, us or ns. Also, negative values are relative to the end of trace. Examples: +<pre> + 81073085947329-81073085958238 From 81073085947329 to 81073085958238 + 100us-200us From 100us to 200us + 10ms- From 10ms to the end + -100ns The first 100ns + -10ms- The last 10ms +</pre> +N.B. Due to the granularity of timestamps, there could be no branches in any given time range. +<h1 id=tables>2. Tables</h1> +The Tables menu shows all tables and views in the database. Most tables have an associated view +which displays the information in a more friendly way. Not all data for large tables is fetched +immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted, +but that can be slow for large tables. +<p>There are also tables of database meta-information. +For SQLite3 databases, the sqlite_master table is included. +For PostgreSQL databases, information_schema.tables/views/columns are included. +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous +will go to the next/previous result in id order, instead of display order. +""" + +# Help window + +class HelpWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(HelpWindow, self).__init__(parent) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setWidget(self.text) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help") + +# Main window that only displays the help text + +class HelpOnlyWindow(QMainWindow): + + def __init__(self, parent=None): + super(HelpOnlyWindow, self).__init__(parent) + + self.setMinimumSize(200, 100) + self.resize(800, 600) + self.setWindowTitle("Exported SQL Viewer Help") + self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setCentralWidget(self.text) + # Font resize def ResizeFont(widget, diff): @@ -1851,6 +2313,9 @@ class MainWindow(QMainWindow): self.window_menu = WindowMenu(self.mdi_area, menu) + help_menu = menu.addMenu("&Help") + help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + def Find(self): win = self.mdi_area.activeSubWindow() if win: @@ -1888,6 +2353,8 @@ class MainWindow(QMainWindow): if event == "branches": label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")" reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self)) + label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self)) def TableMenu(self, tables, menu): table_menu = menu.addMenu("&Tables") @@ -1900,9 +2367,18 @@ class MainWindow(QMainWindow): def NewBranchView(self, event_id): BranchWindow(self.glb, event_id, "", "", self) + def NewSelectedBranchView(self, event_id): + dialog = SelectedBranchDialog(self.glb, self) + ret = dialog.exec_() + if ret: + BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self) + def NewTableView(self, table_name): TableWindow(self.glb, table_name, self) + def Help(self): + HelpWindow(self.glb, self) + # XED Disassembler class xed_state_t(Structure): @@ -1929,7 +2405,12 @@ class XEDInstruction(): class LibXED(): def __init__(self): - self.libxed = CDLL("libxed.so") + try: + self.libxed = CDLL("libxed.so") + except: + self.libxed = None + if not self.libxed: + self.libxed = CDLL("/usr/local/lib/libxed.so") self.xed_tables_init = self.libxed.xed_tables_init self.xed_tables_init.restype = None @@ -2097,10 +2578,16 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>" + print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" raise Exception("Too few arguments") dbname = sys.argv[1] + if dbname == "--help-only": + app = QApplication(sys.argv) + mainwindow = HelpOnlyWindow() + mainwindow.show() + err = app.exec_() + sys.exit(err) is_sqlite3 = False try: diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 8a33ca4f9e1f..f0729c454f16 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -37,4 +37,3 @@ sample_freq=0 sample_period=0 freq=0 write_backward=0 -sample_id_all=0 diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e88e6f9b1463..668d2a9ef0f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist) leader->forced_leader = true; } } + +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, + struct perf_evsel *evsel) +{ + struct perf_evsel *c2, *leader; + bool is_open = true; + + leader = evsel->leader; + pr_debug("Weak group for %s/%d failed\n", + leader->name, leader->nr_members); + + /* + * for_each_group_member doesn't work here because it doesn't + * include the first entry. + */ + evlist__for_each_entry(evsel_list, c2) { + if (c2 == evsel) + is_open = false; + if (c2->leader == leader) { + if (is_open) + perf_evsel__close(c2); + c2->leader = c2; + c2->nr_members = 0; + } + } + return leader; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dc66436add98..9919eed6d15b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); void perf_evlist__force_leader(struct perf_evlist *evlist); +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, + struct perf_evsel *evsel); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d187059a373..d37bb1566cd9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_freq = 0; attr->sample_period = 0; attr->write_backward = 0; - attr->sample_id_all = 0; } if (opts->no_samples) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 58f6a9ceb590..4503f3ca45ab 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) decoder->have_calc_cyc_to_tsc = false; intel_pt_calc_cyc_to_tsc(decoder, true); } + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) @@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) decoder->timestamp = timestamp; decoder->timestamp_insn_cnt = 0; + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } /* Walk PSB+ packets when already in sync. */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index e02bc7b166a0..5e64da270f97 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -31,6 +31,11 @@ static FILE *f; static char log_name[MAX_LOG_NAME]; bool intel_pt_enable_logging; +void *intel_pt_log_fp(void) +{ + return f; +} + void intel_pt_log_enable(void) { intel_pt_enable_logging = true; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index 45b64f93f358..cc084937f701 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -22,6 +22,7 @@ struct intel_pt_pkt; +void *intel_pt_log_fp(void); void intel_pt_log_enable(void); void intel_pt_log_disable(void); void intel_pt_log_set_name(const char *name); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 86cc9a64e982..149ff361ca78 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, intel_pt_dump(pt, buf, len); } +static void intel_pt_log_event(union perf_event *event) +{ + FILE *f = intel_pt_log_fp(); + + if (!intel_pt_enable_logging || !f) + return; + + perf_event__fprintf(event, f); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n", - perf_event__name(event->header.type), event->header.type, - sample->cpu, sample->time, timestamp); + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); return err; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7799788f662f..7e49baad304d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; - if (strncmp(pname, name, strlen(pname))) + if (strcmp(pname, name)) continue; } |