diff options
481 files changed, 15697 insertions, 4502 deletions
diff --git a/Documentation/ABI/testing/sysfs-platform-lg-laptop b/Documentation/ABI/testing/sysfs-platform-lg-laptop new file mode 100644 index 00000000000000..cf47749b19dfdc --- /dev/null +++ b/Documentation/ABI/testing/sysfs-platform-lg-laptop @@ -0,0 +1,35 @@ +What: /sys/devices/platform/lg-laptop/reader_mode +Date: October 2018 +KernelVersion: 4.20 +Contact: "Matan Ziv-Av <matan@svgalib.org> +Description: + Control reader mode. 1 means on, 0 means off. + +What: /sys/devices/platform/lg-laptop/fn_lock +Date: October 2018 +KernelVersion: 4.20 +Contact: "Matan Ziv-Av <matan@svgalib.org> +Description: + Control FN lock mode. 1 means on, 0 means off. + +What: /sys/devices/platform/lg-laptop/battery_care_limit +Date: October 2018 +KernelVersion: 4.20 +Contact: "Matan Ziv-Av <matan@svgalib.org> +Description: + Maximal battery charge level. Accepted values are 80 or 100. + +What: /sys/devices/platform/lg-laptop/fan_mode +Date: October 2018 +KernelVersion: 4.20 +Contact: "Matan Ziv-Av <matan@svgalib.org> +Description: + Control fan mode. 1 for performance mode, 0 for silent mode. + +What: /sys/devices/platform/lg-laptop/usb_charge +Date: October 2018 +KernelVersion: 4.20 +Contact: "Matan Ziv-Av <matan@svgalib.org> +Description: + Control USB port charging when device is turned off. + 1 means on, 0 means off. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8384c681a4b2e0..476722b7b6367c 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1879,10 +1879,8 @@ following two functions. wbc_init_bio(@wbc, @bio) Should be called for each bio carrying writeback data and - associates the bio with the inode's owner cgroup and the - corresponding request queue. This must be called after - a queue (device) has been associated with the bio and - before submission. + associates the bio with the inode's owner cgroup. Can be + called anytime between bio allocation and submission. wbc_account_io(@wbc, @page, @bytes) Should be called for each data segment being written out. @@ -1901,7 +1899,7 @@ the configuration, the bio may be executed at a lower priority and if the writeback session is holding shared resources, e.g. a journal entry, may lead to priority inversion. There is no one easy solution for the problem. Filesystems can try to work around specific problem -cases by skipping wbc_init_bio() or using bio_associate_create_blkg() +cases by skipping wbc_init_bio() or using bio_associate_blkcg() directly. diff --git a/Documentation/crypto/asymmetric-keys.txt b/Documentation/crypto/asymmetric-keys.txt index 5969bf42562a87..8763866b11cfd0 100644 --- a/Documentation/crypto/asymmetric-keys.txt +++ b/Documentation/crypto/asymmetric-keys.txt @@ -183,6 +183,10 @@ and looks like the following: void (*describe)(const struct key *key, struct seq_file *m); void (*destroy)(void *payload); + int (*query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + int (*eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); int (*verify_signature)(const struct key *key, const struct public_key_signature *sig); }; @@ -207,12 +211,22 @@ There are a number of operations defined by the subtype: asymmetric key will look after freeing the fingerprint and releasing the reference on the subtype module. - (3) verify_signature(). + (3) query(). - Optional. These are the entry points for the key usage operations. - Currently there is only the one defined. If not set, the caller will be - given -ENOTSUPP. The subtype may do anything it likes to implement an - operation, including offloading to hardware. + Mandatory. This is a function for querying the capabilities of a key. + + (4) eds_op(). + + Optional. This is the entry point for the encryption, decryption and + signature creation operations (which are distinguished by the operation ID + in the parameter struct). The subtype may do anything it likes to + implement an operation, including offloading to hardware. + + (5) verify_signature(). + + Optional. This is the entry point for signature verification. The + subtype may do anything it likes to implement an operation, including + offloading to hardware. ========================== @@ -234,6 +248,8 @@ Examples of blob formats for which parsers could be implemented include: - X.509 ASN.1 stream. - Pointer to TPM key. - Pointer to UEFI key. + - PKCS#8 private key [RFC 5208]. + - PKCS#5 encrypted private key [RFC 2898]. During key instantiation each parser in the list is tried until one doesn't return -EBADMSG. diff --git a/Documentation/devicetree/bindings/arm/cpu-capacity.txt b/Documentation/devicetree/bindings/arm/cpu-capacity.txt index 9b5685a1d15d98..84262cdb8d29ae 100644 --- a/Documentation/devicetree/bindings/arm/cpu-capacity.txt +++ b/Documentation/devicetree/bindings/arm/cpu-capacity.txt @@ -59,9 +59,11 @@ mhz values (normalized w.r.t. the highest value found while parsing the DT). =========================================== Example 1 (ARM 64-bit, 6-cpu system, two clusters): -capacities-dmips-mhz are scaled w.r.t. 1024 (cpu@0 and cpu@1) -supposing cluster0@max-freq=1100 and custer1@max-freq=850, -final capacities are 1024 for cluster0 and 446 for cluster1 +The capacities-dmips-mhz or DMIPS/MHz values (scaled to 1024) +are 1024 and 578 for cluster0 and cluster1. Further normalization +is done by the operating system based on cluster0@max-freq=1100 and +custer1@max-freq=850, final capacities are 1024 for cluster0 and +446 for cluster1 (576*850/1100). cpus { #address-cells = <2>; diff --git a/Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt b/Documentation/devicetree/bindings/display/panel/innolux,p120zdg-bf1.txt index a9b35265fa13a4..513f03466abac5 100644 --- a/Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt +++ b/Documentation/devicetree/bindings/display/panel/innolux,p120zdg-bf1.txt @@ -1,20 +1,22 @@ -Innolux TV123WAM 12.3 inch eDP 2K display panel +Innolux P120ZDG-BF1 12.02 inch eDP 2K display panel This binding is compatible with the simple-panel binding, which is specified in simple-panel.txt in this directory. Required properties: -- compatible: should be "innolux,tv123wam" +- compatible: should be "innolux,p120zdg-bf1" - power-supply: regulator to provide the supply voltage Optional properties: - enable-gpios: GPIO pin to enable or disable the panel - backlight: phandle of the backlight device attached to the panel +- no-hpd: If HPD isn't hooked up; add this property. Example: panel_edp: panel-edp { - compatible = "innolux,tv123wam"; + compatible = "innolux,p120zdg-bf1"; enable-gpios = <&msmgpio 31 GPIO_ACTIVE_LOW>; power-supply = <&pm8916_l2>; backlight = <&backlight>; + no-hpd; }; diff --git a/Documentation/devicetree/bindings/display/panel/simple-panel.txt b/Documentation/devicetree/bindings/display/panel/simple-panel.txt index 45a457ad38f0f0..b2b872c710f24d 100644 --- a/Documentation/devicetree/bindings/display/panel/simple-panel.txt +++ b/Documentation/devicetree/bindings/display/panel/simple-panel.txt @@ -11,6 +11,9 @@ Optional properties: - ddc-i2c-bus: phandle of an I2C controller used for DDC EDID probing - enable-gpios: GPIO pin to enable or disable the panel - backlight: phandle of the backlight device attached to the panel +- no-hpd: This panel is supposed to communicate that it's ready via HPD + (hot plug detect) signal, but the signal isn't hooked up so we should + hardcode the max delay from the panel spec when powering up the panel. Example: diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt index 091c8dfd322910..b245363d6d60a0 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt @@ -3,6 +3,7 @@ Required properties: - compatible : - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc + - "fsl,imx8qxp-lpi2c" for LPI2C compatible with the one integrated on i.MX8QXP soc - reg : address and length of the lpi2c master registers - interrupts : lpi2c interrupt - clocks : lpi2c clock specifier diff --git a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt index 06a363d9ccef90..b9a1d7402128b9 100644 --- a/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt +++ b/Documentation/devicetree/bindings/pwm/pwm-tiecap.txt @@ -7,6 +7,7 @@ Required properties: for da850 - compatible = "ti,da850-ecap", "ti,am3352-ecap", "ti,am33xx-ecap"; for dra746 - compatible = "ti,dra746-ecap", "ti,am3352-ecap"; for 66ak2g - compatible = "ti,k2g-ecap", "ti,am3352-ecap"; + for am654 - compatible = "ti,am654-ecap", "ti,am3352-ecap"; - #pwm-cells: should be 3. See pwm.txt in this directory for a description of the cells format. The PWM channel index ranges from 0 to 4. The only third cell flag supported by this binding is PWM_POLARITY_INVERTED. diff --git a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt index e1ef6afbe3a74a..7f31fe7e209348 100644 --- a/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt +++ b/Documentation/devicetree/bindings/pwm/renesas,pwm-rcar.txt @@ -3,7 +3,9 @@ Required Properties: - compatible: should be "renesas,pwm-rcar" and one of the following. - "renesas,pwm-r8a7743": for RZ/G1M + - "renesas,pwm-r8a7744": for RZ/G1N - "renesas,pwm-r8a7745": for RZ/G1E + - "renesas,pwm-r8a774a1": for RZ/G2M - "renesas,pwm-r8a7778": for R-Car M1A - "renesas,pwm-r8a7779": for R-Car H1 - "renesas,pwm-r8a7790": for R-Car H2 @@ -12,6 +14,8 @@ Required Properties: - "renesas,pwm-r8a7795": for R-Car H3 - "renesas,pwm-r8a7796": for R-Car M3-W - "renesas,pwm-r8a77965": for R-Car M3-N + - "renesas,pwm-r8a77970": for R-Car V3M + - "renesas,pwm-r8a77980": for R-Car V3H - "renesas,pwm-r8a77990": for R-Car E3 - "renesas,pwm-r8a77995": for R-Car D3 - reg: base address and length of the registers block for the PWM. diff --git a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt index d53a16715da6ac..848a92b53d810e 100644 --- a/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt +++ b/Documentation/devicetree/bindings/pwm/renesas,tpu-pwm.txt @@ -2,13 +2,19 @@ Required Properties: - - compatible: should be one of the following. + - compatible: must contain one or more of the following: - "renesas,tpu-r8a73a4": for R8A73A4 (R-Mobile APE6) compatible PWM controller. - "renesas,tpu-r8a7740": for R8A7740 (R-Mobile A1) compatible PWM controller. - "renesas,tpu-r8a7743": for R8A7743 (RZ/G1M) compatible PWM controller. + - "renesas,tpu-r8a7744": for R8A7744 (RZ/G1N) compatible PWM controller. - "renesas,tpu-r8a7745": for R8A7745 (RZ/G1E) compatible PWM controller. - "renesas,tpu-r8a7790": for R8A7790 (R-Car H2) compatible PWM controller. - - "renesas,tpu": for generic R-Car and RZ/G1 TPU PWM controller. + - "renesas,tpu-r8a77970": for R8A77970 (R-Car V3M) compatible PWM + controller. + - "renesas,tpu-r8a77980": for R8A77980 (R-Car V3H) compatible PWM + controller. + - "renesas,tpu": for the generic TPU PWM controller; this is a fallback for + the entries listed above. - reg: Base address and length of each memory resource used by the PWM controller hardware module. diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt index 51c136c821bfb0..eef7d9d259e857 100644 --- a/Documentation/filesystems/overlayfs.txt +++ b/Documentation/filesystems/overlayfs.txt @@ -286,6 +286,12 @@ pointed by REDIRECT. This should not be possible on local system as setting "trusted." xattrs will require CAP_SYS_ADMIN. But it should be possible for untrusted layers like from a pen drive. +Note: redirect_dir={off|nofollow|follow(*)} conflicts with metacopy=on, and +results in an error. + +(*) redirect_dir=follow only conflicts with metacopy=on if upperdir=... is +given. + Sharing and copying layers -------------------------- diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 321d74b7393723..cf43bc4dbf319b 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -623,6 +623,11 @@ in your dentry operations instead. On success you get a new struct file sharing the mount/dentry with the original, on failure - ERR_PTR(). -- +[mandatory] + ->clone_file_range() and ->dedupe_file_range have been replaced with + ->remap_file_range(). See Documentation/filesystems/vfs.txt for more + information. +-- [recommended] ->lookup() instances doing an equivalent of if (IS_ERR(inode)) diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index a6c6a8af48a296..5f71a252e2e0f5 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -883,8 +883,9 @@ struct file_operations { unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); }; @@ -960,11 +961,18 @@ otherwise noted. copy_file_range: called by the copy_file_range(2) system call. - clone_file_range: called by the ioctl(2) system call for FICLONERANGE and - FICLONE commands. - - dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE - command. + remap_file_range: called by the ioctl(2) system call for FICLONERANGE and + FICLONE and FIDEDUPERANGE commands to remap file ranges. An + implementation should remap len bytes at pos_in of the source file into + the dest file at pos_out. Implementations must handle callers passing + in len == 0; this means "remap to the end of the source file". The + return value should the number of bytes remapped, or the usual + negative error code if errors occurred before any bytes were remapped. + The remap_flags parameter accepts REMAP_FILE_* flags. If + REMAP_FILE_DEDUP is set then the implementation must only remap if the + requested file ranges have identical contents. If REMAP_CAN_SHORTEN is + set, the caller is ok with the implementation shortening the request + length to satisfy alignment or EOF requirements (or any other reason). fadvise: possibly called by the fadvise64() system call. diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt index 7b6a2b2bdc98db..8da26c6dd886a9 100644 --- a/Documentation/kbuild/makefiles.txt +++ b/Documentation/kbuild/makefiles.txt @@ -537,21 +537,6 @@ more details, with real examples. The third parameter may be a text as in this example, but it may also be an expanded variable or a macro. - cc-fullversion - cc-fullversion is useful when the exact version of gcc is needed. - One typical use-case is when a specific GCC version is broken. - cc-fullversion points out a more specific version than cc-version does. - - Example: - #arch/powerpc/Makefile - $(Q)if test "$(cc-fullversion)" = "040200" ; then \ - echo -n '*** GCC-4.2.0 cannot compile the 64-bit powerpc ' ; \ - false ; \ - fi - - In this example for a specific GCC version the build will error out - explaining to the user why it stops. - cc-cross-prefix cc-cross-prefix is used to check if there exists a $(CC) in path with one of the listed prefixes. The first prefix where there exist a diff --git a/Documentation/laptops/lg-laptop.rst b/Documentation/laptops/lg-laptop.rst new file mode 100644 index 00000000000000..e486fe7ddc35e1 --- /dev/null +++ b/Documentation/laptops/lg-laptop.rst @@ -0,0 +1,81 @@ +.. SPDX-License-Identifier: GPL-2.0+ +LG Gram laptop extra features +============================= + +By Matan Ziv-Av <matan@svgalib.org> + + +Hotkeys +------- + +The following FN keys are ignored by the kernel without this driver: +- FN-F1 (LG control panel) - Generates F15 +- FN-F5 (Touchpad toggle) - Generates F13 +- FN-F6 (Airplane mode) - Generates RFKILL +- FN-F8 (Keyboard backlight) - Generates F16. + This key also changes keyboard backlight mode. +- FN-F9 (Reader mode) - Generates F14 + +The rest of the FN key work without a need for a special driver. + + +Reader mode +----------- + +Writing 0/1 to /sys/devices/platform/lg-laptop/reader_mode disables/enables +reader mode. In this mode the screen colors change (blue color reduced), +and the reader mode indicator LED (on F9 key) turns on. + + +FN Lock +------- + +Writing 0/1 to /sys/devices/platform/lg-laptop/fn_lock disables/enables +FN lock. + + +Battery care limit +------------------ + +Writing 80/100 to /sys/devices/platform/lg-laptop/battery_care_limit +sets the maximum capacity to charge the battery. Limiting the charge +reduces battery capacity loss over time. + +This value is reset to 100 when the kernel boots. + + +Fan mode +-------- + +Writing 1/0 to /sys/devices/platform/lg-laptop/fan_mode disables/enables +the fan silent mode. + + +USB charge +---------- + +Writing 0/1 to /sys/devices/platform/lg-laptop/usb_charge disables/enables +charging another device from the USB port while the device is turned off. + +This value is reset to 0 when the kernel boots. + + +LEDs +~~~~ + +The are two LED devices supported by the driver: + +Keyboard backlight +------------------ + +A led device named kbd_led controls the keyboard backlight. There are three +lighting level: off (0), low (127) and high (255). + +The keyboard backlight is also controlled by the key combination FN-F8 +which cycles through those levels. + + +Touchpad indicator LED +---------------------- + +On the F5 key. Controlled by led device names tpad_led. diff --git a/Documentation/networking/ice.rst b/Documentation/networking/ice.rst index 1e4948c9e9897a..4d118b827bbb7e 100644 --- a/Documentation/networking/ice.rst +++ b/Documentation/networking/ice.rst @@ -20,7 +20,7 @@ Enabling the driver The driver is enabled via the standard kernel configuration system, using the make command:: - make oldconfig/silentoldconfig/menuconfig/etc. + make oldconfig/menuconfig/etc. The driver is located in the menu structure at: diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 163b5ff1073cd0..32b21571adfeb5 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -316,6 +316,17 @@ tcp_frto - INTEGER By default it's enabled with a non-zero value. 0 disables F-RTO. +tcp_fwmark_accept - BOOLEAN + If set, incoming connections to listening sockets that do not have a + socket mark will set the mark of the accepting socket to the fwmark of + the incoming SYN packet. This will cause all packets on that connection + (starting from the first SYNACK) to be sent with that fwmark. The + listening socket's mark is unchanged. Listening sockets that already + have a fwmark set via setsockopt(SOL_SOCKET, SO_MARK, ...) are + unaffected. + + Default: 0 + tcp_invalid_ratelimit - INTEGER Limit the maximal rate for sending duplicate acknowledgments in response to incoming TCP packets that are for an existing diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 757808526d9a8b..878ebfda7eeff3 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -25,6 +25,7 @@ Below are the essential guides that every developer should read. code-of-conduct-interpretation development-process submitting-patches + programming-language coding-style maintainer-pgp-guide email-clients diff --git a/Documentation/process/programming-language.rst b/Documentation/process/programming-language.rst new file mode 100644 index 00000000000000..e5f5f065dc24ec --- /dev/null +++ b/Documentation/process/programming-language.rst @@ -0,0 +1,45 @@ +.. _programming_language: + +Programming Language +==================== + +The kernel is written in the C programming language [c-language]_. +More precisely, the kernel is typically compiled with ``gcc`` [gcc]_ +under ``-std=gnu89`` [gcc-c-dialect-options]_: the GNU dialect of ISO C90 +(including some C99 features). + +This dialect contains many extensions to the language [gnu-extensions]_, +and many of them are used within the kernel as a matter of course. + +There is some support for compiling the kernel with ``clang`` [clang]_ +and ``icc`` [icc]_ for several of the architectures, although at the time +of writing it is not completed, requiring third-party patches. + +Attributes +---------- + +One of the common extensions used throughout the kernel are attributes +[gcc-attribute-syntax]_. Attributes allow to introduce +implementation-defined semantics to language entities (like variables, +functions or types) without having to make significant syntactic changes +to the language (e.g. adding a new keyword) [n2049]_. + +In some cases, attributes are optional (i.e. a compiler not supporting them +should still produce proper code, even if it is slower or does not perform +as many compile-time checks/diagnostics). + +The kernel defines pseudo-keywords (e.g. ``__pure``) instead of using +directly the GNU attribute syntax (e.g. ``__attribute__((__pure__))``) +in order to feature detect which ones can be used and/or to shorten the code. + +Please refer to ``include/linux/compiler_attributes.h`` for more information. + +.. [c-language] http://www.open-std.org/jtc1/sc22/wg14/www/standards +.. [gcc] https://gcc.gnu.org +.. [clang] https://clang.llvm.org +.. [icc] https://software.intel.com/en-us/c-compilers +.. [gcc-c-dialect-options] https://gcc.gnu.org/onlinedocs/gcc/C-Dialect-Options.html +.. [gnu-extensions] https://gcc.gnu.org/onlinedocs/gcc/C-Extensions.html +.. [gcc-attribute-syntax] https://gcc.gnu.org/onlinedocs/gcc/Attribute-Syntax.html +.. [n2049] http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2049.pdf + diff --git a/Documentation/security/keys/core.rst b/Documentation/security/keys/core.rst index 9ce7256c6edba8..9521c4207f014d 100644 --- a/Documentation/security/keys/core.rst +++ b/Documentation/security/keys/core.rst @@ -859,6 +859,7 @@ The keyctl syscall functions are: and either the buffer length or the OtherInfo length exceeds the allowed length. + * Restrict keyring linkage:: long keyctl(KEYCTL_RESTRICT_KEYRING, key_serial_t keyring, @@ -890,6 +891,116 @@ The keyctl syscall functions are: applicable to the asymmetric key type. + * Query an asymmetric key:: + + long keyctl(KEYCTL_PKEY_QUERY, + key_serial_t key_id, unsigned long reserved, + struct keyctl_pkey_query *info); + + Get information about an asymmetric key. The information is returned in + the keyctl_pkey_query struct:: + + __u32 supported_ops; + __u32 key_size; + __u16 max_data_size; + __u16 max_sig_size; + __u16 max_enc_size; + __u16 max_dec_size; + __u32 __spare[10]; + + ``supported_ops`` contains a bit mask of flags indicating which ops are + supported. This is constructed from a bitwise-OR of:: + + KEYCTL_SUPPORTS_{ENCRYPT,DECRYPT,SIGN,VERIFY} + + ``key_size`` indicated the size of the key in bits. + + ``max_*_size`` indicate the maximum sizes in bytes of a blob of data to be + signed, a signature blob, a blob to be encrypted and a blob to be + decrypted. + + ``__spare[]`` must be set to 0. This is intended for future use to hand + over one or more passphrases needed unlock a key. + + If successful, 0 is returned. If the key is not an asymmetric key, + EOPNOTSUPP is returned. + + + * Encrypt, decrypt, sign or verify a blob using an asymmetric key:: + + long keyctl(KEYCTL_PKEY_ENCRYPT, + const struct keyctl_pkey_params *params, + const char *info, + const void *in, + void *out); + + long keyctl(KEYCTL_PKEY_DECRYPT, + const struct keyctl_pkey_params *params, + const char *info, + const void *in, + void *out); + + long keyctl(KEYCTL_PKEY_SIGN, + const struct keyctl_pkey_params *params, + const char *info, + const void *in, + void *out); + + long keyctl(KEYCTL_PKEY_VERIFY, + const struct keyctl_pkey_params *params, + const char *info, + const void *in, + const void *in2); + + Use an asymmetric key to perform a public-key cryptographic operation a + blob of data. For encryption and verification, the asymmetric key may + only need the public parts to be available, but for decryption and signing + the private parts are required also. + + The parameter block pointed to by params contains a number of integer + values:: + + __s32 key_id; + __u32 in_len; + __u32 out_len; + __u32 in2_len; + + ``key_id`` is the ID of the asymmetric key to be used. ``in_len`` and + ``in2_len`` indicate the amount of data in the in and in2 buffers and + ``out_len`` indicates the size of the out buffer as appropriate for the + above operations. + + For a given operation, the in and out buffers are used as follows:: + + Operation ID in,in_len out,out_len in2,in2_len + ======================= =============== =============== =============== + KEYCTL_PKEY_ENCRYPT Raw data Encrypted data - + KEYCTL_PKEY_DECRYPT Encrypted data Raw data - + KEYCTL_PKEY_SIGN Raw data Signature - + KEYCTL_PKEY_VERIFY Raw data - Signature + + ``info`` is a string of key=value pairs that supply supplementary + information. These include: + + ``enc=<encoding>`` The encoding of the encrypted/signature blob. This + can be "pkcs1" for RSASSA-PKCS1-v1.5 or + RSAES-PKCS1-v1.5; "pss" for "RSASSA-PSS"; "oaep" for + "RSAES-OAEP". If omitted or is "raw", the raw output + of the encryption function is specified. + + ``hash=<algo>`` If the data buffer contains the output of a hash + function and the encoding includes some indication of + which hash function was used, the hash function can be + specified with this, eg. "hash=sha256". + + The ``__spare[]`` space in the parameter block must be set to 0. This is + intended, amongst other things, to allow the passing of passphrases + required to unlock a key. + + If successful, encrypt, decrypt and sign all return the amount of data + written into the output buffer. Verification returns 0 on success. + + Kernel Services =============== @@ -1483,6 +1594,112 @@ The structure has a number of fields, some of which are mandatory: attempted key link operation. If there is no match, -EINVAL is returned. + * ``int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out);`` + ``int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2);`` + + These methods are optional. If provided the first allows a key to be + used to encrypt, decrypt or sign a blob of data, and the second allows a + key to verify a signature. + + In all cases, the following information is provided in the params block:: + + struct kernel_pkey_params { + struct key *key; + const char *encoding; + const char *hash_algo; + char *info; + __u32 in_len; + union { + __u32 out_len; + __u32 in2_len; + }; + enum kernel_pkey_operation op : 8; + }; + + This includes the key to be used; a string indicating the encoding to use + (for instance, "pkcs1" may be used with an RSA key to indicate + RSASSA-PKCS1-v1.5 or RSAES-PKCS1-v1.5 encoding or "raw" if no encoding); + the name of the hash algorithm used to generate the data for a signature + (if appropriate); the sizes of the input and output (or second input) + buffers; and the ID of the operation to be performed. + + For a given operation ID, the input and output buffers are used as + follows:: + + Operation ID in,in_len out,out_len in2,in2_len + ======================= =============== =============== =============== + kernel_pkey_encrypt Raw data Encrypted data - + kernel_pkey_decrypt Encrypted data Raw data - + kernel_pkey_sign Raw data Signature - + kernel_pkey_verify Raw data - Signature + + asym_eds_op() deals with encryption, decryption and signature creation as + specified by params->op. Note that params->op is also set for + asym_verify_signature(). + + Encrypting and signature creation both take raw data in the input buffer + and return the encrypted result in the output buffer. Padding may have + been added if an encoding was set. In the case of signature creation, + depending on the encoding, the padding created may need to indicate the + digest algorithm - the name of which should be supplied in hash_algo. + + Decryption takes encrypted data in the input buffer and returns the raw + data in the output buffer. Padding will get checked and stripped off if + an encoding was set. + + Verification takes raw data in the input buffer and the signature in the + second input buffer and checks that the one matches the other. Padding + will be validated. Depending on the encoding, the digest algorithm used + to generate the raw data may need to be indicated in hash_algo. + + If successful, asym_eds_op() should return the number of bytes written + into the output buffer. asym_verify_signature() should return 0. + + A variety of errors may be returned, including EOPNOTSUPP if the operation + is not supported; EKEYREJECTED if verification fails; ENOPKG if the + required crypto isn't available. + + + * ``int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info);`` + + This method is optional. If provided it allows information about the + public or asymmetric key held in the key to be determined. + + The parameter block is as for asym_eds_op() and co. but in_len and out_len + are unused. The encoding and hash_algo fields should be used to reduce + the returned buffer/data sizes as appropriate. + + If successful, the following information is filled in:: + + struct kernel_pkey_query { + __u32 supported_ops; + __u32 key_size; + __u16 max_data_size; + __u16 max_sig_size; + __u16 max_enc_size; + __u16 max_dec_size; + }; + + The supported_ops field will contain a bitmask indicating what operations + are supported by the key, including encryption of a blob, decryption of a + blob, signing a blob and verifying the signature on a blob. The following + constants are defined for this:: + + KEYCTL_SUPPORTS_{ENCRYPT,DECRYPT,SIGN,VERIFY} + + The key_size field is the size of the key in bits. max_data_size and + max_sig_size are the maximum raw data and signature sizes for creation and + verification of a signature; max_enc_size and max_dec_size are the maximum + raw data and signature sizes for encryption and decryption. The + max_*_size fields are measured in bytes. + + If successful, 0 will be returned. If the key doesn't support this, + EOPNOTSUPP will be returned. + + Request-Key Callback Service ============================ diff --git a/Documentation/security/self-protection.rst b/Documentation/security/self-protection.rst index e1ca698e000639..f584fb74b4ff28 100644 --- a/Documentation/security/self-protection.rst +++ b/Documentation/security/self-protection.rst @@ -302,11 +302,11 @@ sure structure holes are cleared. Memory poisoning ---------------- -When releasing memory, it is best to poison the contents (clear stack on -syscall return, wipe heap memory on a free), to avoid reuse attacks that -rely on the old contents of memory. This frustrates many uninitialized -variable attacks, stack content exposures, heap content exposures, and -use-after-free attacks. +When releasing memory, it is best to poison the contents, to avoid reuse +attacks that rely on the old contents of memory. E.g., clear stack on a +syscall return (``CONFIG_GCC_PLUGIN_STACKLEAK``), wipe heap memory on a +free. This frustrates many uninitialized variable attacks, stack content +exposures, heap content exposures, and use-after-free attacks. Destination tracking -------------------- diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 37a679501ddc68..1b8775298cf7a0 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -89,6 +89,7 @@ show up in /proc/sys/kernel: - shmmni - softlockup_all_cpu_backtrace - soft_watchdog +- stack_erasing - stop-a [ SPARC only ] - sysrq ==> Documentation/admin-guide/sysrq.rst - sysctl_writes_strict @@ -987,6 +988,23 @@ detect a hard lockup condition. ============================================================== +stack_erasing + +This parameter can be used to control kernel stack erasing at the end +of syscalls for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. + +That erasing reduces the information which kernel stack leak bugs +can reveal and blocks some uninitialized stack variable attacks. +The tradeoff is the performance impact: on a single CPU system kernel +compilation sees a 1% slowdown, other systems and workloads may vary. + + 0: kernel stack erasing is disabled, STACKLEAK_METRICS are not updated. + + 1: kernel stack erasing is enabled (default), it is performed before + returning to the userspace at the end of syscalls. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which can be diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 702898633b0007..73aaaa3da4369e 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -146,3 +146,6 @@ Their order is preserved but their base will be offset early at boot time. Be very careful vs. KASLR when changing anything here. The KASLR address range must not overlap with anything except the KASAN shadow area, which is correct as KASAN disables KASLR. + +For both 4- and 5-level layouts, the STACKLEAK_POISON value in the last 2MB +hole: ffffffffffff4111 diff --git a/MAINTAINERS b/MAINTAINERS index 1c0f771b859ec2..f4855974f32506 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -376,7 +376,7 @@ F: drivers/platform/x86/i2c-multi-instantiate.c ACPI PMIC DRIVERS M: "Rafael J. Wysocki" <rjw@rjwysocki.net> M: Len Brown <lenb@kernel.org> -R: Andy Shevchenko <andy@infradead.org> +R: Andy Shevchenko <andriy.shevchenko@linux.intel.com> R: Mika Westerberg <mika.westerberg@linux.intel.com> L: linux-acpi@vger.kernel.org Q: https://patchwork.kernel.org/project/linux-acpi/list/ @@ -3737,6 +3737,11 @@ L: platform-driver-x86@vger.kernel.org S: Maintained F: drivers/platform/x86/compal-laptop.c +COMPILER ATTRIBUTES +M: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com> +S: Maintained +F: include/linux/compiler_attributes.h + CONEXANT ACCESSRUNNER USB DRIVER L: accessrunner-general@lists.sourceforge.net W: http://accessrunner.sourceforge.net/ @@ -4207,6 +4212,12 @@ M: Pali Rohár <pali.rohar@gmail.com> S: Maintained F: drivers/platform/x86/dell-rbtn.* +DELL REMOTE BIOS UPDATE DRIVER +M: Stuart Hayes <stuart.w.hayes@gmail.com> +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/dell_rbu.c + DELL LAPTOP SMM DRIVER M: Pali Rohár <pali.rohar@gmail.com> S: Maintained @@ -4214,10 +4225,11 @@ F: drivers/hwmon/dell-smm-hwmon.c F: include/uapi/linux/i8k.h DELL SYSTEMS MANAGEMENT BASE DRIVER (dcdbas) -M: Doug Warzecha <Douglas_Warzecha@dell.com> +M: Stuart Hayes <stuart.w.hayes@gmail.com> +L: platform-driver-x86@vger.kernel.org S: Maintained F: Documentation/dcdbas.txt -F: drivers/firmware/dcdbas.* +F: drivers/platform/x86/dcdbas.* DELL WMI NOTIFICATIONS DRIVER M: Matthew Garrett <mjg59@srcf.ucam.org> @@ -5871,6 +5883,14 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-cpm.c +FREESCALE IMX LPI2C DRIVER +M: Dong Aisheng <aisheng.dong@nxp.com> +L: linux-i2c@vger.kernel.org +L: linux-imx@nxp.com +S: Maintained +F: drivers/i2c/busses/i2c-imx-lpi2c.c +F: Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt + FREESCALE IMX / MXC FEC DRIVER M: Fugang Duan <fugang.duan@nxp.com> L: netdev@vger.kernel.org @@ -7347,6 +7367,12 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported F: sound/soc/intel/ +INTEL ATOMISP2 DUMMY / POWER-MANAGEMENT DRIVER +M: Hans de Goede <hdegoede@redhat.com> +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: drivers/platform/x86/intel_atomisp2_pm.c + INTEL C600 SERIES SAS CONTROLLER DRIVER M: Intel SCU Linux support <intel-linux-scu@intel.com> M: Artur Paszkiewicz <artur.paszkiewicz@intel.com> @@ -7533,7 +7559,6 @@ M: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com> M: Vishwanath Somayaji <vishwanath.somayaji@intel.com> L: platform-driver-x86@vger.kernel.org S: Maintained -F: arch/x86/include/asm/pmc_core.h F: drivers/platform/x86/intel_pmc_core* INTEL PMC/P-Unit IPC DRIVER @@ -7577,7 +7602,8 @@ F: drivers/infiniband/hw/i40iw/ F: include/uapi/rdma/i40iw-abi.h INTEL TELEMETRY DRIVER -M: Souvik Kumar Chakravarty <souvik.k.chakravarty@intel.com> +M: Rajneesh Bhardwaj <rajneesh.bhardwaj@linux.intel.com> +M: "David E. Box" <david.e.box@linux.intel.com> L: platform-driver-x86@vger.kernel.org S: Maintained F: arch/x86/include/asm/intel_telemetry.h @@ -8310,6 +8336,14 @@ W: http://legousb.sourceforge.net/ S: Maintained F: drivers/usb/misc/legousbtower.c +LG LAPTOP EXTRAS +M: Matan Ziv-Av <matan@svgalib.org> +L: platform-driver-x86@vger.kernel.org +S: Maintained +F: Documentation/ABI/testing/sysfs-platform-lg-laptop +F: Documentation/laptops/lg-laptop.rst +F: drivers/platform/x86/lg-laptop.c + LG2160 MEDIA DRIVER M: Michael Krufky <mkrufky@linuxtv.org> L: linux-media@vger.kernel.org @@ -15829,7 +15863,6 @@ F: net/vmw_vsock/virtio_transport_common.c F: net/vmw_vsock/virtio_transport.c F: drivers/net/vsockmon.c F: drivers/vhost/vsock.c -F: drivers/vhost/vsock.h F: tools/testing/vsock/ VIRTIO CONSOLE DRIVER diff --git a/Makefile b/Makefile index 9aa352b3881580..bce41f4180fcba 100644 --- a/Makefile +++ b/Makefile @@ -485,7 +485,7 @@ ifneq ($(KBUILD_SRC),) $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkmakefile $(srctree) endif -ifeq ($(cc-name),clang) +ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),) ifneq ($(CROSS_COMPILE),) CLANG_TARGET := --target=$(notdir $(CROSS_COMPILE:%-=%)) GCC_TOOLCHAIN_DIR := $(dir $(shell which $(LD))) @@ -702,7 +702,7 @@ stackp-flags-$(CONFIG_STACKPROTECTOR_STRONG) := -fstack-protector-strong KBUILD_CFLAGS += $(stackp-flags-y) -ifeq ($(cc-name),clang) +ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) diff --git a/arch/Kconfig b/arch/Kconfig index ed27fd26262764..e1e540ffa9793d 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -429,6 +429,13 @@ config SECCOMP_FILTER See Documentation/userspace-api/seccomp_filter.rst for details. +config HAVE_ARCH_STACKLEAK + bool + help + An architecture should select this if it has the code which + fills the used part of the kernel stack with the STACKLEAK_POISON + value before returning from system calls. + config HAVE_STACKPROTECTOR bool help diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi index c50c36baba758f..8bf1c17f8cefb6 100644 --- a/arch/arm/boot/dts/stm32mp157c.dtsi +++ b/arch/arm/boot/dts/stm32mp157c.dtsi @@ -923,7 +923,7 @@ interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; clocks = <&rcc HASH1>; resets = <&rcc HASH1_R>; - dmas = <&mdma1 31 0x10 0x1000A02 0x0 0x0 0x0>; + dmas = <&mdma1 31 0x10 0x1000A02 0x0 0x0>; dma-names = "in"; dma-maxburst = <2>; status = "disabled"; diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 63af6234c1b69a..1c7616815a86ab 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1,6 +1,7 @@ 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/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index af318d958fd2a7..3d191fd52910f1 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -773,7 +773,7 @@ static struct plat_serial8250_port ams_delta_modem_ports[] = { { .membase = IOMEM(MODEM_VIRT), .mapbase = MODEM_PHYS, - .irq = -EINVAL, /* changed later */ + .irq = IRQ_NOTCONNECTED, /* changed later */ .flags = UPF_BOOT_AUTOCONF, .irqflags = IRQF_TRIGGER_RISING, .iotype = UPIO_MEM, @@ -864,8 +864,7 @@ static int __init modem_nreset_init(void) /* - * This function expects MODEM IRQ number already assigned to the port - * and fails if it's not. + * This function expects MODEM IRQ number already assigned to the port. * The MODEM device requires its RESET# pin kept high during probe. * That requirement can be fulfilled in several ways: * - with a descriptor of already functional modem_nreset regulator @@ -888,9 +887,6 @@ static int __init ams_delta_modem_init(void) if (!machine_is_ams_delta()) return -ENODEV; - if (ams_delta_modem_ports[0].irq < 0) - return ams_delta_modem_ports[0].irq; - omap_cfg_reg(M14_1510_GPIO2); /* Initialize the modem_nreset regulator consumer before use */ diff --git a/arch/arm/plat-orion/mpp.c b/arch/arm/plat-orion/mpp.c index 5b4ff9373c8945..8a6880d528b6f1 100644 --- a/arch/arm/plat-orion/mpp.c +++ b/arch/arm/plat-orion/mpp.c @@ -28,10 +28,15 @@ void __init orion_mpp_conf(unsigned int *mpp_list, unsigned int variant_mask, unsigned int mpp_max, void __iomem *dev_bus) { unsigned int mpp_nr_regs = (1 + mpp_max/8); - u32 mpp_ctrl[mpp_nr_regs]; + u32 mpp_ctrl[8]; int i; printk(KERN_DEBUG "initial MPP regs:"); + if (mpp_nr_regs > ARRAY_SIZE(mpp_ctrl)) { + printk(KERN_ERR "orion_mpp_conf: invalid mpp_max\n"); + return; + } + for (i = 0; i < mpp_nr_regs; i++) { mpp_ctrl[i] = readl(mpp_ctrl_addr(i, dev_bus)); printk(" %08x", mpp_ctrl[i]); diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index b4e994cd3a421d..6cb9fc7e9382d7 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -134,6 +134,7 @@ vdso_install: archclean: $(Q)$(MAKE) $(clean)=$(boot) +ifeq ($(KBUILD_EXTMOD),) # We need to generate vdso-offsets.h before compiling certain files in kernel/. # In order to do that, we should use the archprepare target, but we can't since # asm-offsets.h is included in some files used to generate vdso-offsets.h, and @@ -143,6 +144,7 @@ archclean: prepare: vdso_prepare vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h +endif define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 3cb995606e605b..c9a57d11330b85 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -308,6 +308,9 @@ CONFIG_SERIAL_XILINX_PS_UART_CONSOLE=y CONFIG_SERIAL_MVEBU_UART=y CONFIG_SERIAL_DEV_BUS=y CONFIG_VIRTIO_CONSOLE=y +CONFIG_IPMI_HANDLER=m +CONFIG_IPMI_DEVICE_INTERFACE=m +CONFIG_IPMI_SI=m CONFIG_TCG_TPM=y CONFIG_TCG_TIS_I2C_INFINEON=y CONFIG_I2C_CHARDEV=y diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 9234013e759e56..21a81b59a0ccd5 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -96,6 +96,7 @@ static inline unsigned long __percpu_##op(void *ptr, \ : [val] "Ir" (val)); \ break; \ default: \ + ret = 0; \ BUILD_BUG(); \ } \ \ @@ -125,6 +126,7 @@ static inline unsigned long __percpu_read(void *ptr, int size) ret = READ_ONCE(*(u64 *)ptr); break; default: + ret = 0; BUILD_BUG(); } @@ -194,6 +196,7 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, : [val] "r" (val)); break; default: + ret = 0; BUILD_BUG(); } diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index f46d57c3144306..6b5037ed15b288 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -58,7 +58,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, /** * elfcorehdr_read - read from ELF core header * @buf: buffer where the data is placed - * @csize: number of bytes to read + * @count: number of bytes to read * @ppos: address in the memory * * This function reads @count bytes from elf core header which exists diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 9b65132e789a55..2a5b338b254240 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -23,7 +23,9 @@ #include <linux/slab.h> #include <linux/stop_machine.h> #include <linux/sched/debug.h> +#include <linux/set_memory.h> #include <linux/stringify.h> +#include <linux/vmalloc.h> #include <asm/traps.h> #include <asm/ptrace.h> #include <asm/cacheflush.h> @@ -42,10 +44,21 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); +static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) +{ + void *addrs[1]; + u32 insns[1]; + + addrs[0] = addr; + insns[0] = opcode; + + return aarch64_insn_patch_text(addrs, insns, 1); +} + static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { /* prepare insn slot */ - p->ainsn.api.insn[0] = cpu_to_le32(p->opcode); + patch_text(p->ainsn.api.insn, p->opcode); flush_icache_range((uintptr_t) (p->ainsn.api.insn), (uintptr_t) (p->ainsn.api.insn) + @@ -118,15 +131,15 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return 0; } -static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) +void *alloc_insn_page(void) { - void *addrs[1]; - u32 insns[1]; + void *page; - addrs[0] = (void *)addr; - insns[0] = (u32)opcode; + page = vmalloc_exec(PAGE_SIZE); + if (page) + set_memory_ro((unsigned long)page, 1); - return aarch64_insn_patch_text(addrs, insns, 1); + return page; } /* arm kprobe: install breakpoint in text */ diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index ce99c58cd1f1d2..d9a4c2d6dd8b8b 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -497,25 +497,3 @@ void arch_setup_new_exec(void) { current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0; } - -#ifdef CONFIG_GCC_PLUGIN_STACKLEAK -void __used stackleak_check_alloca(unsigned long size) -{ - unsigned long stack_left; - unsigned long current_sp = current_stack_pointer; - struct stack_info info; - - BUG_ON(!on_accessible_stack(current, current_sp, &info)); - - stack_left = current_sp - info.low; - - /* - * There's a good chance we're almost out of stack space if this - * is true. Using panic() over BUG() is more likely to give - * reliable debugging output. - */ - if (size >= stack_left) - panic("alloca() over the kernel stack boundary\n"); -} -EXPORT_SYMBOL(stackleak_check_alloca); -#endif diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3a703e5d4e3237..a3ac262848451a 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -160,6 +160,7 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_unmap_area(phys_to_virt(paddr), size, dir); } +#ifdef CONFIG_IOMMU_DMA static int __swiotlb_get_sgtable_page(struct sg_table *sgt, struct page *page, size_t size) { @@ -188,6 +189,7 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, return ret; } +#endif /* CONFIG_IOMMU_DMA */ static int __init atomic_pool_init(void) { diff --git a/arch/csky/Kconfig.debug b/arch/csky/Kconfig.debug index 48cf6ff9df4a36..22a162cd99e811 100644 --- a/arch/csky/Kconfig.debug +++ b/arch/csky/Kconfig.debug @@ -1,9 +1 @@ -menu "C-SKY Debug Options" -config CSKY_BUILTIN_DTB - string "Use kernel builtin dtb" - help - User could define the dtb instead of the one which is passed from - bootloader. - Sometimes for debug, we want to use a built-in dtb and then we needn't - modify bootloader at all. -endmenu +# dummy file, do not delete diff --git a/arch/csky/Makefile b/arch/csky/Makefile index 67a4ae1fba2ba4..c639fc167895d7 100644 --- a/arch/csky/Makefile +++ b/arch/csky/Makefile @@ -65,26 +65,15 @@ libs-y += arch/csky/lib/ \ $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name) boot := arch/csky/boot -ifneq '$(CONFIG_CSKY_BUILTIN_DTB)' '""' core-y += $(boot)/dts/ -endif all: zImage - -dtbs: scripts - $(Q)$(MAKE) $(build)=$(boot)/dts - -%.dtb %.dtb.S %.dtb.o: scripts - $(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@ - -zImage Image uImage: vmlinux dtbs +zImage Image uImage: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ archclean: $(Q)$(MAKE) $(clean)=$(boot) - $(Q)$(MAKE) $(clean)=$(boot)/dts - rm -rf arch/csky/include/generated define archhelp echo '* zImage - Compressed kernel image (arch/$(ARCH)/boot/zImage)' diff --git a/arch/csky/boot/dts/Makefile b/arch/csky/boot/dts/Makefile index 305e81a5e91e1e..c57ad3c880bfb9 100644 --- a/arch/csky/boot/dts/Makefile +++ b/arch/csky/boot/dts/Makefile @@ -1,13 +1,3 @@ dtstree := $(srctree)/$(src) -ifneq '$(CONFIG_CSKY_BUILTIN_DTB)' '""' -builtindtb-y := $(patsubst "%",%,$(CONFIG_CSKY_BUILTIN_DTB)) -dtb-y += $(builtindtb-y).dtb -obj-y += $(builtindtb-y).dtb.o -.SECONDARY: $(obj)/$(builtindtb-y).dtb.S -else dtb-y := $(patsubst $(dtstree)/%.dts,%.dtb, $(wildcard $(dtstree)/*.dts)) -endif - -always += $(dtb-y) -clean-files += *.dtb *.dtb.S diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 15a84cfd07191f..68410490e12fdc 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -128,7 +128,7 @@ cflags-y += -ffreestanding # clang's output will be based upon the build machine. So for clang we simply # unconditionally specify -EB or -EL as appropriate. # -ifeq ($(cc-name),clang) +ifdef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -EL else diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 34605ca214984c..58a0315ad743d5 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -10,7 +10,7 @@ ccflags-vdso := \ $(filter -march=%,$(KBUILD_CFLAGS)) \ -D__VDSO__ -ifeq ($(cc-name),clang) +ifdef CONFIG_CC_IS_CLANG ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS)) endif diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2d51b2bd4aa132..8be31261aec831 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -930,10 +930,6 @@ config FSL_GTM help Freescale General-purpose Timers support -# Yes MCA RS/6000s exist but Linux-PPC does not currently support any -config MCA - bool - # Platforms that what PCI turned unconditionally just do select PCI # in their config node. Platforms that want to choose at config # time should select PPC_PCI_CHOICE @@ -944,7 +940,6 @@ config PCI bool "PCI support" if PPC_PCI_CHOICE default y if !40x && !CPM2 && !PPC_8xx && !PPC_83xx \ && !PPC_85xx && !PPC_86xx && !GAMECUBE_COMMON - default PCI_QSPAN if PPC_8xx select GENERIC_PCI_IOMAP help Find out whether your system includes a PCI bus. PCI is the name of @@ -958,14 +953,6 @@ config PCI_DOMAINS config PCI_SYSCALL def_bool PCI -config PCI_QSPAN - bool "QSpan PCI" - depends on PPC_8xx - select PPC_I8259 - help - Say Y here if you have a system based on a Motorola 8xx-series - embedded processor with a QSPAN PCI interface, otherwise say N. - config PCI_8260 bool depends on PCI && 8260 diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 17be664dafa2f2..8a2ce14d68d077 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -96,7 +96,7 @@ aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mabi=elfv1) aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mabi=elfv2 endif -ifneq ($(cc-name),clang) +ifndef CONFIG_CC_IS_CLANG cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align endif @@ -175,7 +175,7 @@ endif # Work around gcc code-gen bugs with -pg / -fno-omit-frame-pointer in gcc <= 4.8 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=44199 # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=52828 -ifneq ($(cc-name),clang) +ifndef CONFIG_CC_IS_CLANG CC_FLAGS_FTRACE += $(call cc-ifversion, -lt, 0409, -mno-sched-epilog) endif endif diff --git a/arch/powerpc/boot/dts/fsl/t2080rdb.dts b/arch/powerpc/boot/dts/fsl/t2080rdb.dts index 55c0210a771d1f..092a400740f84e 100644 --- a/arch/powerpc/boot/dts/fsl/t2080rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t2080rdb.dts @@ -77,12 +77,12 @@ }; ethernet@f0000 { - phy-handle = <&xg_cs4315_phy1>; + phy-handle = <&xg_cs4315_phy2>; phy-connection-type = "xgmii"; }; ethernet@f2000 { - phy-handle = <&xg_cs4315_phy2>; + phy-handle = <&xg_cs4315_phy1>; phy-connection-type = "xgmii"; }; diff --git a/arch/powerpc/boot/dts/mpc885ads.dts b/arch/powerpc/boot/dts/mpc885ads.dts index 5b037f51741df1..3aa300afbbca4a 100644 --- a/arch/powerpc/boot/dts/mpc885ads.dts +++ b/arch/powerpc/boot/dts/mpc885ads.dts @@ -72,7 +72,7 @@ #address-cells = <1>; #size-cells = <1>; device_type = "soc"; - ranges = <0x0 0xff000000 0x4000>; + ranges = <0x0 0xff000000 0x28000>; bus-frequency = <0>; // Temporary -- will go away once kernel uses ranges for get_immrbase(). @@ -224,6 +224,17 @@ #size-cells = <0>; }; }; + + crypto@20000 { + compatible = "fsl,sec1.2", "fsl,sec1.0"; + reg = <0x20000 0x8000>; + interrupts = <1 1>; + interrupt-parent = <&PIC>; + fsl,num-channels = <1>; + fsl,channel-fifo-len = <24>; + fsl,exec-units-mask = <0x4c>; + fsl,descriptor-types-mask = <0x05000154>; + }; }; chosen { diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index 31733a95bbd052..3d5acd2b113a2d 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -36,6 +36,11 @@ int raw_patch_instruction(unsigned int *addr, unsigned int instr); int patch_instruction_site(s32 *addr, unsigned int instr); int patch_branch_site(s32 *site, unsigned long target, int flags); +static inline unsigned long patch_site_addr(s32 *site) +{ + return (unsigned long)site + *site; +} + int instr_is_relative_branch(unsigned int instr); int instr_is_relative_link_branch(unsigned int instr); int instr_is_branch_to_addr(const unsigned int *instr, unsigned long addr); diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/mmu-8xx.h index 4f547752ae7959..fa05aa566ece42 100644 --- a/arch/powerpc/include/asm/mmu-8xx.h +++ b/arch/powerpc/include/asm/mmu-8xx.h @@ -34,20 +34,12 @@ * respectively NA for All or X for Supervisor and no access for User. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP: - * When that bit is not set access is done iaw "all user" - * which means no access iaw page rules. - * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED - * 0x => No access => 11 (all accesses performed as user iaw page definition) - * 10 => No user => 01 (all accesses performed according to page definition) - * 11 => User => 00 (all accesses performed as supervisor iaw page definition) + * Therefore, we define 2 APG groups. lsb is _PMD_USER + * 0 => No user => 01 (all accesses performed according to page definition) + * 1 => User => 00 (all accesses performed as supervisor iaw page definition) * We define all 16 groups so that all other bits of APG can take any value */ -#ifdef CONFIG_SWAP -#define MI_APG_INIT 0xf4f4f4f4 -#else #define MI_APG_INIT 0x44444444 -#endif /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -115,20 +107,12 @@ * Supervisor and no access for user and NA for ALL. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * We also use the 2nd APG bit for _PAGE_ACCESSED when having SWAP: - * When that bit is not set access is done iaw "all user" - * which means no access iaw page rules. - * Therefore, we define 4 APG groups. lsb is _PMD_USER, 2nd is _PAGE_ACCESSED - * 0x => No access => 11 (all accesses performed as user iaw page definition) - * 10 => No user => 01 (all accesses performed according to page definition) - * 11 => User => 00 (all accesses performed as supervisor iaw page definition) + * Therefore, we define 2 APG groups. lsb is _PMD_USER + * 0 => No user => 01 (all accesses performed according to page definition) + * 1 => User => 00 (all accesses performed as supervisor iaw page definition) * We define all 16 groups so that all other bits of APG can take any value */ -#ifdef CONFIG_SWAP -#define MD_APG_INIT 0xf4f4f4f4 -#else #define MD_APG_INIT 0x44444444 -#endif /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in @@ -180,12 +164,6 @@ */ #define SPRN_M_TW 799 -/* APGs */ -#define M_APG0 0x00000000 -#define M_APG1 0x00000020 -#define M_APG2 0x00000040 -#define M_APG3 0x00000060 - #ifdef CONFIG_PPC_MM_SLICES #include <asm/nohash/32/slice.h> #define SLICE_ARRAY_SIZE (1 << (32 - SLICE_LOW_SHIFT - 1)) @@ -251,6 +229,15 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize) BUG(); } +/* patch sites */ +extern s32 patch__itlbmiss_linmem_top; +extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp; +extern s32 patch__fixupdar_linmem_top; + +extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2; +extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3; +extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; + #endif /* !__ASSEMBLY__ */ #if defined(CONFIG_PPC_4K_PAGES) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index bb38dd67d47ddb..1b06add4f092ad 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -5,6 +5,7 @@ #include <linux/spinlock.h> #include <asm/page.h> #include <linux/time.h> +#include <linux/cpumask.h> /* * Definitions for talking to the RTAS on CHRP machines. diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 134a573a9f2d0c..3b67b9533c82fe 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -31,6 +31,7 @@ #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/export.h> +#include <asm/code-patching-asm.h> #if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 /* By simply checking Address >= 0x80000000, we know if its a kernel address */ @@ -318,8 +319,8 @@ InstructionTLBMiss: cmpli cr0, r11, PAGE_OFFSET@h #ifndef CONFIG_PIN_TLB_TEXT /* It is assumed that kernel code fits into the first 8M page */ -_ENTRY(ITLBMiss_cmp) - cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h +0: cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h + patch_site 0b, patch__itlbmiss_linmem_top #endif #endif #endif @@ -353,13 +354,14 @@ _ENTRY(ITLBMiss_cmp) #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mtcr r12 #endif - -#ifdef CONFIG_SWAP - rlwinm r11, r10, 31, _PAGE_ACCESSED >> 1 -#endif /* Load the MI_TWC with the attributes for this "segment." */ mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ +#ifdef CONFIG_SWAP + rlwinm r11, r10, 32-5, _PAGE_PRESENT + and r11, r11, r10 + rlwimi r10, r11, 0, _PAGE_PRESENT +#endif li r11, RPN_PATTERN | 0x200 /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. @@ -372,16 +374,17 @@ _ENTRY(ITLBMiss_cmp) mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ /* Restore registers */ -_ENTRY(itlb_miss_exit_1) - mfspr r10, SPRN_SPRG_SCRATCH0 +0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 #if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) mfspr r12, SPRN_SPRG_SCRATCH2 #endif rfi + patch_site 0b, patch__itlbmiss_exit_1 + #ifdef CONFIG_PERF_EVENTS -_ENTRY(itlb_miss_perf) - lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha + patch_site 0f, patch__itlbmiss_perf +0: lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) addi r11, r11, 1 stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) @@ -435,11 +438,11 @@ DataStoreTLBMiss: #ifndef CONFIG_PIN_TLB_IMMR cmpli cr0, r11, VIRT_IMMR_BASE@h #endif -_ENTRY(DTLBMiss_cmp) - cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h +0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h + patch_site 0b, patch__dtlbmiss_linmem_top #ifndef CONFIG_PIN_TLB_IMMR -_ENTRY(DTLBMiss_jmp) - beq- DTLBMissIMMR +0: beq- DTLBMissIMMR + patch_site 0b, patch__dtlbmiss_immr_jmp #endif blt cr7, DTLBMissLinear lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha @@ -470,14 +473,22 @@ _ENTRY(DTLBMiss_jmp) * above. */ rlwimi r11, r10, 0, _PAGE_GUARDED -#ifdef CONFIG_SWAP - /* _PAGE_ACCESSED has to be set. We use second APG bit for that, 0 - * on that bit will represent a Non Access group - */ - rlwinm r11, r10, 31, _PAGE_ACCESSED >> 1 -#endif mtspr SPRN_MD_TWC, r11 + /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. + * We also need to know if the insn is a load/store, so: + * Clear _PAGE_PRESENT and load that which will + * trap into DTLB Error with store bit set accordinly. + */ + /* PRESENT=0x1, ACCESSED=0x20 + * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); + * r10 = (r10 & ~PRESENT) | r11; + */ +#ifdef CONFIG_SWAP + rlwinm r11, r10, 32-5, _PAGE_PRESENT + and r11, r11, r10 + rlwimi r10, r11, 0, _PAGE_PRESENT +#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior @@ -489,14 +500,16 @@ _ENTRY(DTLBMiss_jmp) /* Restore registers */ mtspr SPRN_DAR, r11 /* Tag DAR */ -_ENTRY(dtlb_miss_exit_1) - mfspr r10, SPRN_SPRG_SCRATCH0 + +0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r12, SPRN_SPRG_SCRATCH2 rfi + patch_site 0b, patch__dtlbmiss_exit_1 + #ifdef CONFIG_PERF_EVENTS -_ENTRY(dtlb_miss_perf) - lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha + patch_site 0f, patch__dtlbmiss_perf +0: lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) addi r11, r11, 1 stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) @@ -637,8 +650,8 @@ InstructionBreakpoint: */ DTLBMissIMMR: mtcr r12 - /* Set 512k byte guarded page and mark it valid and accessed */ - li r10, MD_PS512K | MD_GUARDED | MD_SVALID | M_APG2 + /* Set 512k byte guarded page and mark it valid */ + li r10, MD_PS512K | MD_GUARDED | MD_SVALID mtspr SPRN_MD_TWC, r10 mfspr r10, SPRN_IMMR /* Get current IMMR */ rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ @@ -648,16 +661,17 @@ DTLBMissIMMR: li r11, RPN_PATTERN mtspr SPRN_DAR, r11 /* Tag DAR */ -_ENTRY(dtlb_miss_exit_2) - mfspr r10, SPRN_SPRG_SCRATCH0 + +0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r12, SPRN_SPRG_SCRATCH2 rfi + patch_site 0b, patch__dtlbmiss_exit_2 DTLBMissLinear: mtcr r12 - /* Set 8M byte page and mark it valid and accessed */ - li r11, MD_PS8MEG | MD_SVALID | M_APG2 + /* Set 8M byte page and mark it valid */ + li r11, MD_PS8MEG | MD_SVALID mtspr SPRN_MD_TWC, r11 rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ @@ -666,28 +680,29 @@ DTLBMissLinear: li r11, RPN_PATTERN mtspr SPRN_DAR, r11 /* Tag DAR */ -_ENTRY(dtlb_miss_exit_3) - mfspr r10, SPRN_SPRG_SCRATCH0 + +0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r12, SPRN_SPRG_SCRATCH2 rfi + patch_site 0b, patch__dtlbmiss_exit_3 #ifndef CONFIG_PIN_TLB_TEXT ITLBMissLinear: mtcr r12 - /* Set 8M byte page and mark it valid,accessed */ - li r11, MI_PS8MEG | MI_SVALID | M_APG2 + /* Set 8M byte page and mark it valid */ + li r11, MI_PS8MEG | MI_SVALID mtspr SPRN_MI_TWC, r11 rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ _PAGE_PRESENT mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ -_ENTRY(itlb_miss_exit_2) - mfspr r10, SPRN_SPRG_SCRATCH0 +0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r12, SPRN_SPRG_SCRATCH2 rfi + patch_site 0b, patch__itlbmiss_exit_2 #endif /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions @@ -705,8 +720,10 @@ FixupDAR:/* Entry point for dcbx workaround. */ mfspr r11, SPRN_M_TW /* Get level 1 table */ blt+ 3f rlwinm r11, r10, 16, 0xfff8 -_ENTRY(FixupDAR_cmp) - cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h + +0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h + patch_site 0b, patch__fixupdar_linmem_top + /* create physical page address from effective address */ tophys(r11, r10) blt- cr7, 201f @@ -960,7 +977,7 @@ initial_mmu: ori r8, r8, MI_EVALID /* Mark it valid */ mtspr SPRN_MI_EPN, r8 li r8, MI_PS8MEG /* Set 8M byte page */ - ori r8, r8, MI_SVALID | M_APG2 /* Make it valid, APG 2 */ + ori r8, r8, MI_SVALID /* Make it valid */ mtspr SPRN_MI_TWC, r8 li r8, MI_BOOTINIT /* Create RPN for address 0 */ mtspr SPRN_MI_RPN, r8 /* Store TLB entry */ @@ -987,7 +1004,7 @@ initial_mmu: ori r8, r8, MD_EVALID /* Mark it valid */ mtspr SPRN_MD_EPN, r8 li r8, MD_PS512K | MD_GUARDED /* Set 512k byte page */ - ori r8, r8, MD_SVALID | M_APG2 /* Make it valid and accessed */ + ori r8, r8, MD_SVALID /* Make it valid */ mtspr SPRN_MD_TWC, r8 mr r8, r9 /* Create paddr for TLB */ ori r8, r8, MI_BOOTINIT|0x2 /* Inhibit cache -- Cort */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 4d5322cfad25c7..96f34730010fe3 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -590,12 +590,11 @@ void flush_all_to_thread(struct task_struct *tsk) if (tsk->thread.regs) { preempt_disable(); BUG_ON(tsk != current); - save_all(tsk); - #ifdef CONFIG_SPE if (tsk->thread.regs->msr & MSR_SPE) tsk->thread.spefscr = mfspr(SPRN_SPEFSCR); #endif + save_all(tsk); preempt_enable(); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index bf8def2159c31e..d65b961661fbf6 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2337,8 +2337,7 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu) kvmppc_core_prepare_to_enter(vcpu); return; } - dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC - / tb_ticks_per_sec; + dec_nsec = tb_to_ns(vcpu->arch.dec_expires - now); hrtimer_start(&vcpu->arch.dec_timer, dec_nsec, HRTIMER_MODE_REL); vcpu->arch.timer_running = 1; } diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c index fa888bfc347e6e..9f5b8c01c4e165 100644 --- a/arch/powerpc/kvm/emulate.c +++ b/arch/powerpc/kvm/emulate.c @@ -61,11 +61,10 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu) dec_time = vcpu->arch.dec; /* - * Guest timebase ticks at the same frequency as host decrementer. - * So use the host decrementer calculations for decrementer emulation. + * Guest timebase ticks at the same frequency as host timebase. + * So use the host timebase calculations for decrementer emulation. */ - dec_time = dec_time << decrementer_clockevent.shift; - do_div(dec_time, decrementer_clockevent.mult); + dec_time = tb_to_ns(dec_time); dec_nsec = do_div(dec_time, NSEC_PER_SEC); hrtimer_start(&vcpu->arch.dec_timer, ktime_set(dec_time, dec_nsec), HRTIMER_MODE_REL); diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c index 36484a2ef9158e..01b7f5107c3a32 100644 --- a/arch/powerpc/mm/8xx_mmu.c +++ b/arch/powerpc/mm/8xx_mmu.c @@ -13,6 +13,7 @@ */ #include <linux/memblock.h> +#include <linux/mmu_context.h> #include <asm/fixmap.h> #include <asm/code-patching.h> @@ -79,7 +80,7 @@ void __init MMU_init_hw(void) for (; i < 32 && mem >= LARGE_PAGE_SIZE_8M; i++) { mtspr(SPRN_MD_CTR, ctr | (i << 8)); mtspr(SPRN_MD_EPN, (unsigned long)__va(addr) | MD_EVALID); - mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID | M_APG2); + mtspr(SPRN_MD_TWC, MD_PS8MEG | MD_SVALID); mtspr(SPRN_MD_RPN, addr | flags | _PAGE_PRESENT); addr += LARGE_PAGE_SIZE_8M; mem -= LARGE_PAGE_SIZE_8M; @@ -97,22 +98,13 @@ static void __init mmu_mapin_immr(void) map_kernel_page(v + offset, p + offset, PAGE_KERNEL_NCG); } -/* Address of instructions to patch */ -#ifndef CONFIG_PIN_TLB_IMMR -extern unsigned int DTLBMiss_jmp; -#endif -extern unsigned int DTLBMiss_cmp, FixupDAR_cmp; -#ifndef CONFIG_PIN_TLB_TEXT -extern unsigned int ITLBMiss_cmp; -#endif - -static void __init mmu_patch_cmp_limit(unsigned int *addr, unsigned long mapped) +static void __init mmu_patch_cmp_limit(s32 *site, unsigned long mapped) { - unsigned int instr = *addr; + unsigned int instr = *(unsigned int *)patch_site_addr(site); instr &= 0xffff0000; instr |= (unsigned long)__va(mapped) >> 16; - patch_instruction(addr, instr); + patch_instruction_site(site, instr); } unsigned long __init mmu_mapin_ram(unsigned long top) @@ -123,17 +115,17 @@ unsigned long __init mmu_mapin_ram(unsigned long top) mapped = 0; mmu_mapin_immr(); #ifndef CONFIG_PIN_TLB_IMMR - patch_instruction(&DTLBMiss_jmp, PPC_INST_NOP); + patch_instruction_site(&patch__dtlbmiss_immr_jmp, PPC_INST_NOP); #endif #ifndef CONFIG_PIN_TLB_TEXT - mmu_patch_cmp_limit(&ITLBMiss_cmp, 0); + mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, 0); #endif } else { mapped = top & ~(LARGE_PAGE_SIZE_8M - 1); } - mmu_patch_cmp_limit(&DTLBMiss_cmp, mapped); - mmu_patch_cmp_limit(&FixupDAR_cmp, mapped); + mmu_patch_cmp_limit(&patch__dtlbmiss_linmem_top, mapped); + mmu_patch_cmp_limit(&patch__fixupdar_linmem_top, mapped); /* If the size of RAM is not an exact power of two, we may not * have covered RAM in its entirety with 8 MiB diff --git a/arch/powerpc/perf/8xx-pmu.c b/arch/powerpc/perf/8xx-pmu.c index 6c0020d1c5614c..e38f74e9e7a4ae 100644 --- a/arch/powerpc/perf/8xx-pmu.c +++ b/arch/powerpc/perf/8xx-pmu.c @@ -31,9 +31,6 @@ extern unsigned long itlb_miss_counter, dtlb_miss_counter; extern atomic_t instruction_counter; -extern unsigned int itlb_miss_perf, dtlb_miss_perf; -extern unsigned int itlb_miss_exit_1, itlb_miss_exit_2; -extern unsigned int dtlb_miss_exit_1, dtlb_miss_exit_2, dtlb_miss_exit_3; static atomic_t insn_ctr_ref; static atomic_t itlb_miss_ref; @@ -103,22 +100,22 @@ static int mpc8xx_pmu_add(struct perf_event *event, int flags) break; case PERF_8xx_ID_ITLB_LOAD_MISS: if (atomic_inc_return(&itlb_miss_ref) == 1) { - unsigned long target = (unsigned long)&itlb_miss_perf; + unsigned long target = patch_site_addr(&patch__itlbmiss_perf); - patch_branch(&itlb_miss_exit_1, target, 0); + patch_branch_site(&patch__itlbmiss_exit_1, target, 0); #ifndef CONFIG_PIN_TLB_TEXT - patch_branch(&itlb_miss_exit_2, target, 0); + patch_branch_site(&patch__itlbmiss_exit_2, target, 0); #endif } val = itlb_miss_counter; break; case PERF_8xx_ID_DTLB_LOAD_MISS: if (atomic_inc_return(&dtlb_miss_ref) == 1) { - unsigned long target = (unsigned long)&dtlb_miss_perf; + unsigned long target = patch_site_addr(&patch__dtlbmiss_perf); - patch_branch(&dtlb_miss_exit_1, target, 0); - patch_branch(&dtlb_miss_exit_2, target, 0); - patch_branch(&dtlb_miss_exit_3, target, 0); + patch_branch_site(&patch__dtlbmiss_exit_1, target, 0); + patch_branch_site(&patch__dtlbmiss_exit_2, target, 0); + patch_branch_site(&patch__dtlbmiss_exit_3, target, 0); } val = dtlb_miss_counter; break; @@ -180,17 +177,17 @@ static void mpc8xx_pmu_del(struct perf_event *event, int flags) break; case PERF_8xx_ID_ITLB_LOAD_MISS: if (atomic_dec_return(&itlb_miss_ref) == 0) { - patch_instruction(&itlb_miss_exit_1, insn); + patch_instruction_site(&patch__itlbmiss_exit_1, insn); #ifndef CONFIG_PIN_TLB_TEXT - patch_instruction(&itlb_miss_exit_2, insn); + patch_instruction_site(&patch__itlbmiss_exit_2, insn); #endif } break; case PERF_8xx_ID_DTLB_LOAD_MISS: if (atomic_dec_return(&dtlb_miss_ref) == 0) { - patch_instruction(&dtlb_miss_exit_1, insn); - patch_instruction(&dtlb_miss_exit_2, insn); - patch_instruction(&dtlb_miss_exit_3, insn); + patch_instruction_site(&patch__dtlbmiss_exit_1, insn); + patch_instruction_site(&patch__dtlbmiss_exit_2, insn); + patch_instruction_site(&patch__dtlbmiss_exit_3, insn); } break; } diff --git a/arch/powerpc/platforms/40x/Kconfig b/arch/powerpc/platforms/40x/Kconfig index 2a9d66254ffc58..5326ece3612040 100644 --- a/arch/powerpc/platforms/40x/Kconfig +++ b/arch/powerpc/platforms/40x/Kconfig @@ -29,6 +29,7 @@ config KILAUEA select 405EX select PPC40x_SIMPLE select PPC4xx_PCI_EXPRESS + select PCI select PCI_MSI select PPC4xx_MSI help diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig index f024efd5a4c206..9a85d350b1b6c7 100644 --- a/arch/powerpc/platforms/44x/Kconfig +++ b/arch/powerpc/platforms/44x/Kconfig @@ -21,6 +21,7 @@ config BLUESTONE depends on 44x select PPC44x_SIMPLE select APM821xx + select PCI select PCI_MSI select PPC4xx_MSI select PPC4xx_PCI_EXPRESS @@ -200,6 +201,7 @@ config AKEBONO select SWIOTLB select 476FPE select PPC4xx_PCI_EXPRESS + select PCI select PCI_MSI select PPC4xx_HSTA_MSI select I2C diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index 8bd590af488a1a..794487313cc8d2 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -26,6 +26,7 @@ #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/uaccess.h> +#include <linux/hugetlb.h> #include <asm/lppaca.h> #include <asm/hvcall.h> #include <asm/firmware.h> @@ -36,6 +37,7 @@ #include <asm/vio.h> #include <asm/mmu.h> #include <asm/machdep.h> +#include <asm/drmem.h> #include "pseries.h" @@ -433,6 +435,16 @@ static void parse_em_data(struct seq_file *m) seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); } +static void maxmem_data(struct seq_file *m) +{ + unsigned long maxmem = 0; + + maxmem += drmem_info->n_lmbs * drmem_info->lmb_size; + maxmem += hugetlb_total_pages() * PAGE_SIZE; + + seq_printf(m, "MaxMem=%ld\n", maxmem); +} + static int pseries_lparcfg_data(struct seq_file *m, void *v) { int partition_potential_processors; @@ -491,6 +503,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) seq_printf(m, "slb_size=%d\n", mmu_slb_size); #endif parse_em_data(m); + maxmem_data(m); return 0; } diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 69e7fb47bcaa3e..878f9c1d36150c 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -11,6 +11,12 @@ UBSAN_SANITIZE := n ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) +ifdef CONFIG_CC_IS_CLANG +# clang stores addresses on the stack causing the frame size to blow +# out. See https://github.com/ClangBuiltLinux/linux/issues/252 +KBUILD_CFLAGS += -Wframe-larger-than=4096 +endif + ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += xmon.o nonstdio.o spr_access.o diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 36473d7dbaac4a..07fa9ea75fea1f 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -1,6 +1,3 @@ -CONFIG_SMP=y -CONFIG_PCI=y -CONFIG_PCIE_XILINX=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_IKCONFIG=y @@ -11,10 +8,15 @@ CONFIG_CFS_BANDWIDTH=y CONFIG_CGROUP_BPF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y +CONFIG_SMP=y +CONFIG_PCI=y +CONFIG_PCIE_XILINX=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -59,6 +61,7 @@ CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_VIRTIO_MMIO=y +CONFIG_SIFIVE_PLIC=y CONFIG_RAS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y @@ -72,8 +75,5 @@ CONFIG_NFS_V4=y CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y -# CONFIG_RCU_TRACE is not set CONFIG_CRYPTO_USER_API_HASH=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_SIFIVE_PLIC=y +# CONFIG_RCU_TRACE is not set diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index 67b3e6b3ce5d7c..47c871394ccb16 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -1849,16 +1849,12 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { u64 saved_fault_address = current_thread_info()->fault_address; u8 saved_fault_code = get_thread_fault_code(); - mm_segment_t old_fs; perf_callchain_store(entry, regs->tpc); if (!current->mm) return; - old_fs = get_fs(); - set_fs(USER_DS); - flushw_user(); pagefault_disable(); @@ -1870,7 +1866,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs pagefault_enable(); - set_fs(old_fs); set_thread_fault_code(saved_fault_code); current_thread_info()->fault_address = saved_fault_address; } diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S index bb68c805b89185..ff9389a1c9f3f6 100644 --- a/arch/sparc/kernel/systbls_64.S +++ b/arch/sparc/kernel/systbls_64.S @@ -47,9 +47,9 @@ sys_call_table32: .word sys_recvfrom, sys_setreuid16, sys_setregid16, sys_rename, compat_sys_truncate /*130*/ .word compat_sys_ftruncate, sys_flock, compat_sys_lstat64, sys_sendto, sys_shutdown .word sys_socketpair, sys_mkdir, sys_rmdir, compat_sys_utimes, compat_sys_stat64 -/*140*/ .word sys_sendfile64, sys_nis_syscall, compat_sys_futex, sys_gettid, compat_sys_getrlimit +/*140*/ .word sys_sendfile64, sys_getpeername, compat_sys_futex, sys_gettid, compat_sys_getrlimit .word compat_sys_setrlimit, sys_pivot_root, sys_prctl, sys_pciconfig_read, sys_pciconfig_write -/*150*/ .word sys_nis_syscall, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 +/*150*/ .word sys_getsockname, sys_inotify_init, sys_inotify_add_watch, sys_poll, sys_getdents64 .word compat_sys_fcntl64, sys_inotify_rm_watch, compat_sys_statfs, compat_sys_fstatfs, sys_oldumount /*160*/ .word compat_sys_sched_setaffinity, compat_sys_sched_getaffinity, sys_getdomainname, sys_setdomainname, sys_nis_syscall .word sys_quotactl, sys_set_tid_address, compat_sys_mount, compat_sys_ustat, sys_setxattr diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c51c989c19c08d..ba7e3464ee9235 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -129,6 +129,7 @@ config X86 select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_THREAD_STRUCT_WHITELIST + select HAVE_ARCH_STACKLEAK select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64 diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 708b46a54578d8..25e5a6bda8c3a9 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -329,8 +329,22 @@ For 32-bit we have the following conventions - kernel is built with #endif +.macro STACKLEAK_ERASE_NOCLOBBER +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + PUSH_AND_CLEAR_REGS + call stackleak_erase + POP_REGS +#endif +.endm + #endif /* CONFIG_X86_64 */ +.macro STACKLEAK_ERASE +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + call stackleak_erase +#endif +.endm + /* * This does 'call enter_from_user_mode' unless we can avoid it based on * kernel config or using the static jump infrastructure. diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 687e47f8a79662..d309f30cf7af84 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -46,6 +46,8 @@ #include <asm/frame.h> #include <asm/nospec-branch.h> +#include "calling.h" + .section .entry.text, "ax" /* @@ -712,6 +714,7 @@ ENTRY(ret_from_fork) /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax call syscall_return_slowpath + STACKLEAK_ERASE jmp restore_all /* kernel thread */ @@ -886,6 +889,8 @@ ENTRY(entry_SYSENTER_32) ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + STACKLEAK_ERASE + /* Opportunistic SYSEXIT */ TRACE_IRQS_ON /* User mode traces as IRQs on. */ @@ -997,6 +1002,8 @@ ENTRY(entry_INT80_32) call do_int80_syscall_32 .Lsyscall_32_done: + STACKLEAK_ERASE + restore_all: TRACE_IRQS_IRET SWITCH_TO_ENTRY_STACK diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 4d7a2d9d44cfec..ce25d84023c021 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -266,6 +266,8 @@ syscall_return_via_sysret: * We are on the trampoline stack. All regs except RDI are live. * We can do future final exit work right here. */ + STACKLEAK_ERASE_NOCLOBBER + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi popq %rdi @@ -625,6 +627,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) * We are on the trampoline stack. All regs except RDI are live. * We can do future final exit work right here. */ + STACKLEAK_ERASE_NOCLOBBER SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 7d0df78db72729..8eaf8952c408cd 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -261,6 +261,11 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) /* Opportunistic SYSRET */ sysret32_from_system_call: + /* + * We are not going to return to userspace from the trampoline + * stack. So let's erase the thread stack right now. + */ + STACKLEAK_ERASE TRACE_IRQS_ON /* User mode traces as IRQs on. */ movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 60c141af222bc5..d29b7365da8d9f 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -1,7 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -config ZONE_DMA - def_bool y - config XTENSA def_bool y select ARCH_HAS_SG_CHAIN diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile index dc9e0ba7122cad..294846117fc2c5 100644 --- a/arch/xtensa/boot/Makefile +++ b/arch/xtensa/boot/Makefile @@ -33,7 +33,7 @@ uImage: $(obj)/uImage boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y)) $(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS) -OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary +OBJCOPYFLAGS = --strip-all -R .comment -R .notes -O binary vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S index b727b18a68acd9..b80a430453b1cb 100644 --- a/arch/xtensa/kernel/vmlinux.lds.S +++ b/arch/xtensa/kernel/vmlinux.lds.S @@ -131,6 +131,7 @@ SECTIONS .fixup : { *(.fixup) } EXCEPTION_TABLE(16) + NOTES /* Data section */ _sdata = .; @@ -296,38 +297,11 @@ SECTIONS _end = .; - .xt.lit : { *(.xt.lit) } - .xt.prop : { *(.xt.prop) } - - .debug 0 : { *(.debug) } - .line 0 : { *(.line) } - .debug_srcinfo 0 : { *(.debug_srcinfo) } - .debug_sfnames 0 : { *(.debug_sfnames) } - .debug_aranges 0 : { *(.debug_aranges) } - .debug_pubnames 0 : { *(.debug_pubnames) } - .debug_info 0 : { *(.debug_info) } - .debug_abbrev 0 : { *(.debug_abbrev) } - .debug_line 0 : { *(.debug_line) } - .debug_frame 0 : { *(.debug_frame) } - .debug_str 0 : { *(.debug_str) } - .debug_loc 0 : { *(.debug_loc) } - .debug_macinfo 0 : { *(.debug_macinfo) } - .debug_weaknames 0 : { *(.debug_weaknames) } - .debug_funcnames 0 : { *(.debug_funcnames) } - .debug_typenames 0 : { *(.debug_typenames) } - .debug_varnames 0 : { *(.debug_varnames) } - - .xt.insn 0 : - { - *(.xt.insn) - *(.gnu.linkonce.x*) - } + DWARF_DEBUG - .xt.lit 0 : - { - *(.xt.lit) - *(.gnu.linkonce.p*) - } + .xt.prop 0 : { KEEP(*(.xt.prop .xt.prop.* .gnu.linkonce.prop.*)) } + .xt.insn 0 : { KEEP(*(.xt.insn .xt.insn.* .gnu.linkonce.x*)) } + .xt.lit 0 : { KEEP(*(.xt.lit .xt.lit.* .gnu.linkonce.p*)) } /* Sections to be discarded */ DISCARDS diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 9750a48f491b19..30a48bba4a4737 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -71,7 +71,7 @@ void __init zones_init(void) { /* All pages are DMA-able, so we put them all in the DMA zone. */ unsigned long zones_size[MAX_NR_ZONES] = { - [ZONE_DMA] = max_low_pfn - ARCH_PFN_OFFSET, + [ZONE_NORMAL] = max_low_pfn - ARCH_PFN_OFFSET, #ifdef CONFIG_HIGHMEM [ZONE_HIGHMEM] = max_pfn - max_low_pfn, #endif diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d9a7916ff0ab64..9fe5952d117d55 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -642,7 +642,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger @@ -651,7 +651,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) goto out; - bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio)); + bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio)); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 6075100f03a50a..3a27d31fcda602 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4384,7 +4384,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, rcu_read_lock(); - bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio)); + bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); if (!bfqg) { bfqq = &bfqd->oom_bfqq; goto out; diff --git a/block/bio.c b/block/bio.c index bbfeb4ee2892fc..d5368a44556134 100644 --- a/block/bio.c +++ b/block/bio.c @@ -609,9 +609,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); } EXPORT_SYMBOL(__bio_clone_fast); @@ -1256,7 +1254,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, /* * success */ - if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) || + if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) || (map_data && map_data->from_user)) { ret = bio_copy_from_iter(bio, iter); if (ret) @@ -1956,151 +1954,69 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP -/** - * bio_associate_blkg - associate a bio with the a blkg - * @bio: target bio - * @blkg: the blkg to associate - * - * This tries to associate @bio with the specified blkg. Association failure - * is handled by walking up the blkg tree. Therefore, the blkg associated can - * be anything between @blkg and the root_blkg. This situation only happens - * when a cgroup is dying and then the remaining bios will spill to the closest - * alive blkg. - * - * A reference will be taken on the @blkg and will be released when @bio is - * freed. - */ -int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - bio->bi_blkg = blkg_tryget_closest(blkg); - return 0; -} - -/** - * __bio_associate_blkg_from_css - internal blkg association function - * - * This in the core association function that all association paths rely on. - * A blkg reference is taken which is released upon freeing of the bio. - */ -static int __bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - struct request_queue *q = bio->bi_disk->queue; - struct blkcg_gq *blkg; - int ret; - - rcu_read_lock(); - - if (!css || !css->parent) - blkg = q->root_blkg; - else - blkg = blkg_lookup_create(css_to_blkcg(css), q); - - ret = bio_associate_blkg(bio, blkg); - - rcu_read_unlock(); - return ret; -} - -/** - * bio_associate_blkg_from_css - associate a bio with a specified css - * @bio: target bio - * @css: target css - * - * Associate @bio with the blkg found by combining the css's blkg and the - * request_queue of the @bio. This falls back to the queue's root_blkg if - * the association fails with the css. - */ -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - return __bio_associate_blkg_from_css(bio, css); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); - #ifdef CONFIG_MEMCG /** - * bio_associate_blkg_from_page - associate a bio with the page's blkg + * bio_associate_blkcg_from_page - associate a bio with the page's blkcg * @bio: target bio * @page: the page to lookup the blkcg from * - * Associate @bio with the blkg from @page's owning memcg and the respective - * request_queue. If cgroup_e_css returns NULL, fall back to the queue's - * root_blkg. - * - * Note: this must be called after bio has an associated device. + * Associate @bio with the blkcg from @page's owning memcg. This works like + * every other associate function wrt references. */ -int bio_associate_blkg_from_page(struct bio *bio, struct page *page) +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) { - struct cgroup_subsys_state *css; - int ret; + struct cgroup_subsys_state *blkcg_css; - if (unlikely(bio->bi_blkg)) + if (unlikely(bio->bi_css)) return -EBUSY; if (!page->mem_cgroup) return 0; - - rcu_read_lock(); - - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, + &io_cgrp_subsys); + bio->bi_css = blkcg_css; + return 0; } #endif /* CONFIG_MEMCG */ /** - * bio_associate_create_blkg - associate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio + * @blkcg_css: css of the blkcg to associate + * + * Associate @bio with the blkcg specified by @blkcg_css. Block layer will + * treat @bio as if it were issued by a task which belongs to the blkcg. * - * Associate @bio with the blkg found from the bio's css and the request_queue. - * If one is not found, bio_lookup_blkg creates the blkg. This falls back to - * the queue's root_blkg if association fails. + * This function takes an extra reference of @blkcg_css which will be put + * when @bio is released. The caller must own @bio and is responsible for + * synchronizing calls to this function. */ -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { - struct cgroup_subsys_state *css; - int ret = 0; - - /* someone has already associated this bio with a blkg */ - if (bio->bi_blkg) - return ret; - - rcu_read_lock(); - - css = blkcg_css(); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + if (unlikely(bio->bi_css)) + return -EBUSY; + css_get(blkcg_css); + bio->bi_css = blkcg_css; + return 0; } +EXPORT_SYMBOL_GPL(bio_associate_blkcg); /** - * bio_reassociate_blkg - reassociate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkg - associate a bio with the specified blkg * @bio: target bio + * @blkg: the blkg to associate * - * When submitting a bio, multiple recursive calls to make_request() may occur. - * This causes the initial associate done in blkcg_bio_issue_check() to be - * incorrect and reference the prior request_queue. This performs reassociation - * when this situation happens. + * Associate @bio with the blkg specified by @blkg. This is the queue specific + * blkcg information associated with the @bio, a reference will be taken on the + * @blkg and will be freed when the bio is freed. */ -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { - if (bio->bi_blkg) { - blkg_put(bio->bi_blkg); - bio->bi_blkg = NULL; - } - - return bio_associate_create_blkg(q, bio); + if (unlikely(bio->bi_blkg)) + return -EBUSY; + if (!blkg_try_get(blkg)) + return -ENODEV; + bio->bi_blkg = blkg; + return 0; } /** @@ -2113,6 +2029,10 @@ void bio_disassociate_task(struct bio *bio) put_io_context(bio->bi_ioc); bio->bi_ioc = NULL; } + if (bio->bi_css) { + css_put(bio->bi_css); + bio->bi_css = NULL; + } if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; @@ -2120,16 +2040,16 @@ void bio_disassociate_task(struct bio *bio) } /** - * bio_clone_blkg_association - clone blkg association from src to dst bio + * bio_clone_blkcg_association - clone blkcg association from src to dst bio * @dst: destination bio * @src: source bio */ -void bio_clone_blkg_association(struct bio *dst, struct bio *src) +void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { - if (src->bi_blkg) - bio_associate_blkg(dst, src->bi_blkg); + if (src->bi_css) + WARN_ON(bio_associate_blkcg(dst, src->bi_css)); } -EXPORT_SYMBOL_GPL(bio_clone_blkg_association); +EXPORT_SYMBOL_GPL(bio_clone_blkcg_association); #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 992da5592c6ed1..c630e02836a80d 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -84,37 +84,6 @@ static void blkg_free(struct blkcg_gq *blkg) kfree(blkg); } -static void __blkg_release(struct rcu_head *rcu) -{ - struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); - - percpu_ref_exit(&blkg->refcnt); - - /* release the blkcg and parent blkg refs this blkg has been holding */ - css_put(&blkg->blkcg->css); - if (blkg->parent) - blkg_put(blkg->parent); - - wb_congested_put(blkg->wb_congested); - - blkg_free(blkg); -} - -/* - * A group is RCU protected, but having an rcu lock does not mean that one - * can access all the fields of blkg and assume these are valid. For - * example, don't try to follow throtl_data and request queue links. - * - * Having a reference to blkg under an rcu allows accesses to only values - * local to groups like group stats and group rate limits. - */ -static void blkg_release(struct percpu_ref *ref) -{ - struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); - - call_rcu(&blkg->rcu_head, __blkg_release); -} - /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with @@ -141,6 +110,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + atomic_set(&blkg->refcnt, 1); /* root blkg uses @q->root_rl, init rl only for !root blkgs */ if (blkcg != &blkcg_root) { @@ -247,11 +217,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_get(blkg->parent); } - ret = percpu_ref_init(&blkg->refcnt, blkg_release, 0, - GFP_NOWAIT | __GFP_NOWARN); - if (ret) - goto err_cancel_ref; - /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -284,8 +249,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_put(blkg); return ERR_PTR(ret); -err_cancel_ref: - percpu_ref_exit(&blkg->refcnt); err_put_congested: wb_congested_put(wb_congested); err_put_css: @@ -296,7 +259,7 @@ err_free_blkg: } /** - * __blkg_lookup_create - lookup blkg, try to create one if not there + * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * @@ -305,11 +268,12 @@ err_free_blkg: * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and @q->queue_lock. * - * Returns the blkg or the closest blkg if blkg_create fails as it walks - * down from root. + * Returns pointer to the looked up or created blkg on success, ERR_PTR() + * value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not + * dead and bypassing, returns ERR_PTR(-EBUSY). */ -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) +struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q) { struct blkcg_gq *blkg; @@ -321,7 +285,7 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, * we shouldn't allow anything to go through for a bypassing queue. */ if (unlikely(blk_queue_bypass(q))) - return q->root_blkg; + return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); blkg = __blkg_lookup(blkcg, q, true); if (blkg) @@ -329,58 +293,23 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, /* * Create blkgs walking down from blkcg_root to @blkcg, so that all - * non-root blkgs have access to their parents. Returns the closest - * blkg to the intended blkg should blkg_create() fail. + * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); - struct blkcg_gq *ret_blkg = q->root_blkg; - - while (parent) { - blkg = __blkg_lookup(parent, q, false); - if (blkg) { - /* remember closest blkg */ - ret_blkg = blkg; - break; - } + + while (parent && !__blkg_lookup(parent, q, false)) { pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, q, NULL); - if (IS_ERR(blkg)) - return ret_blkg; - if (pos == blkcg) + if (pos == blkcg || IS_ERR(blkg)) return blkg; } } -/** - * blkg_lookup_create - find or create a blkg - * @blkcg: target block cgroup - * @q: target request_queue - * - * This looks up or creates the blkg representing the unique pair - * of the blkcg and the request_queue. - */ -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) -{ - struct blkcg_gq *blkg = blkg_lookup(blkcg, q); - unsigned long flags; - - if (unlikely(!blkg)) { - spin_lock_irqsave(q->queue_lock, flags); - - blkg = __blkg_lookup_create(blkcg, q); - - spin_unlock_irqrestore(q->queue_lock, flags); - } - - return blkg; -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; @@ -424,7 +353,7 @@ static void blkg_destroy(struct blkcg_gq *blkg) * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ - percpu_ref_kill(&blkg->refcnt); + blkg_put(blkg); } /** @@ -452,6 +381,29 @@ static void blkg_destroy_all(struct request_queue *q) } /* + * A group is RCU protected, but having an rcu lock does not mean that one + * can access all the fields of blkg and assume these are valid. For + * example, don't try to follow throtl_data and request queue links. + * + * Having a reference to blkg under an rcu allows accesses to only values + * local to groups like group stats and group rate limits. + */ +void __blkg_release_rcu(struct rcu_head *rcu_head) +{ + struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head); + + /* release the blkcg and parent blkg refs this blkg has been holding */ + css_put(&blkg->blkcg->css); + if (blkg->parent) + blkg_put(blkg->parent); + + wb_congested_put(blkg->wb_congested); + + blkg_free(blkg); +} +EXPORT_SYMBOL_GPL(__blkg_release_rcu); + +/* * The next function used by blk_queue_for_each_rl(). It's a bit tricky * because the root blkg uses @q->root_rl instead of its own rl. */ @@ -1796,7 +1748,8 @@ void blkcg_maybe_throttle_current(void) blkg = blkg_lookup(blkcg, q); if (!blkg) goto out; - if (!blkg_tryget(blkg)) + blkg = blkg_try_get(blkg); + if (!blkg) goto out; rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index bc6ea87d10e02c..ce12515f9b9b99 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -785,6 +785,9 @@ void blk_cleanup_queue(struct request_queue *q) * prevent that q->request_fn() gets invoked after draining finished. */ blk_freeze_queue(q); + + rq_qos_exit(q); + spin_lock_irq(lock); queue_flag_set(QUEUE_FLAG_DEAD, q); spin_unlock_irq(lock); @@ -2432,7 +2435,6 @@ blk_qc_t generic_make_request(struct bio *bio) if (q) blk_queue_exit(q); q = bio->bi_disk->queue; - bio_reassociate_blkg(q, bio); flags = 0; if (bio->bi_opf & REQ_NOWAIT) flags = BLK_MQ_REQ_NOWAIT; diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 28f80d22752858..38c35c32aff2dc 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -482,12 +482,34 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock) { struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); - struct blkcg_gq *blkg = bio->bi_blkg; + struct blkcg *blkcg; + struct blkcg_gq *blkg; + struct request_queue *q = rqos->q; bool issue_as_root = bio_issue_as_root_blkg(bio); if (!blk_iolatency_enabled(blkiolat)) return; + rcu_read_lock(); + blkcg = bio_blkcg(bio); + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + if (!lock) + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + if (!lock) + spin_unlock_irq(q->queue_lock); + } + if (!blkg) + goto out; + + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); + bio_associate_blkg(bio, blkg); +out: + rcu_read_unlock(); while (blkg && blkg->parent) { struct iolatency_grp *iolat = blkg_to_lat(blkg); if (!iolat) { @@ -708,7 +730,7 @@ static void blkiolatency_timer_fn(struct timer_list *t) * We could be exiting, don't access the pd unless we have a * ref on the blkg. */ - if (!blkg_tryget(blkg)) + if (!blkg_try_get(blkg)) continue; iolat = blkg_to_lat(blkg); diff --git a/block/blk-merge.c b/block/blk-merge.c index 42a46744c11b45..6b5ad275ed565d 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -714,6 +714,31 @@ static void blk_account_io_merge(struct request *req) part_stat_unlock(); } } +/* + * Two cases of handling DISCARD merge: + * If max_discard_segments > 1, the driver takes every bio + * as a range and send them to controller together. The ranges + * needn't to be contiguous. + * Otherwise, the bios/requests will be handled as same as + * others which should be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + +enum elv_merge blk_try_req_merge(struct request *req, struct request *next) +{ + if (blk_discard_mergable(req)) + return ELEVATOR_DISCARD_MERGE; + else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) + return ELEVATOR_BACK_MERGE; + + return ELEVATOR_NO_MERGE; +} /* * For non-mq, this has to be called with the request spinlock acquired. @@ -731,12 +756,6 @@ static struct request *attempt_merge(struct request_queue *q, if (req_op(req) != req_op(next)) return NULL; - /* - * not contiguous - */ - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next)) - return NULL; - if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk || req_no_special_merge(next)) @@ -760,11 +779,19 @@ static struct request *attempt_merge(struct request_queue *q, * counts here. Handle DISCARDs separately, as they * have separate settings. */ - if (req_op(req) == REQ_OP_DISCARD) { + + switch (blk_try_req_merge(req, next)) { + case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; - } else if (!ll_merge_requests_fn(q, req, next)) + break; + case ELEVATOR_BACK_MERGE: + if (!ll_merge_requests_fn(q, req, next)) + return NULL; + break; + default: return NULL; + } /* * If failfast settings disagree or any of the two is already @@ -888,8 +915,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { - if (req_op(rq) == REQ_OP_DISCARD && - queue_max_discard_segments(rq->q) > 1) + if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 0641533597f1b2..844a454a7b3a60 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -1007,8 +1007,6 @@ void blk_unregister_queue(struct gendisk *disk) kobject_del(&q->kobj); blk_trace_remove_sysfs(disk_to_dev(disk)); - rq_qos_exit(q); - mutex_lock(&q->sysfs_lock); if (q->request_fn || (q->mq_ops && q->elevator)) elv_unregister_queue(q); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 4bda70e8db48a9..db1a3a2ae00617 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2115,11 +2115,21 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) } #endif +static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) +{ +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); +#endif +} + bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio) { struct throtl_qnode *qn = NULL; - struct throtl_grp *tg = blkg_to_tg(blkg); + struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; @@ -2138,6 +2148,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, if (unlikely(blk_queue_bypass(q))) goto out_unlock; + blk_throtl_assoc_bio(tg, bio); blk_throtl_update_idletime(tg); sq = &tg->service_queue; diff --git a/block/bounce.c b/block/bounce.c index cf49fe02f65cd0..36869afc258ccf 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -276,9 +276,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, } } - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); return bio; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 6a3d87dd3c1ac4..ed41aa978c4abc 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3759,7 +3759,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; rcu_read_unlock(); /* @@ -3824,7 +3824,7 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, struct cfq_group *cfqg; rcu_read_lock(); - cfqg = cfq_lookup_cfqg(cfqd, __bio_blkcg(bio)); + cfqg = cfq_lookup_cfqg(cfqd, bio_blkcg(bio)); if (!cfqg) { cfqq = &cfqd->oom_cfqq; goto out; diff --git a/crypto/asymmetric_keys/Kconfig b/crypto/asymmetric_keys/Kconfig index f3702e533ff410..be70ca6c85d31e 100644 --- a/crypto/asymmetric_keys/Kconfig +++ b/crypto/asymmetric_keys/Kconfig @@ -21,6 +21,18 @@ config ASYMMETRIC_PUBLIC_KEY_SUBTYPE appropriate hash algorithms (such as SHA-1) must be available. ENOPKG will be reported if the requisite algorithm is unavailable. +config ASYMMETRIC_TPM_KEY_SUBTYPE + tristate "Asymmetric TPM backed private key subtype" + depends on TCG_TPM + depends on TRUSTED_KEYS + select CRYPTO_HMAC + select CRYPTO_SHA1 + select CRYPTO_HASH_INFO + help + This option provides support for TPM backed private key type handling. + Operations such as sign, verify, encrypt, decrypt are performed by + the TPM after the private key is loaded. + config X509_CERTIFICATE_PARSER tristate "X.509 certificate parser" depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE @@ -31,6 +43,25 @@ config X509_CERTIFICATE_PARSER data and provides the ability to instantiate a crypto key from a public key packet found inside the certificate. +config PKCS8_PRIVATE_KEY_PARSER + tristate "PKCS#8 private key parser" + depends on ASYMMETRIC_PUBLIC_KEY_SUBTYPE + select ASN1 + select OID_REGISTRY + help + This option provides support for parsing PKCS#8 format blobs for + private key data and provides the ability to instantiate a crypto key + from that data. + +config TPM_KEY_PARSER + tristate "TPM private key parser" + depends on ASYMMETRIC_TPM_KEY_SUBTYPE + select ASN1 + help + This option provides support for parsing TPM format blobs for + private key data and provides the ability to instantiate a crypto key + from that data. + config PKCS7_MESSAGE_PARSER tristate "PKCS#7 message parser" depends on X509_CERTIFICATE_PARSER diff --git a/crypto/asymmetric_keys/Makefile b/crypto/asymmetric_keys/Makefile index d4b2e1b2dc6508..28b91adba2aed3 100644 --- a/crypto/asymmetric_keys/Makefile +++ b/crypto/asymmetric_keys/Makefile @@ -11,6 +11,7 @@ asymmetric_keys-y := \ signature.o obj-$(CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE) += public_key.o +obj-$(CONFIG_ASYMMETRIC_TPM_KEY_SUBTYPE) += asym_tpm.o # # X.509 Certificate handling @@ -30,6 +31,19 @@ $(obj)/x509.asn1.o: $(obj)/x509.asn1.c $(obj)/x509.asn1.h $(obj)/x509_akid.asn1.o: $(obj)/x509_akid.asn1.c $(obj)/x509_akid.asn1.h # +# PKCS#8 private key handling +# +obj-$(CONFIG_PKCS8_PRIVATE_KEY_PARSER) += pkcs8_key_parser.o +pkcs8_key_parser-y := \ + pkcs8.asn1.o \ + pkcs8_parser.o + +$(obj)/pkcs8_parser.o: $(obj)/pkcs8.asn1.h +$(obj)/pkcs8-asn1.o: $(obj)/pkcs8.asn1.c $(obj)/pkcs8.asn1.h + +clean-files += pkcs8.asn1.c pkcs8.asn1.h + +# # PKCS#7 message handling # obj-$(CONFIG_PKCS7_MESSAGE_PARSER) += pkcs7_message.o @@ -61,3 +75,14 @@ verify_signed_pefile-y := \ $(obj)/mscode_parser.o: $(obj)/mscode.asn1.h $(obj)/mscode.asn1.h $(obj)/mscode.asn1.o: $(obj)/mscode.asn1.c $(obj)/mscode.asn1.h + +# +# TPM private key parsing +# +obj-$(CONFIG_TPM_KEY_PARSER) += tpm_key_parser.o +tpm_key_parser-y := \ + tpm.asn1.o \ + tpm_parser.o + +$(obj)/tpm_parser.o: $(obj)/tpm.asn1.h +$(obj)/tpm.asn1.o: $(obj)/tpm.asn1.c $(obj)/tpm.asn1.h diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c new file mode 100644 index 00000000000000..5d4c270463f609 --- /dev/null +++ b/crypto/asymmetric_keys/asym_tpm.c @@ -0,0 +1,988 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) "ASYM-TPM: "fmt +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> +#include <linux/scatterlist.h> +#include <linux/tpm.h> +#include <linux/tpm_command.h> +#include <crypto/akcipher.h> +#include <crypto/hash.h> +#include <crypto/sha.h> +#include <asm/unaligned.h> +#include <keys/asymmetric-subtype.h> +#include <keys/trusted.h> +#include <crypto/asym_tpm_subtype.h> +#include <crypto/public_key.h> + +#define TPM_ORD_FLUSHSPECIFIC 186 +#define TPM_ORD_LOADKEY2 65 +#define TPM_ORD_UNBIND 30 +#define TPM_ORD_SIGN 60 +#define TPM_LOADKEY2_SIZE 59 +#define TPM_FLUSHSPECIFIC_SIZE 18 +#define TPM_UNBIND_SIZE 63 +#define TPM_SIGN_SIZE 63 + +#define TPM_RT_KEY 0x00000001 + +/* + * Load a TPM key from the blob provided by userspace + */ +static int tpm_loadkey2(struct tpm_buf *tb, + uint32_t keyhandle, unsigned char *keyauth, + const unsigned char *keyblob, int keybloblen, + uint32_t *newhandle) +{ + unsigned char nonceodd[TPM_NONCE_SIZE]; + unsigned char enonce[TPM_NONCE_SIZE]; + unsigned char authdata[SHA1_DIGEST_SIZE]; + uint32_t authhandle = 0; + unsigned char cont = 0; + uint32_t ordinal; + int ret; + + ordinal = htonl(TPM_ORD_LOADKEY2); + + /* session for loading the key */ + ret = oiap(tb, &authhandle, enonce); + if (ret < 0) { + pr_info("oiap failed (%d)\n", ret); + return ret; + } + + /* generate odd nonce */ + ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); + if (ret < 0) { + pr_info("tpm_get_random failed (%d)\n", ret); + return ret; + } + + /* calculate authorization HMAC value */ + ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, + nonceodd, cont, sizeof(uint32_t), &ordinal, + keybloblen, keyblob, 0, 0); + if (ret < 0) + return ret; + + /* build the request buffer */ + INIT_BUF(tb); + store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); + store32(tb, TPM_LOADKEY2_SIZE + keybloblen); + store32(tb, TPM_ORD_LOADKEY2); + store32(tb, keyhandle); + storebytes(tb, keyblob, keybloblen); + store32(tb, authhandle); + storebytes(tb, nonceodd, TPM_NONCE_SIZE); + store8(tb, cont); + storebytes(tb, authdata, SHA1_DIGEST_SIZE); + + ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); + if (ret < 0) { + pr_info("authhmac failed (%d)\n", ret); + return ret; + } + + ret = TSS_checkhmac1(tb->data, ordinal, nonceodd, keyauth, + SHA1_DIGEST_SIZE, 0, 0); + if (ret < 0) { + pr_info("TSS_checkhmac1 failed (%d)\n", ret); + return ret; + } + + *newhandle = LOAD32(tb->data, TPM_DATA_OFFSET); + return 0; +} + +/* + * Execute the FlushSpecific TPM command + */ +static int tpm_flushspecific(struct tpm_buf *tb, uint32_t handle) +{ + INIT_BUF(tb); + store16(tb, TPM_TAG_RQU_COMMAND); + store32(tb, TPM_FLUSHSPECIFIC_SIZE); + store32(tb, TPM_ORD_FLUSHSPECIFIC); + store32(tb, handle); + store32(tb, TPM_RT_KEY); + + return trusted_tpm_send(tb->data, MAX_BUF_SIZE); +} + +/* + * Decrypt a blob provided by userspace using a specific key handle. + * The handle is a well known handle or previously loaded by e.g. LoadKey2 + */ +static int tpm_unbind(struct tpm_buf *tb, + uint32_t keyhandle, unsigned char *keyauth, + const unsigned char *blob, uint32_t bloblen, + void *out, uint32_t outlen) +{ + unsigned char nonceodd[TPM_NONCE_SIZE]; + unsigned char enonce[TPM_NONCE_SIZE]; + unsigned char authdata[SHA1_DIGEST_SIZE]; + uint32_t authhandle = 0; + unsigned char cont = 0; + uint32_t ordinal; + uint32_t datalen; + int ret; + + ordinal = htonl(TPM_ORD_UNBIND); + datalen = htonl(bloblen); + + /* session for loading the key */ + ret = oiap(tb, &authhandle, enonce); + if (ret < 0) { + pr_info("oiap failed (%d)\n", ret); + return ret; + } + + /* generate odd nonce */ + ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); + if (ret < 0) { + pr_info("tpm_get_random failed (%d)\n", ret); + return ret; + } + + /* calculate authorization HMAC value */ + ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, + nonceodd, cont, sizeof(uint32_t), &ordinal, + sizeof(uint32_t), &datalen, + bloblen, blob, 0, 0); + if (ret < 0) + return ret; + + /* build the request buffer */ + INIT_BUF(tb); + store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); + store32(tb, TPM_UNBIND_SIZE + bloblen); + store32(tb, TPM_ORD_UNBIND); + store32(tb, keyhandle); + store32(tb, bloblen); + storebytes(tb, blob, bloblen); + store32(tb, authhandle); + storebytes(tb, nonceodd, TPM_NONCE_SIZE); + store8(tb, cont); + storebytes(tb, authdata, SHA1_DIGEST_SIZE); + + ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); + if (ret < 0) { + pr_info("authhmac failed (%d)\n", ret); + return ret; + } + + datalen = LOAD32(tb->data, TPM_DATA_OFFSET); + + ret = TSS_checkhmac1(tb->data, ordinal, nonceodd, + keyauth, SHA1_DIGEST_SIZE, + sizeof(uint32_t), TPM_DATA_OFFSET, + datalen, TPM_DATA_OFFSET + sizeof(uint32_t), + 0, 0); + if (ret < 0) { + pr_info("TSS_checkhmac1 failed (%d)\n", ret); + return ret; + } + + memcpy(out, tb->data + TPM_DATA_OFFSET + sizeof(uint32_t), + min(outlen, datalen)); + + return datalen; +} + +/* + * Sign a blob provided by userspace (that has had the hash function applied) + * using a specific key handle. The handle is assumed to have been previously + * loaded by e.g. LoadKey2. + * + * Note that the key signature scheme of the used key should be set to + * TPM_SS_RSASSAPKCS1v15_DER. This allows the hashed input to be of any size + * up to key_length_in_bytes - 11 and not be limited to size 20 like the + * TPM_SS_RSASSAPKCS1v15_SHA1 signature scheme. + */ +static int tpm_sign(struct tpm_buf *tb, + uint32_t keyhandle, unsigned char *keyauth, + const unsigned char *blob, uint32_t bloblen, + void *out, uint32_t outlen) +{ + unsigned char nonceodd[TPM_NONCE_SIZE]; + unsigned char enonce[TPM_NONCE_SIZE]; + unsigned char authdata[SHA1_DIGEST_SIZE]; + uint32_t authhandle = 0; + unsigned char cont = 0; + uint32_t ordinal; + uint32_t datalen; + int ret; + + ordinal = htonl(TPM_ORD_SIGN); + datalen = htonl(bloblen); + + /* session for loading the key */ + ret = oiap(tb, &authhandle, enonce); + if (ret < 0) { + pr_info("oiap failed (%d)\n", ret); + return ret; + } + + /* generate odd nonce */ + ret = tpm_get_random(NULL, nonceodd, TPM_NONCE_SIZE); + if (ret < 0) { + pr_info("tpm_get_random failed (%d)\n", ret); + return ret; + } + + /* calculate authorization HMAC value */ + ret = TSS_authhmac(authdata, keyauth, SHA1_DIGEST_SIZE, enonce, + nonceodd, cont, sizeof(uint32_t), &ordinal, + sizeof(uint32_t), &datalen, + bloblen, blob, 0, 0); + if (ret < 0) + return ret; + + /* build the request buffer */ + INIT_BUF(tb); + store16(tb, TPM_TAG_RQU_AUTH1_COMMAND); + store32(tb, TPM_SIGN_SIZE + bloblen); + store32(tb, TPM_ORD_SIGN); + store32(tb, keyhandle); + store32(tb, bloblen); + storebytes(tb, blob, bloblen); + store32(tb, authhandle); + storebytes(tb, nonceodd, TPM_NONCE_SIZE); + store8(tb, cont); + storebytes(tb, authdata, SHA1_DIGEST_SIZE); + + ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); + if (ret < 0) { + pr_info("authhmac failed (%d)\n", ret); + return ret; + } + + datalen = LOAD32(tb->data, TPM_DATA_OFFSET); + + ret = TSS_checkhmac1(tb->data, ordinal, nonceodd, + keyauth, SHA1_DIGEST_SIZE, + sizeof(uint32_t), TPM_DATA_OFFSET, + datalen, TPM_DATA_OFFSET + sizeof(uint32_t), + 0, 0); + if (ret < 0) { + pr_info("TSS_checkhmac1 failed (%d)\n", ret); + return ret; + } + + memcpy(out, tb->data + TPM_DATA_OFFSET + sizeof(uint32_t), + min(datalen, outlen)); + + return datalen; +} +/* + * Maximum buffer size for the BER/DER encoded public key. The public key + * is of the form SEQUENCE { INTEGER n, INTEGER e } where n is a maximum 2048 + * bit key and e is usually 65537 + * The encoding overhead is: + * - max 4 bytes for SEQUENCE + * - max 4 bytes for INTEGER n type/length + * - 257 bytes of n + * - max 2 bytes for INTEGER e type/length + * - 3 bytes of e + */ +#define PUB_KEY_BUF_SIZE (4 + 4 + 257 + 2 + 3) + +/* + * Provide a part of a description of the key for /proc/keys. + */ +static void asym_tpm_describe(const struct key *asymmetric_key, + struct seq_file *m) +{ + struct tpm_key *tk = asymmetric_key->payload.data[asym_crypto]; + + if (!tk) + return; + + seq_printf(m, "TPM1.2/Blob"); +} + +static void asym_tpm_destroy(void *payload0, void *payload3) +{ + struct tpm_key *tk = payload0; + + if (!tk) + return; + + kfree(tk->blob); + tk->blob_len = 0; + + kfree(tk); +} + +/* How many bytes will it take to encode the length */ +static inline uint32_t definite_length(uint32_t len) +{ + if (len <= 127) + return 1; + if (len <= 255) + return 2; + return 3; +} + +static inline uint8_t *encode_tag_length(uint8_t *buf, uint8_t tag, + uint32_t len) +{ + *buf++ = tag; + + if (len <= 127) { + buf[0] = len; + return buf + 1; + } + + if (len <= 255) { + buf[0] = 0x81; + buf[1] = len; + return buf + 2; + } + + buf[0] = 0x82; + put_unaligned_be16(len, buf + 1); + return buf + 3; +} + +static uint32_t derive_pub_key(const void *pub_key, uint32_t len, uint8_t *buf) +{ + uint8_t *cur = buf; + uint32_t n_len = definite_length(len) + 1 + len + 1; + uint32_t e_len = definite_length(3) + 1 + 3; + uint8_t e[3] = { 0x01, 0x00, 0x01 }; + + /* SEQUENCE */ + cur = encode_tag_length(cur, 0x30, n_len + e_len); + /* INTEGER n */ + cur = encode_tag_length(cur, 0x02, len + 1); + cur[0] = 0x00; + memcpy(cur + 1, pub_key, len); + cur += len + 1; + cur = encode_tag_length(cur, 0x02, sizeof(e)); + memcpy(cur, e, sizeof(e)); + cur += sizeof(e); + + return cur - buf; +} + +/* + * Determine the crypto algorithm name. + */ +static int determine_akcipher(const char *encoding, const char *hash_algo, + char alg_name[CRYPTO_MAX_ALG_NAME]) +{ + if (strcmp(encoding, "pkcs1") == 0) { + if (!hash_algo) { + strcpy(alg_name, "pkcs1pad(rsa)"); + return 0; + } + + if (snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "pkcs1pad(rsa,%s)", + hash_algo) >= CRYPTO_MAX_ALG_NAME) + return -EINVAL; + + return 0; + } + + if (strcmp(encoding, "raw") == 0) { + strcpy(alg_name, "rsa"); + return 0; + } + + return -ENOPKG; +} + +/* + * Query information about a key. + */ +static int tpm_key_query(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info) +{ + struct tpm_key *tk = params->key->payload.data[asym_crypto]; + int ret; + char alg_name[CRYPTO_MAX_ALG_NAME]; + struct crypto_akcipher *tfm; + uint8_t der_pub_key[PUB_KEY_BUF_SIZE]; + uint32_t der_pub_key_len; + int len; + + /* TPM only works on private keys, public keys still done in software */ + ret = determine_akcipher(params->encoding, params->hash_algo, alg_name); + if (ret < 0) + return ret; + + tfm = crypto_alloc_akcipher(alg_name, 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + der_pub_key_len = derive_pub_key(tk->pub_key, tk->pub_key_len, + der_pub_key); + + ret = crypto_akcipher_set_pub_key(tfm, der_pub_key, der_pub_key_len); + if (ret < 0) + goto error_free_tfm; + + len = crypto_akcipher_maxsize(tfm); + + info->key_size = tk->key_len; + info->max_data_size = tk->key_len / 8; + info->max_sig_size = len; + info->max_enc_size = len; + info->max_dec_size = tk->key_len / 8; + + info->supported_ops = KEYCTL_SUPPORTS_ENCRYPT | + KEYCTL_SUPPORTS_DECRYPT | + KEYCTL_SUPPORTS_VERIFY | + KEYCTL_SUPPORTS_SIGN; + + ret = 0; +error_free_tfm: + crypto_free_akcipher(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} + +/* + * Encryption operation is performed with the public key. Hence it is done + * in software + */ +static int tpm_key_encrypt(struct tpm_key *tk, + struct kernel_pkey_params *params, + const void *in, void *out) +{ + char alg_name[CRYPTO_MAX_ALG_NAME]; + struct crypto_akcipher *tfm; + struct akcipher_request *req; + struct crypto_wait cwait; + struct scatterlist in_sg, out_sg; + uint8_t der_pub_key[PUB_KEY_BUF_SIZE]; + uint32_t der_pub_key_len; + int ret; + + pr_devel("==>%s()\n", __func__); + + ret = determine_akcipher(params->encoding, params->hash_algo, alg_name); + if (ret < 0) + return ret; + + tfm = crypto_alloc_akcipher(alg_name, 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + der_pub_key_len = derive_pub_key(tk->pub_key, tk->pub_key_len, + der_pub_key); + + ret = crypto_akcipher_set_pub_key(tfm, der_pub_key, der_pub_key_len); + if (ret < 0) + goto error_free_tfm; + + req = akcipher_request_alloc(tfm, GFP_KERNEL); + if (!req) + goto error_free_tfm; + + sg_init_one(&in_sg, in, params->in_len); + sg_init_one(&out_sg, out, params->out_len); + akcipher_request_set_crypt(req, &in_sg, &out_sg, params->in_len, + params->out_len); + crypto_init_wait(&cwait); + akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | + CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, &cwait); + + ret = crypto_akcipher_encrypt(req); + ret = crypto_wait_req(ret, &cwait); + + if (ret == 0) + ret = req->dst_len; + + akcipher_request_free(req); +error_free_tfm: + crypto_free_akcipher(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} + +/* + * Decryption operation is performed with the private key in the TPM. + */ +static int tpm_key_decrypt(struct tpm_key *tk, + struct kernel_pkey_params *params, + const void *in, void *out) +{ + struct tpm_buf *tb; + uint32_t keyhandle; + uint8_t srkauth[SHA1_DIGEST_SIZE]; + uint8_t keyauth[SHA1_DIGEST_SIZE]; + int r; + + pr_devel("==>%s()\n", __func__); + + if (params->hash_algo) + return -ENOPKG; + + if (strcmp(params->encoding, "pkcs1")) + return -ENOPKG; + + tb = kzalloc(sizeof(*tb), GFP_KERNEL); + if (!tb) + return -ENOMEM; + + /* TODO: Handle a non-all zero SRK authorization */ + memset(srkauth, 0, sizeof(srkauth)); + + r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + tk->blob, tk->blob_len, &keyhandle); + if (r < 0) { + pr_devel("loadkey2 failed (%d)\n", r); + goto error; + } + + /* TODO: Handle a non-all zero key authorization */ + memset(keyauth, 0, sizeof(keyauth)); + + r = tpm_unbind(tb, keyhandle, keyauth, + in, params->in_len, out, params->out_len); + if (r < 0) + pr_devel("tpm_unbind failed (%d)\n", r); + + if (tpm_flushspecific(tb, keyhandle) < 0) + pr_devel("flushspecific failed (%d)\n", r); + +error: + kzfree(tb); + pr_devel("<==%s() = %d\n", __func__, r); + return r; +} + +/* + * Hash algorithm OIDs plus ASN.1 DER wrappings [RFC4880 sec 5.2.2]. + */ +static const u8 digest_info_md5[] = { + 0x30, 0x20, 0x30, 0x0c, 0x06, 0x08, + 0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x02, 0x05, /* OID */ + 0x05, 0x00, 0x04, 0x10 +}; + +static const u8 digest_info_sha1[] = { + 0x30, 0x21, 0x30, 0x09, 0x06, 0x05, + 0x2b, 0x0e, 0x03, 0x02, 0x1a, + 0x05, 0x00, 0x04, 0x14 +}; + +static const u8 digest_info_rmd160[] = { + 0x30, 0x21, 0x30, 0x09, 0x06, 0x05, + 0x2b, 0x24, 0x03, 0x02, 0x01, + 0x05, 0x00, 0x04, 0x14 +}; + +static const u8 digest_info_sha224[] = { + 0x30, 0x2d, 0x30, 0x0d, 0x06, 0x09, + 0x60, 0x86, 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x04, + 0x05, 0x00, 0x04, 0x1c +}; + +static const u8 digest_info_sha256[] = { + 0x30, 0x31, 0x30, 0x0d, 0x06, 0x09, + 0x60, 0x86, 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x01, + 0x05, 0x00, 0x04, 0x20 +}; + +static const u8 digest_info_sha384[] = { + 0x30, 0x41, 0x30, 0x0d, 0x06, 0x09, + 0x60, 0x86, 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x02, + 0x05, 0x00, 0x04, 0x30 +}; + +static const u8 digest_info_sha512[] = { + 0x30, 0x51, 0x30, 0x0d, 0x06, 0x09, + 0x60, 0x86, 0x48, 0x01, 0x65, 0x03, 0x04, 0x02, 0x03, + 0x05, 0x00, 0x04, 0x40 +}; + +static const struct asn1_template { + const char *name; + const u8 *data; + size_t size; +} asn1_templates[] = { +#define _(X) { #X, digest_info_##X, sizeof(digest_info_##X) } + _(md5), + _(sha1), + _(rmd160), + _(sha256), + _(sha384), + _(sha512), + _(sha224), + { NULL } +#undef _ +}; + +static const struct asn1_template *lookup_asn1(const char *name) +{ + const struct asn1_template *p; + + for (p = asn1_templates; p->name; p++) + if (strcmp(name, p->name) == 0) + return p; + return NULL; +} + +/* + * Sign operation is performed with the private key in the TPM. + */ +static int tpm_key_sign(struct tpm_key *tk, + struct kernel_pkey_params *params, + const void *in, void *out) +{ + struct tpm_buf *tb; + uint32_t keyhandle; + uint8_t srkauth[SHA1_DIGEST_SIZE]; + uint8_t keyauth[SHA1_DIGEST_SIZE]; + void *asn1_wrapped = NULL; + uint32_t in_len = params->in_len; + int r; + + pr_devel("==>%s()\n", __func__); + + if (strcmp(params->encoding, "pkcs1")) + return -ENOPKG; + + if (params->hash_algo) { + const struct asn1_template *asn1 = + lookup_asn1(params->hash_algo); + + if (!asn1) + return -ENOPKG; + + /* request enough space for the ASN.1 template + input hash */ + asn1_wrapped = kzalloc(in_len + asn1->size, GFP_KERNEL); + if (!asn1_wrapped) + return -ENOMEM; + + /* Copy ASN.1 template, then the input */ + memcpy(asn1_wrapped, asn1->data, asn1->size); + memcpy(asn1_wrapped + asn1->size, in, in_len); + + in = asn1_wrapped; + in_len += asn1->size; + } + + if (in_len > tk->key_len / 8 - 11) { + r = -EOVERFLOW; + goto error_free_asn1_wrapped; + } + + r = -ENOMEM; + tb = kzalloc(sizeof(*tb), GFP_KERNEL); + if (!tb) + goto error_free_asn1_wrapped; + + /* TODO: Handle a non-all zero SRK authorization */ + memset(srkauth, 0, sizeof(srkauth)); + + r = tpm_loadkey2(tb, SRKHANDLE, srkauth, + tk->blob, tk->blob_len, &keyhandle); + if (r < 0) { + pr_devel("loadkey2 failed (%d)\n", r); + goto error_free_tb; + } + + /* TODO: Handle a non-all zero key authorization */ + memset(keyauth, 0, sizeof(keyauth)); + + r = tpm_sign(tb, keyhandle, keyauth, in, in_len, out, params->out_len); + if (r < 0) + pr_devel("tpm_sign failed (%d)\n", r); + + if (tpm_flushspecific(tb, keyhandle) < 0) + pr_devel("flushspecific failed (%d)\n", r); + +error_free_tb: + kzfree(tb); +error_free_asn1_wrapped: + kfree(asn1_wrapped); + pr_devel("<==%s() = %d\n", __func__, r); + return r; +} + +/* + * Do encryption, decryption and signing ops. + */ +static int tpm_key_eds_op(struct kernel_pkey_params *params, + const void *in, void *out) +{ + struct tpm_key *tk = params->key->payload.data[asym_crypto]; + int ret = -EOPNOTSUPP; + + /* Perform the encryption calculation. */ + switch (params->op) { + case kernel_pkey_encrypt: + ret = tpm_key_encrypt(tk, params, in, out); + break; + case kernel_pkey_decrypt: + ret = tpm_key_decrypt(tk, params, in, out); + break; + case kernel_pkey_sign: + ret = tpm_key_sign(tk, params, in, out); + break; + default: + BUG(); + } + + return ret; +} + +/* + * Verify a signature using a public key. + */ +static int tpm_key_verify_signature(const struct key *key, + const struct public_key_signature *sig) +{ + const struct tpm_key *tk = key->payload.data[asym_crypto]; + struct crypto_wait cwait; + struct crypto_akcipher *tfm; + struct akcipher_request *req; + struct scatterlist sig_sg, digest_sg; + char alg_name[CRYPTO_MAX_ALG_NAME]; + uint8_t der_pub_key[PUB_KEY_BUF_SIZE]; + uint32_t der_pub_key_len; + void *output; + unsigned int outlen; + int ret; + + pr_devel("==>%s()\n", __func__); + + BUG_ON(!tk); + BUG_ON(!sig); + BUG_ON(!sig->s); + + if (!sig->digest) + return -ENOPKG; + + ret = determine_akcipher(sig->encoding, sig->hash_algo, alg_name); + if (ret < 0) + return ret; + + tfm = crypto_alloc_akcipher(alg_name, 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + der_pub_key_len = derive_pub_key(tk->pub_key, tk->pub_key_len, + der_pub_key); + + ret = crypto_akcipher_set_pub_key(tfm, der_pub_key, der_pub_key_len); + if (ret < 0) + goto error_free_tfm; + + ret = -ENOMEM; + req = akcipher_request_alloc(tfm, GFP_KERNEL); + if (!req) + goto error_free_tfm; + + ret = -ENOMEM; + outlen = crypto_akcipher_maxsize(tfm); + output = kmalloc(outlen, GFP_KERNEL); + if (!output) + goto error_free_req; + + sg_init_one(&sig_sg, sig->s, sig->s_size); + sg_init_one(&digest_sg, output, outlen); + akcipher_request_set_crypt(req, &sig_sg, &digest_sg, sig->s_size, + outlen); + crypto_init_wait(&cwait); + akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | + CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, &cwait); + + /* Perform the verification calculation. This doesn't actually do the + * verification, but rather calculates the hash expected by the + * signature and returns that to us. + */ + ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait); + if (ret) + goto out_free_output; + + /* Do the actual verification step. */ + if (req->dst_len != sig->digest_size || + memcmp(sig->digest, output, sig->digest_size) != 0) + ret = -EKEYREJECTED; + +out_free_output: + kfree(output); +error_free_req: + akcipher_request_free(req); +error_free_tfm: + crypto_free_akcipher(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + if (WARN_ON_ONCE(ret > 0)) + ret = -EINVAL; + return ret; +} + +/* + * Parse enough information out of TPM_KEY structure: + * TPM_STRUCT_VER -> 4 bytes + * TPM_KEY_USAGE -> 2 bytes + * TPM_KEY_FLAGS -> 4 bytes + * TPM_AUTH_DATA_USAGE -> 1 byte + * TPM_KEY_PARMS -> variable + * UINT32 PCRInfoSize -> 4 bytes + * BYTE* -> PCRInfoSize bytes + * TPM_STORE_PUBKEY + * UINT32 encDataSize; + * BYTE* -> encDataSize; + * + * TPM_KEY_PARMS: + * TPM_ALGORITHM_ID -> 4 bytes + * TPM_ENC_SCHEME -> 2 bytes + * TPM_SIG_SCHEME -> 2 bytes + * UINT32 parmSize -> 4 bytes + * BYTE* -> variable + */ +static int extract_key_parameters(struct tpm_key *tk) +{ + const void *cur = tk->blob; + uint32_t len = tk->blob_len; + const void *pub_key; + uint32_t sz; + uint32_t key_len; + + if (len < 11) + return -EBADMSG; + + /* Ensure this is a legacy key */ + if (get_unaligned_be16(cur + 4) != 0x0015) + return -EBADMSG; + + /* Skip to TPM_KEY_PARMS */ + cur += 11; + len -= 11; + + if (len < 12) + return -EBADMSG; + + /* Make sure this is an RSA key */ + if (get_unaligned_be32(cur) != 0x00000001) + return -EBADMSG; + + /* Make sure this is TPM_ES_RSAESPKCSv15 encoding scheme */ + if (get_unaligned_be16(cur + 4) != 0x0002) + return -EBADMSG; + + /* Make sure this is TPM_SS_RSASSAPKCS1v15_DER signature scheme */ + if (get_unaligned_be16(cur + 6) != 0x0003) + return -EBADMSG; + + sz = get_unaligned_be32(cur + 8); + if (len < sz + 12) + return -EBADMSG; + + /* Move to TPM_RSA_KEY_PARMS */ + len -= 12; + cur += 12; + + /* Grab the RSA key length */ + key_len = get_unaligned_be32(cur); + + switch (key_len) { + case 512: + case 1024: + case 1536: + case 2048: + break; + default: + return -EINVAL; + } + + /* Move just past TPM_KEY_PARMS */ + cur += sz; + len -= sz; + + if (len < 4) + return -EBADMSG; + + sz = get_unaligned_be32(cur); + if (len < 4 + sz) + return -EBADMSG; + + /* Move to TPM_STORE_PUBKEY */ + cur += 4 + sz; + len -= 4 + sz; + + /* Grab the size of the public key, it should jive with the key size */ + sz = get_unaligned_be32(cur); + if (sz > 256) + return -EINVAL; + + pub_key = cur + 4; + + tk->key_len = key_len; + tk->pub_key = pub_key; + tk->pub_key_len = sz; + + return 0; +} + +/* Given the blob, parse it and load it into the TPM */ +struct tpm_key *tpm_key_create(const void *blob, uint32_t blob_len) +{ + int r; + struct tpm_key *tk; + + r = tpm_is_tpm2(NULL); + if (r < 0) + goto error; + + /* We don't support TPM2 yet */ + if (r > 0) { + r = -ENODEV; + goto error; + } + + r = -ENOMEM; + tk = kzalloc(sizeof(struct tpm_key), GFP_KERNEL); + if (!tk) + goto error; + + tk->blob = kmemdup(blob, blob_len, GFP_KERNEL); + if (!tk->blob) + goto error_memdup; + + tk->blob_len = blob_len; + + r = extract_key_parameters(tk); + if (r < 0) + goto error_extract; + + return tk; + +error_extract: + kfree(tk->blob); + tk->blob_len = 0; +error_memdup: + kfree(tk); +error: + return ERR_PTR(r); +} +EXPORT_SYMBOL_GPL(tpm_key_create); + +/* + * TPM-based asymmetric key subtype + */ +struct asymmetric_key_subtype asym_tpm_subtype = { + .owner = THIS_MODULE, + .name = "asym_tpm", + .name_len = sizeof("asym_tpm") - 1, + .describe = asym_tpm_describe, + .destroy = asym_tpm_destroy, + .query = tpm_key_query, + .eds_op = tpm_key_eds_op, + .verify_signature = tpm_key_verify_signature, +}; +EXPORT_SYMBOL_GPL(asym_tpm_subtype); + +MODULE_DESCRIPTION("TPM based asymmetric key subtype"); +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); diff --git a/crypto/asymmetric_keys/asymmetric_keys.h b/crypto/asymmetric_keys/asymmetric_keys.h index ca8e9ac34ce621..7be1ccf4fa9f22 100644 --- a/crypto/asymmetric_keys/asymmetric_keys.h +++ b/crypto/asymmetric_keys/asymmetric_keys.h @@ -16,3 +16,6 @@ extern struct asymmetric_key_id *asymmetric_key_hex_to_key_id(const char *id); extern int __asymmetric_key_hex_to_key_id(const char *id, struct asymmetric_key_id *match_id, size_t hexlen); + +extern int asymmetric_key_eds_op(struct kernel_pkey_params *params, + const void *in, void *out); diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index 26539e9a8bda41..69a0788a7de5d0 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/ctype.h> #include <keys/system_keyring.h> +#include <keys/user-type.h> #include "asymmetric_keys.h" MODULE_LICENSE("GPL"); @@ -538,6 +539,45 @@ out: return ret; } +int asymmetric_key_eds_op(struct kernel_pkey_params *params, + const void *in, void *out) +{ + const struct asymmetric_key_subtype *subtype; + struct key *key = params->key; + int ret; + + pr_devel("==>%s()\n", __func__); + + if (key->type != &key_type_asymmetric) + return -EINVAL; + subtype = asymmetric_key_subtype(key); + if (!subtype || + !key->payload.data[0]) + return -EINVAL; + if (!subtype->eds_op) + return -ENOTSUPP; + + ret = subtype->eds_op(params, in, out); + + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} + +static int asymmetric_key_verify_signature(struct kernel_pkey_params *params, + const void *in, const void *in2) +{ + struct public_key_signature sig = { + .s_size = params->in2_len, + .digest_size = params->in_len, + .encoding = params->encoding, + .hash_algo = params->hash_algo, + .digest = (void *)in, + .s = (void *)in2, + }; + + return verify_signature(params->key, &sig); +} + struct key_type key_type_asymmetric = { .name = "asymmetric", .preparse = asymmetric_key_preparse, @@ -548,6 +588,9 @@ struct key_type key_type_asymmetric = { .destroy = asymmetric_key_destroy, .describe = asymmetric_key_describe, .lookup_restriction = asymmetric_lookup_restriction, + .asym_query = query_asymmetric_key, + .asym_eds_op = asymmetric_key_eds_op, + .asym_verify_signature = asymmetric_key_verify_signature, }; EXPORT_SYMBOL_GPL(key_type_asymmetric); diff --git a/crypto/asymmetric_keys/pkcs7_parser.c b/crypto/asymmetric_keys/pkcs7_parser.c index 0f134162cef4b5..f0d56e1a8b7e2b 100644 --- a/crypto/asymmetric_keys/pkcs7_parser.c +++ b/crypto/asymmetric_keys/pkcs7_parser.c @@ -271,6 +271,7 @@ int pkcs7_sig_note_pkey_algo(void *context, size_t hdrlen, switch (ctx->last_oid) { case OID_rsaEncryption: ctx->sinfo->sig->pkey_algo = "rsa"; + ctx->sinfo->sig->encoding = "pkcs1"; break; default: printk("Unsupported pkey algo: %u\n", ctx->last_oid); diff --git a/crypto/asymmetric_keys/pkcs8.asn1 b/crypto/asymmetric_keys/pkcs8.asn1 new file mode 100644 index 00000000000000..702c41a3c7137a --- /dev/null +++ b/crypto/asymmetric_keys/pkcs8.asn1 @@ -0,0 +1,24 @@ +-- +-- This is the unencrypted variant +-- +PrivateKeyInfo ::= SEQUENCE { + version Version, + privateKeyAlgorithm PrivateKeyAlgorithmIdentifier, + privateKey PrivateKey, + attributes [0] IMPLICIT Attributes OPTIONAL +} + +Version ::= INTEGER ({ pkcs8_note_version }) + +PrivateKeyAlgorithmIdentifier ::= AlgorithmIdentifier ({ pkcs8_note_algo }) + +PrivateKey ::= OCTET STRING ({ pkcs8_note_key }) + +Attributes ::= SET OF Attribute + +Attribute ::= ANY + +AlgorithmIdentifier ::= SEQUENCE { + algorithm OBJECT IDENTIFIER ({ pkcs8_note_OID }), + parameters ANY OPTIONAL +} diff --git a/crypto/asymmetric_keys/pkcs8_parser.c b/crypto/asymmetric_keys/pkcs8_parser.c new file mode 100644 index 00000000000000..5f6a7ecc9765e9 --- /dev/null +++ b/crypto/asymmetric_keys/pkcs8_parser.c @@ -0,0 +1,184 @@ +/* PKCS#8 Private Key parser [RFC 5208]. + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define pr_fmt(fmt) "PKCS8: "fmt +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/oid_registry.h> +#include <keys/asymmetric-subtype.h> +#include <keys/asymmetric-parser.h> +#include <crypto/public_key.h> +#include "pkcs8.asn1.h" + +struct pkcs8_parse_context { + struct public_key *pub; + unsigned long data; /* Start of data */ + enum OID last_oid; /* Last OID encountered */ + enum OID algo_oid; /* Algorithm OID */ + u32 key_size; + const void *key; +}; + +/* + * Note an OID when we find one for later processing when we know how to + * interpret it. + */ +int pkcs8_note_OID(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct pkcs8_parse_context *ctx = context; + + ctx->last_oid = look_up_OID(value, vlen); + if (ctx->last_oid == OID__NR) { + char buffer[50]; + + sprint_oid(value, vlen, buffer, sizeof(buffer)); + pr_info("Unknown OID: [%lu] %s\n", + (unsigned long)value - ctx->data, buffer); + } + return 0; +} + +/* + * Note the version number of the ASN.1 blob. + */ +int pkcs8_note_version(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + if (vlen != 1 || ((const u8 *)value)[0] != 0) { + pr_warn("Unsupported PKCS#8 version\n"); + return -EBADMSG; + } + return 0; +} + +/* + * Note the public algorithm. + */ +int pkcs8_note_algo(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct pkcs8_parse_context *ctx = context; + + if (ctx->last_oid != OID_rsaEncryption) + return -ENOPKG; + + ctx->pub->pkey_algo = "rsa"; + return 0; +} + +/* + * Note the key data of the ASN.1 blob. + */ +int pkcs8_note_key(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct pkcs8_parse_context *ctx = context; + + ctx->key = value; + ctx->key_size = vlen; + return 0; +} + +/* + * Parse a PKCS#8 private key blob. + */ +static struct public_key *pkcs8_parse(const void *data, size_t datalen) +{ + struct pkcs8_parse_context ctx; + struct public_key *pub; + long ret; + + memset(&ctx, 0, sizeof(ctx)); + + ret = -ENOMEM; + ctx.pub = kzalloc(sizeof(struct public_key), GFP_KERNEL); + if (!ctx.pub) + goto error; + + ctx.data = (unsigned long)data; + + /* Attempt to decode the private key */ + ret = asn1_ber_decoder(&pkcs8_decoder, &ctx, data, datalen); + if (ret < 0) + goto error_decode; + + ret = -ENOMEM; + pub = ctx.pub; + pub->key = kmemdup(ctx.key, ctx.key_size, GFP_KERNEL); + if (!pub->key) + goto error_decode; + + pub->keylen = ctx.key_size; + pub->key_is_private = true; + return pub; + +error_decode: + kfree(ctx.pub); +error: + return ERR_PTR(ret); +} + +/* + * Attempt to parse a data blob for a key as a PKCS#8 private key. + */ +static int pkcs8_key_preparse(struct key_preparsed_payload *prep) +{ + struct public_key *pub; + + pub = pkcs8_parse(prep->data, prep->datalen); + if (IS_ERR(pub)) + return PTR_ERR(pub); + + pr_devel("Cert Key Algo: %s\n", pub->pkey_algo); + pub->id_type = "PKCS8"; + + /* We're pinning the module by being linked against it */ + __module_get(public_key_subtype.owner); + prep->payload.data[asym_subtype] = &public_key_subtype; + prep->payload.data[asym_key_ids] = NULL; + prep->payload.data[asym_crypto] = pub; + prep->payload.data[asym_auth] = NULL; + prep->quotalen = 100; + return 0; +} + +static struct asymmetric_key_parser pkcs8_key_parser = { + .owner = THIS_MODULE, + .name = "pkcs8", + .parse = pkcs8_key_preparse, +}; + +/* + * Module stuff + */ +static int __init pkcs8_key_init(void) +{ + return register_asymmetric_key_parser(&pkcs8_key_parser); +} + +static void __exit pkcs8_key_exit(void) +{ + unregister_asymmetric_key_parser(&pkcs8_key_parser); +} + +module_init(pkcs8_key_init); +module_exit(pkcs8_key_exit); + +MODULE_DESCRIPTION("PKCS#8 certificate parser"); +MODULE_LICENSE("GPL"); diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index e929fe1e4106c7..f5d85b47fcc6d2 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -60,6 +60,165 @@ static void public_key_destroy(void *payload0, void *payload3) } /* + * Determine the crypto algorithm name. + */ +static +int software_key_determine_akcipher(const char *encoding, + const char *hash_algo, + const struct public_key *pkey, + char alg_name[CRYPTO_MAX_ALG_NAME]) +{ + int n; + + if (strcmp(encoding, "pkcs1") == 0) { + /* The data wangled by the RSA algorithm is typically padded + * and encoded in some manner, such as EMSA-PKCS1-1_5 [RFC3447 + * sec 8.2]. + */ + if (!hash_algo) + n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, + "pkcs1pad(%s)", + pkey->pkey_algo); + else + n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, + "pkcs1pad(%s,%s)", + pkey->pkey_algo, hash_algo); + return n >= CRYPTO_MAX_ALG_NAME ? -EINVAL : 0; + } + + if (strcmp(encoding, "raw") == 0) { + strcpy(alg_name, pkey->pkey_algo); + return 0; + } + + return -ENOPKG; +} + +/* + * Query information about a key. + */ +static int software_key_query(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info) +{ + struct crypto_akcipher *tfm; + struct public_key *pkey = params->key->payload.data[asym_crypto]; + char alg_name[CRYPTO_MAX_ALG_NAME]; + int ret, len; + + ret = software_key_determine_akcipher(params->encoding, + params->hash_algo, + pkey, alg_name); + if (ret < 0) + return ret; + + tfm = crypto_alloc_akcipher(alg_name, 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + if (pkey->key_is_private) + ret = crypto_akcipher_set_priv_key(tfm, + pkey->key, pkey->keylen); + else + ret = crypto_akcipher_set_pub_key(tfm, + pkey->key, pkey->keylen); + if (ret < 0) + goto error_free_tfm; + + len = crypto_akcipher_maxsize(tfm); + info->key_size = len * 8; + info->max_data_size = len; + info->max_sig_size = len; + info->max_enc_size = len; + info->max_dec_size = len; + info->supported_ops = (KEYCTL_SUPPORTS_ENCRYPT | + KEYCTL_SUPPORTS_VERIFY); + if (pkey->key_is_private) + info->supported_ops |= (KEYCTL_SUPPORTS_DECRYPT | + KEYCTL_SUPPORTS_SIGN); + ret = 0; + +error_free_tfm: + crypto_free_akcipher(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} + +/* + * Do encryption, decryption and signing ops. + */ +static int software_key_eds_op(struct kernel_pkey_params *params, + const void *in, void *out) +{ + const struct public_key *pkey = params->key->payload.data[asym_crypto]; + struct akcipher_request *req; + struct crypto_akcipher *tfm; + struct crypto_wait cwait; + struct scatterlist in_sg, out_sg; + char alg_name[CRYPTO_MAX_ALG_NAME]; + int ret; + + pr_devel("==>%s()\n", __func__); + + ret = software_key_determine_akcipher(params->encoding, + params->hash_algo, + pkey, alg_name); + if (ret < 0) + return ret; + + tfm = crypto_alloc_akcipher(alg_name, 0, 0); + if (IS_ERR(tfm)) + return PTR_ERR(tfm); + + req = akcipher_request_alloc(tfm, GFP_KERNEL); + if (!req) + goto error_free_tfm; + + if (pkey->key_is_private) + ret = crypto_akcipher_set_priv_key(tfm, + pkey->key, pkey->keylen); + else + ret = crypto_akcipher_set_pub_key(tfm, + pkey->key, pkey->keylen); + if (ret) + goto error_free_req; + + sg_init_one(&in_sg, in, params->in_len); + sg_init_one(&out_sg, out, params->out_len); + akcipher_request_set_crypt(req, &in_sg, &out_sg, params->in_len, + params->out_len); + crypto_init_wait(&cwait); + akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | + CRYPTO_TFM_REQ_MAY_SLEEP, + crypto_req_done, &cwait); + + /* Perform the encryption calculation. */ + switch (params->op) { + case kernel_pkey_encrypt: + ret = crypto_akcipher_encrypt(req); + break; + case kernel_pkey_decrypt: + ret = crypto_akcipher_decrypt(req); + break; + case kernel_pkey_sign: + ret = crypto_akcipher_sign(req); + break; + default: + BUG(); + } + + ret = crypto_wait_req(ret, &cwait); + if (ret == 0) + ret = req->dst_len; + +error_free_req: + akcipher_request_free(req); +error_free_tfm: + crypto_free_akcipher(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} + +/* * Verify a signature using a public key. */ int public_key_verify_signature(const struct public_key *pkey, @@ -69,8 +228,7 @@ int public_key_verify_signature(const struct public_key *pkey, struct crypto_akcipher *tfm; struct akcipher_request *req; struct scatterlist sig_sg, digest_sg; - const char *alg_name; - char alg_name_buf[CRYPTO_MAX_ALG_NAME]; + char alg_name[CRYPTO_MAX_ALG_NAME]; void *output; unsigned int outlen; int ret; @@ -81,21 +239,11 @@ int public_key_verify_signature(const struct public_key *pkey, BUG_ON(!sig); BUG_ON(!sig->s); - if (!sig->digest) - return -ENOPKG; - - alg_name = sig->pkey_algo; - if (strcmp(sig->pkey_algo, "rsa") == 0) { - /* The data wangled by the RSA algorithm is typically padded - * and encoded in some manner, such as EMSA-PKCS1-1_5 [RFC3447 - * sec 8.2]. - */ - if (snprintf(alg_name_buf, CRYPTO_MAX_ALG_NAME, - "pkcs1pad(rsa,%s)", sig->hash_algo - ) >= CRYPTO_MAX_ALG_NAME) - return -EINVAL; - alg_name = alg_name_buf; - } + ret = software_key_determine_akcipher(sig->encoding, + sig->hash_algo, + pkey, alg_name); + if (ret < 0) + return ret; tfm = crypto_alloc_akcipher(alg_name, 0, 0); if (IS_ERR(tfm)) @@ -106,7 +254,12 @@ int public_key_verify_signature(const struct public_key *pkey, if (!req) goto error_free_tfm; - ret = crypto_akcipher_set_pub_key(tfm, pkey->key, pkey->keylen); + if (pkey->key_is_private) + ret = crypto_akcipher_set_priv_key(tfm, + pkey->key, pkey->keylen); + else + ret = crypto_akcipher_set_pub_key(tfm, + pkey->key, pkey->keylen); if (ret) goto error_free_req; @@ -167,6 +320,8 @@ struct asymmetric_key_subtype public_key_subtype = { .name_len = sizeof("public_key") - 1, .describe = public_key_describe, .destroy = public_key_destroy, + .query = software_key_query, + .eds_op = software_key_eds_op, .verify_signature = public_key_verify_signature_2, }; EXPORT_SYMBOL_GPL(public_key_subtype); diff --git a/crypto/asymmetric_keys/signature.c b/crypto/asymmetric_keys/signature.c index 28198314bc39f4..ad95a58c664275 100644 --- a/crypto/asymmetric_keys/signature.c +++ b/crypto/asymmetric_keys/signature.c @@ -16,7 +16,9 @@ #include <linux/export.h> #include <linux/err.h> #include <linux/slab.h> +#include <linux/keyctl.h> #include <crypto/public_key.h> +#include <keys/user-type.h> #include "asymmetric_keys.h" /* @@ -37,6 +39,99 @@ void public_key_signature_free(struct public_key_signature *sig) EXPORT_SYMBOL_GPL(public_key_signature_free); /** + * query_asymmetric_key - Get information about an aymmetric key. + * @params: Various parameters. + * @info: Where to put the information. + */ +int query_asymmetric_key(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info) +{ + const struct asymmetric_key_subtype *subtype; + struct key *key = params->key; + int ret; + + pr_devel("==>%s()\n", __func__); + + if (key->type != &key_type_asymmetric) + return -EINVAL; + subtype = asymmetric_key_subtype(key); + if (!subtype || + !key->payload.data[0]) + return -EINVAL; + if (!subtype->query) + return -ENOTSUPP; + + ret = subtype->query(params, info); + + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} +EXPORT_SYMBOL_GPL(query_asymmetric_key); + +/** + * encrypt_blob - Encrypt data using an asymmetric key + * @params: Various parameters + * @data: Data blob to be encrypted, length params->data_len + * @enc: Encrypted data buffer, length params->enc_len + * + * Encrypt the specified data blob using the private key specified by + * params->key. The encrypted data is wrapped in an encoding if + * params->encoding is specified (eg. "pkcs1"). + * + * Returns the length of the data placed in the encrypted data buffer or an + * error. + */ +int encrypt_blob(struct kernel_pkey_params *params, + const void *data, void *enc) +{ + params->op = kernel_pkey_encrypt; + return asymmetric_key_eds_op(params, data, enc); +} +EXPORT_SYMBOL_GPL(encrypt_blob); + +/** + * decrypt_blob - Decrypt data using an asymmetric key + * @params: Various parameters + * @enc: Encrypted data to be decrypted, length params->enc_len + * @data: Decrypted data buffer, length params->data_len + * + * Decrypt the specified data blob using the private key specified by + * params->key. The decrypted data is wrapped in an encoding if + * params->encoding is specified (eg. "pkcs1"). + * + * Returns the length of the data placed in the decrypted data buffer or an + * error. + */ +int decrypt_blob(struct kernel_pkey_params *params, + const void *enc, void *data) +{ + params->op = kernel_pkey_decrypt; + return asymmetric_key_eds_op(params, enc, data); +} +EXPORT_SYMBOL_GPL(decrypt_blob); + +/** + * create_signature - Sign some data using an asymmetric key + * @params: Various parameters + * @data: Data blob to be signed, length params->data_len + * @enc: Signature buffer, length params->enc_len + * + * Sign the specified data blob using the private key specified by params->key. + * The signature is wrapped in an encoding if params->encoding is specified + * (eg. "pkcs1"). If the encoding needs to know the digest type, this can be + * passed through params->hash_algo (eg. "sha1"). + * + * Returns the length of the data placed in the signature buffer or an error. + */ +int create_signature(struct kernel_pkey_params *params, + const void *data, void *enc) +{ + params->op = kernel_pkey_sign; + return asymmetric_key_eds_op(params, data, enc); +} +EXPORT_SYMBOL_GPL(create_signature); + +/** * verify_signature - Initiate the use of an asymmetric key to verify a signature * @key: The asymmetric key to verify against * @sig: The signature to check diff --git a/crypto/asymmetric_keys/tpm.asn1 b/crypto/asymmetric_keys/tpm.asn1 new file mode 100644 index 00000000000000..d7f194232f30ac --- /dev/null +++ b/crypto/asymmetric_keys/tpm.asn1 @@ -0,0 +1,5 @@ +-- +-- Unencryted TPM Blob. For details of the format, see: +-- http://david.woodhou.se/draft-woodhouse-cert-best-practice.html#I-D.mavrogiannopoulos-tpmuri +-- +PrivateKeyInfo ::= OCTET STRING ({ tpm_note_key }) diff --git a/crypto/asymmetric_keys/tpm_parser.c b/crypto/asymmetric_keys/tpm_parser.c new file mode 100644 index 00000000000000..96405d8dcd98dd --- /dev/null +++ b/crypto/asymmetric_keys/tpm_parser.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) "TPM-PARSER: "fmt +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/export.h> +#include <linux/slab.h> +#include <linux/err.h> +#include <keys/asymmetric-subtype.h> +#include <keys/asymmetric-parser.h> +#include <crypto/asym_tpm_subtype.h> +#include "tpm.asn1.h" + +struct tpm_parse_context { + const void *blob; + u32 blob_len; +}; + +/* + * Note the key data of the ASN.1 blob. + */ +int tpm_note_key(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct tpm_parse_context *ctx = context; + + ctx->blob = value; + ctx->blob_len = vlen; + + return 0; +} + +/* + * Parse a TPM-encrypted private key blob. + */ +static struct tpm_key *tpm_parse(const void *data, size_t datalen) +{ + struct tpm_parse_context ctx; + long ret; + + memset(&ctx, 0, sizeof(ctx)); + + /* Attempt to decode the private key */ + ret = asn1_ber_decoder(&tpm_decoder, &ctx, data, datalen); + if (ret < 0) + goto error; + + return tpm_key_create(ctx.blob, ctx.blob_len); + +error: + return ERR_PTR(ret); +} +/* + * Attempt to parse a data blob for a key as a TPM private key blob. + */ +static int tpm_key_preparse(struct key_preparsed_payload *prep) +{ + struct tpm_key *tk; + + /* + * TPM 1.2 keys are max 2048 bits long, so assume the blob is no + * more than 4x that + */ + if (prep->datalen > 256 * 4) + return -EMSGSIZE; + + tk = tpm_parse(prep->data, prep->datalen); + + if (IS_ERR(tk)) + return PTR_ERR(tk); + + /* We're pinning the module by being linked against it */ + __module_get(asym_tpm_subtype.owner); + prep->payload.data[asym_subtype] = &asym_tpm_subtype; + prep->payload.data[asym_key_ids] = NULL; + prep->payload.data[asym_crypto] = tk; + prep->payload.data[asym_auth] = NULL; + prep->quotalen = 100; + return 0; +} + +static struct asymmetric_key_parser tpm_key_parser = { + .owner = THIS_MODULE, + .name = "tpm_parser", + .parse = tpm_key_preparse, +}; + +static int __init tpm_key_init(void) +{ + return register_asymmetric_key_parser(&tpm_key_parser); +} + +static void __exit tpm_key_exit(void) +{ + unregister_asymmetric_key_parser(&tpm_key_parser); +} + +module_init(tpm_key_init); +module_exit(tpm_key_exit); + +MODULE_DESCRIPTION("TPM private key-blob parser"); +MODULE_LICENSE("GPL v2"); diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index b6cabac4b62ba6..991f4d735a4ef1 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -199,35 +199,32 @@ int x509_note_pkey_algo(void *context, size_t hdrlen, case OID_md4WithRSAEncryption: ctx->cert->sig->hash_algo = "md4"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; case OID_sha1WithRSAEncryption: ctx->cert->sig->hash_algo = "sha1"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; case OID_sha256WithRSAEncryption: ctx->cert->sig->hash_algo = "sha256"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; case OID_sha384WithRSAEncryption: ctx->cert->sig->hash_algo = "sha384"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; case OID_sha512WithRSAEncryption: ctx->cert->sig->hash_algo = "sha512"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; case OID_sha224WithRSAEncryption: ctx->cert->sig->hash_algo = "sha224"; - ctx->cert->sig->pkey_algo = "rsa"; - break; + goto rsa_pkcs1; } +rsa_pkcs1: + ctx->cert->sig->pkey_algo = "rsa"; + ctx->cert->sig->encoding = "pkcs1"; ctx->algo_oid = ctx->last_oid; return 0; } diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c index 812476e4682138..cfc04e15fd9750 100644 --- a/crypto/rsa-pkcs1pad.c +++ b/crypto/rsa-pkcs1pad.c @@ -392,7 +392,8 @@ static int pkcs1pad_sign(struct akcipher_request *req) if (!ctx->key_size) return -EINVAL; - digest_size = digest_info->size; + if (digest_info) + digest_size = digest_info->size; if (req->src_len + digest_size > ctx->key_size - 11) return -EOVERFLOW; @@ -412,8 +413,9 @@ static int pkcs1pad_sign(struct akcipher_request *req) memset(req_ctx->in_buf + 1, 0xff, ps_end - 1); req_ctx->in_buf[ps_end] = 0x00; - memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data, - digest_info->size); + if (digest_info) + memcpy(req_ctx->in_buf + ps_end + 1, digest_info->data, + digest_info->size); pkcs1pad_sg_set_buf(req_ctx->in_sg, req_ctx->in_buf, ctx->key_size - 1 - req->src_len, req->src); @@ -475,10 +477,13 @@ static int pkcs1pad_verify_complete(struct akcipher_request *req, int err) goto done; pos++; - if (crypto_memneq(out_buf + pos, digest_info->data, digest_info->size)) - goto done; + if (digest_info) { + if (crypto_memneq(out_buf + pos, digest_info->data, + digest_info->size)) + goto done; - pos += digest_info->size; + pos += digest_info->size; + } err = 0; @@ -608,11 +613,14 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb) hash_name = crypto_attr_alg_name(tb[2]); if (IS_ERR(hash_name)) - return PTR_ERR(hash_name); + hash_name = NULL; - digest_info = rsa_lookup_asn1(hash_name); - if (!digest_info) - return -EINVAL; + if (hash_name) { + digest_info = rsa_lookup_asn1(hash_name); + if (!digest_info) + return -EINVAL; + } else + digest_info = NULL; inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL); if (!inst) @@ -632,14 +640,29 @@ static int pkcs1pad_create(struct crypto_template *tmpl, struct rtattr **tb) err = -ENAMETOOLONG; - if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, - "pkcs1pad(%s,%s)", rsa_alg->base.cra_name, hash_name) >= - CRYPTO_MAX_ALG_NAME || - snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME, - "pkcs1pad(%s,%s)", - rsa_alg->base.cra_driver_name, hash_name) >= - CRYPTO_MAX_ALG_NAME) - goto out_drop_alg; + if (!hash_name) { + if (snprintf(inst->alg.base.cra_name, + CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)", + rsa_alg->base.cra_name) >= CRYPTO_MAX_ALG_NAME) + goto out_drop_alg; + + if (snprintf(inst->alg.base.cra_driver_name, + CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)", + rsa_alg->base.cra_driver_name) >= + CRYPTO_MAX_ALG_NAME) + goto out_drop_alg; + } else { + if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME, + "pkcs1pad(%s,%s)", rsa_alg->base.cra_name, + hash_name) >= CRYPTO_MAX_ALG_NAME) + goto out_drop_alg; + + if (snprintf(inst->alg.base.cra_driver_name, + CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)", + rsa_alg->base.cra_driver_name, + hash_name) >= CRYPTO_MAX_ALG_NAME) + goto out_drop_alg; + } inst->alg.base.cra_flags = rsa_alg->base.cra_flags & CRYPTO_ALG_ASYNC; inst->alg.base.cra_priority = rsa_alg->base.cra_priority; diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index a7c2673ffd36e8..824ae985ad93be 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -126,6 +126,7 @@ int acpi_device_get_power(struct acpi_device *device, int *state) return 0; } +EXPORT_SYMBOL(acpi_device_get_power); static int acpi_dev_pm_explicit_set(struct acpi_device *adev, int state) { diff --git a/drivers/auxdisplay/panel.c b/drivers/auxdisplay/panel.c index 3b25a643058c9d..21b9b2f2470a26 100644 --- a/drivers/auxdisplay/panel.c +++ b/drivers/auxdisplay/panel.c @@ -155,10 +155,9 @@ struct logical_input { int release_data; } std; struct { /* valid when type == INPUT_TYPE_KBD */ - /* strings can be non null-terminated */ - char press_str[sizeof(void *) + sizeof(int)]; - char repeat_str[sizeof(void *) + sizeof(int)]; - char release_str[sizeof(void *) + sizeof(int)]; + char press_str[sizeof(void *) + sizeof(int)] __nonstring; + char repeat_str[sizeof(void *) + sizeof(int)] __nonstring; + char release_str[sizeof(void *) + sizeof(int)] __nonstring; } kbd; } u; }; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index df8103dd40ac2d..c18586fccb6f2b 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -396,15 +396,14 @@ static struct brd_device *brd_alloc(int i) disk->first_minor = i * max_part; disk->fops = &brd_fops; disk->private_data = brd; - disk->queue = brd->brd_queue; disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "ram%d", i); set_capacity(disk, rd_size * 2); - disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; + brd->brd_queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; /* Tell the block layer that this is not a rotational device */ - blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); - blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); + blk_queue_flag_set(QUEUE_FLAG_NONROT, brd->brd_queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, brd->brd_queue); return brd; @@ -436,6 +435,7 @@ static struct brd_device *brd_init_one(int i, bool *new) brd = brd_alloc(i); if (brd) { + brd->brd_disk->queue = brd->brd_queue; add_disk(brd->brd_disk); list_add_tail(&brd->brd_list, &brd_devices); } @@ -503,8 +503,14 @@ static int __init brd_init(void) /* point of no return */ - list_for_each_entry(brd, &brd_devices, brd_list) + list_for_each_entry(brd, &brd_devices, brd_list) { + /* + * associate with queue just before adding disk for + * avoiding to mess up failure path + */ + brd->brd_disk->queue = brd->brd_queue; add_disk(brd->brd_disk); + } blk_register_region(MKDEV(RAMDISK_MAJOR, 0), 1UL << MINORBITS, THIS_MODULE, brd_probe, NULL, NULL); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 55fd104f1ed4b9..fa8204214ac027 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1856,7 +1856,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, /* THINK if (signal_pending) return ... ? */ - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size); if (sock == connection->data.socket) { rcu_read_lock(); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index fc67fd853375c0..61c392752fe4bb 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -516,7 +516,7 @@ static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flag struct msghdr msg = { .msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL) }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); return sock_recvmsg(sock, &msg, msg.msg_flags); } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index abad6d15f95634..cb0cc868507620 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -77,7 +77,6 @@ #include <linux/falloc.h> #include <linux/uio.h> #include <linux/ioprio.h> -#include <linux/blk-cgroup.h> #include "loop.h" @@ -269,7 +268,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -347,7 +346,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, ssize_t len; rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len); + iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; @@ -388,7 +387,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, b.bv_offset = 0; b.bv_len = bvec.bv_len; - iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len); + iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; @@ -555,8 +554,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, ITER_BVEC | rw, bvec, - segments, blk_rq_bytes(rq)); + iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; @@ -1761,8 +1759,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP - if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { - cmd->css = &bio_blkcg(rq->bio)->css; + if (cmd->use_aio && rq->bio && rq->bio->bi_css) { + cmd->css = rq->bio->bi_css; css_get(cmd->css); } else #endif diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index dfc8de6ce52548..a7daa8acbab3a5 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1942,8 +1942,8 @@ static int exec_drive_taskfile(struct driver_data *dd, dev_warn(&dd->pdev->dev, "data movement but " "sect_count is 0\n"); - err = -EINVAL; - goto abort; + err = -EINVAL; + goto abort; } } } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 14a51254c3db7f..4d4d6129ff6627 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -473,7 +473,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); switch (req_op(req)) { case REQ_OP_DISCARD: @@ -564,8 +564,7 @@ send_pages: dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", req, bvec.bv_len); - iov_iter_bvec(&from, ITER_BVEC | WRITE, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&from, WRITE, &bvec, 1, bvec.bv_len); if (skip) { if (skip >= iov_iter_count(&from)) { skip -= iov_iter_count(&from); @@ -624,7 +623,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) int ret = 0; reply.magic = 0; - iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); + iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply)); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { if (!nbd_disconnected(config)) @@ -678,8 +677,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { - iov_iter_bvec(&to, ITER_BVEC | READ, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", @@ -1073,7 +1071,7 @@ static void send_disconnects(struct nbd_device *nbd) for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret <= 0) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index df9467eef32a0e..41c9ccdd20d656 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -234,6 +234,7 @@ config EDAC_SKX depends on PCI && X86_64 && X86_MCE_INTEL && PCI_MMCONFIG depends on ACPI_NFIT || !ACPI_NFIT # if ACPI_NFIT=m, EDAC_SKX can't be y select DMI + select ACPI_ADXL if ACPI help Support for error detection and correction the Intel Skylake server Integrated Memory Controllers. If your diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c index dd209e0dd9abb2..a99ea61dad321d 100644 --- a/drivers/edac/skx_edac.c +++ b/drivers/edac/skx_edac.c @@ -26,6 +26,7 @@ #include <linux/bitmap.h> #include <linux/math64.h> #include <linux/mod_devicetable.h> +#include <linux/adxl.h> #include <acpi/nfit.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> @@ -35,6 +36,7 @@ #include "edac_module.h" #define EDAC_MOD_STR "skx_edac" +#define MSG_SIZE 1024 /* * Debug macros @@ -54,6 +56,29 @@ static LIST_HEAD(skx_edac_list); static u64 skx_tolm, skx_tohm; +static char *skx_msg; +static unsigned int nvdimm_count; + +enum { + INDEX_SOCKET, + INDEX_MEMCTRL, + INDEX_CHANNEL, + INDEX_DIMM, + INDEX_MAX +}; + +static const char * const component_names[] = { + [INDEX_SOCKET] = "ProcessorSocketId", + [INDEX_MEMCTRL] = "MemoryControllerId", + [INDEX_CHANNEL] = "ChannelId", + [INDEX_DIMM] = "DimmSlotId", +}; + +static int component_indices[ARRAY_SIZE(component_names)]; +static int adxl_component_count; +static const char * const *adxl_component_names; +static u64 *adxl_values; +static char *adxl_msg; #define NUM_IMC 2 /* memory controllers per socket */ #define NUM_CHANNELS 3 /* channels per memory controller */ @@ -393,6 +418,8 @@ static int get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, u16 flags; u64 size = 0; + nvdimm_count++; + dev_handle = ACPI_NFIT_BUILD_DEVICE_HANDLE(dimmno, chan, imc->lmc, imc->src_id, 0); @@ -941,12 +968,46 @@ static void teardown_skx_debug(void) } #endif /*CONFIG_EDAC_DEBUG*/ +static bool skx_adxl_decode(struct decoded_addr *res) + +{ + int i, len = 0; + + if (res->addr >= skx_tohm || (res->addr >= skx_tolm && + res->addr < BIT_ULL(32))) { + edac_dbg(0, "Address 0x%llx out of range\n", res->addr); + return false; + } + + if (adxl_decode(res->addr, adxl_values)) { + edac_dbg(0, "Failed to decode 0x%llx\n", res->addr); + return false; + } + + res->socket = (int)adxl_values[component_indices[INDEX_SOCKET]]; + res->imc = (int)adxl_values[component_indices[INDEX_MEMCTRL]]; + res->channel = (int)adxl_values[component_indices[INDEX_CHANNEL]]; + res->dimm = (int)adxl_values[component_indices[INDEX_DIMM]]; + + for (i = 0; i < adxl_component_count; i++) { + if (adxl_values[i] == ~0x0ull) + continue; + + len += snprintf(adxl_msg + len, MSG_SIZE - len, " %s:0x%llx", + adxl_component_names[i], adxl_values[i]); + if (MSG_SIZE - len <= 0) + break; + } + + return true; +} + static void skx_mce_output_error(struct mem_ctl_info *mci, const struct mce *m, struct decoded_addr *res) { enum hw_event_mc_err_type tp_event; - char *type, *optype, msg[256]; + char *type, *optype; bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0); bool overflow = GET_BITFIELD(m->status, 62, 62); bool uncorrected_error = GET_BITFIELD(m->status, 61, 61); @@ -1007,22 +1068,47 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, break; } } + if (adxl_component_count) { + snprintf(skx_msg, MSG_SIZE, "%s%s err_code:%04x:%04x %s", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, adxl_msg); + } else { + snprintf(skx_msg, MSG_SIZE, + "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, + res->socket, res->imc, res->rank, + res->bank_group, res->bank_address, res->row, res->column); + } - snprintf(msg, sizeof(msg), - "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", - overflow ? " OVERFLOW" : "", - (uncorrected_error && recoverable) ? " recoverable" : "", - mscod, errcode, - res->socket, res->imc, res->rank, - res->bank_group, res->bank_address, res->row, res->column); - - edac_dbg(0, "%s\n", msg); + edac_dbg(0, "%s\n", skx_msg); /* Call the helper to output message */ edac_mc_handle_error(tp_event, mci, core_err_cnt, m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, res->channel, res->dimm, -1, - optype, msg); + optype, skx_msg); +} + +static struct mem_ctl_info *get_mci(int src_id, int lmc) +{ + struct skx_dev *d; + + if (lmc > NUM_IMC - 1) { + skx_printk(KERN_ERR, "Bad lmc %d\n", lmc); + return NULL; + } + + list_for_each_entry(d, &skx_edac_list, list) { + if (d->imc[0].src_id == src_id) + return d->imc[lmc].mci; + } + + skx_printk(KERN_ERR, "No mci for src_id %d lmc %d\n", src_id, lmc); + + return NULL; } static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, @@ -1040,10 +1126,23 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV)) return NOTIFY_DONE; + memset(&res, 0, sizeof(res)); res.addr = mce->addr; - if (!skx_decode(&res)) + + if (adxl_component_count) { + if (!skx_adxl_decode(&res)) + return NOTIFY_DONE; + + mci = get_mci(res.socket, res.imc); + } else { + if (!skx_decode(&res)) + return NOTIFY_DONE; + + mci = res.dev->imc[res.imc].mci; + } + + if (!mci) return NOTIFY_DONE; - mci = res.dev->imc[res.imc].mci; if (mce->mcgstatus & MCG_STATUS_MCIP) type = "Exception"; @@ -1094,6 +1193,62 @@ static void skx_remove(void) } } +static void __init skx_adxl_get(void) +{ + const char * const *names; + int i, j; + + names = adxl_get_component_names(); + if (!names) { + skx_printk(KERN_NOTICE, "No firmware support for address translation."); + skx_printk(KERN_CONT, " Only decoding DDR4 address!\n"); + return; + } + + for (i = 0; i < INDEX_MAX; i++) { + for (j = 0; names[j]; j++) { + if (!strcmp(component_names[i], names[j])) { + component_indices[i] = j; + break; + } + } + + if (!names[j]) + goto err; + } + + adxl_component_names = names; + while (*names++) + adxl_component_count++; + + adxl_values = kcalloc(adxl_component_count, sizeof(*adxl_values), + GFP_KERNEL); + if (!adxl_values) { + adxl_component_count = 0; + return; + } + + adxl_msg = kzalloc(MSG_SIZE, GFP_KERNEL); + if (!adxl_msg) { + adxl_component_count = 0; + kfree(adxl_values); + } + + return; +err: + skx_printk(KERN_ERR, "'%s' is not matched from DSM parameters: ", + component_names[i]); + for (j = 0; names[j]; j++) + skx_printk(KERN_CONT, "%s ", names[j]); + skx_printk(KERN_CONT, "\n"); +} + +static void __exit skx_adxl_put(void) +{ + kfree(adxl_values); + kfree(adxl_msg); +} + /* * skx_init: * make sure we are running on the correct cpu model @@ -1158,6 +1313,15 @@ static int __init skx_init(void) } } + skx_msg = kzalloc(MSG_SIZE, GFP_KERNEL); + if (!skx_msg) { + rc = -ENOMEM; + goto fail; + } + + if (nvdimm_count) + skx_adxl_get(); + /* Ensure that the OPSTATE is set correctly for POLL or NMI */ opstate_init(); @@ -1176,6 +1340,9 @@ static void __exit skx_exit(void) edac_dbg(2, "\n"); mce_unregister_decode_chain(&skx_mce_dec); skx_remove(); + if (nvdimm_count) + skx_adxl_put(); + kfree(skx_msg); teardown_skx_debug(); } diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 7670e8dda82951..7273e5082b4175 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -145,34 +145,6 @@ config EFI_PCDP See DIG64_HCDPv20_042804.pdf available from <http://www.dig64.org/specifications/> -config DELL_RBU - tristate "BIOS update support for DELL systems via sysfs" - depends on X86 - select FW_LOADER - select FW_LOADER_USER_HELPER - help - Say m if you want to have the option of updating the BIOS for your - DELL system. Note you need a Dell OpenManage or Dell Update package (DUP) - supporting application to communicate with the BIOS regarding the new - image for the image update to take effect. - See <file:Documentation/dell_rbu.txt> for more details on the driver. - -config DCDBAS - tristate "Dell Systems Management Base Driver" - depends on X86 - help - The Dell Systems Management Base Driver provides a sysfs interface - for systems management software to perform System Management - Interrupts (SMIs) and Host Control Actions (system power cycle or - power off after OS shutdown) on certain Dell systems. - - See <file:Documentation/dcdbas.txt> for more details on the driver - and the Dell systems on which Dell systems management software makes - use of this driver. - - Say Y or M here to enable the driver for use by Dell systems - management software such as Dell OpenManage. - config DMIID bool "Export DMI identification via sysfs to userspace" depends on DMI diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 13660a9514379e..3158dffd9914e6 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -11,8 +11,6 @@ obj-$(CONFIG_DMI) += dmi_scan.o obj-$(CONFIG_DMI_SYSFS) += dmi-sysfs.o obj-$(CONFIG_EDD) += edd.o obj-$(CONFIG_EFI_PCDP) += pcdp.o -obj-$(CONFIG_DELL_RBU) += dell_rbu.o -obj-$(CONFIG_DCDBAS) += dcdbas.o obj-$(CONFIG_DMIID) += dmi-id.o obj-$(CONFIG_ISCSI_IBFT_FIND) += iscsi_ibft_find.o obj-$(CONFIG_ISCSI_IBFT) += iscsi_ibft.o diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c index ae861342626e35..d92f5b87c251e1 100644 --- a/drivers/fsi/fsi-sbefifo.c +++ b/drivers/fsi/fsi-sbefifo.c @@ -638,7 +638,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo) } ffdc_iov.iov_base = ffdc; ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE; - iov_iter_kvec(&ffdc_iter, WRITE | ITER_KVEC, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); + iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); cmd[0] = cpu_to_be32(2); cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC); rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter); @@ -735,7 +735,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, rbytes = (*resp_len) * sizeof(__be32); resp_iov.iov_base = response; resp_iov.iov_len = rbytes; - iov_iter_kvec(&resp_iter, WRITE | ITER_KVEC, &resp_iov, 1, rbytes); + iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes); /* Perform the command */ mutex_lock(&sbefifo->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c index 297a5490ad8c0b..0a4fba196b843e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c @@ -135,7 +135,8 @@ static int acp_poweroff(struct generic_pm_domain *genpd) * 2. power off the acp tiles * 3. check and enter ulv state */ - if (adev->powerplay.pp_funcs->set_powergating_by_smu) + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->set_powergating_by_smu) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, true); } return 0; @@ -517,7 +518,8 @@ static int acp_set_powergating_state(void *handle, struct amdgpu_device *adev = (struct amdgpu_device *)handle; bool enable = state == AMD_PG_STATE_GATE ? true : false; - if (adev->powerplay.pp_funcs->set_powergating_by_smu) + if (adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->set_powergating_by_smu) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_ACP, enable); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 1e4dd09a507266..30bc345d6fdf0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1493,8 +1493,6 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) } adev->powerplay.pp_feature = amdgpu_pp_feature_mask; - if (amdgpu_sriov_vf(adev)) - adev->powerplay.pp_feature &= ~PP_GFXOFF_MASK; for (i = 0; i < adev->num_ip_blocks; i++) { if ((amdgpu_ip_block_mask & (1 << i)) == 0) { @@ -1600,7 +1598,7 @@ static int amdgpu_device_fw_loading(struct amdgpu_device *adev) } } - if (adev->powerplay.pp_funcs->load_firmware) { + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->load_firmware) { r = adev->powerplay.pp_funcs->load_firmware(adev->powerplay.pp_handle); if (r) { pr_err("firmware loading failed\n"); @@ -3341,7 +3339,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, kthread_park(ring->sched.thread); - if (job && job->base.sched == &ring->sched) + if (job && job->base.sched != &ring->sched) continue; drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 28781414d71c85..943dbf3c5da12d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -114,8 +114,8 @@ uint amdgpu_pg_mask = 0xffffffff; uint amdgpu_sdma_phase_quantum = 32; char *amdgpu_disable_cu = NULL; char *amdgpu_virtual_display = NULL; -/* OverDrive(bit 14) disabled by default*/ -uint amdgpu_pp_feature_mask = 0xffffbfff; +/* OverDrive(bit 14),gfxoff(bit 15),stutter mode(bit 17) disabled by default*/ +uint amdgpu_pp_feature_mask = 0xfffd3fff; int amdgpu_ngg = 0; int amdgpu_prim_buf_per_se = 0; int amdgpu_pos_buf_per_se = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 790fd5408ddff2..1a656b8657f736 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -392,7 +392,7 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable) if (!(adev->powerplay.pp_feature & PP_GFXOFF_MASK)) return; - if (!adev->powerplay.pp_funcs->set_powergating_by_smu) + if (!adev->powerplay.pp_funcs || !adev->powerplay.pp_funcs->set_powergating_by_smu) return; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 94055a485e0130..59cc678de8c157 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -704,7 +704,10 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev, return ret; if (adev->powerplay.pp_funcs->force_clock_level) - amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask); + ret = amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask); + + if (ret) + return -EINVAL; return count; } @@ -737,7 +740,10 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev, return ret; if (adev->powerplay.pp_funcs->force_clock_level) - amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask); + ret = amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask); + + if (ret) + return -EINVAL; return count; } @@ -770,7 +776,10 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev, return ret; if (adev->powerplay.pp_funcs->force_clock_level) - amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask); + ret = amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask); + + if (ret) + return -EINVAL; return count; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 6904d794d60a7a..352b304090602e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -542,7 +542,8 @@ static void amdgpu_vm_pt_next_leaf(struct amdgpu_device *adev, struct amdgpu_vm_pt_cursor *cursor) { amdgpu_vm_pt_next(adev, cursor); - while (amdgpu_vm_pt_descendant(adev, cursor)); + if (cursor->pfn != ~0ll) + while (amdgpu_vm_pt_descendant(adev, cursor)); } /** @@ -3234,8 +3235,10 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) } rbtree_postorder_for_each_entry_safe(mapping, tmp, &vm->va.rb_root, rb) { + /* Don't remove the mapping here, we don't want to trigger a + * rebalance and the tree is about to be destroyed anyway. + */ list_del(&mapping->list); - amdgpu_vm_it_remove(mapping, &vm->va); kfree(mapping); } list_for_each_entry_safe(mapping, tmp, &vm->freed, list) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 3d0f277a6523f8..617b0c8908a375 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4815,8 +4815,10 @@ static int gfx_v8_0_kcq_resume(struct amdgpu_device *adev) if (r) goto done; - /* Test KCQs */ - for (i = 0; i < adev->gfx.num_compute_rings; i++) { + /* Test KCQs - reversing the order of rings seems to fix ring test failure + * after GPU reset + */ + for (i = adev->gfx.num_compute_rings - 1; i >= 0; i--) { ring = &adev->gfx.compute_ring[i]; ring->ready = true; r = amdgpu_ring_test_ring(ring); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c index 14649f8475f3f6..fd23ba1226a57d 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c @@ -280,7 +280,7 @@ void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev, return; if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) { - if (adev->powerplay.pp_funcs->set_powergating_by_smu) + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->set_powergating_by_smu) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 04fa3d972636bb..7a8c9172d30a94 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1366,7 +1366,8 @@ static int sdma_v4_0_hw_init(void *handle) int r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs->set_powergating_by_smu) + if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs && + adev->powerplay.pp_funcs->set_powergating_by_smu) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false); sdma_v4_0_init_golden_registers(adev); @@ -1386,7 +1387,8 @@ static int sdma_v4_0_hw_fini(void *handle) sdma_v4_0_ctx_switch_enable(adev, false); sdma_v4_0_enable(adev, false); - if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs->set_powergating_by_smu) + if (adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs + && adev->powerplay.pp_funcs->set_powergating_by_smu) amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, true); 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 e224f23e221559..b0df6dc9a775f0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1524,6 +1524,13 @@ 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; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index 0fab64a2a9150f..12001a006b2d8e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -101,7 +101,7 @@ bool dm_pp_apply_display_requirements( adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1; } - if (adev->powerplay.pp_funcs->display_configuration_change) + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->display_configuration_change) adev->powerplay.pp_funcs->display_configuration_change( adev->powerplay.pp_handle, &adev->pm.pm_display_cfg); @@ -304,7 +304,7 @@ bool dm_pp_get_clock_levels_by_type( struct amd_pp_simple_clock_info validation_clks = { 0 }; uint32_t i; - if (adev->powerplay.pp_funcs->get_clock_by_type) { + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_clock_by_type) { if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle, dc_to_pp_clock_type(clk_type), &pp_clks)) { /* Error in pplib. Provide default values. */ @@ -315,7 +315,7 @@ bool dm_pp_get_clock_levels_by_type( pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type); - if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) { + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_display_mode_validation_clocks) { if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks( pp_handle, &validation_clks)) { /* Error in pplib. Provide default values. */ @@ -398,6 +398,9 @@ bool dm_pp_get_clock_levels_by_type_with_voltage( struct pp_clock_levels_with_voltage pp_clk_info = {0}; const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + if (!pp_funcs || !pp_funcs->get_clock_by_type_with_voltage) + return false; + if (pp_funcs->get_clock_by_type_with_voltage(pp_handle, dc_to_pp_clock_type(clk_type), &pp_clk_info)) @@ -438,7 +441,7 @@ bool dm_pp_apply_clock_for_voltage_request( if (!pp_clock_request.clock_type) return false; - if (adev->powerplay.pp_funcs->display_clock_voltage_request) + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->display_clock_voltage_request) ret = adev->powerplay.pp_funcs->display_clock_voltage_request( adev->powerplay.pp_handle, &pp_clock_request); @@ -455,7 +458,7 @@ bool dm_pp_get_static_clocks( struct amd_pp_clock_info pp_clk_info = {0}; int ret = 0; - if (adev->powerplay.pp_funcs->get_current_clocks) + if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_current_clocks) ret = adev->powerplay.pp_funcs->get_current_clocks( adev->powerplay.pp_handle, &pp_clk_info); @@ -505,6 +508,9 @@ void pp_rv_set_wm_ranges(struct pp_smu *pp, wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets; wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets; + if (!pp_funcs || !pp_funcs->set_watermarks_for_clocks_ranges) + return; + for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) { if (ranges->reader_wm_sets[i].wm_inst > 3) wm_dce_clocks[i].wm_set_id = WM_SET_A; 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 de190935f0a456..e3624ca2457482 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -568,7 +568,7 @@ static struct input_pixel_processor *dce110_ipp_create( static const struct encoder_feature_support link_enc_feature = { .max_hdmi_deep_color = COLOR_DEPTH_121212, - .max_hdmi_pixel_clock = 594000, + .max_hdmi_pixel_clock = 300000, .flags.bits.IS_HBR2_CAPABLE = true, .flags.bits.IS_TPS3_CAPABLE = true }; diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index a407892905af29..c0d9f332baedc1 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -40,8 +40,6 @@ #define LITTLEENDIAN_CPU #endif -#undef READ -#undef WRITE #undef FRAME_SIZE #define dm_output_to_console(fmt, ...) DRM_DEBUG_KMS(fmt, ##__VA_ARGS__) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index e8964cae6b93db..d6aa1d414320bf 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -723,11 +723,14 @@ static int pp_dpm_force_clock_level(void *handle, pr_info("%s was not implemented.\n", __func__); return 0; } + + if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) { + pr_info("force clock level is for dpm manual mode only.\n"); + return -EINVAL; + } + mutex_lock(&hwmgr->smu_lock); - if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_MANUAL) - ret = hwmgr->hwmgr_func->force_clock_level(hwmgr, type, mask); - else - ret = -EINVAL; + ret = hwmgr->hwmgr_func->force_clock_level(hwmgr, type, mask); mutex_unlock(&hwmgr->smu_lock); return ret; } @@ -963,6 +966,7 @@ static int pp_dpm_switch_power_profile(void *handle, static int pp_set_power_limit(void *handle, uint32_t limit) { struct pp_hwmgr *hwmgr = handle; + uint32_t max_power_limit; if (!hwmgr || !hwmgr->pm_en) return -EINVAL; @@ -975,7 +979,13 @@ static int pp_set_power_limit(void *handle, uint32_t limit) if (limit == 0) limit = hwmgr->default_power_limit; - if (limit > hwmgr->default_power_limit) + max_power_limit = hwmgr->default_power_limit; + if (hwmgr->od_enabled) { + max_power_limit *= (100 + hwmgr->platform_descriptor.TDPODLimit); + max_power_limit /= 100; + } + + if (limit > max_power_limit) return -EINVAL; mutex_lock(&hwmgr->smu_lock); @@ -994,8 +1004,13 @@ static int pp_get_power_limit(void *handle, uint32_t *limit, bool default_limit) mutex_lock(&hwmgr->smu_lock); - if (default_limit) + if (default_limit) { *limit = hwmgr->default_power_limit; + if (hwmgr->od_enabled) { + *limit *= (100 + hwmgr->platform_descriptor.TDPODLimit); + *limit /= 100; + } + } else *limit = hwmgr->power_limit; @@ -1303,12 +1318,12 @@ static int pp_enable_mgpu_fan_boost(void *handle) { struct pp_hwmgr *hwmgr = handle; - if (!hwmgr || !hwmgr->pm_en) + if (!hwmgr) return -EINVAL; - if (hwmgr->hwmgr_func->enable_mgpu_fan_boost == NULL) { + if (!hwmgr->pm_en || + hwmgr->hwmgr_func->enable_mgpu_fan_boost == NULL) return 0; - } mutex_lock(&hwmgr->smu_lock); hwmgr->hwmgr_func->enable_mgpu_fan_boost(hwmgr); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 6c99cbf51c08fd..ed35ec0341e671 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3588,9 +3588,10 @@ static int smu7_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, cons break; } - if (i >= sclk_table->count) + if (i >= sclk_table->count) { data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK; - else { + sclk_table->dpm_levels[i-1].value = sclk; + } else { /* TODO: Check SCLK in DAL's minimum clocks * in case DeepSleep divider update is required. */ @@ -3605,9 +3606,10 @@ static int smu7_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, cons break; } - if (i >= mclk_table->count) + if (i >= mclk_table->count) { data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK; - + mclk_table->dpm_levels[i-1].value = mclk; + } if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display) data->need_update_smu7_dpm_table |= DPMTABLE_UPDATE_MCLK; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c index 4714b5b598255b..99a33c33a32c9e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c @@ -718,7 +718,7 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table, table->WatermarkRow[1][i].MaxClock = cpu_to_le16((uint16_t) (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) / - 100); + 1000); table->WatermarkRow[1][i].MinUclk = cpu_to_le16((uint16_t) (wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) / diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index 419a1d77d661e3..8c4db86bb4b770 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -1333,7 +1333,6 @@ static int vega10_setup_default_dpm_tables(struct pp_hwmgr *hwmgr) if (hwmgr->platform_descriptor.overdriveLimit.memoryClock == 0) hwmgr->platform_descriptor.overdriveLimit.memoryClock = dpm_table->dpm_levels[dpm_table->count-1].value; - vega10_init_dpm_state(&(dpm_table->dpm_state)); data->dpm_table.eclk_table.count = 0; @@ -3249,6 +3248,37 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, const void *input) { struct vega10_hwmgr *data = hwmgr->backend; + const struct phm_set_power_state_input *states = + (const struct phm_set_power_state_input *)input; + const struct vega10_power_state *vega10_ps = + cast_const_phw_vega10_power_state(states->pnew_state); + struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table); + uint32_t sclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].gfx_clock; + struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); + uint32_t mclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].mem_clock; + uint32_t i; + + for (i = 0; i < sclk_table->count; i++) { + if (sclk == sclk_table->dpm_levels[i].value) + break; + } + + if (i >= sclk_table->count) { + data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK; + sclk_table->dpm_levels[i-1].value = sclk; + } + + for (i = 0; i < mclk_table->count; i++) { + if (mclk == mclk_table->dpm_levels[i].value) + break; + } + + if (i >= mclk_table->count) { + data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_MCLK; + mclk_table->dpm_levels[i-1].value = mclk; + } if (data->display_timing.num_existing_displays != hwmgr->display_config->num_display) data->need_update_dpm_table |= DPMTABLE_UPDATE_MCLK; @@ -4529,11 +4559,13 @@ static int vega10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) if (vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].gfx_clock > - hwmgr->platform_descriptor.overdriveLimit.engineClock) + hwmgr->platform_descriptor.overdriveLimit.engineClock) { vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].gfx_clock = hwmgr->platform_descriptor.overdriveLimit.engineClock; - + pr_warn("max sclk supported by vbios is %d\n", + hwmgr->platform_descriptor.overdriveLimit.engineClock); + } return 0; } @@ -4581,10 +4613,13 @@ static int vega10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) if (vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].mem_clock > - hwmgr->platform_descriptor.overdriveLimit.memoryClock) + hwmgr->platform_descriptor.overdriveLimit.memoryClock) { vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].mem_clock = hwmgr->platform_descriptor.overdriveLimit.memoryClock; + pr_warn("max mclk supported by vbios is %d\n", + hwmgr->platform_descriptor.overdriveLimit.memoryClock); + } return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c index 9600e2f226e98e..74bc37308dc09c 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c @@ -2356,6 +2356,13 @@ static int vega12_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable) return vega12_disable_gfx_off(hwmgr); } +static int vega12_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_hw_power_state *state, + PHM_PerformanceLevelDesignation designation, uint32_t index, + PHM_PerformanceLevel *level) +{ + return 0; +} + static const struct pp_hwmgr_func vega12_hwmgr_funcs = { .backend_init = vega12_hwmgr_backend_init, .backend_fini = vega12_hwmgr_backend_fini, @@ -2406,6 +2413,7 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = { .register_irq_handlers = smu9_register_irq_handlers, .start_thermal_controller = vega12_start_thermal_controller, .powergate_gfx = vega12_gfx_off_control, + .get_performance_level = vega12_get_performance_level, }; int vega12_hwmgr_init(struct pp_hwmgr *hwmgr) diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index b4dbbb7c334ce0..57143d51e3eed6 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -1875,38 +1875,20 @@ static int vega20_get_gpu_power(struct pp_hwmgr *hwmgr, return ret; } -static int vega20_get_current_gfx_clk_freq(struct pp_hwmgr *hwmgr, uint32_t *gfx_freq) +static int vega20_get_current_clk_freq(struct pp_hwmgr *hwmgr, + PPCLK_e clk_id, uint32_t *clk_freq) { - uint32_t gfx_clk = 0; int ret = 0; - *gfx_freq = 0; + *clk_freq = 0; PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16))) == 0, - "[GetCurrentGfxClkFreq] Attempt to get Current GFXCLK Frequency Failed!", + PPSMC_MSG_GetDpmClockFreq, (clk_id << 16))) == 0, + "[GetCurrentClkFreq] Attempt to get Current Frequency Failed!", return ret); - gfx_clk = smum_get_argument(hwmgr); + *clk_freq = smum_get_argument(hwmgr); - *gfx_freq = gfx_clk * 100; - - return 0; -} - -static int vega20_get_current_mclk_freq(struct pp_hwmgr *hwmgr, uint32_t *mclk_freq) -{ - uint32_t mem_clk = 0; - int ret = 0; - - *mclk_freq = 0; - - PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_GetDpmClockFreq, (PPCLK_UCLK << 16))) == 0, - "[GetCurrentMClkFreq] Attempt to get Current MCLK Frequency Failed!", - return ret); - mem_clk = smum_get_argument(hwmgr); - - *mclk_freq = mem_clk * 100; + *clk_freq = *clk_freq * 100; return 0; } @@ -1937,12 +1919,16 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx, switch (idx) { case AMDGPU_PP_SENSOR_GFX_SCLK: - ret = vega20_get_current_gfx_clk_freq(hwmgr, (uint32_t *)value); + ret = vega20_get_current_clk_freq(hwmgr, + PPCLK_GFXCLK, + (uint32_t *)value); if (!ret) *size = 4; break; case AMDGPU_PP_SENSOR_GFX_MCLK: - ret = vega20_get_current_mclk_freq(hwmgr, (uint32_t *)value); + ret = vega20_get_current_clk_freq(hwmgr, + PPCLK_UCLK, + (uint32_t *)value); if (!ret) *size = 4; break; @@ -2012,7 +1998,6 @@ int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) { switch (clk_type) { case amd_pp_dcef_clock: - clk_freq = clock_req->clock_freq_in_khz / 100; clk_select = PPCLK_DCEFCLK; break; case amd_pp_disp_clock: @@ -2041,11 +2026,20 @@ int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, return result; } +static int vega20_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_hw_power_state *state, + PHM_PerformanceLevelDesignation designation, uint32_t index, + PHM_PerformanceLevel *level) +{ + return 0; +} + static int vega20_notify_smc_display_config_after_ps_adjustment( struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); + struct vega20_single_dpm_table *dpm_table = + &data->dpm_table.mem_table; struct PP_Clocks min_clocks = {0}; struct pp_display_clock_request clock_req; int ret = 0; @@ -2063,7 +2057,7 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( if (data->smu_features[GNLD_DPM_DCEFCLK].supported) { clock_req.clock_type = amd_pp_dcef_clock; - clock_req.clock_freq_in_khz = min_clocks.dcefClock; + clock_req.clock_freq_in_khz = min_clocks.dcefClock * 10; if (!vega20_display_clock_voltage_request(hwmgr, &clock_req)) { if (data->smu_features[GNLD_DS_DCEFCLK].supported) PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc_with_parameter( @@ -2076,6 +2070,15 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( } } + if (data->smu_features[GNLD_DPM_UCLK].enabled) { + dpm_table->dpm_state.hard_min_level = min_clocks.memoryClock / 100; + PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetHardMinByFreq, + (PPCLK_UCLK << 16 ) | dpm_table->dpm_state.hard_min_level)), + "[SetHardMinFreq] Set hard min uclk failed!", + return ret); + } + return 0; } @@ -2353,7 +2356,7 @@ static int vega20_get_sclks(struct pp_hwmgr *hwmgr, for (i = 0; i < count; i++) { clocks->data[i].clocks_in_khz = - dpm_table->dpm_levels[i].value * 100; + dpm_table->dpm_levels[i].value * 1000; clocks->data[i].latency_in_us = 0; } @@ -2383,7 +2386,7 @@ static int vega20_get_memclocks(struct pp_hwmgr *hwmgr, for (i = 0; i < count; i++) { clocks->data[i].clocks_in_khz = data->mclk_latency_table.entries[i].frequency = - dpm_table->dpm_levels[i].value * 100; + dpm_table->dpm_levels[i].value * 1000; clocks->data[i].latency_in_us = data->mclk_latency_table.entries[i].latency = vega20_get_mem_latency(hwmgr, dpm_table->dpm_levels[i].value); @@ -2408,7 +2411,7 @@ static int vega20_get_dcefclocks(struct pp_hwmgr *hwmgr, for (i = 0; i < count; i++) { clocks->data[i].clocks_in_khz = - dpm_table->dpm_levels[i].value * 100; + dpm_table->dpm_levels[i].value * 1000; clocks->data[i].latency_in_us = 0; } @@ -2431,7 +2434,7 @@ static int vega20_get_socclocks(struct pp_hwmgr *hwmgr, for (i = 0; i < count; i++) { clocks->data[i].clocks_in_khz = - dpm_table->dpm_levels[i].value * 100; + dpm_table->dpm_levels[i].value * 1000; clocks->data[i].latency_in_us = 0; } @@ -2582,11 +2585,11 @@ static int vega20_odn_edit_dpm_table(struct pp_hwmgr *hwmgr, return -EINVAL; } - if (input_clk < clocks.data[0].clocks_in_khz / 100 || + if (input_clk < clocks.data[0].clocks_in_khz / 1000 || input_clk > od8_settings[OD8_SETTING_UCLK_FMAX].max_value) { pr_info("clock freq %d is not within allowed range [%d - %d]\n", input_clk, - clocks.data[0].clocks_in_khz / 100, + clocks.data[0].clocks_in_khz / 1000, od8_settings[OD8_SETTING_UCLK_FMAX].max_value); return -EINVAL; } @@ -2726,7 +2729,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, switch (type) { case PP_SCLK: - ret = vega20_get_current_gfx_clk_freq(hwmgr, &now); + ret = vega20_get_current_clk_freq(hwmgr, PPCLK_GFXCLK, &now); PP_ASSERT_WITH_CODE(!ret, "Attempt to get current gfx clk Failed!", return ret); @@ -2738,12 +2741,12 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, for (i = 0; i < clocks.num_levels; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", - i, clocks.data[i].clocks_in_khz / 100, + i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now) ? "*" : ""); break; case PP_MCLK: - ret = vega20_get_current_mclk_freq(hwmgr, &now); + ret = vega20_get_current_clk_freq(hwmgr, PPCLK_UCLK, &now); PP_ASSERT_WITH_CODE(!ret, "Attempt to get current mclk freq Failed!", return ret); @@ -2755,7 +2758,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, for (i = 0; i < clocks.num_levels; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", - i, clocks.data[i].clocks_in_khz / 100, + i, clocks.data[i].clocks_in_khz / 1000, (clocks.data[i].clocks_in_khz == now) ? "*" : ""); break; @@ -2820,7 +2823,7 @@ static int vega20_print_clock_levels(struct pp_hwmgr *hwmgr, return ret); size += sprintf(buf + size, "MCLK: %7uMhz %10uMhz\n", - clocks.data[0].clocks_in_khz / 100, + clocks.data[0].clocks_in_khz / 1000, od8_settings[OD8_SETTING_UCLK_FMAX].max_value); } @@ -3476,6 +3479,8 @@ static const struct pp_hwmgr_func vega20_hwmgr_funcs = { vega20_set_watermarks_for_clocks_ranges, .display_clock_voltage_request = vega20_display_clock_voltage_request, + .get_performance_level = + vega20_get_performance_level, /* UMD pstate, profile related */ .force_dpm_level = vega20_dpm_force_dpm_level, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c index e5f7f82300659f..97f8a1a970c37e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_processpptables.c @@ -642,8 +642,14 @@ static int check_powerplay_tables( "Unsupported PPTable format!", return -1); PP_ASSERT_WITH_CODE(powerplay_table->sHeader.structuresize > 0, "Invalid PowerPlay Table!", return -1); - PP_ASSERT_WITH_CODE(powerplay_table->smcPPTable.Version == PPTABLE_V20_SMU_VERSION, - "Unmatch PPTable version, vbios update may be needed!", return -1); + + if (powerplay_table->smcPPTable.Version != PPTABLE_V20_SMU_VERSION) { + pr_info("Unmatch PPTable version: " + "pptable from VBIOS is V%d while driver supported is V%d!", + powerplay_table->smcPPTable.Version, + PPTABLE_V20_SMU_VERSION); + return -EINVAL; + } //dump_pptable(&powerplay_table->smcPPTable); @@ -716,10 +722,6 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable "[appendVbiosPPTable] Failed to retrieve Smc Dpm Table from VBIOS!", return -1); - memset(ppsmc_pptable->Padding32, - 0, - sizeof(struct atom_smc_dpm_info_v4_4) - - sizeof(struct atom_common_table_header)); ppsmc_pptable->MaxVoltageStepGfx = smc_dpm_table->maxvoltagestepgfx; ppsmc_pptable->MaxVoltageStepSoc = smc_dpm_table->maxvoltagestepsoc; @@ -778,22 +780,19 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable ppsmc_pptable->FllGfxclkSpreadPercent = smc_dpm_table->fllgfxclkspreadpercent; ppsmc_pptable->FllGfxclkSpreadFreq = smc_dpm_table->fllgfxclkspreadfreq; - if ((smc_dpm_table->table_header.format_revision == 4) && - (smc_dpm_table->table_header.content_revision == 4)) { - for (i = 0; i < I2C_CONTROLLER_NAME_COUNT; i++) { - ppsmc_pptable->I2cControllers[i].Enabled = - smc_dpm_table->i2ccontrollers[i].enabled; - ppsmc_pptable->I2cControllers[i].SlaveAddress = - smc_dpm_table->i2ccontrollers[i].slaveaddress; - ppsmc_pptable->I2cControllers[i].ControllerPort = - smc_dpm_table->i2ccontrollers[i].controllerport; - ppsmc_pptable->I2cControllers[i].ThermalThrottler = - smc_dpm_table->i2ccontrollers[i].thermalthrottler; - ppsmc_pptable->I2cControllers[i].I2cProtocol = - smc_dpm_table->i2ccontrollers[i].i2cprotocol; - ppsmc_pptable->I2cControllers[i].I2cSpeed = - smc_dpm_table->i2ccontrollers[i].i2cspeed; - } + for (i = 0; i < I2C_CONTROLLER_NAME_COUNT; i++) { + ppsmc_pptable->I2cControllers[i].Enabled = + smc_dpm_table->i2ccontrollers[i].enabled; + ppsmc_pptable->I2cControllers[i].SlaveAddress = + smc_dpm_table->i2ccontrollers[i].slaveaddress; + ppsmc_pptable->I2cControllers[i].ControllerPort = + smc_dpm_table->i2ccontrollers[i].controllerport; + ppsmc_pptable->I2cControllers[i].ThermalThrottler = + smc_dpm_table->i2ccontrollers[i].thermalthrottler; + ppsmc_pptable->I2cControllers[i].I2cProtocol = + smc_dpm_table->i2ccontrollers[i].i2cprotocol; + ppsmc_pptable->I2cControllers[i].I2cSpeed = + smc_dpm_table->i2ccontrollers[i].i2cspeed; } return 0; @@ -882,15 +881,10 @@ static int init_powerplay_table_information( if (pptable_information->smc_pptable == NULL) return -ENOMEM; - if (powerplay_table->smcPPTable.Version <= 2) - memcpy(pptable_information->smc_pptable, - &(powerplay_table->smcPPTable), - sizeof(PPTable_t) - - sizeof(I2cControllerConfig_t) * I2C_CONTROLLER_NAME_COUNT); - else - memcpy(pptable_information->smc_pptable, - &(powerplay_table->smcPPTable), - sizeof(PPTable_t)); + memcpy(pptable_information->smc_pptable, + &(powerplay_table->smcPPTable), + sizeof(PPTable_t)); + result = append_vbios_pptable(hwmgr, (pptable_information->smc_pptable)); diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h index 2998a49960ede1..63d5cf69154967 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h @@ -29,7 +29,7 @@ // any structure is changed in this file #define SMU11_DRIVER_IF_VERSION 0x12 -#define PPTABLE_V20_SMU_VERSION 2 +#define PPTABLE_V20_SMU_VERSION 3 #define NUM_GFXCLK_DPM_LEVELS 16 #define NUM_VCLK_DPM_LEVELS 8 diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c index f836d30fdd4428..09b844ec3eabae 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c @@ -71,7 +71,11 @@ static int smu8_send_msg_to_smc_async(struct pp_hwmgr *hwmgr, uint16_t msg) result = PHM_WAIT_FIELD_UNEQUAL(hwmgr, SMU_MP1_SRBM2P_RESP_0, CONTENT, 0); if (result != 0) { + /* Read the last message to SMU, to report actual cause */ + uint32_t val = cgs_read_register(hwmgr->device, + mmSMU_MP1_SRBM2P_MSG_0); pr_err("smu8_send_msg_to_smc_async (0x%04x) failed\n", msg); + pr_err("SMU still servicing msg (0x%04x)\n", val); return result; } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index f8a931cf3665e8..680566d97adcf6 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -458,18 +458,6 @@ static void ti_sn_bridge_enable(struct drm_bridge *bridge) unsigned int val; int ret; - /* - * FIXME: - * This 70ms was found necessary by experimentation. If it's not - * present, link training fails. It seems like it can go anywhere from - * pre_enable() up to semi-auto link training initiation below. - * - * Neither the datasheet for the bridge nor the panel tested mention a - * delay of this magnitude in the timing requirements. So for now, add - * the mystery delay until someone figures out a better fix. - */ - msleep(70); - /* DSI_A lane config */ val = CHA_DSI_LANES(4 - pdata->dsi->lanes); regmap_update_bits(pdata->regmap, SN_DSI_LANES_REG, @@ -536,7 +524,22 @@ static void ti_sn_bridge_pre_enable(struct drm_bridge *bridge) /* configure bridge ref_clk */ ti_sn_bridge_set_refclk_freq(pdata); - /* in case drm_panel is connected then HPD is not supported */ + /* + * HPD on this bridge chip is a bit useless. This is an eDP bridge + * so the HPD is an internal signal that's only there to signal that + * the panel is done powering up. ...but the bridge chip debounces + * this signal by between 100 ms and 400 ms (depending on process, + * voltage, and temperate--I measured it at about 200 ms). One + * particular panel asserted HPD 84 ms after it was powered on meaning + * that we saw HPD 284 ms after power on. ...but the same panel said + * that instead of looking at HPD you could just hardcode a delay of + * 200 ms. We'll assume that the panel driver will have the hardcoded + * delay in its prepare and always disable HPD. + * + * If HPD somehow makes sense on some future panel we'll have to + * change this to be conditional on someone specifying that HPD should + * be used. + */ regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, HPD_DISABLE); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 701cb334e1ea31..d8b526b7932c3d 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -308,6 +308,26 @@ update_connector_routing(struct drm_atomic_state *state, return 0; } + crtc_state = drm_atomic_get_new_crtc_state(state, + new_connector_state->crtc); + /* + * For compatibility with legacy users, we want to make sure that + * we allow DPMS On->Off modesets on unregistered connectors. Modesets + * which would result in anything else must be considered invalid, to + * avoid turning on new displays on dead connectors. + * + * Since the connector can be unregistered at any point during an + * atomic check or commit, this is racy. But that's OK: all we care + * about is ensuring that userspace can't do anything but shut off the + * display on a connector that was destroyed after its been notified, + * not before. + */ + if (drm_connector_is_unregistered(connector) && crtc_state->active) { + DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] is not registered\n", + connector->base.id, connector->name); + return -EINVAL; + } + funcs = connector->helper_private; if (funcs->atomic_best_encoder) @@ -352,7 +372,6 @@ update_connector_routing(struct drm_atomic_state *state, set_best_encoder(state, new_connector_state, new_encoder); - crtc_state = drm_atomic_get_new_crtc_state(state, new_connector_state->crtc); crtc_state->connectors_changed = true; DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] using [ENCODER:%d:%s] on [CRTC:%d:%s]\n", diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index 1e40e5decbe91a..4943cef178beb7 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -379,7 +379,8 @@ void drm_connector_cleanup(struct drm_connector *connector) /* The connector should have been removed from userspace long before * it is finally destroyed. */ - if (WARN_ON(connector->registered)) + if (WARN_ON(connector->registration_state == + DRM_CONNECTOR_REGISTERED)) drm_connector_unregister(connector); if (connector->tile_group) { @@ -436,7 +437,7 @@ int drm_connector_register(struct drm_connector *connector) return 0; mutex_lock(&connector->mutex); - if (connector->registered) + if (connector->registration_state != DRM_CONNECTOR_INITIALIZING) goto unlock; ret = drm_sysfs_connector_add(connector); @@ -456,7 +457,7 @@ int drm_connector_register(struct drm_connector *connector) drm_mode_object_register(connector->dev, &connector->base); - connector->registered = true; + connector->registration_state = DRM_CONNECTOR_REGISTERED; goto unlock; err_debugfs: @@ -478,7 +479,7 @@ EXPORT_SYMBOL(drm_connector_register); void drm_connector_unregister(struct drm_connector *connector) { mutex_lock(&connector->mutex); - if (!connector->registered) { + if (connector->registration_state != DRM_CONNECTOR_REGISTERED) { mutex_unlock(&connector->mutex); return; } @@ -489,7 +490,7 @@ void drm_connector_unregister(struct drm_connector *connector) drm_sysfs_connector_remove(connector); drm_debugfs_connector_remove(connector); - connector->registered = false; + connector->registration_state = DRM_CONNECTOR_UNREGISTERED; mutex_unlock(&connector->mutex); } EXPORT_SYMBOL(drm_connector_unregister); diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index ff0bfc65a8c1db..b506e3622b08f6 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -122,6 +122,9 @@ static const struct edid_quirk { /* SDC panel of Lenovo B50-80 reports 8 bpc, but is a 6 bpc panel */ { "SDC", 0x3652, EDID_QUIRK_FORCE_6BPC }, + /* BOE model 0x0771 reports 8 bpc, but is a 6 bpc panel */ + { "BOE", 0x0771, EDID_QUIRK_FORCE_6BPC }, + /* Belinea 10 15 55 */ { "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 }, { "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 }, diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 3fae4dab295f09..13f9b56a9ce7ca 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -5102,19 +5102,13 @@ intel_dp_long_pulse(struct intel_connector *connector, */ status = connector_status_disconnected; goto out; - } else { - /* - * If display is now connected check links status, - * there has been known issues of link loss triggering - * long pulse. - * - * Some sinks (eg. ASUS PB287Q) seem to perform some - * weird HPD ping pong during modesets. So we can apparently - * end up with HPD going low during a modeset, and then - * going back up soon after. And once that happens we must - * retrain the link to get a picture. That's in case no - * userspace component reacted to intermittent HPD dip. - */ + } + + /* + * Some external monitors do not signal loss of link synchronization + * with an IRQ_HPD, so force a link status check. + */ + if (!intel_dp_is_edp(intel_dp)) { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; intel_dp_retrain_link(encoder, ctx); diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 7f155b4f1a7d7a..1b00f8ea145ba3 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -77,7 +77,7 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder, pipe_config->pbn = mst_pbn; /* Zombie connectors can't have VCPI slots */ - if (READ_ONCE(connector->registered)) { + if (!drm_connector_is_unregistered(connector)) { slots = drm_dp_atomic_find_vcpi_slots(state, &intel_dp->mst_mgr, port, @@ -313,7 +313,7 @@ static int intel_dp_mst_get_ddc_modes(struct drm_connector *connector) struct edid *edid; int ret; - if (!READ_ONCE(connector->registered)) + if (drm_connector_is_unregistered(connector)) return intel_connector_update_modes(connector, NULL); edid = drm_dp_mst_get_edid(connector, &intel_dp->mst_mgr, intel_connector->port); @@ -329,7 +329,7 @@ intel_dp_mst_detect(struct drm_connector *connector, bool force) struct intel_connector *intel_connector = to_intel_connector(connector); struct intel_dp *intel_dp = intel_connector->mst_port; - if (!READ_ONCE(connector->registered)) + if (drm_connector_is_unregistered(connector)) return connector_status_disconnected; return drm_dp_mst_detect_port(connector, &intel_dp->mst_mgr, intel_connector->port); @@ -372,7 +372,7 @@ intel_dp_mst_mode_valid(struct drm_connector *connector, int bpp = 24; /* MST uses fixed bpp */ int max_rate, mode_rate, max_lanes, max_link_clock; - if (!READ_ONCE(connector->registered)) + if (drm_connector_is_unregistered(connector)) return MODE_ERROR; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 6bb78076b5b583..6cbbae3f438bd0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -881,22 +881,16 @@ nv50_mstc_atomic_best_encoder(struct drm_connector *connector, { struct nv50_head *head = nv50_head(connector_state->crtc); struct nv50_mstc *mstc = nv50_mstc(connector); - if (mstc->port) { - struct nv50_mstm *mstm = mstc->mstm; - return &mstm->msto[head->base.index]->encoder; - } - return NULL; + + return &mstc->mstm->msto[head->base.index]->encoder; } static struct drm_encoder * nv50_mstc_best_encoder(struct drm_connector *connector) { struct nv50_mstc *mstc = nv50_mstc(connector); - if (mstc->port) { - struct nv50_mstm *mstm = mstc->mstm; - return &mstm->msto[0]->encoder; - } - return NULL; + + return &mstc->mstm->msto[0]->encoder; } static enum drm_mode_status diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 97964f7f2acee0..a04ffb3b21742a 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -56,6 +56,8 @@ struct panel_desc { /** * @prepare: the time (in milliseconds) that it takes for the panel to * become ready and start receiving video data + * @hpd_absent_delay: Add this to the prepare delay if we know Hot + * Plug Detect isn't used. * @enable: the time (in milliseconds) that it takes for the panel to * display the first valid frame after starting to receive * video data @@ -66,6 +68,7 @@ struct panel_desc { */ struct { unsigned int prepare; + unsigned int hpd_absent_delay; unsigned int enable; unsigned int disable; unsigned int unprepare; @@ -79,6 +82,7 @@ struct panel_simple { struct drm_panel base; bool prepared; bool enabled; + bool no_hpd; const struct panel_desc *desc; @@ -202,6 +206,7 @@ static int panel_simple_unprepare(struct drm_panel *panel) static int panel_simple_prepare(struct drm_panel *panel) { struct panel_simple *p = to_panel_simple(panel); + unsigned int delay; int err; if (p->prepared) @@ -215,8 +220,11 @@ static int panel_simple_prepare(struct drm_panel *panel) gpiod_set_value_cansleep(p->enable_gpio, 1); - if (p->desc->delay.prepare) - msleep(p->desc->delay.prepare); + delay = p->desc->delay.prepare; + if (p->no_hpd) + delay += p->desc->delay.hpd_absent_delay; + if (delay) + msleep(delay); p->prepared = true; @@ -305,6 +313,8 @@ static int panel_simple_probe(struct device *dev, const struct panel_desc *desc) panel->prepared = false; panel->desc = desc; + panel->no_hpd = of_property_read_bool(dev->of_node, "no-hpd"); + panel->supply = devm_regulator_get(dev, "power"); if (IS_ERR(panel->supply)) return PTR_ERR(panel->supply); @@ -1363,7 +1373,7 @@ static const struct panel_desc innolux_n156bge_l21 = { }, }; -static const struct drm_display_mode innolux_tv123wam_mode = { +static const struct drm_display_mode innolux_p120zdg_bf1_mode = { .clock = 206016, .hdisplay = 2160, .hsync_start = 2160 + 48, @@ -1377,15 +1387,16 @@ static const struct drm_display_mode innolux_tv123wam_mode = { .flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC, }; -static const struct panel_desc innolux_tv123wam = { - .modes = &innolux_tv123wam_mode, +static const struct panel_desc innolux_p120zdg_bf1 = { + .modes = &innolux_p120zdg_bf1_mode, .num_modes = 1, .bpc = 8, .size = { - .width = 259, - .height = 173, + .width = 254, + .height = 169, }, .delay = { + .hpd_absent_delay = 200, .unprepare = 500, }, }; @@ -2445,8 +2456,8 @@ static const struct of_device_id platform_of_match[] = { .compatible = "innolux,n156bge-l21", .data = &innolux_n156bge_l21, }, { - .compatible = "innolux,tv123wam", - .data = &innolux_tv123wam, + .compatible = "innolux,p120zdg-bf1", + .data = &innolux_p120zdg_bf1, }, { .compatible = "innolux,zj070na-01p", .data = &innolux_zj070na_01p, diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 5ed319e3b084d9..41e9935fc5849e 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -149,6 +149,7 @@ config HID_APPLEIR config HID_ASUS tristate "Asus" depends on LEDS_CLASS + depends on ASUS_WMI || ASUS_WMI=n ---help--- Support for Asus notebook built-in keyboard and touchpad via i2c, and the Asus Republic of Gamers laptop keyboard special keys. diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 88a5672f42cd81..dc6d6477e9611e 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -29,6 +29,7 @@ #include <linux/dmi.h> #include <linux/hid.h> #include <linux/module.h> +#include <linux/platform_data/x86/asus-wmi.h> #include <linux/input/mt.h> #include <linux/usb.h> /* For to_usb_interface for T100 touchpad intf check */ @@ -349,6 +350,24 @@ static void asus_kbd_backlight_work(struct work_struct *work) hid_err(led->hdev, "Asus failed to set keyboard backlight: %d\n", ret); } +/* WMI-based keyboard backlight LED control (via asus-wmi driver) takes + * precedence. We only activate HID-based backlight control when the + * WMI control is not available. + */ +static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev) +{ + u32 value; + int ret; + + 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); + if (ret) + return false; + + return !!(value & ASUS_WMI_DSTS_PRESENCE_BIT); +} + static int asus_kbd_register_leds(struct hid_device *hdev) { struct asus_drvdata *drvdata = hid_get_drvdata(hdev); @@ -436,7 +455,9 @@ static int asus_input_configured(struct hid_device *hdev, struct hid_input *hi) drvdata->input = input; - if (drvdata->enable_backlight && asus_kbd_register_leds(hdev)) + if (drvdata->enable_backlight && + !asus_kbd_wmi_led_control_present(hdev) && + asus_kbd_register_leds(hdev)) hid_warn(hdev, "Failed to initialize backlight.\n"); return 0; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index dc78aa7369def4..28460f6a60cc15 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -306,10 +306,7 @@ static int i2c_smbus_host_notify_to_irq(const struct i2c_client *client) if (client->flags & I2C_CLIENT_TEN) return -EINVAL; - irq = irq_find_mapping(adap->host_notify_domain, client->addr); - if (!irq) - irq = irq_create_mapping(adap->host_notify_domain, - client->addr); + irq = irq_create_mapping(adap->host_notify_domain, client->addr); return irq > 0 ? irq : -ENXIO; } @@ -433,6 +430,8 @@ static int i2c_device_remove(struct device *dev) dev_pm_clear_wake_irq(&client->dev); device_init_wakeup(&client->dev, false); + client->irq = 0; + return status; } diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index b05022f94f18c2..072bb5e36c184e 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -718,8 +718,7 @@ l1oip_socket_thread(void *data) printk(KERN_DEBUG "%s: socket created and open\n", __func__); while (!signal_pending(current)) { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, - recvbuf_size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, recvbuf_size); recvlen = sock_recvmsg(socket, &msg, 0); if (recvlen > 0) { l1oip_socket_parse(hc, &sin_rx, recvbuf, recvlen); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f3fb5bb8c82a1c..ac1cffd2a09b05 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -542,7 +542,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) !discard_bio) continue; bio_chain(discard_bio, bio); - bio_clone_blkg_association(discard_bio, bio); + bio_clone_blkcg_association(discard_bio, bio); if (mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rdev->bdev), discard_bio, disk_devt(mddev->gendisk), diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile index 3370a4138e9426..951c984de61ae9 100644 --- a/drivers/misc/lkdtm/Makefile +++ b/drivers/misc/lkdtm/Makefile @@ -8,7 +8,9 @@ lkdtm-$(CONFIG_LKDTM) += perms.o lkdtm-$(CONFIG_LKDTM) += refcount.o lkdtm-$(CONFIG_LKDTM) += rodata_objcopy.o lkdtm-$(CONFIG_LKDTM) += usercopy.o +lkdtm-$(CONFIG_LKDTM) += stackleak.o +KASAN_SANITIZE_stackleak.o := n KCOV_INSTRUMENT_rodata.o := n OBJCOPYFLAGS := diff --git a/drivers/misc/lkdtm/core.c b/drivers/misc/lkdtm/core.c index 5a755590d3dcef..2837dc77478ed4 100644 --- a/drivers/misc/lkdtm/core.c +++ b/drivers/misc/lkdtm/core.c @@ -184,6 +184,7 @@ static const struct crashtype crashtypes[] = { CRASHTYPE(USERCOPY_STACK_BEYOND), CRASHTYPE(USERCOPY_KERNEL), CRASHTYPE(USERCOPY_KERNEL_DS), + CRASHTYPE(STACKLEAK_ERASING), }; diff --git a/drivers/misc/lkdtm/lkdtm.h b/drivers/misc/lkdtm/lkdtm.h index 07db641d71d023..3c6fd327e166a4 100644 --- a/drivers/misc/lkdtm/lkdtm.h +++ b/drivers/misc/lkdtm/lkdtm.h @@ -84,4 +84,7 @@ void lkdtm_USERCOPY_STACK_BEYOND(void); void lkdtm_USERCOPY_KERNEL(void); void lkdtm_USERCOPY_KERNEL_DS(void); +/* lkdtm_stackleak.c */ +void lkdtm_STACKLEAK_ERASING(void); + #endif diff --git a/drivers/misc/lkdtm/stackleak.c b/drivers/misc/lkdtm/stackleak.c new file mode 100644 index 00000000000000..d5a084475abc53 --- /dev/null +++ b/drivers/misc/lkdtm/stackleak.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code tests that the current task stack is properly erased (filled + * with STACKLEAK_POISON). + * + * Authors: + * Alexander Popov <alex.popov@linux.com> + * Tycho Andersen <tycho@tycho.ws> + */ + +#include "lkdtm.h" +#include <linux/stackleak.h> + +void lkdtm_STACKLEAK_ERASING(void) +{ + unsigned long *sp, left, found, i; + const unsigned long check_depth = + STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + + /* + * For the details about the alignment of the poison values, see + * the comment in stackleak_track_stack(). + */ + sp = PTR_ALIGN(&i, sizeof(unsigned long)); + + left = ((unsigned long)sp & (THREAD_SIZE - 1)) / sizeof(unsigned long); + sp--; + + /* + * One 'long int' at the bottom of the thread stack is reserved + * and not poisoned. + */ + if (left > 1) { + left--; + } else { + pr_err("FAIL: not enough stack space for the test\n"); + return; + } + + pr_info("checking unused part of the thread stack (%lu bytes)...\n", + left * sizeof(unsigned long)); + + /* + * Search for 'check_depth' poison values in a row (just like + * stackleak_erase() does). + */ + for (i = 0, found = 0; i < left && found <= check_depth; i++) { + if (*(sp - i) == STACKLEAK_POISON) + found++; + else + found = 0; + } + + if (found <= check_depth) { + pr_err("FAIL: thread stack is not erased (checked %lu bytes)\n", + i * sizeof(unsigned long)); + return; + } + + pr_info("first %lu bytes are unpoisoned\n", + (i - found) * sizeof(unsigned long)); + + /* The rest of thread stack should be erased */ + for (; i < left; i++) { + if (*(sp - i) != STACKLEAK_POISON) { + pr_err("FAIL: thread stack is NOT properly erased\n"); + return; + } + } + + pr_info("OK: the rest of the thread stack is properly erased\n"); + return; +} diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index bd52f29b4a4e27..264f4ed8eef26e 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -3030,7 +3030,7 @@ ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&from, WRITE, &v, 1, buf_size); qp_lock(qpair); @@ -3074,7 +3074,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); @@ -3119,7 +3119,7 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 9697977b80f040..6b9ad86732188c 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -638,8 +638,7 @@ static int bond_fill_info(struct sk_buff *skb, goto nla_put_failure; if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM, - sizeof(bond->params.ad_actor_system), - &bond->params.ad_actor_system)) + ETH_ALEN, &bond->params.ad_actor_system)) goto nla_put_failure; } if (!bond_3ad_get_active_agg_info(bond, &info)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index e82e4ca206205d..055b40606dbc20 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -316,8 +316,8 @@ struct hnae3_ae_ops { int (*set_loopback)(struct hnae3_handle *handle, enum hnae3_loop loop_mode, bool en); - void (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc, - bool en_mc_pmc); + int (*set_promisc_mode)(struct hnae3_handle *handle, bool en_uc_pmc, + bool en_mc_pmc); int (*set_mtu)(struct hnae3_handle *handle, int new_mtu); void (*get_pauseparam)(struct hnae3_handle *handle, @@ -391,7 +391,7 @@ struct hnae3_ae_ops { int vector_num, struct hnae3_ring_chain_node *vr_chain); - void (*reset_queue)(struct hnae3_handle *handle, u16 queue_id); + int (*reset_queue)(struct hnae3_handle *handle, u16 queue_id); u32 (*get_fw_version)(struct hnae3_handle *handle); void (*get_mdix_mode)(struct hnae3_handle *handle, u8 *tp_mdix_ctrl, u8 *tp_mdix); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 32f3aca814e78b..3f96aa30068ec3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -509,16 +509,18 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev) h->netdev_flags = new_flags; } -void hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags) +int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; if (h->ae_algo->ops->set_promisc_mode) { - h->ae_algo->ops->set_promisc_mode(h, - promisc_flags & HNAE3_UPE, - promisc_flags & HNAE3_MPE); + return h->ae_algo->ops->set_promisc_mode(h, + promisc_flags & HNAE3_UPE, + promisc_flags & HNAE3_MPE); } + + return 0; } void hns3_enable_vlan_filter(struct net_device *netdev, bool enable) @@ -1494,18 +1496,22 @@ static int hns3_vlan_rx_kill_vid(struct net_device *netdev, return ret; } -static void hns3_restore_vlan(struct net_device *netdev) +static int hns3_restore_vlan(struct net_device *netdev) { struct hns3_nic_priv *priv = netdev_priv(netdev); + int ret = 0; u16 vid; - int ret; for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) { ret = hns3_vlan_rx_add_vid(netdev, htons(ETH_P_8021Q), vid); - if (ret) - netdev_warn(netdev, "Restore vlan: %d filter, ret:%d\n", - vid, ret); + if (ret) { + netdev_err(netdev, "Restore vlan: %d filter, ret:%d\n", + vid, ret); + return ret; + } } + + return ret; } static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, @@ -2727,7 +2733,7 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); if (!chain) - return -ENOMEM; + goto err_free_chain; cur_chain->next = chain; chain->tqp_index = tx_ring->tqp->tqp_index; @@ -2757,7 +2763,7 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, while (rx_ring) { chain = devm_kzalloc(&pdev->dev, sizeof(*chain), GFP_KERNEL); if (!chain) - return -ENOMEM; + goto err_free_chain; cur_chain->next = chain; chain->tqp_index = rx_ring->tqp->tqp_index; @@ -2772,6 +2778,16 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, } return 0; + +err_free_chain: + cur_chain = head->next; + while (cur_chain) { + chain = cur_chain->next; + devm_kfree(&pdev->dev, chain); + cur_chain = chain; + } + + return -ENOMEM; } static void hns3_free_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector, @@ -2821,7 +2837,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) struct hnae3_handle *h = priv->ae_handle; struct hns3_enet_tqp_vector *tqp_vector; int ret = 0; - u16 i; + int i; hns3_nic_set_cpumask(priv); @@ -2868,13 +2884,19 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv) hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); if (ret) - return ret; + goto map_ring_fail; netif_napi_add(priv->netdev, &tqp_vector->napi, hns3_nic_common_poll, NAPI_POLL_WEIGHT); } return 0; + +map_ring_fail: + while (i--) + netif_napi_del(&priv->tqp_vector[i].napi); + + return ret; } static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv) @@ -3031,8 +3053,10 @@ static int hns3_queue_to_ring(struct hnae3_queue *tqp, return ret; ret = hns3_ring_get_cfg(tqp, priv, HNAE3_RING_TYPE_RX); - if (ret) + if (ret) { + devm_kfree(priv->dev, priv->ring_data[tqp->tqp_index].ring); return ret; + } return 0; } @@ -3059,6 +3083,12 @@ static int hns3_get_ring_config(struct hns3_nic_priv *priv) return 0; err: + while (i--) { + devm_kfree(priv->dev, priv->ring_data[i].ring); + devm_kfree(priv->dev, + priv->ring_data[i + h->kinfo.num_tqps].ring); + } + devm_kfree(&pdev->dev, priv->ring_data); return ret; } @@ -3226,9 +3256,6 @@ int hns3_uninit_all_ring(struct hns3_nic_priv *priv) int i; for (i = 0; i < h->kinfo.num_tqps; i++) { - if (h->ae_algo->ops->reset_queue) - h->ae_algo->ops->reset_queue(h, i); - hns3_fini_ring(priv->ring_data[i].ring); hns3_fini_ring(priv->ring_data[i + h->kinfo.num_tqps].ring); } @@ -3236,11 +3263,12 @@ int hns3_uninit_all_ring(struct hns3_nic_priv *priv) } /* Set mac addr if it is configured. or leave it to the AE driver */ -static void hns3_init_mac_addr(struct net_device *netdev, bool init) +static int hns3_init_mac_addr(struct net_device *netdev, bool init) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; u8 mac_addr_temp[ETH_ALEN]; + int ret = 0; if (h->ae_algo->ops->get_mac_addr && init) { h->ae_algo->ops->get_mac_addr(h, mac_addr_temp); @@ -3255,8 +3283,9 @@ static void hns3_init_mac_addr(struct net_device *netdev, bool init) } if (h->ae_algo->ops->set_mac_addr) - h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); + ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); + return ret; } static int hns3_restore_fd_rules(struct net_device *netdev) @@ -3469,20 +3498,29 @@ err_out: return ret; } -static void hns3_recover_hw_addr(struct net_device *ndev) +static int hns3_recover_hw_addr(struct net_device *ndev) { struct netdev_hw_addr_list *list; struct netdev_hw_addr *ha, *tmp; + int ret = 0; /* go through and sync uc_addr entries to the device */ list = &ndev->uc; - list_for_each_entry_safe(ha, tmp, &list->list, list) - hns3_nic_uc_sync(ndev, ha->addr); + list_for_each_entry_safe(ha, tmp, &list->list, list) { + ret = hns3_nic_uc_sync(ndev, ha->addr); + if (ret) + return ret; + } /* go through and sync mc_addr entries to the device */ list = &ndev->mc; - list_for_each_entry_safe(ha, tmp, &list->list, list) - hns3_nic_mc_sync(ndev, ha->addr); + list_for_each_entry_safe(ha, tmp, &list->list, list) { + ret = hns3_nic_mc_sync(ndev, ha->addr); + if (ret) + return ret; + } + + return ret; } static void hns3_remove_hw_addr(struct net_device *netdev) @@ -3609,7 +3647,10 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) int ret; for (i = 0; i < h->kinfo.num_tqps; i++) { - h->ae_algo->ops->reset_queue(h, i); + ret = h->ae_algo->ops->reset_queue(h, i); + if (ret) + return ret; + hns3_init_ring_hw(priv->ring_data[i].ring); /* We need to clear tx ring here because self test will @@ -3701,18 +3742,30 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) bool vlan_filter_enable; int ret; - hns3_init_mac_addr(netdev, false); - hns3_recover_hw_addr(netdev); - hns3_update_promisc_mode(netdev, handle->netdev_flags); + ret = hns3_init_mac_addr(netdev, false); + if (ret) + return ret; + + ret = hns3_recover_hw_addr(netdev); + if (ret) + return ret; + + ret = hns3_update_promisc_mode(netdev, handle->netdev_flags); + if (ret) + return ret; + vlan_filter_enable = netdev->flags & IFF_PROMISC ? false : true; hns3_enable_vlan_filter(netdev, vlan_filter_enable); - /* Hardware table is only clear when pf resets */ - if (!(handle->flags & HNAE3_SUPPORT_VF)) - hns3_restore_vlan(netdev); + if (!(handle->flags & HNAE3_SUPPORT_VF)) { + ret = hns3_restore_vlan(netdev); + return ret; + } - hns3_restore_fd_rules(netdev); + ret = hns3_restore_fd_rules(netdev); + if (ret) + return ret; /* Carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 71cfca132d0bd0..d3636d088aa3d9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -640,7 +640,7 @@ void hns3_set_vector_coalesce_rl(struct hns3_enet_tqp_vector *tqp_vector, u32 rl_value); void hns3_enable_vlan_filter(struct net_device *netdev, bool enable); -void hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags); +int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags); #ifdef CONFIG_HNS3_DCB void hns3_dcbnl_setup(struct hnae3_handle *handle); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index ac13cb2b168e5a..690f62ed87dcaa 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -24,15 +24,15 @@ static int hclge_ring_space(struct hclge_cmq_ring *ring) return ring->desc_num - used - 1; } -static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int h) +static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int head) { - int u = ring->next_to_use; - int c = ring->next_to_clean; + int ntu = ring->next_to_use; + int ntc = ring->next_to_clean; - if (unlikely(h >= ring->desc_num)) - return 0; + if (ntu > ntc) + return head >= ntc && head <= ntu; - return u > c ? (h > c && h <= u) : (h > c || h <= u); + return head >= ntc || head <= ntu; } static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring) @@ -304,6 +304,10 @@ int hclge_cmd_queue_init(struct hclge_dev *hdev) { int ret; + /* Setup the lock for command queue */ + spin_lock_init(&hdev->hw.cmq.csq.lock); + spin_lock_init(&hdev->hw.cmq.crq.lock); + /* Setup the queue entries for use cmd queue */ hdev->hw.cmq.csq.desc_num = HCLGE_NIC_CMQ_DESC_NUM; hdev->hw.cmq.crq.desc_num = HCLGE_NIC_CMQ_DESC_NUM; @@ -337,18 +341,20 @@ int hclge_cmd_init(struct hclge_dev *hdev) u32 version; int ret; + spin_lock_bh(&hdev->hw.cmq.csq.lock); + spin_lock_bh(&hdev->hw.cmq.crq.lock); + hdev->hw.cmq.csq.next_to_clean = 0; hdev->hw.cmq.csq.next_to_use = 0; hdev->hw.cmq.crq.next_to_clean = 0; hdev->hw.cmq.crq.next_to_use = 0; - /* Setup the lock for command queue */ - spin_lock_init(&hdev->hw.cmq.csq.lock); - spin_lock_init(&hdev->hw.cmq.crq.lock); - hclge_cmd_init_regs(&hdev->hw); clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); + spin_unlock_bh(&hdev->hw.cmq.crq.lock); + spin_unlock_bh(&hdev->hw.cmq.csq.lock); + ret = hclge_cmd_query_firmware_version(&hdev->hw, &version); if (ret) { dev_err(&hdev->pdev->dev, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index dca6f2326c2672..123c37e653f3ed 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -751,7 +751,7 @@ static void hclge_process_ncsi_error(struct hclge_dev *hdev, ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd, HCLGE_NCSI_INT_CLR, 0); if (ret) - dev_err(dev, "failed(=%d) to clear NCSI intrerrupt status\n", + dev_err(dev, "failed(=%d) to clear NCSI interrupt status\n", ret); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 5234b5373ed3b9..ffdd96020860db 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2236,7 +2236,7 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) } /* clear the source of interrupt if it is not cause by reset */ - if (event_cause != HCLGE_VECTOR0_EVENT_RST) { + if (event_cause == HCLGE_VECTOR0_EVENT_MBX) { hclge_clear_event_cause(hdev, event_cause, clearval); hclge_enable_vector(&hdev->misc_vector, true); } @@ -2470,14 +2470,17 @@ static void hclge_reset(struct hclge_dev *hdev) handle = &hdev->vport[0].nic; rtnl_lock(); hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); + rtnl_unlock(); if (!hclge_reset_wait(hdev)) { + rtnl_lock(); hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT); hclge_reset_ae_dev(hdev->ae_dev); hclge_notify_client(hdev, HNAE3_INIT_CLIENT); hclge_clear_reset_cause(hdev); } else { + rtnl_lock(); /* schedule again to check pending resets later */ set_bit(hdev->reset_type, &hdev->reset_pending); hclge_reset_task_schedule(hdev); @@ -3314,8 +3317,8 @@ void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, param->vf_id = vport_id; } -static void hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, - bool en_mc_pmc) +static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, + bool en_mc_pmc) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -3323,7 +3326,7 @@ static void hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, hclge_promisc_param_init(¶m, en_uc_pmc, en_mc_pmc, true, vport->vport_id); - hclge_cmd_set_promisc_mode(hdev, ¶m); + return hclge_cmd_set_promisc_mode(hdev, ¶m); } static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode) @@ -6107,31 +6110,28 @@ static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, return tqp->index; } -void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id) +int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; int reset_try_times = 0; int reset_status; u16 queue_gid; - int ret; - - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) - return; + int ret = 0; queue_gid = hclge_covert_handle_qid_global(handle, queue_id); ret = hclge_tqp_enable(hdev, queue_id, 0, false); if (ret) { - dev_warn(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret); - return; + dev_err(&hdev->pdev->dev, "Disable tqp fail, ret = %d\n", ret); + return ret; } ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, true); if (ret) { - dev_warn(&hdev->pdev->dev, - "Send reset tqp cmd fail, ret = %d\n", ret); - return; + dev_err(&hdev->pdev->dev, + "Send reset tqp cmd fail, ret = %d\n", ret); + return ret; } reset_try_times = 0; @@ -6144,16 +6144,16 @@ void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id) } if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) { - dev_warn(&hdev->pdev->dev, "Reset TQP fail\n"); - return; + dev_err(&hdev->pdev->dev, "Reset TQP fail\n"); + return ret; } ret = hclge_send_reset_tqp_cmd(hdev, queue_gid, false); - if (ret) { - dev_warn(&hdev->pdev->dev, - "Deassert the soft reset fail, ret = %d\n", ret); - return; - } + if (ret) + dev_err(&hdev->pdev->dev, + "Deassert the soft reset fail, ret = %d\n", ret); + + return ret; } void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index e3dfd654eca9a1..0d92154042699c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -778,7 +778,7 @@ int hclge_rss_init_hw(struct hclge_dev *hdev); void hclge_rss_indir_init_cfg(struct hclge_dev *hdev); void hclge_mbx_handler(struct hclge_dev *hdev); -void hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id); +int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id); void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id); int hclge_cfg_flowctrl(struct hclge_dev *hdev); int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 04462a347a9407..f890022938d9a1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -400,6 +400,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev) /* handle all the mailbox requests in the queue */ while (!hclge_cmd_crq_empty(&hdev->hw)) { + if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) { + dev_warn(&hdev->pdev->dev, + "command queue needs re-initializing\n"); + return; + } + desc = &crq->desc[crq->next_to_use]; req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 24b1f2a0c32afc..03018638f701b3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -52,7 +52,7 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum, struct hclge_desc desc; int ret; - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) return 0; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, false); @@ -90,7 +90,7 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum) struct hclge_desc desc; int ret; - if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) + if (test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) return 0; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MDIO_CONFIG, true); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index e0a86a58342c28..085edb945389c5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -925,12 +925,12 @@ static int hclgevf_cmd_set_promisc_mode(struct hclgevf_dev *hdev, return status; } -static void hclgevf_set_promisc_mode(struct hnae3_handle *handle, - bool en_uc_pmc, bool en_mc_pmc) +static int hclgevf_set_promisc_mode(struct hnae3_handle *handle, + bool en_uc_pmc, bool en_mc_pmc) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); - hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc); + return hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc); } static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id, @@ -1080,7 +1080,7 @@ static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) 1, false, NULL, 0); } -static void hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id) +static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); u8 msg_data[2]; @@ -1091,10 +1091,10 @@ static void hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id) /* disable vf queue before send queue reset msg to PF */ ret = hclgevf_tqp_enable(hdev, queue_id, 0, false); if (ret) - return; + return ret; - hclgevf_send_mbx_msg(hdev, HCLGE_MBX_QUEUE_RESET, 0, msg_data, - 2, true, NULL, 0); + return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_QUEUE_RESET, 0, msg_data, + 2, true, NULL, 0); } static int hclgevf_notify_client(struct hclgevf_dev *hdev, @@ -1170,6 +1170,8 @@ static int hclgevf_reset(struct hclgevf_dev *hdev) /* bring down the nic to stop any ongoing TX/RX */ hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT); + rtnl_unlock(); + /* check if VF could successfully fetch the hardware reset completion * status from the hardware */ @@ -1181,12 +1183,15 @@ static int hclgevf_reset(struct hclgevf_dev *hdev) ret); dev_warn(&hdev->pdev->dev, "VF reset failed, disabling VF!\n"); + rtnl_lock(); hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT); rtnl_unlock(); return ret; } + rtnl_lock(); + /* now, re-initialize the nic client and ae device*/ ret = hclgevf_reset_stack(hdev); if (ret) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c index 967c993d5303ab..bbf9bdd0ee3e74 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c @@ -532,7 +532,7 @@ void hinic_task_set_inner_l3(struct hinic_sq_task *task, } void hinic_task_set_tunnel_l4(struct hinic_sq_task *task, - enum hinic_l4_offload_type l4_type, + enum hinic_l4_tunnel_type l4_type, u32 tunnel_len) { task->pkt_info2 |= HINIC_SQ_TASK_INFO2_SET(l4_type, TUNNEL_L4TYPE) | diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h index a0dc63a4bfc7ab..038522e202b6f6 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h @@ -160,7 +160,7 @@ void hinic_task_set_inner_l3(struct hinic_sq_task *task, u32 network_len); void hinic_task_set_tunnel_l4(struct hinic_sq_task *task, - enum hinic_l4_offload_type l4_type, + enum hinic_l4_tunnel_type l4_type, u32 tunnel_len); void hinic_set_cs_inner_l4(struct hinic_sq_task *task, diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index fd3373d82a9e94..59e1bc0f609ee3 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -200,6 +200,15 @@ config IXGBE_DCB If unsure, say N. +config IXGBE_IPSEC + bool "IPSec XFRM cryptography-offload acceleration" + depends on IXGBE + depends on XFRM_OFFLOAD + default y + select XFRM_ALGO + ---help--- + Enable support for IPSec offload in ixgbe.ko + config IXGBEVF tristate "Intel(R) 10GbE PCI Express Virtual Function Ethernet support" depends on PCI_MSI @@ -217,6 +226,15 @@ config IXGBEVF will be called ixgbevf. MSI-X interrupt support is required for this driver to work correctly. +config IXGBEVF_IPSEC + bool "IPSec XFRM cryptography-offload acceleration" + depends on IXGBEVF + depends on XFRM_OFFLOAD + default y + select XFRM_ALGO + ---help--- + Enable support for IPSec offload in ixgbevf.ko + config I40E tristate "Intel(R) Ethernet Controller XL710 Family support" imply PTP_1588_CLOCK diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index e707d717012faa..5d4f1761dc0c2e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -244,7 +244,8 @@ process_mbx: } /* guarantee we have free space in the SM mailbox */ - if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) { + if (hw->mbx.state == FM10K_STATE_OPEN && + !hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) { /* keep track of how many times this occurs */ interface->hw_sm_mbx_full++; @@ -302,6 +303,28 @@ void fm10k_iov_suspend(struct pci_dev *pdev) } } +static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev) +{ + u32 err_mask; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); + if (!pos) + return; + + /* Mask the completion abort bit in the ERR_UNCOR_MASK register, + * preventing the device from reporting these errors to the upstream + * PCIe root device. This avoids bringing down platforms which upgrade + * non-fatal completer aborts into machine check exceptions. Completer + * aborts can occur whenever a VF reads a queue it doesn't own. + */ + pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask); + err_mask |= PCI_ERR_UNC_COMP_ABORT; + pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask); + + mmiowb(); +} + int fm10k_iov_resume(struct pci_dev *pdev) { struct fm10k_intfc *interface = pci_get_drvdata(pdev); @@ -317,6 +340,12 @@ int fm10k_iov_resume(struct pci_dev *pdev) if (!iov_data) return -ENOMEM; + /* Lower severity of completer abort error reporting as + * the VFs can trigger this any time they read a queue + * that they don't own. + */ + fm10k_mask_aer_comp_abort(pdev); + /* allocate hardware resources for the VFs */ hw->iov.ops.assign_resources(hw, num_vfs, num_vfs); @@ -460,20 +489,6 @@ void fm10k_iov_disable(struct pci_dev *pdev) fm10k_iov_free_data(pdev); } -static void fm10k_disable_aer_comp_abort(struct pci_dev *pdev) -{ - u32 err_sev; - int pos; - - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR); - if (!pos) - return; - - pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, &err_sev); - err_sev &= ~PCI_ERR_UNC_COMP_ABORT; - pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_SEVER, err_sev); -} - int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) { int current_vfs = pci_num_vf(pdev); @@ -495,12 +510,6 @@ int fm10k_iov_configure(struct pci_dev *pdev, int num_vfs) /* allocate VFs if not already allocated */ if (num_vfs && num_vfs != current_vfs) { - /* Disable completer abort error reporting as - * the VFs can trigger this any time they read a queue - * that they don't own. - */ - fm10k_disable_aer_comp_abort(pdev); - err = pci_enable_sriov(pdev, num_vfs); if (err) { dev_err(&pdev->dev, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 503bbc0177922c..5b2a50e5798f75 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -11,7 +11,7 @@ #include "fm10k.h" -#define DRV_VERSION "0.23.4-k" +#define DRV_VERSION "0.26.1-k" #define DRV_SUMMARY "Intel(R) Ethernet Switch Host Interface Driver" const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 02345d3813036c..e49fb51d36133f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -23,6 +23,8 @@ static const struct fm10k_info *fm10k_info_tbl[] = { */ static const struct pci_device_id fm10k_pci_tbl[] = { { PCI_VDEVICE(INTEL, FM10K_DEV_ID_PF), fm10k_device_pf }, + { PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_QDA2), fm10k_device_pf }, + { PCI_VDEVICE(INTEL, FM10K_DEV_ID_SDI_FM10420_DA2), fm10k_device_pf }, { PCI_VDEVICE(INTEL, FM10K_DEV_ID_VF), fm10k_device_vf }, /* required last entry */ { 0, } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 3e608e493f9df6..9fb9fca375e3f6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -15,6 +15,8 @@ struct fm10k_hw; #define FM10K_DEV_ID_PF 0x15A4 #define FM10K_DEV_ID_VF 0x15A5 +#define FM10K_DEV_ID_SDI_FM10420_QDA2 0x15D0 +#define FM10K_DEV_ID_SDI_FM10420_DA2 0x15D5 #define FM10K_MAX_QUEUES 256 #define FM10K_MAX_QUEUES_PF 128 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 81b0e1f8d14b6d..ac5698ed0b1119 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3674,7 +3674,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, dev_err(&pf->pdev->dev, "Invalid message from VF %d, opcode %d, len %d\n", local_vf_id, v_opcode, msglen); switch (ret) { - case VIRTCHNL_ERR_PARAM: + case VIRTCHNL_STATUS_ERR_PARAM: return -EPERM; default: return -EINVAL; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 9f4d700e09df33..29ced6b74d3646 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -51,9 +51,15 @@ * * The 40 bit 82580 SYSTIM overflows every * 2^40 * 10^-9 / 60 = 18.3 minutes. + * + * SYSTIM is converted to real time using a timecounter. As + * timecounter_cyc2time() allows old timestamps, the timecounter + * needs to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, so we aim for 8 + * minutes to be sure the actual interval is shorter than 9.16 minutes. */ -#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 8) #define IGB_PTP_TX_TIMEOUT (HZ * 15) #define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index ca6b0c458e4a50..4fb0d9e3f2da21 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -17,4 +17,4 @@ ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o -ixgbe-$(CONFIG_XFRM_OFFLOAD) += ixgbe_ipsec.o +ixgbe-$(CONFIG_IXGBE_IPSEC) += ixgbe_ipsec.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index ec1b87cc441009..143bdd5ee2a088 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -769,9 +769,9 @@ struct ixgbe_adapter { #define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ u32 *rss_key; -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBE_IPSEC struct ixgbe_ipsec *ipsec; -#endif /* CONFIG_XFRM_OFFLOAD */ +#endif /* CONFIG_IXGBE_IPSEC */ /* AF_XDP zero-copy */ struct xdp_umem **xsk_umems; @@ -1008,7 +1008,7 @@ void ixgbe_store_key(struct ixgbe_adapter *adapter); void ixgbe_store_reta(struct ixgbe_adapter *adapter); s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm); -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBE_IPSEC void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter); void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter); void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter); @@ -1036,5 +1036,5 @@ static inline int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf) { return -EACCES; } static inline int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf) { return -EACCES; } -#endif /* CONFIG_XFRM_OFFLOAD */ +#endif /* CONFIG_IXGBE_IPSEC */ #endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0049a2becd7e73..113b38e0defbf5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8694,7 +8694,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, #endif /* IXGBE_FCOE */ -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBE_IPSEC if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) goto out_drop; #endif @@ -10190,7 +10190,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, * the TSO, so it's the exception. */ if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) { -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBE_IPSEC if (!skb->sp) #endif features &= ~NETIF_F_TSO; @@ -10883,7 +10883,7 @@ skip_sriov: if (hw->mac.type >= ixgbe_mac_82599EB) netdev->features |= NETIF_F_SCTP_CRC; -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBE_IPSEC #define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \ NETIF_F_HW_ESP_TX_CSUM | \ NETIF_F_GSO_ESP) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index af25a8fffeb8ba..5dacfc87025988 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -722,8 +722,10 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, adapter->default_up, vf); - if (vfinfo->spoofchk_enabled) + if (vfinfo->spoofchk_enabled) { hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + hw->mac.ops.set_mac_anti_spoofing(hw, true, vf); + } } /* reset multicast table array for vf */ diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile index 297d0f0858b59e..186a4bb24fdea5 100644 --- a/drivers/net/ethernet/intel/ixgbevf/Makefile +++ b/drivers/net/ethernet/intel/ixgbevf/Makefile @@ -10,5 +10,5 @@ ixgbevf-objs := vf.o \ mbx.o \ ethtool.o \ ixgbevf_main.o -ixgbevf-$(CONFIG_XFRM_OFFLOAD) += ipsec.o +ixgbevf-$(CONFIG_IXGBEVF_IPSEC) += ipsec.o diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index e399e1c0c54ab1..ecab686574b65d 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -459,7 +459,7 @@ int ethtool_ioctl(struct ifreq *ifr); extern void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector); -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBEVF_IPSEC void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter); void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter); void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter); @@ -482,7 +482,7 @@ static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, struct ixgbevf_tx_buffer *first, struct ixgbevf_ipsec_tx_data *itd) { return 0; } -#endif /* CONFIG_XFRM_OFFLOAD */ +#endif /* CONFIG_IXGBEVF_IPSEC */ void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter); void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 98707ee11d7266..5e47ede7e83200 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4150,7 +4150,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, first->tx_flags = tx_flags; first->protocol = vlan_get_protocol(skb); -#ifdef CONFIG_XFRM_OFFLOAD +#ifdef CONFIG_IXGBEVF_IPSEC if (skb->sp && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx)) goto out_drop; #endif diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 176c6b56fdccda..398328f107437e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -796,6 +796,7 @@ struct mvpp2_queue_vector { int nrxqs; u32 pending_cause_rx; struct mvpp2_port *port; + struct cpumask *mask; }; struct mvpp2_port { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 14f9679c957c6a..7a37a37e3fb347 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3298,24 +3298,30 @@ static int mvpp2_irqs_init(struct mvpp2_port *port) for (i = 0; i < port->nqvecs; i++) { struct mvpp2_queue_vector *qv = port->qvecs + i; - if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) + if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) { + qv->mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!qv->mask) { + err = -ENOMEM; + goto err; + } + irq_set_status_flags(qv->irq, IRQ_NO_BALANCING); + } err = request_irq(qv->irq, mvpp2_isr, 0, port->dev->name, qv); if (err) goto err; if (qv->type == MVPP2_QUEUE_VECTOR_PRIVATE) { - unsigned long mask = 0; unsigned int cpu; for_each_present_cpu(cpu) { if (mvpp2_cpu_to_thread(port->priv, cpu) == qv->sw_thread_id) - mask |= BIT(cpu); + cpumask_set_cpu(cpu, qv->mask); } - irq_set_affinity_hint(qv->irq, to_cpumask(&mask)); + irq_set_affinity_hint(qv->irq, qv->mask); } } @@ -3325,6 +3331,8 @@ err: struct mvpp2_queue_vector *qv = port->qvecs + i; irq_set_affinity_hint(qv->irq, NULL); + kfree(qv->mask); + qv->mask = NULL; free_irq(qv->irq, qv); } @@ -3339,6 +3347,8 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port) struct mvpp2_queue_vector *qv = port->qvecs + i; irq_set_affinity_hint(qv->irq, NULL); + kfree(qv->mask); + qv->mask = NULL; irq_clear_status_flags(qv->irq, IRQ_NO_BALANCING); free_irq(qv->irq, qv); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 5a6d0919533d6e..db00bf1c23f5ad 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -43,6 +43,7 @@ #include <linux/vmalloc.h> #include <linux/irq.h> +#include <net/ip.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ip6_checksum.h> #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 94224c22ecc310..79638dcbae7839 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -713,43 +713,15 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb) rq->stats->ecn_mark += !!rc; } -static __be32 mlx5e_get_fcs(struct sk_buff *skb) +static u32 mlx5e_get_fcs(const struct sk_buff *skb) { - int last_frag_sz, bytes_in_prev, nr_frags; - u8 *fcs_p1, *fcs_p2; - skb_frag_t *last_frag; - __be32 fcs_bytes; + const void *fcs_bytes; + u32 _fcs_bytes; - if (!skb_is_nonlinear(skb)) - return *(__be32 *)(skb->data + skb->len - ETH_FCS_LEN); + fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN, + ETH_FCS_LEN, &_fcs_bytes); - nr_frags = skb_shinfo(skb)->nr_frags; - last_frag = &skb_shinfo(skb)->frags[nr_frags - 1]; - last_frag_sz = skb_frag_size(last_frag); - - /* If all FCS data is in last frag */ - if (last_frag_sz >= ETH_FCS_LEN) - return *(__be32 *)(skb_frag_address(last_frag) + - last_frag_sz - ETH_FCS_LEN); - - fcs_p2 = (u8 *)skb_frag_address(last_frag); - bytes_in_prev = ETH_FCS_LEN - last_frag_sz; - - /* Find where the other part of the FCS is - Linear or another frag */ - if (nr_frags == 1) { - fcs_p1 = skb_tail_pointer(skb); - } else { - skb_frag_t *prev_frag = &skb_shinfo(skb)->frags[nr_frags - 2]; - - fcs_p1 = skb_frag_address(prev_frag) + - skb_frag_size(prev_frag); - } - fcs_p1 -= bytes_in_prev; - - memcpy(&fcs_bytes, fcs_p1, bytes_in_prev); - memcpy(((u8 *)&fcs_bytes) + bytes_in_prev, fcs_p2, last_frag_sz); - - return fcs_bytes; + return __get_unaligned_cpu32(fcs_bytes); } static u8 get_ip_proto(struct sk_buff *skb, __be16 proto) @@ -797,8 +769,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, network_depth - ETH_HLEN, skb->csum); if (unlikely(netdev->features & NETIF_F_RXFCS)) - skb->csum = csum_add(skb->csum, - (__force __wsum)mlx5e_get_fcs(skb)); + skb->csum = csum_block_add(skb->csum, + (__force __wsum)mlx5e_get_fcs(skb), + skb->len - ETH_FCS_LEN); stats->csum_complete++; return; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 937d0ace699a7e..30f751e696980d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -943,8 +943,8 @@ static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink, mlxsw_core->bus, mlxsw_core->bus_priv, true, devlink); - if (err) - mlxsw_core->reload_fail = true; + mlxsw_core->reload_fail = !!err; + return err; } @@ -1083,8 +1083,15 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (mlxsw_core->reload_fail) - goto reload_fail; + if (mlxsw_core->reload_fail) { + if (!reload) + /* Only the parts that were not de-initialized in the + * failed reload attempt need to be de-initialized. + */ + goto reload_fail_deinit; + else + return; + } if (mlxsw_core->driver->fini) mlxsw_core->driver->fini(mlxsw_core); @@ -1098,9 +1105,12 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, if (!reload) devlink_resources_unregister(devlink, NULL); mlxsw_core->bus->fini(mlxsw_core->bus_priv); - if (reload) - return; -reload_fail: + + return; + +reload_fail_deinit: + devlink_unregister(devlink); + devlink_resources_unregister(devlink, NULL); devlink_free(devlink); } EXPORT_SYMBOL(mlxsw_core_bus_device_unregister); diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 32cb6718bb173f..db3d2790aeecf9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3284,7 +3284,7 @@ static inline void mlxsw_reg_qtct_pack(char *payload, u8 local_port, * Configures the ETS elements. */ #define MLXSW_REG_QEEC_ID 0x400D -#define MLXSW_REG_QEEC_LEN 0x1C +#define MLXSW_REG_QEEC_LEN 0x20 MLXSW_REG_DEFINE(qeec, MLXSW_REG_QEEC_ID, MLXSW_REG_QEEC_LEN); @@ -3326,6 +3326,15 @@ MLXSW_ITEM32(reg, qeec, element_index, 0x04, 0, 8); */ MLXSW_ITEM32(reg, qeec, next_element_index, 0x08, 0, 8); +/* reg_qeec_mise + * Min shaper configuration enable. Enables configuration of the min + * shaper on this ETS element + * 0 - Disable + * 1 - Enable + * Access: RW + */ +MLXSW_ITEM32(reg, qeec, mise, 0x0C, 31, 1); + enum { MLXSW_REG_QEEC_BYTES_MODE, MLXSW_REG_QEEC_PACKETS_MODE, @@ -3342,6 +3351,17 @@ enum { */ MLXSW_ITEM32(reg, qeec, pb, 0x0C, 28, 1); +/* The smallest permitted min shaper rate. */ +#define MLXSW_REG_QEEC_MIS_MIN 200000 /* Kbps */ + +/* reg_qeec_min_shaper_rate + * Min shaper information rate. + * For CPU port, can only be configured for port hierarchy. + * When in bytes mode, value is specified in units of 1000bps. + * Access: RW + */ +MLXSW_ITEM32(reg, qeec, min_shaper_rate, 0x0C, 0, 28); + /* reg_qeec_mase * Max shaper configuration enable. Enables configuration of the max * shaper on this ETS element. diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 8a4983adae940a..a2df12b79f8e91 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2740,6 +2740,21 @@ int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl); } +static int mlxsw_sp_port_min_bw_set(struct mlxsw_sp_port *mlxsw_sp_port, + enum mlxsw_reg_qeec_hr hr, u8 index, + u8 next_index, u32 minrate) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char qeec_pl[MLXSW_REG_QEEC_LEN]; + + mlxsw_reg_qeec_pack(qeec_pl, mlxsw_sp_port->local_port, hr, index, + next_index); + mlxsw_reg_qeec_mise_set(qeec_pl, true); + mlxsw_reg_qeec_min_shaper_rate_set(qeec_pl, minrate); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qeec), qeec_pl); +} + int mlxsw_sp_port_prio_tc_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 switch_prio, u8 tclass) { @@ -2817,6 +2832,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) return err; } + /* Configure the min shaper for multicast TCs. */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + err = mlxsw_sp_port_min_bw_set(mlxsw_sp_port, + MLXSW_REG_QEEC_HIERARCY_TC, + i + 8, i, + MLXSW_REG_QEEC_MIS_MIN); + if (err) + return err; + } + /* Map all priorities to traffic class 0. */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { err = mlxsw_sp_port_prio_tc_set(mlxsw_sp_port, i, 0); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index bc60d7a8b49d76..739a51f0a366f4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -2661,8 +2661,6 @@ static void mlxsw_sp_switchdev_bridge_fdb_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; - if (!fdb_info->added_by_user) - break; mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false); break; case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index b72ef171477e0e..bdd351597b5525 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -243,7 +243,7 @@ static int stmmac_mdio_write(struct mii_bus *bus, int phyaddr, int phyreg, */ int stmmac_mdio_reset(struct mii_bus *bus) { -#if defined(CONFIG_STMMAC_PLATFORM) +#if IS_ENABLED(CONFIG_STMMAC_PLATFORM) struct net_device *ndev = bus->priv; struct stmmac_priv *priv = netdev_priv(ndev); unsigned int mii_address = priv->hw->mii.addr; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e52b9d3c0bd6cc..0b70c8bab045ac 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1704,7 +1704,6 @@ __nvme_fc_init_request(struct nvme_fc_ctrl *ctrl, op->fcp_req.rspaddr = &op->rsp_iu; op->fcp_req.rsplen = sizeof(op->rsp_iu); op->fcp_req.done = nvme_fc_fcpio_done; - op->fcp_req.private = &op->fcp_req.first_sgl[SG_CHUNK_SIZE]; op->ctrl = ctrl; op->queue = queue; op->rq = rq; @@ -1752,6 +1751,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, if (res) return res; op->op.fcp_req.first_sgl = &op->sgl[0]; + op->op.fcp_req.private = &op->priv[0]; return res; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index f30031945ee4b6..c33bb201b8846f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1663,6 +1663,9 @@ static void nvme_map_cmb(struct nvme_dev *dev) struct pci_dev *pdev = to_pci_dev(dev->dev); int bar; + if (dev->cmb_size) + return; + dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ); if (!dev->cmbsz) return; @@ -2147,7 +2150,6 @@ static void nvme_pci_disable(struct nvme_dev *dev) { struct pci_dev *pdev = to_pci_dev(dev->dev); - nvme_release_cmb(dev); pci_free_irq_vectors(pdev); if (pci_is_enabled(pdev)) { @@ -2595,6 +2597,7 @@ static void nvme_remove(struct pci_dev *pdev) nvme_stop_ctrl(&dev->ctrl); nvme_remove_namespaces(&dev->ctrl); nvme_dev_disable(dev, true); + nvme_release_cmb(dev); nvme_free_host_mem(dev); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0); diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 39d972e2595f0d..01feebec29ea2d 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -101,7 +101,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, rw = READ; } - iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count); + iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count); iocb->ki_pos = pos; iocb->ki_filp = req->ns->file; diff --git a/drivers/of/base.c b/drivers/of/base.c index d023cf303d56c3..09692c9b32a71c 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -777,8 +777,6 @@ struct device_node *of_get_next_cpu_node(struct device_node *prev) if (!(of_node_name_eq(next, "cpu") || (next->type && !of_node_cmp(next->type, "cpu")))) continue; - if (!__of_device_is_available(next)) - continue; if (of_node_get(next)) break; } diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index bdac939de223c9..54f6a40c75c69c 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -60,7 +60,10 @@ config ACERHDF After loading this driver the BIOS is still in control of the fan. To let the kernel handle the fan, do: - echo -n enabled > /sys/class/thermal/thermal_zone0/mode + echo -n enabled > /sys/class/thermal/thermal_zoneN/mode + where N=0,1,2... depending on the number of thermal nodes and the + detection order of your particular system. The "type" parameter + in the same node directory will tell you if it is "acerhdf". For more information about this driver see <http://piie.net/files/acerhdf_README.txt> @@ -105,6 +108,22 @@ config ASUS_LAPTOP If you have an ACPI-compatible ASUS laptop, say Y or M here. +config DCDBAS + tristate "Dell Systems Management Base Driver" + depends on X86 + help + The Dell Systems Management Base Driver provides a sysfs interface + for systems management software to perform System Management + Interrupts (SMIs) and Host Control Actions (system power cycle or + power off after OS shutdown) on certain Dell systems. + + See <file:Documentation/dcdbas.txt> for more details on the driver + and the Dell systems on which Dell systems management software makes + use of this driver. + + Say Y or M here to enable the driver for use by Dell systems + management software such as Dell OpenManage. + # # The DELL_SMBIOS driver depends on ACPI_WMI and/or DCDBAS if those # backends are selected. The "depends" line prevents a configuration @@ -227,6 +246,18 @@ config DELL_RBTN To compile this driver as a module, choose M here: the module will be called dell-rbtn. +config DELL_RBU + tristate "BIOS update support for DELL systems via sysfs" + depends on X86 + select FW_LOADER + select FW_LOADER_USER_HELPER + help + Say m if you want to have the option of updating the BIOS for your + DELL system. Note you need a Dell OpenManage or Dell Update package (DUP) + supporting application to communicate with the BIOS regarding the new + image for the image update to take effect. + See <file:Documentation/dell_rbu.txt> for more details on the driver. + config FUJITSU_LAPTOP tristate "Fujitsu Laptop Extras" @@ -336,6 +367,20 @@ config HP_WMI To compile this driver as a module, choose M here: the module will be called hp-wmi. +config LG_LAPTOP + tristate "LG Laptop Extras" + depends on ACPI + depends on ACPI_WMI + depends on INPUT + select INPUT_SPARSEKMAP + select LEDS_CLASS + help + This driver adds support for hotkeys as well as control of keyboard + backlight, battery maximum charge level and various other ACPI + features. + + If you have an LG Gram laptop, say Y or M here. + config MSI_LAPTOP tristate "MSI Laptop Extras" depends on ACPI @@ -1231,6 +1276,18 @@ config I2C_MULTI_INSTANTIATE To compile this driver as a module, choose M here: the module will be called i2c-multi-instantiate. +config INTEL_ATOMISP2_PM + tristate "Intel AtomISP2 dummy / power-management driver" + depends on PCI && IOSF_MBI && PM + help + Power-management driver for Intel's Image Signal Processor found on + Bay and Cherry Trail devices. This dummy driver's sole purpose is to + turn the ISP off (put it in D3) to save power and to allow entering + of S0ix modes. + + To compile this driver as a module, choose M here: the module + will be called intel_atomisp2_pm. + endif # X86_PLATFORM_DEVICES config PMC_ATOM diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index e6d1becf81ce8c..39ae94135406b6 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -9,9 +9,11 @@ obj-$(CONFIG_ASUS_NB_WMI) += asus-nb-wmi.o obj-$(CONFIG_ASUS_WIRELESS) += asus-wireless.o obj-$(CONFIG_EEEPC_LAPTOP) += eeepc-laptop.o obj-$(CONFIG_EEEPC_WMI) += eeepc-wmi.o +obj-$(CONFIG_LG_LAPTOP) += lg-laptop.o obj-$(CONFIG_MSI_LAPTOP) += msi-laptop.o obj-$(CONFIG_ACPI_CMPC) += classmate-laptop.o obj-$(CONFIG_COMPAL_LAPTOP) += compal-laptop.o +obj-$(CONFIG_DCDBAS) += dcdbas.o obj-$(CONFIG_DELL_SMBIOS) += dell-smbios.o dell-smbios-objs := dell-smbios-base.o dell-smbios-$(CONFIG_DELL_SMBIOS_WMI) += dell-smbios-wmi.o @@ -23,6 +25,7 @@ obj-$(CONFIG_DELL_WMI_AIO) += dell-wmi-aio.o obj-$(CONFIG_DELL_WMI_LED) += dell-wmi-led.o obj-$(CONFIG_DELL_SMO8800) += dell-smo8800.o obj-$(CONFIG_DELL_RBTN) += dell-rbtn.o +obj-$(CONFIG_DELL_RBU) += dell_rbu.o obj-$(CONFIG_ACER_WMI) += acer-wmi.o obj-$(CONFIG_ACER_WIRELESS) += acer-wireless.o obj-$(CONFIG_ACERHDF) += acerhdf.o @@ -92,3 +95,4 @@ obj-$(CONFIG_MLX_PLATFORM) += mlx-platform.o obj-$(CONFIG_INTEL_TURBO_MAX_3) += intel_turbo_max_3.o obj-$(CONFIG_INTEL_CHTDC_TI_PWRBTN) += intel_chtdc_ti_pwrbtn.o obj-$(CONFIG_I2C_MULTI_INSTANTIATE) += i2c-multi-instantiate.o +obj-$(CONFIG_INTEL_ATOMISP2_PM) += intel_atomisp2_pm.o diff --git a/drivers/platform/x86/acerhdf.c b/drivers/platform/x86/acerhdf.c index ea22591ee66feb..50522422537886 100644 --- a/drivers/platform/x86/acerhdf.c +++ b/drivers/platform/x86/acerhdf.c @@ -86,6 +86,7 @@ static unsigned int interval = 10; static unsigned int fanon = 60000; static unsigned int fanoff = 53000; static unsigned int verbose; +static unsigned int list_supported; static unsigned int fanstate = ACERHDF_FAN_AUTO; static char force_bios[16]; static char force_product[16]; @@ -104,10 +105,12 @@ module_param(fanoff, uint, 0600); MODULE_PARM_DESC(fanoff, "Turn the fan off below this temperature"); module_param(verbose, uint, 0600); MODULE_PARM_DESC(verbose, "Enable verbose dmesg output"); +module_param(list_supported, uint, 0600); +MODULE_PARM_DESC(list_supported, "List supported models and BIOS versions"); module_param_string(force_bios, force_bios, 16, 0); -MODULE_PARM_DESC(force_bios, "Force BIOS version and omit BIOS check"); +MODULE_PARM_DESC(force_bios, "Pretend system has this known supported BIOS version"); module_param_string(force_product, force_product, 16, 0); -MODULE_PARM_DESC(force_product, "Force BIOS product and omit BIOS check"); +MODULE_PARM_DESC(force_product, "Pretend system is this known supported model"); /* * cmd_off: to switch the fan completely off and check if the fan is off @@ -130,7 +133,7 @@ static const struct manualcmd mcmd = { .moff = 0xff, }; -/* BIOS settings */ +/* BIOS settings - only used during probe */ struct bios_settings { const char *vendor; const char *product; @@ -141,8 +144,18 @@ struct bios_settings { int mcmd_enable; }; +/* This could be a daughter struct in the above, but not worth the redirect */ +struct ctrl_settings { + u8 fanreg; + u8 tempreg; + struct fancmd cmd; + int mcmd_enable; +}; + +static struct ctrl_settings ctrl_cfg __read_mostly; + /* Register addresses and values for different BIOS versions */ -static const struct bios_settings bios_tbl[] = { +static const struct bios_settings bios_tbl[] __initconst = { /* AOA110 */ {"Acer", "AOA110", "v0.3109", 0x55, 0x58, {0x1f, 0x00}, 0}, {"Acer", "AOA110", "v0.3114", 0x55, 0x58, {0x1f, 0x00}, 0}, @@ -233,6 +246,7 @@ static const struct bios_settings bios_tbl[] = { {"Gateway", "LT31", "v1.3201", 0x55, 0x58, {0x9e, 0x00}, 0}, {"Gateway", "LT31", "v1.3302", 0x55, 0x58, {0x9e, 0x00}, 0}, {"Gateway", "LT31", "v1.3303t", 0x55, 0x58, {0x9e, 0x00}, 0}, + {"Gateway", "LT31", "v1.3307", 0x55, 0x58, {0x9e, 0x00}, 0}, /* Packard Bell */ {"Packard Bell", "DOA150", "v0.3104", 0x55, 0x58, {0x21, 0x00}, 0}, {"Packard Bell", "DOA150", "v0.3105", 0x55, 0x58, {0x20, 0x00}, 0}, @@ -256,8 +270,6 @@ static const struct bios_settings bios_tbl[] = { {"", "", "", 0, 0, {0, 0}, 0} }; -static const struct bios_settings *bios_cfg __read_mostly; - /* * this struct is used to instruct thermal layer to use bang_bang instead of * default governor for acerhdf @@ -270,7 +282,7 @@ static int acerhdf_get_temp(int *temp) { u8 read_temp; - if (ec_read(bios_cfg->tempreg, &read_temp)) + if (ec_read(ctrl_cfg.tempreg, &read_temp)) return -EINVAL; *temp = read_temp * 1000; @@ -282,10 +294,10 @@ static int acerhdf_get_fanstate(int *state) { u8 fan; - if (ec_read(bios_cfg->fanreg, &fan)) + if (ec_read(ctrl_cfg.fanreg, &fan)) return -EINVAL; - if (fan != bios_cfg->cmd.cmd_off) + if (fan != ctrl_cfg.cmd.cmd_off) *state = ACERHDF_FAN_AUTO; else *state = ACERHDF_FAN_OFF; @@ -306,13 +318,13 @@ static void acerhdf_change_fanstate(int state) state = ACERHDF_FAN_AUTO; } - cmd = (state == ACERHDF_FAN_OFF) ? bios_cfg->cmd.cmd_off - : bios_cfg->cmd.cmd_auto; + cmd = (state == ACERHDF_FAN_OFF) ? ctrl_cfg.cmd.cmd_off + : ctrl_cfg.cmd.cmd_auto; fanstate = state; - ec_write(bios_cfg->fanreg, cmd); + ec_write(ctrl_cfg.fanreg, cmd); - if (bios_cfg->mcmd_enable && state == ACERHDF_FAN_OFF) { + if (ctrl_cfg.mcmd_enable && state == ACERHDF_FAN_OFF) { if (verbose) pr_notice("turning off fan manually\n"); ec_write(mcmd.mreg, mcmd.moff); @@ -615,10 +627,11 @@ static int str_starts_with(const char *str, const char *start) } /* check hardware */ -static int acerhdf_check_hardware(void) +static int __init acerhdf_check_hardware(void) { char const *vendor, *version, *product; const struct bios_settings *bt = NULL; + int found = 0; /* get BIOS data */ vendor = dmi_get_system_info(DMI_SYS_VENDOR); @@ -632,6 +645,17 @@ static int acerhdf_check_hardware(void) pr_info("Acer Aspire One Fan driver, v.%s\n", DRV_VER); + if (list_supported) { + pr_info("List of supported Manufacturer/Model/BIOS:\n"); + pr_info("---------------------------------------------------\n"); + for (bt = bios_tbl; bt->vendor[0]; bt++) { + pr_info("%-13s | %-17s | %-10s\n", bt->vendor, + bt->product, bt->version); + } + pr_info("---------------------------------------------------\n"); + return -ECANCELED; + } + if (force_bios[0]) { version = force_bios; pr_info("forcing BIOS version: %s\n", version); @@ -657,30 +681,36 @@ static int acerhdf_check_hardware(void) if (str_starts_with(vendor, bt->vendor) && str_starts_with(product, bt->product) && str_starts_with(version, bt->version)) { - bios_cfg = bt; + found = 1; break; } } - if (!bios_cfg) { + if (!found) { pr_err("unknown (unsupported) BIOS version %s/%s/%s, please report, aborting!\n", vendor, product, version); return -EINVAL; } + /* Copy control settings from BIOS table before we free it. */ + ctrl_cfg.fanreg = bt->fanreg; + ctrl_cfg.tempreg = bt->tempreg; + memcpy(&ctrl_cfg.cmd, &bt->cmd, sizeof(struct fancmd)); + ctrl_cfg.mcmd_enable = bt->mcmd_enable; + /* * if started with kernel mode off, prevent the kernel from switching * off the fan */ if (!kernelmode) { pr_notice("Fan control off, to enable do:\n"); - pr_notice("echo -n \"enabled\" > /sys/class/thermal/thermal_zone0/mode\n"); + pr_notice("echo -n \"enabled\" > /sys/class/thermal/thermal_zoneN/mode # N=0,1,2...\n"); } return 0; } -static int acerhdf_register_platform(void) +static int __init acerhdf_register_platform(void) { int err = 0; @@ -712,7 +742,7 @@ static void acerhdf_unregister_platform(void) platform_driver_unregister(&acerhdf_driver); } -static int acerhdf_register_thermal(void) +static int __init acerhdf_register_thermal(void) { cl_dev = thermal_cooling_device_register("acerhdf-fan", NULL, &acerhdf_cooling_ops); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 93ee2d5466f809..c285a16675ee7d 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -43,6 +43,7 @@ #include <linux/hwmon-sysfs.h> #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/platform_data/x86/asus-wmi.h> #include <linux/platform_device.h> #include <linux/thermal.h> #include <linux/acpi.h> @@ -69,89 +70,6 @@ MODULE_LICENSE("GPL"); #define NOTIFY_KBD_BRTDWN 0xc5 #define NOTIFY_KBD_BRTTOGGLE 0xc7 -/* WMI Methods */ -#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ -#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ -#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ -#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ -#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ -#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ -#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ -#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ -#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ -#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ -#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ -#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ -#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ -#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ -#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ -#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ -#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ -#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ -#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ -#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ - -#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE - -/* Wireless */ -#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 -#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 -#define ASUS_WMI_DEVID_CWAP 0x00010003 -#define ASUS_WMI_DEVID_WLAN 0x00010011 -#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 -#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 -#define ASUS_WMI_DEVID_GPS 0x00010015 -#define ASUS_WMI_DEVID_WIMAX 0x00010017 -#define ASUS_WMI_DEVID_WWAN3G 0x00010019 -#define ASUS_WMI_DEVID_UWB 0x00010021 - -/* Leds */ -/* 0x000200XX and 0x000400XX */ -#define ASUS_WMI_DEVID_LED1 0x00020011 -#define ASUS_WMI_DEVID_LED2 0x00020012 -#define ASUS_WMI_DEVID_LED3 0x00020013 -#define ASUS_WMI_DEVID_LED4 0x00020014 -#define ASUS_WMI_DEVID_LED5 0x00020015 -#define ASUS_WMI_DEVID_LED6 0x00020016 - -/* Backlight and Brightness */ -#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ -#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 -#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 -#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 -#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ -#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 - -/* Misc */ -#define ASUS_WMI_DEVID_CAMERA 0x00060013 - -/* Storage */ -#define ASUS_WMI_DEVID_CARDREADER 0x00080013 - -/* Input */ -#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 -#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 - -/* Fan, Thermal */ -#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 -#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 - -/* Power */ -#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 - -/* Deep S3 / Resume on LID open */ -#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 - -/* DSTS masks */ -#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 -#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 -#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 -#define ASUS_WMI_DSTS_USER_BIT 0x00020000 -#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 -#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF -#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 -#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F - #define ASUS_FAN_DESC "cpu_fan" #define ASUS_FAN_MFUN 0x13 #define ASUS_FAN_SFUN_READ 0x06 @@ -239,7 +157,6 @@ struct asus_wmi { int lightbar_led_wk; struct workqueue_struct *led_workqueue; struct work_struct tpd_led_work; - struct work_struct kbd_led_work; struct work_struct wlan_led_work; struct work_struct lightbar_led_work; @@ -302,8 +219,7 @@ static void asus_wmi_input_exit(struct asus_wmi *asus) asus->inputdev = NULL; } -static int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, - u32 *retval) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval) { struct bios_args args = { .arg0 = arg0, @@ -339,6 +255,7 @@ exit: return 0; } +EXPORT_SYMBOL_GPL(asus_wmi_evaluate_method); static int asus_wmi_evaluate_method_agfn(const struct acpi_buffer args) { @@ -456,12 +373,9 @@ static enum led_brightness tpd_led_get(struct led_classdev *led_cdev) return read_tpd_led_state(asus); } -static void kbd_led_update(struct work_struct *work) +static void kbd_led_update(struct asus_wmi *asus) { int ctrl_param = 0; - struct asus_wmi *asus; - - asus = container_of(work, struct asus_wmi, kbd_led_work); /* * bits 0-2: level @@ -471,7 +385,6 @@ static void kbd_led_update(struct work_struct *work) ctrl_param = 0x80 | (asus->kbd_led_wk & 0x7F); asus_wmi_set_devstate(ASUS_WMI_DEVID_KBD_BACKLIGHT, ctrl_param, NULL); - led_classdev_notify_brightness_hw_changed(&asus->kbd_led, asus->kbd_led_wk); } static int kbd_led_read(struct asus_wmi *asus, int *level, int *env) @@ -516,7 +429,7 @@ static void do_kbd_led_set(struct led_classdev *led_cdev, int value) value = 0; asus->kbd_led_wk = value; - queue_work(asus->led_workqueue, &asus->kbd_led_work); + kbd_led_update(asus); } static void kbd_led_set(struct led_classdev *led_cdev, @@ -525,6 +438,14 @@ static void kbd_led_set(struct led_classdev *led_cdev, do_kbd_led_set(led_cdev, value); } +static void kbd_led_set_by_kbd(struct asus_wmi *asus, enum led_brightness value) +{ + struct led_classdev *led_cdev = &asus->kbd_led; + + do_kbd_led_set(led_cdev, value); + led_classdev_notify_brightness_hw_changed(led_cdev, asus->kbd_led_wk); +} + static enum led_brightness kbd_led_get(struct led_classdev *led_cdev) { struct asus_wmi *asus; @@ -671,8 +592,6 @@ static int asus_wmi_led_init(struct asus_wmi *asus) led_val = kbd_led_read(asus, NULL, NULL); if (led_val >= 0) { - INIT_WORK(&asus->kbd_led_work, kbd_led_update); - asus->kbd_led_wk = led_val; asus->kbd_led.name = "asus::kbd_backlight"; asus->kbd_led.flags = LED_BRIGHT_HW_CHANGED; @@ -1746,18 +1665,18 @@ static void asus_wmi_notify(u32 value, void *context) } if (code == NOTIFY_KBD_BRTUP) { - do_kbd_led_set(&asus->kbd_led, asus->kbd_led_wk + 1); + kbd_led_set_by_kbd(asus, asus->kbd_led_wk + 1); goto exit; } if (code == NOTIFY_KBD_BRTDWN) { - do_kbd_led_set(&asus->kbd_led, asus->kbd_led_wk - 1); + kbd_led_set_by_kbd(asus, asus->kbd_led_wk - 1); goto exit; } if (code == NOTIFY_KBD_BRTTOGGLE) { if (asus->kbd_led_wk == asus->kbd_led.max_brightness) - do_kbd_led_set(&asus->kbd_led, 0); + kbd_led_set_by_kbd(asus, 0); else - do_kbd_led_set(&asus->kbd_led, asus->kbd_led_wk + 1); + kbd_led_set_by_kbd(asus, asus->kbd_led_wk + 1); goto exit; } @@ -2291,7 +2210,7 @@ static int asus_hotk_resume(struct device *device) struct asus_wmi *asus = dev_get_drvdata(device); if (!IS_ERR_OR_NULL(asus->kbd_led.dev)) - queue_work(asus->led_workqueue, &asus->kbd_led_work); + kbd_led_update(asus); return 0; } @@ -2327,7 +2246,7 @@ static int asus_hotk_restore(struct device *device) rfkill_set_sw_state(asus->uwb.rfkill, bl); } if (!IS_ERR_OR_NULL(asus->kbd_led.dev)) - queue_work(asus->led_workqueue, &asus->kbd_led_work); + kbd_led_update(asus); return 0; } diff --git a/drivers/firmware/dcdbas.c b/drivers/platform/x86/dcdbas.c index 0bdea60c65ddbf..88bd7efafe14a3 100644 --- a/drivers/firmware/dcdbas.c +++ b/drivers/platform/x86/dcdbas.c @@ -21,11 +21,13 @@ */ #include <linux/platform_device.h> +#include <linux/acpi.h> #include <linux/dma-mapping.h> #include <linux/errno.h> #include <linux/cpu.h> #include <linux/gfp.h> #include <linux/init.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/mc146818rtc.h> #include <linux/module.h> @@ -36,12 +38,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/mutex.h> -#include <asm/io.h> #include "dcdbas.h" #define DRIVER_NAME "dcdbas" -#define DRIVER_VERSION "5.6.0-3.2" +#define DRIVER_VERSION "5.6.0-3.3" #define DRIVER_DESCRIPTION "Dell Systems Management Base Driver" static struct platform_device *dcdbas_pdev; @@ -49,19 +50,23 @@ static struct platform_device *dcdbas_pdev; static u8 *smi_data_buf; static dma_addr_t smi_data_buf_handle; static unsigned long smi_data_buf_size; +static unsigned long max_smi_data_buf_size = MAX_SMI_DATA_BUF_SIZE; static u32 smi_data_buf_phys_addr; static DEFINE_MUTEX(smi_data_lock); +static u8 *eps_buffer; static unsigned int host_control_action; static unsigned int host_control_smi_type; static unsigned int host_control_on_shutdown; +static bool wsmt_enabled; + /** * smi_data_buf_free: free SMI data buffer */ static void smi_data_buf_free(void) { - if (!smi_data_buf) + if (!smi_data_buf || wsmt_enabled) return; dev_dbg(&dcdbas_pdev->dev, "%s: phys: %x size: %lu\n", @@ -86,7 +91,7 @@ static int smi_data_buf_realloc(unsigned long size) if (smi_data_buf_size >= size) return 0; - if (size > MAX_SMI_DATA_BUF_SIZE) + if (size > max_smi_data_buf_size) return -EINVAL; /* new buffer is needed */ @@ -169,7 +174,7 @@ static ssize_t smi_data_write(struct file *filp, struct kobject *kobj, { ssize_t ret; - if ((pos + count) > MAX_SMI_DATA_BUF_SIZE) + if ((pos + count) > max_smi_data_buf_size) return -EINVAL; mutex_lock(&smi_data_lock); @@ -322,8 +327,20 @@ static ssize_t smi_request_store(struct device *dev, ret = count; break; case 1: - /* Calling Interface SMI */ - smi_cmd->ebx = (u32) virt_to_phys(smi_cmd->command_buffer); + /* + * Calling Interface SMI + * + * Provide physical address of command buffer field within + * the struct smi_cmd to BIOS. + * + * Because the address that smi_cmd (smi_data_buf) points to + * will be from memremap() of a non-memory address if WSMT + * is present, we can't use virt_to_phys() on smi_cmd, so + * we have to use the physical address that was saved when + * the virtual address for smi_cmd was received. + */ + smi_cmd->ebx = smi_data_buf_phys_addr + + offsetof(struct smi_cmd, command_buffer); ret = dcdbas_smi_request(smi_cmd); if (!ret) ret = count; @@ -482,6 +499,93 @@ static void dcdbas_host_control(void) } } +/* WSMT */ + +static u8 checksum(u8 *buffer, u8 length) +{ + u8 sum = 0; + u8 *end = buffer + length; + + while (buffer < end) + sum += *buffer++; + return sum; +} + +static inline struct smm_eps_table *check_eps_table(u8 *addr) +{ + struct smm_eps_table *eps = (struct smm_eps_table *)addr; + + if (strncmp(eps->smm_comm_buff_anchor, SMM_EPS_SIG, 4) != 0) + return NULL; + + if (checksum(addr, eps->length) != 0) + return NULL; + + return eps; +} + +static int dcdbas_check_wsmt(void) +{ + struct acpi_table_wsmt *wsmt = NULL; + struct smm_eps_table *eps = NULL; + u64 remap_size; + u8 *addr; + + acpi_get_table(ACPI_SIG_WSMT, 0, (struct acpi_table_header **)&wsmt); + if (!wsmt) + return 0; + + /* Check if WSMT ACPI table shows that protection is enabled */ + if (!(wsmt->protection_flags & ACPI_WSMT_FIXED_COMM_BUFFERS) || + !(wsmt->protection_flags & ACPI_WSMT_COMM_BUFFER_NESTED_PTR_PROTECTION)) + return 0; + + /* Scan for EPS (entry point structure) */ + for (addr = (u8 *)__va(0xf0000); + addr < (u8 *)__va(0x100000 - sizeof(struct smm_eps_table)); + addr += 16) { + eps = check_eps_table(addr); + if (eps) + break; + } + + if (!eps) { + dev_dbg(&dcdbas_pdev->dev, "found WSMT, but no EPS found\n"); + return -ENODEV; + } + + /* + * Get physical address of buffer and map to virtual address. + * Table gives size in 4K pages, regardless of actual system page size. + */ + if (upper_32_bits(eps->smm_comm_buff_addr + 8)) { + dev_warn(&dcdbas_pdev->dev, "found WSMT, but EPS buffer address is above 4GB\n"); + return -EINVAL; + } + /* + * Limit remap size to MAX_SMI_DATA_BUF_SIZE + 8 (since the first 8 + * bytes are used for a semaphore, not the data buffer itself). + */ + remap_size = eps->num_of_4k_pages * PAGE_SIZE; + if (remap_size > MAX_SMI_DATA_BUF_SIZE + 8) + remap_size = MAX_SMI_DATA_BUF_SIZE + 8; + eps_buffer = memremap(eps->smm_comm_buff_addr, remap_size, MEMREMAP_WB); + if (!eps_buffer) { + dev_warn(&dcdbas_pdev->dev, "found WSMT, but failed to map EPS buffer\n"); + return -ENOMEM; + } + + /* First 8 bytes is for a semaphore, not part of the smi_data_buf */ + smi_data_buf_phys_addr = eps->smm_comm_buff_addr + 8; + smi_data_buf = eps_buffer + 8; + smi_data_buf_size = remap_size - 8; + max_smi_data_buf_size = smi_data_buf_size; + wsmt_enabled = true; + dev_info(&dcdbas_pdev->dev, + "WSMT found, using firmware-provided SMI buffer.\n"); + return 1; +} + /** * dcdbas_reboot_notify: handle reboot notification for host control */ @@ -548,6 +652,11 @@ static int dcdbas_probe(struct platform_device *dev) dcdbas_pdev = dev; + /* Check if ACPI WSMT table specifies protected SMI buffer address */ + error = dcdbas_check_wsmt(); + if (error < 0) + return error; + /* * BIOS SMI calls require buffer addresses be in 32-bit address space. * This is done by setting the DMA mask below. @@ -635,6 +744,8 @@ static void __exit dcdbas_exit(void) */ if (dcdbas_pdev) smi_data_buf_free(); + if (eps_buffer) + memunmap(eps_buffer); platform_device_unregister(dcdbas_pdev_reg); platform_driver_unregister(&dcdbas_driver); } diff --git a/drivers/firmware/dcdbas.h b/drivers/platform/x86/dcdbas.h index ca3cb0a54ab67a..52729a494b000e 100644 --- a/drivers/firmware/dcdbas.h +++ b/drivers/platform/x86/dcdbas.h @@ -53,6 +53,7 @@ #define EXPIRED_TIMER (0) #define SMI_CMD_MAGIC (0x534D4931) +#define SMM_EPS_SIG "$SCB" #define DCDBAS_DEV_ATTR_RW(_name) \ DEVICE_ATTR(_name,0600,_name##_show,_name##_store); @@ -103,5 +104,14 @@ struct apm_cmd { int dcdbas_smi_request(struct smi_cmd *smi_cmd); +struct smm_eps_table { + char smm_comm_buff_anchor[4]; + u8 length; + u8 checksum; + u8 version; + u64 smm_comm_buff_addr; + u64 num_of_4k_pages; +} __packed; + #endif /* _DCDBAS_H_ */ diff --git a/drivers/platform/x86/dell-smbios-smm.c b/drivers/platform/x86/dell-smbios-smm.c index 97a90bebc36079..ab9b822a6dfe6d 100644 --- a/drivers/platform/x86/dell-smbios-smm.c +++ b/drivers/platform/x86/dell-smbios-smm.c @@ -18,7 +18,7 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/platform_device.h> -#include "../../firmware/dcdbas.h" +#include "dcdbas.h" #include "dell-smbios.h" static int da_command_address; diff --git a/drivers/firmware/dell_rbu.c b/drivers/platform/x86/dell_rbu.c index fb8af5cb7c9bff..ccefa84f730576 100644 --- a/drivers/firmware/dell_rbu.c +++ b/drivers/platform/x86/dell_rbu.c @@ -45,6 +45,7 @@ #include <linux/moduleparam.h> #include <linux/firmware.h> #include <linux/dma-mapping.h> +#include <asm/set_memory.h> MODULE_AUTHOR("Abhay Salunke <abhay_salunke@dell.com>"); MODULE_DESCRIPTION("Driver for updating BIOS image on DELL systems"); @@ -181,6 +182,11 @@ static int create_packet(void *data, size_t length) packet_data_temp_buf = NULL; } } + /* + * set to uncachable or it may never get written back before reboot + */ + set_memory_uc((unsigned long)packet_data_temp_buf, 1 << ordernum); + spin_lock(&rbu_data.lock); newpacket->data = packet_data_temp_buf; @@ -349,6 +355,8 @@ static void packet_empty_list(void) * to make sure there are no stale RBU packets left in memory */ memset(newpacket->data, 0, rbu_data.packetsize); + set_memory_wb((unsigned long)newpacket->data, + 1 << newpacket->ordernum); free_pages((unsigned long) newpacket->data, newpacket->ordernum); kfree(newpacket); diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index d4f1259ff5a233..b6489cba29853e 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -212,7 +212,7 @@ static int read_ec_data(acpi_handle handle, int cmd, unsigned long *data) return 0; } } - pr_err("timeout in read_ec_cmd\n"); + pr_err("timeout in %s\n", __func__); return -1; } @@ -1147,6 +1147,13 @@ static const struct dmi_system_id no_hw_rfkill_list[] = { }, }, { + .ident = "Lenovo Legion Y530-15ICH", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion Y530-15ICH"), + }, + }, + { .ident = "Lenovo Legion Y720-15IKB", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 6cf9b7fa5bf048..e28bcf61b12698 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -1,19 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Intel HID event & 5 button array driver * * Copyright (C) 2015 Alex Hung <alex.hung@canonical.com> * Copyright (C) 2015 Andrew Lutomirski <luto@kernel.org> - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include <linux/acpi.h> diff --git a/drivers/platform/x86/intel-rst.c b/drivers/platform/x86/intel-rst.c index 7344d841f4d98d..3b81cb896fedff 100644 --- a/drivers/platform/x86/intel-rst.c +++ b/drivers/platform/x86/intel-rst.c @@ -1,26 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright 2013 Matthew Garrett <mjg59@srcf.ucam.org> - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ - -#include <linux/init.h> +#include <linux/acpi.h> #include <linux/module.h> #include <linux/slab.h> -#include <linux/acpi.h> MODULE_LICENSE("GPL"); @@ -53,12 +38,10 @@ static ssize_t irst_store_wakeup_events(struct device *dev, acpi = to_acpi_device(dev); error = kstrtoul(buf, 0, &value); - if (error) return error; status = acpi_execute_simple_method(acpi->handle, "SFFS", value); - if (ACPI_FAILURE(status)) return -EINVAL; @@ -99,12 +82,10 @@ static ssize_t irst_store_wakeup_time(struct device *dev, acpi = to_acpi_device(dev); error = kstrtoul(buf, 0, &value); - if (error) return error; status = acpi_execute_simple_method(acpi->handle, "SFTV", value); - if (ACPI_FAILURE(status)) return -EINVAL; diff --git a/drivers/platform/x86/intel-smartconnect.c b/drivers/platform/x86/intel-smartconnect.c index bbe4c06c769f66..64c2dc93472f47 100644 --- a/drivers/platform/x86/intel-smartconnect.c +++ b/drivers/platform/x86/intel-smartconnect.c @@ -1,25 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright 2013 Matthew Garrett <mjg59@srcf.ucam.org> - * - * 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. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ - -#include <linux/init.h> -#include <linux/module.h> #include <linux/acpi.h> +#include <linux/module.h> MODULE_LICENSE("GPL"); @@ -44,6 +29,7 @@ static const struct acpi_device_id smartconnect_ids[] = { {"INT33A0", 0}, {"", 0} }; +MODULE_DEVICE_TABLE(acpi, smartconnect_ids); static struct acpi_driver smartconnect_driver = { .owner = THIS_MODULE, @@ -56,5 +42,3 @@ static struct acpi_driver smartconnect_driver = { }; module_acpi_driver(smartconnect_driver); - -MODULE_DEVICE_TABLE(acpi, smartconnect_ids); diff --git a/drivers/platform/x86/intel-wmi-thunderbolt.c b/drivers/platform/x86/intel-wmi-thunderbolt.c index c2257bd06f1863..9ded8e2af312f2 100644 --- a/drivers/platform/x86/intel-wmi-thunderbolt.c +++ b/drivers/platform/x86/intel-wmi-thunderbolt.c @@ -1,16 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * WMI Thunderbolt driver * * Copyright (C) 2017 Dell Inc. All Rights Reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License version 2 as published - * by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -38,12 +30,16 @@ static ssize_t force_power_store(struct device *dev, input.length = sizeof(u8); input.pointer = &mode; mode = hex_to_bin(buf[0]); + dev_dbg(dev, "force_power: storing %#x\n", mode); if (mode == 0 || mode == 1) { status = wmi_evaluate_method(INTEL_WMI_THUNDERBOLT_GUID, 0, 1, &input, NULL); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + dev_dbg(dev, "force_power: failed to evaluate ACPI method\n"); return -ENODEV; + } } else { + dev_dbg(dev, "force_power: unsupported mode\n"); return -EINVAL; } return count; @@ -95,4 +91,4 @@ module_wmi_driver(intel_wmi_thunderbolt_driver); MODULE_ALIAS("wmi:" INTEL_WMI_THUNDERBOLT_GUID); MODULE_AUTHOR("Mario Limonciello <mario.limonciello@dell.com>"); MODULE_DESCRIPTION("Intel WMI Thunderbolt force power driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_atomisp2_pm.c b/drivers/platform/x86/intel_atomisp2_pm.c new file mode 100644 index 00000000000000..9371603a0ac90c --- /dev/null +++ b/drivers/platform/x86/intel_atomisp2_pm.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Dummy driver for Intel's Image Signal Processor found on Bay and Cherry + * Trail devices. The sole purpose of this driver is to allow the ISP to + * be put in D3. + * + * Copyright (C) 2018 Hans de Goede <hdegoede@redhat.com> + * + * Based on various non upstream patches for ISP support: + * Copyright (C) 2010-2017 Intel Corporation. All rights reserved. + * Copyright (c) 2010 Silicon Hive www.siliconhive.com. + */ + +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/pm_runtime.h> +#include <asm/iosf_mbi.h> + +/* PCI configuration regs */ +#define PCI_INTERRUPT_CTRL 0x9c + +#define PCI_CSI_CONTROL 0xe8 +#define PCI_CSI_CONTROL_PORTS_OFF_MASK 0x7 + +/* IOSF BT_MBI_UNIT_PMC regs */ +#define ISPSSPM0 0x39 +#define ISPSSPM0_ISPSSC_OFFSET 0 +#define ISPSSPM0_ISPSSC_MASK 0x00000003 +#define ISPSSPM0_ISPSSS_OFFSET 24 +#define ISPSSPM0_ISPSSS_MASK 0x03000000 +#define ISPSSPM0_IUNIT_POWER_ON 0x0 +#define ISPSSPM0_IUNIT_POWER_OFF 0x3 + +static int isp_probe(struct pci_dev *dev, const struct pci_device_id *id) +{ + unsigned long timeout; + u32 val; + + pci_write_config_dword(dev, PCI_INTERRUPT_CTRL, 0); + + /* + * MRFLD IUNIT DPHY is located in an always-power-on island + * MRFLD HW design need all CSI ports are disabled before + * powering down the IUNIT. + */ + pci_read_config_dword(dev, PCI_CSI_CONTROL, &val); + val |= PCI_CSI_CONTROL_PORTS_OFF_MASK; + pci_write_config_dword(dev, PCI_CSI_CONTROL, val); + + /* Write 0x3 to ISPSSPM0 bit[1:0] to power off the IUNIT */ + iosf_mbi_modify(BT_MBI_UNIT_PMC, MBI_REG_READ, ISPSSPM0, + ISPSSPM0_IUNIT_POWER_OFF, ISPSSPM0_ISPSSC_MASK); + + /* + * There should be no IUNIT access while power-down is + * in progress HW sighting: 4567865 + * Wait up to 50 ms for the IUNIT to shut down. + */ + timeout = jiffies + msecs_to_jiffies(50); + while (1) { + /* Wait until ISPSSPM0 bit[25:24] shows 0x3 */ + iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ, ISPSSPM0, &val); + val = (val & ISPSSPM0_ISPSSS_MASK) >> ISPSSPM0_ISPSSS_OFFSET; + if (val == ISPSSPM0_IUNIT_POWER_OFF) + break; + + if (time_after(jiffies, timeout)) { + dev_err(&dev->dev, "IUNIT power-off timeout.\n"); + return -EBUSY; + } + usleep_range(1000, 2000); + } + + pm_runtime_allow(&dev->dev); + pm_runtime_put_sync_suspend(&dev->dev); + + return 0; +} + +static void isp_remove(struct pci_dev *dev) +{ + pm_runtime_get_sync(&dev->dev); + pm_runtime_forbid(&dev->dev); +} + +static int isp_pci_suspend(struct device *dev) +{ + return 0; +} + +static int isp_pci_resume(struct device *dev) +{ + return 0; +} + +static UNIVERSAL_DEV_PM_OPS(isp_pm_ops, isp_pci_suspend, + isp_pci_resume, NULL); + +static const struct pci_device_id isp_id_table[] = { + { PCI_VDEVICE(INTEL, 0x22b8), }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, isp_id_table); + +static struct pci_driver isp_pci_driver = { + .name = "intel_atomisp2_pm", + .id_table = isp_id_table, + .probe = isp_probe, + .remove = isp_remove, + .driver.pm = &isp_pm_ops, +}; + +module_pci_driver(isp_pci_driver); + +MODULE_DESCRIPTION("Intel AtomISP2 dummy / power-management drv (for suspend)"); +MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_bxtwc_tmu.c b/drivers/platform/x86/intel_bxtwc_tmu.c index 227943a20212cc..951c105bafc1b8 100644 --- a/drivers/platform/x86/intel_bxtwc_tmu.c +++ b/drivers/platform/x86/intel_bxtwc_tmu.c @@ -1,21 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_bxtwc_tmu.c - Intel BXT Whiskey Cove PMIC TMU driver + * Intel BXT Whiskey Cove PMIC TMU driver * * Copyright (C) 2016 Intel Corporation. All rights reserved. * * This driver adds TMU (Time Management Unit) support for Intel BXT platform. * It enables the alarm wake-up functionality in the TMU unit of Whiskey Cove * PMIC. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include <linux/module.h> diff --git a/drivers/platform/x86/intel_cht_int33fe.c b/drivers/platform/x86/intel_cht_int33fe.c index f40b1c1921064b..464fe93657b53e 100644 --- a/drivers/platform/x86/intel_cht_int33fe.c +++ b/drivers/platform/x86/intel_cht_int33fe.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Cherry Trail ACPI INT33FE pseudo device driver * * Copyright (C) 2017 Hans de Goede <hdegoede@redhat.com> * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Some Intel Cherry Trail based device which ship with Windows 10, have * this weird INT33FE ACPI device with a CRS table with 4 I2cSerialBusV2 * resources, for 4 different chips attached to various i2c busses: @@ -257,4 +254,4 @@ module_platform_driver(cht_int33fe_driver); MODULE_DESCRIPTION("Intel Cherry Trail ACPI INT33FE pseudo device driver"); MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c b/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c index 38b8e7cfe88c06..0df2e82dd24924 100644 --- a/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c +++ b/drivers/platform/x86/intel_chtdc_ti_pwrbtn.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Power-button driver for Dollar Cove TI PMIC * Copyright (C) 2014 Intel Corp diff --git a/drivers/platform/x86/intel_int0002_vgpio.c b/drivers/platform/x86/intel_int0002_vgpio.c index e89ad4964dc139..4b8f7305fc8a77 100644 --- a/drivers/platform/x86/intel_int0002_vgpio.c +++ b/drivers/platform/x86/intel_int0002_vgpio.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel INT0002 "Virtual GPIO" driver * @@ -9,10 +10,6 @@ * * Author: Dyut Kumar Sil <dyut.k.sil@intel.com> * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * Some peripherals on Bay Trail and Cherry Trail platforms signal a Power * Management Event (PME) to the Power Management Controller (PMC) to wakeup * the system. When this happens software needs to clear the PME bus 0 status @@ -57,11 +54,7 @@ #define ICPU(model) { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, } static const struct x86_cpu_id int0002_cpu_ids[] = { -/* - * Limit ourselves to Cherry Trail for now, until testing shows we - * need to handle the INT0002 device on Baytrail too. - * ICPU(INTEL_FAM6_ATOM_SILVERMONT), * Valleyview, Bay Trail * - */ + ICPU(INTEL_FAM6_ATOM_SILVERMONT), /* Valleyview, Bay Trail */ ICPU(INTEL_FAM6_ATOM_AIRMONT), /* Braswell, Cherry Trail */ {} }; @@ -110,6 +103,21 @@ static void int0002_irq_mask(struct irq_data *data) outl(gpe_en_reg, GPE0A_EN_PORT); } +static int int0002_irq_set_wake(struct irq_data *data, unsigned int on) +{ + struct gpio_chip *chip = irq_data_get_irq_chip_data(data); + struct platform_device *pdev = to_platform_device(chip->parent); + int irq = platform_get_irq(pdev, 0); + + /* Propagate to parent irq */ + if (on) + enable_irq_wake(irq); + else + disable_irq_wake(irq); + + return 0; +} + static irqreturn_t int0002_irq(int irq, void *data) { struct gpio_chip *chip = data; @@ -132,6 +140,7 @@ static struct irq_chip int0002_irqchip = { .irq_ack = int0002_irq_ack, .irq_mask = int0002_irq_mask, .irq_unmask = int0002_irq_unmask, + .irq_set_wake = int0002_irq_set_wake, }; static int int0002_probe(struct platform_device *pdev) @@ -216,4 +225,4 @@ module_platform_driver(int0002_driver); MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>"); MODULE_DESCRIPTION("Intel INT0002 Virtual GPIO driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_ips.c b/drivers/platform/x86/intel_ips.c index c5ece7ef08c6df..225638a1b09e45 100644 --- a/drivers/platform/x86/intel_ips.c +++ b/drivers/platform/x86/intel_ips.c @@ -1,18 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2009-2010 Intel Corporation * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * * Authors: * Jesse Barnes <jbarnes@virtuousgeek.org> */ @@ -1697,6 +1686,6 @@ static struct pci_driver ips_pci_driver = { module_pci_driver(ips_pci_driver); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jesse Barnes <jbarnes@virtuousgeek.org>"); MODULE_DESCRIPTION("Intelligent Power Sharing Driver"); diff --git a/drivers/platform/x86/intel_ips.h b/drivers/platform/x86/intel_ips.h index 60f4e3ddbe9f5b..512ad234ad0d67 100644 --- a/drivers/platform/x86/intel_ips.h +++ b/drivers/platform/x86/intel_ips.h @@ -1,17 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2010 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". */ void ips_link_to_i915_driver(void); diff --git a/drivers/platform/x86/intel_menlow.c b/drivers/platform/x86/intel_menlow.c index ef9b0af8cdd36a..77eb8709c931c0 100644 --- a/drivers/platform/x86/intel_menlow.c +++ b/drivers/platform/x86/intel_menlow.c @@ -1,25 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_menlow.c - Intel menlow Driver for thermal management extension + * Intel menlow Driver for thermal management extension * * Copyright (C) 2008 Intel Corp * Copyright (C) 2008 Sujith Thomas <sujith.thomas@intel.com> * Copyright (C) 2008 Zhang Rui <rui.zhang@intel.com> - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * * This driver creates the sys I/F for programming the sensors. * It also implements the driver for intel menlow memory controller (hardware @@ -29,20 +14,19 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/acpi.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> #include <linux/pci.h> #include <linux/pm.h> +#include <linux/slab.h> #include <linux/thermal.h> -#include <linux/acpi.h> +#include <linux/types.h> MODULE_AUTHOR("Thomas Sujith"); MODULE_AUTHOR("Zhang Rui"); MODULE_DESCRIPTION("Intel Menlow platform specific driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); /* * Memory controller device control diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c index 5ad44204a9c3c9..292bace83f1e3d 100644 --- a/drivers/platform/x86/intel_mid_powerbtn.c +++ b/drivers/platform/x86/intel_mid_powerbtn.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Power button driver for Intel MID platforms. * @@ -5,18 +6,8 @@ * * Author: Hong Liu <hong.liu@intel.com> * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com> - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ -#include <linux/init.h> #include <linux/input.h> #include <linux/interrupt.h> #include <linux/mfd/intel_msic.h> @@ -121,12 +112,9 @@ static const struct mid_pb_ddata mrfld_ddata = { .setup = mrfld_setup, }; -#define ICPU(model, ddata) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (kernel_ulong_t)&ddata } - static const struct x86_cpu_id mid_pb_cpu_ids[] = { - ICPU(INTEL_FAM6_ATOM_SALTWELL_MID, mfld_ddata), - ICPU(INTEL_FAM6_ATOM_SILVERMONT_MID, mrfld_ddata), + INTEL_CPU_FAM6(ATOM_SALTWELL_MID, mfld_ddata), + INTEL_CPU_FAM6(ATOM_SILVERMONT_MID, mrfld_ddata), {} }; diff --git a/drivers/platform/x86/intel_mid_thermal.c b/drivers/platform/x86/intel_mid_thermal.c index 008a76903cbfb6..f402e2e74a3839 100644 --- a/drivers/platform/x86/intel_mid_thermal.c +++ b/drivers/platform/x86/intel_mid_thermal.c @@ -1,39 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_mid_thermal.c - Intel MID platform thermal driver + * Intel MID platform thermal driver * * Copyright (C) 2011 Intel Corporation * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * Author: Durgadoss R <durgadoss.r@intel.com> */ #define pr_fmt(fmt) "intel_mid_thermal: " fmt -#include <linux/module.h> -#include <linux/init.h> +#include <linux/device.h> #include <linux/err.h> +#include <linux/mfd/intel_msic.h> +#include <linux/module.h> #include <linux/param.h> -#include <linux/device.h> #include <linux/platform_device.h> -#include <linux/slab.h> #include <linux/pm.h> +#include <linux/slab.h> #include <linux/thermal.h> -#include <linux/mfd/intel_msic.h> /* Number of thermal sensors */ #define MSIC_THERMAL_SENSORS 4 @@ -567,4 +551,4 @@ module_platform_driver(mid_thermal_driver); MODULE_AUTHOR("Durgadoss R <durgadoss.r@intel.com>"); MODULE_DESCRIPTION("Intel Medfield Platform Thermal Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_oaktrail.c b/drivers/platform/x86/intel_oaktrail.c index 5747f63c8d9f49..3c0438ba385ee8 100644 --- a/drivers/platform/x86/intel_oaktrail.c +++ b/drivers/platform/x86/intel_oaktrail.c @@ -1,5 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0+ /* - * intel_oaktrail.c - Intel OakTrail Platform support. + * Intel OakTrail Platform support * * Copyright (C) 2010-2011 Intel Corporation * Author: Yin Kangkai (kangkai.yin@intel.com) @@ -8,21 +9,6 @@ * <cezary.jackiewicz (at) gmail.com>, based on MSI driver * Copyright (C) 2006 Lennart Poettering <mzxreary (at) 0pointer (dot) de> * - * 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. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - * 02110-1301, USA. - * * This driver does below things: * 1. registers itself in the Linux backlight control in * /sys/class/backlight/intel_oaktrail/ @@ -38,18 +24,18 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/init.h> #include <linux/acpi.h> -#include <linux/fb.h> -#include <linux/mutex.h> +#include <linux/backlight.h> +#include <linux/dmi.h> #include <linux/err.h> +#include <linux/fb.h> #include <linux/i2c.h> -#include <linux/backlight.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> #include <linux/platform_device.h> -#include <linux/dmi.h> #include <linux/rfkill.h> + #include <acpi/video.h> #define DRIVER_NAME "intel_oaktrail" diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index 2d272a3e017621..6b31d410cb09ab 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Core SoC Power Management Controller Driver * @@ -6,16 +7,6 @@ * * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com> * Vishwanath Somayaji <vishwanath.somayaji@intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h index 93a7e99e1f8b8a..be045348ad86b2 100644 --- a/drivers/platform/x86/intel_pmc_core.h +++ b/drivers/platform/x86/intel_pmc_core.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Core SoC Power Management Controller Header File * @@ -6,16 +7,6 @@ * * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com> * Vishwanath Somayaji <vishwanath.somayaji@intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef PMC_CORE_H diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c index e7edc8c6393674..7964ba22ef8d99 100644 --- a/drivers/platform/x86/intel_pmc_ipc.c +++ b/drivers/platform/x86/intel_pmc_ipc.c @@ -1,39 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_pmc_ipc.c: Driver for the Intel PMC IPC mechanism + * Driver for the Intel PMC IPC mechanism * * (C) Copyright 2014-2015 Intel Corporation * - * This driver is based on Intel SCU IPC driver(intel_scu_opc.c) by + * This driver is based on Intel SCU IPC driver(intel_scu_ipc.c) by * Sreedhara DS <sreedhara.ds@intel.com> * - * 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; version 2 - * of the License. - * * PMC running in ARC processor communicates with other entity running in IA * core through IPC mechanism which in turn messaging between IA core ad PMC. */ -#include <linux/module.h> +#include <linux/acpi.h> +#include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/delay.h> -#include <linux/errno.h> -#include <linux/init.h> #include <linux/device.h> -#include <linux/pm.h> +#include <linux/errno.h> +#include <linux/interrupt.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/notifier.h> #include <linux/pci.h> #include <linux/platform_device.h> -#include <linux/interrupt.h> +#include <linux/pm.h> #include <linux/pm_qos.h> -#include <linux/kernel.h> -#include <linux/bitops.h> #include <linux/sched.h> -#include <linux/atomic.h> -#include <linux/notifier.h> -#include <linux/suspend.h> -#include <linux/acpi.h> -#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/spinlock.h> +#include <linux/suspend.h> #include <asm/intel_pmc_ipc.h> @@ -1029,7 +1024,7 @@ static void __exit intel_pmc_ipc_exit(void) MODULE_AUTHOR("Zha Qipeng <qipeng.zha@intel.com>"); MODULE_DESCRIPTION("Intel PMC IPC driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); /* Some modules are dependent on this, so init earlier */ fs_initcall(intel_pmc_ipc_init); diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c index 2efeab650345c0..79671927f4ef6a 100644 --- a/drivers/platform/x86/intel_punit_ipc.c +++ b/drivers/platform/x86/intel_punit_ipc.c @@ -1,25 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Driver for the Intel P-Unit Mailbox IPC mechanism * * (C) Copyright 2015 Intel Corporation * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * * The heart of the P-Unit is the Foxton microcontroller and its firmware, * which provide mailbox interface for power management usage. */ -#include <linux/module.h> -#include <linux/mod_devicetable.h> #include <linux/acpi.h> -#include <linux/delay.h> #include <linux/bitops.h> +#include <linux/delay.h> #include <linux/device.h> #include <linux/interrupt.h> #include <linux/io.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> #include <linux/platform_device.h> + #include <asm/intel_punit_ipc.h> /* IPC Mailbox registers */ diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c index 75c8fef7a482c4..cdab916fbf9277 100644 --- a/drivers/platform/x86/intel_scu_ipc.c +++ b/drivers/platform/x86/intel_scu_ipc.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_scu_ipc.c: Driver for the Intel SCU IPC mechanism + * Driver for the Intel SCU IPC mechanism * * (C) Copyright 2008-2010,2015 Intel Corporation * Author: Sreedhara DS (sreedhara.ds@intel.com) * - * 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; version 2 - * of the License. - * * SCU running in ARC processor communicates with other entity running in IA * core through IPC mechanism which in turn messaging between IA core ad SCU. * SCU has two IPC mechanism IPC-1 and IPC-2. IPC-1 is used between IA32 and @@ -16,14 +12,16 @@ * IPC-1 Driver provides an API for power control unit registers (e.g. MSIC) * along with other APIs. */ + #include <linux/delay.h> +#include <linux/device.h> #include <linux/errno.h> #include <linux/init.h> -#include <linux/device.h> -#include <linux/pm.h> -#include <linux/pci.h> #include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/pm.h> #include <linux/sfi.h> + #include <asm/intel-mid.h> #include <asm/intel_scu_ipc.h> diff --git a/drivers/platform/x86/intel_scu_ipcutil.c b/drivers/platform/x86/intel_scu_ipcutil.c index aa454241489c9f..8afe6fa06d7b8d 100644 --- a/drivers/platform/x86/intel_scu_ipcutil.c +++ b/drivers/platform/x86/intel_scu_ipcutil.c @@ -1,32 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * intel_scu_ipc.c: Driver for the Intel SCU IPC mechanism + * Driver for the Intel SCU IPC mechanism * * (C) Copyright 2008-2010 Intel Corporation * Author: Sreedhara DS (sreedhara.ds@intel.com) * - * 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; version 2 - * of the License. - * - * This driver provides ioctl interfaces to call intel scu ipc driver api + * This driver provides IOCTL interfaces to call Intel SCU IPC driver API. */ -#include <linux/module.h> -#include <linux/kernel.h> #include <linux/errno.h> -#include <linux/types.h> -#include <linux/fs.h> #include <linux/fcntl.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/module.h> #include <linux/sched.h> -#include <linux/uaccess.h> #include <linux/slab.h> -#include <linux/init.h> +#include <linux/types.h> +#include <linux/uaccess.h> + #include <asm/intel_scu_ipc.h> static int major; -/* ioctl commnds */ +/* IOCTL commands */ #define INTE_SCU_IPC_REGISTER_READ 0 #define INTE_SCU_IPC_REGISTER_WRITE 1 #define INTE_SCU_IPC_REGISTER_UPDATE 2 diff --git a/drivers/platform/x86/intel_telemetry_core.c b/drivers/platform/x86/intel_telemetry_core.c index f378621b5fe9d8..d4040bb222b485 100644 --- a/drivers/platform/x86/intel_telemetry_core.c +++ b/drivers/platform/x86/intel_telemetry_core.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel SoC Core Telemetry Driver * Copyright (C) 2015, Intel Corporation. * 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, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * * Telemetry Framework provides platform related PM and performance statistics. * This file provides the core telemetry API implementation. */ @@ -460,4 +452,4 @@ module_exit(telemetry_module_exit); MODULE_AUTHOR("Souvik Kumar Chakravarty <souvik.k.chakravarty@intel.com>"); MODULE_DESCRIPTION("Intel SoC Telemetry Interface"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_telemetry_debugfs.c b/drivers/platform/x86/intel_telemetry_debugfs.c index cee08f23629245..40bce560eb30d9 100644 --- a/drivers/platform/x86/intel_telemetry_debugfs.c +++ b/drivers/platform/x86/intel_telemetry_debugfs.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel SOC Telemetry debugfs Driver: Currently supports APL * Copyright (c) 2015, Intel Corporation. * 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, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * * This file provides the debugfs interfaces for telemetry. * /sys/kernel/debug/telemetry/pss_info: Shows Primary Control Sub-Sys Counters * /sys/kernel/debug/telemetry/ioss_info: Shows IO Sub-System Counters @@ -72,9 +64,6 @@ #define TELEM_IOSS_DX_D0IX_EVTS 25 #define TELEM_IOSS_PG_EVTS 30 -#define TELEM_DEBUGFS_CPU(model, data) \ - { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&data} - #define TELEM_CHECK_AND_PARSE_EVTS(EVTID, EVTNUM, BUF, EVTLOG, EVTDAT, MASK) { \ if (evtlog[index].telem_evtid == (EVTID)) { \ for (idx = 0; idx < (EVTNUM); idx++) \ @@ -319,8 +308,8 @@ static struct telemetry_debugfs_conf telem_apl_debugfs_conf = { }; static const struct x86_cpu_id telemetry_debugfs_cpu_ids[] = { - TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT, telem_apl_debugfs_conf), - TELEM_DEBUGFS_CPU(INTEL_FAM6_ATOM_GOLDMONT_PLUS, telem_apl_debugfs_conf), + INTEL_CPU_FAM6(ATOM_GOLDMONT, telem_apl_debugfs_conf), + INTEL_CPU_FAM6(ATOM_GOLDMONT_PLUS, telem_apl_debugfs_conf), {} }; @@ -951,12 +940,16 @@ static int __init telemetry_debugfs_init(void) debugfs_conf = (struct telemetry_debugfs_conf *)id->driver_data; err = telemetry_pltconfig_valid(); - if (err < 0) + if (err < 0) { + pr_info("Invalid pltconfig, ensure IPC1 device is enabled in BIOS\n"); return -ENODEV; + } err = telemetry_debugfs_check_evts(); - if (err < 0) + if (err < 0) { + pr_info("telemetry_debugfs_check_evts failed\n"); return -EINVAL; + } register_pm_notifier(&pm_notifier); @@ -1037,4 +1030,4 @@ module_exit(telemetry_debugfs_exit); MODULE_AUTHOR("Souvik Kumar Chakravarty <souvik.k.chakravarty@intel.com>"); MODULE_DESCRIPTION("Intel SoC Telemetry debugfs Interface"); MODULE_VERSION(DRIVER_VERSION); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_telemetry_pltdrv.c b/drivers/platform/x86/intel_telemetry_pltdrv.c index fcc6bee51a422a..df8565bad595c7 100644 --- a/drivers/platform/x86/intel_telemetry_pltdrv.c +++ b/drivers/platform/x86/intel_telemetry_pltdrv.c @@ -1,17 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel SOC Telemetry Platform Driver: Currently supports APL * Copyright (c) 2015, Intel Corporation. * 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, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * * This file provides the platform specific telemetry implementation for APL. * It used the PUNIT and PMC IPC interfaces for configuring the counters. * The accumulated results are fetched from SRAM. @@ -1242,4 +1234,4 @@ module_exit(telemetry_module_exit); MODULE_AUTHOR("Souvik Kumar Chakravarty <souvik.k.chakravarty@intel.com>"); MODULE_DESCRIPTION("Intel SoC Telemetry Platform Driver"); MODULE_VERSION(DRIVER_VERSION); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/platform/x86/intel_turbo_max_3.c b/drivers/platform/x86/intel_turbo_max_3.c index a6d5aa0c3c479d..7b9cc841ab6557 100644 --- a/drivers/platform/x86/intel_turbo_max_3.c +++ b/drivers/platform/x86/intel_turbo_max_3.c @@ -1,28 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Turbo Boost Max Technology 3.0 legacy (non HWP) enumeration driver * Copyright (c) 2017, Intel Corporation. * All rights reserved. * * Author: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/kernel.h> +#include <linux/cpufeature.h> +#include <linux/cpuhotplug.h> #include <linux/init.h> +#include <linux/kernel.h> #include <linux/topology.h> #include <linux/workqueue.h> -#include <linux/cpuhotplug.h> -#include <linux/cpufeature.h> + #include <asm/cpu_device_id.h> #include <asm/intel-family.h> diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c new file mode 100644 index 00000000000000..c0bb1f864dfeb5 --- /dev/null +++ b/drivers/platform/x86/lg-laptop.c @@ -0,0 +1,700 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * lg-laptop.c - LG Gram ACPI features and hotkeys Driver + * + * Copyright (C) 2018 Matan Ziv-Av <matan@svgalib.org> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/acpi.h> +#include <linux/input.h> +#include <linux/input/sparse-keymap.h> +#include <linux/kernel.h> +#include <linux/leds.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define LED_DEVICE(_name, max) struct led_classdev _name = { \ + .name = __stringify(_name), \ + .max_brightness = max, \ + .brightness_set = _name##_set, \ + .brightness_get = _name##_get, \ +} + +MODULE_AUTHOR("Matan Ziv-Av"); +MODULE_DESCRIPTION("LG WMI Hotkey Driver"); +MODULE_LICENSE("GPL"); + +#define WMI_EVENT_GUID0 "E4FB94F9-7F2B-4173-AD1A-CD1D95086248" +#define WMI_EVENT_GUID1 "023B133E-49D1-4E10-B313-698220140DC2" +#define WMI_EVENT_GUID2 "37BE1AC0-C3F2-4B1F-BFBE-8FDEAF2814D6" +#define WMI_EVENT_GUID3 "911BAD44-7DF8-4FBB-9319-BABA1C4B293B" +#define WMI_METHOD_WMAB "C3A72B38-D3EF-42D3-8CBB-D5A57049F66D" +#define WMI_METHOD_WMBB "2B4F501A-BD3C-4394-8DCF-00A7D2BC8210" +#define WMI_EVENT_GUID WMI_EVENT_GUID0 + +#define WMAB_METHOD "\\XINI.WMAB" +#define WMBB_METHOD "\\XINI.WMBB" +#define SB_GGOV_METHOD "\\_SB.GGOV" +#define GOV_TLED 0x2020008 +#define WM_GET 1 +#define WM_SET 2 +#define WM_KEY_LIGHT 0x400 +#define WM_TLED 0x404 +#define WM_FN_LOCK 0x407 +#define WM_BATT_LIMIT 0x61 +#define WM_READER_MODE 0xBF +#define WM_FAN_MODE 0x33 +#define WMBB_USB_CHARGE 0x10B +#define WMBB_BATT_LIMIT 0x10C + +#define PLATFORM_NAME "lg-laptop" + +MODULE_ALIAS("wmi:" WMI_EVENT_GUID0); +MODULE_ALIAS("wmi:" WMI_EVENT_GUID1); +MODULE_ALIAS("wmi:" WMI_EVENT_GUID2); +MODULE_ALIAS("wmi:" WMI_EVENT_GUID3); +MODULE_ALIAS("wmi:" WMI_METHOD_WMAB); +MODULE_ALIAS("wmi:" WMI_METHOD_WMBB); +MODULE_ALIAS("acpi*:LGEX0815:*"); + +static struct platform_device *pf_device; +static struct input_dev *wmi_input_dev; + +static u32 inited; +#define INIT_INPUT_WMI_0 0x01 +#define INIT_INPUT_WMI_2 0x02 +#define INIT_INPUT_ACPI 0x04 +#define INIT_TPAD_LED 0x08 +#define INIT_KBD_LED 0x10 +#define INIT_SPARSE_KEYMAP 0x80 + +static const struct key_entry wmi_keymap[] = { + {KE_KEY, 0x70, {KEY_F15} }, /* LG control panel (F1) */ + {KE_KEY, 0x74, {KEY_F13} }, /* Touchpad toggle (F5) */ + {KE_KEY, 0xf020000, {KEY_F14} }, /* Read mode (F9) */ + {KE_KEY, 0x10000000, {KEY_F16} },/* Keyboard backlight (F8) - pressing + * this key both sends an event and + * changes backlight level. + */ + {KE_KEY, 0x80, {KEY_RFKILL} }, + {KE_END, 0} +}; + +static int ggov(u32 arg0) +{ + union acpi_object args[1]; + union acpi_object *r; + acpi_status status; + acpi_handle handle; + struct acpi_object_list arg; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + int res; + + args[0].type = ACPI_TYPE_INTEGER; + args[0].integer.value = arg0; + + status = acpi_get_handle(NULL, (acpi_string) SB_GGOV_METHOD, &handle); + if (ACPI_FAILURE(status)) { + pr_err("Cannot get handle"); + return -ENODEV; + } + + arg.count = 1; + arg.pointer = args; + + status = acpi_evaluate_object(handle, NULL, &arg, &buffer); + if (ACPI_FAILURE(status)) { + acpi_handle_err(handle, "GGOV: call failed.\n"); + return -EINVAL; + } + + r = buffer.pointer; + if (r->type != ACPI_TYPE_INTEGER) { + kfree(r); + return -EINVAL; + } + + res = r->integer.value; + kfree(r); + + return res; +} + +static union acpi_object *lg_wmab(u32 method, u32 arg1, u32 arg2) +{ + union acpi_object args[3]; + acpi_status status; + acpi_handle handle; + struct acpi_object_list arg; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + + args[0].type = ACPI_TYPE_INTEGER; + args[0].integer.value = method; + args[1].type = ACPI_TYPE_INTEGER; + args[1].integer.value = arg1; + args[2].type = ACPI_TYPE_INTEGER; + args[2].integer.value = arg2; + + status = acpi_get_handle(NULL, (acpi_string) WMAB_METHOD, &handle); + if (ACPI_FAILURE(status)) { + pr_err("Cannot get handle"); + return NULL; + } + + arg.count = 3; + arg.pointer = args; + + status = acpi_evaluate_object(handle, NULL, &arg, &buffer); + if (ACPI_FAILURE(status)) { + acpi_handle_err(handle, "WMAB: call failed.\n"); + return NULL; + } + + return buffer.pointer; +} + +static union acpi_object *lg_wmbb(u32 method_id, u32 arg1, u32 arg2) +{ + union acpi_object args[3]; + acpi_status status; + acpi_handle handle; + struct acpi_object_list arg; + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + u8 buf[32]; + + *(u32 *)buf = method_id; + *(u32 *)(buf + 4) = arg1; + *(u32 *)(buf + 16) = arg2; + args[0].type = ACPI_TYPE_INTEGER; + args[0].integer.value = 0; /* ignored */ + args[1].type = ACPI_TYPE_INTEGER; + args[1].integer.value = 1; /* Must be 1 or 2. Does not matter which */ + args[2].type = ACPI_TYPE_BUFFER; + args[2].buffer.length = 32; + args[2].buffer.pointer = buf; + + status = acpi_get_handle(NULL, (acpi_string)WMBB_METHOD, &handle); + if (ACPI_FAILURE(status)) { + pr_err("Cannot get handle"); + return NULL; + } + + arg.count = 3; + arg.pointer = args; + + status = acpi_evaluate_object(handle, NULL, &arg, &buffer); + if (ACPI_FAILURE(status)) { + acpi_handle_err(handle, "WMAB: call failed.\n"); + return NULL; + } + + return (union acpi_object *)buffer.pointer; +} + +static void wmi_notify(u32 value, void *context) +{ + struct acpi_buffer response = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object *obj; + acpi_status status; + long data = (long)context; + + pr_debug("event guid %li\n", data); + status = wmi_get_event_data(value, &response); + if (ACPI_FAILURE(status)) { + pr_err("Bad event status 0x%x\n", status); + return; + } + + obj = (union acpi_object *)response.pointer; + if (!obj) + return; + + if (obj->type == ACPI_TYPE_INTEGER) { + int eventcode = obj->integer.value; + struct key_entry *key; + + key = + sparse_keymap_entry_from_scancode(wmi_input_dev, eventcode); + if (key && key->type == KE_KEY) + sparse_keymap_report_entry(wmi_input_dev, key, 1, true); + } + + pr_debug("Type: %i Eventcode: 0x%llx\n", obj->type, + obj->integer.value); + kfree(response.pointer); +} + +static void wmi_input_setup(void) +{ + acpi_status status; + + wmi_input_dev = input_allocate_device(); + if (wmi_input_dev) { + wmi_input_dev->name = "LG WMI hotkeys"; + wmi_input_dev->phys = "wmi/input0"; + wmi_input_dev->id.bustype = BUS_HOST; + + if (sparse_keymap_setup(wmi_input_dev, wmi_keymap, NULL) || + input_register_device(wmi_input_dev)) { + pr_info("Cannot initialize input device"); + input_free_device(wmi_input_dev); + return; + } + + inited |= INIT_SPARSE_KEYMAP; + status = wmi_install_notify_handler(WMI_EVENT_GUID0, wmi_notify, + (void *)0); + if (ACPI_SUCCESS(status)) + inited |= INIT_INPUT_WMI_0; + + status = wmi_install_notify_handler(WMI_EVENT_GUID2, wmi_notify, + (void *)2); + if (ACPI_SUCCESS(status)) + inited |= INIT_INPUT_WMI_2; + } else { + pr_info("Cannot allocate input device"); + } +} + +static void acpi_notify(struct acpi_device *device, u32 event) +{ + struct key_entry *key; + + acpi_handle_debug(device->handle, "notify: %d\n", event); + if (inited & INIT_SPARSE_KEYMAP) { + key = sparse_keymap_entry_from_scancode(wmi_input_dev, 0x80); + if (key && key->type == KE_KEY) + sparse_keymap_report_entry(wmi_input_dev, key, 1, true); + } +} + +static ssize_t fan_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + bool value; + union acpi_object *r; + u32 m; + int ret; + + ret = kstrtobool(buffer, &value); + if (ret) + return ret; + + r = lg_wmab(WM_FAN_MODE, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_INTEGER) { + kfree(r); + return -EIO; + } + + m = r->integer.value; + kfree(r); + r = lg_wmab(WM_FAN_MODE, WM_SET, (m & 0xffffff0f) | (value << 4)); + kfree(r); + r = lg_wmab(WM_FAN_MODE, WM_SET, (m & 0xfffffff0) | value); + kfree(r); + + return count; +} + +static ssize_t fan_mode_show(struct device *dev, + struct device_attribute *attr, char *buffer) +{ + unsigned int status; + union acpi_object *r; + + r = lg_wmab(WM_FAN_MODE, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_INTEGER) { + kfree(r); + return -EIO; + } + + status = r->integer.value & 0x01; + kfree(r); + + return snprintf(buffer, PAGE_SIZE, "%d\n", status); +} + +static ssize_t usb_charge_store(struct device *dev, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + bool value; + union acpi_object *r; + int ret; + + ret = kstrtobool(buffer, &value); + if (ret) + return ret; + + r = lg_wmbb(WMBB_USB_CHARGE, WM_SET, value); + if (!r) + return -EIO; + + kfree(r); + return count; +} + +static ssize_t usb_charge_show(struct device *dev, + struct device_attribute *attr, char *buffer) +{ + unsigned int status; + union acpi_object *r; + + r = lg_wmbb(WMBB_USB_CHARGE, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_BUFFER) { + kfree(r); + return -EIO; + } + + status = !!r->buffer.pointer[0x10]; + + kfree(r); + + return snprintf(buffer, PAGE_SIZE, "%d\n", status); +} + +static ssize_t reader_mode_store(struct device *dev, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + bool value; + union acpi_object *r; + int ret; + + ret = kstrtobool(buffer, &value); + if (ret) + return ret; + + r = lg_wmab(WM_READER_MODE, WM_SET, value); + if (!r) + return -EIO; + + kfree(r); + return count; +} + +static ssize_t reader_mode_show(struct device *dev, + struct device_attribute *attr, char *buffer) +{ + unsigned int status; + union acpi_object *r; + + r = lg_wmab(WM_READER_MODE, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_INTEGER) { + kfree(r); + return -EIO; + } + + status = !!r->integer.value; + + kfree(r); + + return snprintf(buffer, PAGE_SIZE, "%d\n", status); +} + +static ssize_t fn_lock_store(struct device *dev, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + bool value; + union acpi_object *r; + int ret; + + ret = kstrtobool(buffer, &value); + if (ret) + return ret; + + r = lg_wmab(WM_FN_LOCK, WM_SET, value); + if (!r) + return -EIO; + + kfree(r); + return count; +} + +static ssize_t fn_lock_show(struct device *dev, + struct device_attribute *attr, char *buffer) +{ + unsigned int status; + union acpi_object *r; + + r = lg_wmab(WM_FN_LOCK, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_BUFFER) { + kfree(r); + return -EIO; + } + + status = !!r->buffer.pointer[0]; + kfree(r); + + return snprintf(buffer, PAGE_SIZE, "%d\n", status); +} + +static ssize_t battery_care_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buffer, size_t count) +{ + unsigned long value; + int ret; + + ret = kstrtoul(buffer, 10, &value); + if (ret) + return ret; + + if (value == 100 || value == 80) { + union acpi_object *r; + + r = lg_wmab(WM_BATT_LIMIT, WM_SET, value); + if (!r) + return -EIO; + + kfree(r); + return count; + } + + return -EINVAL; +} + +static ssize_t battery_care_limit_show(struct device *dev, + struct device_attribute *attr, + char *buffer) +{ + unsigned int status; + union acpi_object *r; + + r = lg_wmab(WM_BATT_LIMIT, WM_GET, 0); + if (!r) + return -EIO; + + if (r->type != ACPI_TYPE_INTEGER) { + kfree(r); + return -EIO; + } + + status = r->integer.value; + kfree(r); + if (status != 80 && status != 100) + status = 0; + + return snprintf(buffer, PAGE_SIZE, "%d\n", status); +} + +static DEVICE_ATTR_RW(fan_mode); +static DEVICE_ATTR_RW(usb_charge); +static DEVICE_ATTR_RW(reader_mode); +static DEVICE_ATTR_RW(fn_lock); +static DEVICE_ATTR_RW(battery_care_limit); + +static struct attribute *dev_attributes[] = { + &dev_attr_fan_mode.attr, + &dev_attr_usb_charge.attr, + &dev_attr_reader_mode.attr, + &dev_attr_fn_lock.attr, + &dev_attr_battery_care_limit.attr, + NULL +}; + +static const struct attribute_group dev_attribute_group = { + .attrs = dev_attributes, +}; + +static void tpad_led_set(struct led_classdev *cdev, + enum led_brightness brightness) +{ + union acpi_object *r; + + r = lg_wmab(WM_TLED, WM_SET, brightness > LED_OFF); + kfree(r); +} + +static enum led_brightness tpad_led_get(struct led_classdev *cdev) +{ + return ggov(GOV_TLED) > 0 ? LED_ON : LED_OFF; +} + +static LED_DEVICE(tpad_led, 1); + +static void kbd_backlight_set(struct led_classdev *cdev, + enum led_brightness brightness) +{ + u32 val; + union acpi_object *r; + + val = 0x22; + if (brightness <= LED_OFF) + val = 0; + if (brightness >= LED_FULL) + val = 0x24; + r = lg_wmab(WM_KEY_LIGHT, WM_SET, val); + kfree(r); +} + +static enum led_brightness kbd_backlight_get(struct led_classdev *cdev) +{ + union acpi_object *r; + int val; + + r = lg_wmab(WM_KEY_LIGHT, WM_GET, 0); + + if (!r) + return LED_OFF; + + if (r->type != ACPI_TYPE_BUFFER || r->buffer.pointer[1] != 0x05) { + kfree(r); + return LED_OFF; + } + + switch (r->buffer.pointer[0] & 0x27) { + case 0x24: + val = LED_FULL; + break; + case 0x22: + val = LED_HALF; + break; + default: + val = LED_OFF; + } + + kfree(r); + + return val; +} + +static LED_DEVICE(kbd_backlight, 255); + +static void wmi_input_destroy(void) +{ + if (inited & INIT_INPUT_WMI_2) + wmi_remove_notify_handler(WMI_EVENT_GUID2); + + if (inited & INIT_INPUT_WMI_0) + wmi_remove_notify_handler(WMI_EVENT_GUID0); + + if (inited & INIT_SPARSE_KEYMAP) + input_unregister_device(wmi_input_dev); + + inited &= ~(INIT_INPUT_WMI_0 | INIT_INPUT_WMI_2 | INIT_SPARSE_KEYMAP); +} + +static struct platform_driver pf_driver = { + .driver = { + .name = PLATFORM_NAME, + } +}; + +static int acpi_add(struct acpi_device *device) +{ + int ret; + + if (pf_device) + return 0; + + ret = platform_driver_register(&pf_driver); + if (ret) + return ret; + + pf_device = platform_device_register_simple(PLATFORM_NAME, + PLATFORM_DEVID_NONE, + NULL, 0); + if (IS_ERR(pf_device)) { + ret = PTR_ERR(pf_device); + pf_device = NULL; + pr_err("unable to register platform device\n"); + goto out_platform_registered; + } + + ret = sysfs_create_group(&pf_device->dev.kobj, &dev_attribute_group); + if (ret) + goto out_platform_device; + + if (!led_classdev_register(&pf_device->dev, &kbd_backlight)) + inited |= INIT_KBD_LED; + + if (!led_classdev_register(&pf_device->dev, &tpad_led)) + inited |= INIT_TPAD_LED; + + wmi_input_setup(); + + return 0; + +out_platform_device: + platform_device_unregister(pf_device); +out_platform_registered: + platform_driver_unregister(&pf_driver); + return ret; +} + +static int acpi_remove(struct acpi_device *device) +{ + sysfs_remove_group(&pf_device->dev.kobj, &dev_attribute_group); + if (inited & INIT_KBD_LED) + led_classdev_unregister(&kbd_backlight); + + if (inited & INIT_TPAD_LED) + led_classdev_unregister(&tpad_led); + + wmi_input_destroy(); + platform_device_unregister(pf_device); + pf_device = NULL; + platform_driver_unregister(&pf_driver); + + return 0; +} + +static const struct acpi_device_id device_ids[] = { + {"LGEX0815", 0}, + {"", 0} +}; +MODULE_DEVICE_TABLE(acpi, device_ids); + +static struct acpi_driver acpi_driver = { + .name = "LG Gram Laptop Support", + .class = "lg-laptop", + .ids = device_ids, + .ops = { + .add = acpi_add, + .remove = acpi_remove, + .notify = acpi_notify, + }, + .owner = THIS_MODULE, +}; + +static int __init acpi_init(void) +{ + int result; + + result = acpi_bus_register_driver(&acpi_driver); + if (result < 0) { + ACPI_DEBUG_PRINT((ACPI_DB_ERROR, "Error registering driver\n")); + return -ENODEV; + } + + return 0; +} + +static void __exit acpi_exit(void) +{ + acpi_bus_unregister_driver(&acpi_driver); +} + +module_init(acpi_init); +module_exit(acpi_exit); diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index d89936c93ba0fe..c2c3a1a1987959 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -575,7 +575,7 @@ static struct mlxreg_core_item mlxplat_mlxcpld_msn201x_items[] = { static struct mlxreg_core_hotplug_platform_data mlxplat_mlxcpld_msn201x_data = { - .items = mlxplat_mlxcpld_msn21xx_items, + .items = mlxplat_mlxcpld_msn201x_items, .counter = ARRAY_SIZE(mlxplat_mlxcpld_msn201x_items), .cell = MLXPLAT_CPLD_LPC_REG_AGGR_OFFSET, .mask = MLXPLAT_CPLD_AGGR_MASK_DEF, diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index cb204f9734913a..5f2d7ea912b56e 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -42,10 +42,13 @@ static const struct ts_dmi_data chuwi_hi8_data = { }; static const struct property_entry chuwi_hi8_pro_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 6), + PROPERTY_ENTRY_U32("touchscreen-min-y", 3), PROPERTY_ENTRY_U32("touchscreen-size-x", 1728), PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3680-chuwi-hi8-pro.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -56,6 +59,8 @@ static const struct ts_dmi_data chuwi_hi8_pro_data = { }; static const struct property_entry chuwi_vi8_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 4), + PROPERTY_ENTRY_U32("touchscreen-min-y", 6), PROPERTY_ENTRY_U32("touchscreen-size-x", 1724), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), @@ -88,9 +93,9 @@ static const struct ts_dmi_data chuwi_vi10_data = { static const struct property_entry connect_tablet9_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 9), - PROPERTY_ENTRY_U32("touchscreen-min-y", 8), + PROPERTY_ENTRY_U32("touchscreen-min-y", 10), PROPERTY_ENTRY_U32("touchscreen-size-x", 1664), - PROPERTY_ENTRY_U32("touchscreen-size-y", 878), + PROPERTY_ENTRY_U32("touchscreen-size-y", 880), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-connect-tablet9.fw"), @@ -104,8 +109,10 @@ static const struct ts_dmi_data connect_tablet9_data = { }; static const struct property_entry cube_iwork8_air_props[] = { - PROPERTY_ENTRY_U32("touchscreen-size-x", 1660), - PROPERTY_ENTRY_U32("touchscreen-size-y", 900), + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 3), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1664), + PROPERTY_ENTRY_U32("touchscreen-size-y", 896), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-cube-iwork8-air.fw"), PROPERTY_ENTRY_U32("silead,max-fingers", 10), @@ -179,11 +186,14 @@ static const struct ts_dmi_data gp_electronic_t701_data = { }; static const struct property_entry itworks_tw891_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 5), PROPERTY_ENTRY_U32("touchscreen-size-x", 1600), - PROPERTY_ENTRY_U32("touchscreen-size-y", 890), + PROPERTY_ENTRY_U32("touchscreen-size-y", 896), PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3670-itworks-tw891.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), { } }; @@ -207,8 +217,10 @@ static const struct ts_dmi_data jumper_ezpad_6_pro_data = { }; static const struct property_entry jumper_ezpad_mini3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 23), + PROPERTY_ENTRY_U32("touchscreen-min-y", 16), PROPERTY_ENTRY_U32("touchscreen-size-x", 1700), - PROPERTY_ENTRY_U32("touchscreen-size-y", 1150), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1138), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3676-jumper-ezpad-mini3.fw"), PROPERTY_ENTRY_U32("silead,max-fingers", 10), @@ -237,6 +249,24 @@ static const struct ts_dmi_data onda_obook_20_plus_data = { .properties = onda_obook_20_plus_props, }; +static const struct property_entry onda_v80_plus_v3_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 22), + PROPERTY_ENTRY_U32("touchscreen-min-y", 15), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1698), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl3676-onda-v80-plus-v3.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data onda_v80_plus_v3_data = { + .acpi_name = "MSSL1680:00", + .properties = onda_v80_plus_v3_props, +}; + static const struct property_entry onda_v820w_32g_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1665), PROPERTY_ENTRY_U32("touchscreen-size-y", 1140), @@ -322,11 +352,14 @@ static const struct ts_dmi_data pov_mobii_wintab_p800w_v20_data = { }; static const struct property_entry pov_mobii_wintab_p800w_v21_props[] = { - PROPERTY_ENTRY_U32("touchscreen-size-x", 1800), - PROPERTY_ENTRY_U32("touchscreen-size-y", 1150), + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 8), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1794), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1148), PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), PROPERTY_ENTRY_STRING("firmware-name", "gsl3692-pov-mobii-wintab-p800w.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), PROPERTY_ENTRY_BOOL("silead,home-button"), { } }; @@ -366,6 +399,22 @@ static const struct ts_dmi_data teclast_x98plus2_data = { .properties = teclast_x98plus2_props, }; +static const struct property_entry trekstor_primebook_c11_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 1970), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1530), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl1680-trekstor-primebook-c11.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + { } +}; + +static const struct ts_dmi_data trekstor_primebook_c11_data = { + .acpi_name = "MSSL1680:00", + .properties = trekstor_primebook_c11_props, +}; + static const struct property_entry trekstor_primebook_c13_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 2624), PROPERTY_ENTRY_U32("touchscreen-size-y", 1920), @@ -381,6 +430,22 @@ static const struct ts_dmi_data trekstor_primebook_c13_data = { .properties = trekstor_primebook_c13_props, }; +static const struct property_entry trekstor_primetab_t13b_props[] = { + PROPERTY_ENTRY_U32("touchscreen-size-x", 2500), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1900), + PROPERTY_ENTRY_STRING("firmware-name", + "gsl1680-trekstor-primetab-t13b.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + PROPERTY_ENTRY_BOOL("silead,home-button"), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + { } +}; + +static const struct ts_dmi_data trekstor_primetab_t13b_data = { + .acpi_name = "MSSL1680:00", + .properties = trekstor_primetab_t13b_props, +}; + static const struct property_entry trekstor_surftab_twin_10_1_props[] = { PROPERTY_ENTRY_U32("touchscreen-size-x", 1900), PROPERTY_ENTRY_U32("touchscreen-size-y", 1280), @@ -397,6 +462,8 @@ static const struct ts_dmi_data trekstor_surftab_twin_10_1_data = { }; static const struct property_entry trekstor_surftab_wintron70_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 12), + PROPERTY_ENTRY_U32("touchscreen-min-y", 8), PROPERTY_ENTRY_U32("touchscreen-size-x", 884), PROPERTY_ENTRY_U32("touchscreen-size-y", 632), PROPERTY_ENTRY_STRING("firmware-name", @@ -556,6 +623,14 @@ static const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* ONDA V80 plus v3 (P80PSBG9V3A01501) */ + .driver_data = (void *)&onda_v80_plus_v3_data, + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ONDA"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "V80 PLUS") + }, + }, + { /* ONDA V820w DualOS */ .driver_data = (void *)&onda_v820w_32g_data, .matches = { @@ -641,6 +716,14 @@ static const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Trekstor Primebook C11 */ + .driver_data = (void *)&trekstor_primebook_c11_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_MATCH(DMI_PRODUCT_NAME, "Primebook C11"), + }, + }, + { /* Trekstor Primebook C13 */ .driver_data = (void *)&trekstor_primebook_c13_data, .matches = { @@ -649,6 +732,14 @@ static const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Trekstor Primetab T13B */ + .driver_data = (void *)&trekstor_primetab_t13b_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "TREKSTOR"), + DMI_MATCH(DMI_PRODUCT_NAME, "Primetab T13B"), + }, + }, + { /* TrekStor SurfTab twin 10.1 ST10432-8 */ .driver_data = (void *)&trekstor_surftab_twin_10_1_data, .matches = { diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 04791ea5d97b69..bea35be68706d7 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -987,19 +987,19 @@ static struct bus_type wmi_bus_type = { .remove = wmi_dev_remove, }; -static struct device_type wmi_type_event = { +static const struct device_type wmi_type_event = { .name = "event", .groups = wmi_event_groups, .release = wmi_dev_release, }; -static struct device_type wmi_type_method = { +static const struct device_type wmi_type_method = { .name = "method", .groups = wmi_method_groups, .release = wmi_dev_release, }; -static struct device_type wmi_type_data = { +static const struct device_type wmi_type_data = { .name = "data", .groups = wmi_data_groups, .release = wmi_dev_release, diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig index 504d252716f2e1..27e5dd47a01f95 100644 --- a/drivers/pwm/Kconfig +++ b/drivers/pwm/Kconfig @@ -447,10 +447,9 @@ config PWM_TEGRA config PWM_TIECAP tristate "ECAP PWM support" - depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_KEYSTONE + depends on ARCH_OMAP2PLUS || ARCH_DAVINCI_DA8XX || ARCH_KEYSTONE || ARCH_K3 help - PWM driver support for the ECAP APWM controller found on AM33XX - TI SOC + PWM driver support for the ECAP APWM controller found on TI SOCs To compile this driver as a module, choose M here: the module will be called pwm-tiecap. diff --git a/drivers/pwm/pwm-lpss-platform.c b/drivers/pwm/pwm-lpss-platform.c index 5561b9e190f84a..757230e1f575e6 100644 --- a/drivers/pwm/pwm-lpss-platform.c +++ b/drivers/pwm/pwm-lpss-platform.c @@ -30,6 +30,7 @@ static const struct pwm_lpss_boardinfo pwm_lpss_bsw_info = { .clk_rate = 19200000, .npwm = 1, .base_unit_bits = 16, + .other_devices_aml_touches_pwm_regs = true, }; /* Broxton */ @@ -60,6 +61,7 @@ static int pwm_lpss_probe_platform(struct platform_device *pdev) platform_set_drvdata(pdev, lpwm); + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); @@ -74,13 +76,29 @@ static int pwm_lpss_remove_platform(struct platform_device *pdev) return pwm_lpss_remove(lpwm); } -static SIMPLE_DEV_PM_OPS(pwm_lpss_platform_pm_ops, - pwm_lpss_suspend, - pwm_lpss_resume); +static int pwm_lpss_prepare(struct device *dev) +{ + struct pwm_lpss_chip *lpwm = dev_get_drvdata(dev); + + /* + * If other device's AML code touches the PWM regs on suspend/resume + * force runtime-resume the PWM controller to allow this. + */ + if (lpwm->info->other_devices_aml_touches_pwm_regs) + return 0; /* Force runtime-resume */ + + return 1; /* If runtime-suspended leave as is */ +} + +static const struct dev_pm_ops pwm_lpss_platform_pm_ops = { + .prepare = pwm_lpss_prepare, + SET_SYSTEM_SLEEP_PM_OPS(pwm_lpss_suspend, pwm_lpss_resume) +}; static const struct acpi_device_id pwm_lpss_acpi_match[] = { { "80860F09", (unsigned long)&pwm_lpss_byt_info }, { "80862288", (unsigned long)&pwm_lpss_bsw_info }, + { "80862289", (unsigned long)&pwm_lpss_bsw_info }, { "80865AC8", (unsigned long)&pwm_lpss_bxt_info }, { }, }; diff --git a/drivers/pwm/pwm-lpss.c b/drivers/pwm/pwm-lpss.c index 4721a264bac258..2ac3a2aa9e53f5 100644 --- a/drivers/pwm/pwm-lpss.c +++ b/drivers/pwm/pwm-lpss.c @@ -32,15 +32,6 @@ /* Size of each PWM register space if multiple */ #define PWM_SIZE 0x400 -#define MAX_PWMS 4 - -struct pwm_lpss_chip { - struct pwm_chip chip; - void __iomem *regs; - const struct pwm_lpss_boardinfo *info; - u32 saved_ctrl[MAX_PWMS]; -}; - static inline struct pwm_lpss_chip *to_lpwm(struct pwm_chip *chip) { return container_of(chip, struct pwm_lpss_chip, chip); @@ -97,7 +88,7 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, unsigned long long on_time_div; unsigned long c = lpwm->info->clk_rate, base_unit_range; unsigned long long base_unit, freq = NSEC_PER_SEC; - u32 ctrl; + u32 orig_ctrl, ctrl; do_div(freq, period_ns); @@ -114,13 +105,17 @@ static void pwm_lpss_prepare(struct pwm_lpss_chip *lpwm, struct pwm_device *pwm, do_div(on_time_div, period_ns); on_time_div = 255ULL - on_time_div; - ctrl = pwm_lpss_read(pwm); + orig_ctrl = ctrl = pwm_lpss_read(pwm); ctrl &= ~PWM_ON_TIME_DIV_MASK; ctrl &= ~(base_unit_range << PWM_BASE_UNIT_SHIFT); base_unit &= base_unit_range; ctrl |= (u32) base_unit << PWM_BASE_UNIT_SHIFT; ctrl |= on_time_div; - pwm_lpss_write(pwm, ctrl); + + if (orig_ctrl != ctrl) { + pwm_lpss_write(pwm, ctrl); + pwm_lpss_write(pwm, ctrl | PWM_SW_UPDATE); + } } static inline void pwm_lpss_cond_enable(struct pwm_device *pwm, bool cond) @@ -144,7 +139,6 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, return ret; } pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); pwm_lpss_cond_enable(pwm, lpwm->info->bypass == false); ret = pwm_lpss_wait_for_update(pwm); if (ret) { @@ -157,7 +151,6 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, if (ret) return ret; pwm_lpss_prepare(lpwm, pwm, state->duty_cycle, state->period); - pwm_lpss_write(pwm, pwm_lpss_read(pwm) | PWM_SW_UPDATE); return pwm_lpss_wait_for_update(pwm); } } else if (pwm_is_enabled(pwm)) { @@ -168,8 +161,42 @@ static int pwm_lpss_apply(struct pwm_chip *chip, struct pwm_device *pwm, return 0; } +/* This function gets called once from pwmchip_add to get the initial state */ +static void pwm_lpss_get_state(struct pwm_chip *chip, struct pwm_device *pwm, + struct pwm_state *state) +{ + struct pwm_lpss_chip *lpwm = to_lpwm(chip); + unsigned long base_unit_range; + unsigned long long base_unit, freq, on_time_div; + u32 ctrl; + + base_unit_range = BIT(lpwm->info->base_unit_bits); + + ctrl = pwm_lpss_read(pwm); + on_time_div = 255 - (ctrl & PWM_ON_TIME_DIV_MASK); + base_unit = (ctrl >> PWM_BASE_UNIT_SHIFT) & (base_unit_range - 1); + + freq = base_unit * lpwm->info->clk_rate; + do_div(freq, base_unit_range); + if (freq == 0) + state->period = NSEC_PER_SEC; + else + state->period = NSEC_PER_SEC / (unsigned long)freq; + + on_time_div *= state->period; + do_div(on_time_div, 255); + state->duty_cycle = on_time_div; + + state->polarity = PWM_POLARITY_NORMAL; + state->enabled = !!(ctrl & PWM_ENABLE); + + if (state->enabled) + pm_runtime_get(chip->dev); +} + static const struct pwm_ops pwm_lpss_ops = { .apply = pwm_lpss_apply, + .get_state = pwm_lpss_get_state, .owner = THIS_MODULE, }; @@ -214,6 +241,12 @@ EXPORT_SYMBOL_GPL(pwm_lpss_probe); int pwm_lpss_remove(struct pwm_lpss_chip *lpwm) { + int i; + + for (i = 0; i < lpwm->info->npwm; i++) { + if (pwm_is_enabled(&lpwm->chip.pwms[i])) + pm_runtime_put(lpwm->chip.dev); + } return pwmchip_remove(&lpwm->chip); } EXPORT_SYMBOL_GPL(pwm_lpss_remove); diff --git a/drivers/pwm/pwm-lpss.h b/drivers/pwm/pwm-lpss.h index 7a4238ad1fcb1f..3236be835bd9c9 100644 --- a/drivers/pwm/pwm-lpss.h +++ b/drivers/pwm/pwm-lpss.h @@ -16,13 +16,25 @@ #include <linux/device.h> #include <linux/pwm.h> -struct pwm_lpss_chip; +#define MAX_PWMS 4 + +struct pwm_lpss_chip { + struct pwm_chip chip; + void __iomem *regs; + const struct pwm_lpss_boardinfo *info; + u32 saved_ctrl[MAX_PWMS]; +}; struct pwm_lpss_boardinfo { unsigned long clk_rate; unsigned int npwm; unsigned long base_unit_bits; bool bypass; + /* + * On some devices the _PS0/_PS3 AML code of the GPU (GFX0) device + * messes with the PWM0 controllers state, + */ + bool other_devices_aml_touches_pwm_regs; }; struct pwm_lpss_chip *pwm_lpss_probe(struct device *dev, struct resource *r, diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c index 748f614d53755d..a41812fc6f9573 100644 --- a/drivers/pwm/pwm-rcar.c +++ b/drivers/pwm/pwm-rcar.c @@ -1,11 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Car PWM Timer driver * * Copyright (C) 2015 Renesas Electronics Corporation - * - * This is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. */ #include <linux/clk.h> diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c index 29267d12fb4c9d..4a855a21b782de 100644 --- a/drivers/pwm/pwm-renesas-tpu.c +++ b/drivers/pwm/pwm-renesas-tpu.c @@ -1,16 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Mobile TPU PWM driver * * Copyright (C) 2012 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 - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <linux/clk.h> diff --git a/drivers/pwm/pwm-tegra.c b/drivers/pwm/pwm-tegra.c index f8ebbece57b71a..48c4595a0ffcec 100644 --- a/drivers/pwm/pwm-tegra.c +++ b/drivers/pwm/pwm-tegra.c @@ -300,7 +300,6 @@ static const struct of_device_id tegra_pwm_of_match[] = { { .compatible = "nvidia,tegra186-pwm", .data = &tegra186_pwm_soc }, { } }; - MODULE_DEVICE_TABLE(of, tegra_pwm_of_match); static const struct dev_pm_ops tegra_pwm_pm_ops = { diff --git a/drivers/pwm/sysfs.c b/drivers/pwm/sysfs.c index 7c71cdb8a9d8f9..ceb233dd604840 100644 --- a/drivers/pwm/sysfs.c +++ b/drivers/pwm/sysfs.c @@ -249,6 +249,7 @@ static void pwm_export_release(struct device *child) static int pwm_export_child(struct device *parent, struct pwm_device *pwm) { struct pwm_export *export; + char *pwm_prop[2]; int ret; if (test_and_set_bit(PWMF_EXPORTED, &pwm->flags)) @@ -263,7 +264,6 @@ static int pwm_export_child(struct device *parent, struct pwm_device *pwm) export->pwm = pwm; mutex_init(&export->lock); - export->child.class = parent->class; export->child.release = pwm_export_release; export->child.parent = parent; export->child.devt = MKDEV(0, 0); @@ -277,6 +277,10 @@ static int pwm_export_child(struct device *parent, struct pwm_device *pwm) export = NULL; return ret; } + pwm_prop[0] = kasprintf(GFP_KERNEL, "EXPORT=pwm%u", pwm->hwpwm); + pwm_prop[1] = NULL; + kobject_uevent_env(&parent->kobj, KOBJ_CHANGE, pwm_prop); + kfree(pwm_prop[0]); return 0; } @@ -289,6 +293,7 @@ static int pwm_unexport_match(struct device *child, void *data) static int pwm_unexport_child(struct device *parent, struct pwm_device *pwm) { struct device *child; + char *pwm_prop[2]; if (!test_and_clear_bit(PWMF_EXPORTED, &pwm->flags)) return -ENODEV; @@ -297,6 +302,11 @@ static int pwm_unexport_child(struct device *parent, struct pwm_device *pwm) if (!child) return -ENODEV; + pwm_prop[0] = kasprintf(GFP_KERNEL, "UNEXPORT=pwm%u", pwm->hwpwm); + pwm_prop[1] = NULL; + kobject_uevent_env(&parent->kobj, KOBJ_CHANGE, pwm_prop); + kfree(pwm_prop[0]); + /* for device_find_child() */ put_device(child); device_unregister(child); diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index 05293babb03106..2d655a97b959e9 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -143,7 +143,9 @@ static int twa_poll_status_gone(TW_Device_Extension *tw_dev, u32 flag, int secon static int twa_post_command_packet(TW_Device_Extension *tw_dev, int request_id, char internal); static int twa_reset_device_extension(TW_Device_Extension *tw_dev); static int twa_reset_sequence(TW_Device_Extension *tw_dev, int soft_reset); -static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg); +static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, + unsigned char *cdb, int use_sg, + TW_SG_Entry *sglistarg); static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int request_id); static char *twa_string_lookup(twa_message_type *table, unsigned int aen_code); @@ -278,7 +280,7 @@ out: static int twa_aen_drain_queue(TW_Device_Extension *tw_dev, int no_check_reset) { int request_id = 0; - char cdb[TW_MAX_CDB_LEN]; + unsigned char cdb[TW_MAX_CDB_LEN]; TW_SG_Entry sglist[1]; int finished = 0, count = 0; TW_Command_Full *full_command_packet; @@ -423,7 +425,7 @@ static void twa_aen_queue_event(TW_Device_Extension *tw_dev, TW_Command_Apache_H /* This function will read the aen queue from the isr */ static int twa_aen_read_queue(TW_Device_Extension *tw_dev, int request_id) { - char cdb[TW_MAX_CDB_LEN]; + unsigned char cdb[TW_MAX_CDB_LEN]; TW_SG_Entry sglist[1]; TW_Command_Full *full_command_packet; int retval = 1; @@ -1798,7 +1800,9 @@ out: static DEF_SCSI_QCMD(twa_scsi_queue) /* This function hands scsi cdb's to the firmware */ -static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry *sglistarg) +static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, + unsigned char *cdb, int use_sg, + TW_SG_Entry *sglistarg) { TW_Command_Full *full_command_packet; TW_Command_Apache *command_packet; diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index 266bdac7530427..480cf82700e9f4 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -287,7 +287,9 @@ static int twl_post_command_packet(TW_Device_Extension *tw_dev, int request_id) } /* End twl_post_command_packet() */ /* This function hands scsi cdb's to the firmware */ -static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, char *cdb, int use_sg, TW_SG_Entry_ISO *sglistarg) +static int twl_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id, + unsigned char *cdb, int use_sg, + TW_SG_Entry_ISO *sglistarg) { TW_Command_Full *full_command_packet; TW_Command_Apache *command_packet; @@ -372,7 +374,7 @@ out: /* This function will read the aen queue from the isr */ static int twl_aen_read_queue(TW_Device_Extension *tw_dev, int request_id) { - char cdb[TW_MAX_CDB_LEN]; + unsigned char cdb[TW_MAX_CDB_LEN]; TW_SG_Entry_ISO sglist[1]; TW_Command_Full *full_command_packet; int retval = 1; @@ -554,7 +556,7 @@ out: static int twl_aen_drain_queue(TW_Device_Extension *tw_dev, int no_check_reset) { int request_id = 0; - char cdb[TW_MAX_CDB_LEN]; + unsigned char cdb[TW_MAX_CDB_LEN]; TW_SG_Entry_ISO sglist[1]; int finished = 0, count = 0; TW_Command_Full *full_command_packet; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 70988c3812684c..f07444d30b216d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -538,7 +538,7 @@ config SCSI_HPTIOP config SCSI_BUSLOGIC tristate "BusLogic SCSI support" - depends on (PCI || ISA || MCA) && SCSI && ISA_DMA_API && VIRT_TO_BUS + depends on (PCI || ISA) && SCSI && ISA_DMA_API && VIRT_TO_BUS ---help--- This is support for BusLogic MultiMaster and FlashPoint SCSI Host Adapters. Consult the SCSI-HOWTO, available from @@ -1175,12 +1175,12 @@ config SCSI_LPFC_DEBUG_FS config SCSI_SIM710 tristate "Simple 53c710 SCSI support (Compaq, NCR machines)" - depends on (EISA || MCA) && SCSI + depends on EISA && SCSI select SCSI_SPI_ATTRS ---help--- This driver is for NCR53c710 based SCSI host adapters. - It currently supports Compaq EISA cards and NCR MCA cards + It currently supports Compaq EISA cards. config SCSI_DC395x tristate "Tekram DC395(U/UW/F) and DC315(U) SCSI support" diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c index 4d7b0e0adbf70c..301b3cad15f88f 100644 --- a/drivers/scsi/aha152x.c +++ b/drivers/scsi/aha152x.c @@ -269,7 +269,7 @@ static LIST_HEAD(aha152x_host_list); /* DEFINES */ /* For PCMCIA cards, always use AUTOCONF */ -#if defined(PCMCIA) || defined(MODULE) +#if defined(AHA152X_PCMCIA) || defined(MODULE) #if !defined(AUTOCONF) #define AUTOCONF #endif @@ -297,7 +297,7 @@ CMD_INC_RESID(struct scsi_cmnd *cmd, int inc) #define DELAY_DEFAULT 1000 -#if defined(PCMCIA) +#if defined(AHA152X_PCMCIA) #define IRQ_MIN 0 #define IRQ_MAX 16 #else @@ -328,7 +328,7 @@ MODULE_AUTHOR("Jürgen Fischer"); MODULE_DESCRIPTION(AHA152X_REVID); MODULE_LICENSE("GPL"); -#if !defined(PCMCIA) +#if !defined(AHA152X_PCMCIA) #if defined(MODULE) static int io[] = {0, 0}; module_param_hw_array(io, int, ioport, NULL, 0); @@ -391,7 +391,7 @@ static struct isapnp_device_id id_table[] = { MODULE_DEVICE_TABLE(isapnp, id_table); #endif /* ISAPNP */ -#endif /* !PCMCIA */ +#endif /* !AHA152X_PCMCIA */ static struct scsi_host_template aha152x_driver_template; @@ -863,7 +863,7 @@ void aha152x_release(struct Scsi_Host *shpnt) if (shpnt->irq) free_irq(shpnt->irq, shpnt); -#if !defined(PCMCIA) +#if !defined(AHA152X_PCMCIA) if (shpnt->io_port) release_region(shpnt->io_port, IO_RANGE); #endif @@ -2924,7 +2924,7 @@ static struct scsi_host_template aha152x_driver_template = { .slave_alloc = aha152x_adjust_queue, }; -#if !defined(PCMCIA) +#if !defined(AHA152X_PCMCIA) static int setup_count; static struct aha152x_setup setup[2]; @@ -3392,4 +3392,4 @@ static int __init aha152x_setup(char *str) __setup("aha152x=", aha152x_setup); #endif -#endif /* !PCMCIA */ +#endif /* !AHA152X_PCMCIA */ diff --git a/drivers/scsi/mvsas/mv_sas.c b/drivers/scsi/mvsas/mv_sas.c index 3df1428df31727..311d23c727cef0 100644 --- a/drivers/scsi/mvsas/mv_sas.c +++ b/drivers/scsi/mvsas/mv_sas.c @@ -790,12 +790,11 @@ static int mvs_task_prep(struct sas_task *task, struct mvs_info *mvi, int is_tmf slot->n_elem = n_elem; slot->slot_tag = tag; - slot->buf = dma_pool_alloc(mvi->dma_pool, GFP_ATOMIC, &slot->buf_dma); + slot->buf = dma_pool_zalloc(mvi->dma_pool, GFP_ATOMIC, &slot->buf_dma); if (!slot->buf) { rc = -ENOMEM; goto err_out_tag; } - memset(slot->buf, 0, MVS_SLOT_BUF_SZ); tei.task = task; tei.hdr = &mvi->slot[tag]; @@ -1906,8 +1905,7 @@ static void mvs_work_queue(struct work_struct *work) if (phy->phy_event & PHY_PLUG_OUT) { u32 tmp; - struct sas_identify_frame *id; - id = (struct sas_identify_frame *)phy->frame_rcvd; + tmp = MVS_CHIP_DISP->read_phy_ctl(mvi, phy_no); phy->phy_event &= ~PHY_PLUG_OUT; if (!(tmp & PHY_READY_MASK)) { diff --git a/drivers/scsi/pcmcia/aha152x_core.c b/drivers/scsi/pcmcia/aha152x_core.c index dba3716511c565..24b89228b2414c 100644 --- a/drivers/scsi/pcmcia/aha152x_core.c +++ b/drivers/scsi/pcmcia/aha152x_core.c @@ -1,3 +1,3 @@ -#define PCMCIA 1 +#define AHA152X_PCMCIA 1 #define AHA152X_STAT 1 #include "aha152x.c" diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index b28f159fdaee79..0bb9ac6ece9205 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -218,7 +218,7 @@ qla2x00_sysfs_write_nvram(struct file *filp, struct kobject *kobj, mutex_lock(&ha->optrom_mutex); if (qla2x00_chip_is_down(vha)) { - mutex_unlock(&vha->hw->optrom_mutex); + mutex_unlock(&ha->optrom_mutex); return -EAGAIN; } diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index c72d8012fe2aab..6fe20c27acc16e 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -425,7 +425,7 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea) __qla24xx_handle_gpdb_event(vha, ea); } -int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport) +static int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport) { struct qla_work_evt *e; @@ -680,7 +680,7 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha, fcport); break; } - /* drop through */ + /* fall through */ default: if (fcport_is_smaller(fcport)) { /* local adapter is bigger */ @@ -1551,7 +1551,8 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha, } -void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea) +static void qla_handle_els_plogi_done(scsi_qla_host_t *vha, + struct event_arg *ea) { ql_dbg(ql_dbg_disc, vha, 0x2118, "%s %d %8phC post PRLI\n", diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index 86fb8b21aa7108..032635321ad6e7 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -1195,8 +1195,8 @@ qla24xx_walk_and_build_prot_sglist(struct qla_hw_data *ha, srb_t *sp, * @sp: SRB command to process * @cmd_pkt: Command type 3 IOCB * @tot_dsds: Total number of segments to transfer - * @tot_prot_dsds: - * @fw_prot_opts: + * @tot_prot_dsds: Total number of segments with protection information + * @fw_prot_opts: Protection options to be passed to firmware */ inline int qla24xx_build_scsi_crc_2_iocbs(srb_t *sp, struct cmd_type_crc_2 *cmd_pkt, diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index d73b04e405902b..30d3090842f856 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -25,7 +25,7 @@ static int qla2x00_error_entry(scsi_qla_host_t *, struct rsp_que *, /** * qla2100_intr_handler() - Process interrupts for the ISP2100 and ISP2200. - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. @@ -144,7 +144,7 @@ qla2x00_check_reg16_for_disconnect(scsi_qla_host_t *vha, uint16_t reg) /** * qla2300_intr_handler() - Process interrupts for the ISP23xx and ISP63xx. - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. @@ -3109,7 +3109,7 @@ done: /** * qla24xx_intr_handler() - Process interrupts for the ISP23xx and ISP24xx. - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 2f3e5075ae76e8..191b6b7c8747df 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3478,9 +3478,9 @@ qla8044_read_serdes_word(scsi_qla_host_t *vha, uint32_t addr, uint32_t *data) /** * qla2x00_set_serdes_params() - * @vha: HA context - * @sw_em_1g: - * @sw_em_2g: - * @sw_em_4g: + * @sw_em_1g: serial link options + * @sw_em_2g: serial link options + * @sw_em_4g: serial link options * * Returns */ diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c index 521a513705549a..60f964c53c01a7 100644 --- a/drivers/scsi/qla2xxx/qla_mr.c +++ b/drivers/scsi/qla2xxx/qla_mr.c @@ -2212,7 +2212,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req, struct bsg_job *bsg_job; struct fc_bsg_reply *bsg_reply; struct srb_iocb *iocb_job; - int res; + int res = 0; struct qla_mt_iocb_rsp_fx00 fstatus; uint8_t *fw_sts_ptr; @@ -2624,7 +2624,7 @@ qlafx00_status_cont_entry(struct rsp_que *rsp, sts_cont_entry_t *pkt) * qlafx00_multistatus_entry() - Process Multi response queue entries. * @vha: SCSI driver HA context * @rsp: response queue - * @pkt: + * @pkt: received packet */ static void qlafx00_multistatus_entry(struct scsi_qla_host *vha, @@ -2681,12 +2681,10 @@ qlafx00_multistatus_entry(struct scsi_qla_host *vha, * @vha: SCSI driver HA context * @rsp: response queue * @pkt: Entry pointer - * @estatus: - * @etype: */ static void qlafx00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, - struct sts_entry_fx00 *pkt, uint8_t estatus, uint8_t etype) + struct sts_entry_fx00 *pkt) { srb_t *sp; struct qla_hw_data *ha = vha->hw; @@ -2695,9 +2693,6 @@ qlafx00_error_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, struct req_que *req = NULL; int res = DID_ERROR << 16; - ql_dbg(ql_dbg_async, vha, 0x507f, - "type of error status in response: 0x%x\n", estatus); - req = ha->req_q_map[que]; sp = qla2x00_get_sp_from_handle(vha, func, req, pkt); @@ -2745,9 +2740,11 @@ qlafx00_process_response_queue(struct scsi_qla_host *vha, if (pkt->entry_status != 0 && pkt->entry_type != IOCTL_IOSB_TYPE_FX00) { + ql_dbg(ql_dbg_async, vha, 0x507f, + "type of error status in response: 0x%x\n", + pkt->entry_status); qlafx00_error_entry(vha, rsp, - (struct sts_entry_fx00 *)pkt, pkt->entry_status, - pkt->entry_type); + (struct sts_entry_fx00 *)pkt); continue; } @@ -2867,7 +2864,7 @@ qlafx00_async_event(scsi_qla_host_t *vha) /** * qlafx00x_mbx_completion() - Process mailbox command completions. * @vha: SCSI driver HA context - * @mb0: + * @mb0: value to be written into mailbox register 0 */ static void qlafx00_mbx_completion(scsi_qla_host_t *vha, uint32_t mb0) @@ -2893,7 +2890,7 @@ qlafx00_mbx_completion(scsi_qla_host_t *vha, uint32_t mb0) /** * qlafx00_intr_handler() - Process interrupts for the ISPFX00. - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c index 121e18b3b9f839..f2f54806f4da9d 100644 --- a/drivers/scsi/qla2xxx/qla_nx.c +++ b/drivers/scsi/qla2xxx/qla_nx.c @@ -2010,7 +2010,7 @@ qla82xx_mbx_completion(scsi_qla_host_t *vha, uint16_t mb0) /** * qla82xx_intr_handler() - Process interrupts for the ISP23xx and ISP63xx. - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. diff --git a/drivers/scsi/qla2xxx/qla_nx2.c b/drivers/scsi/qla2xxx/qla_nx2.c index 3a2b0282df1495..fe856b602e0319 100644 --- a/drivers/scsi/qla2xxx/qla_nx2.c +++ b/drivers/scsi/qla2xxx/qla_nx2.c @@ -3878,7 +3878,7 @@ out: #define PF_BITS_MASK (0xF << 16) /** * qla8044_intr_handler() - Process interrupts for the ISP8044 - * @irq: + * @irq: interrupt number * @dev_id: SCSI driver HA context * * Called by system whenever the host adapter generates an interrupt. diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 8794e54f43a95d..518f15141170e7 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1749,7 +1749,7 @@ qla2x00_loop_reset(scsi_qla_host_t *vha) static void __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) { - int cnt, status; + int cnt; unsigned long flags; srb_t *sp; scsi_qla_host_t *vha = qp->vha; @@ -1799,8 +1799,8 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res) if (!sp_get(sp)) { spin_unlock_irqrestore (qp->qp_lock_ptr, flags); - status = qla2xxx_eh_abort( - GET_CMD_SP(sp)); + qla2xxx_eh_abort( + GET_CMD_SP(sp)); spin_lock_irqsave (qp->qp_lock_ptr, flags); } diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c index 4499c787165f14..2a3055c799fb61 100644 --- a/drivers/scsi/qla2xxx/qla_sup.c +++ b/drivers/scsi/qla2xxx/qla_sup.c @@ -2229,7 +2229,7 @@ qla2x00_erase_flash_sector(struct qla_hw_data *ha, uint32_t addr, /** * qla2x00_get_flash_manufacturer() - Read manufacturer ID from flash chip. - * @ha: + * @ha: host adapter * @man_id: Flash manufacturer ID * @flash_id: Flash ID */ diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index 39828207bc1d22..c4504740f0e212 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -4540,7 +4540,7 @@ static int qlt_issue_task_mgmt(struct fc_port *sess, u64 lun, case QLA_TGT_CLEAR_TS: case QLA_TGT_ABORT_TS: abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id); - /* drop through */ + /* fall through */ case QLA_TGT_CLEAR_ACA: h = qlt_find_qphint(vha, mcmd->unpacked_lun); mcmd->qpair = h->qpair; @@ -6598,9 +6598,9 @@ static void qlt_lport_dump(struct scsi_qla_host *vha, u64 wwpn, * qla_tgt_lport_register - register lport with external module * * @target_lport_ptr: pointer for tcm_qla2xxx specific lport data - * @phys_wwpn: - * @npiv_wwpn: - * @npiv_wwnn: + * @phys_wwpn: physical port WWPN + * @npiv_wwpn: NPIV WWPN + * @npiv_wwnn: NPIV WWNN * @callback: lport initialization callback for tcm_qla2xxx code */ int qlt_lport_register(void *target_lport_ptr, u64 phys_wwpn, diff --git a/drivers/soc/ti/knav_qmss.h b/drivers/soc/ti/knav_qmss.h index 7c128132799e0c..4c28fa938ac76a 100644 --- a/drivers/soc/ti/knav_qmss.h +++ b/drivers/soc/ti/knav_qmss.h @@ -329,8 +329,8 @@ struct knav_range_ops { }; struct knav_irq_info { - int irq; - u32 cpu_map; + int irq; + struct cpumask *cpu_mask; }; struct knav_range_info { diff --git a/drivers/soc/ti/knav_qmss_acc.c b/drivers/soc/ti/knav_qmss_acc.c index 316e82e46f6cbf..2f7fb2dcc1d66d 100644 --- a/drivers/soc/ti/knav_qmss_acc.c +++ b/drivers/soc/ti/knav_qmss_acc.c @@ -205,18 +205,18 @@ static int knav_range_setup_acc_irq(struct knav_range_info *range, { struct knav_device *kdev = range->kdev; struct knav_acc_channel *acc; - unsigned long cpu_map; + struct cpumask *cpu_mask; int ret = 0, irq; u32 old, new; if (range->flags & RANGE_MULTI_QUEUE) { acc = range->acc; irq = range->irqs[0].irq; - cpu_map = range->irqs[0].cpu_map; + cpu_mask = range->irqs[0].cpu_mask; } else { acc = range->acc + queue; irq = range->irqs[queue].irq; - cpu_map = range->irqs[queue].cpu_map; + cpu_mask = range->irqs[queue].cpu_mask; } old = acc->open_mask; @@ -239,8 +239,8 @@ static int knav_range_setup_acc_irq(struct knav_range_info *range, acc->name, acc->name); ret = request_irq(irq, knav_acc_int_handler, 0, acc->name, range); - if (!ret && cpu_map) { - ret = irq_set_affinity_hint(irq, to_cpumask(&cpu_map)); + if (!ret && cpu_mask) { + ret = irq_set_affinity_hint(irq, cpu_mask); if (ret) { dev_warn(range->kdev->dev, "Failed to set IRQ affinity\n"); diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index b5d5673c255cad..8b418379272da7 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -118,19 +118,17 @@ static int knav_queue_setup_irq(struct knav_range_info *range, struct knav_queue_inst *inst) { unsigned queue = inst->id - range->queue_base; - unsigned long cpu_map; int ret = 0, irq; if (range->flags & RANGE_HAS_IRQ) { irq = range->irqs[queue].irq; - cpu_map = range->irqs[queue].cpu_map; ret = request_irq(irq, knav_queue_int_handler, 0, inst->irq_name, inst); if (ret) return ret; disable_irq(irq); - if (cpu_map) { - ret = irq_set_affinity_hint(irq, to_cpumask(&cpu_map)); + if (range->irqs[queue].cpu_mask) { + ret = irq_set_affinity_hint(irq, range->irqs[queue].cpu_mask); if (ret) { dev_warn(range->kdev->dev, "Failed to set IRQ affinity\n"); @@ -1262,9 +1260,19 @@ static int knav_setup_queue_range(struct knav_device *kdev, range->num_irqs++; - if (IS_ENABLED(CONFIG_SMP) && oirq.args_count == 3) - range->irqs[i].cpu_map = - (oirq.args[2] & 0x0000ff00) >> 8; + if (IS_ENABLED(CONFIG_SMP) && oirq.args_count == 3) { + unsigned long mask; + int bit; + + range->irqs[i].cpu_mask = devm_kzalloc(dev, + cpumask_size(), GFP_KERNEL); + if (!range->irqs[i].cpu_mask) + return -ENOMEM; + + mask = (oirq.args[2] & 0x0000ff00) >> 8; + for_each_set_bit(bit, &mask, BITS_PER_LONG) + cpumask_set_cpu(bit, range->irqs[i].cpu_mask); + } } range->num_irqs = min(range->num_irqs, range->num_queues); diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 1227872227dc44..36b742932c724c 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1245,8 +1245,7 @@ static int iscsit_do_rx_data( return -1; memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, - count->iov, count->iov_count, data); + iov_iter_kvec(&msg.msg_iter, READ, count->iov, count->iov_count, data); while (msg_data_left(&msg)) { rx_loop = sock_recvmsg(conn->sock, &msg, MSG_WAITALL); @@ -1302,8 +1301,7 @@ int tx_data( memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, - iov, iov_count, data); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, iov_count, data); while (msg_data_left(&msg)) { int tx_loop = sock_sendmsg(conn->sock, &msg); diff --git a/drivers/target/target_core_alua.c b/drivers/target/target_core_alua.c index e46ca968009c06..4f134b0c3e29e0 100644 --- a/drivers/target/target_core_alua.c +++ b/drivers/target/target_core_alua.c @@ -268,7 +268,7 @@ target_emulate_report_target_port_groups(struct se_cmd *cmd) } transport_kunmap_data_sg(cmd); - target_complete_cmd(cmd, GOOD); + target_complete_cmd_with_length(cmd, GOOD, rd_len + 4); return 0; } diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 16751ae55d7b6f..49b110d1b972b6 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -303,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC | is_write, bvec, sgl_nents, len); + iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); aio_cmd->cmd = cmd; aio_cmd->len = len; @@ -353,7 +353,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, sgl_nents, len); + iov_iter_bvec(&iter, READ, bvec, sgl_nents, len); if (is_write) ret = vfs_iter_write(fd, &iter, &pos, 0); else @@ -490,7 +490,7 @@ fd_execute_write_same(struct se_cmd *cmd) len += se_dev->dev_attrib.block_size; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, nolb, len); + iov_iter_bvec(&iter, READ, bvec, nolb, len); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); kfree(bvec); diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 4cf33e2cc70588..e31e4fc31aa150 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -205,19 +205,19 @@ void transport_subsystem_check_init(void) if (sub_api_initialized) return; - ret = request_module("target_core_iblock"); + ret = IS_ENABLED(CONFIG_TCM_IBLOCK) && request_module("target_core_iblock"); if (ret != 0) pr_err("Unable to load target_core_iblock\n"); - ret = request_module("target_core_file"); + ret = IS_ENABLED(CONFIG_TCM_FILEIO) && request_module("target_core_file"); if (ret != 0) pr_err("Unable to load target_core_file\n"); - ret = request_module("target_core_pscsi"); + ret = IS_ENABLED(CONFIG_TCM_PSCSI) && request_module("target_core_pscsi"); if (ret != 0) pr_err("Unable to load target_core_pscsi\n"); - ret = request_module("target_core_user"); + ret = IS_ENABLED(CONFIG_TCM_USER2) && request_module("target_core_user"); if (ret != 0) pr_err("Unable to load target_core_user\n"); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 9756752c0681f9..45da3e01c7b03a 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -309,7 +309,7 @@ int usbip_recv(struct socket *sock, void *buf, int size) if (!sock || !buf || !size) return -EINVAL; - iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); usbip_dbg_xmit("enter\n"); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index c24bb690680b41..50dffe83714c63 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -203,6 +203,19 @@ struct vhost_scsi { int vs_events_nr; /* num of pending events, protected by vq->mutex */ }; +/* + * Context for processing request and control queue operations. + */ +struct vhost_scsi_ctx { + int head; + unsigned int out, in; + size_t req_size, rsp_size; + size_t out_size, in_size; + u8 *target, *lunp; + void *req; + struct iov_iter out_iter; +}; + static struct workqueue_struct *vhost_scsi_workqueue; /* Global spinlock to protect vhost_scsi TPG list for vhost IOCTL access */ @@ -800,24 +813,120 @@ vhost_scsi_send_bad_target(struct vhost_scsi *vs, pr_err("Faulted on virtio_scsi_cmd_resp\n"); } +static int +vhost_scsi_get_desc(struct vhost_scsi *vs, struct vhost_virtqueue *vq, + struct vhost_scsi_ctx *vc) +{ + int ret = -ENXIO; + + vc->head = vhost_get_vq_desc(vq, vq->iov, + ARRAY_SIZE(vq->iov), &vc->out, &vc->in, + NULL, NULL); + + pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n", + vc->head, vc->out, vc->in); + + /* On error, stop handling until the next kick. */ + if (unlikely(vc->head < 0)) + goto done; + + /* Nothing new? Wait for eventfd to tell us they refilled. */ + if (vc->head == vq->num) { + if (unlikely(vhost_enable_notify(&vs->dev, vq))) { + vhost_disable_notify(&vs->dev, vq); + ret = -EAGAIN; + } + goto done; + } + + /* + * Get the size of request and response buffers. + * FIXME: Not correct for BIDI operation + */ + vc->out_size = iov_length(vq->iov, vc->out); + vc->in_size = iov_length(&vq->iov[vc->out], vc->in); + + /* + * Copy over the virtio-scsi request header, which for a + * ANY_LAYOUT enabled guest may span multiple iovecs, or a + * single iovec may contain both the header + outgoing + * WRITE payloads. + * + * copy_from_iter() will advance out_iter, so that it will + * point at the start of the outgoing WRITE payload, if + * DMA_TO_DEVICE is set. + */ + iov_iter_init(&vc->out_iter, WRITE, vq->iov, vc->out, vc->out_size); + ret = 0; + +done: + return ret; +} + +static int +vhost_scsi_chk_size(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc) +{ + if (unlikely(vc->in_size < vc->rsp_size)) { + vq_err(vq, + "Response buf too small, need min %zu bytes got %zu", + vc->rsp_size, vc->in_size); + return -EINVAL; + } else if (unlikely(vc->out_size < vc->req_size)) { + vq_err(vq, + "Request buf too small, need min %zu bytes got %zu", + vc->req_size, vc->out_size); + return -EIO; + } + + return 0; +} + +static int +vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, + struct vhost_scsi_tpg **tpgp) +{ + int ret = -EIO; + + if (unlikely(!copy_from_iter_full(vc->req, vc->req_size, + &vc->out_iter))) { + vq_err(vq, "Faulted on copy_from_iter\n"); + } else if (unlikely(*vc->lunp != 1)) { + /* virtio-scsi spec requires byte 0 of the lun to be 1 */ + vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp); + } else { + struct vhost_scsi_tpg **vs_tpg, *tpg; + + vs_tpg = vq->private_data; /* validated at handler entry */ + + tpg = READ_ONCE(vs_tpg[*vc->target]); + if (unlikely(!tpg)) { + vq_err(vq, "Target 0x%x does not exist\n", *vc->target); + } else { + if (tpgp) + *tpgp = tpg; + ret = 0; + } + } + + return ret; +} + static void vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) { struct vhost_scsi_tpg **vs_tpg, *tpg; struct virtio_scsi_cmd_req v_req; struct virtio_scsi_cmd_req_pi v_req_pi; + struct vhost_scsi_ctx vc; struct vhost_scsi_cmd *cmd; - struct iov_iter out_iter, in_iter, prot_iter, data_iter; + struct iov_iter in_iter, prot_iter, data_iter; u64 tag; u32 exp_data_len, data_direction; - unsigned int out = 0, in = 0; - int head, ret, prot_bytes; - size_t req_size, rsp_size = sizeof(struct virtio_scsi_cmd_resp); - size_t out_size, in_size; + int ret, prot_bytes; u16 lun; - u8 *target, *lunp, task_attr; + u8 task_attr; bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI); - void *req, *cdb; + void *cdb; mutex_lock(&vq->mutex); /* @@ -828,85 +937,47 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (!vs_tpg) goto out; + memset(&vc, 0, sizeof(vc)); + vc.rsp_size = sizeof(struct virtio_scsi_cmd_resp); + vhost_disable_notify(&vs->dev, vq); for (;;) { - head = vhost_get_vq_desc(vq, vq->iov, - ARRAY_SIZE(vq->iov), &out, &in, - NULL, NULL); - pr_debug("vhost_get_vq_desc: head: %d, out: %u in: %u\n", - head, out, in); - /* On error, stop handling until the next kick. */ - if (unlikely(head < 0)) - break; - /* Nothing new? Wait for eventfd to tell us they refilled. */ - if (head == vq->num) { - if (unlikely(vhost_enable_notify(&vs->dev, vq))) { - vhost_disable_notify(&vs->dev, vq); - continue; - } - break; - } - /* - * Check for a sane response buffer so we can report early - * errors back to the guest. - */ - if (unlikely(vq->iov[out].iov_len < rsp_size)) { - vq_err(vq, "Expecting at least virtio_scsi_cmd_resp" - " size, got %zu bytes\n", vq->iov[out].iov_len); - break; - } + ret = vhost_scsi_get_desc(vs, vq, &vc); + if (ret) + goto err; + /* * Setup pointers and values based upon different virtio-scsi * request header if T10_PI is enabled in KVM guest. */ if (t10_pi) { - req = &v_req_pi; - req_size = sizeof(v_req_pi); - lunp = &v_req_pi.lun[0]; - target = &v_req_pi.lun[1]; + vc.req = &v_req_pi; + vc.req_size = sizeof(v_req_pi); + vc.lunp = &v_req_pi.lun[0]; + vc.target = &v_req_pi.lun[1]; } else { - req = &v_req; - req_size = sizeof(v_req); - lunp = &v_req.lun[0]; - target = &v_req.lun[1]; + vc.req = &v_req; + vc.req_size = sizeof(v_req); + vc.lunp = &v_req.lun[0]; + vc.target = &v_req.lun[1]; } - /* - * FIXME: Not correct for BIDI operation - */ - out_size = iov_length(vq->iov, out); - in_size = iov_length(&vq->iov[out], in); /* - * Copy over the virtio-scsi request header, which for a - * ANY_LAYOUT enabled guest may span multiple iovecs, or a - * single iovec may contain both the header + outgoing - * WRITE payloads. - * - * copy_from_iter() will advance out_iter, so that it will - * point at the start of the outgoing WRITE payload, if - * DMA_TO_DEVICE is set. + * Validate the size of request and response buffers. + * Check for a sane response buffer so we can report + * early errors back to the guest. */ - iov_iter_init(&out_iter, WRITE, vq->iov, out, out_size); + ret = vhost_scsi_chk_size(vq, &vc); + if (ret) + goto err; - if (unlikely(!copy_from_iter_full(req, req_size, &out_iter))) { - vq_err(vq, "Faulted on copy_from_iter\n"); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; - } - /* virtio-scsi spec requires byte 0 of the lun to be 1 */ - if (unlikely(*lunp != 1)) { - vq_err(vq, "Illegal virtio-scsi lun: %u\n", *lunp); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; - } + ret = vhost_scsi_get_req(vq, &vc, &tpg); + if (ret) + goto err; + + ret = -EIO; /* bad target on any error from here on */ - tpg = READ_ONCE(vs_tpg[*target]); - if (unlikely(!tpg)) { - /* Target does not exist, fail the request */ - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; - } /* * Determine data_direction by calculating the total outgoing * iovec sizes + incoming iovec sizes vs. virtio-scsi request + @@ -924,17 +995,17 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) */ prot_bytes = 0; - if (out_size > req_size) { + if (vc.out_size > vc.req_size) { data_direction = DMA_TO_DEVICE; - exp_data_len = out_size - req_size; - data_iter = out_iter; - } else if (in_size > rsp_size) { + exp_data_len = vc.out_size - vc.req_size; + data_iter = vc.out_iter; + } else if (vc.in_size > vc.rsp_size) { data_direction = DMA_FROM_DEVICE; - exp_data_len = in_size - rsp_size; + exp_data_len = vc.in_size - vc.rsp_size; - iov_iter_init(&in_iter, READ, &vq->iov[out], in, - rsp_size + exp_data_len); - iov_iter_advance(&in_iter, rsp_size); + iov_iter_init(&in_iter, READ, &vq->iov[vc.out], vc.in, + vc.rsp_size + exp_data_len); + iov_iter_advance(&in_iter, vc.rsp_size); data_iter = in_iter; } else { data_direction = DMA_NONE; @@ -950,21 +1021,20 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (data_direction != DMA_TO_DEVICE) { vq_err(vq, "Received non zero pi_bytesout," " but wrong data_direction\n"); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; + goto err; } prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesout); } else if (v_req_pi.pi_bytesin) { if (data_direction != DMA_FROM_DEVICE) { vq_err(vq, "Received non zero pi_bytesin," " but wrong data_direction\n"); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; + goto err; } prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin); } /* - * Set prot_iter to data_iter, and advance past any + * Set prot_iter to data_iter and truncate it to + * prot_bytes, and advance data_iter past any * preceeding prot_bytes that may be present. * * Also fix up the exp_data_len to reflect only the @@ -973,6 +1043,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (prot_bytes) { exp_data_len -= prot_bytes; prot_iter = data_iter; + iov_iter_truncate(&prot_iter, prot_bytes); iov_iter_advance(&data_iter, prot_bytes); } tag = vhost64_to_cpu(vq, v_req_pi.tag); @@ -996,8 +1067,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) vq_err(vq, "Received SCSI CDB with command_size: %d that" " exceeds SCSI_MAX_VARLEN_CDB_SIZE: %d\n", scsi_command_size(cdb), VHOST_SCSI_MAX_CDB_SIZE); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; + goto err; } cmd = vhost_scsi_get_tag(vq, tpg, cdb, tag, lun, task_attr, exp_data_len + prot_bytes, @@ -1005,13 +1075,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) if (IS_ERR(cmd)) { vq_err(vq, "vhost_scsi_get_tag failed %ld\n", PTR_ERR(cmd)); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; + goto err; } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = vq->iov[out]; - cmd->tvc_in_iovs = in; + cmd->tvc_resp_iov = vq->iov[vc.out]; + cmd->tvc_in_iovs = vc.in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", cmd->tvc_cdb[0], cmd->tvc_lun); @@ -1019,14 +1088,12 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) " %d\n", cmd, exp_data_len, prot_bytes, data_direction); if (data_direction != DMA_NONE) { - ret = vhost_scsi_mapal(cmd, - prot_bytes, &prot_iter, - exp_data_len, &data_iter); - if (unlikely(ret)) { + if (unlikely(vhost_scsi_mapal(cmd, prot_bytes, + &prot_iter, exp_data_len, + &data_iter))) { vq_err(vq, "Failed to map iov to sgl\n"); vhost_scsi_release_cmd(&cmd->tvc_se_cmd); - vhost_scsi_send_bad_target(vs, vq, head, out); - continue; + goto err; } } /* @@ -1034,7 +1101,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) * complete the virtio-scsi request in TCM callback context via * vhost_scsi_queue_data_in() and vhost_scsi_queue_status() */ - cmd->tvc_vq_desc = head; + cmd->tvc_vq_desc = vc.head; /* * Dispatch cmd descriptor for cmwq execution in process * context provided by vhost_scsi_workqueue. This also ensures @@ -1043,6 +1110,166 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) */ INIT_WORK(&cmd->work, vhost_scsi_submission_work); queue_work(vhost_scsi_workqueue, &cmd->work); + ret = 0; +err: + /* + * ENXIO: No more requests, or read error, wait for next kick + * EINVAL: Invalid response buffer, drop the request + * EIO: Respond with bad target + * EAGAIN: Pending request + */ + if (ret == -ENXIO) + break; + else if (ret == -EIO) + vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out); + } +out: + mutex_unlock(&vq->mutex); +} + +static void +vhost_scsi_send_tmf_reject(struct vhost_scsi *vs, + struct vhost_virtqueue *vq, + struct vhost_scsi_ctx *vc) +{ + struct virtio_scsi_ctrl_tmf_resp __user *resp; + struct virtio_scsi_ctrl_tmf_resp rsp; + int ret; + + pr_debug("%s\n", __func__); + memset(&rsp, 0, sizeof(rsp)); + rsp.response = VIRTIO_SCSI_S_FUNCTION_REJECTED; + resp = vq->iov[vc->out].iov_base; + ret = __copy_to_user(resp, &rsp, sizeof(rsp)); + if (!ret) + vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + else + pr_err("Faulted on virtio_scsi_ctrl_tmf_resp\n"); +} + +static void +vhost_scsi_send_an_resp(struct vhost_scsi *vs, + struct vhost_virtqueue *vq, + struct vhost_scsi_ctx *vc) +{ + struct virtio_scsi_ctrl_an_resp __user *resp; + struct virtio_scsi_ctrl_an_resp rsp; + int ret; + + pr_debug("%s\n", __func__); + memset(&rsp, 0, sizeof(rsp)); /* event_actual = 0 */ + rsp.response = VIRTIO_SCSI_S_OK; + resp = vq->iov[vc->out].iov_base; + ret = __copy_to_user(resp, &rsp, sizeof(rsp)); + if (!ret) + vhost_add_used_and_signal(&vs->dev, vq, vc->head, 0); + else + pr_err("Faulted on virtio_scsi_ctrl_an_resp\n"); +} + +static void +vhost_scsi_ctl_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) +{ + union { + __virtio32 type; + struct virtio_scsi_ctrl_an_req an; + struct virtio_scsi_ctrl_tmf_req tmf; + } v_req; + struct vhost_scsi_ctx vc; + size_t typ_size; + int ret; + + mutex_lock(&vq->mutex); + /* + * We can handle the vq only after the endpoint is setup by calling the + * VHOST_SCSI_SET_ENDPOINT ioctl. + */ + if (!vq->private_data) + goto out; + + memset(&vc, 0, sizeof(vc)); + + vhost_disable_notify(&vs->dev, vq); + + for (;;) { + ret = vhost_scsi_get_desc(vs, vq, &vc); + if (ret) + goto err; + + /* + * Get the request type first in order to setup + * other parameters dependent on the type. + */ + vc.req = &v_req.type; + typ_size = sizeof(v_req.type); + + if (unlikely(!copy_from_iter_full(vc.req, typ_size, + &vc.out_iter))) { + vq_err(vq, "Faulted on copy_from_iter tmf type\n"); + /* + * The size of the response buffer depends on the + * request type and must be validated against it. + * Since the request type is not known, don't send + * a response. + */ + continue; + } + + switch (v_req.type) { + case VIRTIO_SCSI_T_TMF: + vc.req = &v_req.tmf; + vc.req_size = sizeof(struct virtio_scsi_ctrl_tmf_req); + vc.rsp_size = sizeof(struct virtio_scsi_ctrl_tmf_resp); + vc.lunp = &v_req.tmf.lun[0]; + vc.target = &v_req.tmf.lun[1]; + break; + case VIRTIO_SCSI_T_AN_QUERY: + case VIRTIO_SCSI_T_AN_SUBSCRIBE: + vc.req = &v_req.an; + vc.req_size = sizeof(struct virtio_scsi_ctrl_an_req); + vc.rsp_size = sizeof(struct virtio_scsi_ctrl_an_resp); + vc.lunp = &v_req.an.lun[0]; + vc.target = NULL; + break; + default: + vq_err(vq, "Unknown control request %d", v_req.type); + continue; + } + + /* + * Validate the size of request and response buffers. + * Check for a sane response buffer so we can report + * early errors back to the guest. + */ + ret = vhost_scsi_chk_size(vq, &vc); + if (ret) + goto err; + + /* + * Get the rest of the request now that its size is known. + */ + vc.req += typ_size; + vc.req_size -= typ_size; + + ret = vhost_scsi_get_req(vq, &vc, NULL); + if (ret) + goto err; + + if (v_req.type == VIRTIO_SCSI_T_TMF) + vhost_scsi_send_tmf_reject(vs, vq, &vc); + else + vhost_scsi_send_an_resp(vs, vq, &vc); +err: + /* + * ENXIO: No more requests, or read error, wait for next kick + * EINVAL: Invalid response buffer, drop the request + * EIO: Respond with bad target + * EAGAIN: Pending request + */ + if (ret == -ENXIO) + break; + else if (ret == -EIO) + vhost_scsi_send_bad_target(vs, vq, vc.head, vc.out); } out: mutex_unlock(&vq->mutex); @@ -1050,7 +1277,12 @@ out: static void vhost_scsi_ctl_handle_kick(struct vhost_work *work) { + struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, + poll.work); + struct vhost_scsi *vs = container_of(vq->dev, struct vhost_scsi, dev); + pr_debug("%s: The handling func for control queue.\n", __func__); + vhost_scsi_ctl_handle_vq(vs, vq); } static void diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index f52008bb8df76e..3a5f81a66d34f0 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -30,6 +30,7 @@ #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/interval_tree_generic.h> +#include <linux/nospec.h> #include "vhost.h" @@ -1387,6 +1388,7 @@ long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *arg if (idx >= d->nvqs) return -ENOBUFS; + idx = array_index_nospec(idx, d->nvqs); vq = d->vqs[idx]; mutex_lock(&vq->mutex); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index d1c1f628372962..728ecd1eea305a 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -41,13 +41,34 @@ #define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256 #define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80 +#define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \ + __GFP_NOMEMALLOC) +/* The order of free page blocks to report to host */ +#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1) +/* The size of a free page block in bytes */ +#define VIRTIO_BALLOON_FREE_PAGE_SIZE \ + (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT)) + #ifdef CONFIG_BALLOON_COMPACTION static struct vfsmount *balloon_mnt; #endif +enum virtio_balloon_vq { + VIRTIO_BALLOON_VQ_INFLATE, + VIRTIO_BALLOON_VQ_DEFLATE, + VIRTIO_BALLOON_VQ_STATS, + VIRTIO_BALLOON_VQ_FREE_PAGE, + VIRTIO_BALLOON_VQ_MAX +}; + struct virtio_balloon { struct virtio_device *vdev; - struct virtqueue *inflate_vq, *deflate_vq, *stats_vq; + struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq; + + /* Balloon's own wq for cpu-intensive work items */ + struct workqueue_struct *balloon_wq; + /* The free page reporting work item submitted to the balloon wq */ + struct work_struct report_free_page_work; /* The balloon servicing is delegated to a freezable workqueue. */ struct work_struct update_balloon_stats_work; @@ -57,6 +78,18 @@ struct virtio_balloon { spinlock_t stop_update_lock; bool stop_update; + /* The list of allocated free pages, waiting to be given back to mm */ + struct list_head free_page_list; + spinlock_t free_page_list_lock; + /* The number of free page blocks on the above list */ + unsigned long num_free_page_blocks; + /* The cmd id received from host */ + u32 cmd_id_received; + /* The cmd id that is actively in use */ + __virtio32 cmd_id_active; + /* Buffer to store the stop sign */ + __virtio32 cmd_id_stop; + /* Waiting for host to ack the pages we released. */ wait_queue_head_t acked; @@ -320,17 +353,6 @@ static void stats_handle_request(struct virtio_balloon *vb) virtqueue_kick(vq); } -static void virtballoon_changed(struct virtio_device *vdev) -{ - struct virtio_balloon *vb = vdev->priv; - unsigned long flags; - - spin_lock_irqsave(&vb->stop_update_lock, flags); - if (!vb->stop_update) - queue_work(system_freezable_wq, &vb->update_balloon_size_work); - spin_unlock_irqrestore(&vb->stop_update_lock, flags); -} - static inline s64 towards_target(struct virtio_balloon *vb) { s64 target; @@ -347,6 +369,60 @@ static inline s64 towards_target(struct virtio_balloon *vb) return target - vb->num_pages; } +/* Gives back @num_to_return blocks of free pages to mm. */ +static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb, + unsigned long num_to_return) +{ + struct page *page; + unsigned long num_returned; + + spin_lock_irq(&vb->free_page_list_lock); + for (num_returned = 0; num_returned < num_to_return; num_returned++) { + page = balloon_page_pop(&vb->free_page_list); + if (!page) + break; + free_pages((unsigned long)page_address(page), + VIRTIO_BALLOON_FREE_PAGE_ORDER); + } + vb->num_free_page_blocks -= num_returned; + spin_unlock_irq(&vb->free_page_list_lock); + + return num_returned; +} + +static void virtballoon_changed(struct virtio_device *vdev) +{ + struct virtio_balloon *vb = vdev->priv; + unsigned long flags; + s64 diff = towards_target(vb); + + if (diff) { + spin_lock_irqsave(&vb->stop_update_lock, flags); + if (!vb->stop_update) + queue_work(system_freezable_wq, + &vb->update_balloon_size_work); + spin_unlock_irqrestore(&vb->stop_update_lock, flags); + } + + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { + virtio_cread(vdev, struct virtio_balloon_config, + free_page_report_cmd_id, &vb->cmd_id_received); + if (vb->cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) { + /* Pass ULONG_MAX to give back all the free pages */ + return_free_pages_to_mm(vb, ULONG_MAX); + } else if (vb->cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP && + vb->cmd_id_received != + virtio32_to_cpu(vdev, vb->cmd_id_active)) { + spin_lock_irqsave(&vb->stop_update_lock, flags); + if (!vb->stop_update) { + queue_work(vb->balloon_wq, + &vb->report_free_page_work); + } + spin_unlock_irqrestore(&vb->stop_update_lock, flags); + } + } +} + static void update_balloon_size(struct virtio_balloon *vb) { u32 actual = vb->num_pages; @@ -389,26 +465,44 @@ static void update_balloon_size_func(struct work_struct *work) static int init_vqs(struct virtio_balloon *vb) { - struct virtqueue *vqs[3]; - vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request }; - static const char * const names[] = { "inflate", "deflate", "stats" }; - int err, nvqs; + struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX]; + vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX]; + const char *names[VIRTIO_BALLOON_VQ_MAX]; + int err; /* - * We expect two virtqueues: inflate and deflate, and - * optionally stat. + * Inflateq and deflateq are used unconditionally. The names[] + * will be NULL if the related feature is not enabled, which will + * cause no allocation for the corresponding virtqueue in find_vqs. */ - nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2; - err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL); + callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack; + names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate"; + callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack; + names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate"; + names[VIRTIO_BALLOON_VQ_STATS] = NULL; + names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { + names[VIRTIO_BALLOON_VQ_STATS] = "stats"; + callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request; + } + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { + names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq"; + callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL; + } + + err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, + vqs, callbacks, names, NULL, NULL); if (err) return err; - vb->inflate_vq = vqs[0]; - vb->deflate_vq = vqs[1]; + vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE]; + vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE]; if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { struct scatterlist sg; unsigned int num_stats; - vb->stats_vq = vqs[2]; + vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS]; /* * Prime this virtqueue with one buffer so the hypervisor can @@ -426,9 +520,145 @@ static int init_vqs(struct virtio_balloon *vb) } virtqueue_kick(vb->stats_vq); } + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE]; + + return 0; +} + +static int send_cmd_id_start(struct virtio_balloon *vb) +{ + struct scatterlist sg; + struct virtqueue *vq = vb->free_page_vq; + int err, unused; + + /* Detach all the used buffers from the vq */ + while (virtqueue_get_buf(vq, &unused)) + ; + + vb->cmd_id_active = cpu_to_virtio32(vb->vdev, vb->cmd_id_received); + sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active)); + err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL); + if (!err) + virtqueue_kick(vq); + return err; +} + +static int send_cmd_id_stop(struct virtio_balloon *vb) +{ + struct scatterlist sg; + struct virtqueue *vq = vb->free_page_vq; + int err, unused; + + /* Detach all the used buffers from the vq */ + while (virtqueue_get_buf(vq, &unused)) + ; + + sg_init_one(&sg, &vb->cmd_id_stop, sizeof(vb->cmd_id_stop)); + err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_stop, GFP_KERNEL); + if (!err) + virtqueue_kick(vq); + return err; +} + +static int get_free_page_and_send(struct virtio_balloon *vb) +{ + struct virtqueue *vq = vb->free_page_vq; + struct page *page; + struct scatterlist sg; + int err, unused; + void *p; + + /* Detach all the used buffers from the vq */ + while (virtqueue_get_buf(vq, &unused)) + ; + + page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG, + VIRTIO_BALLOON_FREE_PAGE_ORDER); + /* + * When the allocation returns NULL, it indicates that we have got all + * the possible free pages, so return -EINTR to stop. + */ + if (!page) + return -EINTR; + + p = page_address(page); + sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE); + /* There is always 1 entry reserved for the cmd id to use. */ + if (vq->num_free > 1) { + err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL); + if (unlikely(err)) { + free_pages((unsigned long)p, + VIRTIO_BALLOON_FREE_PAGE_ORDER); + return err; + } + virtqueue_kick(vq); + spin_lock_irq(&vb->free_page_list_lock); + balloon_page_push(&vb->free_page_list, page); + vb->num_free_page_blocks++; + spin_unlock_irq(&vb->free_page_list_lock); + } else { + /* + * The vq has no available entry to add this page block, so + * just free it. + */ + free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER); + } + + return 0; +} + +static int send_free_pages(struct virtio_balloon *vb) +{ + int err; + u32 cmd_id_active; + + while (1) { + /* + * If a stop id or a new cmd id was just received from host, + * stop the reporting. + */ + cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active); + if (cmd_id_active != vb->cmd_id_received) + break; + + /* + * The free page blocks are allocated and sent to host one by + * one. + */ + err = get_free_page_and_send(vb); + if (err == -EINTR) + break; + else if (unlikely(err)) + return err; + } + return 0; } +static void report_free_page_func(struct work_struct *work) +{ + int err; + struct virtio_balloon *vb = container_of(work, struct virtio_balloon, + report_free_page_work); + struct device *dev = &vb->vdev->dev; + + /* Start by sending the received cmd id to host with an outbuf. */ + err = send_cmd_id_start(vb); + if (unlikely(err)) + dev_err(dev, "Failed to send a start id, err = %d\n", err); + + err = send_free_pages(vb); + if (unlikely(err)) + dev_err(dev, "Failed to send a free page, err = %d\n", err); + + /* End by sending a stop id to host with an outbuf. */ + err = send_cmd_id_stop(vb); + if (unlikely(err)) + dev_err(dev, "Failed to send a stop id, err = %d\n", err); +} + #ifdef CONFIG_BALLOON_COMPACTION /* * virtballoon_migratepage - perform the balloon page migration on behalf of @@ -512,14 +742,23 @@ static struct file_system_type balloon_fs = { #endif /* CONFIG_BALLOON_COMPACTION */ -static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, - struct shrink_control *sc) +static unsigned long shrink_free_pages(struct virtio_balloon *vb, + unsigned long pages_to_free) { - unsigned long pages_to_free, pages_freed = 0; - struct virtio_balloon *vb = container_of(shrinker, - struct virtio_balloon, shrinker); + unsigned long blocks_to_free, blocks_freed; - pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE; + pages_to_free = round_up(pages_to_free, + 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER); + blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + blocks_freed = return_free_pages_to_mm(vb, blocks_to_free); + + return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER; +} + +static unsigned long shrink_balloon_pages(struct virtio_balloon *vb, + unsigned long pages_to_free) +{ + unsigned long pages_freed = 0; /* * One invocation of leak_balloon can deflate at most @@ -527,12 +766,33 @@ static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, * multiple times to deflate pages till reaching pages_to_free. */ while (vb->num_pages && pages_to_free) { + pages_freed += leak_balloon(vb, pages_to_free) / + VIRTIO_BALLOON_PAGES_PER_PAGE; pages_to_free -= pages_freed; - pages_freed += leak_balloon(vb, pages_to_free); } update_balloon_size(vb); - return pages_freed / VIRTIO_BALLOON_PAGES_PER_PAGE; + return pages_freed; +} + +static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long pages_to_free, pages_freed = 0; + struct virtio_balloon *vb = container_of(shrinker, + struct virtio_balloon, shrinker); + + pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE; + + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + pages_freed = shrink_free_pages(vb, pages_to_free); + + if (pages_freed >= pages_to_free) + return pages_freed; + + pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed); + + return pages_freed; } static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, @@ -540,8 +800,12 @@ static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker, { struct virtio_balloon *vb = container_of(shrinker, struct virtio_balloon, shrinker); + unsigned long count; - return vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; + count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE; + count += vb->num_free_page_blocks >> VIRTIO_BALLOON_FREE_PAGE_ORDER; + + return count; } static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb) @@ -561,6 +825,7 @@ static int virtio_balloon_register_shrinker(struct virtio_balloon *vb) static int virtballoon_probe(struct virtio_device *vdev) { struct virtio_balloon *vb; + __u32 poison_val; int err; if (!vdev->config->get) { @@ -604,6 +869,36 @@ static int virtballoon_probe(struct virtio_device *vdev) } vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops; #endif + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { + /* + * There is always one entry reserved for cmd id, so the ring + * size needs to be at least two to report free page hints. + */ + if (virtqueue_get_vring_size(vb->free_page_vq) < 2) { + err = -ENOSPC; + goto out_del_vqs; + } + vb->balloon_wq = alloc_workqueue("balloon-wq", + WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0); + if (!vb->balloon_wq) { + err = -ENOMEM; + goto out_del_vqs; + } + INIT_WORK(&vb->report_free_page_work, report_free_page_func); + vb->cmd_id_received = VIRTIO_BALLOON_CMD_ID_STOP; + vb->cmd_id_active = cpu_to_virtio32(vb->vdev, + VIRTIO_BALLOON_CMD_ID_STOP); + vb->cmd_id_stop = cpu_to_virtio32(vb->vdev, + VIRTIO_BALLOON_CMD_ID_STOP); + vb->num_free_page_blocks = 0; + spin_lock_init(&vb->free_page_list_lock); + INIT_LIST_HEAD(&vb->free_page_list); + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) { + memset(&poison_val, PAGE_POISON, sizeof(poison_val)); + virtio_cwrite(vb->vdev, struct virtio_balloon_config, + poison_val, &poison_val); + } + } /* * We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a * shrinker needs to be registered to relieve memory pressure. @@ -611,7 +906,7 @@ static int virtballoon_probe(struct virtio_device *vdev) if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) { err = virtio_balloon_register_shrinker(vb); if (err) - goto out_del_vqs; + goto out_del_balloon_wq; } virtio_device_ready(vdev); @@ -619,6 +914,9 @@ static int virtballoon_probe(struct virtio_device *vdev) virtballoon_changed(vdev); return 0; +out_del_balloon_wq: + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) + destroy_workqueue(vb->balloon_wq); out_del_vqs: vdev->config->del_vqs(vdev); out_free_vb: @@ -652,6 +950,11 @@ static void virtballoon_remove(struct virtio_device *vdev) cancel_work_sync(&vb->update_balloon_size_work); cancel_work_sync(&vb->update_balloon_stats_work); + if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) { + cancel_work_sync(&vb->report_free_page_work); + destroy_workqueue(vb->balloon_wq); + } + remove_common(vb); #ifdef CONFIG_BALLOON_COMPACTION if (vb->vb_dev_info.inode) @@ -695,6 +998,9 @@ static int virtballoon_restore(struct virtio_device *vdev) static int virtballoon_validate(struct virtio_device *vdev) { + if (!page_poisoning_enabled()) + __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON); + __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM); return 0; } @@ -703,6 +1009,8 @@ static unsigned int features[] = { VIRTIO_BALLOON_F_MUST_TELL_HOST, VIRTIO_BALLOON_F_STATS_VQ, VIRTIO_BALLOON_F_DEFLATE_ON_OOM, + VIRTIO_BALLOON_F_FREE_PAGE_HINT, + VIRTIO_BALLOON_F_PAGE_POISON, }; static struct virtio_driver virtio_balloon_driver = { diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index b1092fbefa6309..2e5d845b509147 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -137,13 +137,13 @@ static void pvcalls_conn_back_read(void *opaque) if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 1, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted); } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 2, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted); } atomic_set(&map->read, 0); @@ -195,13 +195,13 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size); } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 2, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size); } atomic_set(&map->write, 0); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index e1cbdfdb7c684f..0bcbcc20f76954 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -65,7 +65,7 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) if (retval == 0) return retval; - iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bvec, 1, PAGE_SIZE); retval = p9_client_read(fid, page_offset(page), &to, &err); if (err) { @@ -175,7 +175,7 @@ static int v9fs_vfs_writepage_locked(struct page *page) bvec.bv_page = page; bvec.bv_offset = 0; bvec.bv_len = len; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len); + iov_iter_bvec(&from, WRITE, &bvec, 1, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index cb6c4031af552b..00745147329dc9 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -123,7 +123,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) if (rdir->tail == rdir->head) { struct iov_iter to; int n; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen); + iov_iter_kvec(&to, READ, &kvec, 1, buflen); n = p9_client_read(file->private_data, ctx->pos, &to, &err); if (err) diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 352abc39e891a1..ac8ff8ca4c115f 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -32,7 +32,7 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, struct iov_iter to; int err; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size); + iov_iter_kvec(&to, READ, &kvec, 1, buffer_size); attr_fid = p9_client_xattrwalk(fid, name, &attr_size); if (IS_ERR(attr_fid)) { @@ -107,7 +107,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, struct iov_iter from; int retval, err; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len); + iov_iter_kvec(&from, WRITE, &kvec, 1, value_len); p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n", name, value_len, flags); diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig index ebba3b18e5da6d..701aaa9b18994a 100644 --- a/fs/afs/Kconfig +++ b/fs/afs/Kconfig @@ -27,3 +27,15 @@ config AFS_FSCACHE help Say Y here if you want AFS data to be cached locally on disk through the generic filesystem cache manager + +config AFS_DEBUG_CURSOR + bool "AFS server cursor debugging" + depends on AFS_FS + help + Say Y here to cause the contents of a server cursor to be dumped to + the dmesg log if the server rotation algorithm fails to successfully + contact a server. + + See <file:Documentation/filesystems/afs.txt> for more information. + + If unsure, say N. diff --git a/fs/afs/Makefile b/fs/afs/Makefile index 546874057bd359..0738e2bf51936e 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -17,6 +17,7 @@ kafs-y := \ file.o \ flock.o \ fsclient.o \ + fs_probe.o \ inode.o \ main.o \ misc.o \ @@ -29,9 +30,13 @@ kafs-y := \ super.o \ netdevices.o \ vlclient.o \ + vl_list.o \ + vl_probe.o \ + vl_rotate.o \ volume.o \ write.o \ - xattr.o + xattr.o \ + yfsclient.o kafs-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_AFS_FS) := kafs.o diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 55a756c60746ca..967db336d11ae0 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -64,19 +64,25 @@ struct afs_addr_list *afs_alloc_addrlist(unsigned int nr, /* * Parse a text string consisting of delimited addresses. */ -struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, - char delim, - unsigned short service, - unsigned short port) +struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *net, + const char *text, size_t len, + char delim, + unsigned short service, + unsigned short port) { + struct afs_vlserver_list *vllist; struct afs_addr_list *alist; const char *p, *end = text + len; + const char *problem; unsigned int nr = 0; + int ret = -ENOMEM; _enter("%*.*s,%c", (int)len, (int)len, text, delim); - if (!len) + if (!len) { + _leave(" = -EDESTADDRREQ [empty]"); return ERR_PTR(-EDESTADDRREQ); + } if (delim == ':' && (memchr(text, ',', len) || !memchr(text, '.', len))) delim = ','; @@ -84,18 +90,24 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, /* Count the addresses */ p = text; do { - if (!*p) - return ERR_PTR(-EINVAL); + if (!*p) { + problem = "nul"; + goto inval; + } if (*p == delim) continue; nr++; if (*p == '[') { p++; - if (p == end) - return ERR_PTR(-EINVAL); + if (p == end) { + problem = "brace1"; + goto inval; + } p = memchr(p, ']', end - p); - if (!p) - return ERR_PTR(-EINVAL); + if (!p) { + problem = "brace2"; + goto inval; + } p++; if (p >= end) break; @@ -109,10 +121,19 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, _debug("%u/%u addresses", nr, AFS_MAX_ADDRESSES); - alist = afs_alloc_addrlist(nr, service, port); - if (!alist) + vllist = afs_alloc_vlserver_list(1); + if (!vllist) return ERR_PTR(-ENOMEM); + vllist->nr_servers = 1; + vllist->servers[0].server = afs_alloc_vlserver("<dummy>", 7, AFS_VL_PORT); + if (!vllist->servers[0].server) + goto error_vl; + + alist = afs_alloc_addrlist(nr, service, AFS_VL_PORT); + if (!alist) + goto error; + /* Extract the addresses */ p = text; do { @@ -135,17 +156,21 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, break; } - if (in4_pton(p, q - p, (u8 *)&x[0], -1, &stop)) + if (in4_pton(p, q - p, (u8 *)&x[0], -1, &stop)) { family = AF_INET; - else if (in6_pton(p, q - p, (u8 *)x, -1, &stop)) + } else if (in6_pton(p, q - p, (u8 *)x, -1, &stop)) { family = AF_INET6; - else + } else { + problem = "family"; goto bad_address; + } - if (stop != q) + p = q; + if (stop != p) { + problem = "nostop"; goto bad_address; + } - p = q; if (q < end && *q == ']') p++; @@ -154,18 +179,23 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, /* Port number specification "+1234" */ xport = 0; p++; - if (p >= end || !isdigit(*p)) + if (p >= end || !isdigit(*p)) { + problem = "port"; goto bad_address; + } do { xport *= 10; xport += *p - '0'; - if (xport > 65535) + if (xport > 65535) { + problem = "pval"; goto bad_address; + } p++; } while (p < end && isdigit(*p)); } else if (*p == delim) { p++; } else { + problem = "weird"; goto bad_address; } } @@ -177,12 +207,23 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, } while (p < end); + rcu_assign_pointer(vllist->servers[0].server->addresses, alist); _leave(" = [nr %u]", alist->nr_addrs); - return alist; + return vllist; -bad_address: - kfree(alist); +inval: + _leave(" = -EINVAL [%s %zu %*.*s]", + problem, p - text, (int)len, (int)len, text); return ERR_PTR(-EINVAL); +bad_address: + _leave(" = -EINVAL [%s %zu %*.*s]", + problem, p - text, (int)len, (int)len, text); + ret = -EINVAL; +error: + afs_put_addrlist(alist); +error_vl: + afs_put_vlserverlist(net, vllist); + return ERR_PTR(ret); } /* @@ -201,30 +242,34 @@ static int afs_cmp_addr_list(const struct afs_addr_list *a1, /* * Perform a DNS query for VL servers and build a up an address list. */ -struct afs_addr_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry) +struct afs_vlserver_list *afs_dns_query(struct afs_cell *cell, time64_t *_expiry) { - struct afs_addr_list *alist; - char *vllist = NULL; + struct afs_vlserver_list *vllist; + char *result = NULL; int ret; _enter("%s", cell->name); - ret = dns_query("afsdb", cell->name, cell->name_len, - "", &vllist, _expiry); - if (ret < 0) + ret = dns_query("afsdb", cell->name, cell->name_len, "srv=1", + &result, _expiry); + if (ret < 0) { + _leave(" = %d [dns]", ret); return ERR_PTR(ret); - - alist = afs_parse_text_addrs(vllist, strlen(vllist), ',', - VL_SERVICE, AFS_VL_PORT); - if (IS_ERR(alist)) { - kfree(vllist); - if (alist != ERR_PTR(-ENOMEM)) - pr_err("Failed to parse DNS data\n"); - return alist; } - kfree(vllist); - return alist; + if (*_expiry == 0) + *_expiry = ktime_get_real_seconds() + 60; + + if (ret > 1 && result[0] == 0) + vllist = afs_extract_vlserver_list(cell, result, ret); + else + vllist = afs_parse_text_addrs(cell->net, result, ret, ',', + VL_SERVICE, AFS_VL_PORT); + kfree(result); + if (IS_ERR(vllist) && vllist != ERR_PTR(-ENOMEM)) + pr_err("Failed to parse DNS data %ld\n", PTR_ERR(vllist)); + + return vllist; } /* @@ -258,6 +303,8 @@ void afs_merge_fs_addr4(struct afs_addr_list *alist, __be32 xdr, u16 port) sizeof(alist->addrs[0]) * (alist->nr_addrs - i)); srx = &alist->addrs[i]; + srx->srx_family = AF_RXRPC; + srx->transport_type = SOCK_DGRAM; srx->transport_len = sizeof(srx->transport.sin); srx->transport.sin.sin_family = AF_INET; srx->transport.sin.sin_port = htons(port); @@ -296,6 +343,8 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port) sizeof(alist->addrs[0]) * (alist->nr_addrs - i)); srx = &alist->addrs[i]; + srx->srx_family = AF_RXRPC; + srx->transport_type = SOCK_DGRAM; srx->transport_len = sizeof(srx->transport.sin6); srx->transport.sin6.sin6_family = AF_INET6; srx->transport.sin6.sin6_port = htons(port); @@ -308,25 +357,33 @@ void afs_merge_fs_addr6(struct afs_addr_list *alist, __be32 *xdr, u16 port) */ bool afs_iterate_addresses(struct afs_addr_cursor *ac) { - _enter("%hu+%hd", ac->start, (short)ac->index); + unsigned long set, failed; + int index; if (!ac->alist) return false; - if (ac->begun) { - ac->index++; - if (ac->index == ac->alist->nr_addrs) - ac->index = 0; + set = ac->alist->responded; + failed = ac->alist->failed; + _enter("%lx-%lx-%lx,%d", set, failed, ac->tried, ac->index); - if (ac->index == ac->start) { - ac->error = -EDESTADDRREQ; - return false; - } - } + ac->nr_iterations++; + + set &= ~(failed | ac->tried); + + if (!set) + return false; - ac->begun = true; + index = READ_ONCE(ac->alist->preferred); + if (test_bit(index, &set)) + goto selected; + + index = __ffs(set); + +selected: + ac->index = index; + set_bit(index, &ac->tried); ac->responded = false; - ac->addr = &ac->alist->addrs[ac->index]; return true; } @@ -339,53 +396,13 @@ int afs_end_cursor(struct afs_addr_cursor *ac) alist = ac->alist; if (alist) { - if (ac->responded && ac->index != ac->start) - WRITE_ONCE(alist->index, ac->index); + if (ac->responded && + ac->index != alist->preferred && + test_bit(ac->alist->preferred, &ac->tried)) + WRITE_ONCE(alist->preferred, ac->index); afs_put_addrlist(alist); + ac->alist = NULL; } - ac->addr = NULL; - ac->alist = NULL; - ac->begun = false; return ac->error; } - -/* - * Set the address cursor for iterating over VL servers. - */ -int afs_set_vl_cursor(struct afs_addr_cursor *ac, struct afs_cell *cell) -{ - struct afs_addr_list *alist; - int ret; - - if (!rcu_access_pointer(cell->vl_addrs)) { - ret = wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET, - TASK_INTERRUPTIBLE); - if (ret < 0) - return ret; - - if (!rcu_access_pointer(cell->vl_addrs) && - ktime_get_real_seconds() < cell->dns_expiry) - return cell->error; - } - - read_lock(&cell->vl_addrs_lock); - alist = rcu_dereference_protected(cell->vl_addrs, - lockdep_is_held(&cell->vl_addrs_lock)); - if (alist->nr_addrs > 0) - afs_get_addrlist(alist); - else - alist = NULL; - read_unlock(&cell->vl_addrs_lock); - - if (!alist) - return -EDESTADDRREQ; - - ac->alist = alist; - ac->addr = NULL; - ac->start = READ_ONCE(alist->index); - ac->index = ac->start; - ac->error = 0; - ac->begun = false; - return 0; -} diff --git a/fs/afs/afs.h b/fs/afs/afs.h index b4ff1f7ae4ab04..d12ffb457e4745 100644 --- a/fs/afs/afs.h +++ b/fs/afs/afs.h @@ -23,9 +23,9 @@ #define AFSPATHMAX 1024 /* Maximum length of a pathname plus NUL */ #define AFSOPAQUEMAX 1024 /* Maximum length of an opaque field */ -typedef unsigned afs_volid_t; -typedef unsigned afs_vnodeid_t; -typedef unsigned long long afs_dataversion_t; +typedef u64 afs_volid_t; +typedef u64 afs_vnodeid_t; +typedef u64 afs_dataversion_t; typedef enum { AFSVL_RWVOL, /* read/write volume */ @@ -52,8 +52,9 @@ typedef enum { */ struct afs_fid { afs_volid_t vid; /* volume ID */ - afs_vnodeid_t vnode; /* file index within volume */ - unsigned unique; /* unique ID number (file index version) */ + afs_vnodeid_t vnode; /* Lower 64-bits of file index within volume */ + u32 vnode_hi; /* Upper 32-bits of file index */ + u32 unique; /* unique ID number (file index version) */ }; /* @@ -67,14 +68,14 @@ typedef enum { } afs_callback_type_t; struct afs_callback { + time64_t expires_at; /* Time at which expires */ unsigned version; /* Callback version */ - unsigned expiry; /* Time at which expires */ afs_callback_type_t type; /* Type of callback */ }; struct afs_callback_break { struct afs_fid fid; /* File identifier */ - struct afs_callback cb; /* Callback details */ + //struct afs_callback cb; /* Callback details */ }; #define AFSCBMAX 50 /* maximum callbacks transferred per bulk op */ @@ -129,19 +130,18 @@ typedef u32 afs_access_t; struct afs_file_status { u64 size; /* file size */ afs_dataversion_t data_version; /* current data version */ - time_t mtime_client; /* last time client changed data */ - time_t mtime_server; /* last time server changed data */ - unsigned abort_code; /* Abort if bulk-fetching this failed */ - - afs_file_type_t type; /* file type */ - unsigned nlink; /* link count */ - u32 author; /* author ID */ - u32 owner; /* owner ID */ - u32 group; /* group ID */ + struct timespec64 mtime_client; /* Last time client changed data */ + struct timespec64 mtime_server; /* Last time server changed data */ + s64 author; /* author ID */ + s64 owner; /* owner ID */ + s64 group; /* group ID */ afs_access_t caller_access; /* access rights for authenticated caller */ afs_access_t anon_access; /* access rights for unauthenticated caller */ umode_t mode; /* UNIX mode */ + afs_file_type_t type; /* file type */ + u32 nlink; /* link count */ s32 lock_count; /* file lock count (0=UNLK -1=WRLCK +ve=#RDLCK */ + u32 abort_code; /* Abort if bulk-fetching this failed */ }; /* @@ -158,25 +158,27 @@ struct afs_file_status { * AFS volume synchronisation information */ struct afs_volsync { - time_t creation; /* volume creation time */ + time64_t creation; /* volume creation time */ }; /* * AFS volume status record */ struct afs_volume_status { - u32 vid; /* volume ID */ - u32 parent_id; /* parent volume ID */ + afs_volid_t vid; /* volume ID */ + afs_volid_t parent_id; /* parent volume ID */ u8 online; /* true if volume currently online and available */ u8 in_service; /* true if volume currently in service */ u8 blessed; /* same as in_service */ u8 needs_salvage; /* true if consistency checking required */ u32 type; /* volume type (afs_voltype_t) */ - u32 min_quota; /* minimum space set aside (blocks) */ - u32 max_quota; /* maximum space this volume may occupy (blocks) */ - u32 blocks_in_use; /* space this volume currently occupies (blocks) */ - u32 part_blocks_avail; /* space available in volume's partition */ - u32 part_max_blocks; /* size of volume's partition */ + u64 min_quota; /* minimum space set aside (blocks) */ + u64 max_quota; /* maximum space this volume may occupy (blocks) */ + u64 blocks_in_use; /* space this volume currently occupies (blocks) */ + u64 part_blocks_avail; /* space available in volume's partition */ + u64 part_max_blocks; /* size of volume's partition */ + s64 vol_copy_date; + s64 vol_backup_date; }; #define AFS_BLOCK_SIZE 1024 diff --git a/fs/afs/cache.c b/fs/afs/cache.c index b1c31ec4523a89..f6d0a21e8052f0 100644 --- a/fs/afs/cache.c +++ b/fs/afs/cache.c @@ -49,7 +49,7 @@ static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data, struct afs_vnode *vnode = cookie_netfs_data; struct afs_vnode_cache_aux aux; - _enter("{%x,%x,%llx},%p,%u", + _enter("{%llx,%x,%llx},%p,%u", vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version, buffer, buflen); diff --git a/fs/afs/callback.c b/fs/afs/callback.c index 5f261fbf2182b2..1c7955f5cdaf2e 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -210,12 +210,10 @@ void afs_init_callback_state(struct afs_server *server) /* * actually break a callback */ -void afs_break_callback(struct afs_vnode *vnode) +void __afs_break_callback(struct afs_vnode *vnode) { _enter(""); - write_seqlock(&vnode->cb_lock); - clear_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { vnode->cb_break++; @@ -230,7 +228,12 @@ void afs_break_callback(struct afs_vnode *vnode) afs_lock_may_be_available(vnode); spin_unlock(&vnode->lock); } +} +void afs_break_callback(struct afs_vnode *vnode) +{ + write_seqlock(&vnode->cb_lock); + __afs_break_callback(vnode); write_sequnlock(&vnode->cb_lock); } @@ -310,14 +313,10 @@ void afs_break_callbacks(struct afs_server *server, size_t count, /* TODO: Sort the callback break list by volume ID */ for (; count > 0; callbacks++, count--) { - _debug("- Fid { vl=%08x n=%u u=%u } CB { v=%u x=%u t=%u }", + _debug("- Fid { vl=%08llx n=%llu u=%u }", callbacks->fid.vid, callbacks->fid.vnode, - callbacks->fid.unique, - callbacks->cb.version, - callbacks->cb.expiry, - callbacks->cb.type - ); + callbacks->fid.unique); afs_break_one_callback(server, &callbacks->fid); } diff --git a/fs/afs/cell.c b/fs/afs/cell.c index 6127f0fcd62c4e..cf445dbd5f2e05 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -20,6 +20,8 @@ #include "internal.h" static unsigned __read_mostly afs_cell_gc_delay = 10; +static unsigned __read_mostly afs_cell_min_ttl = 10 * 60; +static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60; static void afs_manage_cell(struct work_struct *); @@ -119,7 +121,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, */ static struct afs_cell *afs_alloc_cell(struct afs_net *net, const char *name, unsigned int namelen, - const char *vllist) + const char *addresses) { struct afs_cell *cell; int i, ret; @@ -134,7 +136,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, if (namelen == 5 && memcmp(name, "@cell", 5) == 0) return ERR_PTR(-EINVAL); - _enter("%*.*s,%s", namelen, namelen, name, vllist); + _enter("%*.*s,%s", namelen, namelen, name, addresses); cell = kzalloc(sizeof(struct afs_cell), GFP_KERNEL); if (!cell) { @@ -153,23 +155,26 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, (1 << AFS_CELL_FL_NO_LOOKUP_YET)); INIT_LIST_HEAD(&cell->proc_volumes); rwlock_init(&cell->proc_lock); - rwlock_init(&cell->vl_addrs_lock); + rwlock_init(&cell->vl_servers_lock); /* Fill in the VL server list if we were given a list of addresses to * use. */ - if (vllist) { - struct afs_addr_list *alist; - - alist = afs_parse_text_addrs(vllist, strlen(vllist), ':', - VL_SERVICE, AFS_VL_PORT); - if (IS_ERR(alist)) { - ret = PTR_ERR(alist); + if (addresses) { + struct afs_vlserver_list *vllist; + + vllist = afs_parse_text_addrs(net, + addresses, strlen(addresses), ':', + VL_SERVICE, AFS_VL_PORT); + if (IS_ERR(vllist)) { + ret = PTR_ERR(vllist); goto parse_failed; } - rcu_assign_pointer(cell->vl_addrs, alist); + rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = TIME64_MAX; + } else { + cell->dns_expiry = ktime_get_real_seconds(); } _leave(" = %p", cell); @@ -356,26 +361,40 @@ int afs_cell_init(struct afs_net *net, const char *rootcell) */ static void afs_update_cell(struct afs_cell *cell) { - struct afs_addr_list *alist, *old; - time64_t now, expiry; + struct afs_vlserver_list *vllist, *old; + unsigned int min_ttl = READ_ONCE(afs_cell_min_ttl); + unsigned int max_ttl = READ_ONCE(afs_cell_max_ttl); + time64_t now, expiry = 0; _enter("%s", cell->name); - alist = afs_dns_query(cell, &expiry); - if (IS_ERR(alist)) { - switch (PTR_ERR(alist)) { + vllist = afs_dns_query(cell, &expiry); + + now = ktime_get_real_seconds(); + if (min_ttl > max_ttl) + max_ttl = min_ttl; + if (expiry < now + min_ttl) + expiry = now + min_ttl; + else if (expiry > now + max_ttl) + expiry = now + max_ttl; + + if (IS_ERR(vllist)) { + switch (PTR_ERR(vllist)) { case -ENODATA: - /* The DNS said that the cell does not exist */ + case -EDESTADDRREQ: + /* The DNS said that the cell does not exist or there + * weren't any addresses to be had. + */ set_bit(AFS_CELL_FL_NOT_FOUND, &cell->flags); clear_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); - cell->dns_expiry = ktime_get_real_seconds() + 61; + cell->dns_expiry = expiry; break; case -EAGAIN: case -ECONNREFUSED: default: set_bit(AFS_CELL_FL_DNS_FAIL, &cell->flags); - cell->dns_expiry = ktime_get_real_seconds() + 10; + cell->dns_expiry = now + 10; break; } @@ -387,12 +406,12 @@ static void afs_update_cell(struct afs_cell *cell) /* Exclusion on changing vl_addrs is achieved by a * non-reentrant work item. */ - old = rcu_dereference_protected(cell->vl_addrs, true); - rcu_assign_pointer(cell->vl_addrs, alist); + old = rcu_dereference_protected(cell->vl_servers, true); + rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = expiry; if (old) - afs_put_addrlist(old); + afs_put_vlserverlist(cell->net, old); } if (test_and_clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags)) @@ -414,7 +433,7 @@ static void afs_cell_destroy(struct rcu_head *rcu) ASSERTCMP(atomic_read(&cell->usage), ==, 0); - afs_put_addrlist(rcu_access_pointer(cell->vl_addrs)); + afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers)); key_put(cell->anonymous_key); kfree(cell); diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 9e51d6fe7e8f97..8ee5972893ed5a 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -16,6 +16,7 @@ #include <linux/ip.h> #include "internal.h" #include "afs_cm.h" +#include "protocol_yfs.h" static int afs_deliver_cb_init_call_back_state(struct afs_call *); static int afs_deliver_cb_init_call_back_state3(struct afs_call *); @@ -30,6 +31,8 @@ static void SRXAFSCB_Probe(struct work_struct *); static void SRXAFSCB_ProbeUuid(struct work_struct *); static void SRXAFSCB_TellMeAboutYourself(struct work_struct *); +static int afs_deliver_yfs_cb_callback(struct afs_call *); + #define CM_NAME(name) \ const char afs_SRXCB##name##_name[] __tracepoint_string = \ "CB." #name @@ -101,12 +104,25 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { }; /* + * YFS CB.CallBack operation type + */ +static CM_NAME(YFS_CallBack); +static const struct afs_call_type afs_SRXYFSCB_CallBack = { + .name = afs_SRXCBYFS_CallBack_name, + .deliver = afs_deliver_yfs_cb_callback, + .destructor = afs_cm_destructor, + .work = SRXAFSCB_CallBack, +}; + +/* * route an incoming cache manager call * - return T if supported, F if not */ bool afs_cm_incoming_call(struct afs_call *call) { - _enter("{CB.OP %u}", call->operation_ID); + _enter("{%u, CB.OP %u}", call->service_id, call->operation_ID); + + call->epoch = rxrpc_kernel_get_epoch(call->net->socket, call->rxcall); switch (call->operation_ID) { case CBCallBack: @@ -127,12 +143,102 @@ bool afs_cm_incoming_call(struct afs_call *call) case CBTellMeAboutYourself: call->type = &afs_SRXCBTellMeAboutYourself; return true; + case YFSCBCallBack: + if (call->service_id != YFS_CM_SERVICE) + return false; + call->type = &afs_SRXYFSCB_CallBack; + return true; default: return false; } } /* + * Record a probe to the cache manager from a server. + */ +static int afs_record_cm_probe(struct afs_call *call, struct afs_server *server) +{ + _enter(""); + + if (test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags) && + !test_bit(AFS_SERVER_FL_PROBING, &server->flags)) { + if (server->cm_epoch == call->epoch) + return 0; + + if (!server->probe.said_rebooted) { + pr_notice("kAFS: FS rebooted %pU\n", &server->uuid); + server->probe.said_rebooted = true; + } + } + + spin_lock(&server->probe_lock); + + if (!test_bit(AFS_SERVER_FL_HAVE_EPOCH, &server->flags)) { + server->cm_epoch = call->epoch; + server->probe.cm_epoch = call->epoch; + goto out; + } + + if (server->probe.cm_probed && + call->epoch != server->probe.cm_epoch && + !server->probe.said_inconsistent) { + pr_notice("kAFS: FS endpoints inconsistent %pU\n", + &server->uuid); + server->probe.said_inconsistent = true; + } + + if (!server->probe.cm_probed || call->epoch == server->cm_epoch) + server->probe.cm_epoch = server->cm_epoch; + +out: + server->probe.cm_probed = true; + spin_unlock(&server->probe_lock); + return 0; +} + +/* + * Find the server record by peer address and record a probe to the cache + * manager from a server. + */ +static int afs_find_cm_server_by_peer(struct afs_call *call) +{ + struct sockaddr_rxrpc srx; + struct afs_server *server; + + rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); + + server = afs_find_server(call->net, &srx); + if (!server) { + trace_afs_cm_no_server(call, &srx); + return 0; + } + + call->cm_server = server; + return afs_record_cm_probe(call, server); +} + +/* + * Find the server record by server UUID and record a probe to the cache + * manager from a server. + */ +static int afs_find_cm_server_by_uuid(struct afs_call *call, + struct afs_uuid *uuid) +{ + struct afs_server *server; + + rcu_read_lock(); + server = afs_find_server_by_uuid(call->net, call->request); + rcu_read_unlock(); + if (!server) { + trace_afs_cm_no_server_u(call, call->request); + return 0; + } + + call->cm_server = server; + return afs_record_cm_probe(call, server); +} + +/* * Clean up a cache manager call. */ static void afs_cm_destructor(struct afs_call *call) @@ -168,7 +274,6 @@ static void SRXAFSCB_CallBack(struct work_struct *work) static int afs_deliver_cb_callback(struct afs_call *call) { struct afs_callback_break *cb; - struct sockaddr_rxrpc srx; __be32 *bp; int ret, loop; @@ -176,32 +281,32 @@ static int afs_deliver_cb_callback(struct afs_call *call) switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; /* extract the FID array and its count in two steps */ case 1: _debug("extract FID count"); - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->count = ntohl(call->tmp); _debug("FID count: %u", call->count); if (call->count > AFSCBMAX) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_cb_fid_count); call->buffer = kmalloc(array3_size(call->count, 3, 4), GFP_KERNEL); if (!call->buffer) return -ENOMEM; - call->offset = 0; + afs_extract_to_buf(call, call->count * 3 * 4); call->unmarshall++; case 2: _debug("extract FID array"); - ret = afs_extract_data(call, call->buffer, - call->count * 3 * 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -218,59 +323,46 @@ static int afs_deliver_cb_callback(struct afs_call *call) cb->fid.vid = ntohl(*bp++); cb->fid.vnode = ntohl(*bp++); cb->fid.unique = ntohl(*bp++); - cb->cb.type = AFSCM_CB_UNTYPED; } - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; /* extract the callback array and its count in two steps */ case 3: _debug("extract CB count"); - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->count2 = ntohl(call->tmp); _debug("CB count: %u", call->count2); if (call->count2 != call->count && call->count2 != 0) - return afs_protocol_error(call, -EBADMSG); - call->offset = 0; + return afs_protocol_error(call, -EBADMSG, + afs_eproto_cb_count); + call->_iter = &call->iter; + iov_iter_discard(&call->iter, READ, call->count2 * 3 * 4); call->unmarshall++; case 4: - _debug("extract CB array"); - ret = afs_extract_data(call, call->buffer, - call->count2 * 3 * 4, false); + _debug("extract discard %zu/%u", + iov_iter_count(&call->iter), call->count2 * 3 * 4); + + ret = afs_extract_data(call, false); if (ret < 0) return ret; - _debug("unmarshall CB array"); - cb = call->request; - bp = call->buffer; - for (loop = call->count2; loop > 0; loop--, cb++) { - cb->cb.version = ntohl(*bp++); - cb->cb.expiry = ntohl(*bp++); - cb->cb.type = ntohl(*bp++); - } - - call->offset = 0; call->unmarshall++; case 5: break; } if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) - return -EIO; + return afs_io_error(call, afs_io_error_cm_reply); /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); - call->cm_server = afs_find_server(call->net, &srx); - if (!call->cm_server) - trace_afs_cm_no_server(call, &srx); - - return afs_queue_call_work(call); + return afs_find_cm_server_by_peer(call); } /* @@ -294,24 +386,18 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) */ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) { - struct sockaddr_rxrpc srx; int ret; _enter(""); - rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); - - ret = afs_extract_data(call, NULL, 0, false); + afs_extract_discard(call, 0); + ret = afs_extract_data(call, false); if (ret < 0) return ret; /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - call->cm_server = afs_find_server(call->net, &srx); - if (!call->cm_server) - trace_afs_cm_no_server(call, &srx); - - return afs_queue_call_work(call); + return afs_find_cm_server_by_peer(call); } /* @@ -330,16 +416,15 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) switch (call->unmarshall) { case 0: - call->offset = 0; call->buffer = kmalloc_array(11, sizeof(__be32), GFP_KERNEL); if (!call->buffer) return -ENOMEM; + afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; case 1: _debug("extract UUID"); - ret = afs_extract_data(call, call->buffer, - 11 * sizeof(__be32), false); + ret = afs_extract_data(call, false); switch (ret) { case 0: break; case -EAGAIN: return 0; @@ -362,7 +447,6 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) for (loop = 0; loop < 6; loop++) r->node[loop] = ntohl(b[loop + 5]); - call->offset = 0; call->unmarshall++; case 2: @@ -370,17 +454,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) } if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) - return -EIO; + return afs_io_error(call, afs_io_error_cm_reply); /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - rcu_read_lock(); - call->cm_server = afs_find_server_by_uuid(call->net, call->request); - rcu_read_unlock(); - if (!call->cm_server) - trace_afs_cm_no_server_u(call, call->request); - - return afs_queue_call_work(call); + return afs_find_cm_server_by_uuid(call, call->request); } /* @@ -405,14 +483,14 @@ static int afs_deliver_cb_probe(struct afs_call *call) _enter(""); - ret = afs_extract_data(call, NULL, 0, false); + afs_extract_discard(call, 0); + ret = afs_extract_data(call, false); if (ret < 0) return ret; if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) - return -EIO; - - return afs_queue_call_work(call); + return afs_io_error(call, afs_io_error_cm_reply); + return afs_find_cm_server_by_peer(call); } /* @@ -453,16 +531,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) switch (call->unmarshall) { case 0: - call->offset = 0; call->buffer = kmalloc_array(11, sizeof(__be32), GFP_KERNEL); if (!call->buffer) return -ENOMEM; + afs_extract_to_buf(call, 11 * sizeof(__be32)); call->unmarshall++; case 1: _debug("extract UUID"); - ret = afs_extract_data(call, call->buffer, - 11 * sizeof(__be32), false); + ret = afs_extract_data(call, false); switch (ret) { case 0: break; case -EAGAIN: return 0; @@ -485,7 +562,6 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) for (loop = 0; loop < 6; loop++) r->node[loop] = ntohl(b[loop + 5]); - call->offset = 0; call->unmarshall++; case 2: @@ -493,9 +569,8 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call) } if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) - return -EIO; - - return afs_queue_call_work(call); + return afs_io_error(call, afs_io_error_cm_reply); + return afs_find_cm_server_by_uuid(call, call->request); } /* @@ -570,12 +645,88 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call) _enter(""); - ret = afs_extract_data(call, NULL, 0, false); + afs_extract_discard(call, 0); + ret = afs_extract_data(call, false); if (ret < 0) return ret; if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) - return -EIO; + return afs_io_error(call, afs_io_error_cm_reply); + return afs_find_cm_server_by_peer(call); +} + +/* + * deliver request data to a YFS CB.CallBack call + */ +static int afs_deliver_yfs_cb_callback(struct afs_call *call) +{ + struct afs_callback_break *cb; + struct yfs_xdr_YFSFid *bp; + size_t size; + int ret, loop; + + _enter("{%u}", call->unmarshall); + + switch (call->unmarshall) { + case 0: + afs_extract_to_tmp(call); + call->unmarshall++; + + /* extract the FID array and its count in two steps */ + case 1: + _debug("extract FID count"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + call->count = ntohl(call->tmp); + _debug("FID count: %u", call->count); + if (call->count > YFSCBMAX) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_cb_fid_count); + + size = array_size(call->count, sizeof(struct yfs_xdr_YFSFid)); + call->buffer = kmalloc(size, GFP_KERNEL); + if (!call->buffer) + return -ENOMEM; + afs_extract_to_buf(call, size); + call->unmarshall++; + + case 2: + _debug("extract FID array"); + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + _debug("unmarshall FID array"); + call->request = kcalloc(call->count, + sizeof(struct afs_callback_break), + GFP_KERNEL); + if (!call->request) + return -ENOMEM; + + cb = call->request; + bp = call->buffer; + for (loop = call->count; loop > 0; loop--, cb++) { + cb->fid.vid = xdr_to_u64(bp->volume); + cb->fid.vnode = xdr_to_u64(bp->vnode.lo); + cb->fid.vnode_hi = ntohl(bp->vnode.hi); + cb->fid.unique = ntohl(bp->vnode.unique); + bp++; + } + + afs_extract_to_tmp(call); + call->unmarshall++; + + case 3: + break; + } + + if (!afs_check_call_state(call, AFS_CALL_SV_REPLYING)) + return afs_io_error(call, afs_io_error_cm_reply); - return afs_queue_call_work(call); + /* We'll need the file server record as that tells us which set of + * vnodes to operate upon. + */ + return afs_find_cm_server_by_peer(call); } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 855bf2b79fed41..43dea3b00c29b9 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -138,6 +138,7 @@ static bool afs_dir_check_page(struct afs_vnode *dvnode, struct page *page, ntohs(dbuf->blocks[tmp].hdr.magic)); trace_afs_dir_check_failed(dvnode, off, i_size); kunmap(page); + trace_afs_file_error(dvnode, -EIO, afs_file_error_dir_bad_magic); goto error; } @@ -190,9 +191,11 @@ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) retry: i_size = i_size_read(&dvnode->vfs_inode); if (i_size < 2048) - return ERR_PTR(-EIO); - if (i_size > 2048 * 1024) + return ERR_PTR(afs_bad(dvnode, afs_file_error_dir_small)); + if (i_size > 2048 * 1024) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); return ERR_PTR(-EFBIG); + } _enter("%llu", i_size); @@ -315,7 +318,8 @@ content_has_grown: /* * deal with one block in an AFS directory */ -static int afs_dir_iterate_block(struct dir_context *ctx, +static int afs_dir_iterate_block(struct afs_vnode *dvnode, + struct dir_context *ctx, union afs_xdr_dir_block *block, unsigned blkoff) { @@ -365,7 +369,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx, " (len %u/%zu)", blkoff / sizeof(union afs_xdr_dir_block), offset, next, tmp, nlen); - return -EIO; + return afs_bad(dvnode, afs_file_error_dir_over_end); } if (!(block->hdr.bitmap[next / 8] & (1 << (next % 8)))) { @@ -373,7 +377,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx, " %u unmarked extension (len %u/%zu)", blkoff / sizeof(union afs_xdr_dir_block), offset, next, tmp, nlen); - return -EIO; + return afs_bad(dvnode, afs_file_error_dir_unmarked_ext); } _debug("ENT[%zu.%u]: ext %u/%zu", @@ -442,7 +446,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, */ page = req->pages[blkoff / PAGE_SIZE]; if (!page) { - ret = -EIO; + ret = afs_bad(dvnode, afs_file_error_dir_missing_page); break; } mark_page_accessed(page); @@ -455,7 +459,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, do { dblock = &dbuf->blocks[(blkoff % PAGE_SIZE) / sizeof(union afs_xdr_dir_block)]; - ret = afs_dir_iterate_block(ctx, dblock, blkoff); + ret = afs_dir_iterate_block(dvnode, ctx, dblock, blkoff); if (ret != 1) { kunmap(page); goto out; @@ -548,7 +552,7 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, } *fid = cookie.fid; - _leave(" = 0 { vn=%u u=%u }", fid->vnode, fid->unique); + _leave(" = 0 { vn=%llu u=%u }", fid->vnode, fid->unique); return 0; } @@ -826,7 +830,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, struct key *key; int ret; - _enter("{%x:%u},%p{%pd},", + _enter("{%llx:%llu},%p{%pd},", dvnode->fid.vid, dvnode->fid.vnode, dentry, dentry); ASSERTCMP(d_inode(dentry), ==, NULL); @@ -896,7 +900,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (d_really_is_positive(dentry)) { vnode = AFS_FS_I(d_inode(dentry)); - _enter("{v={%x:%u} n=%pd fl=%lx},", + _enter("{v={%llx:%llu} n=%pd fl=%lx},", vnode->fid.vid, vnode->fid.vnode, dentry, vnode->flags); } else { @@ -965,7 +969,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) /* if the vnode ID has changed, then the dirent points to a * different file */ if (fid.vnode != vnode->fid.vnode) { - _debug("%pd: dirent changed [%u != %u]", + _debug("%pd: dirent changed [%llu != %llu]", dentry, fid.vnode, vnode->fid.vnode); goto not_found; @@ -1085,6 +1089,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); + afs_vnode_commit_status(fc, vnode, 0); d_add(new_dentry, inode); } @@ -1104,7 +1109,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) mode |= S_IFDIR; - _enter("{%x:%u},{%pd},%ho", + _enter("{%llx:%llu},{%pd},%ho", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); key = afs_request_key(dvnode->volume->cell); @@ -1169,12 +1174,12 @@ static void afs_dir_remove_subdir(struct dentry *dentry) static int afs_rmdir(struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; - struct afs_vnode *dvnode = AFS_FS_I(dir); + struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; u64 data_version = dvnode->status.data_version; int ret; - _enter("{%x:%u},{%pd}", + _enter("{%llx:%llu},{%pd}", dvnode->fid.vid, dvnode->fid.vnode, dentry); key = afs_request_key(dvnode->volume->cell); @@ -1183,11 +1188,19 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) goto error; } + /* Try to make sure we have a callback promise on the victim. */ + if (d_really_is_positive(dentry)) { + vnode = AFS_FS_I(d_inode(dentry)); + ret = afs_validate(vnode, key); + if (ret < 0) + goto error_key; + } + ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_remove(&fc, dentry->d_name.name, true, + afs_fs_remove(&fc, vnode, dentry->d_name.name, true, data_version); } @@ -1201,6 +1214,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) } } +error_key: key_put(key); error: return ret; @@ -1231,7 +1245,9 @@ static int afs_dir_remove_link(struct dentry *dentry, struct key *key, if (d_really_is_positive(dentry)) { struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry)); - if (dir_valid) { + if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { + /* Already done */ + } else if (dir_valid) { drop_nlink(&vnode->vfs_inode); if (vnode->vfs_inode.i_nlink == 0) { set_bit(AFS_VNODE_DELETED, &vnode->flags); @@ -1260,13 +1276,13 @@ static int afs_dir_remove_link(struct dentry *dentry, struct key *key, static int afs_unlink(struct inode *dir, struct dentry *dentry) { struct afs_fs_cursor fc; - struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode; + struct afs_vnode *dvnode = AFS_FS_I(dir), *vnode = NULL; struct key *key; unsigned long d_version = (unsigned long)dentry->d_fsdata; u64 data_version = dvnode->status.data_version; int ret; - _enter("{%x:%u},{%pd}", + _enter("{%llx:%llu},{%pd}", dvnode->fid.vid, dvnode->fid.vnode, dentry); if (dentry->d_name.len >= AFSNAMEMAX) @@ -1290,7 +1306,18 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { fc.cb_break = afs_calc_vnode_cb_break(dvnode); - afs_fs_remove(&fc, dentry->d_name.name, false, + + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc.cbi->server->flags) && + !test_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags)) { + yfs_fs_remove_file2(&fc, vnode, dentry->d_name.name, + data_version); + if (fc.ac.error != -ECONNABORTED || + fc.ac.abort_code != RXGEN_OPCODE) + continue; + set_bit(AFS_SERVER_FL_NO_RM2, &fc.cbi->server->flags); + } + + afs_fs_remove(&fc, vnode, dentry->d_name.name, false, data_version); } @@ -1330,7 +1357,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, mode |= S_IFREG; - _enter("{%x:%u},{%pd},%ho,", + _enter("{%llx:%llu},{%pd},%ho,", dvnode->fid.vid, dvnode->fid.vnode, dentry, mode); ret = -ENAMETOOLONG; @@ -1393,7 +1420,7 @@ static int afs_link(struct dentry *from, struct inode *dir, dvnode = AFS_FS_I(dir); data_version = dvnode->status.data_version; - _enter("{%x:%u},{%x:%u},{%pd}", + _enter("{%llx:%llu},{%llx:%llu},{%pd}", vnode->fid.vid, vnode->fid.vnode, dvnode->fid.vid, dvnode->fid.vnode, dentry); @@ -1464,7 +1491,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, u64 data_version = dvnode->status.data_version; int ret; - _enter("{%x:%u},{%pd},%s", + _enter("{%llx:%llu},{%pd},%s", dvnode->fid.vid, dvnode->fid.vnode, dentry, content); @@ -1540,7 +1567,7 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, orig_data_version = orig_dvnode->status.data_version; new_data_version = new_dvnode->status.data_version; - _enter("{%x:%u},{%x:%u},{%x:%u},{%pd}", + _enter("{%llx:%llu},{%llx:%llu},{%llx:%llu},{%pd}", orig_dvnode->fid.vid, orig_dvnode->fid.vnode, vnode->fid.vid, vnode->fid.vnode, new_dvnode->fid.vid, new_dvnode->fid.vnode, @@ -1607,7 +1634,7 @@ static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags) { struct afs_vnode *dvnode = AFS_FS_I(page->mapping->host); - _enter("{{%x:%u}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index); + _enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index); set_page_private(page, 0); ClearPagePrivate(page); diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index f29c6dade7f625..a9ba81ddf15462 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -46,7 +46,7 @@ static int afs_probe_cell_name(struct dentry *dentry) return 0; } - ret = dns_query("afsdb", name, len, "", NULL, NULL); + ret = dns_query("afsdb", name, len, "srv=1", NULL, NULL); if (ret == -ENODATA) ret = -EDESTADDRREQ; return ret; @@ -62,7 +62,7 @@ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir) struct inode *inode; int ret = -ENOENT; - _enter("%p{%pd}, {%x:%u}", + _enter("%p{%pd}, {%llx:%llu}", dentry, dentry, vnode->fid.vid, vnode->fid.vnode); if (!test_bit(AFS_VNODE_AUTOCELL, &vnode->flags)) diff --git a/fs/afs/file.c b/fs/afs/file.c index 7d4f26198573d7..d6bc3f5d784b56 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -121,7 +121,7 @@ int afs_open(struct inode *inode, struct file *file) struct key *key; int ret; - _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode); key = afs_request_key(vnode->volume->cell); if (IS_ERR(key)) { @@ -170,7 +170,7 @@ int afs_release(struct inode *inode, struct file *file) struct afs_vnode *vnode = AFS_FS_I(inode); struct afs_file *af = file->private_data; - _enter("{%x:%u},", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu},", vnode->fid.vid, vnode->fid.vnode); if ((file->f_mode & FMODE_WRITE)) return vfs_fsync(file, 0); @@ -228,7 +228,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de struct afs_fs_cursor fc; int ret; - _enter("%s{%x:%u.%u},%x,,,", + _enter("%s{%llx:%llu.%u},%x,,,", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, @@ -634,7 +634,7 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags) struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); unsigned long priv; - _enter("{{%x:%u}[%lu],%lx},%x", + _enter("{{%llx:%llu}[%lu],%lx},%x", vnode->fid.vid, vnode->fid.vnode, page->index, page->flags, gfp_flags); diff --git a/fs/afs/flock.c b/fs/afs/flock.c index dc62d15a964b88..0568fd98682109 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -29,7 +29,7 @@ static const struct file_lock_operations afs_lock_ops = { */ void afs_lock_may_be_available(struct afs_vnode *vnode) { - _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); queue_delayed_work(afs_lock_manager, &vnode->lock_work, 0); } @@ -76,7 +76,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, struct afs_fs_cursor fc; int ret; - _enter("%s{%x:%u.%u},%x,%u", + _enter("%s{%llx:%llu.%u},%x,%u", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, @@ -107,7 +107,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) struct afs_fs_cursor fc; int ret; - _enter("%s{%x:%u.%u},%x", + _enter("%s{%llx:%llu.%u},%x", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, @@ -138,7 +138,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) struct afs_fs_cursor fc; int ret; - _enter("%s{%x:%u.%u},%x", + _enter("%s{%llx:%llu.%u},%x", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, @@ -175,7 +175,7 @@ void afs_lock_work(struct work_struct *work) struct key *key; int ret; - _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); spin_lock(&vnode->lock); @@ -192,7 +192,7 @@ again: ret = afs_release_lock(vnode, vnode->lock_key); if (ret < 0) printk(KERN_WARNING "AFS:" - " Failed to release lock on {%x:%x} error %d\n", + " Failed to release lock on {%llx:%llx} error %d\n", vnode->fid.vid, vnode->fid.vnode, ret); spin_lock(&vnode->lock); @@ -229,7 +229,7 @@ again: key_put(key); if (ret < 0) - pr_warning("AFS: Failed to extend lock on {%x:%x} error %d\n", + pr_warning("AFS: Failed to extend lock on {%llx:%llx} error %d\n", vnode->fid.vid, vnode->fid.vnode, ret); spin_lock(&vnode->lock); @@ -430,7 +430,7 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl) struct key *key = afs_file_key(file); int ret; - _enter("{%x:%u},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); + _enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); /* only whole-file locks are supported */ if (fl->fl_start != 0 || fl->fl_end != OFFSET_MAX) @@ -582,7 +582,7 @@ static int afs_do_unlk(struct file *file, struct file_lock *fl) struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); int ret; - _enter("{%x:%u},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); + _enter("{%llx:%llu},%u", vnode->fid.vid, vnode->fid.vnode, fl->fl_type); /* Flush all pending writes before doing anything with locks. */ vfs_fsync(file, 0); @@ -639,7 +639,7 @@ int afs_lock(struct file *file, int cmd, struct file_lock *fl) { struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); - _enter("{%x:%u},%d,{t=%x,fl=%x,r=%Ld:%Ld}", + _enter("{%llx:%llu},%d,{t=%x,fl=%x,r=%Ld:%Ld}", vnode->fid.vid, vnode->fid.vnode, cmd, fl->fl_type, fl->fl_flags, (long long) fl->fl_start, (long long) fl->fl_end); @@ -662,7 +662,7 @@ int afs_flock(struct file *file, int cmd, struct file_lock *fl) { struct afs_vnode *vnode = AFS_FS_I(locks_inode(file)); - _enter("{%x:%u},%d,{t=%x,fl=%x}", + _enter("{%llx:%llu},%d,{t=%x,fl=%x}", vnode->fid.vid, vnode->fid.vnode, cmd, fl->fl_type, fl->fl_flags); diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c new file mode 100644 index 00000000000000..d049cb45974254 --- /dev/null +++ b/fs/afs/fs_probe.c @@ -0,0 +1,270 @@ +/* AFS fileserver probing + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/sched.h> +#include <linux/slab.h> +#include "afs_fs.h" +#include "internal.h" +#include "protocol_yfs.h" + +static bool afs_fs_probe_done(struct afs_server *server) +{ + if (!atomic_dec_and_test(&server->probe_outstanding)) + return false; + + wake_up_var(&server->probe_outstanding); + clear_bit_unlock(AFS_SERVER_FL_PROBING, &server->flags); + wake_up_bit(&server->flags, AFS_SERVER_FL_PROBING); + return true; +} + +/* + * Process the result of probing a fileserver. This is called after successful + * or failed delivery of an FS.GetCapabilities operation. + */ +void afs_fileserver_probe_result(struct afs_call *call) +{ + struct afs_addr_list *alist = call->alist; + struct afs_server *server = call->reply[0]; + unsigned int server_index = (long)call->reply[1]; + unsigned int index = call->addr_ix; + unsigned int rtt = UINT_MAX; + bool have_result = false; + u64 _rtt; + int ret = call->error; + + _enter("%pU,%u", &server->uuid, index); + + spin_lock(&server->probe_lock); + + switch (ret) { + case 0: + server->probe.error = 0; + goto responded; + case -ECONNABORTED: + if (!server->probe.responded) { + server->probe.abort_code = call->abort_code; + server->probe.error = ret; + } + goto responded; + case -ENOMEM: + case -ENONET: + server->probe.local_failure = true; + afs_io_error(call, afs_io_error_fs_probe_fail); + goto out; + case -ECONNRESET: /* Responded, but call expired. */ + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + case -ETIMEDOUT: + case -ETIME: + default: + clear_bit(index, &alist->responded); + set_bit(index, &alist->failed); + if (!server->probe.responded && + (server->probe.error == 0 || + server->probe.error == -ETIMEDOUT || + server->probe.error == -ETIME)) + server->probe.error = ret; + afs_io_error(call, afs_io_error_fs_probe_fail); + goto out; + } + +responded: + set_bit(index, &alist->responded); + clear_bit(index, &alist->failed); + + if (call->service_id == YFS_FS_SERVICE) { + server->probe.is_yfs = true; + set_bit(AFS_SERVER_FL_IS_YFS, &server->flags); + alist->addrs[index].srx_service = call->service_id; + } else { + server->probe.not_yfs = true; + if (!server->probe.is_yfs) { + clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags); + alist->addrs[index].srx_service = call->service_id; + } + } + + /* Get the RTT and scale it to fit into a 32-bit value that represents + * over a minute of time so that we can access it with one instruction + * on a 32-bit system. + */ + _rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall); + _rtt /= 64; + rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt; + if (rtt < server->probe.rtt) { + server->probe.rtt = rtt; + alist->preferred = index; + have_result = true; + } + + smp_wmb(); /* Set rtt before responded. */ + server->probe.responded = true; + set_bit(AFS_SERVER_FL_PROBED, &server->flags); +out: + spin_unlock(&server->probe_lock); + + _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", + server_index, index, &alist->addrs[index].transport, + (unsigned int)rtt, ret); + + have_result |= afs_fs_probe_done(server); + if (have_result) { + server->probe.have_result = true; + wake_up_var(&server->probe.have_result); + wake_up_all(&server->probe_wq); + } +} + +/* + * Probe all of a fileserver's addresses to find out the best route and to + * query its capabilities. + */ +static int afs_do_probe_fileserver(struct afs_net *net, + struct afs_server *server, + struct key *key, + unsigned int server_index) +{ + struct afs_addr_cursor ac = { + .index = 0, + }; + int ret; + + _enter("%pU", &server->uuid); + + read_lock(&server->fs_lock); + ac.alist = rcu_dereference_protected(server->addresses, + lockdep_is_held(&server->fs_lock)); + read_unlock(&server->fs_lock); + + atomic_set(&server->probe_outstanding, ac.alist->nr_addrs); + memset(&server->probe, 0, sizeof(server->probe)); + server->probe.rtt = UINT_MAX; + + for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { + ret = afs_fs_get_capabilities(net, server, &ac, key, server_index, + true); + if (ret != -EINPROGRESS) { + afs_fs_probe_done(server); + return ret; + } + } + + return 0; +} + +/* + * Send off probes to all unprobed servers. + */ +int afs_probe_fileservers(struct afs_net *net, struct key *key, + struct afs_server_list *list) +{ + struct afs_server *server; + int i, ret; + + for (i = 0; i < list->nr_servers; i++) { + server = list->servers[i].server; + if (test_bit(AFS_SERVER_FL_PROBED, &server->flags)) + continue; + + if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags)) { + ret = afs_do_probe_fileserver(net, server, key, i); + if (ret) + return ret; + } + } + + return 0; +} + +/* + * Wait for the first as-yet untried fileserver to respond. + */ +int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried) +{ + struct wait_queue_entry *waits; + struct afs_server *server; + unsigned int rtt = UINT_MAX; + bool have_responders = false; + int pref = -1, i; + + _enter("%u,%lx", slist->nr_servers, untried); + + /* Only wait for servers that have a probe outstanding. */ + for (i = 0; i < slist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = slist->servers[i].server; + if (!test_bit(AFS_SERVER_FL_PROBING, &server->flags)) + __clear_bit(i, &untried); + if (server->probe.responded) + have_responders = true; + } + } + if (have_responders || !untried) + return 0; + + waits = kmalloc(array_size(slist->nr_servers, sizeof(*waits)), GFP_KERNEL); + if (!waits) + return -ENOMEM; + + for (i = 0; i < slist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = slist->servers[i].server; + init_waitqueue_entry(&waits[i], current); + add_wait_queue(&server->probe_wq, &waits[i]); + } + } + + for (;;) { + bool still_probing = false; + + set_current_state(TASK_INTERRUPTIBLE); + for (i = 0; i < slist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = slist->servers[i].server; + if (server->probe.responded) + goto stop; + if (test_bit(AFS_SERVER_FL_PROBING, &server->flags)) + still_probing = true; + } + } + + if (!still_probing || unlikely(signal_pending(current))) + goto stop; + schedule(); + } + +stop: + set_current_state(TASK_RUNNING); + + for (i = 0; i < slist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = slist->servers[i].server; + if (server->probe.responded && + server->probe.rtt < rtt) { + pref = i; + rtt = server->probe.rtt; + } + + remove_wait_queue(&server->probe_wq, &waits[i]); + } + } + + kfree(waits); + + if (pref == -1 && signal_pending(current)) + return -ERESTARTSYS; + + if (pref >= 0) + slist->preferred = pref; + return 0; +} diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 50929cb91732f5..ca08c83168f5fb 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -17,15 +17,10 @@ #include "internal.h" #include "afs_fs.h" #include "xdr_fs.h" +#include "protocol_yfs.h" static const struct afs_fid afs_zero_fid; -/* - * We need somewhere to discard into in case the server helpfully returns more - * than we asked for in FS.FetchData{,64}. - */ -static u8 afs_discard_buffer[64]; - static inline void afs_use_fs_server(struct afs_call *call, struct afs_cb_interest *cbi) { call->cbi = afs_get_cb_interest(cbi); @@ -75,8 +70,7 @@ void afs_update_inode_from_status(struct afs_vnode *vnode, struct timespec64 t; umode_t mode; - t.tv_sec = status->mtime_client; - t.tv_nsec = 0; + t = status->mtime_client; vnode->vfs_inode.i_ctime = t; vnode->vfs_inode.i_mtime = t; vnode->vfs_inode.i_atime = t; @@ -96,7 +90,7 @@ void afs_update_inode_from_status(struct afs_vnode *vnode, if (!(flags & AFS_VNODE_NOT_YET_SET)) { if (expected_version && *expected_version != status->data_version) { - _debug("vnode modified %llx on {%x:%u} [exp %llx]", + _debug("vnode modified %llx on {%llx:%llu} [exp %llx]", (unsigned long long) status->data_version, vnode->fid.vid, vnode->fid.vnode, (unsigned long long) *expected_version); @@ -170,7 +164,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, if (type != status->type && vnode && !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { - pr_warning("Vnode %x:%x:%x changed type %u to %u\n", + pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, @@ -200,8 +194,10 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, EXTRACT_M(mode); EXTRACT_M(group); - status->mtime_client = ntohl(xdr->mtime_client); - status->mtime_server = ntohl(xdr->mtime_server); + status->mtime_client.tv_sec = ntohl(xdr->mtime_client); + status->mtime_client.tv_nsec = 0; + status->mtime_server.tv_sec = ntohl(xdr->mtime_server); + status->mtime_server.tv_nsec = 0; status->lock_count = ntohl(xdr->lock_count); size = (u64)ntohl(xdr->size_lo); @@ -233,7 +229,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, bad: xdr_dump_bad(*_bp); - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); } /* @@ -273,7 +269,7 @@ static void xdr_decode_AFSCallBack(struct afs_call *call, write_seqlock(&vnode->cb_lock); - if (call->cb_break == afs_cb_break_sum(vnode, cbi)) { + if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { vnode->cb_version = ntohl(*bp++); cb_expiry = ntohl(*bp++); vnode->cb_type = ntohl(*bp++); @@ -293,13 +289,19 @@ static void xdr_decode_AFSCallBack(struct afs_call *call, *_bp = bp; } -static void xdr_decode_AFSCallBack_raw(const __be32 **_bp, +static ktime_t xdr_decode_expiry(struct afs_call *call, u32 expiry) +{ + return ktime_add_ns(call->reply_time, expiry * NSEC_PER_SEC); +} + +static void xdr_decode_AFSCallBack_raw(struct afs_call *call, + const __be32 **_bp, struct afs_callback *cb) { const __be32 *bp = *_bp; cb->version = ntohl(*bp++); - cb->expiry = ntohl(*bp++); + cb->expires_at = xdr_decode_expiry(call, ntohl(*bp++)); cb->type = ntohl(*bp++); *_bp = bp; } @@ -311,14 +313,18 @@ static void xdr_decode_AFSVolSync(const __be32 **_bp, struct afs_volsync *volsync) { const __be32 *bp = *_bp; + u32 creation; - volsync->creation = ntohl(*bp++); + creation = ntohl(*bp++); bp++; /* spare2 */ bp++; /* spare3 */ bp++; /* spare4 */ bp++; /* spare5 */ bp++; /* spare6 */ *_bp = bp; + + if (volsync) + volsync->creation = creation; } /* @@ -379,6 +385,8 @@ static void xdr_decode_AFSFetchVolumeStatus(const __be32 **_bp, vs->blocks_in_use = ntohl(*bp++); vs->part_blocks_avail = ntohl(*bp++); vs->part_max_blocks = ntohl(*bp++); + vs->vol_copy_date = 0; + vs->vol_backup_date = 0; *_bp = bp; } @@ -395,16 +403,16 @@ static int afs_deliver_fs_fetch_status_vnode(struct afs_call *call) if (ret < 0) return ret; - _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; xdr_decode_AFSCallBack(call, vnode, &bp); - if (call->reply[1]) - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSVolSync(&bp, call->reply[1]); _leave(" = 0 [done]"); return 0; @@ -431,7 +439,10 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy struct afs_net *net = afs_v2net(vnode); __be32 *bp; - _enter(",%x,{%x:%u},,", + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_fetch_file_status(fc, volsync, new_inode); + + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); call = afs_alloc_flat_call(net, &afs_RXFSFetchStatus_vnode, @@ -445,6 +456,7 @@ int afs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsy call->reply[0] = vnode; call->reply[1] = volsync; call->expected_version = new_inode ? 1 : vnode->status.data_version; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -468,139 +480,117 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) struct afs_read *req = call->reply[2]; const __be32 *bp; unsigned int size; - void *buffer; int ret; - _enter("{%u,%zu/%u;%llu/%llu}", - call->unmarshall, call->offset, call->count, - req->remain, req->actual_len); + _enter("{%u,%zu/%llu}", + call->unmarshall, iov_iter_count(&call->iter), req->actual_len); switch (call->unmarshall) { case 0: req->actual_len = 0; - call->offset = 0; + req->index = 0; + req->offset = req->pos & (PAGE_SIZE - 1); call->unmarshall++; - if (call->operation_ID != FSFETCHDATA64) { - call->unmarshall++; - goto no_msw; + if (call->operation_ID == FSFETCHDATA64) { + afs_extract_to_tmp64(call); + } else { + call->tmp_u = htonl(0); + afs_extract_to_tmp(call); } - /* extract the upper part of the returned data length of an - * FSFETCHDATA64 op (which should always be 0 using this - * client) */ - case 1: - _debug("extract data length (MSW)"); - ret = afs_extract_data(call, &call->tmp, 4, true); - if (ret < 0) - return ret; - - req->actual_len = ntohl(call->tmp); - req->actual_len <<= 32; - call->offset = 0; - call->unmarshall++; - - no_msw: /* extract the returned data length */ - case 2: + case 1: _debug("extract data length"); - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; - req->actual_len |= ntohl(call->tmp); + req->actual_len = be64_to_cpu(call->tmp64); _debug("DATA length: %llu", req->actual_len); - - req->remain = req->actual_len; - call->offset = req->pos & (PAGE_SIZE - 1); - req->index = 0; - if (req->actual_len == 0) + req->remain = min(req->len, req->actual_len); + if (req->remain == 0) goto no_more_data; + call->unmarshall++; begin_page: ASSERTCMP(req->index, <, req->nr_pages); - if (req->remain > PAGE_SIZE - call->offset) - size = PAGE_SIZE - call->offset; + if (req->remain > PAGE_SIZE - req->offset) + size = PAGE_SIZE - req->offset; else size = req->remain; - call->count = call->offset + size; - ASSERTCMP(call->count, <=, PAGE_SIZE); - req->remain -= size; + call->bvec[0].bv_len = size; + call->bvec[0].bv_offset = req->offset; + call->bvec[0].bv_page = req->pages[req->index]; + iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); + ASSERTCMP(size, <=, PAGE_SIZE); /* extract the returned data */ - case 3: - _debug("extract data %llu/%llu %zu/%u", - req->remain, req->actual_len, call->offset, call->count); + case 2: + _debug("extract data %zu/%llu", + iov_iter_count(&call->iter), req->remain); - buffer = kmap(req->pages[req->index]); - ret = afs_extract_data(call, buffer, call->count, true); - kunmap(req->pages[req->index]); + ret = afs_extract_data(call, true); if (ret < 0) return ret; - if (call->offset == PAGE_SIZE) { + req->remain -= call->bvec[0].bv_len; + req->offset += call->bvec[0].bv_len; + ASSERTCMP(req->offset, <=, PAGE_SIZE); + if (req->offset == PAGE_SIZE) { + req->offset = 0; if (req->page_done) req->page_done(call, req); req->index++; - if (req->remain > 0) { - call->offset = 0; - if (req->index >= req->nr_pages) { - call->unmarshall = 4; - goto begin_discard; - } + if (req->remain > 0) goto begin_page; - } } - goto no_more_data; + + ASSERTCMP(req->remain, ==, 0); + if (req->actual_len <= req->len) + goto no_more_data; /* Discard any excess data the server gave us */ - begin_discard: - case 4: - size = min_t(loff_t, sizeof(afs_discard_buffer), req->remain); - call->count = size; - _debug("extract discard %llu/%llu %zu/%u", - req->remain, req->actual_len, call->offset, call->count); - - call->offset = 0; - ret = afs_extract_data(call, afs_discard_buffer, call->count, true); - req->remain -= call->offset; + iov_iter_discard(&call->iter, READ, req->actual_len - req->len); + call->unmarshall = 3; + case 3: + _debug("extract discard %zu/%llu", + iov_iter_count(&call->iter), req->actual_len - req->len); + + ret = afs_extract_data(call, true); if (ret < 0) return ret; - if (req->remain > 0) - goto begin_discard; no_more_data: - call->offset = 0; - call->unmarshall = 5; + call->unmarshall = 4; + afs_extract_to_buf(call, (21 + 3 + 6) * 4); /* extract the metadata */ - case 5: - ret = afs_extract_data(call, call->buffer, - (21 + 3 + 6) * 4, false); + case 4: + ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, - &vnode->status.data_version, req) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &vnode->status.data_version, req); + if (ret < 0) + return ret; xdr_decode_AFSCallBack(call, vnode, &bp); - if (call->reply[1]) - xdr_decode_AFSVolSync(&bp, call->reply[1]); + xdr_decode_AFSVolSync(&bp, call->reply[1]); - call->offset = 0; call->unmarshall++; - case 6: + case 5: break; } for (; req->index < req->nr_pages; req->index++) { - if (call->count < PAGE_SIZE) + if (req->offset < PAGE_SIZE) zero_user_segment(req->pages[req->index], - call->count, PAGE_SIZE); + req->offset, PAGE_SIZE); if (req->page_done) req->page_done(call, req); - call->count = 0; + req->offset = 0; } _leave(" = 0 [done]"); @@ -653,6 +643,7 @@ static int afs_fs_fetch_data64(struct afs_fs_cursor *fc, struct afs_read *req) call->reply[1] = NULL; /* volsync */ call->reply[2] = req; call->expected_version = vnode->status.data_version; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -682,6 +673,9 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) struct afs_net *net = afs_v2net(vnode); __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_fetch_data(fc, req); + if (upper_32_bits(req->pos) || upper_32_bits(req->len) || upper_32_bits(req->pos + req->len)) @@ -698,6 +692,7 @@ int afs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) call->reply[1] = NULL; /* volsync */ call->reply[2] = req; call->expected_version = vnode->status.data_version; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -733,11 +728,14 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_AFSFid(&bp, call->reply[1]); - if (afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL) < 0 || - afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); - xdr_decode_AFSCallBack_raw(&bp, call->reply[3]); + ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + if (ret < 0) + return ret; + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_AFSCallBack_raw(call, &bp, call->reply[3]); /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -778,6 +776,15 @@ int afs_fs_create(struct afs_fs_cursor *fc, size_t namesz, reqsz, padsz; __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)){ + if (S_ISDIR(mode)) + return yfs_fs_make_dir(fc, name, mode, current_data_version, + newfid, newstatus, newcb); + else + return yfs_fs_create_file(fc, name, mode, current_data_version, + newfid, newstatus, newcb); + } + _enter(""); namesz = strlen(name); @@ -796,6 +803,7 @@ int afs_fs_create(struct afs_fs_cursor *fc, call->reply[2] = newstatus; call->reply[3] = newcb; call->expected_version = current_data_version + 1; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -839,9 +847,10 @@ static int afs_deliver_fs_remove(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -868,15 +877,18 @@ static const struct afs_call_type afs_RXFSRemoveDir = { /* * remove a file or directory */ -int afs_fs_remove(struct afs_fs_cursor *fc, const char *name, bool isdir, - u64 current_data_version) +int afs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, + const char *name, bool isdir, u64 current_data_version) { - struct afs_vnode *vnode = fc->vnode; + struct afs_vnode *dvnode = fc->vnode; struct afs_call *call; - struct afs_net *net = afs_v2net(vnode); + struct afs_net *net = afs_v2net(dvnode); size_t namesz, reqsz, padsz; __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_remove(fc, vnode, name, isdir, current_data_version); + _enter(""); namesz = strlen(name); @@ -890,15 +902,16 @@ int afs_fs_remove(struct afs_fs_cursor *fc, const char *name, bool isdir, return -ENOMEM; call->key = fc->key; - call->reply[0] = vnode; + call->reply[0] = dvnode; + call->reply[1] = vnode; call->expected_version = current_data_version + 1; /* marshall the parameters */ bp = call->request; *bp++ = htonl(isdir ? FSREMOVEDIR : FSREMOVEFILE); - *bp++ = htonl(vnode->fid.vid); - *bp++ = htonl(vnode->fid.vnode); - *bp++ = htonl(vnode->fid.unique); + *bp++ = htonl(dvnode->fid.vid); + *bp++ = htonl(dvnode->fid.vnode); + *bp++ = htonl(dvnode->fid.unique); *bp++ = htonl(namesz); memcpy(bp, name, namesz); bp = (void *) bp + namesz; @@ -908,7 +921,7 @@ int afs_fs_remove(struct afs_fs_cursor *fc, const char *name, bool isdir, } afs_use_fs_server(call, fc->cbi); - trace_afs_make_fs_call(call, &vnode->fid); + trace_afs_make_fs_call(call, &dvnode->fid); return afs_make_call(&fc->ac, call, GFP_NOFS, false); } @@ -929,10 +942,13 @@ static int afs_deliver_fs_link(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL) < 0 || - afs_decode_status(call, &bp, &dvnode->status, dvnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + if (ret < 0) + return ret; + ret = afs_decode_status(call, &bp, &dvnode->status, dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -961,6 +977,9 @@ int afs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, size_t namesz, reqsz, padsz; __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_link(fc, vnode, name, current_data_version); + _enter(""); namesz = strlen(name); @@ -1016,10 +1035,13 @@ static int afs_deliver_fs_symlink(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; xdr_decode_AFSFid(&bp, call->reply[1]); - if (afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL) || - afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + if (ret < 0) + return ret; + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -1052,6 +1074,10 @@ int afs_fs_symlink(struct afs_fs_cursor *fc, size_t namesz, reqsz, padsz, c_namesz, c_padsz; __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_symlink(fc, name, contents, current_data_version, + newfid, newstatus); + _enter(""); namesz = strlen(name); @@ -1122,13 +1148,16 @@ static int afs_deliver_fs_rename(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); - if (new_dvnode != orig_dvnode && - afs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, - &call->expected_version_2, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + if (new_dvnode != orig_dvnode) { + ret = afs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, + &call->expected_version_2, NULL); + if (ret < 0) + return ret; + } /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -1161,6 +1190,12 @@ int afs_fs_rename(struct afs_fs_cursor *fc, size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz; __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_rename(fc, orig_name, + new_dvnode, new_name, + current_orig_data_version, + current_new_data_version); + _enter(""); o_namesz = strlen(orig_name); @@ -1231,9 +1266,10 @@ static int afs_deliver_fs_store_data(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ afs_pages_written_back(vnode, call); @@ -1273,7 +1309,7 @@ static int afs_fs_store_data64(struct afs_fs_cursor *fc, struct afs_net *net = afs_v2net(vnode); __be32 *bp; - _enter(",%x,{%x:%u},,", + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); call = afs_alloc_flat_call(net, &afs_RXFSStoreData64, @@ -1330,7 +1366,10 @@ int afs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, loff_t size, pos, i_size; __be32 *bp; - _enter(",%x,{%x:%u},,", + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_store_data(fc, mapping, first, last, offset, to); + + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); size = (loff_t)to - (loff_t)offset; @@ -1407,9 +1446,10 @@ static int afs_deliver_fs_store_status(struct afs_call *call) /* unmarshall the reply once we've received all of it */ bp = call->buffer; - if (afs_decode_status(call, &bp, &vnode->status, vnode, - &call->expected_version, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; /* xdr_decode_AFSVolSync(&bp, call->reply[X]); */ _leave(" = 0 [done]"); @@ -1451,7 +1491,7 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr) struct afs_net *net = afs_v2net(vnode); __be32 *bp; - _enter(",%x,{%x:%u},,", + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); ASSERT(attr->ia_valid & ATTR_SIZE); @@ -1498,7 +1538,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) struct afs_net *net = afs_v2net(vnode); __be32 *bp; - _enter(",%x,{%x:%u},,", + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); ASSERT(attr->ia_valid & ATTR_SIZE); @@ -1544,10 +1584,13 @@ int afs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) struct afs_net *net = afs_v2net(vnode); __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_setattr(fc, attr); + if (attr->ia_valid & ATTR_SIZE) return afs_fs_setattr_size(fc, attr); - _enter(",%x,{%x:%u},,", + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); call = afs_alloc_flat_call(net, &afs_RXFSStoreStatus, @@ -1581,164 +1624,114 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call) { const __be32 *bp; char *p; + u32 size; int ret; _enter("{%u}", call->unmarshall); switch (call->unmarshall) { case 0: - call->offset = 0; call->unmarshall++; + afs_extract_to_buf(call, 12 * 4); /* extract the returned status record */ case 1: _debug("extract status"); - ret = afs_extract_data(call, call->buffer, - 12 * 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; bp = call->buffer; xdr_decode_AFSFetchVolumeStatus(&bp, call->reply[1]); - call->offset = 0; call->unmarshall++; + afs_extract_to_tmp(call); /* extract the volume name length */ case 2: - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->count = ntohl(call->tmp); _debug("volname length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG); - call->offset = 0; + return afs_protocol_error(call, -EBADMSG, + afs_eproto_volname_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); call->unmarshall++; /* extract the volume name */ case 3: _debug("extract volname"); - if (call->count > 0) { - ret = afs_extract_data(call, call->reply[2], - call->count, true); - if (ret < 0) - return ret; - } + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; p = call->reply[2]; p[call->count] = 0; _debug("volname '%s'", p); - - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; - /* extract the volume name padding */ - if ((call->count & 3) == 0) { - call->unmarshall++; - goto no_volname_padding; - } - call->count = 4 - (call->count & 3); - - case 4: - ret = afs_extract_data(call, call->buffer, - call->count, true); - if (ret < 0) - return ret; - - call->offset = 0; - call->unmarshall++; - no_volname_padding: - /* extract the offline message length */ - case 5: - ret = afs_extract_data(call, &call->tmp, 4, true); + case 4: + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->count = ntohl(call->tmp); _debug("offline msg length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG); - call->offset = 0; + return afs_protocol_error(call, -EBADMSG, + afs_eproto_offline_msg_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); call->unmarshall++; /* extract the offline message */ - case 6: + case 5: _debug("extract offline"); - if (call->count > 0) { - ret = afs_extract_data(call, call->reply[2], - call->count, true); - if (ret < 0) - return ret; - } + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; p = call->reply[2]; p[call->count] = 0; _debug("offline '%s'", p); - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; - /* extract the offline message padding */ - if ((call->count & 3) == 0) { - call->unmarshall++; - goto no_offline_padding; - } - call->count = 4 - (call->count & 3); - - case 7: - ret = afs_extract_data(call, call->buffer, - call->count, true); - if (ret < 0) - return ret; - - call->offset = 0; - call->unmarshall++; - no_offline_padding: - /* extract the message of the day length */ - case 8: - ret = afs_extract_data(call, &call->tmp, 4, true); + case 6: + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->count = ntohl(call->tmp); _debug("motd length: %u", call->count); if (call->count >= AFSNAMEMAX) - return afs_protocol_error(call, -EBADMSG); - call->offset = 0; + return afs_protocol_error(call, -EBADMSG, + afs_eproto_motd_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); call->unmarshall++; /* extract the message of the day */ - case 9: + case 7: _debug("extract motd"); - if (call->count > 0) { - ret = afs_extract_data(call, call->reply[2], - call->count, true); - if (ret < 0) - return ret; - } + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; p = call->reply[2]; p[call->count] = 0; _debug("motd '%s'", p); - call->offset = 0; call->unmarshall++; - /* extract the message of the day padding */ - call->count = (4 - (call->count & 3)) & 3; - - case 10: - ret = afs_extract_data(call, call->buffer, - call->count, false); - if (ret < 0) - return ret; - - call->offset = 0; - call->unmarshall++; - case 11: + case 8: break; } @@ -1778,6 +1771,9 @@ int afs_fs_get_volume_status(struct afs_fs_cursor *fc, __be32 *bp; void *tmpbuf; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_get_volume_status(fc, vs); + _enter(""); tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); @@ -1867,6 +1863,9 @@ int afs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) struct afs_net *net = afs_v2net(vnode); __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_set_lock(fc, type); + _enter(""); call = afs_alloc_flat_call(net, &afs_RXFSSetLock, 5 * 4, 6 * 4); @@ -1899,6 +1898,9 @@ int afs_fs_extend_lock(struct afs_fs_cursor *fc) struct afs_net *net = afs_v2net(vnode); __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_extend_lock(fc); + _enter(""); call = afs_alloc_flat_call(net, &afs_RXFSExtendLock, 4 * 4, 6 * 4); @@ -1930,6 +1932,9 @@ int afs_fs_release_lock(struct afs_fs_cursor *fc) struct afs_net *net = afs_v2net(vnode); __be32 *bp; + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_release_lock(fc); + _enter(""); call = afs_alloc_flat_call(net, &afs_RXFSReleaseLock, 4 * 4, 6 * 4); @@ -2004,19 +2009,16 @@ static int afs_deliver_fs_get_capabilities(struct afs_call *call) u32 count; int ret; - _enter("{%u,%zu/%u}", call->unmarshall, call->offset, call->count); + _enter("{%u,%zu}", call->unmarshall, iov_iter_count(&call->iter)); -again: switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; /* Extract the capabilities word count */ case 1: - ret = afs_extract_data(call, &call->tmp, - 1 * sizeof(__be32), - true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -2024,24 +2026,17 @@ again: call->count = count; call->count2 = count; - call->offset = 0; + iov_iter_discard(&call->iter, READ, count * sizeof(__be32)); call->unmarshall++; /* Extract capabilities words */ case 2: - count = min(call->count, 16U); - ret = afs_extract_data(call, call->buffer, - count * sizeof(__be32), - call->count > 16); + ret = afs_extract_data(call, false); if (ret < 0) return ret; /* TODO: Examine capabilities */ - call->count -= count; - if (call->count > 0) - goto again; - call->offset = 0; call->unmarshall++; break; } @@ -2050,6 +2045,14 @@ again: return 0; } +static void afs_destroy_fs_get_capabilities(struct afs_call *call) +{ + struct afs_server *server = call->reply[0]; + + afs_put_server(call->net, server); + afs_flat_call_destructor(call); +} + /* * FS.GetCapabilities operation type */ @@ -2057,7 +2060,8 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { .name = "FS.GetCapabilities", .op = afs_FS_GetCapabilities, .deliver = afs_deliver_fs_get_capabilities, - .destructor = afs_flat_call_destructor, + .done = afs_fileserver_probe_result, + .destructor = afs_destroy_fs_get_capabilities, }; /* @@ -2067,7 +2071,9 @@ static const struct afs_call_type afs_RXFSGetCapabilities = { int afs_fs_get_capabilities(struct afs_net *net, struct afs_server *server, struct afs_addr_cursor *ac, - struct key *key) + struct key *key, + unsigned int server_index, + bool async) { struct afs_call *call; __be32 *bp; @@ -2079,6 +2085,10 @@ int afs_fs_get_capabilities(struct afs_net *net, return -ENOMEM; call->key = key; + call->reply[0] = afs_get_server(server); + call->reply[1] = (void *)(long)server_index; + call->upgrade = true; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -2086,7 +2096,7 @@ int afs_fs_get_capabilities(struct afs_net *net, /* Can't take a ref on server */ trace_afs_make_fs_call(call, NULL); - return afs_make_call(ac, call, GFP_NOFS, false); + return afs_make_call(ac, call, GFP_NOFS, async); } /* @@ -2097,7 +2107,7 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call) struct afs_file_status *status = call->reply[1]; struct afs_callback *callback = call->reply[2]; struct afs_volsync *volsync = call->reply[3]; - struct afs_vnode *vnode = call->reply[0]; + struct afs_fid *fid = call->reply[0]; const __be32 *bp; int ret; @@ -2105,21 +2115,16 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call) if (ret < 0) return ret; - _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu}", fid->vid, fid->vnode); /* unmarshall the reply once we've received all of it */ bp = call->buffer; - afs_decode_status(call, &bp, status, vnode, - &call->expected_version, NULL); - callback[call->count].version = ntohl(bp[0]); - callback[call->count].expiry = ntohl(bp[1]); - callback[call->count].type = ntohl(bp[2]); - if (vnode) - xdr_decode_AFSCallBack(call, vnode, &bp); - else - bp += 3; - if (volsync) - xdr_decode_AFSVolSync(&bp, volsync); + ret = afs_decode_status(call, &bp, status, NULL, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_AFSCallBack_raw(call, &bp, callback); + xdr_decode_AFSVolSync(&bp, volsync); _leave(" = 0 [done]"); return 0; @@ -2148,7 +2153,10 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, struct afs_call *call; __be32 *bp; - _enter(",%x,{%x:%u},,", + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_fetch_status(fc, net, fid, status, callback, volsync); + + _enter(",%x,{%llx:%llu},,", key_serial(fc->key), fid->vid, fid->vnode); call = afs_alloc_flat_call(net, &afs_RXFSFetchStatus, 16, (21 + 3 + 6) * 4); @@ -2158,11 +2166,12 @@ int afs_fs_fetch_status(struct afs_fs_cursor *fc, } call->key = fc->key; - call->reply[0] = NULL; /* vnode for fid[0] */ + call->reply[0] = fid; call->reply[1] = status; call->reply[2] = callback; call->reply[3] = volsync; call->expected_version = 1; /* vnode->status.data_version */ + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -2193,38 +2202,40 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; /* Extract the file status count and array in two steps */ case 1: _debug("extract status count"); - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; tmp = ntohl(call->tmp); _debug("status count: %u/%u", tmp, call->count2); if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_ibulkst_count); call->count = 0; call->unmarshall++; more_counts: - call->offset = 0; + afs_extract_to_buf(call, 21 * sizeof(__be32)); case 2: _debug("extract status array %u", call->count); - ret = afs_extract_data(call, call->buffer, 21 * 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; bp = call->buffer; statuses = call->reply[1]; - if (afs_decode_status(call, &bp, &statuses[call->count], - call->count == 0 ? vnode : NULL, - NULL, NULL) < 0) - return afs_protocol_error(call, -EBADMSG); + ret = afs_decode_status(call, &bp, &statuses[call->count], + call->count == 0 ? vnode : NULL, + NULL, NULL); + if (ret < 0) + return ret; call->count++; if (call->count < call->count2) @@ -2232,27 +2243,28 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) call->count = 0; call->unmarshall++; - call->offset = 0; + afs_extract_to_tmp(call); /* Extract the callback count and array in two steps */ case 3: _debug("extract CB count"); - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; tmp = ntohl(call->tmp); _debug("CB count: %u", tmp); if (tmp != call->count2) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_ibulkst_cb_count); call->count = 0; call->unmarshall++; more_cbs: - call->offset = 0; + afs_extract_to_buf(call, 3 * sizeof(__be32)); case 4: _debug("extract CB array"); - ret = afs_extract_data(call, call->buffer, 3 * 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -2260,7 +2272,7 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) bp = call->buffer; callbacks = call->reply[2]; callbacks[call->count].version = ntohl(bp[0]); - callbacks[call->count].expiry = ntohl(bp[1]); + callbacks[call->count].expires_at = xdr_decode_expiry(call, ntohl(bp[1])); callbacks[call->count].type = ntohl(bp[2]); statuses = call->reply[1]; if (call->count == 0 && vnode && statuses[0].abort_code == 0) @@ -2269,19 +2281,17 @@ static int afs_deliver_fs_inline_bulk_status(struct afs_call *call) if (call->count < call->count2) goto more_cbs; - call->offset = 0; + afs_extract_to_buf(call, 6 * sizeof(__be32)); call->unmarshall++; case 5: - ret = afs_extract_data(call, call->buffer, 6 * 4, false); + ret = afs_extract_data(call, false); if (ret < 0) return ret; bp = call->buffer; - if (call->reply[3]) - xdr_decode_AFSVolSync(&bp, call->reply[3]); + xdr_decode_AFSVolSync(&bp, call->reply[3]); - call->offset = 0; call->unmarshall++; case 6: @@ -2317,7 +2327,11 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, __be32 *bp; int i; - _enter(",%x,{%x:%u},%u", + if (test_bit(AFS_SERVER_FL_IS_YFS, &fc->cbi->server->flags)) + return yfs_fs_inline_bulk_status(fc, net, fids, statuses, callbacks, + nr_fids, volsync); + + _enter(",%x,{%llx:%llu},%u", key_serial(fc->key), fids[0].vid, fids[1].vnode, nr_fids); call = afs_alloc_flat_call(net, &afs_RXFSInlineBulkStatus, @@ -2334,6 +2348,7 @@ int afs_fs_inline_bulk_status(struct afs_fs_cursor *fc, call->reply[2] = callbacks; call->reply[3] = volsync; call->count2 = nr_fids; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 479b7fdda1244f..4c6d8e1112c2b7 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -82,7 +82,7 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key) default: printk("kAFS: AFS vnode with undefined type\n"); read_sequnlock_excl(&vnode->cb_lock); - return afs_protocol_error(NULL, -EBADMSG); + return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type); } inode->i_blocks = 0; @@ -100,7 +100,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) struct afs_fs_cursor fc; int ret; - _enter("%s,{%x:%u.%u,S=%lx}", + _enter("%s,{%llx:%llu.%u,S=%lx}", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique, vnode->flags); @@ -127,9 +127,9 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) int afs_iget5_test(struct inode *inode, void *opaque) { struct afs_iget_data *data = opaque; + struct afs_vnode *vnode = AFS_FS_I(inode); - return inode->i_ino == data->fid.vnode && - inode->i_generation == data->fid.unique; + return memcmp(&vnode->fid, &data->fid, sizeof(data->fid)) == 0; } /* @@ -150,11 +150,14 @@ static int afs_iget5_set(struct inode *inode, void *opaque) struct afs_iget_data *data = opaque; struct afs_vnode *vnode = AFS_FS_I(inode); - inode->i_ino = data->fid.vnode; - inode->i_generation = data->fid.unique; vnode->fid = data->fid; vnode->volume = data->volume; + /* YFS supports 96-bit vnode IDs, but Linux only supports + * 64-bit inode numbers. + */ + inode->i_ino = data->fid.vnode; + inode->i_generation = data->fid.unique; return 0; } @@ -193,7 +196,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root) return ERR_PTR(-ENOMEM); } - _debug("GOT INODE %p { ino=%lu, vl=%x, vn=%x, u=%x }", + _debug("GOT INODE %p { ino=%lu, vl=%llx, vn=%llx, u=%x }", inode, inode->i_ino, data.fid.vid, data.fid.vnode, data.fid.unique); @@ -252,8 +255,8 @@ static void afs_get_inode_cache(struct afs_vnode *vnode) key.vnode_id = vnode->fid.vnode; key.unique = vnode->fid.unique; - key.vnode_id_ext[0] = 0; - key.vnode_id_ext[1] = 0; + key.vnode_id_ext[0] = vnode->fid.vnode >> 32; + key.vnode_id_ext[1] = vnode->fid.vnode_hi; aux.data_version = vnode->status.data_version; vnode->cache = fscache_acquire_cookie(vnode->volume->cache, @@ -277,7 +280,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, struct inode *inode; int ret; - _enter(",{%x:%u.%u},,", fid->vid, fid->vnode, fid->unique); + _enter(",{%llx:%llu.%u},,", fid->vid, fid->vnode, fid->unique); as = sb->s_fs_info; data.volume = as->volume; @@ -289,7 +292,7 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, return ERR_PTR(-ENOMEM); } - _debug("GOT INODE %p { vl=%x vn=%x, u=%x }", + _debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }", inode, fid->vid, fid->vnode, fid->unique); vnode = AFS_FS_I(inode); @@ -314,11 +317,11 @@ struct inode *afs_iget(struct super_block *sb, struct key *key, * didn't give us a callback) */ vnode->cb_version = 0; vnode->cb_type = 0; - vnode->cb_expires_at = 0; + vnode->cb_expires_at = ktime_get(); } else { vnode->cb_version = cb->version; vnode->cb_type = cb->type; - vnode->cb_expires_at = cb->expiry; + vnode->cb_expires_at = cb->expires_at; vnode->cb_interest = afs_get_cb_interest(cbi); set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); } @@ -352,7 +355,7 @@ bad_inode: */ void afs_zap_data(struct afs_vnode *vnode) { - _enter("{%x:%u}", vnode->fid.vid, vnode->fid.vnode); + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); #ifdef CONFIG_AFS_FSCACHE fscache_invalidate(vnode->cache); @@ -382,7 +385,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) bool valid = false; int ret; - _enter("{v={%x:%u} fl=%lx},%x", + _enter("{v={%llx:%llu} fl=%lx},%x", vnode->fid.vid, vnode->fid.vnode, vnode->flags, key_serial(key)); @@ -501,7 +504,7 @@ void afs_evict_inode(struct inode *inode) vnode = AFS_FS_I(inode); - _enter("{%x:%u.%d}", + _enter("{%llx:%llu.%d}", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); @@ -550,7 +553,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) struct key *key; int ret; - _enter("{%x:%u},{n=%pd},%x", + _enter("{%llx:%llu},{n=%pd},%x", vnode->fid.vid, vnode->fid.vnode, dentry, attr->ia_valid); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 72de1f157d2023..5da3b09b751867 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -22,6 +22,7 @@ #include <linux/backing-dev.h> #include <linux/uuid.h> #include <linux/mm_types.h> +#include <linux/dns_resolver.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> @@ -75,10 +76,13 @@ struct afs_addr_list { u32 version; /* Version */ unsigned char max_addrs; unsigned char nr_addrs; - unsigned char index; /* Address currently in use */ + unsigned char preferred; /* Preferred address */ unsigned char nr_ipv4; /* Number of IPv4 addresses */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; unsigned long probed; /* Mask of servers that have been probed */ - unsigned long yfs; /* Mask of servers that are YFS */ + unsigned long failed; /* Mask of addrs that failed locally/ICMP */ + unsigned long responded; /* Mask of addrs that responded */ struct sockaddr_rxrpc addrs[]; #define AFS_MAX_ADDRESSES ((unsigned int)(sizeof(unsigned long) * 8)) }; @@ -88,6 +92,7 @@ struct afs_addr_list { */ struct afs_call { const struct afs_call_type *type; /* type of call */ + struct afs_addr_list *alist; /* Address is alist[addr_ix] */ wait_queue_head_t waitq; /* processes awaiting completion */ struct work_struct async_work; /* async I/O processor */ struct work_struct work; /* actual work processor */ @@ -98,16 +103,22 @@ struct afs_call { struct afs_cb_interest *cbi; /* Callback interest for server used */ void *request; /* request data (first part) */ struct address_space *mapping; /* Pages being written from */ + struct iov_iter iter; /* Buffer iterator */ + struct iov_iter *_iter; /* Iterator currently in use */ + union { /* Convenience for ->iter */ + struct kvec kvec[1]; + struct bio_vec bvec[1]; + }; void *buffer; /* reply receive buffer */ void *reply[4]; /* Where to put the reply */ pgoff_t first; /* first page in mapping to deal with */ pgoff_t last; /* last page in mapping to deal with */ - size_t offset; /* offset into received data store */ atomic_t usage; enum afs_call_state state; spinlock_t state_lock; int error; /* error code */ u32 abort_code; /* Remote abort ID or 0 */ + u32 epoch; unsigned request_size; /* size of request data */ unsigned reply_max; /* maximum size of reply */ unsigned first_offset; /* offset into mapping[first] */ @@ -117,19 +128,28 @@ struct afs_call { unsigned count2; /* count used in unmarshalling */ }; unsigned char unmarshall; /* unmarshalling phase */ + unsigned char addr_ix; /* Address in ->alist */ bool incoming; /* T if incoming call */ bool send_pages; /* T if data from mapping should be sent */ bool need_attention; /* T if RxRPC poked us */ bool async; /* T if asynchronous */ bool ret_reply0; /* T if should return reply[0] on success */ bool upgrade; /* T to request service upgrade */ + bool want_reply_time; /* T if want reply_time */ u16 service_id; /* Actual service ID (after upgrade) */ unsigned int debug_id; /* Trace ID */ u32 operation_ID; /* operation ID for an incoming call */ u32 count; /* count for use in unmarshalling */ - __be32 tmp; /* place to extract temporary data */ + union { /* place to extract temporary data */ + struct { + __be32 tmp_u; + __be32 tmp; + } __attribute__((packed)); + __be64 tmp64; + }; afs_dataversion_t expected_version; /* Updated version expected from store */ afs_dataversion_t expected_version_2; /* 2nd updated version expected from store */ + ktime_t reply_time; /* Time of first reply packet */ }; struct afs_call_type { @@ -146,6 +166,9 @@ struct afs_call_type { /* Work function */ void (*work)(struct work_struct *work); + + /* Call done function (gets called immediately on success or failure) */ + void (*done)(struct afs_call *call); }; /* @@ -185,6 +208,7 @@ struct afs_read { refcount_t usage; unsigned int index; /* Which page we're reading into */ unsigned int nr_pages; + unsigned int offset; /* offset into current page */ void (*page_done)(struct afs_call *, struct afs_read *); struct page **pages; struct page *array[]; @@ -343,13 +367,70 @@ struct afs_cell { rwlock_t proc_lock; /* VL server list. */ - rwlock_t vl_addrs_lock; /* Lock on vl_addrs */ - struct afs_addr_list __rcu *vl_addrs; /* List of VL servers */ + rwlock_t vl_servers_lock; /* Lock on vl_servers */ + struct afs_vlserver_list __rcu *vl_servers; + u8 name_len; /* Length of name */ char name[64 + 1]; /* Cell name, case-flattened and NUL-padded */ }; /* + * Volume Location server record. + */ +struct afs_vlserver { + struct rcu_head rcu; + struct afs_addr_list __rcu *addresses; /* List of addresses for this VL server */ + unsigned long flags; +#define AFS_VLSERVER_FL_PROBED 0 /* The VL server has been probed */ +#define AFS_VLSERVER_FL_PROBING 1 /* VL server is being probed */ +#define AFS_VLSERVER_FL_IS_YFS 2 /* Server is YFS not AFS */ + rwlock_t lock; /* Lock on addresses */ + atomic_t usage; + + /* Probe state */ + wait_queue_head_t probe_wq; + atomic_t probe_outstanding; + spinlock_t probe_lock; + struct { + unsigned int rtt; /* RTT as ktime/64 */ + u32 abort_code; + short error; + bool have_result; + bool responded:1; + bool is_yfs:1; + bool not_yfs:1; + bool local_failure:1; + } probe; + + u16 port; + u16 name_len; /* Length of name */ + char name[]; /* Server name, case-flattened */ +}; + +/* + * Weighted list of Volume Location servers. + */ +struct afs_vlserver_entry { + u16 priority; /* Preference (as SRV) */ + u16 weight; /* Weight (as SRV) */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; + struct afs_vlserver *server; +}; + +struct afs_vlserver_list { + struct rcu_head rcu; + atomic_t usage; + u8 nr_servers; + u8 index; /* Server currently in use */ + u8 preferred; /* Preferred server */ + enum dns_record_source source:8; + enum dns_lookup_status status:8; + rwlock_t lock; + struct afs_vlserver_entry servers[]; +}; + +/* * Cached VLDB entry. * * This is pointed to by cell->vldb_entries, indexed by name. @@ -403,8 +484,12 @@ struct afs_server { #define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */ #define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */ #define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */ +#define AFS_SERVER_FL_IS_YFS 9 /* Server is YFS not AFS */ +#define AFS_SERVER_FL_NO_RM2 10 /* Fileserver doesn't support YFS.RemoveFile2 */ +#define AFS_SERVER_FL_HAVE_EPOCH 11 /* ->epoch is valid */ atomic_t usage; u32 addr_version; /* Address list version */ + u32 cm_epoch; /* Server RxRPC epoch */ /* file service access */ rwlock_t fs_lock; /* access lock */ @@ -413,6 +498,26 @@ struct afs_server { struct hlist_head cb_volumes; /* List of volume interests on this server */ unsigned cb_s_break; /* Break-everything counter. */ rwlock_t cb_break_lock; /* Volume finding lock */ + + /* Probe state */ + wait_queue_head_t probe_wq; + atomic_t probe_outstanding; + spinlock_t probe_lock; + struct { + unsigned int rtt; /* RTT as ktime/64 */ + u32 abort_code; + u32 cm_epoch; + short error; + bool have_result; + bool responded:1; + bool is_yfs:1; + bool not_yfs:1; + bool local_failure:1; + bool no_epoch:1; + bool cm_probed:1; + bool said_rebooted:1; + bool said_inconsistent:1; + } probe; }; /* @@ -447,8 +552,8 @@ struct afs_server_entry { struct afs_server_list { refcount_t usage; - unsigned short nr_servers; - unsigned short index; /* Server currently in use */ + unsigned char nr_servers; + unsigned char preferred; /* Preferred server */ unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */ unsigned int seq; /* Set to ->servers_seq when installed */ rwlock_t lock; @@ -550,6 +655,15 @@ struct afs_vnode { afs_callback_type_t cb_type; /* type of callback */ }; +static inline struct fscache_cookie *afs_vnode_cache(struct afs_vnode *vnode) +{ +#ifdef CONFIG_AFS_FSCACHE + return vnode->cache; +#else + return NULL; +#endif +} + /* * cached security record for one user's attempt to access a vnode */ @@ -586,13 +700,31 @@ struct afs_interface { */ struct afs_addr_cursor { struct afs_addr_list *alist; /* Current address list (pins ref) */ - struct sockaddr_rxrpc *addr; + unsigned long tried; /* Tried addresses */ + signed char index; /* Current address */ + bool responded; /* T if the current address responded */ + unsigned short nr_iterations; /* Number of address iterations */ + short error; u32 abort_code; - unsigned short start; /* Starting point in alist->addrs[] */ - unsigned short index; /* Wrapping offset from start to current addr */ +}; + +/* + * Cursor for iterating over a set of volume location servers. + */ +struct afs_vl_cursor { + struct afs_addr_cursor ac; + struct afs_cell *cell; /* The cell we're querying */ + struct afs_vlserver_list *server_list; /* Current server list (pins ref) */ + struct afs_vlserver *server; /* Server on which this resides */ + struct key *key; /* Key for the server */ + unsigned long untried; /* Bitmask of untried servers */ + short index; /* Current server */ short error; - bool begun; /* T if we've begun iteration */ - bool responded; /* T if the current address responded */ + unsigned short flags; +#define AFS_VL_CURSOR_STOP 0x0001 /* Set to cease iteration */ +#define AFS_VL_CURSOR_RETRY 0x0002 /* Set to do a retry */ +#define AFS_VL_CURSOR_RETRIED 0x0004 /* Set if started a retry */ + unsigned short nr_iterations; /* Number of server iterations */ }; /* @@ -604,10 +736,11 @@ struct afs_fs_cursor { struct afs_server_list *server_list; /* Current server list (pins ref) */ struct afs_cb_interest *cbi; /* Server on which this resides (pins ref) */ struct key *key; /* Key for the server */ + unsigned long untried; /* Bitmask of untried servers */ unsigned int cb_break; /* cb_break + cb_s_break before the call */ unsigned int cb_break_2; /* cb_break + cb_s_break (2nd vnode) */ - unsigned char start; /* Initial index in server list */ - unsigned char index; /* Number of servers tried beyond start */ + short index; /* Current server */ + short error; unsigned short flags; #define AFS_FS_CURSOR_STOP 0x0001 /* Set to cease iteration */ #define AFS_FS_CURSOR_VBUSY 0x0002 /* Set if seen VBUSY */ @@ -615,6 +748,7 @@ struct afs_fs_cursor { #define AFS_FS_CURSOR_VNOVOL 0x0008 /* Set if seen VNOVOL */ #define AFS_FS_CURSOR_CUR_ONLY 0x0010 /* Set if current server only (file lock held) */ #define AFS_FS_CURSOR_NO_VSLEEP 0x0020 /* Set to prevent sleep on VBUSY, VOFFLINE, ... */ + unsigned short nr_iterations; /* Number of server iterations */ }; /* @@ -640,12 +774,12 @@ extern struct afs_addr_list *afs_alloc_addrlist(unsigned int, unsigned short, unsigned short); extern void afs_put_addrlist(struct afs_addr_list *); -extern struct afs_addr_list *afs_parse_text_addrs(const char *, size_t, char, - unsigned short, unsigned short); -extern struct afs_addr_list *afs_dns_query(struct afs_cell *, time64_t *); +extern struct afs_vlserver_list *afs_parse_text_addrs(struct afs_net *, + const char *, size_t, char, + unsigned short, unsigned short); +extern struct afs_vlserver_list *afs_dns_query(struct afs_cell *, time64_t *); extern bool afs_iterate_addresses(struct afs_addr_cursor *); extern int afs_end_cursor(struct afs_addr_cursor *); -extern int afs_set_vl_cursor(struct afs_addr_cursor *, struct afs_cell *); extern void afs_merge_fs_addr4(struct afs_addr_list *, __be32, u16); extern void afs_merge_fs_addr6(struct afs_addr_list *, __be32 *, u16); @@ -668,6 +802,7 @@ extern struct fscache_cookie_def afs_vnode_cache_index_def; * callback.c */ extern void afs_init_callback_state(struct afs_server *); +extern void __afs_break_callback(struct afs_vnode *); extern void afs_break_callback(struct afs_vnode *); extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*); @@ -688,10 +823,13 @@ static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; } -static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode, - struct afs_cb_interest *cbi) +static inline bool afs_cb_is_broken(unsigned int cb_break, + const struct afs_vnode *vnode, + const struct afs_cb_interest *cbi) { - return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break; + return !cbi || cb_break != (vnode->cb_break + + cbi->server->cb_s_break + + vnode->volume->cb_v_break); } /* @@ -781,7 +919,7 @@ extern int afs_fs_give_up_callbacks(struct afs_net *, struct afs_server *); extern int afs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); extern int afs_fs_create(struct afs_fs_cursor *, const char *, umode_t, u64, struct afs_fid *, struct afs_file_status *, struct afs_callback *); -extern int afs_fs_remove(struct afs_fs_cursor *, const char *, bool, u64); +extern int afs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); extern int afs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); extern int afs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, struct afs_fid *, struct afs_file_status *); @@ -797,7 +935,7 @@ extern int afs_fs_release_lock(struct afs_fs_cursor *); extern int afs_fs_give_up_all_callbacks(struct afs_net *, struct afs_server *, struct afs_addr_cursor *, struct key *); extern int afs_fs_get_capabilities(struct afs_net *, struct afs_server *, - struct afs_addr_cursor *, struct key *); + struct afs_addr_cursor *, struct key *, unsigned int, bool); extern int afs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, struct afs_fid *, struct afs_file_status *, struct afs_callback *, unsigned int, @@ -807,6 +945,13 @@ extern int afs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, struct afs_callback *, struct afs_volsync *); /* + * fs_probe.c + */ +extern void afs_fileserver_probe_result(struct afs_call *); +extern int afs_probe_fileservers(struct afs_net *, struct key *, struct afs_server_list *); +extern int afs_wait_for_fs_probes(struct afs_server_list *, unsigned long); + +/* * inode.c */ extern int afs_fetch_status(struct afs_vnode *, struct key *, bool); @@ -922,7 +1067,6 @@ extern int __net_init afs_open_socket(struct afs_net *); extern void __net_exit afs_close_socket(struct afs_net *); extern void afs_charge_preallocation(struct work_struct *); extern void afs_put_call(struct afs_call *); -extern int afs_queue_call_work(struct afs_call *); extern long afs_make_call(struct afs_addr_cursor *, struct afs_call *, gfp_t, bool); extern struct afs_call *afs_alloc_flat_call(struct afs_net *, const struct afs_call_type *, @@ -930,12 +1074,39 @@ extern struct afs_call *afs_alloc_flat_call(struct afs_net *, extern void afs_flat_call_destructor(struct afs_call *); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); -extern int afs_extract_data(struct afs_call *, void *, size_t, bool); -extern int afs_protocol_error(struct afs_call *, int); +extern int afs_extract_data(struct afs_call *, bool); +extern int afs_protocol_error(struct afs_call *, int, enum afs_eproto_cause); + +static inline void afs_extract_begin(struct afs_call *call, void *buf, size_t size) +{ + call->kvec[0].iov_base = buf; + call->kvec[0].iov_len = size; + iov_iter_kvec(&call->iter, READ, call->kvec, 1, size); +} + +static inline void afs_extract_to_tmp(struct afs_call *call) +{ + afs_extract_begin(call, &call->tmp, sizeof(call->tmp)); +} + +static inline void afs_extract_to_tmp64(struct afs_call *call) +{ + afs_extract_begin(call, &call->tmp64, sizeof(call->tmp64)); +} + +static inline void afs_extract_discard(struct afs_call *call, size_t size) +{ + iov_iter_discard(&call->iter, READ, size); +} + +static inline void afs_extract_to_buf(struct afs_call *call, size_t size) +{ + afs_extract_begin(call, call->buffer, size); +} static inline int afs_transfer_reply(struct afs_call *call) { - return afs_extract_data(call, call->buffer, call->reply_max, false); + return afs_extract_data(call, false); } static inline bool afs_check_call_state(struct afs_call *call, @@ -1012,7 +1183,6 @@ extern void afs_put_server(struct afs_net *, struct afs_server *); extern void afs_manage_servers(struct work_struct *); extern void afs_servers_timer(struct timer_list *); extern void __net_exit afs_purge_servers(struct afs_net *); -extern bool afs_probe_fileserver(struct afs_fs_cursor *); extern bool afs_check_server_record(struct afs_fs_cursor *, struct afs_server *); /* @@ -1039,14 +1209,51 @@ extern void afs_fs_exit(void); /* * vlclient.c */ -extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *, - struct afs_addr_cursor *, - struct key *, const char *, int); -extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *, struct afs_addr_cursor *, - struct key *, const uuid_t *); -extern int afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *); -extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *, struct afs_addr_cursor *, - struct key *, const uuid_t *); +extern struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *, + const char *, int); +extern struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *, const uuid_t *); +extern int afs_vl_get_capabilities(struct afs_net *, struct afs_addr_cursor *, struct key *, + struct afs_vlserver *, unsigned int, bool); +extern struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *, const uuid_t *); + +/* + * vl_probe.c + */ +extern void afs_vlserver_probe_result(struct afs_call *); +extern int afs_send_vl_probes(struct afs_net *, struct key *, struct afs_vlserver_list *); +extern int afs_wait_for_vl_probes(struct afs_vlserver_list *, unsigned long); + +/* + * vl_rotate.c + */ +extern bool afs_begin_vlserver_operation(struct afs_vl_cursor *, + struct afs_cell *, struct key *); +extern bool afs_select_vlserver(struct afs_vl_cursor *); +extern bool afs_select_current_vlserver(struct afs_vl_cursor *); +extern int afs_end_vlserver_operation(struct afs_vl_cursor *); + +/* + * vlserver_list.c + */ +static inline struct afs_vlserver *afs_get_vlserver(struct afs_vlserver *vlserver) +{ + atomic_inc(&vlserver->usage); + return vlserver; +} + +static inline struct afs_vlserver_list *afs_get_vlserverlist(struct afs_vlserver_list *vllist) +{ + if (vllist) + atomic_inc(&vllist->usage); + return vllist; +} + +extern struct afs_vlserver *afs_alloc_vlserver(const char *, size_t, unsigned short); +extern void afs_put_vlserver(struct afs_net *, struct afs_vlserver *); +extern struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int); +extern void afs_put_vlserverlist(struct afs_net *, struct afs_vlserver_list *); +extern struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *, + const void *, size_t); /* * volume.c @@ -1089,6 +1296,36 @@ extern int afs_launder_page(struct page *); extern const struct xattr_handler *afs_xattr_handlers[]; extern ssize_t afs_listxattr(struct dentry *, char *, size_t); +/* + * yfsclient.c + */ +extern int yfs_fs_fetch_file_status(struct afs_fs_cursor *, struct afs_volsync *, bool); +extern int yfs_fs_fetch_data(struct afs_fs_cursor *, struct afs_read *); +extern int yfs_fs_create_file(struct afs_fs_cursor *, const char *, umode_t, u64, + struct afs_fid *, struct afs_file_status *, struct afs_callback *); +extern int yfs_fs_make_dir(struct afs_fs_cursor *, const char *, umode_t, u64, + struct afs_fid *, struct afs_file_status *, struct afs_callback *); +extern int yfs_fs_remove_file2(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); +extern int yfs_fs_remove(struct afs_fs_cursor *, struct afs_vnode *, const char *, bool, u64); +extern int yfs_fs_link(struct afs_fs_cursor *, struct afs_vnode *, const char *, u64); +extern int yfs_fs_symlink(struct afs_fs_cursor *, const char *, const char *, u64, + struct afs_fid *, struct afs_file_status *); +extern int yfs_fs_rename(struct afs_fs_cursor *, const char *, + struct afs_vnode *, const char *, u64, u64); +extern int yfs_fs_store_data(struct afs_fs_cursor *, struct address_space *, + pgoff_t, pgoff_t, unsigned, unsigned); +extern int yfs_fs_setattr(struct afs_fs_cursor *, struct iattr *); +extern int yfs_fs_get_volume_status(struct afs_fs_cursor *, struct afs_volume_status *); +extern int yfs_fs_set_lock(struct afs_fs_cursor *, afs_lock_type_t); +extern int yfs_fs_extend_lock(struct afs_fs_cursor *); +extern int yfs_fs_release_lock(struct afs_fs_cursor *); +extern int yfs_fs_fetch_status(struct afs_fs_cursor *, struct afs_net *, + struct afs_fid *, struct afs_file_status *, + struct afs_callback *, struct afs_volsync *); +extern int yfs_fs_inline_bulk_status(struct afs_fs_cursor *, struct afs_net *, + struct afs_fid *, struct afs_file_status *, + struct afs_callback *, unsigned int, + struct afs_volsync *); /* * Miscellaneous inline functions. @@ -1120,6 +1357,17 @@ static inline void afs_check_for_remote_deletion(struct afs_fs_cursor *fc, } } +static inline int afs_io_error(struct afs_call *call, enum afs_io_error where) +{ + trace_afs_io_error(call->debug_id, -EIO, where); + return -EIO; +} + +static inline int afs_bad(struct afs_vnode *vnode, enum afs_file_error where) +{ + trace_afs_file_error(vnode, -EIO, where); + return -EIO; +} /*****************************************************************************/ /* diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 99fd13500a97f9..2e51c6994148f3 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -130,9 +130,10 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) goto error_no_page; } - ret = -EIO; - if (PageError(page)) + if (PageError(page)) { + ret = afs_bad(AFS_FS_I(d_inode(mntpt)), afs_file_error_mntpt); goto error; + } buf = kmap_atomic(page); memcpy(devname, buf, size); diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 9101f62707af2d..be2ee3bbd0a953 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -17,6 +17,11 @@ #include <linux/uaccess.h> #include "internal.h" +struct afs_vl_seq_net_private { + struct seq_net_private seq; /* Must be first */ + struct afs_vlserver_list *vllist; +}; + static inline struct afs_net *afs_seq2net(struct seq_file *m) { return afs_net(seq_file_net(m)); @@ -32,16 +37,24 @@ static inline struct afs_net *afs_seq2net_single(struct seq_file *m) */ static int afs_proc_cells_show(struct seq_file *m, void *v) { - struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link); + struct afs_vlserver_list *vllist; + struct afs_cell *cell; if (v == SEQ_START_TOKEN) { /* display header on line 1 */ - seq_puts(m, "USE NAME\n"); + seq_puts(m, "USE TTL SV NAME\n"); return 0; } + cell = list_entry(v, struct afs_cell, proc_link); + vllist = rcu_dereference(cell->vl_servers); + /* display one cell per line on subsequent lines */ - seq_printf(m, "%3u %s\n", atomic_read(&cell->usage), cell->name); + seq_printf(m, "%3u %6lld %2u %s\n", + atomic_read(&cell->usage), + cell->dns_expiry - ktime_get_real_seconds(), + vllist ? vllist->nr_servers : 0, + cell->name); return 0; } @@ -208,7 +221,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v) return 0; } - seq_printf(m, "%3d %08x %s\n", + seq_printf(m, "%3d %08llx %s\n", atomic_read(&vol->usage), vol->vid, afs_vol_types[vol->type]); @@ -247,61 +260,102 @@ static const struct seq_operations afs_proc_cell_volumes_ops = { .show = afs_proc_cell_volumes_show, }; +static const char *const dns_record_sources[NR__dns_record_source + 1] = { + [DNS_RECORD_UNAVAILABLE] = "unav", + [DNS_RECORD_FROM_CONFIG] = "cfg", + [DNS_RECORD_FROM_DNS_A] = "A", + [DNS_RECORD_FROM_DNS_AFSDB] = "AFSDB", + [DNS_RECORD_FROM_DNS_SRV] = "SRV", + [DNS_RECORD_FROM_NSS] = "nss", + [NR__dns_record_source] = "[weird]" +}; + +static const char *const dns_lookup_statuses[NR__dns_lookup_status + 1] = { + [DNS_LOOKUP_NOT_DONE] = "no-lookup", + [DNS_LOOKUP_GOOD] = "good", + [DNS_LOOKUP_GOOD_WITH_BAD] = "good/bad", + [DNS_LOOKUP_BAD] = "bad", + [DNS_LOOKUP_GOT_NOT_FOUND] = "not-found", + [DNS_LOOKUP_GOT_LOCAL_FAILURE] = "local-failure", + [DNS_LOOKUP_GOT_TEMP_FAILURE] = "temp-failure", + [DNS_LOOKUP_GOT_NS_FAILURE] = "ns-failure", + [NR__dns_lookup_status] = "[weird]" +}; + /* * Display the list of Volume Location servers we're using for a cell. */ static int afs_proc_cell_vlservers_show(struct seq_file *m, void *v) { - struct sockaddr_rxrpc *addr = v; + const struct afs_vl_seq_net_private *priv = m->private; + const struct afs_vlserver_list *vllist = priv->vllist; + const struct afs_vlserver_entry *entry; + const struct afs_vlserver *vlserver; + const struct afs_addr_list *alist; + int i; - /* display header on line 1 */ - if (v == (void *)1) { - seq_puts(m, "ADDRESS\n"); + if (v == SEQ_START_TOKEN) { + seq_printf(m, "# source %s, status %s\n", + dns_record_sources[vllist->source], + dns_lookup_statuses[vllist->status]); return 0; } - /* display one cell per line on subsequent lines */ - seq_printf(m, "%pISp\n", &addr->transport); + entry = v; + vlserver = entry->server; + alist = rcu_dereference(vlserver->addresses); + + seq_printf(m, "%s [p=%hu w=%hu s=%s,%s]:\n", + vlserver->name, entry->priority, entry->weight, + dns_record_sources[alist ? alist->source : entry->source], + dns_lookup_statuses[alist ? alist->status : entry->status]); + if (alist) { + for (i = 0; i < alist->nr_addrs; i++) + seq_printf(m, " %c %pISpc\n", + alist->preferred == i ? '>' : '-', + &alist->addrs[i].transport); + } return 0; } static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos) __acquires(rcu) { - struct afs_addr_list *alist; + struct afs_vl_seq_net_private *priv = m->private; + struct afs_vlserver_list *vllist; struct afs_cell *cell = PDE_DATA(file_inode(m->file)); loff_t pos = *_pos; rcu_read_lock(); - alist = rcu_dereference(cell->vl_addrs); + vllist = rcu_dereference(cell->vl_servers); + priv->vllist = vllist; - /* allow for the header line */ - if (!pos) - return (void *) 1; - pos--; + if (pos < 0) + *_pos = pos = 0; + if (pos == 0) + return SEQ_START_TOKEN; - if (!alist || pos >= alist->nr_addrs) + if (!vllist || pos - 1 >= vllist->nr_servers) return NULL; - return alist->addrs + pos; + return &vllist->servers[pos - 1]; } static void *afs_proc_cell_vlservers_next(struct seq_file *m, void *v, loff_t *_pos) { - struct afs_addr_list *alist; - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_vl_seq_net_private *priv = m->private; + struct afs_vlserver_list *vllist = priv->vllist; loff_t pos; - alist = rcu_dereference(cell->vl_addrs); - pos = *_pos; - (*_pos)++; - if (!alist || pos >= alist->nr_addrs) + pos++; + *_pos = pos; + if (!vllist || pos - 1 >= vllist->nr_servers) return NULL; - return alist->addrs + pos; + return &vllist->servers[pos - 1]; } static void afs_proc_cell_vlservers_stop(struct seq_file *m, void *v) @@ -337,11 +391,11 @@ static int afs_proc_servers_show(struct seq_file *m, void *v) &server->uuid, atomic_read(&server->usage), &alist->addrs[0].transport, - alist->index == 0 ? "*" : ""); + alist->preferred == 0 ? "*" : ""); for (i = 1; i < alist->nr_addrs; i++) seq_printf(m, " %pISpc%s\n", &alist->addrs[i].transport, - alist->index == i ? "*" : ""); + alist->preferred == i ? "*" : ""); return 0; } @@ -562,7 +616,7 @@ int afs_proc_cell_setup(struct afs_cell *cell) if (!proc_create_net_data("vlservers", 0444, dir, &afs_proc_cell_vlservers_ops, - sizeof(struct seq_net_private), + sizeof(struct afs_vl_seq_net_private), cell) || !proc_create_net_data("volumes", 0444, dir, &afs_proc_cell_volumes_ops, diff --git a/fs/afs/protocol_yfs.h b/fs/afs/protocol_yfs.h new file mode 100644 index 00000000000000..07bc10f076aacf --- /dev/null +++ b/fs/afs/protocol_yfs.h @@ -0,0 +1,163 @@ +/* YFS protocol bits + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#define YFS_FS_SERVICE 2500 +#define YFS_CM_SERVICE 2501 + +#define YFSCBMAX 1024 + +enum YFS_CM_Operations { + YFSCBProbe = 206, /* probe client */ + YFSCBGetLock = 207, /* get contents of CM lock table */ + YFSCBXStatsVersion = 209, /* get version of extended statistics */ + YFSCBGetXStats = 210, /* get contents of extended statistics data */ + YFSCBInitCallBackState3 = 213, /* initialise callback state, version 3 */ + YFSCBProbeUuid = 214, /* check the client hasn't rebooted */ + YFSCBGetServerPrefs = 215, + YFSCBGetCellServDV = 216, + YFSCBGetLocalCell = 217, + YFSCBGetCacheConfig = 218, + YFSCBGetCellByNum = 65537, + YFSCBTellMeAboutYourself = 65538, /* get client capabilities */ + YFSCBCallBack = 64204, +}; + +enum YFS_FS_Operations { + YFSFETCHACL = 64131, /* YFS Fetch file ACL */ + YFSFETCHSTATUS = 64132, /* YFS Fetch file status */ + YFSSTOREACL = 64134, /* YFS Store file ACL */ + YFSSTORESTATUS = 64135, /* YFS Store file status */ + YFSREMOVEFILE = 64136, /* YFS Remove a file */ + YFSCREATEFILE = 64137, /* YFS Create a file */ + YFSRENAME = 64138, /* YFS Rename or move a file or directory */ + YFSSYMLINK = 64139, /* YFS Create a symbolic link */ + YFSLINK = 64140, /* YFS Create a hard link */ + YFSMAKEDIR = 64141, /* YFS Create a directory */ + YFSREMOVEDIR = 64142, /* YFS Remove a directory */ + YFSGETVOLUMESTATUS = 64149, /* YFS Get volume status information */ + YFSSETVOLUMESTATUS = 64150, /* YFS Set volume status information */ + YFSSETLOCK = 64156, /* YFS Request a file lock */ + YFSEXTENDLOCK = 64157, /* YFS Extend a file lock */ + YFSRELEASELOCK = 64158, /* YFS Release a file lock */ + YFSLOOKUP = 64161, /* YFS lookup file in directory */ + YFSFLUSHCPS = 64165, + YFSFETCHOPAQUEACL = 64168, + YFSWHOAMI = 64170, + YFSREMOVEACL = 64171, + YFSREMOVEFILE2 = 64173, + YFSSTOREOPAQUEACL2 = 64174, + YFSINLINEBULKSTATUS = 64536, /* YFS Fetch multiple file statuses with errors */ + YFSFETCHDATA64 = 64537, /* YFS Fetch file data */ + YFSSTOREDATA64 = 64538, /* YFS Store file data */ + YFSUPDATESYMLINK = 64540, +}; + +struct yfs_xdr_u64 { + __be32 msw; + __be32 lsw; +} __packed; + +static inline u64 xdr_to_u64(const struct yfs_xdr_u64 x) +{ + return ((u64)ntohl(x.msw) << 32) | ntohl(x.lsw); +} + +static inline struct yfs_xdr_u64 u64_to_xdr(const u64 x) +{ + return (struct yfs_xdr_u64){ .msw = htonl(x >> 32), .lsw = htonl(x) }; +} + +struct yfs_xdr_vnode { + struct yfs_xdr_u64 lo; + __be32 hi; + __be32 unique; +} __packed; + +struct yfs_xdr_YFSFid { + struct yfs_xdr_u64 volume; + struct yfs_xdr_vnode vnode; +} __packed; + + +struct yfs_xdr_YFSFetchStatus { + __be32 type; + __be32 nlink; + struct yfs_xdr_u64 size; + struct yfs_xdr_u64 data_version; + struct yfs_xdr_u64 author; + struct yfs_xdr_u64 owner; + struct yfs_xdr_u64 group; + __be32 mode; + __be32 caller_access; + __be32 anon_access; + struct yfs_xdr_vnode parent; + __be32 data_access_protocol; + struct yfs_xdr_u64 mtime_client; + struct yfs_xdr_u64 mtime_server; + __be32 lock_count; + __be32 abort_code; +} __packed; + +struct yfs_xdr_YFSCallBack { + __be32 version; + struct yfs_xdr_u64 expiration_time; + __be32 type; +} __packed; + +struct yfs_xdr_YFSStoreStatus { + __be32 mask; + __be32 mode; + struct yfs_xdr_u64 mtime_client; + struct yfs_xdr_u64 owner; + struct yfs_xdr_u64 group; +} __packed; + +struct yfs_xdr_RPCFlags { + __be32 rpc_flags; +} __packed; + +struct yfs_xdr_YFSVolSync { + struct yfs_xdr_u64 vol_creation_date; + struct yfs_xdr_u64 vol_update_date; + struct yfs_xdr_u64 max_quota; + struct yfs_xdr_u64 blocks_in_use; + struct yfs_xdr_u64 blocks_avail; +} __packed; + +enum yfs_volume_type { + yfs_volume_type_ro = 0, + yfs_volume_type_rw = 1, +}; + +#define yfs_FVSOnline 0x1 +#define yfs_FVSInservice 0x2 +#define yfs_FVSBlessed 0x4 +#define yfs_FVSNeedsSalvage 0x8 + +struct yfs_xdr_YFSFetchVolumeStatus { + struct yfs_xdr_u64 vid; + struct yfs_xdr_u64 parent_id; + __be32 flags; + __be32 type; + struct yfs_xdr_u64 max_quota; + struct yfs_xdr_u64 blocks_in_use; + struct yfs_xdr_u64 part_blocks_avail; + struct yfs_xdr_u64 part_max_blocks; + struct yfs_xdr_u64 vol_copy_date; + struct yfs_xdr_u64 vol_backup_date; +} __packed; + +struct yfs_xdr_YFSStoreVolumeStatus { + __be32 mask; + struct yfs_xdr_u64 min_quota; + struct yfs_xdr_u64 max_quota; + struct yfs_xdr_u64 file_quota; +} __packed; diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 1faef56b12bd3f..00504254c1c24b 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -19,14 +19,6 @@ #include "afs_fs.h" /* - * Initialise a filesystem server cursor for iterating over FS servers. - */ -static void afs_init_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode) -{ - memset(fc, 0, sizeof(*fc)); -} - -/* * Begin an operation on the fileserver. * * Fileserver operations are serialised on the server by vnode, so we serialise @@ -35,13 +27,14 @@ static void afs_init_fs_cursor(struct afs_fs_cursor *fc, struct afs_vnode *vnode bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode, struct key *key) { - afs_init_fs_cursor(fc, vnode); + memset(fc, 0, sizeof(*fc)); fc->vnode = vnode; fc->key = key; fc->ac.error = SHRT_MAX; + fc->error = -EDESTADDRREQ; if (mutex_lock_interruptible(&vnode->io_lock) < 0) { - fc->ac.error = -EINTR; + fc->error = -EINTR; fc->flags |= AFS_FS_CURSOR_STOP; return false; } @@ -65,12 +58,15 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, fc->server_list = afs_get_serverlist(vnode->volume->servers); read_unlock(&vnode->volume->servers_lock); + fc->untried = (1UL << fc->server_list->nr_servers) - 1; + fc->index = READ_ONCE(fc->server_list->preferred); + cbi = vnode->cb_interest; if (cbi) { /* See if the vnode's preferred record is still available */ for (i = 0; i < fc->server_list->nr_servers; i++) { if (fc->server_list->servers[i].cb_interest == cbi) { - fc->start = i; + fc->index = i; goto found_interest; } } @@ -80,7 +76,7 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, * and have to return an error. */ if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) { - fc->ac.error = -ESTALE; + fc->error = -ESTALE; return false; } @@ -94,12 +90,9 @@ static bool afs_start_fs_iteration(struct afs_fs_cursor *fc, afs_put_cb_interest(afs_v2net(vnode), cbi); cbi = NULL; - } else { - fc->start = READ_ONCE(fc->server_list->index); } found_interest: - fc->index = fc->start; return true; } @@ -117,7 +110,7 @@ static void afs_busy(struct afs_volume *volume, u32 abort_code) default: m = "busy"; break; } - pr_notice("kAFS: Volume %u '%s' is %s\n", volume->vid, volume->name, m); + pr_notice("kAFS: Volume %llu '%s' is %s\n", volume->vid, volume->name, m); } /* @@ -127,7 +120,7 @@ static bool afs_sleep_and_retry(struct afs_fs_cursor *fc) { msleep_interruptible(1000); if (signal_pending(current)) { - fc->ac.error = -ERESTARTSYS; + fc->error = -ERESTARTSYS; return false; } @@ -143,27 +136,32 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) struct afs_addr_list *alist; struct afs_server *server; struct afs_vnode *vnode = fc->vnode; + u32 rtt, abort_code; + int error = fc->ac.error, i; - _enter("%u/%u,%u/%u,%d,%d", - fc->index, fc->start, - fc->ac.index, fc->ac.start, - fc->ac.error, fc->ac.abort_code); + _enter("%lx[%d],%lx[%d],%d,%d", + fc->untried, fc->index, + fc->ac.tried, fc->ac.index, + error, fc->ac.abort_code); if (fc->flags & AFS_FS_CURSOR_STOP) { _leave(" = f [stopped]"); return false; } + fc->nr_iterations++; + /* Evaluate the result of the previous operation, if there was one. */ - switch (fc->ac.error) { + switch (error) { case SHRT_MAX: goto start; case 0: default: /* Success or local failure. Stop. */ + fc->error = error; fc->flags |= AFS_FS_CURSOR_STOP; - _leave(" = f [okay/local %d]", fc->ac.error); + _leave(" = f [okay/local %d]", error); return false; case -ECONNABORTED: @@ -178,7 +176,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * - May indicate that the fileserver couldn't attach to the vol. */ if (fc->flags & AFS_FS_CURSOR_VNOVOL) { - fc->ac.error = -EREMOTEIO; + fc->error = -EREMOTEIO; goto next_server; } @@ -187,12 +185,12 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) write_unlock(&vnode->volume->servers_lock); set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - fc->ac.error = afs_check_volume_status(vnode->volume, fc->key); - if (fc->ac.error < 0) - goto failed; + error = afs_check_volume_status(vnode->volume, fc->key); + if (error < 0) + goto failed_set_error; if (test_bit(AFS_VOLUME_DELETED, &vnode->volume->flags)) { - fc->ac.error = -ENOMEDIUM; + fc->error = -ENOMEDIUM; goto failed; } @@ -200,7 +198,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * it's the fileserver having trouble. */ if (vnode->volume->servers == fc->server_list) { - fc->ac.error = -EREMOTEIO; + fc->error = -EREMOTEIO; goto next_server; } @@ -215,7 +213,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) case VONLINE: case VDISKFULL: case VOVERQUOTA: - fc->ac.error = afs_abort_to_error(fc->ac.abort_code); + fc->error = afs_abort_to_error(fc->ac.abort_code); goto next_server; case VOFFLINE: @@ -224,11 +222,11 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags); } if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) { - fc->ac.error = -EADV; + fc->error = -EADV; goto failed; } if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) { - fc->ac.error = -ESTALE; + fc->error = -ESTALE; goto failed; } goto busy; @@ -240,7 +238,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * have a file lock we need to maintain. */ if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) { - fc->ac.error = -EBUSY; + fc->error = -EBUSY; goto failed; } if (!test_and_set_bit(AFS_VOLUME_BUSY, &vnode->volume->flags)) { @@ -269,16 +267,16 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * honour, just in case someone sets up a loop. */ if (fc->flags & AFS_FS_CURSOR_VMOVED) { - fc->ac.error = -EREMOTEIO; + fc->error = -EREMOTEIO; goto failed; } fc->flags |= AFS_FS_CURSOR_VMOVED; set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags); set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags); - fc->ac.error = afs_check_volume_status(vnode->volume, fc->key); - if (fc->ac.error < 0) - goto failed; + error = afs_check_volume_status(vnode->volume, fc->key); + if (error < 0) + goto failed_set_error; /* If the server list didn't change, then the VLDB is * out of sync with the fileservers. This is hopefully @@ -290,7 +288,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) * TODO: Retry a few times with sleeps. */ if (vnode->volume->servers == fc->server_list) { - fc->ac.error = -ENOMEDIUM; + fc->error = -ENOMEDIUM; goto failed; } @@ -299,20 +297,25 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) default: clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags); clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags); - fc->ac.error = afs_abort_to_error(fc->ac.abort_code); + fc->error = afs_abort_to_error(fc->ac.abort_code); goto failed; } + case -ETIMEDOUT: + case -ETIME: + if (fc->error != -EDESTADDRREQ) + goto iterate_address; + /* Fall through */ case -ENETUNREACH: case -EHOSTUNREACH: case -ECONNREFUSED: - case -ETIMEDOUT: - case -ETIME: _debug("no conn"); + fc->error = error; goto iterate_address; case -ECONNRESET: _debug("call reset"); + fc->error = error; goto failed; } @@ -328,15 +331,57 @@ start: /* See if we need to do an update of the volume record. Note that the * volume may have moved or even have been deleted. */ - fc->ac.error = afs_check_volume_status(vnode->volume, fc->key); - if (fc->ac.error < 0) - goto failed; + error = afs_check_volume_status(vnode->volume, fc->key); + if (error < 0) + goto failed_set_error; if (!afs_start_fs_iteration(fc, vnode)) goto failed; -use_server: - _debug("use"); + _debug("__ VOL %llx __", vnode->volume->vid); + error = afs_probe_fileservers(afs_v2net(vnode), fc->key, fc->server_list); + if (error < 0) + goto failed_set_error; + +pick_server: + _debug("pick [%lx]", fc->untried); + + error = afs_wait_for_fs_probes(fc->server_list, fc->untried); + if (error < 0) + goto failed_set_error; + + /* Pick the untried server with the lowest RTT. If we have outstanding + * callbacks, we stick with the server we're already using if we can. + */ + if (fc->cbi) { + _debug("cbi %u", fc->index); + if (test_bit(fc->index, &fc->untried)) + goto selected_server; + afs_put_cb_interest(afs_v2net(vnode), fc->cbi); + fc->cbi = NULL; + _debug("nocbi"); + } + + fc->index = -1; + rtt = U32_MAX; + for (i = 0; i < fc->server_list->nr_servers; i++) { + struct afs_server *s = fc->server_list->servers[i].server; + + if (!test_bit(i, &fc->untried) || !s->probe.responded) + continue; + if (s->probe.rtt < rtt) { + fc->index = i; + rtt = s->probe.rtt; + } + } + + if (fc->index == -1) + goto no_more_servers; + +selected_server: + _debug("use %d", fc->index); + __clear_bit(fc->index, &fc->untried); + /* We're starting on a different fileserver from the list. We need to * check it, create a callback intercept, find its address list and * probe its capabilities before we use it. @@ -354,10 +399,10 @@ use_server: * break request before we've finished decoding the reply and * installing the vnode. */ - fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list, - fc->index); - if (fc->ac.error < 0) - goto failed; + error = afs_register_server_cb_interest(vnode, fc->server_list, + fc->index); + if (error < 0) + goto failed_set_error; fc->cbi = afs_get_cb_interest(vnode->cb_interest); @@ -369,66 +414,88 @@ use_server: memset(&fc->ac, 0, sizeof(fc->ac)); - /* Probe the current fileserver if we haven't done so yet. */ - if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) { - fc->ac.alist = afs_get_addrlist(alist); - - if (!afs_probe_fileserver(fc)) { - switch (fc->ac.error) { - case -ENOMEM: - case -ERESTARTSYS: - case -EINTR: - goto failed; - default: - goto next_server; - } - } - } - if (!fc->ac.alist) fc->ac.alist = alist; else afs_put_addrlist(alist); - fc->ac.start = READ_ONCE(alist->index); - fc->ac.index = fc->ac.start; + fc->ac.index = -1; iterate_address: ASSERT(fc->ac.alist); - _debug("iterate %d/%d", fc->ac.index, fc->ac.alist->nr_addrs); /* Iterate over the current server's address list to try and find an * address on which it will respond to us. */ if (!afs_iterate_addresses(&fc->ac)) goto next_server; + _debug("address [%u] %u/%u", fc->index, fc->ac.index, fc->ac.alist->nr_addrs); + _leave(" = t"); return true; next_server: _debug("next"); afs_end_cursor(&fc->ac); - afs_put_cb_interest(afs_v2net(vnode), fc->cbi); - fc->cbi = NULL; - fc->index++; - if (fc->index >= fc->server_list->nr_servers) - fc->index = 0; - if (fc->index != fc->start) - goto use_server; + goto pick_server; +no_more_servers: /* That's all the servers poked to no good effect. Try again if some * of them were busy. */ if (fc->flags & AFS_FS_CURSOR_VBUSY) goto restart_from_beginning; - fc->ac.error = -EDESTADDRREQ; - goto failed; + abort_code = 0; + error = -EDESTADDRREQ; + for (i = 0; i < fc->server_list->nr_servers; i++) { + struct afs_server *s = fc->server_list->servers[i].server; + int probe_error = READ_ONCE(s->probe.error); + + switch (probe_error) { + case 0: + continue; + default: + if (error == -ETIMEDOUT || + error == -ETIME) + continue; + case -ETIMEDOUT: + case -ETIME: + if (error == -ENOMEM || + error == -ENONET) + continue; + case -ENOMEM: + case -ENONET: + if (error == -ENETUNREACH) + continue; + case -ENETUNREACH: + if (error == -EHOSTUNREACH) + continue; + case -EHOSTUNREACH: + if (error == -ECONNREFUSED) + continue; + case -ECONNREFUSED: + if (error == -ECONNRESET) + continue; + case -ECONNRESET: /* Responded, but call expired. */ + if (error == -ECONNABORTED) + continue; + case -ECONNABORTED: + abort_code = s->probe.abort_code; + error = probe_error; + continue; + } + } + + if (error == -ECONNABORTED) + error = afs_abort_to_error(abort_code); +failed_set_error: + fc->error = error; failed: fc->flags |= AFS_FS_CURSOR_STOP; afs_end_cursor(&fc->ac); - _leave(" = f [failed %d]", fc->ac.error); + _leave(" = f [failed %d]", fc->error); return false; } @@ -442,13 +509,14 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) struct afs_vnode *vnode = fc->vnode; struct afs_cb_interest *cbi = vnode->cb_interest; struct afs_addr_list *alist; + int error = fc->ac.error; _enter(""); - switch (fc->ac.error) { + switch (error) { case SHRT_MAX: if (!cbi) { - fc->ac.error = -ESTALE; + fc->error = -ESTALE; fc->flags |= AFS_FS_CURSOR_STOP; return false; } @@ -461,25 +529,26 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) afs_get_addrlist(alist); read_unlock(&cbi->server->fs_lock); if (!alist) { - fc->ac.error = -ESTALE; + fc->error = -ESTALE; fc->flags |= AFS_FS_CURSOR_STOP; return false; } memset(&fc->ac, 0, sizeof(fc->ac)); fc->ac.alist = alist; - fc->ac.start = READ_ONCE(alist->index); - fc->ac.index = fc->ac.start; + fc->ac.index = -1; goto iterate_address; case 0: default: /* Success or local failure. Stop. */ + fc->error = error; fc->flags |= AFS_FS_CURSOR_STOP; - _leave(" = f [okay/local %d]", fc->ac.error); + _leave(" = f [okay/local %d]", error); return false; case -ECONNABORTED: + fc->error = afs_abort_to_error(fc->ac.abort_code); fc->flags |= AFS_FS_CURSOR_STOP; _leave(" = f [abort]"); return false; @@ -490,6 +559,7 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) case -ETIMEDOUT: case -ETIME: _debug("no conn"); + fc->error = error; goto iterate_address; } @@ -507,12 +577,65 @@ iterate_address: } /* + * Dump cursor state in the case of the error being EDESTADDRREQ. + */ +static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc) +{ + static int count; + int i; + + if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3) + return; + count++; + + rcu_read_lock(); + + pr_notice("EDESTADDR occurred\n"); + pr_notice("FC: cbb=%x cbb2=%x fl=%hx err=%hd\n", + fc->cb_break, fc->cb_break_2, fc->flags, fc->error); + pr_notice("FC: ut=%lx ix=%d ni=%u\n", + fc->untried, fc->index, fc->nr_iterations); + + if (fc->server_list) { + const struct afs_server_list *sl = fc->server_list; + pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n", + sl->nr_servers, sl->preferred, sl->vnovol_mask); + for (i = 0; i < sl->nr_servers; i++) { + const struct afs_server *s = sl->servers[i].server; + pr_notice("FC: server fl=%lx av=%u %pU\n", + s->flags, s->addr_version, &s->uuid); + if (s->addresses) { + const struct afs_addr_list *a = + rcu_dereference(s->addresses); + pr_notice("FC: - av=%u nr=%u/%u/%u pr=%u\n", + a->version, + a->nr_ipv4, a->nr_addrs, a->max_addrs, + a->preferred); + pr_notice("FC: - pr=%lx R=%lx F=%lx\n", + a->probed, a->responded, a->failed); + if (a == fc->ac.alist) + pr_notice("FC: - current\n"); + } + } + } + + pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n", + fc->ac.tried, fc->ac.index, fc->ac.abort_code, fc->ac.error, + fc->ac.responded, fc->ac.nr_iterations); + rcu_read_unlock(); +} + +/* * Tidy up a filesystem cursor and unlock the vnode. */ int afs_end_vnode_operation(struct afs_fs_cursor *fc) { struct afs_net *net = afs_v2net(fc->vnode); - int ret; + + if (fc->error == -EDESTADDRREQ || + fc->error == -ENETUNREACH || + fc->error == -EHOSTUNREACH) + afs_dump_edestaddrreq(fc); mutex_unlock(&fc->vnode->io_lock); @@ -520,9 +643,8 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc) afs_put_cb_interest(net, fc->cbi); afs_put_serverlist(net, fc->server_list); - ret = fc->ac.error; - if (ret == -ECONNABORTED) - afs_abort_to_error(fc->ac.abort_code); + if (fc->error == -ECONNABORTED) + fc->error = afs_abort_to_error(fc->ac.abort_code); - return fc->ac.error; + return fc->error; } diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 77a83790a31f38..59970886690f1b 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -16,6 +16,7 @@ #include <net/af_rxrpc.h> #include "internal.h" #include "afs_cm.h" +#include "protocol_yfs.h" struct workqueue_struct *afs_async_calls; @@ -75,6 +76,18 @@ int afs_open_socket(struct afs_net *net) if (ret < 0) goto error_2; + srx.srx_service = YFS_CM_SERVICE; + ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); + if (ret < 0) + goto error_2; + + /* Ideally, we'd turn on service upgrade here, but we can't because + * OpenAFS is buggy and leaks the userStatus field from packet to + * packet and between FS packets and CB packets - so if we try to do an + * upgrade on an FS packet, OpenAFS will leak that into the CB packet + * it sends back to us. + */ + rxrpc_kernel_new_call_notification(socket, afs_rx_new_call, afs_rx_discard_new_call); @@ -143,6 +156,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net, INIT_WORK(&call->async_work, afs_process_async_call); init_waitqueue_head(&call->waitq); spin_lock_init(&call->state_lock); + call->_iter = &call->iter; o = atomic_inc_return(&net->nr_outstanding_calls); trace_afs_call(call, afs_call_trace_alloc, 1, o, @@ -176,6 +190,7 @@ void afs_put_call(struct afs_call *call) afs_put_server(call->net, call->cm_server); afs_put_cb_interest(call->net, call->cbi); + afs_put_addrlist(call->alist); kfree(call->request); trace_afs_call(call, afs_call_trace_free, 0, o, @@ -189,21 +204,22 @@ void afs_put_call(struct afs_call *call) } /* - * Queue the call for actual work. Returns 0 unconditionally for convenience. + * Queue the call for actual work. */ -int afs_queue_call_work(struct afs_call *call) +static void afs_queue_call_work(struct afs_call *call) { - int u = atomic_inc_return(&call->usage); + if (call->type->work) { + int u = atomic_inc_return(&call->usage); - trace_afs_call(call, afs_call_trace_work, u, - atomic_read(&call->net->nr_outstanding_calls), - __builtin_return_address(0)); + trace_afs_call(call, afs_call_trace_work, u, + atomic_read(&call->net->nr_outstanding_calls), + __builtin_return_address(0)); - INIT_WORK(&call->work, call->type->work); + INIT_WORK(&call->work, call->type->work); - if (!queue_work(afs_wq, &call->work)) - afs_put_call(call); - return 0; + if (!queue_work(afs_wq, &call->work)) + afs_put_call(call); + } } /* @@ -233,6 +249,7 @@ struct afs_call *afs_alloc_flat_call(struct afs_net *net, goto nomem_free; } + afs_extract_to_buf(call, call->reply_max); call->operation_ID = type->op; init_waitqueue_head(&call->waitq); return call; @@ -286,7 +303,7 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, offset = 0; } - iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes); + iov_iter_bvec(&msg->msg_iter, WRITE, bv, nr, bytes); } /* @@ -342,7 +359,7 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg) long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp, bool async) { - struct sockaddr_rxrpc *srx = ac->addr; + struct sockaddr_rxrpc *srx = &ac->alist->addrs[ac->index]; struct rxrpc_call *rxcall; struct msghdr msg; struct kvec iov[1]; @@ -359,6 +376,8 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, atomic_read(&call->net->nr_outstanding_calls)); call->async = async; + call->addr_ix = ac->index; + call->alist = afs_get_addrlist(ac->alist); /* Work out the length we're going to transmit. This is awkward for * calls such as FS.StoreData where there's an extra injection of data @@ -390,6 +409,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, call->debug_id); if (IS_ERR(rxcall)) { ret = PTR_ERR(rxcall); + call->error = ret; goto error_kill_call; } @@ -401,8 +421,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, - call->request_size); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = MSG_WAITALL | (call->send_pages ? MSG_MORE : 0); @@ -432,7 +451,7 @@ error_do_abort: rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); } else { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, READ, NULL, 0, 0); rxrpc_kernel_recv_data(call->net->socket, rxcall, &msg.msg_iter, false, &call->abort_code, &call->service_id); @@ -442,6 +461,8 @@ error_do_abort: call->error = ret; trace_afs_call_done(call); error_kill_call: + if (call->type->done) + call->type->done(call); afs_put_call(call); ac->error = ret; _leave(" = %d", ret); @@ -466,14 +487,12 @@ static void afs_deliver_to_call(struct afs_call *call) state == AFS_CALL_SV_AWAIT_ACK ) { if (state == AFS_CALL_SV_AWAIT_ACK) { - struct iov_iter iter; - - iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&call->iter, READ, NULL, 0, 0); ret = rxrpc_kernel_recv_data(call->net->socket, - call->rxcall, &iter, false, - &remote_abort, + call->rxcall, &call->iter, + false, &remote_abort, &call->service_id); - trace_afs_recv_data(call, 0, 0, false, ret); + trace_afs_receive_data(call, &call->iter, false, ret); if (ret == -EINPROGRESS || ret == -EAGAIN) return; @@ -485,10 +504,17 @@ static void afs_deliver_to_call(struct afs_call *call) return; } + if (call->want_reply_time && + rxrpc_kernel_get_reply_time(call->net->socket, + call->rxcall, + &call->reply_time)) + call->want_reply_time = false; + ret = call->type->deliver(call); state = READ_ONCE(call->state); switch (ret) { case 0: + afs_queue_call_work(call); if (state == AFS_CALL_CL_PROC_REPLY) { if (call->cbi) set_bit(AFS_SERVER_FL_MAY_HAVE_CB, @@ -500,7 +526,6 @@ static void afs_deliver_to_call(struct afs_call *call) case -EINPROGRESS: case -EAGAIN: goto out; - case -EIO: case -ECONNABORTED: ASSERTCMP(state, ==, AFS_CALL_COMPLETE); goto done; @@ -509,6 +534,10 @@ static void afs_deliver_to_call(struct afs_call *call) rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, ret, "KIV"); goto local_abort; + case -EIO: + pr_err("kAFS: Call %u in bad state %u\n", + call->debug_id, state); + /* Fall through */ case -ENODATA: case -EBADMSG: case -EMSGSIZE: @@ -517,12 +546,14 @@ static void afs_deliver_to_call(struct afs_call *call) if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, -EBADMSG, "KUM"); + abort_code, ret, "KUM"); goto local_abort; } } done: + if (call->type->done) + call->type->done(call); if (state == AFS_CALL_COMPLETE && call->incoming) afs_put_call(call); out: @@ -728,6 +759,7 @@ void afs_charge_preallocation(struct work_struct *work) call->async = true; call->state = AFS_CALL_SV_AWAIT_OP_ID; init_waitqueue_head(&call->waitq); + afs_extract_to_tmp(call); } if (rxrpc_kernel_charge_accept(net->socket, @@ -773,18 +805,15 @@ static int afs_deliver_cm_op_id(struct afs_call *call) { int ret; - _enter("{%zu}", call->offset); - - ASSERTCMP(call->offset, <, 4); + _enter("{%zu}", iov_iter_count(call->_iter)); /* the operation ID forms the first four bytes of the request data */ - ret = afs_extract_data(call, &call->tmp, 4, true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; call->operation_ID = ntohl(call->tmp); afs_set_call_state(call, AFS_CALL_SV_AWAIT_OP_ID, AFS_CALL_SV_AWAIT_REQUEST); - call->offset = 0; /* ask the cache manager to route the call (it'll change the call type * if successful) */ @@ -825,7 +854,7 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, WRITE, NULL, 0, 0); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -864,7 +893,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -888,30 +917,19 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) /* * Extract a piece of data from the received data socket buffers. */ -int afs_extract_data(struct afs_call *call, void *buf, size_t count, - bool want_more) +int afs_extract_data(struct afs_call *call, bool want_more) { struct afs_net *net = call->net; - struct iov_iter iter; - struct kvec iov; + struct iov_iter *iter = call->_iter; enum afs_call_state state; u32 remote_abort = 0; int ret; - _enter("{%s,%zu},,%zu,%d", - call->type->name, call->offset, count, want_more); - - ASSERTCMP(call->offset, <=, count); - - iov.iov_base = buf + call->offset; - iov.iov_len = count - call->offset; - iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset); + _enter("{%s,%zu},%d", call->type->name, iov_iter_count(iter), want_more); - ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter, + ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter, want_more, &remote_abort, &call->service_id); - call->offset += (count - call->offset) - iov_iter_count(&iter); - trace_afs_recv_data(call, count, call->offset, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; @@ -926,7 +944,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, break; case AFS_CALL_COMPLETE: kdebug("prem complete %d", call->error); - return -EIO; + return afs_io_error(call, afs_io_error_extract); default: break; } @@ -940,8 +958,9 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, /* * Log protocol error production. */ -noinline int afs_protocol_error(struct afs_call *call, int error) +noinline int afs_protocol_error(struct afs_call *call, int error, + enum afs_eproto_cause cause) { - trace_afs_protocol_error(call, error, __builtin_return_address(0)); + trace_afs_protocol_error(call, error, cause); return error; } diff --git a/fs/afs/security.c b/fs/afs/security.c index 81dfedb7879ff9..5f58a9a17e694a 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -126,7 +126,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, bool changed = false; int i, j; - _enter("{%x:%u},%x,%x", + _enter("{%llx:%llu},%x,%x", vnode->fid.vid, vnode->fid.vnode, key_serial(key), caller_access); rcu_read_lock(); @@ -147,7 +147,8 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, break; } - if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) { + if (afs_cb_is_broken(cb_break, vnode, + vnode->cb_interest)) { changed = true; break; } @@ -177,7 +178,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } } - if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) + if (afs_cb_is_broken(cb_break, vnode, vnode->cb_interest)) goto someone_else_changed_it; /* We need a ref on any permits list we want to copy as we'll have to @@ -256,7 +257,7 @@ found: spin_lock(&vnode->lock); zap = rcu_access_pointer(vnode->permit_cache); - if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) && + if (!afs_cb_is_broken(cb_break, vnode, vnode->cb_interest) && zap == permits) rcu_assign_pointer(vnode->permit_cache, replacement); else @@ -289,7 +290,7 @@ int afs_check_permit(struct afs_vnode *vnode, struct key *key, bool valid = false; int i, ret; - _enter("{%x:%u},%x", + _enter("{%llx:%llu},%x", vnode->fid.vid, vnode->fid.vnode, key_serial(key)); /* check the permits to see if we've got one yet */ @@ -349,7 +350,7 @@ int afs_permission(struct inode *inode, int mask) if (mask & MAY_NOT_BLOCK) return -ECHILD; - _enter("{{%x:%u},%lx},%x,", + _enter("{{%llx:%llu},%lx},%x,", vnode->fid.vid, vnode->fid.vnode, vnode->flags, mask); key = afs_request_key(vnode->volume->cell); diff --git a/fs/afs/server.c b/fs/afs/server.c index 1d329e6981d515..642afa2e9783c4 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -13,6 +13,7 @@ #include <linux/slab.h> #include "afs_fs.h" #include "internal.h" +#include "protocol_yfs.h" static unsigned afs_server_gc_delay = 10; /* Server record timeout in seconds */ static unsigned afs_server_update_delay = 30; /* Time till VLDB recheck in secs */ @@ -230,6 +231,8 @@ static struct afs_server *afs_alloc_server(struct afs_net *net, rwlock_init(&server->fs_lock); INIT_HLIST_HEAD(&server->cb_volumes); rwlock_init(&server->cb_break_lock); + init_waitqueue_head(&server->probe_wq); + spin_lock_init(&server->probe_lock); afs_inc_servers_outstanding(net); _leave(" = %p", server); @@ -246,41 +249,23 @@ enomem: static struct afs_addr_list *afs_vl_lookup_addrs(struct afs_cell *cell, struct key *key, const uuid_t *uuid) { - struct afs_addr_cursor ac; - struct afs_addr_list *alist; + struct afs_vl_cursor vc; + struct afs_addr_list *alist = NULL; int ret; - ret = afs_set_vl_cursor(&ac, cell); - if (ret < 0) - return ERR_PTR(ret); - - while (afs_iterate_addresses(&ac)) { - if (test_bit(ac.index, &ac.alist->yfs)) - alist = afs_yfsvl_get_endpoints(cell->net, &ac, key, uuid); - else - alist = afs_vl_get_addrs_u(cell->net, &ac, key, uuid); - switch (ac.error) { - case 0: - afs_end_cursor(&ac); - return alist; - case -ECONNABORTED: - ac.error = afs_abort_to_error(ac.abort_code); - goto error; - case -ENOMEM: - case -ENONET: - goto error; - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - break; - default: - ac.error = -EIO; - goto error; + ret = -ERESTARTSYS; + if (afs_begin_vlserver_operation(&vc, cell, key)) { + while (afs_select_vlserver(&vc)) { + if (test_bit(AFS_VLSERVER_FL_IS_YFS, &vc.server->flags)) + alist = afs_yfsvl_get_endpoints(&vc, uuid); + else + alist = afs_vl_get_addrs_u(&vc, uuid); } + + ret = afs_end_vlserver_operation(&vc); } -error: - return ERR_PTR(afs_end_cursor(&ac)); + return ret < 0 ? ERR_PTR(ret) : alist; } /* @@ -382,9 +367,7 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) struct afs_addr_list *alist = rcu_access_pointer(server->addresses); struct afs_addr_cursor ac = { .alist = alist, - .start = alist->index, - .index = 0, - .addr = &alist->addrs[alist->index], + .index = alist->preferred, .error = 0, }; _enter("%p", server); @@ -392,6 +375,9 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) afs_fs_give_up_all_callbacks(net, server, &ac, NULL); + wait_var_event(&server->probe_outstanding, + atomic_read(&server->probe_outstanding) == 0); + call_rcu(&server->rcu, afs_server_rcu); afs_dec_servers_outstanding(net); } @@ -525,99 +511,6 @@ void afs_purge_servers(struct afs_net *net) } /* - * Probe a fileserver to find its capabilities. - * - * TODO: Try service upgrade. - */ -static bool afs_do_probe_fileserver(struct afs_fs_cursor *fc) -{ - _enter(""); - - fc->ac.addr = NULL; - fc->ac.start = READ_ONCE(fc->ac.alist->index); - fc->ac.index = fc->ac.start; - fc->ac.error = 0; - fc->ac.begun = false; - - while (afs_iterate_addresses(&fc->ac)) { - afs_fs_get_capabilities(afs_v2net(fc->vnode), fc->cbi->server, - &fc->ac, fc->key); - switch (fc->ac.error) { - case 0: - afs_end_cursor(&fc->ac); - set_bit(AFS_SERVER_FL_PROBED, &fc->cbi->server->flags); - return true; - case -ECONNABORTED: - fc->ac.error = afs_abort_to_error(fc->ac.abort_code); - goto error; - case -ENOMEM: - case -ENONET: - goto error; - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - case -ETIMEDOUT: - case -ETIME: - break; - default: - fc->ac.error = -EIO; - goto error; - } - } - -error: - afs_end_cursor(&fc->ac); - return false; -} - -/* - * If we haven't already, try probing the fileserver to get its capabilities. - * We try not to instigate parallel probes, but it's possible that the parallel - * probes will fail due to authentication failure when ours would succeed. - * - * TODO: Try sending an anonymous probe if an authenticated probe fails. - */ -bool afs_probe_fileserver(struct afs_fs_cursor *fc) -{ - bool success; - int ret, retries = 0; - - _enter(""); - -retry: - if (test_bit(AFS_SERVER_FL_PROBED, &fc->cbi->server->flags)) { - _leave(" = t"); - return true; - } - - if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &fc->cbi->server->flags)) { - success = afs_do_probe_fileserver(fc); - clear_bit_unlock(AFS_SERVER_FL_PROBING, &fc->cbi->server->flags); - wake_up_bit(&fc->cbi->server->flags, AFS_SERVER_FL_PROBING); - _leave(" = t"); - return success; - } - - _debug("wait"); - ret = wait_on_bit(&fc->cbi->server->flags, AFS_SERVER_FL_PROBING, - TASK_INTERRUPTIBLE); - if (ret == -ERESTARTSYS) { - fc->ac.error = ret; - _leave(" = f [%d]", ret); - return false; - } - - retries++; - if (retries == 4) { - fc->ac.error = -ESTALE; - _leave(" = f [stale]"); - return false; - } - _debug("retry"); - goto retry; -} - -/* * Get an update for a server's address list. */ static noinline bool afs_update_server_record(struct afs_fs_cursor *fc, struct afs_server *server) diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 8a5760aa583213..95d0761cdb34ef 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -118,11 +118,11 @@ bool afs_annotate_server_list(struct afs_server_list *new, return false; changed: - /* Maintain the same current server as before if possible. */ - cur = old->servers[old->index].server; + /* Maintain the same preferred server as before if possible. */ + cur = old->servers[old->preferred].server; for (j = 0; j < new->nr_servers; j++) { if (new->servers[j].server == cur) { - new->index = j; + new->preferred = j; break; } } diff --git a/fs/afs/super.c b/fs/afs/super.c index 4d3e274207fb7a..dcd07fe99871b9 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -406,10 +406,11 @@ static int afs_fill_super(struct super_block *sb, inode = afs_iget_pseudo_dir(sb, true); sb->s_flags |= SB_RDONLY; } else { - sprintf(sb->s_id, "%u", as->volume->vid); + sprintf(sb->s_id, "%llu", as->volume->vid); afs_activate_volume(as->volume); fid.vid = as->volume->vid; fid.vnode = 1; + fid.vnode_hi = 0; fid.unique = 1; inode = afs_iget(sb, params->key, &fid, NULL, NULL, NULL); } @@ -663,7 +664,7 @@ static void afs_destroy_inode(struct inode *inode) { struct afs_vnode *vnode = AFS_FS_I(inode); - _enter("%p{%x:%u}", inode, vnode->fid.vid, vnode->fid.vnode); + _enter("%p{%llx:%llu}", inode, vnode->fid.vid, vnode->fid.vnode); _debug("DESTROY INODE %p", inode); diff --git a/fs/afs/vl_list.c b/fs/afs/vl_list.c new file mode 100644 index 00000000000000..b4f1a84519b952 --- /dev/null +++ b/fs/afs/vl_list.c @@ -0,0 +1,340 @@ +/* AFS vlserver list management. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * 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> +#include <linux/slab.h> +#include "internal.h" + +struct afs_vlserver *afs_alloc_vlserver(const char *name, size_t name_len, + unsigned short port) +{ + struct afs_vlserver *vlserver; + + vlserver = kzalloc(struct_size(vlserver, name, name_len + 1), + GFP_KERNEL); + if (vlserver) { + atomic_set(&vlserver->usage, 1); + rwlock_init(&vlserver->lock); + init_waitqueue_head(&vlserver->probe_wq); + spin_lock_init(&vlserver->probe_lock); + vlserver->name_len = name_len; + vlserver->port = port; + memcpy(vlserver->name, name, name_len); + } + return vlserver; +} + +static void afs_vlserver_rcu(struct rcu_head *rcu) +{ + struct afs_vlserver *vlserver = container_of(rcu, struct afs_vlserver, rcu); + + afs_put_addrlist(rcu_access_pointer(vlserver->addresses)); + kfree_rcu(vlserver, rcu); +} + +void afs_put_vlserver(struct afs_net *net, struct afs_vlserver *vlserver) +{ + if (vlserver) { + unsigned int u = atomic_dec_return(&vlserver->usage); + //_debug("VL PUT %p{%u}", vlserver, u); + + if (u == 0) + call_rcu(&vlserver->rcu, afs_vlserver_rcu); + } +} + +struct afs_vlserver_list *afs_alloc_vlserver_list(unsigned int nr_servers) +{ + struct afs_vlserver_list *vllist; + + vllist = kzalloc(struct_size(vllist, servers, nr_servers), GFP_KERNEL); + if (vllist) { + atomic_set(&vllist->usage, 1); + rwlock_init(&vllist->lock); + } + + return vllist; +} + +void afs_put_vlserverlist(struct afs_net *net, struct afs_vlserver_list *vllist) +{ + if (vllist) { + unsigned int u = atomic_dec_return(&vllist->usage); + + //_debug("VLLS PUT %p{%u}", vllist, u); + if (u == 0) { + int i; + + for (i = 0; i < vllist->nr_servers; i++) { + afs_put_vlserver(net, vllist->servers[i].server); + } + kfree_rcu(vllist, rcu); + } + } +} + +static u16 afs_extract_le16(const u8 **_b) +{ + u16 val; + + val = (u16)*(*_b)++ << 0; + val |= (u16)*(*_b)++ << 8; + return val; +} + +/* + * Build a VL server address list from a DNS queried server list. + */ +static struct afs_addr_list *afs_extract_vl_addrs(const u8 **_b, const u8 *end, + u8 nr_addrs, u16 port) +{ + struct afs_addr_list *alist; + const u8 *b = *_b; + int ret = -EINVAL; + + alist = afs_alloc_addrlist(nr_addrs, VL_SERVICE, port); + if (!alist) + return ERR_PTR(-ENOMEM); + if (nr_addrs == 0) + return alist; + + for (; nr_addrs > 0 && end - b >= nr_addrs; nr_addrs--) { + struct dns_server_list_v1_address hdr; + __be32 x[4]; + + hdr.address_type = *b++; + + switch (hdr.address_type) { + case DNS_ADDRESS_IS_IPV4: + if (end - b < 4) { + _leave(" = -EINVAL [short inet]"); + goto error; + } + memcpy(x, b, 4); + afs_merge_fs_addr4(alist, x[0], port); + b += 4; + break; + + case DNS_ADDRESS_IS_IPV6: + if (end - b < 16) { + _leave(" = -EINVAL [short inet6]"); + goto error; + } + memcpy(x, b, 16); + afs_merge_fs_addr6(alist, x, port); + b += 16; + break; + + default: + _leave(" = -EADDRNOTAVAIL [unknown af %u]", + hdr.address_type); + ret = -EADDRNOTAVAIL; + goto error; + } + } + + /* Start with IPv6 if available. */ + if (alist->nr_ipv4 < alist->nr_addrs) + alist->preferred = alist->nr_ipv4; + + *_b = b; + return alist; + +error: + *_b = b; + afs_put_addrlist(alist); + return ERR_PTR(ret); +} + +/* + * Build a VL server list from a DNS queried server list. + */ +struct afs_vlserver_list *afs_extract_vlserver_list(struct afs_cell *cell, + const void *buffer, + size_t buffer_size) +{ + const struct dns_server_list_v1_header *hdr = buffer; + struct dns_server_list_v1_server bs; + struct afs_vlserver_list *vllist, *previous; + struct afs_addr_list *addrs; + struct afs_vlserver *server; + const u8 *b = buffer, *end = buffer + buffer_size; + int ret = -ENOMEM, nr_servers, i, j; + + _enter(""); + + /* Check that it's a server list, v1 */ + if (end - b < sizeof(*hdr) || + hdr->hdr.content != DNS_PAYLOAD_IS_SERVER_LIST || + hdr->hdr.version != 1) { + pr_notice("kAFS: Got DNS record [%u,%u] len %zu\n", + hdr->hdr.content, hdr->hdr.version, end - b); + ret = -EDESTADDRREQ; + goto dump; + } + + nr_servers = hdr->nr_servers; + + vllist = afs_alloc_vlserver_list(nr_servers); + if (!vllist) + return ERR_PTR(-ENOMEM); + + vllist->source = (hdr->source < NR__dns_record_source) ? + hdr->source : NR__dns_record_source; + vllist->status = (hdr->status < NR__dns_lookup_status) ? + hdr->status : NR__dns_lookup_status; + + read_lock(&cell->vl_servers_lock); + previous = afs_get_vlserverlist( + rcu_dereference_protected(cell->vl_servers, + lockdep_is_held(&cell->vl_servers_lock))); + read_unlock(&cell->vl_servers_lock); + + b += sizeof(*hdr); + while (end - b >= sizeof(bs)) { + bs.name_len = afs_extract_le16(&b); + bs.priority = afs_extract_le16(&b); + bs.weight = afs_extract_le16(&b); + bs.port = afs_extract_le16(&b); + bs.source = *b++; + bs.status = *b++; + bs.protocol = *b++; + bs.nr_addrs = *b++; + + _debug("extract %u %u %u %u %u %u %*.*s", + bs.name_len, bs.priority, bs.weight, + bs.port, bs.protocol, bs.nr_addrs, + bs.name_len, bs.name_len, b); + + if (end - b < bs.name_len) + break; + + ret = -EPROTONOSUPPORT; + if (bs.protocol == DNS_SERVER_PROTOCOL_UNSPECIFIED) { + bs.protocol = DNS_SERVER_PROTOCOL_UDP; + } else if (bs.protocol != DNS_SERVER_PROTOCOL_UDP) { + _leave(" = [proto %u]", bs.protocol); + goto error; + } + + if (bs.port == 0) + bs.port = AFS_VL_PORT; + if (bs.source > NR__dns_record_source) + bs.source = NR__dns_record_source; + if (bs.status > NR__dns_lookup_status) + bs.status = NR__dns_lookup_status; + + server = NULL; + if (previous) { + /* See if we can update an old server record */ + for (i = 0; i < previous->nr_servers; i++) { + struct afs_vlserver *p = previous->servers[i].server; + + if (p->name_len == bs.name_len && + p->port == bs.port && + strncasecmp(b, p->name, bs.name_len) == 0) { + server = afs_get_vlserver(p); + break; + } + } + } + + if (!server) { + ret = -ENOMEM; + server = afs_alloc_vlserver(b, bs.name_len, bs.port); + if (!server) + goto error; + } + + b += bs.name_len; + + /* Extract the addresses - note that we can't skip this as we + * have to advance the payload pointer. + */ + addrs = afs_extract_vl_addrs(&b, end, bs.nr_addrs, bs.port); + if (IS_ERR(addrs)) { + ret = PTR_ERR(addrs); + goto error_2; + } + + if (vllist->nr_servers >= nr_servers) { + _debug("skip %u >= %u", vllist->nr_servers, nr_servers); + afs_put_addrlist(addrs); + afs_put_vlserver(cell->net, server); + continue; + } + + addrs->source = bs.source; + addrs->status = bs.status; + + if (addrs->nr_addrs == 0) { + afs_put_addrlist(addrs); + if (!rcu_access_pointer(server->addresses)) { + afs_put_vlserver(cell->net, server); + continue; + } + } else { + struct afs_addr_list *old = addrs; + + write_lock(&server->lock); + rcu_swap_protected(server->addresses, old, + lockdep_is_held(&server->lock)); + write_unlock(&server->lock); + afs_put_addrlist(old); + } + + + /* TODO: Might want to check for duplicates */ + + /* Insertion-sort by priority and weight */ + for (j = 0; j < vllist->nr_servers; j++) { + if (bs.priority < vllist->servers[j].priority) + break; /* Lower preferable */ + if (bs.priority == vllist->servers[j].priority && + bs.weight > vllist->servers[j].weight) + break; /* Higher preferable */ + } + + if (j < vllist->nr_servers) { + memmove(vllist->servers + j + 1, + vllist->servers + j, + (vllist->nr_servers - j) * sizeof(struct afs_vlserver_entry)); + } + + clear_bit(AFS_VLSERVER_FL_PROBED, &server->flags); + + vllist->servers[j].priority = bs.priority; + vllist->servers[j].weight = bs.weight; + vllist->servers[j].server = server; + vllist->nr_servers++; + } + + if (b != end) { + _debug("parse error %zd", b - end); + goto error; + } + + afs_put_vlserverlist(cell->net, previous); + _leave(" = ok [%u]", vllist->nr_servers); + return vllist; + +error_2: + afs_put_vlserver(cell->net, server); +error: + afs_put_vlserverlist(cell->net, vllist); + afs_put_vlserverlist(cell->net, previous); +dump: + if (ret != -ENOMEM) { + printk(KERN_DEBUG "DNS: at %zu\n", (const void *)b - buffer); + print_hex_dump_bytes("DNS: ", DUMP_PREFIX_NONE, buffer, buffer_size); + } + return ERR_PTR(ret); +} diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c new file mode 100644 index 00000000000000..c0f616bd70cba3 --- /dev/null +++ b/fs/afs/vl_probe.c @@ -0,0 +1,273 @@ +/* AFS vlserver probing + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/sched.h> +#include <linux/slab.h> +#include "afs_fs.h" +#include "internal.h" +#include "protocol_yfs.h" + +static bool afs_vl_probe_done(struct afs_vlserver *server) +{ + if (!atomic_dec_and_test(&server->probe_outstanding)) + return false; + + wake_up_var(&server->probe_outstanding); + clear_bit_unlock(AFS_VLSERVER_FL_PROBING, &server->flags); + wake_up_bit(&server->flags, AFS_VLSERVER_FL_PROBING); + return true; +} + +/* + * Process the result of probing a vlserver. This is called after successful + * or failed delivery of an VL.GetCapabilities operation. + */ +void afs_vlserver_probe_result(struct afs_call *call) +{ + struct afs_addr_list *alist = call->alist; + struct afs_vlserver *server = call->reply[0]; + unsigned int server_index = (long)call->reply[1]; + unsigned int index = call->addr_ix; + unsigned int rtt = UINT_MAX; + bool have_result = false; + u64 _rtt; + int ret = call->error; + + _enter("%s,%u,%u,%d,%d", server->name, server_index, index, ret, call->abort_code); + + spin_lock(&server->probe_lock); + + switch (ret) { + case 0: + server->probe.error = 0; + goto responded; + case -ECONNABORTED: + if (!server->probe.responded) { + server->probe.abort_code = call->abort_code; + server->probe.error = ret; + } + goto responded; + case -ENOMEM: + case -ENONET: + server->probe.local_failure = true; + afs_io_error(call, afs_io_error_vl_probe_fail); + goto out; + case -ECONNRESET: /* Responded, but call expired. */ + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + case -ETIMEDOUT: + case -ETIME: + default: + clear_bit(index, &alist->responded); + set_bit(index, &alist->failed); + if (!server->probe.responded && + (server->probe.error == 0 || + server->probe.error == -ETIMEDOUT || + server->probe.error == -ETIME)) + server->probe.error = ret; + afs_io_error(call, afs_io_error_vl_probe_fail); + goto out; + } + +responded: + set_bit(index, &alist->responded); + clear_bit(index, &alist->failed); + + if (call->service_id == YFS_VL_SERVICE) { + server->probe.is_yfs = true; + set_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); + alist->addrs[index].srx_service = call->service_id; + } else { + server->probe.not_yfs = true; + if (!server->probe.is_yfs) { + clear_bit(AFS_VLSERVER_FL_IS_YFS, &server->flags); + alist->addrs[index].srx_service = call->service_id; + } + } + + /* Get the RTT and scale it to fit into a 32-bit value that represents + * over a minute of time so that we can access it with one instruction + * on a 32-bit system. + */ + _rtt = rxrpc_kernel_get_rtt(call->net->socket, call->rxcall); + _rtt /= 64; + rtt = (_rtt > UINT_MAX) ? UINT_MAX : _rtt; + if (rtt < server->probe.rtt) { + server->probe.rtt = rtt; + alist->preferred = index; + have_result = true; + } + + smp_wmb(); /* Set rtt before responded. */ + server->probe.responded = true; + set_bit(AFS_VLSERVER_FL_PROBED, &server->flags); +out: + spin_unlock(&server->probe_lock); + + _debug("probe [%u][%u] %pISpc rtt=%u ret=%d", + server_index, index, &alist->addrs[index].transport, + (unsigned int)rtt, ret); + + have_result |= afs_vl_probe_done(server); + if (have_result) { + server->probe.have_result = true; + wake_up_var(&server->probe.have_result); + wake_up_all(&server->probe_wq); + } +} + +/* + * Probe all of a vlserver's addresses to find out the best route and to + * query its capabilities. + */ +static int afs_do_probe_vlserver(struct afs_net *net, + struct afs_vlserver *server, + struct key *key, + unsigned int server_index) +{ + struct afs_addr_cursor ac = { + .index = 0, + }; + int ret; + + _enter("%s", server->name); + + read_lock(&server->lock); + ac.alist = rcu_dereference_protected(server->addresses, + lockdep_is_held(&server->lock)); + read_unlock(&server->lock); + + atomic_set(&server->probe_outstanding, ac.alist->nr_addrs); + memset(&server->probe, 0, sizeof(server->probe)); + server->probe.rtt = UINT_MAX; + + for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { + ret = afs_vl_get_capabilities(net, &ac, key, server, + server_index, true); + if (ret != -EINPROGRESS) { + afs_vl_probe_done(server); + return ret; + } + } + + return 0; +} + +/* + * Send off probes to all unprobed servers. + */ +int afs_send_vl_probes(struct afs_net *net, struct key *key, + struct afs_vlserver_list *vllist) +{ + struct afs_vlserver *server; + int i, ret; + + for (i = 0; i < vllist->nr_servers; i++) { + server = vllist->servers[i].server; + if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags)) + continue; + + if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags)) { + ret = afs_do_probe_vlserver(net, server, key, i); + if (ret) + return ret; + } + } + + return 0; +} + +/* + * Wait for the first as-yet untried server to respond. + */ +int afs_wait_for_vl_probes(struct afs_vlserver_list *vllist, + unsigned long untried) +{ + struct wait_queue_entry *waits; + struct afs_vlserver *server; + unsigned int rtt = UINT_MAX; + bool have_responders = false; + int pref = -1, i; + + _enter("%u,%lx", vllist->nr_servers, untried); + + /* Only wait for servers that have a probe outstanding. */ + for (i = 0; i < vllist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = vllist->servers[i].server; + if (!test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) + __clear_bit(i, &untried); + if (server->probe.responded) + have_responders = true; + } + } + if (have_responders || !untried) + return 0; + + waits = kmalloc(array_size(vllist->nr_servers, sizeof(*waits)), GFP_KERNEL); + if (!waits) + return -ENOMEM; + + for (i = 0; i < vllist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = vllist->servers[i].server; + init_waitqueue_entry(&waits[i], current); + add_wait_queue(&server->probe_wq, &waits[i]); + } + } + + for (;;) { + bool still_probing = false; + + set_current_state(TASK_INTERRUPTIBLE); + for (i = 0; i < vllist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = vllist->servers[i].server; + if (server->probe.responded) + goto stop; + if (test_bit(AFS_VLSERVER_FL_PROBING, &server->flags)) + still_probing = true; + } + } + + if (!still_probing || unlikely(signal_pending(current))) + goto stop; + schedule(); + } + +stop: + set_current_state(TASK_RUNNING); + + for (i = 0; i < vllist->nr_servers; i++) { + if (test_bit(i, &untried)) { + server = vllist->servers[i].server; + if (server->probe.responded && + server->probe.rtt < rtt) { + pref = i; + rtt = server->probe.rtt; + } + + remove_wait_queue(&server->probe_wq, &waits[i]); + } + } + + kfree(waits); + + if (pref == -1 && signal_pending(current)) + return -ERESTARTSYS; + + if (pref >= 0) + vllist->preferred = pref; + + _leave(" = 0 [%u]", pref); + return 0; +} diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c new file mode 100644 index 00000000000000..b64a284b99d272 --- /dev/null +++ b/fs/afs/vl_rotate.c @@ -0,0 +1,355 @@ +/* Handle vlserver selection and rotation. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/sched/signal.h> +#include "internal.h" +#include "afs_vl.h" + +/* + * Begin an operation on a volume location server. + */ +bool afs_begin_vlserver_operation(struct afs_vl_cursor *vc, struct afs_cell *cell, + struct key *key) +{ + memset(vc, 0, sizeof(*vc)); + vc->cell = cell; + vc->key = key; + vc->error = -EDESTADDRREQ; + vc->ac.error = SHRT_MAX; + + if (signal_pending(current)) { + vc->error = -EINTR; + vc->flags |= AFS_VL_CURSOR_STOP; + return false; + } + + return true; +} + +/* + * Begin iteration through a server list, starting with the last used server if + * possible, or the last recorded good server if not. + */ +static bool afs_start_vl_iteration(struct afs_vl_cursor *vc) +{ + struct afs_cell *cell = vc->cell; + + if (wait_on_bit(&cell->flags, AFS_CELL_FL_NO_LOOKUP_YET, + TASK_INTERRUPTIBLE)) { + vc->error = -ERESTARTSYS; + return false; + } + + read_lock(&cell->vl_servers_lock); + vc->server_list = afs_get_vlserverlist( + rcu_dereference_protected(cell->vl_servers, + lockdep_is_held(&cell->vl_servers_lock))); + read_unlock(&cell->vl_servers_lock); + if (!vc->server_list || !vc->server_list->nr_servers) + return false; + + vc->untried = (1UL << vc->server_list->nr_servers) - 1; + vc->index = -1; + return true; +} + +/* + * Select the vlserver to use. May be called multiple times to rotate + * through the vlservers. + */ +bool afs_select_vlserver(struct afs_vl_cursor *vc) +{ + struct afs_addr_list *alist; + struct afs_vlserver *vlserver; + u32 rtt; + int error = vc->ac.error, abort_code, i; + + _enter("%lx[%d],%lx[%d],%d,%d", + vc->untried, vc->index, + vc->ac.tried, vc->ac.index, + error, vc->ac.abort_code); + + if (vc->flags & AFS_VL_CURSOR_STOP) { + _leave(" = f [stopped]"); + return false; + } + + vc->nr_iterations++; + + /* Evaluate the result of the previous operation, if there was one. */ + switch (error) { + case SHRT_MAX: + goto start; + + default: + case 0: + /* Success or local failure. Stop. */ + vc->error = error; + vc->flags |= AFS_VL_CURSOR_STOP; + _leave(" = f [okay/local %d]", vc->ac.error); + return false; + + case -ECONNABORTED: + /* The far side rejected the operation on some grounds. This + * might involve the server being busy or the volume having been moved. + */ + switch (vc->ac.abort_code) { + case AFSVL_IO: + case AFSVL_BADVOLOPER: + case AFSVL_NOMEM: + /* The server went weird. */ + vc->error = -EREMOTEIO; + //write_lock(&vc->cell->vl_servers_lock); + //vc->server_list->weird_mask |= 1 << vc->index; + //write_unlock(&vc->cell->vl_servers_lock); + goto next_server; + + default: + vc->error = afs_abort_to_error(vc->ac.abort_code); + goto failed; + } + + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + case -ETIMEDOUT: + case -ETIME: + _debug("no conn %d", error); + vc->error = error; + goto iterate_address; + + case -ECONNRESET: + _debug("call reset"); + vc->error = error; + vc->flags |= AFS_VL_CURSOR_RETRY; + goto next_server; + } + +restart_from_beginning: + _debug("restart"); + afs_end_cursor(&vc->ac); + afs_put_vlserverlist(vc->cell->net, vc->server_list); + vc->server_list = NULL; + if (vc->flags & AFS_VL_CURSOR_RETRIED) + goto failed; + vc->flags |= AFS_VL_CURSOR_RETRIED; +start: + _debug("start"); + + if (!afs_start_vl_iteration(vc)) + goto failed; + + error = afs_send_vl_probes(vc->cell->net, vc->key, vc->server_list); + if (error < 0) + goto failed_set_error; + +pick_server: + _debug("pick [%lx]", vc->untried); + + error = afs_wait_for_vl_probes(vc->server_list, vc->untried); + if (error < 0) + goto failed_set_error; + + /* Pick the untried server with the lowest RTT. */ + vc->index = vc->server_list->preferred; + if (test_bit(vc->index, &vc->untried)) + goto selected_server; + + vc->index = -1; + rtt = U32_MAX; + for (i = 0; i < vc->server_list->nr_servers; i++) { + struct afs_vlserver *s = vc->server_list->servers[i].server; + + if (!test_bit(i, &vc->untried) || !s->probe.responded) + continue; + if (s->probe.rtt < rtt) { + vc->index = i; + rtt = s->probe.rtt; + } + } + + if (vc->index == -1) + goto no_more_servers; + +selected_server: + _debug("use %d", vc->index); + __clear_bit(vc->index, &vc->untried); + + /* We're starting on a different vlserver from the list. We need to + * check it, find its address list and probe its capabilities before we + * use it. + */ + ASSERTCMP(vc->ac.alist, ==, NULL); + vlserver = vc->server_list->servers[vc->index].server; + vc->server = vlserver; + + _debug("USING VLSERVER: %s", vlserver->name); + + read_lock(&vlserver->lock); + alist = rcu_dereference_protected(vlserver->addresses, + lockdep_is_held(&vlserver->lock)); + afs_get_addrlist(alist); + read_unlock(&vlserver->lock); + + memset(&vc->ac, 0, sizeof(vc->ac)); + + if (!vc->ac.alist) + vc->ac.alist = alist; + else + afs_put_addrlist(alist); + + vc->ac.index = -1; + +iterate_address: + ASSERT(vc->ac.alist); + /* Iterate over the current server's address list to try and find an + * address on which it will respond to us. + */ + if (!afs_iterate_addresses(&vc->ac)) + goto next_server; + + _debug("VL address %d/%d", vc->ac.index, vc->ac.alist->nr_addrs); + + _leave(" = t %pISpc", &vc->ac.alist->addrs[vc->ac.index].transport); + return true; + +next_server: + _debug("next"); + afs_end_cursor(&vc->ac); + goto pick_server; + +no_more_servers: + /* That's all the servers poked to no good effect. Try again if some + * of them were busy. + */ + if (vc->flags & AFS_VL_CURSOR_RETRY) + goto restart_from_beginning; + + abort_code = 0; + error = -EDESTADDRREQ; + for (i = 0; i < vc->server_list->nr_servers; i++) { + struct afs_vlserver *s = vc->server_list->servers[i].server; + int probe_error = READ_ONCE(s->probe.error); + + switch (probe_error) { + case 0: + continue; + default: + if (error == -ETIMEDOUT || + error == -ETIME) + continue; + case -ETIMEDOUT: + case -ETIME: + if (error == -ENOMEM || + error == -ENONET) + continue; + case -ENOMEM: + case -ENONET: + if (error == -ENETUNREACH) + continue; + case -ENETUNREACH: + if (error == -EHOSTUNREACH) + continue; + case -EHOSTUNREACH: + if (error == -ECONNREFUSED) + continue; + case -ECONNREFUSED: + if (error == -ECONNRESET) + continue; + case -ECONNRESET: /* Responded, but call expired. */ + if (error == -ECONNABORTED) + continue; + case -ECONNABORTED: + abort_code = s->probe.abort_code; + error = probe_error; + continue; + } + } + + if (error == -ECONNABORTED) + error = afs_abort_to_error(abort_code); + +failed_set_error: + vc->error = error; +failed: + vc->flags |= AFS_VL_CURSOR_STOP; + afs_end_cursor(&vc->ac); + _leave(" = f [failed %d]", vc->error); + return false; +} + +/* + * Dump cursor state in the case of the error being EDESTADDRREQ. + */ +static void afs_vl_dump_edestaddrreq(const struct afs_vl_cursor *vc) +{ + static int count; + int i; + + if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3) + return; + count++; + + rcu_read_lock(); + pr_notice("EDESTADDR occurred\n"); + pr_notice("VC: ut=%lx ix=%u ni=%hu fl=%hx err=%hd\n", + vc->untried, vc->index, vc->nr_iterations, vc->flags, vc->error); + + if (vc->server_list) { + const struct afs_vlserver_list *sl = vc->server_list; + pr_notice("VC: SL nr=%u ix=%u\n", + sl->nr_servers, sl->index); + for (i = 0; i < sl->nr_servers; i++) { + const struct afs_vlserver *s = sl->servers[i].server; + pr_notice("VC: server %s+%hu fl=%lx E=%hd\n", + s->name, s->port, s->flags, s->probe.error); + if (s->addresses) { + const struct afs_addr_list *a = + rcu_dereference(s->addresses); + pr_notice("VC: - nr=%u/%u/%u pf=%u\n", + a->nr_ipv4, a->nr_addrs, a->max_addrs, + a->preferred); + pr_notice("VC: - pr=%lx R=%lx F=%lx\n", + a->probed, a->responded, a->failed); + if (a == vc->ac.alist) + pr_notice("VC: - current\n"); + } + } + } + + pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n", + vc->ac.tried, vc->ac.index, vc->ac.abort_code, vc->ac.error, + vc->ac.responded, vc->ac.nr_iterations); + rcu_read_unlock(); +} + +/* + * Tidy up a volume location server cursor and unlock the vnode. + */ +int afs_end_vlserver_operation(struct afs_vl_cursor *vc) +{ + struct afs_net *net = vc->cell->net; + + if (vc->error == -EDESTADDRREQ || + vc->error == -ENETUNREACH || + vc->error == -EHOSTUNREACH) + afs_vl_dump_edestaddrreq(vc); + + afs_end_cursor(&vc->ac); + afs_put_vlserverlist(net, vc->server_list); + + if (vc->error == -ECONNABORTED) + vc->error = afs_abort_to_error(vc->ac.abort_code); + + return vc->error; +} diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index c3b740813fc719..c3d9e5a5f67eeb 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -128,14 +128,13 @@ static const struct afs_call_type afs_RXVLGetEntryByNameU = { * Dispatch a get volume entry by name or ID operation (uuid variant). If the * volname is a decimal number then it's a volume ID not a volume name. */ -struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net, - struct afs_addr_cursor *ac, - struct key *key, +struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_vl_cursor *vc, const char *volname, int volnamesz) { struct afs_vldb_entry *entry; struct afs_call *call; + struct afs_net *net = vc->cell->net; size_t reqsz, padsz; __be32 *bp; @@ -155,7 +154,7 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net, return ERR_PTR(-ENOMEM); } - call->key = key; + call->key = vc->key; call->reply[0] = entry; call->ret_reply0 = true; @@ -168,7 +167,7 @@ struct afs_vldb_entry *afs_vl_get_entry_by_name_u(struct afs_net *net, memset((void *)bp + volnamesz, 0, padsz); trace_afs_make_vl_call(call); - return (struct afs_vldb_entry *)afs_make_call(ac, call, GFP_KERNEL, false); + return (struct afs_vldb_entry *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); } /* @@ -187,19 +186,18 @@ static int afs_deliver_vl_get_addrs_u(struct afs_call *call) u32 uniquifier, nentries, count; int i, ret; - _enter("{%u,%zu/%u}", call->unmarshall, call->offset, call->count); + _enter("{%u,%zu/%u}", + call->unmarshall, iov_iter_count(call->_iter), call->count); -again: switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_buf(call, + sizeof(struct afs_uuid__xdr) + 3 * sizeof(__be32)); call->unmarshall++; /* Extract the returned uuid, uniquifier, nentries and blkaddrs size */ case 1: - ret = afs_extract_data(call, call->buffer, - sizeof(struct afs_uuid__xdr) + 3 * sizeof(__be32), - true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -216,28 +214,28 @@ again: call->reply[0] = alist; call->count = count; call->count2 = nentries; - call->offset = 0; call->unmarshall++; + more_entries: + count = min(call->count, 4U); + afs_extract_to_buf(call, count * sizeof(__be32)); + /* Extract entries */ case 2: - count = min(call->count, 4U); - ret = afs_extract_data(call, call->buffer, - count * sizeof(__be32), - call->count > 4); + ret = afs_extract_data(call, call->count > 4); if (ret < 0) return ret; alist = call->reply[0]; bp = call->buffer; + count = min(call->count, 4U); for (i = 0; i < count; i++) if (alist->nr_addrs < call->count2) afs_merge_fs_addr4(alist, *bp++, AFS_FS_PORT); call->count -= count; if (call->count > 0) - goto again; - call->offset = 0; + goto more_entries; call->unmarshall++; break; } @@ -267,14 +265,13 @@ static const struct afs_call_type afs_RXVLGetAddrsU = { * Dispatch an operation to get the addresses for a server, where the server is * nominated by UUID. */ -struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net, - struct afs_addr_cursor *ac, - struct key *key, +struct afs_addr_list *afs_vl_get_addrs_u(struct afs_vl_cursor *vc, const uuid_t *uuid) { struct afs_ListAddrByAttributes__xdr *r; const struct afs_uuid *u = (const struct afs_uuid *)uuid; struct afs_call *call; + struct afs_net *net = vc->cell->net; __be32 *bp; int i; @@ -286,7 +283,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net, if (!call) return ERR_PTR(-ENOMEM); - call->key = key; + call->key = vc->key; call->reply[0] = NULL; call->ret_reply0 = true; @@ -307,7 +304,7 @@ struct afs_addr_list *afs_vl_get_addrs_u(struct afs_net *net, r->uuid.node[i] = htonl(u->node[i]); trace_afs_make_vl_call(call); - return (struct afs_addr_list *)afs_make_call(ac, call, GFP_KERNEL, false); + return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); } /* @@ -318,54 +315,51 @@ static int afs_deliver_vl_get_capabilities(struct afs_call *call) u32 count; int ret; - _enter("{%u,%zu/%u}", call->unmarshall, call->offset, call->count); + _enter("{%u,%zu/%u}", + call->unmarshall, iov_iter_count(call->_iter), call->count); -again: switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_tmp(call); call->unmarshall++; /* Extract the capabilities word count */ case 1: - ret = afs_extract_data(call, &call->tmp, - 1 * sizeof(__be32), - true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; count = ntohl(call->tmp); - call->count = count; call->count2 = count; - call->offset = 0; + call->unmarshall++; + afs_extract_discard(call, count * sizeof(__be32)); /* Extract capabilities words */ case 2: - count = min(call->count, 16U); - ret = afs_extract_data(call, call->buffer, - count * sizeof(__be32), - call->count > 16); + ret = afs_extract_data(call, false); if (ret < 0) return ret; /* TODO: Examine capabilities */ - call->count -= count; - if (call->count > 0) - goto again; - call->offset = 0; call->unmarshall++; break; } - call->reply[0] = (void *)(unsigned long)call->service_id; - _leave(" = 0 [done]"); return 0; } +static void afs_destroy_vl_get_capabilities(struct afs_call *call) +{ + struct afs_vlserver *server = call->reply[0]; + + afs_put_vlserver(call->net, server); + afs_flat_call_destructor(call); +} + /* * VL.GetCapabilities operation type */ @@ -373,11 +367,12 @@ static const struct afs_call_type afs_RXVLGetCapabilities = { .name = "VL.GetCapabilities", .op = afs_VL_GetCapabilities, .deliver = afs_deliver_vl_get_capabilities, - .destructor = afs_flat_call_destructor, + .done = afs_vlserver_probe_result, + .destructor = afs_destroy_vl_get_capabilities, }; /* - * Probe a fileserver for the capabilities that it supports. This can + * Probe a volume server for the capabilities that it supports. This can * return up to 196 words. * * We use this to probe for service upgrade to determine what the server at the @@ -385,7 +380,10 @@ static const struct afs_call_type afs_RXVLGetCapabilities = { */ int afs_vl_get_capabilities(struct afs_net *net, struct afs_addr_cursor *ac, - struct key *key) + struct key *key, + struct afs_vlserver *server, + unsigned int server_index, + bool async) { struct afs_call *call; __be32 *bp; @@ -397,9 +395,10 @@ int afs_vl_get_capabilities(struct afs_net *net, return -ENOMEM; call->key = key; - call->upgrade = true; /* Let's see if this is a YFS server */ - call->reply[0] = (void *)VLGETCAPABILITIES; - call->ret_reply0 = true; + call->reply[0] = afs_get_vlserver(server); + call->reply[1] = (void *)(long)server_index; + call->upgrade = true; + call->want_reply_time = true; /* marshall the parameters */ bp = call->request; @@ -407,7 +406,7 @@ int afs_vl_get_capabilities(struct afs_net *net, /* Can't take a ref on server */ trace_afs_make_vl_call(call); - return afs_make_call(ac, call, GFP_KERNEL, false); + return afs_make_call(ac, call, GFP_KERNEL, async); } /* @@ -426,22 +425,19 @@ static int afs_deliver_yfsvl_get_endpoints(struct afs_call *call) u32 uniquifier, size; int ret; - _enter("{%u,%zu/%u,%u}", call->unmarshall, call->offset, call->count, call->count2); + _enter("{%u,%zu,%u}", + call->unmarshall, iov_iter_count(call->_iter), call->count2); -again: switch (call->unmarshall) { case 0: - call->offset = 0; + afs_extract_to_buf(call, sizeof(uuid_t) + 3 * sizeof(__be32)); call->unmarshall = 1; /* Extract the returned uuid, uniquifier, fsEndpoints count and * either the first fsEndpoint type or the volEndpoints * count if there are no fsEndpoints. */ case 1: - ret = afs_extract_data(call, call->buffer, - sizeof(uuid_t) + - 3 * sizeof(__be32), - true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -451,22 +447,19 @@ again: call->count2 = ntohl(*bp); /* Type or next count */ if (call->count > YFS_MAXENDPOINTS) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_fsendpt_num); alist = afs_alloc_addrlist(call->count, FS_SERVICE, AFS_FS_PORT); if (!alist) return -ENOMEM; alist->version = uniquifier; call->reply[0] = alist; - call->offset = 0; if (call->count == 0) goto extract_volendpoints; - call->unmarshall = 2; - - /* Extract fsEndpoints[] entries */ - case 2: + next_fsendpoint: switch (call->count2) { case YFS_ENDPOINT_IPV4: size = sizeof(__be32) * (1 + 1 + 1); @@ -475,11 +468,17 @@ again: size = sizeof(__be32) * (1 + 4 + 1); break; default: - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_fsendpt_type); } size += sizeof(__be32); - ret = afs_extract_data(call, call->buffer, size, true); + afs_extract_to_buf(call, size); + call->unmarshall = 2; + + /* Extract fsEndpoints[] entries */ + case 2: + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -488,18 +487,21 @@ again: switch (call->count2) { case YFS_ENDPOINT_IPV4: if (ntohl(bp[0]) != sizeof(__be32) * 2) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_fsendpt4_len); afs_merge_fs_addr4(alist, bp[1], ntohl(bp[2])); bp += 3; break; case YFS_ENDPOINT_IPV6: if (ntohl(bp[0]) != sizeof(__be32) * 5) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_fsendpt6_len); afs_merge_fs_addr6(alist, bp + 1, ntohl(bp[5])); bp += 6; break; default: - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_fsendpt_type); } /* Got either the type of the next entry or the count of @@ -507,10 +509,9 @@ again: */ call->count2 = ntohl(*bp++); - call->offset = 0; call->count--; if (call->count > 0) - goto again; + goto next_fsendpoint; extract_volendpoints: /* Extract the list of volEndpoints. */ @@ -518,8 +519,10 @@ again: if (!call->count) goto end; if (call->count > YFS_MAXENDPOINTS) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_vlendpt_type); + afs_extract_to_buf(call, 1 * sizeof(__be32)); call->unmarshall = 3; /* Extract the type of volEndpoints[0]. Normally we would @@ -527,17 +530,14 @@ again: * data of the current one, but this is the first... */ case 3: - ret = afs_extract_data(call, call->buffer, sizeof(__be32), true); + ret = afs_extract_data(call, true); if (ret < 0) return ret; bp = call->buffer; - call->count2 = ntohl(*bp++); - call->offset = 0; - call->unmarshall = 4; - /* Extract volEndpoints[] entries */ - case 4: + next_volendpoint: + call->count2 = ntohl(*bp++); switch (call->count2) { case YFS_ENDPOINT_IPV4: size = sizeof(__be32) * (1 + 1 + 1); @@ -546,12 +546,18 @@ again: size = sizeof(__be32) * (1 + 4 + 1); break; default: - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_vlendpt_type); } if (call->count > 1) - size += sizeof(__be32); - ret = afs_extract_data(call, call->buffer, size, true); + size += sizeof(__be32); /* Get next type too */ + afs_extract_to_buf(call, size); + call->unmarshall = 4; + + /* Extract volEndpoints[] entries */ + case 4: + ret = afs_extract_data(call, true); if (ret < 0) return ret; @@ -559,34 +565,35 @@ again: switch (call->count2) { case YFS_ENDPOINT_IPV4: if (ntohl(bp[0]) != sizeof(__be32) * 2) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_vlendpt4_len); bp += 3; break; case YFS_ENDPOINT_IPV6: if (ntohl(bp[0]) != sizeof(__be32) * 5) - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_vlendpt6_len); bp += 6; break; default: - return afs_protocol_error(call, -EBADMSG); + return afs_protocol_error(call, -EBADMSG, + afs_eproto_yvl_vlendpt_type); } /* Got either the type of the next entry or the count of * volEndpoints if no more fsEndpoints. */ - call->offset = 0; call->count--; - if (call->count > 0) { - call->count2 = ntohl(*bp++); - goto again; - } + if (call->count > 0) + goto next_volendpoint; end: + afs_extract_discard(call, 0); call->unmarshall = 5; /* Done */ case 5: - ret = afs_extract_data(call, call->buffer, 0, false); + ret = afs_extract_data(call, false); if (ret < 0) return ret; call->unmarshall = 6; @@ -596,11 +603,6 @@ again: } alist = call->reply[0]; - - /* Start with IPv6 if available. */ - if (alist->nr_ipv4 < alist->nr_addrs) - alist->index = alist->nr_ipv4; - _leave(" = 0 [done]"); return 0; } @@ -619,12 +621,11 @@ static const struct afs_call_type afs_YFSVLGetEndpoints = { * Dispatch an operation to get the addresses for a server, where the server is * nominated by UUID. */ -struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net, - struct afs_addr_cursor *ac, - struct key *key, +struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_vl_cursor *vc, const uuid_t *uuid) { struct afs_call *call; + struct afs_net *net = vc->cell->net; __be32 *bp; _enter(""); @@ -635,7 +636,7 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net, if (!call) return ERR_PTR(-ENOMEM); - call->key = key; + call->key = vc->key; call->reply[0] = NULL; call->ret_reply0 = true; @@ -646,5 +647,5 @@ struct afs_addr_list *afs_yfsvl_get_endpoints(struct afs_net *net, memcpy(bp, uuid, sizeof(*uuid)); /* Type opr_uuid */ trace_afs_make_vl_call(call); - return (struct afs_addr_list *)afs_make_call(ac, call, GFP_KERNEL, false); + return (struct afs_addr_list *)afs_make_call(&vc->ac, call, GFP_KERNEL, false); } diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 3037bd01f617d1..00975ed3640f8a 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -74,55 +74,19 @@ static struct afs_vldb_entry *afs_vl_lookup_vldb(struct afs_cell *cell, const char *volname, size_t volnamesz) { - struct afs_addr_cursor ac; - struct afs_vldb_entry *vldb; + struct afs_vldb_entry *vldb = ERR_PTR(-EDESTADDRREQ); + struct afs_vl_cursor vc; int ret; - ret = afs_set_vl_cursor(&ac, cell); - if (ret < 0) - return ERR_PTR(ret); - - while (afs_iterate_addresses(&ac)) { - if (!test_bit(ac.index, &ac.alist->probed)) { - ret = afs_vl_get_capabilities(cell->net, &ac, key); - switch (ret) { - case VL_SERVICE: - clear_bit(ac.index, &ac.alist->yfs); - set_bit(ac.index, &ac.alist->probed); - ac.addr->srx_service = ret; - break; - case YFS_VL_SERVICE: - set_bit(ac.index, &ac.alist->yfs); - set_bit(ac.index, &ac.alist->probed); - ac.addr->srx_service = ret; - break; - } - } - - vldb = afs_vl_get_entry_by_name_u(cell->net, &ac, key, - volname, volnamesz); - switch (ac.error) { - case 0: - afs_end_cursor(&ac); - return vldb; - case -ECONNABORTED: - ac.error = afs_abort_to_error(ac.abort_code); - goto error; - case -ENOMEM: - case -ENONET: - goto error; - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - break; - default: - ac.error = -EIO; - goto error; - } + if (!afs_begin_vlserver_operation(&vc, cell, key)) + return ERR_PTR(-ERESTARTSYS); + + while (afs_select_vlserver(&vc)) { + vldb = afs_vl_get_entry_by_name_u(&vc, volname, volnamesz); } -error: - return ERR_PTR(afs_end_cursor(&ac)); + ret = afs_end_vlserver_operation(&vc); + return ret < 0 ? ERR_PTR(ret) : vldb; } /* @@ -270,7 +234,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%u", volume->vid); + idsz = sprintf(idbuf, "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { diff --git a/fs/afs/write.c b/fs/afs/write.c index 19c04caf3c012b..72efcfcf9f95ef 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -33,10 +33,21 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key, loff_t pos, unsigned int len, struct page *page) { struct afs_read *req; + size_t p; + void *data; int ret; _enter(",,%llu", (unsigned long long)pos); + if (pos >= vnode->vfs_inode.i_size) { + p = pos & ~PAGE_MASK; + ASSERTCMP(p + len, <=, PAGE_SIZE); + data = kmap(page); + memset(data + p, 0, len); + kunmap(page); + return 0; + } + req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *), GFP_KERNEL); if (!req) @@ -81,7 +92,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, pgoff_t index = pos >> PAGE_SHIFT; int ret; - _enter("{%x:%u},{%lx},%u,%u", + _enter("{%llx:%llu},{%lx},%u,%u", vnode->fid.vid, vnode->fid.vnode, index, from, to); /* We want to store information about how much of a page is altered in @@ -181,7 +192,7 @@ int afs_write_end(struct file *file, struct address_space *mapping, loff_t i_size, maybe_i_size; int ret; - _enter("{%x:%u},{%lx}", + _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); maybe_i_size = pos + copied; @@ -230,7 +241,7 @@ static void afs_kill_pages(struct address_space *mapping, struct pagevec pv; unsigned count, loop; - _enter("{%x:%u},%lx-%lx", + _enter("{%llx:%llu},%lx-%lx", vnode->fid.vid, vnode->fid.vnode, first, last); pagevec_init(&pv); @@ -272,7 +283,7 @@ static void afs_redirty_pages(struct writeback_control *wbc, struct pagevec pv; unsigned count, loop; - _enter("{%x:%u},%lx-%lx", + _enter("{%llx:%llu},%lx-%lx", vnode->fid.vid, vnode->fid.vnode, first, last); pagevec_init(&pv); @@ -314,7 +325,7 @@ static int afs_store_data(struct address_space *mapping, struct list_head *p; int ret = -ENOKEY, ret2; - _enter("%s{%x:%u.%u},%lx,%lx,%x,%x", + _enter("%s{%llx:%llu.%u},%lx,%lx,%x,%x", vnode->volume->name, vnode->fid.vid, vnode->fid.vnode, @@ -533,6 +544,7 @@ no_more: case -ENOENT: case -ENOMEDIUM: case -ENXIO: + trace_afs_file_error(vnode, ret, afs_file_error_writeback_fail); afs_kill_pages(mapping, first, last); mapping_set_error(mapping, ret); break; @@ -675,7 +687,7 @@ void afs_pages_written_back(struct afs_vnode *vnode, struct afs_call *call) unsigned count, loop; pgoff_t first = call->first, last = call->last; - _enter("{%x:%u},{%lx-%lx}", + _enter("{%llx:%llu},{%lx-%lx}", vnode->fid.vid, vnode->fid.vnode, first, last); pagevec_init(&pv); @@ -714,7 +726,7 @@ ssize_t afs_file_write(struct kiocb *iocb, struct iov_iter *from) ssize_t result; size_t count = iov_iter_count(from); - _enter("{%x.%u},{%zu},", + _enter("{%llx:%llu},{%zu},", vnode->fid.vid, vnode->fid.vnode, count); if (IS_SWAPFILE(&vnode->vfs_inode)) { @@ -742,7 +754,7 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); - _enter("{%x:%u},{n=%pD},%d", + _enter("{%llx:%llu},{n=%pD},%d", vnode->fid.vid, vnode->fid.vnode, file, datasync); @@ -760,7 +772,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) struct afs_vnode *vnode = AFS_FS_I(inode); unsigned long priv; - _enter("{{%x:%u}},{%lx}", + _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, vmf->page->index); sb_start_pagefault(inode->i_sb); diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index cfcc674e64a55b..a2cdf25573e241 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -72,7 +72,7 @@ static int afs_xattr_get_fid(const struct xattr_handler *handler, char text[8 + 1 + 8 + 1 + 8 + 1]; size_t len; - len = sprintf(text, "%x:%x:%x", + len = sprintf(text, "%llx:%llx:%x", vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique); if (size == 0) return len; diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c new file mode 100644 index 00000000000000..12658c1363ae41 --- /dev/null +++ b/fs/afs/yfsclient.c @@ -0,0 +1,2184 @@ +/* YFS File Server client stubs + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/circ_buf.h> +#include <linux/iversion.h> +#include "internal.h" +#include "afs_fs.h" +#include "xdr_fs.h" +#include "protocol_yfs.h" + +static const struct afs_fid afs_zero_fid; + +static inline void afs_use_fs_server(struct afs_call *call, struct afs_cb_interest *cbi) +{ + call->cbi = afs_get_cb_interest(cbi); +} + +#define xdr_size(x) (sizeof(*x) / sizeof(__be32)) + +static void xdr_decode_YFSFid(const __be32 **_bp, struct afs_fid *fid) +{ + const struct yfs_xdr_YFSFid *x = (const void *)*_bp; + + fid->vid = xdr_to_u64(x->volume); + fid->vnode = xdr_to_u64(x->vnode.lo); + fid->vnode_hi = ntohl(x->vnode.hi); + fid->unique = ntohl(x->vnode.unique); + *_bp += xdr_size(x); +} + +static __be32 *xdr_encode_u32(__be32 *bp, u32 n) +{ + *bp++ = htonl(n); + return bp; +} + +static __be32 *xdr_encode_u64(__be32 *bp, u64 n) +{ + struct yfs_xdr_u64 *x = (void *)bp; + + *x = u64_to_xdr(n); + return bp + xdr_size(x); +} + +static __be32 *xdr_encode_YFSFid(__be32 *bp, struct afs_fid *fid) +{ + struct yfs_xdr_YFSFid *x = (void *)bp; + + x->volume = u64_to_xdr(fid->vid); + x->vnode.lo = u64_to_xdr(fid->vnode); + x->vnode.hi = htonl(fid->vnode_hi); + x->vnode.unique = htonl(fid->unique); + return bp + xdr_size(x); +} + +static size_t xdr_strlen(unsigned int len) +{ + return sizeof(__be32) + round_up(len, sizeof(__be32)); +} + +static __be32 *xdr_encode_string(__be32 *bp, const char *p, unsigned int len) +{ + bp = xdr_encode_u32(bp, len); + bp = memcpy(bp, p, len); + if (len & 3) { + unsigned int pad = 4 - (len & 3); + + memset((u8 *)bp + len, 0, pad); + len += pad; + } + + return bp + len / sizeof(__be32); +} + +static s64 linux_to_yfs_time(const struct timespec64 *t) +{ + /* Convert to 100ns intervals. */ + return (u64)t->tv_sec * 10000000 + t->tv_nsec/100; +} + +static __be32 *xdr_encode_YFSStoreStatus_mode(__be32 *bp, mode_t mode) +{ + struct yfs_xdr_YFSStoreStatus *x = (void *)bp; + + x->mask = htonl(AFS_SET_MODE); + x->mode = htonl(mode & S_IALLUGO); + x->mtime_client = u64_to_xdr(0); + x->owner = u64_to_xdr(0); + x->group = u64_to_xdr(0); + return bp + xdr_size(x); +} + +static __be32 *xdr_encode_YFSStoreStatus_mtime(__be32 *bp, const struct timespec64 *t) +{ + struct yfs_xdr_YFSStoreStatus *x = (void *)bp; + s64 mtime = linux_to_yfs_time(t); + + x->mask = htonl(AFS_SET_MTIME); + x->mode = htonl(0); + x->mtime_client = u64_to_xdr(mtime); + x->owner = u64_to_xdr(0); + x->group = u64_to_xdr(0); + return bp + xdr_size(x); +} + +/* + * Convert a signed 100ns-resolution 64-bit time into a timespec. + */ +static struct timespec64 yfs_time_to_linux(s64 t) +{ + struct timespec64 ts; + u64 abs_t; + + /* + * Unfortunately can not use normal 64 bit division on 32 bit arch, but + * the alternative, do_div, does not work with negative numbers so have + * to special case them + */ + if (t < 0) { + abs_t = -t; + ts.tv_nsec = (time64_t)(do_div(abs_t, 10000000) * 100); + ts.tv_nsec = -ts.tv_nsec; + ts.tv_sec = -abs_t; + } else { + abs_t = t; + ts.tv_nsec = (time64_t)do_div(abs_t, 10000000) * 100; + ts.tv_sec = abs_t; + } + + return ts; +} + +static struct timespec64 xdr_to_time(const struct yfs_xdr_u64 xdr) +{ + s64 t = xdr_to_u64(xdr); + + return yfs_time_to_linux(t); +} + +static void yfs_check_req(struct afs_call *call, __be32 *bp) +{ + size_t len = (void *)bp - call->request; + + if (len > call->request_size) + pr_err("kAFS: %s: Request buffer overflow (%zu>%u)\n", + call->type->name, len, call->request_size); + else if (len < call->request_size) + pr_warning("kAFS: %s: Request buffer underflow (%zu<%u)\n", + call->type->name, len, call->request_size); +} + +/* + * Dump a bad file status record. + */ +static void xdr_dump_bad(const __be32 *bp) +{ + __be32 x[4]; + int i; + + pr_notice("YFS XDR: Bad status record\n"); + for (i = 0; i < 5 * 4 * 4; i += 16) { + memcpy(x, bp, 16); + bp += 4; + pr_notice("%03x: %08x %08x %08x %08x\n", + i, ntohl(x[0]), ntohl(x[1]), ntohl(x[2]), ntohl(x[3])); + } + + memcpy(x, bp, 4); + pr_notice("0x50: %08x\n", ntohl(x[0])); +} + +/* + * Decode a YFSFetchStatus block + */ +static int xdr_decode_YFSFetchStatus(struct afs_call *call, + const __be32 **_bp, + struct afs_file_status *status, + struct afs_vnode *vnode, + const afs_dataversion_t *expected_version, + struct afs_read *read_req) +{ + const struct yfs_xdr_YFSFetchStatus *xdr = (const void *)*_bp; + u32 type; + u8 flags = 0; + + status->abort_code = ntohl(xdr->abort_code); + if (status->abort_code != 0) { + if (vnode && status->abort_code == VNOVNODE) { + set_bit(AFS_VNODE_DELETED, &vnode->flags); + status->nlink = 0; + __afs_break_callback(vnode); + } + return 0; + } + + type = ntohl(xdr->type); + switch (type) { + case AFS_FTYPE_FILE: + case AFS_FTYPE_DIR: + case AFS_FTYPE_SYMLINK: + if (type != status->type && + vnode && + !test_bit(AFS_VNODE_UNSET, &vnode->flags)) { + pr_warning("Vnode %llx:%llx:%x changed type %u to %u\n", + vnode->fid.vid, + vnode->fid.vnode, + vnode->fid.unique, + status->type, type); + goto bad; + } + status->type = type; + break; + default: + goto bad; + } + +#define EXTRACT_M4(FIELD) \ + do { \ + u32 x = ntohl(xdr->FIELD); \ + if (status->FIELD != x) { \ + flags |= AFS_VNODE_META_CHANGED; \ + status->FIELD = x; \ + } \ + } while (0) + +#define EXTRACT_M8(FIELD) \ + do { \ + u64 x = xdr_to_u64(xdr->FIELD); \ + if (status->FIELD != x) { \ + flags |= AFS_VNODE_META_CHANGED; \ + status->FIELD = x; \ + } \ + } while (0) + +#define EXTRACT_D8(FIELD) \ + do { \ + u64 x = xdr_to_u64(xdr->FIELD); \ + if (status->FIELD != x) { \ + flags |= AFS_VNODE_DATA_CHANGED; \ + status->FIELD = x; \ + } \ + } while (0) + + EXTRACT_M4(nlink); + EXTRACT_D8(size); + EXTRACT_D8(data_version); + EXTRACT_M8(author); + EXTRACT_M8(owner); + EXTRACT_M8(group); + EXTRACT_M4(mode); + EXTRACT_M4(caller_access); /* call ticket dependent */ + EXTRACT_M4(anon_access); + + status->mtime_client = xdr_to_time(xdr->mtime_client); + status->mtime_server = xdr_to_time(xdr->mtime_server); + status->lock_count = ntohl(xdr->lock_count); + + if (read_req) { + read_req->data_version = status->data_version; + read_req->file_size = status->size; + } + + *_bp += xdr_size(xdr); + + if (vnode) { + if (test_bit(AFS_VNODE_UNSET, &vnode->flags)) + flags |= AFS_VNODE_NOT_YET_SET; + afs_update_inode_from_status(vnode, status, expected_version, + flags); + } + + return 0; + +bad: + xdr_dump_bad(*_bp); + return afs_protocol_error(call, -EBADMSG, afs_eproto_bad_status); +} + +/* + * Decode the file status. We need to lock the target vnode if we're going to + * update its status so that stat() sees the attributes update atomically. + */ +static int yfs_decode_status(struct afs_call *call, + const __be32 **_bp, + struct afs_file_status *status, + struct afs_vnode *vnode, + const afs_dataversion_t *expected_version, + struct afs_read *read_req) +{ + int ret; + + if (!vnode) + return xdr_decode_YFSFetchStatus(call, _bp, status, vnode, + expected_version, read_req); + + write_seqlock(&vnode->cb_lock); + ret = xdr_decode_YFSFetchStatus(call, _bp, status, vnode, + expected_version, read_req); + write_sequnlock(&vnode->cb_lock); + return ret; +} + +/* + * Decode a YFSCallBack block + */ +static void xdr_decode_YFSCallBack(struct afs_call *call, + struct afs_vnode *vnode, + const __be32 **_bp) +{ + struct yfs_xdr_YFSCallBack *xdr = (void *)*_bp; + struct afs_cb_interest *old, *cbi = call->cbi; + u64 cb_expiry; + + write_seqlock(&vnode->cb_lock); + + if (!afs_cb_is_broken(call->cb_break, vnode, cbi)) { + cb_expiry = xdr_to_u64(xdr->expiration_time); + do_div(cb_expiry, 10 * 1000 * 1000); + vnode->cb_version = ntohl(xdr->version); + vnode->cb_type = ntohl(xdr->type); + vnode->cb_expires_at = cb_expiry + ktime_get_real_seconds(); + old = vnode->cb_interest; + if (old != call->cbi) { + vnode->cb_interest = cbi; + cbi = old; + } + set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); + } + + write_sequnlock(&vnode->cb_lock); + call->cbi = cbi; + *_bp += xdr_size(xdr); +} + +static void xdr_decode_YFSCallBack_raw(const __be32 **_bp, + struct afs_callback *cb) +{ + struct yfs_xdr_YFSCallBack *x = (void *)*_bp; + u64 cb_expiry; + + cb_expiry = xdr_to_u64(x->expiration_time); + do_div(cb_expiry, 10 * 1000 * 1000); + cb->version = ntohl(x->version); + cb->type = ntohl(x->type); + cb->expires_at = cb_expiry + ktime_get_real_seconds(); + + *_bp += xdr_size(x); +} + +/* + * Decode a YFSVolSync block + */ +static void xdr_decode_YFSVolSync(const __be32 **_bp, + struct afs_volsync *volsync) +{ + struct yfs_xdr_YFSVolSync *x = (void *)*_bp; + u64 creation; + + if (volsync) { + creation = xdr_to_u64(x->vol_creation_date); + do_div(creation, 10 * 1000 * 1000); + volsync->creation = creation; + } + + *_bp += xdr_size(x); +} + +/* + * Encode the requested attributes into a YFSStoreStatus block + */ +static __be32 *xdr_encode_YFS_StoreStatus(__be32 *bp, struct iattr *attr) +{ + struct yfs_xdr_YFSStoreStatus *x = (void *)bp; + s64 mtime = 0, owner = 0, group = 0; + u32 mask = 0, mode = 0; + + mask = 0; + if (attr->ia_valid & ATTR_MTIME) { + mask |= AFS_SET_MTIME; + mtime = linux_to_yfs_time(&attr->ia_mtime); + } + + if (attr->ia_valid & ATTR_UID) { + mask |= AFS_SET_OWNER; + owner = from_kuid(&init_user_ns, attr->ia_uid); + } + + if (attr->ia_valid & ATTR_GID) { + mask |= AFS_SET_GROUP; + group = from_kgid(&init_user_ns, attr->ia_gid); + } + + if (attr->ia_valid & ATTR_MODE) { + mask |= AFS_SET_MODE; + mode = attr->ia_mode & S_IALLUGO; + } + + x->mask = htonl(mask); + x->mode = htonl(mode); + x->mtime_client = u64_to_xdr(mtime); + x->owner = u64_to_xdr(owner); + x->group = u64_to_xdr(group); + return bp + xdr_size(x); +} + +/* + * Decode a YFSFetchVolumeStatus block. + */ +static void xdr_decode_YFSFetchVolumeStatus(const __be32 **_bp, + struct afs_volume_status *vs) +{ + const struct yfs_xdr_YFSFetchVolumeStatus *x = (const void *)*_bp; + u32 flags; + + vs->vid = xdr_to_u64(x->vid); + vs->parent_id = xdr_to_u64(x->parent_id); + flags = ntohl(x->flags); + vs->online = flags & yfs_FVSOnline; + vs->in_service = flags & yfs_FVSInservice; + vs->blessed = flags & yfs_FVSBlessed; + vs->needs_salvage = flags & yfs_FVSNeedsSalvage; + vs->type = ntohl(x->type); + vs->min_quota = 0; + vs->max_quota = xdr_to_u64(x->max_quota); + vs->blocks_in_use = xdr_to_u64(x->blocks_in_use); + vs->part_blocks_avail = xdr_to_u64(x->part_blocks_avail); + vs->part_max_blocks = xdr_to_u64(x->part_max_blocks); + vs->vol_copy_date = xdr_to_u64(x->vol_copy_date); + vs->vol_backup_date = xdr_to_u64(x->vol_backup_date); + *_bp += sizeof(*x) / sizeof(__be32); +} + +/* + * deliver reply data to an FS.FetchStatus + */ +static int yfs_deliver_fs_fetch_status_vnode(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSCallBack(call, vnode, &bp); + xdr_decode_YFSVolSync(&bp, call->reply[1]); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.FetchStatus operation type + */ +static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = { + .name = "YFS.FetchStatus(vnode)", + .op = yfs_FS_FetchStatus, + .deliver = yfs_deliver_fs_fetch_status_vnode, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the status information for a file. + */ +int yfs_fs_fetch_file_status(struct afs_fs_cursor *fc, struct afs_volsync *volsync, + bool new_inode) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + call = afs_alloc_flat_call(net, &yfs_RXYFSFetchStatus_vnode, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) { + fc->ac.error = -ENOMEM; + return -ENOMEM; + } + + call->key = fc->key; + call->reply[0] = vnode; + call->reply[1] = volsync; + call->expected_version = new_inode ? 1 : vnode->status.data_version; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSFETCHSTATUS); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + yfs_check_req(call, bp); + + call->cb_break = fc->cb_break; + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to an YFS.FetchData64. + */ +static int yfs_deliver_fs_fetch_data64(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + struct afs_read *req = call->reply[2]; + const __be32 *bp; + unsigned int size; + int ret; + + _enter("{%u,%zu/%llu}", + call->unmarshall, iov_iter_count(&call->iter), req->actual_len); + + switch (call->unmarshall) { + case 0: + req->actual_len = 0; + req->index = 0; + req->offset = req->pos & (PAGE_SIZE - 1); + afs_extract_to_tmp64(call); + call->unmarshall++; + + /* extract the returned data length */ + case 1: + _debug("extract data length"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + req->actual_len = be64_to_cpu(call->tmp64); + _debug("DATA length: %llu", req->actual_len); + req->remain = min(req->len, req->actual_len); + if (req->remain == 0) + goto no_more_data; + + call->unmarshall++; + + begin_page: + ASSERTCMP(req->index, <, req->nr_pages); + if (req->remain > PAGE_SIZE - req->offset) + size = PAGE_SIZE - req->offset; + else + size = req->remain; + call->bvec[0].bv_len = size; + call->bvec[0].bv_offset = req->offset; + call->bvec[0].bv_page = req->pages[req->index]; + iov_iter_bvec(&call->iter, READ, call->bvec, 1, size); + ASSERTCMP(size, <=, PAGE_SIZE); + + /* extract the returned data */ + case 2: + _debug("extract data %zu/%llu", + iov_iter_count(&call->iter), req->remain); + + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + req->remain -= call->bvec[0].bv_len; + req->offset += call->bvec[0].bv_len; + ASSERTCMP(req->offset, <=, PAGE_SIZE); + if (req->offset == PAGE_SIZE) { + req->offset = 0; + if (req->page_done) + req->page_done(call, req); + req->index++; + if (req->remain > 0) + goto begin_page; + } + + ASSERTCMP(req->remain, ==, 0); + if (req->actual_len <= req->len) + goto no_more_data; + + /* Discard any excess data the server gave us */ + iov_iter_discard(&call->iter, READ, req->actual_len - req->len); + call->unmarshall = 3; + case 3: + _debug("extract discard %zu/%llu", + iov_iter_count(&call->iter), req->actual_len - req->len); + + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + no_more_data: + call->unmarshall = 4; + afs_extract_to_buf(call, + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + + /* extract the metadata */ + case 4: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &vnode->status.data_version, req); + if (ret < 0) + return ret; + xdr_decode_YFSCallBack(call, vnode, &bp); + xdr_decode_YFSVolSync(&bp, call->reply[1]); + + call->unmarshall++; + + case 5: + break; + } + + for (; req->index < req->nr_pages; req->index++) { + if (req->offset < PAGE_SIZE) + zero_user_segment(req->pages[req->index], + req->offset, PAGE_SIZE); + if (req->page_done) + req->page_done(call, req); + req->offset = 0; + } + + _leave(" = 0 [done]"); + return 0; +} + +static void yfs_fetch_data_destructor(struct afs_call *call) +{ + struct afs_read *req = call->reply[2]; + + afs_put_read(req); + afs_flat_call_destructor(call); +} + +/* + * YFS.FetchData64 operation type + */ +static const struct afs_call_type yfs_RXYFSFetchData64 = { + .name = "YFS.FetchData64", + .op = yfs_FS_FetchData64, + .deliver = yfs_deliver_fs_fetch_data64, + .destructor = yfs_fetch_data_destructor, +}; + +/* + * Fetch data from a file. + */ +int yfs_fs_fetch_data(struct afs_fs_cursor *fc, struct afs_read *req) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(",%x,{%llx:%llu},%llx,%llx", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode, + req->pos, req->len); + + call = afs_alloc_flat_call(net, &yfs_RXYFSFetchData64, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_u64) * 2, + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + call->reply[1] = NULL; /* volsync */ + call->reply[2] = req; + call->expected_version = vnode->status.data_version; + call->want_reply_time = true; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSFETCHDATA64); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_u64(bp, req->pos); + bp = xdr_encode_u64(bp, req->len); + yfs_check_req(call, bp); + + refcount_inc(&req->usage); + call->cb_break = fc->cb_break; + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data for YFS.CreateFile or YFS.MakeDir. + */ +static int yfs_deliver_fs_create_vnode(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + xdr_decode_YFSFid(&bp, call->reply[1]); + ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + if (ret < 0) + return ret; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSCallBack_raw(&bp, call->reply[3]); + xdr_decode_YFSVolSync(&bp, NULL); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * FS.CreateFile and FS.MakeDir operation type + */ +static const struct afs_call_type afs_RXFSCreateFile = { + .name = "YFS.CreateFile", + .op = yfs_FS_CreateFile, + .deliver = yfs_deliver_fs_create_vnode, + .destructor = afs_flat_call_destructor, +}; + +/* + * Create a file. + */ +int yfs_fs_create_file(struct afs_fs_cursor *fc, + const char *name, + umode_t mode, + u64 current_data_version, + struct afs_fid *newfid, + struct afs_file_status *newstatus, + struct afs_callback *newcb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + size_t namesz, reqsz, rplsz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + reqsz = (sizeof(__be32) + + sizeof(__be32) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz) + + sizeof(struct yfs_xdr_YFSStoreStatus) + + sizeof(__be32)); + rplsz = (sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + + call = afs_alloc_flat_call(net, &afs_RXFSCreateFile, reqsz, rplsz); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + call->reply[1] = newfid; + call->reply[2] = newstatus; + call->reply[3] = newcb; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSCREATEFILE); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_YFSStoreStatus_mode(bp, mode); + bp = xdr_encode_u32(bp, 0); /* ViceLockType */ + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +static const struct afs_call_type yfs_RXFSMakeDir = { + .name = "YFS.MakeDir", + .op = yfs_FS_MakeDir, + .deliver = yfs_deliver_fs_create_vnode, + .destructor = afs_flat_call_destructor, +}; + +/* + * Make a directory. + */ +int yfs_fs_make_dir(struct afs_fs_cursor *fc, + const char *name, + umode_t mode, + u64 current_data_version, + struct afs_fid *newfid, + struct afs_file_status *newstatus, + struct afs_callback *newcb) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + size_t namesz, reqsz, rplsz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + reqsz = (sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz) + + sizeof(struct yfs_xdr_YFSStoreStatus)); + rplsz = (sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + + call = afs_alloc_flat_call(net, &yfs_RXFSMakeDir, reqsz, rplsz); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + call->reply[1] = newfid; + call->reply[2] = newstatus; + call->reply[3] = newcb; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSMAKEDIR); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_YFSStoreStatus_mode(bp, mode); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.RemoveFile2 operation. + */ +static int yfs_deliver_fs_remove_file2(struct afs_call *call) +{ + struct afs_vnode *dvnode = call->reply[0]; + struct afs_vnode *vnode = call->reply[1]; + struct afs_fid fid; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + + xdr_decode_YFSFid(&bp, &fid); + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + if (ret < 0) + return ret; + /* Was deleted if vnode->status.abort_code == VNOVNODE. */ + + xdr_decode_YFSVolSync(&bp, NULL); + return 0; +} + +/* + * YFS.RemoveFile2 operation type. + */ +static const struct afs_call_type yfs_RXYFSRemoveFile2 = { + .name = "YFS.RemoveFile2", + .op = yfs_FS_RemoveFile2, + .deliver = yfs_deliver_fs_remove_file2, + .destructor = afs_flat_call_destructor, +}; + +/* + * Remove a file and retrieve new file status. + */ +int yfs_fs_remove_file2(struct afs_fs_cursor *fc, struct afs_vnode *vnode, + const char *name, u64 current_data_version) +{ + struct afs_vnode *dvnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(dvnode); + size_t namesz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + + call = afs_alloc_flat_call(net, &yfs_RXYFSRemoveFile2, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = dvnode; + call->reply[1] = vnode; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSREMOVEFILE2); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &dvnode->fid); + bp = xdr_encode_string(bp, name, namesz); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &dvnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.RemoveFile or YFS.RemoveDir operation. + */ +static int yfs_deliver_fs_remove(struct afs_call *call) +{ + struct afs_vnode *dvnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + + xdr_decode_YFSVolSync(&bp, NULL); + return 0; +} + +/* + * FS.RemoveDir and FS.RemoveFile operation types. + */ +static const struct afs_call_type yfs_RXYFSRemoveFile = { + .name = "YFS.RemoveFile", + .op = yfs_FS_RemoveFile, + .deliver = yfs_deliver_fs_remove, + .destructor = afs_flat_call_destructor, +}; + +static const struct afs_call_type yfs_RXYFSRemoveDir = { + .name = "YFS.RemoveDir", + .op = yfs_FS_RemoveDir, + .deliver = yfs_deliver_fs_remove, + .destructor = afs_flat_call_destructor, +}; + +/* + * remove a file or directory + */ +int yfs_fs_remove(struct afs_fs_cursor *fc, struct afs_vnode *vnode, + const char *name, bool isdir, u64 current_data_version) +{ + struct afs_vnode *dvnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(dvnode); + size_t namesz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + call = afs_alloc_flat_call( + net, isdir ? &yfs_RXYFSRemoveDir : &yfs_RXYFSRemoveFile, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = dvnode; + call->reply[1] = vnode; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, isdir ? YFSREMOVEDIR : YFSREMOVEFILE); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &dvnode->fid); + bp = xdr_encode_string(bp, name, namesz); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &dvnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.Link operation. + */ +static int yfs_deliver_fs_link(struct afs_call *call) +{ + struct afs_vnode *dvnode = call->reply[0], *vnode = call->reply[1]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, NULL, NULL); + if (ret < 0) + return ret; + ret = yfs_decode_status(call, &bp, &dvnode->status, dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, NULL); + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.Link operation type. + */ +static const struct afs_call_type yfs_RXYFSLink = { + .name = "YFS.Link", + .op = yfs_FS_Link, + .deliver = yfs_deliver_fs_link, + .destructor = afs_flat_call_destructor, +}; + +/* + * Make a hard link. + */ +int yfs_fs_link(struct afs_fs_cursor *fc, struct afs_vnode *vnode, + const char *name, u64 current_data_version) +{ + struct afs_vnode *dvnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + size_t namesz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + call = afs_alloc_flat_call(net, &yfs_RXYFSLink, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz) + + sizeof(struct yfs_xdr_YFSFid), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = dvnode; + call->reply[1] = vnode; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSLINK); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &dvnode->fid); + bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_YFSFid(bp, &vnode->fid); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.Symlink operation. + */ +static int yfs_deliver_fs_symlink(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + xdr_decode_YFSFid(&bp, call->reply[1]); + ret = yfs_decode_status(call, &bp, call->reply[2], NULL, NULL, NULL); + if (ret < 0) + return ret; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, NULL); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.Symlink operation type + */ +static const struct afs_call_type yfs_RXYFSSymlink = { + .name = "YFS.Symlink", + .op = yfs_FS_Symlink, + .deliver = yfs_deliver_fs_symlink, + .destructor = afs_flat_call_destructor, +}; + +/* + * Create a symbolic link. + */ +int yfs_fs_symlink(struct afs_fs_cursor *fc, + const char *name, + const char *contents, + u64 current_data_version, + struct afs_fid *newfid, + struct afs_file_status *newstatus) +{ + struct afs_vnode *dvnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(dvnode); + size_t namesz, contents_sz; + __be32 *bp; + + _enter(""); + + namesz = strlen(name); + contents_sz = strlen(contents); + call = afs_alloc_flat_call(net, &yfs_RXYFSSymlink, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(namesz) + + xdr_strlen(contents_sz) + + sizeof(struct yfs_xdr_YFSStoreStatus), + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = dvnode; + call->reply[1] = newfid; + call->reply[2] = newstatus; + call->expected_version = current_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSYMLINK); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &dvnode->fid); + bp = xdr_encode_string(bp, name, namesz); + bp = xdr_encode_string(bp, contents, contents_sz); + bp = xdr_encode_YFSStoreStatus_mode(bp, S_IRWXUGO); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &dvnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.Rename operation. + */ +static int yfs_deliver_fs_rename(struct afs_call *call) +{ + struct afs_vnode *orig_dvnode = call->reply[0]; + struct afs_vnode *new_dvnode = call->reply[1]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &orig_dvnode->status, orig_dvnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + if (new_dvnode != orig_dvnode) { + ret = yfs_decode_status(call, &bp, &new_dvnode->status, new_dvnode, + &call->expected_version_2, NULL); + if (ret < 0) + return ret; + } + + xdr_decode_YFSVolSync(&bp, NULL); + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.Rename operation type + */ +static const struct afs_call_type yfs_RXYFSRename = { + .name = "FS.Rename", + .op = yfs_FS_Rename, + .deliver = yfs_deliver_fs_rename, + .destructor = afs_flat_call_destructor, +}; + +/* + * Rename a file or directory. + */ +int yfs_fs_rename(struct afs_fs_cursor *fc, + const char *orig_name, + struct afs_vnode *new_dvnode, + const char *new_name, + u64 current_orig_data_version, + u64 current_new_data_version) +{ + struct afs_vnode *orig_dvnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(orig_dvnode); + size_t o_namesz, n_namesz; + __be32 *bp; + + _enter(""); + + o_namesz = strlen(orig_name); + n_namesz = strlen(new_name); + call = afs_alloc_flat_call(net, &yfs_RXYFSRename, + sizeof(__be32) + + sizeof(struct yfs_xdr_RPCFlags) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(o_namesz) + + sizeof(struct yfs_xdr_YFSFid) + + xdr_strlen(n_namesz), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = orig_dvnode; + call->reply[1] = new_dvnode; + call->expected_version = current_orig_data_version + 1; + call->expected_version_2 = current_new_data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSRENAME); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &orig_dvnode->fid); + bp = xdr_encode_string(bp, orig_name, o_namesz); + bp = xdr_encode_YFSFid(bp, &new_dvnode->fid); + bp = xdr_encode_string(bp, new_name, n_namesz); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &orig_dvnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.StoreData64 operation. + */ +static int yfs_deliver_fs_store_data(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter(""); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, NULL); + + afs_pages_written_back(vnode, call); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.StoreData64 operation type. + */ +static const struct afs_call_type yfs_RXYFSStoreData64 = { + .name = "YFS.StoreData64", + .op = yfs_FS_StoreData64, + .deliver = yfs_deliver_fs_store_data, + .destructor = afs_flat_call_destructor, +}; + +/* + * Store a set of pages to a large file. + */ +int yfs_fs_store_data(struct afs_fs_cursor *fc, struct address_space *mapping, + pgoff_t first, pgoff_t last, + unsigned offset, unsigned to) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + loff_t size, pos, i_size; + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + size = (loff_t)to - (loff_t)offset; + if (first != last) + size += (loff_t)(last - first) << PAGE_SHIFT; + pos = (loff_t)first << PAGE_SHIFT; + pos += offset; + + i_size = i_size_read(&vnode->vfs_inode); + if (pos + size > i_size) + i_size = size + pos; + + _debug("size %llx, at %llx, i_size %llx", + (unsigned long long)size, (unsigned long long)pos, + (unsigned long long)i_size); + + call = afs_alloc_flat_call(net, &yfs_RXYFSStoreData64, + sizeof(__be32) + + sizeof(__be32) + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSStoreStatus) + + sizeof(struct yfs_xdr_u64) * 3, + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->mapping = mapping; + call->reply[0] = vnode; + call->first = first; + call->last = last; + call->first_offset = offset; + call->last_to = to; + call->send_pages = true; + call->expected_version = vnode->status.data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSTOREDATA64); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFSStoreStatus_mtime(bp, &vnode->vfs_inode.i_mtime); + bp = xdr_encode_u64(bp, pos); + bp = xdr_encode_u64(bp, size); + bp = xdr_encode_u64(bp, i_size); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * deliver reply data to an FS.StoreStatus + */ +static int yfs_deliver_fs_store_status(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter(""); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, NULL); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.StoreStatus operation type + */ +static const struct afs_call_type yfs_RXYFSStoreStatus = { + .name = "YFS.StoreStatus", + .op = yfs_FS_StoreStatus, + .deliver = yfs_deliver_fs_store_status, + .destructor = afs_flat_call_destructor, +}; + +static const struct afs_call_type yfs_RXYFSStoreData64_as_Status = { + .name = "YFS.StoreData64", + .op = yfs_FS_StoreData64, + .deliver = yfs_deliver_fs_store_status, + .destructor = afs_flat_call_destructor, +}; + +/* + * Set the attributes on a file, using YFS.StoreData64 rather than + * YFS.StoreStatus so as to alter the file size also. + */ +static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + call = afs_alloc_flat_call(net, &yfs_RXYFSStoreData64_as_Status, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSStoreStatus) + + sizeof(struct yfs_xdr_u64) * 3, + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + call->expected_version = vnode->status.data_version + 1; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSTOREDATA64); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFS_StoreStatus(bp, attr); + bp = xdr_encode_u64(bp, 0); /* position of start of write */ + bp = xdr_encode_u64(bp, 0); /* size of write */ + bp = xdr_encode_u64(bp, attr->ia_size); /* new file length */ + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Set the attributes on a file, using YFS.StoreData64 if there's a change in + * file size, and YFS.StoreStatus otherwise. + */ +int yfs_fs_setattr(struct afs_fs_cursor *fc, struct iattr *attr) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + if (attr->ia_valid & ATTR_SIZE) + return yfs_fs_setattr_size(fc, attr); + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), vnode->fid.vid, vnode->fid.vnode); + + call = afs_alloc_flat_call(net, &yfs_RXYFSStoreStatus, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(struct yfs_xdr_YFSStoreStatus), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + call->expected_version = vnode->status.data_version; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSTORESTATUS); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_YFS_StoreStatus(bp, attr); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to a YFS.GetVolumeStatus operation. + */ +static int yfs_deliver_fs_get_volume_status(struct afs_call *call) +{ + const __be32 *bp; + char *p; + u32 size; + int ret; + + _enter("{%u}", call->unmarshall); + + switch (call->unmarshall) { + case 0: + call->unmarshall++; + afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchVolumeStatus)); + + /* extract the returned status record */ + case 1: + _debug("extract status"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + bp = call->buffer; + xdr_decode_YFSFetchVolumeStatus(&bp, call->reply[1]); + call->unmarshall++; + afs_extract_to_tmp(call); + + /* extract the volume name length */ + case 2: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + call->count = ntohl(call->tmp); + _debug("volname length: %u", call->count); + if (call->count >= AFSNAMEMAX) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_volname_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); + call->unmarshall++; + + /* extract the volume name */ + case 3: + _debug("extract volname"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + p = call->reply[2]; + p[call->count] = 0; + _debug("volname '%s'", p); + afs_extract_to_tmp(call); + call->unmarshall++; + + /* extract the offline message length */ + case 4: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + call->count = ntohl(call->tmp); + _debug("offline msg length: %u", call->count); + if (call->count >= AFSNAMEMAX) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_offline_msg_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); + call->unmarshall++; + + /* extract the offline message */ + case 5: + _debug("extract offline"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + p = call->reply[2]; + p[call->count] = 0; + _debug("offline '%s'", p); + + afs_extract_to_tmp(call); + call->unmarshall++; + + /* extract the message of the day length */ + case 6: + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + call->count = ntohl(call->tmp); + _debug("motd length: %u", call->count); + if (call->count >= AFSNAMEMAX) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_motd_len); + size = (call->count + 3) & ~3; /* It's padded */ + afs_extract_begin(call, call->reply[2], size); + call->unmarshall++; + + /* extract the message of the day */ + case 7: + _debug("extract motd"); + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + p = call->reply[2]; + p[call->count] = 0; + _debug("motd '%s'", p); + + call->unmarshall++; + + case 8: + break; + } + + _leave(" = 0 [done]"); + return 0; +} + +/* + * Destroy a YFS.GetVolumeStatus call. + */ +static void yfs_get_volume_status_call_destructor(struct afs_call *call) +{ + kfree(call->reply[2]); + call->reply[2] = NULL; + afs_flat_call_destructor(call); +} + +/* + * YFS.GetVolumeStatus operation type + */ +static const struct afs_call_type yfs_RXYFSGetVolumeStatus = { + .name = "YFS.GetVolumeStatus", + .op = yfs_FS_GetVolumeStatus, + .deliver = yfs_deliver_fs_get_volume_status, + .destructor = yfs_get_volume_status_call_destructor, +}; + +/* + * fetch the status of a volume + */ +int yfs_fs_get_volume_status(struct afs_fs_cursor *fc, + struct afs_volume_status *vs) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + void *tmpbuf; + + _enter(""); + + tmpbuf = kmalloc(AFSOPAQUEMAX, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + + call = afs_alloc_flat_call(net, &yfs_RXYFSGetVolumeStatus, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_u64), + sizeof(struct yfs_xdr_YFSFetchVolumeStatus) + + sizeof(__be32)); + if (!call) { + kfree(tmpbuf); + return -ENOMEM; + } + + call->key = fc->key; + call->reply[0] = vnode; + call->reply[1] = vs; + call->reply[2] = tmpbuf; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSGETVOLUMESTATUS); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_u64(bp, vnode->fid.vid); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to an YFS.SetLock, YFS.ExtendLock or YFS.ReleaseLock + */ +static int yfs_deliver_fs_xxxx_lock(struct afs_call *call) +{ + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + _enter("{%u}", call->unmarshall); + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, &vnode->status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSVolSync(&bp, NULL); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.SetLock operation type + */ +static const struct afs_call_type yfs_RXYFSSetLock = { + .name = "YFS.SetLock", + .op = yfs_FS_SetLock, + .deliver = yfs_deliver_fs_xxxx_lock, + .destructor = afs_flat_call_destructor, +}; + +/* + * YFS.ExtendLock operation type + */ +static const struct afs_call_type yfs_RXYFSExtendLock = { + .name = "YFS.ExtendLock", + .op = yfs_FS_ExtendLock, + .deliver = yfs_deliver_fs_xxxx_lock, + .destructor = afs_flat_call_destructor, +}; + +/* + * YFS.ReleaseLock operation type + */ +static const struct afs_call_type yfs_RXYFSReleaseLock = { + .name = "YFS.ReleaseLock", + .op = yfs_FS_ReleaseLock, + .deliver = yfs_deliver_fs_xxxx_lock, + .destructor = afs_flat_call_destructor, +}; + +/* + * Set a lock on a file + */ +int yfs_fs_set_lock(struct afs_fs_cursor *fc, afs_lock_type_t type) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(""); + + call = afs_alloc_flat_call(net, &yfs_RXYFSSetLock, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid) + + sizeof(__be32), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSSETLOCK); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + bp = xdr_encode_u32(bp, type); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * extend a lock on a file + */ +int yfs_fs_extend_lock(struct afs_fs_cursor *fc) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(""); + + call = afs_alloc_flat_call(net, &yfs_RXYFSExtendLock, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSEXTENDLOCK); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * release a lock on a file + */ +int yfs_fs_release_lock(struct afs_fs_cursor *fc) +{ + struct afs_vnode *vnode = fc->vnode; + struct afs_call *call; + struct afs_net *net = afs_v2net(vnode); + __be32 *bp; + + _enter(""); + + call = afs_alloc_flat_call(net, &yfs_RXYFSReleaseLock, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) + return -ENOMEM; + + call->key = fc->key; + call->reply[0] = vnode; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSRELEASELOCK); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, &vnode->fid); + yfs_check_req(call, bp); + + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &vnode->fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to an FS.FetchStatus with no vnode. + */ +static int yfs_deliver_fs_fetch_status(struct afs_call *call) +{ + struct afs_file_status *status = call->reply[1]; + struct afs_callback *callback = call->reply[2]; + struct afs_volsync *volsync = call->reply[3]; + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + int ret; + + ret = afs_transfer_reply(call); + if (ret < 0) + return ret; + + _enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode); + + /* unmarshall the reply once we've received all of it */ + bp = call->buffer; + ret = yfs_decode_status(call, &bp, status, vnode, + &call->expected_version, NULL); + if (ret < 0) + return ret; + xdr_decode_YFSCallBack_raw(&bp, callback); + xdr_decode_YFSVolSync(&bp, volsync); + + _leave(" = 0 [done]"); + return 0; +} + +/* + * YFS.FetchStatus operation type + */ +static const struct afs_call_type yfs_RXYFSFetchStatus = { + .name = "YFS.FetchStatus", + .op = yfs_FS_FetchStatus, + .deliver = yfs_deliver_fs_fetch_status, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the status information for a fid without needing a vnode handle. + */ +int yfs_fs_fetch_status(struct afs_fs_cursor *fc, + struct afs_net *net, + struct afs_fid *fid, + struct afs_file_status *status, + struct afs_callback *callback, + struct afs_volsync *volsync) +{ + struct afs_call *call; + __be32 *bp; + + _enter(",%x,{%llx:%llu},,", + key_serial(fc->key), fid->vid, fid->vnode); + + call = afs_alloc_flat_call(net, &yfs_RXYFSFetchStatus, + sizeof(__be32) * 2 + + sizeof(struct yfs_xdr_YFSFid), + sizeof(struct yfs_xdr_YFSFetchStatus) + + sizeof(struct yfs_xdr_YFSCallBack) + + sizeof(struct yfs_xdr_YFSVolSync)); + if (!call) { + fc->ac.error = -ENOMEM; + return -ENOMEM; + } + + call->key = fc->key; + call->reply[0] = NULL; /* vnode for fid[0] */ + call->reply[1] = status; + call->reply[2] = callback; + call->reply[3] = volsync; + call->expected_version = 1; /* vnode->status.data_version */ + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSFETCHSTATUS); + bp = xdr_encode_u32(bp, 0); /* RPC flags */ + bp = xdr_encode_YFSFid(bp, fid); + yfs_check_req(call, bp); + + call->cb_break = fc->cb_break; + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, fid); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} + +/* + * Deliver reply data to an YFS.InlineBulkStatus call + */ +static int yfs_deliver_fs_inline_bulk_status(struct afs_call *call) +{ + struct afs_file_status *statuses; + struct afs_callback *callbacks; + struct afs_vnode *vnode = call->reply[0]; + const __be32 *bp; + u32 tmp; + int ret; + + _enter("{%u}", call->unmarshall); + + switch (call->unmarshall) { + case 0: + afs_extract_to_tmp(call); + call->unmarshall++; + + /* Extract the file status count and array in two steps */ + case 1: + _debug("extract status count"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + tmp = ntohl(call->tmp); + _debug("status count: %u/%u", tmp, call->count2); + if (tmp != call->count2) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_ibulkst_count); + + call->count = 0; + call->unmarshall++; + more_counts: + afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSFetchStatus)); + + case 2: + _debug("extract status array %u", call->count); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + bp = call->buffer; + statuses = call->reply[1]; + ret = yfs_decode_status(call, &bp, &statuses[call->count], + call->count == 0 ? vnode : NULL, + NULL, NULL); + if (ret < 0) + return ret; + + call->count++; + if (call->count < call->count2) + goto more_counts; + + call->count = 0; + call->unmarshall++; + afs_extract_to_tmp(call); + + /* Extract the callback count and array in two steps */ + case 3: + _debug("extract CB count"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + tmp = ntohl(call->tmp); + _debug("CB count: %u", tmp); + if (tmp != call->count2) + return afs_protocol_error(call, -EBADMSG, + afs_eproto_ibulkst_cb_count); + call->count = 0; + call->unmarshall++; + more_cbs: + afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSCallBack)); + + case 4: + _debug("extract CB array"); + ret = afs_extract_data(call, true); + if (ret < 0) + return ret; + + _debug("unmarshall CB array"); + bp = call->buffer; + callbacks = call->reply[2]; + xdr_decode_YFSCallBack_raw(&bp, &callbacks[call->count]); + statuses = call->reply[1]; + if (call->count == 0 && vnode && statuses[0].abort_code == 0) { + bp = call->buffer; + xdr_decode_YFSCallBack(call, vnode, &bp); + } + call->count++; + if (call->count < call->count2) + goto more_cbs; + + afs_extract_to_buf(call, sizeof(struct yfs_xdr_YFSVolSync)); + call->unmarshall++; + + case 5: + ret = afs_extract_data(call, false); + if (ret < 0) + return ret; + + bp = call->buffer; + xdr_decode_YFSVolSync(&bp, call->reply[3]); + + call->unmarshall++; + + case 6: + break; + } + + _leave(" = 0 [done]"); + return 0; +} + +/* + * FS.InlineBulkStatus operation type + */ +static const struct afs_call_type yfs_RXYFSInlineBulkStatus = { + .name = "YFS.InlineBulkStatus", + .op = yfs_FS_InlineBulkStatus, + .deliver = yfs_deliver_fs_inline_bulk_status, + .destructor = afs_flat_call_destructor, +}; + +/* + * Fetch the status information for up to 1024 files + */ +int yfs_fs_inline_bulk_status(struct afs_fs_cursor *fc, + struct afs_net *net, + struct afs_fid *fids, + struct afs_file_status *statuses, + struct afs_callback *callbacks, + unsigned int nr_fids, + struct afs_volsync *volsync) +{ + struct afs_call *call; + __be32 *bp; + int i; + + _enter(",%x,{%llx:%llu},%u", + key_serial(fc->key), fids[0].vid, fids[1].vnode, nr_fids); + + call = afs_alloc_flat_call(net, &yfs_RXYFSInlineBulkStatus, + sizeof(__be32) + + sizeof(__be32) + + sizeof(__be32) + + sizeof(struct yfs_xdr_YFSFid) * nr_fids, + sizeof(struct yfs_xdr_YFSFetchStatus)); + if (!call) { + fc->ac.error = -ENOMEM; + return -ENOMEM; + } + + call->key = fc->key; + call->reply[0] = NULL; /* vnode for fid[0] */ + call->reply[1] = statuses; + call->reply[2] = callbacks; + call->reply[3] = volsync; + call->count2 = nr_fids; + + /* marshall the parameters */ + bp = call->request; + bp = xdr_encode_u32(bp, YFSINLINEBULKSTATUS); + bp = xdr_encode_u32(bp, 0); /* RPCFlags */ + bp = xdr_encode_u32(bp, nr_fids); + for (i = 0; i < nr_fids; i++) + bp = xdr_encode_YFSFid(bp, &fids[i]); + yfs_check_req(call, bp); + + call->cb_break = fc->cb_break; + afs_use_fs_server(call, fc->cbi); + trace_afs_make_fs_call(call, &fids[0]); + return afs_make_call(&fc->ac, call, GFP_NOFS, false); +} diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index 9a69392f1fb375..d81c148682e715 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -350,7 +350,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) s->s_magic = BFS_MAGIC; - if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) { + if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) || + le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) { printf("Superblock is corrupted\n"); goto out1; } @@ -359,9 +360,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; imap_len = (info->si_lasti / 8) + 1; - info->si_imap = kzalloc(imap_len, GFP_KERNEL); - if (!info->si_imap) + info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN); + if (!info->si_imap) { + printf("Cannot allocate %u bytes\n", imap_len); goto out1; + } for (i = 0; i < BFS_ROOT_INO; i++) set_bit(i, info->si_imap); diff --git a/fs/block_dev.c b/fs/block_dev.c index 38b8ce05cbc7e6..a80b4f0ee7c4f1 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -349,7 +349,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) dio->size = 0; dio->multi_bio = false; - dio->should_dirty = is_read && (iter->type == ITER_IOVEC); + dio->should_dirty = is_read && iter_is_iovec(iter); blk_start_plug(&plug); for (;;) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 68ca41dbbef387..80953528572db5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3201,9 +3201,6 @@ void btrfs_get_block_group_info(struct list_head *groups_list, struct btrfs_ioctl_space_info *space); void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_balance_args *bargs); -int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff, - struct file *dst_file, loff_t dst_loff, - u64 olen); /* file.c */ int __init btrfs_auto_defrag_init(void); @@ -3233,8 +3230,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); -int btrfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); +loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 97c7a086f7bd69..a3c22e16509b30 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3298,8 +3298,7 @@ const struct file_operations btrfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = btrfs_compat_ioctl, #endif - .clone_file_range = btrfs_clone_file_range, - .dedupe_file_range = btrfs_dedupe_file_range, + .remap_file_range = btrfs_remap_file_range, }; void __cold btrfs_auto_defrag_exit(void) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a990a904513929..3ca6943827ef88 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3629,26 +3629,6 @@ out_unlock: return ret; } -int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff, - struct file *dst_file, loff_t dst_loff, - u64 olen) -{ - struct inode *src = file_inode(src_file); - struct inode *dst = file_inode(dst_file); - u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; - - if (WARN_ON_ONCE(bs < PAGE_SIZE)) { - /* - * Btrfs does not support blocksize < page_size. As a - * result, btrfs_cmp_data() won't correctly handle - * this situation without an update. - */ - return -EINVAL; - } - - return btrfs_extent_same(src, src_loff, olen, dst, dst_loff); -} - static int clone_finish_inode_update(struct btrfs_trans_handle *trans, struct inode *inode, u64 endoff, @@ -4350,10 +4330,34 @@ out_unlock: return ret; } -int btrfs_clone_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len) +loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, + unsigned int remap_flags) { - return btrfs_clone_files(dst_file, src_file, off, len, destoff); + int ret; + + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + + if (remap_flags & REMAP_FILE_DEDUP) { + struct inode *src = file_inode(src_file); + struct inode *dst = file_inode(dst_file); + u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; + + if (WARN_ON_ONCE(bs < PAGE_SIZE)) { + /* + * Btrfs does not support blocksize < page_size. As a + * result, btrfs_cmp_data() won't correctly handle + * this situation without an update. + */ + return -EINVAL; + } + + ret = btrfs_extent_same(src, off, len, dst, destoff); + } else { + ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); + } + return ret < 0 ? ret : len; } static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) diff --git a/fs/buffer.c b/fs/buffer.c index d60d61e8ed7de4..1286c2b95498de 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3060,6 +3060,11 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, */ bio = bio_alloc(GFP_NOIO, 1); + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_io(wbc, bh->b_page, bh->b_size); + } + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; @@ -3079,11 +3084,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); - if (wbc) { - wbc_init_bio(wbc, bio); - wbc_account_io(wbc, bh->b_page, bh->b_size); - } - submit_bio(bio); return 0; } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index f788496fafcc9e..27cad84dab23a9 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -615,7 +615,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, more = len < iov_iter_count(to); - if (unlikely(to->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(to))) { ret = iov_iter_get_pages_alloc(to, &pages, len, &page_off); if (ret <= 0) { @@ -662,7 +662,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ret += zlen; } - if (unlikely(to->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(to))) { if (ret > 0) { iov_iter_advance(to, ret); off += ret; @@ -815,7 +815,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) aio_req->total_len = rc + zlen; } - iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs, + iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs, osd_data->num_bvecs, osd_data->bvec_pos.iter.bi_size); iov_iter_advance(&i, rc); @@ -1038,8 +1038,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, int zlen = min_t(size_t, len - ret, size - pos - ret); - iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages, - len); + iov_iter_bvec(&i, READ, bvecs, num_pages, len); iov_iter_advance(&i, ret); iov_iter_zero(zlen, &i); ret += zlen; diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 3e812428ac8d95..ba178b09de0b48 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -145,6 +145,58 @@ cifs_dump_iface(struct seq_file *m, struct cifs_server_iface *iface) seq_printf(m, "\t\tIPv6: %pI6\n", &ipv6->sin6_addr); } +static int cifs_debug_files_proc_show(struct seq_file *m, void *v) +{ + struct list_head *stmp, *tmp, *tmp1, *tmp2; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + struct cifsFileInfo *cfile; + + seq_puts(m, "# Version:1\n"); + seq_puts(m, "# Format:\n"); + seq_puts(m, "# <tree id> <persistent fid> <flags> <count> <pid> <uid>"); +#ifdef CONFIG_CIFS_DEBUG2 + seq_printf(m, " <filename> <mid>\n"); +#else + seq_printf(m, " <filename>\n"); +#endif /* CIFS_DEBUG2 */ + spin_lock(&cifs_tcp_ses_lock); + list_for_each(stmp, &cifs_tcp_ses_list) { + server = list_entry(stmp, struct TCP_Server_Info, + tcp_ses_list); + list_for_each(tmp, &server->smb_ses_list) { + ses = list_entry(tmp, struct cifs_ses, smb_ses_list); + list_for_each(tmp1, &ses->tcon_list) { + tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); + spin_lock(&tcon->open_file_lock); + list_for_each(tmp2, &tcon->openFileList) { + cfile = list_entry(tmp2, struct cifsFileInfo, + tlist); + seq_printf(m, + "0x%x 0x%llx 0x%x %d %d %d %s", + tcon->tid, + cfile->fid.persistent_fid, + cfile->f_flags, + cfile->count, + cfile->pid, + from_kuid(&init_user_ns, cfile->uid), + cfile->dentry->d_name.name); +#ifdef CONFIG_CIFS_DEBUG2 + seq_printf(m, " 0x%llx\n", cfile->fid.mid); +#else + seq_printf(m, "\n"); +#endif /* CIFS_DEBUG2 */ + } + spin_unlock(&tcon->open_file_lock); + } + } + } + spin_unlock(&cifs_tcp_ses_lock); + seq_putc(m, '\n'); + return 0; +} + static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct list_head *tmp1, *tmp2, *tmp3; @@ -565,6 +617,9 @@ cifs_proc_init(void) proc_create_single("DebugData", 0, proc_fs_cifs, cifs_debug_data_proc_show); + proc_create_single("open_files", 0400, proc_fs_cifs, + cifs_debug_files_proc_show); + proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops); proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops); proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops); @@ -601,6 +656,7 @@ cifs_proc_clean(void) return; remove_proc_entry("DebugData", proc_fs_cifs); + remove_proc_entry("open_files", proc_fs_cifs); remove_proc_entry("cifsFYI", proc_fs_cifs); remove_proc_entry("traceSMB", proc_fs_cifs); remove_proc_entry("Stats", proc_fs_cifs); diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index b611fc2e8984e0..7f01c6e607918d 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -147,8 +147,10 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo) sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) sprintf(dp, ";sec=mskrb5"); - else - goto out; + else { + cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); + sprintf(dp, ";sec=krb5"); + } dp = description + strlen(description); sprintf(dp, ";uid=0x%x", diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 7de9603c54f103..865706edb307df 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -992,17 +992,21 @@ const struct inode_operations cifs_symlink_inode_ops = { .listxattr = cifs_listxattr, }; -static int cifs_clone_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len) +static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, + unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); struct inode *target_inode = file_inode(dst_file); struct cifsFileInfo *smb_file_src = src_file->private_data; - struct cifsFileInfo *smb_file_target = dst_file->private_data; - struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink); + struct cifsFileInfo *smb_file_target; + struct cifs_tcon *target_tcon; unsigned int xid; int rc; + if (remap_flags & ~REMAP_FILE_ADVISORY) + return -EINVAL; + cifs_dbg(FYI, "clone range\n"); xid = get_xid(); @@ -1013,6 +1017,9 @@ static int cifs_clone_file_range(struct file *src_file, loff_t off, goto out; } + smb_file_target = dst_file->private_data; + target_tcon = tlink_tcon(smb_file_target->tlink); + /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants @@ -1042,7 +1049,7 @@ static int cifs_clone_file_range(struct file *src_file, loff_t off, unlock_two_nondirectories(src_inode, target_inode); out: free_xid(xid); - return rc; + return rc < 0 ? rc : len; } ssize_t cifs_file_copychunk_range(unsigned int xid, @@ -1151,7 +1158,7 @@ const struct file_operations cifs_file_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1170,15 +1177,14 @@ const struct file_operations cifs_file_strict_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; const struct file_operations cifs_file_direct_ops = { - /* BB reevaluate whether they can be done with directio, no cache */ - .read_iter = cifs_user_readv, - .write_iter = cifs_user_writev, + .read_iter = cifs_direct_readv, + .write_iter = cifs_direct_writev, .open = cifs_open, .release = cifs_close, .lock = cifs_lock, @@ -1189,7 +1195,7 @@ const struct file_operations cifs_file_direct_ops = { .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1208,7 +1214,7 @@ const struct file_operations cifs_file_nobrl_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; @@ -1226,15 +1232,14 @@ const struct file_operations cifs_file_strict_nobrl_ops = { .llseek = cifs_llseek, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .setlease = cifs_setlease, .fallocate = cifs_fallocate, }; const struct file_operations cifs_file_direct_nobrl_ops = { - /* BB reevaluate whether they can be done with directio, no cache */ - .read_iter = cifs_user_readv, - .write_iter = cifs_user_writev, + .read_iter = cifs_direct_readv, + .write_iter = cifs_direct_writev, .open = cifs_open, .release = cifs_close, .fsync = cifs_fsync, @@ -1244,7 +1249,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = { .splice_write = iter_file_splice_write, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = cifs_llseek, .setlease = cifs_setlease, .fallocate = cifs_fallocate, @@ -1256,7 +1261,7 @@ const struct file_operations cifs_dir_ops = { .read = generic_read_dir, .unlocked_ioctl = cifs_ioctl, .copy_file_range = cifs_copy_file_range, - .clone_file_range = cifs_clone_file_range, + .remap_file_range = cifs_remap_file_range, .llseek = generic_file_llseek, .fsync = cifs_dir_fsync, }; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 24e265a5187465..4c3b5cfccc49ae 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -101,8 +101,10 @@ extern int cifs_open(struct inode *inode, struct file *file); extern int cifs_close(struct inode *inode, struct file *file); extern int cifs_closedir(struct inode *inode, struct file *file); extern ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to); +extern ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to); extern ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to); extern ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from); +extern ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from); extern ssize_t cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from); extern int cifs_lock(struct file *, int, struct file_lock *); extern int cifs_fsync(struct file *, loff_t, loff_t, int); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index ed1e0fcb69e3f6..38ab0fca49e1da 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1125,6 +1125,9 @@ struct cifs_fid { __u8 create_guid[16]; struct cifs_pending_open *pending_open; unsigned int epoch; +#ifdef CONFIG_CIFS_DEBUG2 + __u64 mid; +#endif /* CIFS_DEBUG2 */ bool purge_cache; }; @@ -1183,6 +1186,11 @@ struct cifs_aio_ctx { unsigned int len; unsigned int total_len; bool should_dirty; + /* + * Indicates if this aio_ctx is for direct_io, + * If yes, iter is a copy of the user passed iov_iter + */ + bool direct_io; }; struct cifs_readdata; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 1ce733f3582f66..79d842e7240c7c 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1539,6 +1539,9 @@ struct reparse_symlink_data { char PathBuffer[0]; } __attribute__((packed)); +/* Flag above */ +#define SYMLINK_FLAG_RELATIVE 0x00000001 + /* For IO_REPARSE_TAG_NFS */ #define NFS_SPECFILE_LNK 0x00000000014B4E4C #define NFS_SPECFILE_CHR 0x0000000000524843 diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d82f0cc7175508..6f24f129a75135 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -589,7 +589,7 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, { struct msghdr smb_msg; struct kvec iov = {.iov_base = buf, .iov_len = to_read}; - iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read); + iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } @@ -601,7 +601,7 @@ cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, struct msghdr smb_msg; struct bio_vec bv = { .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; - iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read); + iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } diff --git a/fs/cifs/file.c b/fs/cifs/file.c index c620d4b5d5d4c8..74c33d5fafc83f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1005,7 +1005,7 @@ cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock) * Set the byte-range lock (mandatory style). Returns: * 1) 0, if we set the lock and don't need to request to the server; * 2) 1, if no locks prevent us but we need to request to the server; - * 3) -EACCESS, if there is a lock that prevents us and wait is false. + * 3) -EACCES, if there is a lock that prevents us and wait is false. */ static int cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock, @@ -2538,6 +2538,61 @@ wdata_fill_from_iovec(struct cifs_writedata *wdata, struct iov_iter *from, } static int +cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, + struct cifs_aio_ctx *ctx) +{ + int wait_retry = 0; + unsigned int wsize, credits; + int rc; + struct TCP_Server_Info *server = + tlink_tcon(wdata->cfile->tlink)->ses->server; + + /* + * Try to resend this wdata, waiting for credits up to 3 seconds. + * Note: we are attempting to resend the whole wdata not in segments + */ + do { + rc = server->ops->wait_mtu_credits( + server, wdata->bytes, &wsize, &credits); + + if (rc) + break; + + if (wsize < wdata->bytes) { + add_credits_and_wake_if(server, credits, 0); + msleep(1000); + wait_retry++; + } + } while (wsize < wdata->bytes && wait_retry < 3); + + if (wsize < wdata->bytes) { + rc = -EBUSY; + goto out; + } + + rc = -EAGAIN; + while (rc == -EAGAIN) { + rc = 0; + if (wdata->cfile->invalidHandle) + rc = cifs_reopen_file(wdata->cfile, false); + if (!rc) + rc = server->ops->async_writev(wdata, + cifs_uncached_writedata_release); + } + + if (!rc) { + list_add_tail(&wdata->list, wdata_list); + return 0; + } + + add_credits_and_wake_if(server, wdata->credits, 0); +out: + kref_put(&wdata->refcount, cifs_uncached_writedata_release); + + return rc; +} + +static int cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, struct cifsFileInfo *open_file, struct cifs_sb_info *cifs_sb, struct list_head *wdata_list, @@ -2551,6 +2606,8 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, loff_t saved_offset = offset; pid_t pid; struct TCP_Server_Info *server; + struct page **pagevec; + size_t start; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) pid = open_file->pid; @@ -2567,38 +2624,79 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (rc) break; - nr_pages = get_numpages(wsize, len, &cur_len); - wdata = cifs_writedata_alloc(nr_pages, + if (ctx->direct_io) { + ssize_t result; + + result = iov_iter_get_pages_alloc( + from, &pagevec, wsize, &start); + if (result < 0) { + cifs_dbg(VFS, + "direct_writev couldn't get user pages " + "(rc=%zd) iter type %d iov_offset %zd " + "count %zd\n", + result, from->type, + from->iov_offset, from->count); + dump_stack(); + break; + } + cur_len = (size_t)result; + iov_iter_advance(from, cur_len); + + nr_pages = + (cur_len + start + PAGE_SIZE - 1) / PAGE_SIZE; + + wdata = cifs_writedata_direct_alloc(pagevec, cifs_uncached_writev_complete); - if (!wdata) { - rc = -ENOMEM; - add_credits_and_wake_if(server, credits, 0); - break; - } + if (!wdata) { + rc = -ENOMEM; + add_credits_and_wake_if(server, credits, 0); + break; + } - rc = cifs_write_allocate_pages(wdata->pages, nr_pages); - if (rc) { - kfree(wdata); - add_credits_and_wake_if(server, credits, 0); - break; - } - num_pages = nr_pages; - rc = wdata_fill_from_iovec(wdata, from, &cur_len, &num_pages); - if (rc) { - for (i = 0; i < nr_pages; i++) - put_page(wdata->pages[i]); - kfree(wdata); - add_credits_and_wake_if(server, credits, 0); - break; - } + wdata->page_offset = start; + wdata->tailsz = + nr_pages > 1 ? + cur_len - (PAGE_SIZE - start) - + (nr_pages - 2) * PAGE_SIZE : + cur_len; + } else { + nr_pages = get_numpages(wsize, len, &cur_len); + wdata = cifs_writedata_alloc(nr_pages, + cifs_uncached_writev_complete); + if (!wdata) { + rc = -ENOMEM; + add_credits_and_wake_if(server, credits, 0); + break; + } - /* - * Bring nr_pages down to the number of pages we actually used, - * and free any pages that we didn't use. - */ - for ( ; nr_pages > num_pages; nr_pages--) - put_page(wdata->pages[nr_pages - 1]); + rc = cifs_write_allocate_pages(wdata->pages, nr_pages); + if (rc) { + kfree(wdata); + add_credits_and_wake_if(server, credits, 0); + break; + } + + num_pages = nr_pages; + rc = wdata_fill_from_iovec( + wdata, from, &cur_len, &num_pages); + if (rc) { + for (i = 0; i < nr_pages; i++) + put_page(wdata->pages[i]); + kfree(wdata); + add_credits_and_wake_if(server, credits, 0); + break; + } + + /* + * Bring nr_pages down to the number of pages we + * actually used, and free any pages that we didn't use. + */ + for ( ; nr_pages > num_pages; nr_pages--) + put_page(wdata->pages[nr_pages - 1]); + + wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE); + } wdata->sync_mode = WB_SYNC_ALL; wdata->nr_pages = nr_pages; @@ -2607,7 +2705,6 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, wdata->pid = pid; wdata->bytes = cur_len; wdata->pagesz = PAGE_SIZE; - wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE); wdata->credits = credits; wdata->ctx = ctx; kref_get(&ctx->refcount); @@ -2682,13 +2779,18 @@ restart_loop: INIT_LIST_HEAD(&tmp_list); list_del_init(&wdata->list); - iov_iter_advance(&tmp_from, + if (ctx->direct_io) + rc = cifs_resend_wdata( + wdata, &tmp_list, ctx); + else { + iov_iter_advance(&tmp_from, wdata->offset - ctx->pos); - rc = cifs_write_from_iter(wdata->offset, + rc = cifs_write_from_iter(wdata->offset, wdata->bytes, &tmp_from, ctx->cfile, cifs_sb, &tmp_list, ctx); + } list_splice(&tmp_list, &ctx->list); @@ -2701,8 +2803,9 @@ restart_loop: kref_put(&wdata->refcount, cifs_uncached_writedata_release); } - for (i = 0; i < ctx->npages; i++) - put_page(ctx->bv[i].bv_page); + if (!ctx->direct_io) + for (i = 0; i < ctx->npages; i++) + put_page(ctx->bv[i].bv_page); cifs_stats_bytes_written(tcon, ctx->total_len); set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags); @@ -2717,7 +2820,8 @@ restart_loop: complete(&ctx->done); } -ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) +static ssize_t __cifs_writev( + struct kiocb *iocb, struct iov_iter *from, bool direct) { struct file *file = iocb->ki_filp; ssize_t total_written = 0; @@ -2726,13 +2830,18 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) struct cifs_sb_info *cifs_sb; struct cifs_aio_ctx *ctx; struct iov_iter saved_from = *from; + size_t len = iov_iter_count(from); int rc; /* - * BB - optimize the way when signing is disabled. We can drop this - * extra memory-to-memory copying and use iovec buffers for constructing - * write request. + * iov_iter_get_pages_alloc doesn't work with ITER_KVEC. + * In this case, fall back to non-direct write function. + * this could be improved by getting pages directly in ITER_KVEC */ + if (direct && from->type & ITER_KVEC) { + cifs_dbg(FYI, "use non-direct cifs_writev for kvec I/O\n"); + direct = false; + } rc = generic_write_checks(iocb, from); if (rc <= 0) @@ -2756,10 +2865,16 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) ctx->pos = iocb->ki_pos; - rc = setup_aio_ctx_iter(ctx, from, WRITE); - if (rc) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; + if (direct) { + ctx->direct_io = true; + ctx->iter = *from; + ctx->len = len; + } else { + rc = setup_aio_ctx_iter(ctx, from, WRITE); + if (rc) { + kref_put(&ctx->refcount, cifs_aio_ctx_release); + return rc; + } } /* grab a lock here due to read response handlers can access ctx */ @@ -2809,6 +2924,16 @@ ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) return total_written; } +ssize_t cifs_direct_writev(struct kiocb *iocb, struct iov_iter *from) +{ + return __cifs_writev(iocb, from, true); +} + +ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from) +{ + return __cifs_writev(iocb, from, false); +} + static ssize_t cifs_writev(struct kiocb *iocb, struct iov_iter *from) { @@ -2979,7 +3104,6 @@ cifs_uncached_readdata_release(struct kref *refcount) kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release); for (i = 0; i < rdata->nr_pages; i++) { put_page(rdata->pages[i]); - rdata->pages[i] = NULL; } cifs_readdata_release(refcount); } @@ -3004,7 +3128,7 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter) size_t copy = min_t(size_t, remaining, PAGE_SIZE); size_t written; - if (unlikely(iter->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(iter))) { void *addr = kmap_atomic(page); written = copy_to_iter(addr, copy, iter); @@ -3106,6 +3230,67 @@ cifs_uncached_copy_into_pages(struct TCP_Server_Info *server, return uncached_fill_pages(server, rdata, iter, iter->count); } +static int cifs_resend_rdata(struct cifs_readdata *rdata, + struct list_head *rdata_list, + struct cifs_aio_ctx *ctx) +{ + int wait_retry = 0; + unsigned int rsize, credits; + int rc; + struct TCP_Server_Info *server = + tlink_tcon(rdata->cfile->tlink)->ses->server; + + /* + * Try to resend this rdata, waiting for credits up to 3 seconds. + * Note: we are attempting to resend the whole rdata not in segments + */ + do { + rc = server->ops->wait_mtu_credits(server, rdata->bytes, + &rsize, &credits); + + if (rc) + break; + + if (rsize < rdata->bytes) { + add_credits_and_wake_if(server, credits, 0); + msleep(1000); + wait_retry++; + } + } while (rsize < rdata->bytes && wait_retry < 3); + + /* + * If we can't find enough credits to send this rdata + * release the rdata and return failure, this will pass + * whatever I/O amount we have finished to VFS. + */ + if (rsize < rdata->bytes) { + rc = -EBUSY; + goto out; + } + + rc = -EAGAIN; + while (rc == -EAGAIN) { + rc = 0; + if (rdata->cfile->invalidHandle) + rc = cifs_reopen_file(rdata->cfile, true); + if (!rc) + rc = server->ops->async_readv(rdata); + } + + if (!rc) { + /* Add to aio pending list */ + list_add_tail(&rdata->list, rdata_list); + return 0; + } + + add_credits_and_wake_if(server, rdata->credits, 0); +out: + kref_put(&rdata->refcount, + cifs_uncached_readdata_release); + + return rc; +} + static int cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, struct cifs_sb_info *cifs_sb, struct list_head *rdata_list, @@ -3117,6 +3302,9 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, int rc; pid_t pid; struct TCP_Server_Info *server; + struct page **pagevec; + size_t start; + struct iov_iter direct_iov = ctx->iter; server = tlink_tcon(open_file->tlink)->ses->server; @@ -3125,6 +3313,9 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, else pid = current->tgid; + if (ctx->direct_io) + iov_iter_advance(&direct_iov, offset - ctx->pos); + do { rc = server->ops->wait_mtu_credits(server, cifs_sb->rsize, &rsize, &credits); @@ -3132,20 +3323,59 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, break; cur_len = min_t(const size_t, len, rsize); - npages = DIV_ROUND_UP(cur_len, PAGE_SIZE); - /* allocate a readdata struct */ - rdata = cifs_readdata_alloc(npages, + if (ctx->direct_io) { + ssize_t result; + + result = iov_iter_get_pages_alloc( + &direct_iov, &pagevec, + cur_len, &start); + if (result < 0) { + cifs_dbg(VFS, + "couldn't get user pages (cur_len=%zd)" + " iter type %d" + " iov_offset %zd count %zd\n", + result, direct_iov.type, + direct_iov.iov_offset, + direct_iov.count); + dump_stack(); + break; + } + cur_len = (size_t)result; + iov_iter_advance(&direct_iov, cur_len); + + rdata = cifs_readdata_direct_alloc( + pagevec, cifs_uncached_readv_complete); + if (!rdata) { + add_credits_and_wake_if(server, credits, 0); + rc = -ENOMEM; + break; + } + + npages = (cur_len + start + PAGE_SIZE-1) / PAGE_SIZE; + rdata->page_offset = start; + rdata->tailsz = npages > 1 ? + cur_len-(PAGE_SIZE-start)-(npages-2)*PAGE_SIZE : + cur_len; + + } else { + + npages = DIV_ROUND_UP(cur_len, PAGE_SIZE); + /* allocate a readdata struct */ + rdata = cifs_readdata_alloc(npages, cifs_uncached_readv_complete); - if (!rdata) { - add_credits_and_wake_if(server, credits, 0); - rc = -ENOMEM; - break; - } + if (!rdata) { + add_credits_and_wake_if(server, credits, 0); + rc = -ENOMEM; + break; + } - rc = cifs_read_allocate_pages(rdata, npages); - if (rc) - goto error; + rc = cifs_read_allocate_pages(rdata, npages); + if (rc) + goto error; + + rdata->tailsz = PAGE_SIZE; + } rdata->cfile = cifsFileInfo_get(open_file); rdata->nr_pages = npages; @@ -3153,7 +3383,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, rdata->bytes = cur_len; rdata->pid = pid; rdata->pagesz = PAGE_SIZE; - rdata->tailsz = PAGE_SIZE; rdata->read_into_pages = cifs_uncached_read_into_pages; rdata->copy_into_pages = cifs_uncached_copy_into_pages; rdata->credits = credits; @@ -3167,9 +3396,11 @@ error: if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); kref_put(&rdata->refcount, - cifs_uncached_readdata_release); - if (rc == -EAGAIN) + cifs_uncached_readdata_release); + if (rc == -EAGAIN) { + iov_iter_revert(&direct_iov, cur_len); continue; + } break; } @@ -3225,45 +3456,62 @@ again: * reading. */ if (got_bytes && got_bytes < rdata->bytes) { - rc = cifs_readdata_to_iov(rdata, to); + rc = 0; + if (!ctx->direct_io) + rc = cifs_readdata_to_iov(rdata, to); if (rc) { kref_put(&rdata->refcount, - cifs_uncached_readdata_release); + cifs_uncached_readdata_release); continue; } } - rc = cifs_send_async_read( + if (ctx->direct_io) { + /* + * Re-use rdata as this is a + * direct I/O + */ + rc = cifs_resend_rdata( + rdata, + &tmp_list, ctx); + } else { + rc = cifs_send_async_read( rdata->offset + got_bytes, rdata->bytes - got_bytes, rdata->cfile, cifs_sb, &tmp_list, ctx); + kref_put(&rdata->refcount, + cifs_uncached_readdata_release); + } + list_splice(&tmp_list, &ctx->list); - kref_put(&rdata->refcount, - cifs_uncached_readdata_release); goto again; } else if (rdata->result) rc = rdata->result; - else + else if (!ctx->direct_io) rc = cifs_readdata_to_iov(rdata, to); /* if there was a short read -- discard anything left */ if (rdata->got_bytes && rdata->got_bytes < rdata->bytes) rc = -ENODATA; + + ctx->total_len += rdata->got_bytes; } list_del_init(&rdata->list); kref_put(&rdata->refcount, cifs_uncached_readdata_release); } - for (i = 0; i < ctx->npages; i++) { - if (ctx->should_dirty) - set_page_dirty(ctx->bv[i].bv_page); - put_page(ctx->bv[i].bv_page); - } + if (!ctx->direct_io) { + for (i = 0; i < ctx->npages; i++) { + if (ctx->should_dirty) + set_page_dirty(ctx->bv[i].bv_page); + put_page(ctx->bv[i].bv_page); + } - ctx->total_len = ctx->len - iov_iter_count(to); + ctx->total_len = ctx->len - iov_iter_count(to); + } cifs_stats_bytes_read(tcon, ctx->total_len); @@ -3281,18 +3529,28 @@ again: complete(&ctx->done); } -ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) +static ssize_t __cifs_readv( + struct kiocb *iocb, struct iov_iter *to, bool direct) { - struct file *file = iocb->ki_filp; - ssize_t rc; size_t len; - ssize_t total_read = 0; - loff_t offset = iocb->ki_pos; + struct file *file = iocb->ki_filp; struct cifs_sb_info *cifs_sb; - struct cifs_tcon *tcon; struct cifsFileInfo *cfile; + struct cifs_tcon *tcon; + ssize_t rc, total_read = 0; + loff_t offset = iocb->ki_pos; struct cifs_aio_ctx *ctx; + /* + * iov_iter_get_pages_alloc() doesn't work with ITER_KVEC, + * fall back to data copy read path + * this could be improved by getting pages directly in ITER_KVEC + */ + if (direct && to->type & ITER_KVEC) { + cifs_dbg(FYI, "use non-direct cifs_user_readv for kvec I/O\n"); + direct = false; + } + len = iov_iter_count(to); if (!len) return 0; @@ -3316,17 +3574,23 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) if (!is_sync_kiocb(iocb)) ctx->iocb = iocb; - if (to->type == ITER_IOVEC) + if (iter_is_iovec(to)) ctx->should_dirty = true; - rc = setup_aio_ctx_iter(ctx, to, READ); - if (rc) { - kref_put(&ctx->refcount, cifs_aio_ctx_release); - return rc; + if (direct) { + ctx->pos = offset; + ctx->direct_io = true; + ctx->iter = *to; + ctx->len = len; + } else { + rc = setup_aio_ctx_iter(ctx, to, READ); + if (rc) { + kref_put(&ctx->refcount, cifs_aio_ctx_release); + return rc; + } + len = ctx->len; } - len = ctx->len; - /* grab a lock here due to read response handlers can access ctx */ mutex_lock(&ctx->aio_mutex); @@ -3368,6 +3632,16 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) return rc; } +ssize_t cifs_direct_readv(struct kiocb *iocb, struct iov_iter *to) +{ + return __cifs_readv(iocb, to, true); +} + +ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) +{ + return __cifs_readv(iocb, to, false); +} + ssize_t cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) { diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 1023d78673fb14..a81a9df997c1c1 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1320,8 +1320,8 @@ cifs_drop_nlink(struct inode *inode) /* * If d_inode(dentry) is null (usually meaning the cached dentry * is a negative dentry) then we would attempt a standard SMB delete, but - * if that fails we can not attempt the fall back mechanisms on EACCESS - * but will return the EACCESS to the caller. Note that the VFS does not call + * if that fails we can not attempt the fall back mechanisms on EACCES + * but will return the EACCES to the caller. Note that the VFS does not call * unlink on negative dentries currently. */ int cifs_unlink(struct inode *dir, struct dentry *dentry) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index fc43d5d25d1df1..8a41f4eba7264f 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -788,7 +788,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) struct page **pages = NULL; struct bio_vec *bv = NULL; - if (iter->type & ITER_KVEC) { + if (iov_iter_is_kvec(iter)) { memcpy(&ctx->iter, iter, sizeof(struct iov_iter)); ctx->len = count; iov_iter_advance(iter, count); @@ -859,7 +859,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) ctx->bv = bv; ctx->len = saved_len - count; ctx->npages = npages; - iov_iter_bvec(&ctx->iter, ITER_BVEC | rw, ctx->bv, npages, ctx->len); + iov_iter_bvec(&ctx->iter, rw, ctx->bv, npages, ctx->len); return 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index f85fc5aa271082..225fec1cfa6733 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -747,6 +747,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, int rc = 0; unsigned int ea_name_len = ea_name ? strlen(ea_name) : 0; char *name, *value; + size_t buf_size = dst_size; size_t name_len, value_len, user_name_len; while (src_size > 0) { @@ -782,9 +783,10 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, /* 'user.' plus a terminating null */ user_name_len = 5 + 1 + name_len; - rc += user_name_len; - - if (dst_size >= user_name_len) { + if (buf_size == 0) { + /* skip copy - calc size only */ + rc += user_name_len; + } else if (dst_size >= user_name_len) { dst_size -= user_name_len; memcpy(dst, "user.", 5); dst += 5; @@ -792,8 +794,7 @@ move_smb2_ea_to_cifs(char *dst, size_t dst_size, dst += name_len; *dst = 0; ++dst; - } else if (dst_size == 0) { - /* skip copy - calc size only */ + rc += user_name_len; } else { /* stop before overrun buffer */ rc = -ERANGE; @@ -1078,6 +1079,9 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock) cfile->fid.persistent_fid = fid->persistent_fid; cfile->fid.volatile_fid = fid->volatile_fid; +#ifdef CONFIG_CIFS_DEBUG2 + cfile->fid.mid = fid->mid; +#endif /* CIFS_DEBUG2 */ server->ops->set_oplock_level(cinode, oplock, fid->epoch, &fid->purge_cache); cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode); @@ -3152,13 +3156,13 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, return 0; } - iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len); + iov_iter_bvec(&iter, WRITE, bvec, npages, data_len); } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ WARN_ONCE(npages > 0, "read data can be either in buf or in pages"); iov.iov_base = buf + data_offset; iov.iov_len = data_len; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len); + iov_iter_kvec(&iter, WRITE, &iov, 1, data_len); } else { /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7d7b016fe8bb0e..27f86537a5d11a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1512,7 +1512,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov); cifs_small_buf_release(req); rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base; - + trace_smb3_tcon(xid, tcon->tid, ses->Suid, tree, rc); if (rc != 0) { if (tcon) { cifs_stats_fail_inc(tcon, SMB2_TREE_CONNECT_HE); @@ -1559,6 +1559,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree, if (tcon->ses->server->ops->validate_negotiate) rc = tcon->ses->server->ops->validate_negotiate(xid, tcon); tcon_exit: + free_rsp_buf(resp_buftype, rsp); kfree(unc_path); return rc; @@ -2308,6 +2309,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, atomic_inc(&tcon->num_remote_opens); oparms->fid->persistent_fid = rsp->PersistentFileId; oparms->fid->volatile_fid = rsp->VolatileFileId; +#ifdef CONFIG_CIFS_DEBUG2 + oparms->fid->mid = le64_to_cpu(rsp->sync_hdr.MessageId); +#endif /* CIFS_DEBUG2 */ if (buf) { memcpy(buf, &rsp->CreationTime, 32); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index f753f424d7f111..5671d5ee7f58f6 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -842,6 +842,41 @@ struct fsctl_get_integrity_information_rsp { /* Integrity flags for above */ #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF 0x00000001 +/* Reparse structures - see MS-FSCC 2.1.2 */ + +/* struct fsctl_reparse_info_req is empty, only response structs (see below) */ + +struct reparse_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __u8 DataBuffer[0]; /* Variable Length */ +} __packed; + +struct reparse_guid_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __u8 ReparseGuid[16]; + __u8 DataBuffer[0]; /* Variable Length */ +} __packed; + +struct reparse_mount_point_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le16 SubstituteNameOffset; + __le16 SubstituteNameLength; + __le16 PrintNameOffset; + __le16 PrintNameLength; + __u8 PathBuffer[0]; /* Variable Length */ +} __packed; + +/* See MS-FSCC 2.1.2.4 and cifspdu.h for struct reparse_symlink_data */ + +/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ + + /* See MS-DFSC 2.2.2 */ struct fsctl_get_dfs_referral_req { __le16 MaxReferralLevel; diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 5e282368cc4a9f..e94a8d1d08a3ce 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2054,14 +2054,22 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) info->smbd_recv_pending++; - switch (msg->msg_iter.type) { - case READ | ITER_KVEC: + if (iov_iter_rw(&msg->msg_iter) == WRITE) { + /* It's a bug in upper layer to get there */ + cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n", + iov_iter_rw(&msg->msg_iter)); + rc = -EINVAL; + goto out; + } + + switch (iov_iter_type(&msg->msg_iter)) { + case ITER_KVEC: buf = msg->msg_iter.kvec->iov_base; to_read = msg->msg_iter.kvec->iov_len; rc = smbd_recv_buf(info, buf, to_read); break; - case READ | ITER_BVEC: + case ITER_BVEC: page = msg->msg_iter.bvec->bv_page; page_offset = msg->msg_iter.bvec->bv_offset; to_read = msg->msg_iter.bvec->bv_len; @@ -2071,10 +2079,11 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) default: /* It's a bug in upper layer to get there */ cifs_dbg(VFS, "CIFS: invalid msg type %d\n", - msg->msg_iter.type); + iov_iter_type(&msg->msg_iter)); rc = -EINVAL; } +out: info->smbd_recv_pending--; wake_up(&info->wait_smbd_recv_pending); diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index cce8414fe7ec2b..fb049809555fea 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -374,6 +374,48 @@ DEFINE_SMB3_ENTER_EXIT_EVENT(enter); DEFINE_SMB3_ENTER_EXIT_EVENT(exit_done); /* + * For SMB2/SMB3 tree connect + */ + +DECLARE_EVENT_CLASS(smb3_tcon_class, + TP_PROTO(unsigned int xid, + __u32 tid, + __u64 sesid, + const char *unc_name, + int rc), + TP_ARGS(xid, tid, sesid, unc_name, rc), + TP_STRUCT__entry( + __field(unsigned int, xid) + __field(__u32, tid) + __field(__u64, sesid) + __field(const char *, unc_name) + __field(int, rc) + ), + TP_fast_assign( + __entry->xid = xid; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->unc_name = unc_name; + __entry->rc = rc; + ), + TP_printk("xid=%u sid=0x%llx tid=0x%x unc_name=%s rc=%d", + __entry->xid, __entry->sesid, __entry->tid, + __entry->unc_name, __entry->rc) +) + +#define DEFINE_SMB3_TCON_EVENT(name) \ +DEFINE_EVENT(smb3_tcon_class, smb3_##name, \ + TP_PROTO(unsigned int xid, \ + __u32 tid, \ + __u64 sesid, \ + const char *unc_name, \ + int rc), \ + TP_ARGS(xid, tid, sesid, unc_name, rc)) + +DEFINE_SMB3_TCON_EVENT(tcon); + + +/* * For smb2/smb3 open call */ DECLARE_EVENT_CLASS(smb3_open_err_class, diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index f8112433f0c8b3..83ff0c25710d08 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -316,8 +316,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, .iov_base = &rfc1002_marker, .iov_len = 4 }; - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov, - 1, 4); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, &hiov, 1, 4); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) goto uncork; @@ -338,8 +337,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, size += iov[i].iov_len; } - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, - iov, n_vec, size); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, iov, n_vec, size); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) @@ -355,7 +353,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, rqst_page_get_length(&rqst[j], i, &bvec.bv_len, &bvec.bv_offset); - iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, + iov_iter_bvec(&smb_msg.msg_iter, WRITE, &bvec, 1, bvec.bv_len); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) diff --git a/fs/direct-io.c b/fs/direct-io.c index 093fb54cd3163d..722d17c88edb90 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1313,7 +1313,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; - dio->should_dirty = (iter->type == ITER_IOVEC); + dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index a5e4a221435c04..76976d6e50f93a 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -674,7 +674,7 @@ static int receive_from_sock(struct connection *con) nvec = 2; } len = iov[0].iov_len + iov[1].iov_len; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nvec, len); + iov_iter_kvec(&msg.msg_iter, READ, iov, nvec, len); r = ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT | MSG_NOSIGNAL); if (ret <= 0) diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 41cf2fbee50da4..906839a4da8ff8 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -101,6 +101,7 @@ static int parse_options(char *options, struct exofs_mountopt *opts) token = match_token(p, tokens, args); switch (token) { case Opt_name: + kfree(opts->dev_name); opts->dev_name = match_strdup(&args[0]); if (unlikely(!opts->dev_name)) { EXOFS_ERR("Error allocating dev_name"); @@ -117,7 +118,7 @@ static int parse_options(char *options, struct exofs_mountopt *opts) EXOFS_MIN_PID); return -EINVAL; } - s_pid = 1; + s_pid = true; break; case Opt_to: if (match_int(&args[0], &option)) @@ -866,8 +867,10 @@ static struct dentry *exofs_mount(struct file_system_type *type, int ret; ret = parse_options(data, &opts); - if (ret) + if (ret) { + kfree(opts.dev_name); return ERR_PTR(ret); + } if (!opts.dev_name) opts.dev_name = dev_name; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 12f90d48ba6137..3f89d0ab08fc4c 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -45,15 +45,6 @@ #include <linux/compiler.h> -/* Until this gets included into linux/compiler-gcc.h */ -#ifndef __nonstring -#if defined(GCC_VERSION) && (GCC_VERSION >= 80000) -#define __nonstring __attribute__((nonstring)) -#else -#define __nonstring -#endif -#endif - /* * The fourth extended filesystem constants/structures */ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 2addcb8730e19a..014f6a698cb712 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1216,7 +1216,7 @@ struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino) bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb); bitmap_bh = ext4_read_inode_bitmap(sb, block_group); if (IS_ERR(bitmap_bh)) - return (struct inode *) bitmap_bh; + return ERR_CAST(bitmap_bh); /* Having the inode bit set should be a 100% indicator that this * is a valid orphan (no e2fsck run on fs). Orphans also include diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 67a38532032ae8..17adcb16a9c85f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1556,7 +1556,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); if (IS_ERR(bh)) - return (struct dentry *) bh; + return ERR_CAST(bh); inode = NULL; if (bh) { __u32 ino = le32_to_cpu(de->inode); @@ -1600,7 +1600,7 @@ struct dentry *ext4_get_parent(struct dentry *child) bh = ext4_find_entry(d_inode(child), &dotdot, &de, NULL); if (IS_ERR(bh)) - return (struct dentry *) bh; + return ERR_CAST(bh); if (!bh) return ERR_PTR(-ENOENT); ino = le32_to_cpu(de->inode); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 2aa62d58d8dd87..db7590178dfcf1 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -374,13 +374,13 @@ static int io_submit_init_bio(struct ext4_io_submit *io, bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); if (!bio) return -ENOMEM; + wbc_init_bio(io->io_wbc, bio); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); io->io_bio = bio; io->io_next_block = bh->b_blocknr; - wbc_init_bio(io->io_wbc, bio); return 0; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 58dbc39fea639e..cc2121b37bf5f7 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1275,7 +1275,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, ssize_t ret = 0; /* Special case for kernel I/O: can copy directly into the buffer */ - if (ii->type & ITER_KVEC) { + if (iov_iter_is_kvec(ii)) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); diff --git a/fs/ioctl.c b/fs/ioctl.c index 2005529af56089..d64f622cac8b8f 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -223,6 +223,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); + loff_t cloned; int ret; if (!src_file.file) @@ -230,7 +231,14 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; - ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); + cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, + olen, 0); + if (cloned < 0) + ret = cloned; + else if (olen && cloned != olen) + ret = -EINVAL; + else + ret = 0; fdput: fdput(src_file); return ret; @@ -669,6 +677,9 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, return ioctl_fiemap(filp, arg); case FIGETBSZ: + /* anon_bdev filesystems may not have a block size */ + if (!inode->i_sb->s_blocksize) + return -EINVAL; return put_user(inode->i_sb->s_blocksize, argp); case FICLONE: diff --git a/fs/iomap.c b/fs/iomap.c index 90c2febc93acc7..64ce240217a189 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -30,7 +30,6 @@ #include <linux/task_io_accounting_ops.h> #include <linux/dax.h> #include <linux/sched/signal.h> -#include <linux/swap.h> #include "internal.h" @@ -1795,7 +1794,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (pos >= dio->i_size) goto out_free_dio; - if (iter->type == ITER_IOVEC) + if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ) dio->flags |= IOMAP_DIO_DIRTY; } else { flags |= IOMAP_WRITE; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 4288a6ecaf7563..46d691ba04bc8f 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -180,8 +180,9 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_allocate(filep, offset, len); } -static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, - struct file *dst_file, loff_t dst_off, u64 count) +static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, loff_t count, + unsigned int remap_flags) { struct inode *dst_inode = file_inode(dst_file); struct nfs_server *server = NFS_SERVER(dst_inode); @@ -190,6 +191,9 @@ static int nfs42_clone_file_range(struct file *src_file, loff_t src_off, bool same_inode = false; int ret; + if (remap_flags & ~REMAP_FILE_ADVISORY) + return -EINVAL; + /* check alignment w.r.t. clone_blksize */ ret = -EINVAL; if (bs) { @@ -240,7 +244,7 @@ out_unlock: inode_unlock(src_inode); } out: - return ret; + return ret < 0 ? ret : count; } #endif /* CONFIG_NFS_V4_2 */ @@ -262,7 +266,7 @@ const struct file_operations nfs4_file_operations = { .copy_file_range = nfs4_copy_file_range, .llseek = nfs4_file_llseek, .fallocate = nfs42_fallocate, - .clone_file_range = nfs42_clone_file_range, + .remap_file_range = nfs42_remap_file_range, #else .llseek = nfs_file_llseek, #endif diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 2751976704e938..eb67098117b4c0 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -541,8 +541,12 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { - return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, - count)); + loff_t cloned; + + cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); + if (count && cloned != count) + cloned = -EINVAL; + return nfserrno(cloned < 0 ? cloned : 0); } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, @@ -923,7 +927,7 @@ __be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, int host_err; trace_nfsd_read_vector(rqstp, fhp, offset, *count); - iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count); + iov_iter_kvec(&iter, READ, vec, vlen, *count); host_err = vfs_iter_read(file, &iter, &offset, 0); return nfsd_finish_read(rqstp, fhp, file, offset, count, host_err); } @@ -999,7 +1003,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (stable && !use_wgather) flags |= RWF_SYNC; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt); + iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) goto out_nfserr; diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 4690cd75d8d794..3986c7a1f6a88c 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -312,7 +312,7 @@ static struct dentry *ntfs_get_parent(struct dentry *child_dent) /* Get the mft record of the inode belonging to the child dentry. */ mrec = map_mft_record(ni); if (IS_ERR(mrec)) - return (struct dentry *)mrec; + return ERR_CAST(mrec); /* Find the first file name attribute in the mft record. */ ctx = ntfs_attr_get_search_ctx(ni, mrec); if (unlikely(!ctx)) { diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c index 1d098c3c00e023..4ebbd57cbf8460 100644 --- a/fs/ocfs2/buffer_head_io.c +++ b/fs/ocfs2/buffer_head_io.c @@ -99,25 +99,34 @@ out: return ret; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, unsigned int nr, struct buffer_head *bhs[]) { int status = 0; unsigned int i; struct buffer_head *bh; + int new_bh = 0; trace_ocfs2_read_blocks_sync((unsigned long long)block, nr); if (!nr) goto bail; + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { bhs[i] = sb_getblk(osb->sb, block++); if (bhs[i] == NULL) { status = -ENOMEM; mlog_errno(status); - goto bail; + break; } } bh = bhs[i]; @@ -158,9 +167,26 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, submit_bh(REQ_OP_READ, 0, bh); } +read_failure: for (i = nr; i > 0; i--) { bh = bhs[i - 1]; + if (unlikely(status)) { + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i - 1] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } + continue; + } + /* No need to wait on the buffer if it's managed by JBD. */ if (!buffer_jbd(bh)) wait_on_buffer(bh); @@ -170,8 +196,7 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block, * so we can safely record this and loop back * to cleanup the other buffers. */ status = -EIO; - put_bh(bh); - bhs[i - 1] = NULL; + goto read_failure; } } @@ -179,6 +204,9 @@ bail: return status; } +/* Caller must provide a bhs[] with all NULL or non-NULL entries, so it + * will be easier to handle read failure. + */ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, struct buffer_head *bhs[], int flags, int (*validate)(struct super_block *sb, @@ -188,6 +216,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, int i, ignore_cache = 0; struct buffer_head *bh; struct super_block *sb = ocfs2_metadata_cache_get_super(ci); + int new_bh = 0; trace_ocfs2_read_blocks_begin(ci, (unsigned long long)block, nr, flags); @@ -213,6 +242,11 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, goto bail; } + /* Don't put buffer head and re-assign it to NULL if it is allocated + * outside since the caller can't be aware of this alternation! + */ + new_bh = (bhs[0] == NULL); + ocfs2_metadata_cache_io_lock(ci); for (i = 0 ; i < nr ; i++) { if (bhs[i] == NULL) { @@ -221,7 +255,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, ocfs2_metadata_cache_io_unlock(ci); status = -ENOMEM; mlog_errno(status); - goto bail; + /* Don't forget to put previous bh! */ + break; } } bh = bhs[i]; @@ -316,16 +351,27 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, } } - status = 0; - +read_failure: for (i = (nr - 1); i >= 0; i--) { bh = bhs[i]; if (!(flags & OCFS2_BH_READAHEAD)) { - if (status) { - /* Clear the rest of the buffers on error */ - put_bh(bh); - bhs[i] = NULL; + if (unlikely(status)) { + /* Clear the buffers on error including those + * ever succeeded in reading + */ + if (new_bh && bh) { + /* If middle bh fails, let previous bh + * finish its read and then put it to + * aovoid bh leak + */ + if (!buffer_jbd(bh)) + wait_on_buffer(bh); + put_bh(bh); + bhs[i] = NULL; + } else if (bh && buffer_uptodate(bh)) { + clear_buffer_uptodate(bh); + } continue; } /* We know this can't have changed as we hold the @@ -343,9 +389,7 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, * uptodate. */ status = -EIO; clear_buffer_needs_validate(bh); - put_bh(bh); - bhs[i] = NULL; - continue; + goto read_failure; } if (buffer_needs_validate(bh)) { @@ -355,11 +399,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr, BUG_ON(buffer_jbd(bh)); clear_buffer_needs_validate(bh); status = validate(sb, bh); - if (status) { - put_bh(bh); - bhs[i] = NULL; - continue; - } + if (status) + goto read_failure; } } diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 7d9eea7d4a8733..e9f236af1927d3 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -916,7 +916,7 @@ static int o2net_recv_tcp_msg(struct socket *sock, void *data, size_t len) { struct kvec vec = { .iov_len = len, .iov_base = data, }; struct msghdr msg = { .msg_flags = MSG_DONTWAIT, }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, len); return sock_recvmsg(sock, &msg, MSG_DONTWAIT); } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index b048d4fa395908..c121abbdfc7dbc 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1897,8 +1897,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, /* On error, skip the f_pos to the next block. */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; - brelse(bh); - continue; + break; } if (le64_to_cpu(de->inode)) { unsigned char d_type = DT_UNKNOWN; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 933aac5da19341..7c835824247eb7 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2123,10 +2123,10 @@ static void ocfs2_downconvert_on_unlock(struct ocfs2_super *osb, /* LVB only has room for 64 bits of time here so we pack it for * now. */ -static u64 ocfs2_pack_timespec(struct timespec *spec) +static u64 ocfs2_pack_timespec(struct timespec64 *spec) { u64 res; - u64 sec = spec->tv_sec; + u64 sec = clamp_t(time64_t, spec->tv_sec, 0, 0x3ffffffffull); u32 nsec = spec->tv_nsec; res = (sec << OCFS2_SEC_SHIFT) | (nsec & OCFS2_NSEC_MASK); @@ -2142,7 +2142,6 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; - struct timespec ts; lvb = ocfs2_dlm_lvb(&lockres->l_lksb); @@ -2163,15 +2162,12 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) lvb->lvb_igid = cpu_to_be32(i_gid_read(inode)); lvb->lvb_imode = cpu_to_be16(inode->i_mode); lvb->lvb_inlink = cpu_to_be16(inode->i_nlink); - ts = timespec64_to_timespec(inode->i_atime); lvb->lvb_iatime_packed = - cpu_to_be64(ocfs2_pack_timespec(&ts)); - ts = timespec64_to_timespec(inode->i_ctime); + cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime)); lvb->lvb_ictime_packed = - cpu_to_be64(ocfs2_pack_timespec(&ts)); - ts = timespec64_to_timespec(inode->i_mtime); + cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime)); lvb->lvb_imtime_packed = - cpu_to_be64(ocfs2_pack_timespec(&ts)); + cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime)); lvb->lvb_iattr = cpu_to_be32(oi->ip_attr); lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features); lvb->lvb_igeneration = cpu_to_be32(inode->i_generation); @@ -2180,7 +2176,7 @@ out: mlog_meta_lvb(0, lockres); } -static void ocfs2_unpack_timespec(struct timespec *spec, +static void ocfs2_unpack_timespec(struct timespec64 *spec, u64 packed_time) { spec->tv_sec = packed_time >> OCFS2_SEC_SHIFT; @@ -2189,7 +2185,6 @@ static void ocfs2_unpack_timespec(struct timespec *spec, static void ocfs2_refresh_inode_from_lvb(struct inode *inode) { - struct timespec ts; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; @@ -2217,15 +2212,12 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode) i_gid_write(inode, be32_to_cpu(lvb->lvb_igid)); inode->i_mode = be16_to_cpu(lvb->lvb_imode); set_nlink(inode, be16_to_cpu(lvb->lvb_inlink)); - ocfs2_unpack_timespec(&ts, + ocfs2_unpack_timespec(&inode->i_atime, be64_to_cpu(lvb->lvb_iatime_packed)); - inode->i_atime = timespec_to_timespec64(ts); - ocfs2_unpack_timespec(&ts, + ocfs2_unpack_timespec(&inode->i_mtime, be64_to_cpu(lvb->lvb_imtime_packed)); - inode->i_mtime = timespec_to_timespec64(ts); - ocfs2_unpack_timespec(&ts, + ocfs2_unpack_timespec(&inode->i_ctime, be64_to_cpu(lvb->lvb_ictime_packed)); - inode->i_ctime = timespec_to_timespec64(ts); spin_unlock(&oi->ip_lock); } @@ -3603,7 +3595,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb, * we can recover correctly from node failure. Otherwise, we may get * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set. */ - if (!ocfs2_is_o2cb_active() && + if (ocfs2_userspace_stack(osb) && lockres->l_ops->flags & LOCK_TYPE_USES_LVB) lvb = 1; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9fa35cb6f6e0b5..d640c5f8a85da8 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2343,7 +2343,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb, written = __generic_file_write_iter(iocb, from); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(written == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); + BUG_ON(written == -EIOCBQUEUED && !direct_io); /* * deep in g_f_a_w_n()->ocfs2_direct_IO we pass in a ocfs2_dio_end_io @@ -2463,7 +2463,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb, trace_generic_file_read_iter_ret(ret); /* buffered aio wouldn't have proper lock coverage today */ - BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT)); + BUG_ON(ret == -EIOCBQUEUED && !direct_io); /* see ocfs2_file_write_iter */ if (ret == -EIOCBQUEUED || !ocfs2_iocb_is_rw_locked(iocb)) { @@ -2527,24 +2527,79 @@ out: return offset; } -static int ocfs2_file_clone_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) +static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { - return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, false); -} + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); + struct ocfs2_super *osb = OCFS2_SB(inode_in->i_sb); + struct buffer_head *in_bh = NULL, *out_bh = NULL; + bool same_inode = (inode_in == inode_out); + loff_t remapped = 0; + ssize_t ret; -static int ocfs2_file_dedupe_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) -{ - return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, true); + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + if (!ocfs2_refcount_tree(osb)) + return -EOPNOTSUPP; + if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) + return -EROFS; + + /* Lock both files against IO */ + ret = ocfs2_reflink_inodes_lock(inode_in, &in_bh, inode_out, &out_bh); + if (ret) + return ret; + + /* Check file eligibility and prepare for block sharing. */ + ret = -EINVAL; + if ((OCFS2_I(inode_in)->ip_flags & OCFS2_INODE_SYSTEM_FILE) || + (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) + goto out_unlock; + + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, + &len, remap_flags); + if (ret < 0 || len == 0) + goto out_unlock; + + /* Lock out changes to the allocation maps and remap. */ + down_write(&OCFS2_I(inode_in)->ip_alloc_sem); + if (!same_inode) + down_write_nested(&OCFS2_I(inode_out)->ip_alloc_sem, + SINGLE_DEPTH_NESTING); + + /* Zap any page cache for the destination file's range. */ + truncate_inode_pages_range(&inode_out->i_data, + round_down(pos_out, PAGE_SIZE), + round_up(pos_out + len, PAGE_SIZE) - 1); + + remapped = ocfs2_reflink_remap_blocks(inode_in, in_bh, pos_in, + inode_out, out_bh, pos_out, len); + up_write(&OCFS2_I(inode_in)->ip_alloc_sem); + if (!same_inode) + up_write(&OCFS2_I(inode_out)->ip_alloc_sem); + if (remapped < 0) { + ret = remapped; + mlog_errno(ret); + goto out_unlock; + } + + /* + * Empty the extent map so that we may get the right extent + * record from the disk. + */ + ocfs2_extent_map_trunc(inode_in, 0); + ocfs2_extent_map_trunc(inode_out, 0); + + ret = ocfs2_reflink_update_dest(inode_out, out_bh, pos_out + len); + if (ret) { + mlog_errno(ret); + goto out_unlock; + } + +out_unlock: + ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); + return remapped > 0 ? remapped : ret; } const struct inode_operations ocfs2_file_iops = { @@ -2586,8 +2641,7 @@ const struct file_operations ocfs2_fops = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, - .clone_file_range = ocfs2_file_clone_range, - .dedupe_file_range = ocfs2_file_dedupe_range, + .remap_file_range = ocfs2_remap_file_range, }; const struct file_operations ocfs2_dops = { @@ -2633,8 +2687,7 @@ const struct file_operations ocfs2_fops_no_plocks = { .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .fallocate = ocfs2_fallocate, - .clone_file_range = ocfs2_file_clone_range, - .dedupe_file_range = ocfs2_file_dedupe_range, + .remap_file_range = ocfs2_remap_file_range, }; const struct file_operations ocfs2_dops_no_plocks = { diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index bd3475694e83a0..b63c97f4318e06 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -1378,15 +1378,23 @@ static int __ocfs2_recovery_thread(void *arg) int rm_quota_used = 0, i; struct ocfs2_quota_recovery *qrec; + /* Whether the quota supported. */ + int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_USRQUOTA) + || OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, + OCFS2_FEATURE_RO_COMPAT_GRPQUOTA); + status = ocfs2_wait_on_mount(osb); if (status < 0) { goto bail; } - rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); - if (!rm_quota) { - status = -ENOMEM; - goto bail; + if (quota_enabled) { + rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS); + if (!rm_quota) { + status = -ENOMEM; + goto bail; + } } restart: status = ocfs2_super_lock(osb, 1); @@ -1422,9 +1430,14 @@ restart: * then quota usage would be out of sync until some node takes * the slot. So we remember which nodes need quota recovery * and when everything else is done, we recover quotas. */ - for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++); - if (i == rm_quota_used) - rm_quota[rm_quota_used++] = slot_num; + if (quota_enabled) { + for (i = 0; i < rm_quota_used + && rm_quota[i] != slot_num; i++) + ; + + if (i == rm_quota_used) + rm_quota[rm_quota_used++] = slot_num; + } status = ocfs2_recover_node(osb, node_num, slot_num); skip_recovery: @@ -1452,16 +1465,19 @@ skip_recovery: /* Now it is right time to recover quotas... We have to do this under * superblock lock so that no one can start using the slot (and crash) * before we recover it */ - for (i = 0; i < rm_quota_used; i++) { - qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); - if (IS_ERR(qrec)) { - status = PTR_ERR(qrec); - mlog_errno(status); - continue; + if (quota_enabled) { + for (i = 0; i < rm_quota_used; i++) { + qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]); + if (IS_ERR(qrec)) { + status = PTR_ERR(qrec); + mlog_errno(status); + continue; + } + ocfs2_queue_recovery_completion(osb->journal, + rm_quota[i], + NULL, NULL, qrec, + ORPHAN_NEED_TRUNCATE); } - ocfs2_queue_recovery_completion(osb->journal, rm_quota[i], - NULL, NULL, qrec, - ORPHAN_NEED_TRUNCATE); } ocfs2_super_unlock(osb, 1); @@ -1483,7 +1499,8 @@ bail: mutex_unlock(&osb->recovery_lock); - kfree(rm_quota); + if (quota_enabled) + kfree(rm_quota); /* no one is callint kthread_stop() for us so the kthread() api * requires that we call do_exit(). And it isn't exported, but diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 7eb3b0a6347ef7..3f1685d7d43bf3 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -25,6 +25,7 @@ #include "ocfs2_ioctl.h" #include "alloc.h" +#include "localalloc.h" #include "aops.h" #include "dlmglue.h" #include "extent_map.h" @@ -233,6 +234,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, struct ocfs2_refcount_tree *ref_tree = NULL; u32 new_phys_cpos, new_len; u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos); + int need_free = 0; if ((ext_flags & OCFS2_EXT_REFCOUNTED) && *len) { BUG_ON(!ocfs2_is_refcount_inode(inode)); @@ -308,6 +310,7 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, if (!partial) { context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE; ret = -ENOSPC; + need_free = 1; goto out_commit; } } @@ -332,6 +335,20 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, mlog_errno(ret); out_commit: + if (need_free && context->data_ac) { + struct ocfs2_alloc_context *data_ac = context->data_ac; + + if (context->data_ac->ac_which == OCFS2_AC_USE_LOCAL) + ocfs2_free_local_alloc_bits(osb, handle, data_ac, + new_phys_cpos, new_len); + else + ocfs2_free_clusters(handle, + data_ac->ac_inode, + data_ac->ac_bh, + ocfs2_clusters_to_blocks(osb->sb, new_phys_cpos), + new_len); + } + ocfs2_commit_trans(osb, handle); out_unlock_mutex: diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 1114ef02e7803f..a35259eebc5673 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4466,9 +4466,9 @@ out: } /* Update destination inode size, if necessary. */ -static int ocfs2_reflink_update_dest(struct inode *dest, - struct buffer_head *d_bh, - loff_t newlen) +int ocfs2_reflink_update_dest(struct inode *dest, + struct buffer_head *d_bh, + loff_t newlen) { handle_t *handle; int ret; @@ -4505,14 +4505,14 @@ out_commit: } /* Remap the range pos_in:len in s_inode to pos_out:len in t_inode. */ -static int ocfs2_reflink_remap_extent(struct inode *s_inode, - struct buffer_head *s_bh, - loff_t pos_in, - struct inode *t_inode, - struct buffer_head *t_bh, - loff_t pos_out, - loff_t len, - struct ocfs2_cached_dealloc_ctxt *dealloc) +static loff_t ocfs2_reflink_remap_extent(struct inode *s_inode, + struct buffer_head *s_bh, + loff_t pos_in, + struct inode *t_inode, + struct buffer_head *t_bh, + loff_t pos_out, + loff_t len, + struct ocfs2_cached_dealloc_ctxt *dealloc) { struct ocfs2_extent_tree s_et; struct ocfs2_extent_tree t_et; @@ -4520,8 +4520,9 @@ static int ocfs2_reflink_remap_extent(struct inode *s_inode, struct buffer_head *ref_root_bh = NULL; struct ocfs2_refcount_tree *ref_tree; struct ocfs2_super *osb; + loff_t remapped_bytes = 0; loff_t pstart, plen; - u32 p_cluster, num_clusters, slast, spos, tpos; + u32 p_cluster, num_clusters, slast, spos, tpos, remapped_clus = 0; unsigned int ext_flags; int ret = 0; @@ -4603,30 +4604,34 @@ static int ocfs2_reflink_remap_extent(struct inode *s_inode, next_loop: spos += num_clusters; tpos += num_clusters; + remapped_clus += num_clusters; } -out: - return ret; + goto out; out_unlock_refcount: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); - return ret; +out: + remapped_bytes = ocfs2_clusters_to_bytes(t_inode->i_sb, remapped_clus); + remapped_bytes = min_t(loff_t, len, remapped_bytes); + + return remapped_bytes > 0 ? remapped_bytes : ret; } /* Set up refcount tree and remap s_inode to t_inode. */ -static int ocfs2_reflink_remap_blocks(struct inode *s_inode, - struct buffer_head *s_bh, - loff_t pos_in, - struct inode *t_inode, - struct buffer_head *t_bh, - loff_t pos_out, - loff_t len) +loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, + struct buffer_head *s_bh, + loff_t pos_in, + struct inode *t_inode, + struct buffer_head *t_bh, + loff_t pos_out, + loff_t len) { struct ocfs2_cached_dealloc_ctxt dealloc; struct ocfs2_super *osb; struct ocfs2_dinode *dis; struct ocfs2_dinode *dit; - int ret; + loff_t ret; osb = OCFS2_SB(s_inode->i_sb); dis = (struct ocfs2_dinode *)s_bh->b_data; @@ -4698,7 +4703,7 @@ static int ocfs2_reflink_remap_blocks(struct inode *s_inode, /* Actually remap extents now. */ ret = ocfs2_reflink_remap_extent(s_inode, s_bh, pos_in, t_inode, t_bh, pos_out, len, &dealloc); - if (ret) { + if (ret < 0) { mlog_errno(ret); goto out; } @@ -4713,10 +4718,10 @@ out: } /* Lock an inode and grab a bh pointing to the inode. */ -static int ocfs2_reflink_inodes_lock(struct inode *s_inode, - struct buffer_head **bh1, - struct inode *t_inode, - struct buffer_head **bh2) +int ocfs2_reflink_inodes_lock(struct inode *s_inode, + struct buffer_head **bh1, + struct inode *t_inode, + struct buffer_head **bh2) { struct inode *inode1; struct inode *inode2; @@ -4801,10 +4806,10 @@ out_i1: } /* Unlock both inodes and release buffers. */ -static void ocfs2_reflink_inodes_unlock(struct inode *s_inode, - struct buffer_head *s_bh, - struct inode *t_inode, - struct buffer_head *t_bh) +void ocfs2_reflink_inodes_unlock(struct inode *s_inode, + struct buffer_head *s_bh, + struct inode *t_inode, + struct buffer_head *t_bh) { ocfs2_inode_unlock(s_inode, 1); ocfs2_rw_unlock(s_inode, 1); @@ -4816,82 +4821,3 @@ static void ocfs2_reflink_inodes_unlock(struct inode *s_inode, } unlock_two_nondirectories(s_inode, t_inode); } - -/* Link a range of blocks from one file to another. */ -int ocfs2_reflink_remap_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe) -{ - struct inode *inode_in = file_inode(file_in); - struct inode *inode_out = file_inode(file_out); - struct ocfs2_super *osb = OCFS2_SB(inode_in->i_sb); - struct buffer_head *in_bh = NULL, *out_bh = NULL; - bool same_inode = (inode_in == inode_out); - ssize_t ret; - - if (!ocfs2_refcount_tree(osb)) - return -EOPNOTSUPP; - if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) - return -EROFS; - - /* Lock both files against IO */ - ret = ocfs2_reflink_inodes_lock(inode_in, &in_bh, inode_out, &out_bh); - if (ret) - return ret; - - /* Check file eligibility and prepare for block sharing. */ - ret = -EINVAL; - if ((OCFS2_I(inode_in)->ip_flags & OCFS2_INODE_SYSTEM_FILE) || - (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) - goto out_unlock; - - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, - &len, is_dedupe); - if (ret <= 0) - goto out_unlock; - - /* Lock out changes to the allocation maps and remap. */ - down_write(&OCFS2_I(inode_in)->ip_alloc_sem); - if (!same_inode) - down_write_nested(&OCFS2_I(inode_out)->ip_alloc_sem, - SINGLE_DEPTH_NESTING); - - ret = ocfs2_reflink_remap_blocks(inode_in, in_bh, pos_in, inode_out, - out_bh, pos_out, len); - - /* Zap any page cache for the destination file's range. */ - if (!ret) - truncate_inode_pages_range(&inode_out->i_data, pos_out, - PAGE_ALIGN(pos_out + len) - 1); - - up_write(&OCFS2_I(inode_in)->ip_alloc_sem); - if (!same_inode) - up_write(&OCFS2_I(inode_out)->ip_alloc_sem); - if (ret) { - mlog_errno(ret); - goto out_unlock; - } - - /* - * Empty the extent map so that we may get the right extent - * record from the disk. - */ - ocfs2_extent_map_trunc(inode_in, 0); - ocfs2_extent_map_trunc(inode_out, 0); - - ret = ocfs2_reflink_update_dest(inode_out, out_bh, pos_out + len); - if (ret) { - mlog_errno(ret); - goto out_unlock; - } - - ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); - return 0; - -out_unlock: - ocfs2_reflink_inodes_unlock(inode_in, in_bh, inode_out, out_bh); - return ret; -} diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index 4af55bf4b35b97..e9e862be4a1e51 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -115,11 +115,23 @@ int ocfs2_reflink_ioctl(struct inode *inode, const char __user *oldname, const char __user *newname, bool preserve); -int ocfs2_reflink_remap_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe); +loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, + struct buffer_head *s_bh, + loff_t pos_in, + struct inode *t_inode, + struct buffer_head *t_bh, + loff_t pos_out, + loff_t len); +int ocfs2_reflink_inodes_lock(struct inode *s_inode, + struct buffer_head **bh1, + struct inode *t_inode, + struct buffer_head **bh2); +void ocfs2_reflink_inodes_unlock(struct inode *s_inode, + struct buffer_head *s_bh, + struct inode *t_inode, + struct buffer_head *t_bh); +int ocfs2_reflink_update_dest(struct inode *dest, + struct buffer_head *d_bh, + loff_t newlen); #endif /* OCFS2_REFCOUNTTREE_H */ diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index d6c350ba25b96e..c4b029c43464e0 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl"; */ static struct ocfs2_stack_plugin *active_stack; -inline int ocfs2_is_o2cb_active(void) -{ - return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB); -} -EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active); - static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name) { struct ocfs2_stack_plugin *p; diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h index e3036e1790e86d..f2dce10fae543c 100644 --- a/fs/ocfs2/stackglue.h +++ b/fs/ocfs2/stackglue.h @@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin); void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin); -/* In ocfs2_downconvert_lock(), we need to know which stack we are using */ -int ocfs2_is_o2cb_active(void); - extern struct kset *ocfs2_kset; #endif /* STACKGLUE_H */ diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 5e65d818937bb1..fe53381b26b184 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -25,7 +25,7 @@ static int read_one_page(struct page *page) struct iov_iter to; struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE}; - iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bv, 1, PAGE_SIZE); gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpage called with page %p\n", diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 1cc797a08a5b5f..9e62dcf06fc4a9 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -125,6 +125,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) struct file *new_file; loff_t old_pos = 0; loff_t new_pos = 0; + loff_t cloned; int error = 0; if (len == 0) @@ -141,11 +142,10 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) } /* Try to use clone_file_range to clone up within the same fs */ - error = do_clone_file_range(old_file, 0, new_file, 0, len); - if (!error) + cloned = do_clone_file_range(old_file, 0, new_file, 0, len, 0); + if (cloned == len) goto out; /* Couldn't clone, so now we try to copy the data */ - error = 0; /* FIXME: copy up sparse files efficiently */ while (len) { @@ -395,7 +395,6 @@ struct ovl_copy_up_ctx { struct dentry *destdir; struct qstr destname; struct dentry *workdir; - bool tmpfile; bool origin; bool indexed; bool metacopy; @@ -440,63 +439,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c) return err; } -static int ovl_install_temp(struct ovl_copy_up_ctx *c, struct dentry *temp, - struct dentry **newdentry) -{ - int err; - struct dentry *upper; - struct inode *udir = d_inode(c->destdir); - - upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len); - if (IS_ERR(upper)) - return PTR_ERR(upper); - - if (c->tmpfile) - err = ovl_do_link(temp, udir, upper); - else - err = ovl_do_rename(d_inode(c->workdir), temp, udir, upper, 0); - - if (!err) - *newdentry = dget(c->tmpfile ? upper : temp); - dput(upper); - - return err; -} - -static struct dentry *ovl_get_tmpfile(struct ovl_copy_up_ctx *c) -{ - int err; - struct dentry *temp; - const struct cred *old_creds = NULL; - struct cred *new_creds = NULL; - struct ovl_cattr cattr = { - /* Can't properly set mode on creation because of the umask */ - .mode = c->stat.mode & S_IFMT, - .rdev = c->stat.rdev, - .link = c->link - }; - - err = security_inode_copy_up(c->dentry, &new_creds); - temp = ERR_PTR(err); - if (err < 0) - goto out; - - if (new_creds) - old_creds = override_creds(new_creds); - - if (c->tmpfile) - temp = ovl_do_tmpfile(c->workdir, c->stat.mode); - else - temp = ovl_create_temp(c->workdir, &cattr); -out: - if (new_creds) { - revert_creds(old_creds); - put_cred(new_creds); - } - - return temp; -} - static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) { int err; @@ -548,51 +490,148 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp) return err; } -static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c) +struct ovl_cu_creds { + const struct cred *old; + struct cred *new; +}; + +static int ovl_prep_cu_creds(struct dentry *dentry, struct ovl_cu_creds *cc) +{ + int err; + + cc->old = cc->new = NULL; + err = security_inode_copy_up(dentry, &cc->new); + if (err < 0) + return err; + + if (cc->new) + cc->old = override_creds(cc->new); + + return 0; +} + +static void ovl_revert_cu_creds(struct ovl_cu_creds *cc) +{ + if (cc->new) { + revert_creds(cc->old); + put_cred(cc->new); + } +} + +/* + * Copyup using workdir to prepare temp file. Used when copying up directories, + * special files or when upper fs doesn't support O_TMPFILE. + */ +static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c) { - struct inode *udir = c->destdir->d_inode; struct inode *inode; - struct dentry *newdentry = NULL; - struct dentry *temp; + struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir); + struct dentry *temp, *upper; + struct ovl_cu_creds cc; int err; + struct ovl_cattr cattr = { + /* Can't properly set mode on creation because of the umask */ + .mode = c->stat.mode & S_IFMT, + .rdev = c->stat.rdev, + .link = c->link + }; + + err = ovl_lock_rename_workdir(c->workdir, c->destdir); + if (err) + return err; + + err = ovl_prep_cu_creds(c->dentry, &cc); + if (err) + goto unlock; - temp = ovl_get_tmpfile(c); + temp = ovl_create_temp(c->workdir, &cattr); + ovl_revert_cu_creds(&cc); + + err = PTR_ERR(temp); if (IS_ERR(temp)) - return PTR_ERR(temp); + goto unlock; err = ovl_copy_up_inode(c, temp); if (err) - goto out; + goto cleanup; if (S_ISDIR(c->stat.mode) && c->indexed) { err = ovl_create_index(c->dentry, c->lowerpath.dentry, temp); if (err) - goto out; + goto cleanup; } - if (c->tmpfile) { - inode_lock_nested(udir, I_MUTEX_PARENT); - err = ovl_install_temp(c, temp, &newdentry); - inode_unlock(udir); - } else { - err = ovl_install_temp(c, temp, &newdentry); - } + upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len); + err = PTR_ERR(upper); + if (IS_ERR(upper)) + goto cleanup; + + err = ovl_do_rename(wdir, temp, udir, upper, 0); + dput(upper); if (err) - goto out; + goto cleanup; if (!c->metacopy) ovl_set_upperdata(d_inode(c->dentry)); inode = d_inode(c->dentry); - ovl_inode_update(inode, newdentry); + ovl_inode_update(inode, temp); if (S_ISDIR(inode->i_mode)) ovl_set_flag(OVL_WHITEOUTS, inode); +unlock: + unlock_rename(c->workdir, c->destdir); -out: - if (err && !c->tmpfile) - ovl_cleanup(d_inode(c->workdir), temp); - dput(temp); return err; +cleanup: + ovl_cleanup(wdir, temp); + dput(temp); + goto unlock; +} + +/* Copyup using O_TMPFILE which does not require cross dir locking */ +static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) +{ + struct inode *udir = d_inode(c->destdir); + struct dentry *temp, *upper; + struct ovl_cu_creds cc; + int err; + + err = ovl_prep_cu_creds(c->dentry, &cc); + if (err) + return err; + + temp = ovl_do_tmpfile(c->workdir, c->stat.mode); + ovl_revert_cu_creds(&cc); + + if (IS_ERR(temp)) + return PTR_ERR(temp); + + err = ovl_copy_up_inode(c, temp); + if (err) + goto out_dput; + + inode_lock_nested(udir, I_MUTEX_PARENT); + + upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len); + err = PTR_ERR(upper); + if (!IS_ERR(upper)) { + err = ovl_do_link(temp, udir, upper); + dput(upper); + } + inode_unlock(udir); + + if (err) + goto out_dput; + + if (!c->metacopy) + ovl_set_upperdata(d_inode(c->dentry)); + ovl_inode_update(d_inode(c->dentry), temp); + + return 0; + +out_dput: + dput(temp); + return err; } /* @@ -646,18 +685,10 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c) } /* Should we copyup with O_TMPFILE or with workdir? */ - if (S_ISREG(c->stat.mode) && ofs->tmpfile) { - c->tmpfile = true; - err = ovl_copy_up_locked(c); - } else { - err = ovl_lock_rename_workdir(c->workdir, c->destdir); - if (!err) { - err = ovl_copy_up_locked(c); - unlock_rename(c->workdir, c->destdir); - } - } - - + if (S_ISREG(c->stat.mode) && ofs->tmpfile) + err = ovl_copy_up_tmpfile(c); + else + err = ovl_copy_up_workdir(c); if (err) goto out; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 276914ae3c60aa..c6289147c7871f 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -414,13 +414,12 @@ static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name, if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl) return 0; - size = posix_acl_to_xattr(NULL, acl, NULL, 0); + size = posix_acl_xattr_size(acl->a_count); buffer = kmalloc(size, GFP_KERNEL); if (!buffer) return -ENOMEM; - size = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); - err = size; + err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); if (err < 0) goto out_free; @@ -463,6 +462,10 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (IS_ERR(upper)) goto out_unlock; + err = -ESTALE; + if (d_is_negative(upper) || !IS_WHITEOUT(d_inode(upper))) + goto out_dput; + newdentry = ovl_create_temp(workdir, cattr); err = PTR_ERR(newdentry); if (IS_ERR(newdentry)) @@ -652,7 +655,6 @@ static int ovl_link(struct dentry *old, struct inode *newdir, struct dentry *new) { int err; - bool locked = false; struct inode *inode; err = ovl_want_write(old); @@ -663,13 +665,17 @@ static int ovl_link(struct dentry *old, struct inode *newdir, if (err) goto out_drop_write; + err = ovl_copy_up(new->d_parent); + if (err) + goto out_drop_write; + if (ovl_is_metacopy_dentry(old)) { err = ovl_set_redirect(old, false); if (err) goto out_drop_write; } - err = ovl_nlink_start(old, &locked); + err = ovl_nlink_start(old); if (err) goto out_drop_write; @@ -682,7 +688,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir, if (err) iput(inode); - ovl_nlink_end(old, locked); + ovl_nlink_end(old); out_drop_write: ovl_drop_write(old); out: @@ -807,7 +813,6 @@ static bool ovl_pure_upper(struct dentry *dentry) static int ovl_do_remove(struct dentry *dentry, bool is_dir) { int err; - bool locked = false; const struct cred *old_cred; struct dentry *upperdentry; bool lower_positive = ovl_lower_positive(dentry); @@ -828,7 +833,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) if (err) goto out_drop_write; - err = ovl_nlink_start(dentry, &locked); + err = ovl_nlink_start(dentry); if (err) goto out_drop_write; @@ -844,7 +849,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir) else drop_nlink(dentry->d_inode); } - ovl_nlink_end(dentry, locked); + ovl_nlink_end(dentry); /* * Copy ctime @@ -1008,7 +1013,6 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, unsigned int flags) { int err; - bool locked = false; struct dentry *old_upperdir; struct dentry *new_upperdir; struct dentry *olddentry; @@ -1017,6 +1021,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, bool old_opaque; bool new_opaque; bool cleanup_whiteout = false; + bool update_nlink = false; bool overwrite = !(flags & RENAME_EXCHANGE); bool is_dir = d_is_dir(old); bool new_is_dir = d_is_dir(new); @@ -1074,10 +1079,12 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, err = ovl_copy_up(new); if (err) goto out_drop_write; - } else { - err = ovl_nlink_start(new, &locked); + } else if (d_inode(new)) { + err = ovl_nlink_start(new); if (err) goto out_drop_write; + + update_nlink = true; } old_cred = ovl_override_creds(old->d_sb); @@ -1206,7 +1213,8 @@ out_unlock: unlock_rename(new_upperdir, old_upperdir); out_revert_creds: revert_creds(old_cred); - ovl_nlink_end(new, locked); + if (update_nlink) + ovl_nlink_end(new); out_drop_write: ovl_drop_write(old); out: diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 986313da0c8895..84dd957efa24a1 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -434,14 +434,14 @@ enum ovl_copyop { OVL_DEDUPE, }; -static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in, +static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, unsigned int flags, enum ovl_copyop op) + loff_t len, unsigned int flags, enum ovl_copyop op) { struct inode *inode_out = file_inode(file_out); struct fd real_in, real_out; const struct cred *old_cred; - ssize_t ret; + loff_t ret; ret = ovl_real_fdget(file_out, &real_out); if (ret) @@ -462,12 +462,13 @@ static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in, case OVL_CLONE: ret = vfs_clone_file_range(real_in.file, pos_in, - real_out.file, pos_out, len); + real_out.file, pos_out, len, flags); break; case OVL_DEDUPE: ret = vfs_dedupe_file_range_one(real_in.file, pos_in, - real_out.file, pos_out, len); + real_out.file, pos_out, len, + flags); break; } revert_creds(old_cred); @@ -489,26 +490,31 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in, OVL_COPY); } -static int ovl_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { - return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0, - OVL_CLONE); -} + enum ovl_copyop op; + + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + + if (remap_flags & REMAP_FILE_DEDUP) + op = OVL_DEDUPE; + else + op = OVL_CLONE; -static int ovl_dedupe_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) -{ /* * Don't copy up because of a dedupe request, this wouldn't make sense * most of the time (data would be duplicated instead of deduplicated). */ - if (!ovl_inode_upper(file_inode(file_in)) || - !ovl_inode_upper(file_inode(file_out))) + if (op == OVL_DEDUPE && + (!ovl_inode_upper(file_inode(file_in)) || + !ovl_inode_upper(file_inode(file_out)))) return -EPERM; - return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0, - OVL_DEDUPE); + return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, + remap_flags, op); } const struct file_operations ovl_file_operations = { @@ -525,6 +531,5 @@ const struct file_operations ovl_file_operations = { .compat_ioctl = ovl_compat_ioctl, .copy_file_range = ovl_copy_file_range, - .clone_file_range = ovl_clone_file_range, - .dedupe_file_range = ovl_dedupe_file_range, + .remap_file_range = ovl_remap_file_range, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 3b7ed5d2279c6a..6bcc9dedc342cc 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -286,13 +286,22 @@ int ovl_permission(struct inode *inode, int mask) if (err) return err; - old_cred = ovl_override_creds(inode->i_sb); - if (!upperinode && - !special_file(realinode->i_mode) && mask & MAY_WRITE) { + /* No need to do any access on underlying for special files */ + if (special_file(realinode->i_mode)) + return 0; + + /* No need to access underlying for execute */ + mask &= ~MAY_EXEC; + if ((mask & (MAY_READ | MAY_WRITE)) == 0) + return 0; + + /* Lower files get copied up, so turn write access into read */ + if (!upperinode && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); - /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } + + old_cred = ovl_override_creds(inode->i_sb); err = inode_permission(realinode, mask); revert_creds(old_cred); diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 9c0ca6a7becfbe..efd372312ef100 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -422,8 +422,10 @@ int ovl_verify_set_fh(struct dentry *dentry, const char *name, fh = ovl_encode_real_fh(real, is_upper); err = PTR_ERR(fh); - if (IS_ERR(fh)) + if (IS_ERR(fh)) { + fh = NULL; goto fail; + } err = ovl_verify_fh(dentry, name, fh); if (set && err == -ENODATA) diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index a3c0d95843121e..5e45cb3630a06f 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -271,8 +271,8 @@ bool ovl_test_flag(unsigned long flag, struct inode *inode); bool ovl_inuse_trylock(struct dentry *dentry); void ovl_inuse_unlock(struct dentry *dentry); bool ovl_need_index(struct dentry *dentry); -int ovl_nlink_start(struct dentry *dentry, bool *locked); -void ovl_nlink_end(struct dentry *dentry, bool locked); +int ovl_nlink_start(struct dentry *dentry); +void ovl_nlink_end(struct dentry *dentry); int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir); int ovl_check_metacopy_xattr(struct dentry *dentry); bool ovl_is_metacopy_dentry(struct dentry *dentry); @@ -290,6 +290,16 @@ static inline unsigned int ovl_xino_bits(struct super_block *sb) return ofs->xino_bits; } +static inline int ovl_inode_lock(struct inode *inode) +{ + return mutex_lock_interruptible(&OVL_I(inode)->lock); +} + +static inline void ovl_inode_unlock(struct inode *inode) +{ + mutex_unlock(&OVL_I(inode)->lock); +} + /* namei.c */ int ovl_check_fh_len(struct ovl_fh *fh, int fh_len); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 30adc9d408a0df..0116735cc32147 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -472,6 +472,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; int err; + bool metacopy_opt = false, redirect_opt = false; config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL); if (!config->redirect_mode) @@ -516,6 +517,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->redirect_mode = match_strdup(&args[0]); if (!config->redirect_mode) return -ENOMEM; + redirect_opt = true; break; case OPT_INDEX_ON: @@ -548,6 +550,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) case OPT_METACOPY_ON: config->metacopy = true; + metacopy_opt = true; break; case OPT_METACOPY_OFF: @@ -572,13 +575,32 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) if (err) return err; - /* metacopy feature with upper requires redirect_dir=on */ - if (config->upperdir && config->metacopy && !config->redirect_dir) { - pr_warn("overlayfs: metadata only copy up requires \"redirect_dir=on\", falling back to metacopy=off.\n"); - config->metacopy = false; - } else if (config->metacopy && !config->redirect_follow) { - pr_warn("overlayfs: metadata only copy up requires \"redirect_dir=follow\" on non-upper mount, falling back to metacopy=off.\n"); - config->metacopy = false; + /* + * This is to make the logic below simpler. It doesn't make any other + * difference, since config->redirect_dir is only used for upper. + */ + if (!config->upperdir && config->redirect_follow) + config->redirect_dir = true; + + /* Resolve metacopy -> redirect_dir dependency */ + if (config->metacopy && !config->redirect_dir) { + if (metacopy_opt && redirect_opt) { + pr_err("overlayfs: conflicting options: metacopy=on,redirect_dir=%s\n", + config->redirect_mode); + return -EINVAL; + } + if (redirect_opt) { + /* + * There was an explicit redirect_dir=... that resulted + * in this conflict. + */ + pr_info("overlayfs: disabling metacopy due to redirect_dir=%s\n", + config->redirect_mode); + config->metacopy = false; + } else { + /* Automatically enable redirect otherwise. */ + config->redirect_follow = config->redirect_dir = true; + } } return 0; @@ -1175,9 +1197,29 @@ out: return err; } +static bool ovl_lower_uuid_ok(struct ovl_fs *ofs, const uuid_t *uuid) +{ + unsigned int i; + + if (!ofs->config.nfs_export && !(ofs->config.index && ofs->upper_mnt)) + return true; + + for (i = 0; i < ofs->numlowerfs; i++) { + /* + * We use uuid to associate an overlay lower file handle with a + * lower layer, so we can accept lower fs with null uuid as long + * as all lower layers with null uuid are on the same fs. + */ + if (uuid_equal(&ofs->lower_fs[i].sb->s_uuid, uuid)) + return false; + } + return true; +} + /* Get a unique fsid for the layer */ -static int ovl_get_fsid(struct ovl_fs *ofs, struct super_block *sb) +static int ovl_get_fsid(struct ovl_fs *ofs, const struct path *path) { + struct super_block *sb = path->mnt->mnt_sb; unsigned int i; dev_t dev; int err; @@ -1191,6 +1233,14 @@ static int ovl_get_fsid(struct ovl_fs *ofs, struct super_block *sb) return i + 1; } + if (!ovl_lower_uuid_ok(ofs, &sb->s_uuid)) { + ofs->config.index = false; + ofs->config.nfs_export = false; + pr_warn("overlayfs: %s uuid detected in lower fs '%pd2', falling back to index=off,nfs_export=off.\n", + uuid_is_null(&sb->s_uuid) ? "null" : "conflicting", + path->dentry); + } + err = get_anon_bdev(&dev); if (err) { pr_err("overlayfs: failed to get anonymous bdev for lowerpath\n"); @@ -1225,7 +1275,7 @@ static int ovl_get_lower_layers(struct ovl_fs *ofs, struct path *stack, struct vfsmount *mnt; int fsid; - err = fsid = ovl_get_fsid(ofs, stack[i].mnt->mnt_sb); + err = fsid = ovl_get_fsid(ofs, &stack[i]); if (err < 0) goto out; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index ace4fe4c39a930..7c01327b185205 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -65,8 +65,7 @@ struct super_block *ovl_same_sb(struct super_block *sb) */ int ovl_can_decode_fh(struct super_block *sb) { - if (!sb->s_export_op || !sb->s_export_op->fh_to_dentry || - uuid_is_null(&sb->s_uuid)) + if (!sb->s_export_op || !sb->s_export_op->fh_to_dentry) return 0; return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN; @@ -522,13 +521,13 @@ bool ovl_already_copied_up(struct dentry *dentry, int flags) int ovl_copy_up_start(struct dentry *dentry, int flags) { - struct ovl_inode *oi = OVL_I(d_inode(dentry)); + struct inode *inode = d_inode(dentry); int err; - err = mutex_lock_interruptible(&oi->lock); + err = ovl_inode_lock(inode); if (!err && ovl_already_copied_up_locked(dentry, flags)) { err = 1; /* Already copied up */ - mutex_unlock(&oi->lock); + ovl_inode_unlock(inode); } return err; @@ -536,7 +535,7 @@ int ovl_copy_up_start(struct dentry *dentry, int flags) void ovl_copy_up_end(struct dentry *dentry) { - mutex_unlock(&OVL_I(d_inode(dentry))->lock); + ovl_inode_unlock(d_inode(dentry)); } bool ovl_check_origin_xattr(struct dentry *dentry) @@ -739,14 +738,14 @@ fail: * Operations that change overlay inode and upper inode nlink need to be * synchronized with copy up for persistent nlink accounting. */ -int ovl_nlink_start(struct dentry *dentry, bool *locked) +int ovl_nlink_start(struct dentry *dentry) { - struct ovl_inode *oi = OVL_I(d_inode(dentry)); + struct inode *inode = d_inode(dentry); const struct cred *old_cred; int err; - if (!d_inode(dentry)) - return 0; + if (WARN_ON(!inode)) + return -ENOENT; /* * With inodes index is enabled, we store the union overlay nlink @@ -768,11 +767,11 @@ int ovl_nlink_start(struct dentry *dentry, bool *locked) return err; } - err = mutex_lock_interruptible(&oi->lock); + err = ovl_inode_lock(inode); if (err) return err; - if (d_is_dir(dentry) || !ovl_test_flag(OVL_INDEX, d_inode(dentry))) + if (d_is_dir(dentry) || !ovl_test_flag(OVL_INDEX, inode)) goto out; old_cred = ovl_override_creds(dentry->d_sb); @@ -787,27 +786,24 @@ int ovl_nlink_start(struct dentry *dentry, bool *locked) out: if (err) - mutex_unlock(&oi->lock); - else - *locked = true; + ovl_inode_unlock(inode); return err; } -void ovl_nlink_end(struct dentry *dentry, bool locked) +void ovl_nlink_end(struct dentry *dentry) { - if (locked) { - if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) && - d_inode(dentry)->i_nlink == 0) { - const struct cred *old_cred; + struct inode *inode = d_inode(dentry); - old_cred = ovl_override_creds(dentry->d_sb); - ovl_cleanup_index(dentry); - revert_creds(old_cred); - } + if (ovl_test_flag(OVL_INDEX, inode) && inode->i_nlink == 0) { + const struct cred *old_cred; - mutex_unlock(&OVL_I(d_inode(dentry))->lock); + old_cred = ovl_override_creds(dentry->d_sb); + ovl_cleanup_index(dentry); + revert_creds(old_cred); } + + ovl_inode_unlock(inode); } int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir) diff --git a/fs/proc/base.c b/fs/proc/base.c index 7e9f07bf260d20..ce34654794472d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2905,6 +2905,21 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_STACKLEAK_METRICS +static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + unsigned long prev_depth = THREAD_SIZE - + (task->prev_lowest_stack & (THREAD_SIZE - 1)); + unsigned long depth = THREAD_SIZE - + (task->lowest_stack & (THREAD_SIZE - 1)); + + seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", + prev_depth, depth); + return 0; +} +#endif /* CONFIG_STACKLEAK_METRICS */ + /* * Thread groups */ @@ -3006,6 +3021,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_STACKLEAK_METRICS + ONE("stack_depth", S_IRUGO, proc_stack_depth), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/read_write.c b/fs/read_write.c index 603794b207ebad..bfcb4ced5664c0 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1407,7 +1407,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, goto fput_in; if (!(out.file->f_mode & FMODE_WRITE)) goto fput_out; - retval = -EINVAL; in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; @@ -1588,11 +1587,15 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * Try cloning first, this is supported by more file systems, and * more efficient if both clone and copy are supported (e.g. NFS). */ - if (file_in->f_op->clone_file_range) { - ret = file_in->f_op->clone_file_range(file_in, pos_in, - file_out, pos_out, len); - if (ret == 0) { - ret = len; + if (file_in->f_op->remap_file_range) { + loff_t cloned; + + cloned = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, + min_t(loff_t, MAX_RW_COUNT, len), + REMAP_FILE_CAN_SHORTEN); + if (cloned > 0) { + ret = cloned; goto done; } } @@ -1686,11 +1689,12 @@ out2: return ret; } -static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) +static int remap_verify_area(struct file *file, loff_t pos, loff_t len, + bool write) { struct inode *inode = file_inode(file); - if (unlikely(pos < 0)) + if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely((loff_t) (pos + len) < 0)) @@ -1708,22 +1712,150 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) return security_file_permission(file, write ? MAY_WRITE : MAY_READ); } +/* + * Ensure that we don't remap a partial EOF block in the middle of something + * else. Assume that the offsets have already been checked for block + * alignment. + * + * For deduplication we always scale down to the previous block because we + * can't meaningfully compare post-EOF contents. + * + * For clone we only link a partial EOF block above the destination file's EOF. + * + * Shorten the request if possible. + */ +static int generic_remap_check_len(struct inode *inode_in, + struct inode *inode_out, + loff_t pos_out, + loff_t *len, + unsigned int remap_flags) +{ + u64 blkmask = i_blocksize(inode_in) - 1; + loff_t new_len = *len; + + if ((*len & blkmask) == 0) + return 0; + + if ((remap_flags & REMAP_FILE_DEDUP) || + pos_out + *len < i_size_read(inode_out)) + new_len &= ~blkmask; + + if (new_len == *len) + return 0; + + if (remap_flags & REMAP_FILE_CAN_SHORTEN) { + *len = new_len; + return 0; + } + + return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; +} + +/* + * Read a page's worth of file data into the page cache. Return the page + * locked. + */ +static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) +{ + struct page *page; + + page = read_mapping_page(inode->i_mapping, offset >> PAGE_SHIFT, NULL); + if (IS_ERR(page)) + return page; + if (!PageUptodate(page)) { + put_page(page); + return ERR_PTR(-EIO); + } + lock_page(page); + return page; +} + +/* + * Compare extents of two files to see if they are the same. + * Caller must have locked both inodes to prevent write races. + */ +static int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, + struct inode *dest, loff_t destoff, + loff_t len, bool *is_same) +{ + loff_t src_poff; + loff_t dest_poff; + void *src_addr; + void *dest_addr; + struct page *src_page; + struct page *dest_page; + loff_t cmp_len; + bool same; + int error; + + error = -EINVAL; + same = true; + while (len) { + src_poff = srcoff & (PAGE_SIZE - 1); + dest_poff = destoff & (PAGE_SIZE - 1); + cmp_len = min(PAGE_SIZE - src_poff, + PAGE_SIZE - dest_poff); + cmp_len = min(cmp_len, len); + if (cmp_len <= 0) + goto out_error; + + src_page = vfs_dedupe_get_page(src, srcoff); + if (IS_ERR(src_page)) { + error = PTR_ERR(src_page); + goto out_error; + } + dest_page = vfs_dedupe_get_page(dest, destoff); + if (IS_ERR(dest_page)) { + error = PTR_ERR(dest_page); + unlock_page(src_page); + put_page(src_page); + goto out_error; + } + src_addr = kmap_atomic(src_page); + dest_addr = kmap_atomic(dest_page); + + flush_dcache_page(src_page); + flush_dcache_page(dest_page); + + if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) + same = false; + + kunmap_atomic(dest_addr); + kunmap_atomic(src_addr); + unlock_page(dest_page); + unlock_page(src_page); + put_page(dest_page); + put_page(src_page); + + if (!same) + break; + + srcoff += cmp_len; + destoff += cmp_len; + len -= cmp_len; + } + + *is_same = same; + return 0; + +out_error: + return error; +} /* * Check that the two inodes are eligible for cloning, the ranges make * sense, and then flush all dirty data. Caller must ensure that the * inodes have been locked against any other modifications. * - * Returns: 0 for "nothing to clone", 1 for "something to clone", or - * the usual negative error code. + * If there's an error, then the usual negative error code is returned. + * Otherwise returns 0 with *len set to the request length. */ -int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe) +int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *len, unsigned int remap_flags) { - loff_t bs = inode_out->i_sb->s_blocksize; - loff_t blen; - loff_t isize; + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; @@ -1740,50 +1872,24 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; - /* Are we going all the way to the end? */ - isize = i_size_read(inode_in); - if (isize == 0) - return 0; - /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { - if (is_dedupe || pos_in == isize) + loff_t isize = i_size_read(inode_in); + + if ((remap_flags & REMAP_FILE_DEDUP) || pos_in == isize) return 0; if (pos_in > isize) return -EINVAL; *len = isize - pos_in; + if (*len == 0) + return 0; } - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + *len < pos_in || pos_out + *len < pos_out || - pos_in + *len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + *len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + *len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = *len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode) { - if (pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - } + /* Check that we don't violate system file offset limits. */ + ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, + remap_flags); + if (ret) + return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); @@ -1803,7 +1909,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, /* * Check that the extents are the same. */ - if (is_dedupe) { + if (remap_flags & REMAP_FILE_DEDUP) { bool is_same = false; ret = vfs_dedupe_file_range_compare(inode_in, pos_in, @@ -1814,16 +1920,43 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, return -EBADE; } - return 1; + ret = generic_remap_check_len(inode_in, inode_out, pos_out, len, + remap_flags); + if (ret) + return ret; + + /* If can't alter the file contents, we're done. */ + if (!(remap_flags & REMAP_FILE_DEDUP)) { + /* Update the timestamps, since we can alter file contents. */ + if (!(file_out->f_mode & FMODE_NOCMTIME)) { + ret = file_update_time(file_out); + if (ret) + return ret; + } + + /* + * Clear the security bits if the process is not being run by + * root. This keeps people from modifying setuid and setgid + * binaries. + */ + ret = file_remove_privs(file_out); + if (ret) + return ret; + } + + return 0; } -EXPORT_SYMBOL(vfs_clone_file_prep_inodes); +EXPORT_SYMBOL(generic_remap_file_range_prep); -int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); - int ret; + loff_t ret; + + WARN_ON_ONCE(remap_flags); if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; @@ -1843,155 +1976,76 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, (file_out->f_flags & O_APPEND)) return -EBADF; - if (!file_in->f_op->clone_file_range) + if (!file_in->f_op->remap_file_range) return -EOPNOTSUPP; - ret = clone_verify_area(file_in, pos_in, len, false); + ret = remap_verify_area(file_in, pos_in, len, false); if (ret) return ret; - ret = clone_verify_area(file_out, pos_out, len, true); + ret = remap_verify_area(file_out, pos_out, len, true); if (ret) return ret; - if (pos_in + len > i_size_read(inode_in)) - return -EINVAL; - - ret = file_in->f_op->clone_file_range(file_in, pos_in, - file_out, pos_out, len); - if (!ret) { - fsnotify_access(file_in); - fsnotify_modify(file_out); - } + ret = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, len, remap_flags); + if (ret < 0) + return ret; + fsnotify_access(file_in); + fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(do_clone_file_range); -int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { - int ret; + loff_t ret; file_start_write(file_out); - ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len); + ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len, + remap_flags); file_end_write(file_out); return ret; } EXPORT_SYMBOL(vfs_clone_file_range); -/* - * Read a page's worth of file data into the page cache. Return the page - * locked. - */ -static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset) +/* Check whether we are allowed to dedupe the destination file */ +static bool allow_file_dedupe(struct file *file) { - struct address_space *mapping; - struct page *page; - pgoff_t n; - - n = offset >> PAGE_SHIFT; - mapping = inode->i_mapping; - page = read_mapping_page(mapping, n, NULL); - if (IS_ERR(page)) - return page; - if (!PageUptodate(page)) { - put_page(page); - return ERR_PTR(-EIO); - } - lock_page(page); - return page; + if (capable(CAP_SYS_ADMIN)) + return true; + if (file->f_mode & FMODE_WRITE) + return true; + if (uid_eq(current_fsuid(), file_inode(file)->i_uid)) + return true; + if (!inode_permission(file_inode(file), MAY_WRITE)) + return true; + return false; } -/* - * Compare extents of two files to see if they are the same. - * Caller must have locked both inodes to prevent write races. - */ -int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same) +loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len, unsigned int remap_flags) { - loff_t src_poff; - loff_t dest_poff; - void *src_addr; - void *dest_addr; - struct page *src_page; - struct page *dest_page; - loff_t cmp_len; - bool same; - int error; - - error = -EINVAL; - same = true; - while (len) { - src_poff = srcoff & (PAGE_SIZE - 1); - dest_poff = destoff & (PAGE_SIZE - 1); - cmp_len = min(PAGE_SIZE - src_poff, - PAGE_SIZE - dest_poff); - cmp_len = min(cmp_len, len); - if (cmp_len <= 0) - goto out_error; - - src_page = vfs_dedupe_get_page(src, srcoff); - if (IS_ERR(src_page)) { - error = PTR_ERR(src_page); - goto out_error; - } - dest_page = vfs_dedupe_get_page(dest, destoff); - if (IS_ERR(dest_page)) { - error = PTR_ERR(dest_page); - unlock_page(src_page); - put_page(src_page); - goto out_error; - } - src_addr = kmap_atomic(src_page); - dest_addr = kmap_atomic(dest_page); + loff_t ret; - flush_dcache_page(src_page); - flush_dcache_page(dest_page); - - if (memcmp(src_addr + src_poff, dest_addr + dest_poff, cmp_len)) - same = false; - - kunmap_atomic(dest_addr); - kunmap_atomic(src_addr); - unlock_page(dest_page); - unlock_page(src_page); - put_page(dest_page); - put_page(src_page); - - if (!same) - break; - - srcoff += cmp_len; - destoff += cmp_len; - len -= cmp_len; - } - - *is_same = same; - return 0; - -out_error: - return error; -} -EXPORT_SYMBOL(vfs_dedupe_file_range_compare); - -int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, u64 len) -{ - s64 ret; + WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | + REMAP_FILE_CAN_SHORTEN)); ret = mnt_want_write_file(dst_file); if (ret) return ret; - ret = clone_verify_area(dst_file, dst_pos, len, true); + ret = remap_verify_area(dst_file, dst_pos, len, true); if (ret < 0) goto out_drop_write; - ret = -EINVAL; - if (!(capable(CAP_SYS_ADMIN) || (dst_file->f_mode & FMODE_WRITE))) + ret = -EPERM; + if (!allow_file_dedupe(dst_file)) goto out_drop_write; ret = -EXDEV; @@ -2003,11 +2057,16 @@ int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, goto out_drop_write; ret = -EINVAL; - if (!dst_file->f_op->dedupe_file_range) + if (!dst_file->f_op->remap_file_range) goto out_drop_write; - ret = dst_file->f_op->dedupe_file_range(src_file, src_pos, - dst_file, dst_pos, len); + if (len == 0) { + ret = 0; + goto out_drop_write; + } + + ret = dst_file->f_op->remap_file_range(src_file, src_pos, dst_file, + dst_pos, len, remap_flags | REMAP_FILE_DEDUP); out_drop_write: mnt_drop_write_file(dst_file); @@ -2024,7 +2083,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) int i; int ret; u16 count = same->dest_count; - int deduped; + loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; @@ -2043,7 +2102,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) if (!S_ISREG(src->i_mode)) goto out; - ret = clone_verify_area(file, off, len, false); + ret = remap_verify_area(file, off, len, false); if (ret < 0) goto out; ret = 0; @@ -2075,7 +2134,8 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) } deduped = vfs_dedupe_file_range_one(file, off, dst_file, - info->dest_offset, len); + info->dest_offset, len, + REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) diff --git a/fs/splice.c b/fs/splice.c index b3daa971f59771..3553f1956508da 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -301,7 +301,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct kiocb kiocb; int idx, ret; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); + iov_iter_pipe(&to, READ, pipe, len); idx = to.idx; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; @@ -386,7 +386,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, */ offset = *ppos & ~PAGE_MASK; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset); + iov_iter_pipe(&to, READ, pipe, len + offset); res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base); if (res <= 0) @@ -745,8 +745,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, left -= this_len; } - iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n, - sd.total_len - left); + iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left); ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 61a5ad2600e865..53c9ab8fb777f4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -919,28 +919,67 @@ out_unlock: return error; } -STATIC int -xfs_file_clone_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) -{ - return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, false); -} -STATIC int -xfs_file_dedupe_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len) +loff_t +xfs_file_remap_range( + struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + loff_t len, + unsigned int remap_flags) { - return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, true); + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); + struct xfs_mount *mp = src->i_mount; + loff_t remapped = 0; + xfs_extlen_t cowextsize; + int ret; + + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) + return -EINVAL; + + if (!xfs_sb_version_hasreflink(&mp->m_sb)) + return -EOPNOTSUPP; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + /* Prepare and then clone file data. */ + ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out, + &len, remap_flags); + if (ret < 0 || len == 0) + return ret; + + trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + + ret = xfs_reflink_remap_blocks(src, pos_in, dest, pos_out, len, + &remapped); + if (ret) + goto out_unlock; + + /* + * Carry the cowextsize hint from src to dest if we're sharing the + * entire source file to the entire destination file, the source file + * has a cowextsize hint, and the destination file does not. + */ + cowextsize = 0; + if (pos_in == 0 && len == i_size_read(inode_in) && + (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && + pos_out == 0 && len >= i_size_read(inode_out) && + !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) + cowextsize = src->i_d.di_cowextsize; + + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, + remap_flags); + +out_unlock: + xfs_reflink_remap_unlock(file_in, file_out); + if (ret) + trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + return remapped > 0 ? remapped : ret; } STATIC int @@ -1175,8 +1214,7 @@ const struct file_operations xfs_file_operations = { .fsync = xfs_file_fsync, .get_unmapped_area = thp_get_unmapped_area, .fallocate = xfs_file_fallocate, - .clone_file_range = xfs_file_clone_range, - .dedupe_file_range = xfs_file_dedupe_range, + .remap_file_range = xfs_file_remap_range, }; const struct file_operations xfs_dir_file_operations = { diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 8eaeec9d58ed67..ecdb086bc23e55 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -913,18 +913,18 @@ out_error: /* * Update destination inode size & cowextsize hint, if necessary. */ -STATIC int +int xfs_reflink_update_dest( struct xfs_inode *dest, xfs_off_t newlen, xfs_extlen_t cowextsize, - bool is_dedupe) + unsigned int remap_flags) { struct xfs_mount *mp = dest->i_mount; struct xfs_trans *tp; int error; - if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) + if (newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0) return 0; error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp); @@ -945,10 +945,6 @@ xfs_reflink_update_dest( dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; } - if (!is_dedupe) { - xfs_trans_ichgtime(tp, dest, - XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG); - } xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE); error = xfs_trans_commit(tp); @@ -1112,19 +1108,28 @@ out: /* * Iteratively remap one file's extents (and holes) to another's. */ -STATIC int +int xfs_reflink_remap_blocks( struct xfs_inode *src, - xfs_fileoff_t srcoff, + loff_t pos_in, struct xfs_inode *dest, - xfs_fileoff_t destoff, - xfs_filblks_t len, - xfs_off_t new_isize) + loff_t pos_out, + loff_t remap_len, + loff_t *remapped) { struct xfs_bmbt_irec imap; + xfs_fileoff_t srcoff; + xfs_fileoff_t destoff; + xfs_filblks_t len; + xfs_filblks_t range_len; + xfs_filblks_t remapped_len = 0; + xfs_off_t new_isize = pos_out + remap_len; int nimaps; int error = 0; - xfs_filblks_t range_len; + + destoff = XFS_B_TO_FSBT(src->i_mount, pos_out); + srcoff = XFS_B_TO_FSBT(src->i_mount, pos_in); + len = XFS_B_TO_FSB(src->i_mount, remap_len); /* drange = (destoff, destoff + len); srange = (srcoff, srcoff + len) */ while (len) { @@ -1139,7 +1144,7 @@ xfs_reflink_remap_blocks( error = xfs_bmapi_read(src, srcoff, len, &imap, &nimaps, 0); xfs_iunlock(src, lock_mode); if (error) - goto err; + break; ASSERT(nimaps == 1); trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_IO_OVERWRITE, @@ -1153,23 +1158,24 @@ xfs_reflink_remap_blocks( error = xfs_reflink_remap_extent(dest, &imap, destoff, new_isize); if (error) - goto err; + break; if (fatal_signal_pending(current)) { error = -EINTR; - goto err; + break; } /* Advance drange/srange */ srcoff += range_len; destoff += range_len; len -= range_len; + remapped_len += range_len; } - return 0; - -err: - trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_); + if (error) + trace_xfs_reflink_remap_blocks_error(dest, error, _RET_IP_); + *remapped = min_t(loff_t, remap_len, + XFS_FSB_TO_B(src->i_mount, remapped_len)); return error; } @@ -1218,7 +1224,7 @@ retry: } /* Unlock both inodes after they've been prepped for a range clone. */ -STATIC void +void xfs_reflink_remap_unlock( struct file *file_in, struct file *file_out) @@ -1286,21 +1292,20 @@ xfs_reflink_zero_posteof( * stale data in the destination file. Hence we reject these clone attempts with * -EINVAL in this case. */ -STATIC int +int xfs_reflink_remap_prep( struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, - bool is_dedupe) + loff_t *len, + unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct xfs_inode *src = XFS_I(inode_in); struct inode *inode_out = file_inode(file_out); struct xfs_inode *dest = XFS_I(inode_out); bool same_inode = (inode_in == inode_out); - u64 blkmask = i_blocksize(inode_in) - 1; ssize_t ret; /* Lock both files against IO */ @@ -1323,29 +1328,11 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, - len, is_dedupe); - if (ret <= 0) + ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out, + len, remap_flags); + if (ret < 0 || *len == 0) goto out_unlock; - /* - * If the dedupe data matches, chop off the partial EOF block - * from the source file so we don't try to dedupe the partial - * EOF block. - */ - if (is_dedupe) { - *len &= ~blkmask; - } else if (*len & blkmask) { - /* - * The user is attempting to share a partial EOF block, - * if it's inside the destination EOF then reject it. - */ - if (pos_out + *len < i_size_read(inode_out)) { - ret = -EINVAL; - goto out_unlock; - } - } - /* Attach dquots to dest inode before changing block map */ ret = xfs_qm_dqattach(dest); if (ret) @@ -1365,31 +1352,9 @@ xfs_reflink_remap_prep( goto out_unlock; /* Zap any page cache for the destination file's range. */ - truncate_inode_pages_range(&inode_out->i_data, pos_out, - PAGE_ALIGN(pos_out + *len) - 1); - - /* If we're altering the file contents... */ - if (!is_dedupe) { - /* - * ...update the timestamps (which will grab the ilock again - * from xfs_fs_dirty_inode, so we have to call it before we - * take the ilock). - */ - if (!(file_out->f_mode & FMODE_NOCMTIME)) { - ret = file_update_time(file_out); - if (ret) - goto out_unlock; - } - - /* - * ...clear the security bits if the process is not being run - * by root. This keeps people from modifying setuid and setgid - * binaries. - */ - ret = file_remove_privs(file_out); - if (ret) - goto out_unlock; - } + truncate_inode_pages_range(&inode_out->i_data, + round_down(pos_out, PAGE_SIZE), + round_up(pos_out + *len, PAGE_SIZE) - 1); return 1; out_unlock: @@ -1398,72 +1363,6 @@ out_unlock: } /* - * Link a range of blocks from one file to another. - */ -int -xfs_reflink_remap_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe) -{ - struct inode *inode_in = file_inode(file_in); - struct xfs_inode *src = XFS_I(inode_in); - struct inode *inode_out = file_inode(file_out); - struct xfs_inode *dest = XFS_I(inode_out); - struct xfs_mount *mp = src->i_mount; - xfs_fileoff_t sfsbno, dfsbno; - xfs_filblks_t fsblen; - xfs_extlen_t cowextsize; - ssize_t ret; - - if (!xfs_sb_version_hasreflink(&mp->m_sb)) - return -EOPNOTSUPP; - - if (XFS_FORCED_SHUTDOWN(mp)) - return -EIO; - - /* Prepare and then clone file data. */ - ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out, - &len, is_dedupe); - if (ret <= 0) - return ret; - - trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); - - dfsbno = XFS_B_TO_FSBT(mp, pos_out); - sfsbno = XFS_B_TO_FSBT(mp, pos_in); - fsblen = XFS_B_TO_FSB(mp, len); - ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, - pos_out + len); - if (ret) - goto out_unlock; - - /* - * Carry the cowextsize hint from src to dest if we're sharing the - * entire source file to the entire destination file, the source file - * has a cowextsize hint, and the destination file does not. - */ - cowextsize = 0; - if (pos_in == 0 && len == i_size_read(inode_in) && - (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && - pos_out == 0 && len >= i_size_read(inode_out) && - !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) - cowextsize = src->i_d.di_cowextsize; - - ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize, - is_dedupe); - -out_unlock: - xfs_reflink_remap_unlock(file_in, file_out); - if (ret) - trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); - return ret; -} - -/* * The user wants to preemptively CoW all shared blocks in this file, * which enables us to turn off the reflink flag. Iterate all * extents which are not prealloc/delalloc to see which ranges are diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 7f47202b563914..6d73daef1f1323 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -27,13 +27,24 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); -extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); +extern loff_t xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t len, + unsigned int remap_flags); extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *has_shared); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, struct xfs_trans **tpp); extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t len); +extern int xfs_reflink_remap_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t *len, + unsigned int remap_flags); +extern int xfs_reflink_remap_blocks(struct xfs_inode *src, loff_t pos_in, + struct xfs_inode *dest, loff_t pos_out, loff_t remap_len, + loff_t *remapped); +extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen, + xfs_extlen_t cowextsize, unsigned int remap_flags); +extern void xfs_reflink_remap_unlock(struct file *file_in, + struct file *file_out); #endif /* __XFS_REFLINK_H */ diff --git a/include/crypto/asym_tpm_subtype.h b/include/crypto/asym_tpm_subtype.h new file mode 100644 index 00000000000000..48198c36d6b9bd --- /dev/null +++ b/include/crypto/asym_tpm_subtype.h @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _LINUX_ASYM_TPM_SUBTYPE_H +#define _LINUX_ASYM_TPM_SUBTYPE_H + +#include <linux/keyctl.h> + +struct tpm_key { + void *blob; + u32 blob_len; + uint16_t key_len; /* Size in bits of the key */ + const void *pub_key; /* pointer inside blob to the public key bytes */ + uint16_t pub_key_len; /* length of the public key */ +}; + +struct tpm_key *tpm_key_create(const void *blob, uint32_t blob_len); + +extern struct asymmetric_key_subtype asym_tpm_subtype; + +#endif /* _LINUX_ASYM_TPM_SUBTYPE_H */ diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h index e0b681a717bac9..be626eac911338 100644 --- a/include/crypto/public_key.h +++ b/include/crypto/public_key.h @@ -14,6 +14,8 @@ #ifndef _LINUX_PUBLIC_KEY_H #define _LINUX_PUBLIC_KEY_H +#include <linux/keyctl.h> + /* * Cryptographic data for the public-key subtype of the asymmetric key type. * @@ -23,6 +25,7 @@ struct public_key { void *key; u32 keylen; + bool key_is_private; const char *id_type; const char *pkey_algo; }; @@ -40,6 +43,7 @@ struct public_key_signature { u8 digest_size; /* Number of bytes in digest */ const char *pkey_algo; const char *hash_algo; + const char *encoding; }; extern void public_key_signature_free(struct public_key_signature *sig); @@ -65,8 +69,14 @@ extern int restrict_link_by_key_or_keyring_chain(struct key *trust_keyring, const union key_payload *payload, struct key *trusted); -extern int verify_signature(const struct key *key, - const struct public_key_signature *sig); +extern int query_asymmetric_key(const struct kernel_pkey_params *, + struct kernel_pkey_query *); + +extern int encrypt_blob(struct kernel_pkey_params *, const void *, void *); +extern int decrypt_blob(struct kernel_pkey_params *, const void *, void *); +extern int create_signature(struct kernel_pkey_params *, const void *, void *); +extern int verify_signature(const struct key *, + const struct public_key_signature *); int public_key_verify_signature(const struct public_key *pkey, const struct public_key_signature *sig); diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h index 91a877fa00cb59..9ccad6b062f2bb 100644 --- a/include/drm/drm_connector.h +++ b/include/drm/drm_connector.h @@ -82,6 +82,53 @@ enum drm_connector_status { connector_status_unknown = 3, }; +/** + * enum drm_connector_registration_status - userspace registration status for + * a &drm_connector + * + * This enum is used to track the status of initializing a connector and + * registering it with userspace, so that DRM can prevent bogus modesets on + * connectors that no longer exist. + */ +enum drm_connector_registration_state { + /** + * @DRM_CONNECTOR_INITIALIZING: The connector has just been created, + * but has yet to be exposed to userspace. There should be no + * additional restrictions to how the state of this connector may be + * modified. + */ + DRM_CONNECTOR_INITIALIZING = 0, + + /** + * @DRM_CONNECTOR_REGISTERED: The connector has been fully initialized + * and registered with sysfs, as such it has been exposed to + * userspace. There should be no additional restrictions to how the + * state of this connector may be modified. + */ + DRM_CONNECTOR_REGISTERED = 1, + + /** + * @DRM_CONNECTOR_UNREGISTERED: The connector has either been exposed + * to userspace and has since been unregistered and removed from + * userspace, or the connector was unregistered before it had a chance + * to be exposed to userspace (e.g. still in the + * @DRM_CONNECTOR_INITIALIZING state). When a connector is + * unregistered, there are additional restrictions to how its state + * may be modified: + * + * - An unregistered connector may only have its DPMS changed from + * On->Off. Once DPMS is changed to Off, it may not be switched back + * to On. + * - Modesets are not allowed on unregistered connectors, unless they + * would result in disabling its assigned CRTCs. This means + * disabling a CRTC on an unregistered connector is OK, but enabling + * one is not. + * - Removing a CRTC from an unregistered connector is OK, but new + * CRTCs may never be assigned to an unregistered connector. + */ + DRM_CONNECTOR_UNREGISTERED = 2, +}; + enum subpixel_order { SubPixelUnknown = 0, SubPixelHorizontalRGB, @@ -853,10 +900,12 @@ struct drm_connector { bool ycbcr_420_allowed; /** - * @registered: Is this connector exposed (registered) with userspace? + * @registration_state: Is this connector initializing, exposed + * (registered) with userspace, or unregistered? + * * Protected by @mutex. */ - bool registered; + enum drm_connector_registration_state registration_state; /** * @modes: @@ -1166,6 +1215,24 @@ static inline void drm_connector_unreference(struct drm_connector *connector) drm_connector_put(connector); } +/** + * drm_connector_is_unregistered - has the connector been unregistered from + * userspace? + * @connector: DRM connector + * + * Checks whether or not @connector has been unregistered from userspace. + * + * Returns: + * True if the connector was unregistered, false if the connector is + * registered or has not yet been registered with userspace. + */ +static inline bool +drm_connector_is_unregistered(struct drm_connector *connector) +{ + return READ_ONCE(connector->registration_state) == + DRM_CONNECTOR_UNREGISTERED; +} + const char *drm_get_connector_status_name(enum drm_connector_status status); const char *drm_get_subpixel_order_name(enum subpixel_order order); const char *drm_get_dpms_name(int val); diff --git a/include/keys/asymmetric-subtype.h b/include/keys/asymmetric-subtype.h index e0a9c236887281..9ce2f0fae57e39 100644 --- a/include/keys/asymmetric-subtype.h +++ b/include/keys/asymmetric-subtype.h @@ -17,6 +17,8 @@ #include <linux/seq_file.h> #include <keys/asymmetric-type.h> +struct kernel_pkey_query; +struct kernel_pkey_params; struct public_key_signature; /* @@ -34,6 +36,13 @@ struct asymmetric_key_subtype { /* Destroy a key of this subtype */ void (*destroy)(void *payload_crypto, void *payload_auth); + int (*query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + + /* Encrypt/decrypt/sign data */ + int (*eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); + /* Verify the signature on a key of this subtype (optional) */ int (*verify_signature)(const struct key *key, const struct public_key_signature *sig); diff --git a/security/keys/trusted.h b/include/keys/trusted.h index 8d5fe9eafb22ae..adbcb681782604 100644 --- a/security/keys/trusted.h +++ b/include/keys/trusted.h @@ -3,7 +3,7 @@ #define __TRUSTED_KEY_H /* implementation specific TPM constants */ -#define MAX_BUF_SIZE 512 +#define MAX_BUF_SIZE 1024 #define TPM_GETRANDOM_SIZE 14 #define TPM_OSAP_SIZE 36 #define TPM_OIAP_SIZE 10 @@ -36,6 +36,18 @@ enum { SRK_keytype = 4 }; +int TSS_authhmac(unsigned char *digest, const unsigned char *key, + unsigned int keylen, unsigned char *h1, + unsigned char *h2, unsigned char h3, ...); +int TSS_checkhmac1(unsigned char *buffer, + const uint32_t command, + const unsigned char *ononce, + const unsigned char *key, + unsigned int keylen, ...); + +int trusted_tpm_send(unsigned char *cmd, size_t buflen); +int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce); + #define TPM_DEBUG 0 #if TPM_DEBUG diff --git a/include/linux/adxl.h b/include/linux/adxl.h index 2a629acb4c3f46..2d29f55923e3ad 100644 --- a/include/linux/adxl.h +++ b/include/linux/adxl.h @@ -7,7 +7,12 @@ #ifndef _LINUX_ADXL_H #define _LINUX_ADXL_H +#ifdef CONFIG_ACPI_ADXL const char * const *adxl_get_component_names(void); int adxl_decode(u64 addr, u64 component_values[]); +#else +static inline const char * const *adxl_get_component_names(void) { return NULL; } +static inline int adxl_decode(u64 addr, u64 component_values[]) { return -EOPNOTSUPP; } +#endif #endif /* _LINUX_ADXL_H */ diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2c9756bd9c4cdc..b2488055fd1d18 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -62,13 +62,19 @@ /* Error Codes */ enum virtchnl_status_code { VIRTCHNL_STATUS_SUCCESS = 0, - VIRTCHNL_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_PARAM = -5, + VIRTCHNL_STATUS_ERR_NO_MEMORY = -18, VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH = -38, VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR = -39, VIRTCHNL_STATUS_ERR_INVALID_VF_ID = -40, - VIRTCHNL_STATUS_NOT_SUPPORTED = -64, + VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR = -53, + VIRTCHNL_STATUS_ERR_NOT_SUPPORTED = -64, }; +/* Backward compatibility */ +#define VIRTCHNL_ERR_PARAM VIRTCHNL_STATUS_ERR_PARAM +#define VIRTCHNL_STATUS_NOT_SUPPORTED VIRTCHNL_STATUS_ERR_NOT_SUPPORTED + #define VIRTCHNL_LINK_SPEED_100MB_SHIFT 0x1 #define VIRTCHNL_LINK_SPEED_1000MB_SHIFT 0x2 #define VIRTCHNL_LINK_SPEED_10GB_SHIFT 0x3 @@ -831,7 +837,7 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: default: - return VIRTCHNL_ERR_PARAM; + return VIRTCHNL_STATUS_ERR_PARAM; } /* few more checks */ if (err_msg_format || valid_len != msglen) diff --git a/include/linux/bio.h b/include/linux/bio.h index b47c7f716731fc..056fb627edb3e8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -503,31 +503,23 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css); -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ return 0; } -static inline int bio_associate_create_blkg(struct request_queue *q, - struct bio *bio) { return 0; } -static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) -{ return 0; } +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1e76ceebeb5dc5..6d766a19f2bbb2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - struct percpu_ref refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -184,8 +184,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -232,59 +230,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal version of bio_blkcg for bfq and cfq - * - * DO NOT USE. - * There is a flaw using this version of the function. In particular, this was - * used in a broken paradigm where association was called on the given css. It - * is possible though that the returned css from task_css() is in the process - * of dying due to migration of the current task. So it is improper to assume - * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will - * take additional work to handle more gracefully. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, NULL if not associated. - * Callers are expected to either handle NULL or know association has been - * done prior to calling this. - */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; + struct cgroup_subsys_state *css; + + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } static inline bool blk_cgroup_congested(void) @@ -490,35 +451,26 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - percpu_ref_get(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } /** - * blkg_tryget - try and get a blkg reference + * blkg_try_get - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - while (!percpu_ref_tryget(&blkg->refcnt)) - blkg = blkg->parent; - return blkg; -} +void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference @@ -526,7 +478,9 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) */ static inline void blkg_put(struct blkcg_gq *blkg) { - percpu_ref_put(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); } /** @@ -579,36 +533,25 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - if (bio && bio->bi_blkg) { - blkcg = bio->bi_blkg->blkcg; - if (blkcg == &blkcg_root) - goto rl_use_root; - - blkg_get(bio->bi_blkg); - rcu_read_unlock(); - return &bio->bi_blkg->rl; - } + blkcg = bio_blkcg(bio); - blkcg = css_to_blkcg(blkcg_css()); + /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) - goto rl_use_root; + goto root_rl; + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - blkg = __blkg_lookup_create(blkcg, q); - - if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) - goto rl_use_root; + goto root_rl; + blkg_get(blkg); rcu_read_unlock(); return &blkg->rl; - - /* - * Each blkg has its own request_list, however, the root blkcg - * uses the request_queue's root_rl. This is to avoid most - * overhead for the root blkcg. - */ -rl_use_root: +root_rl: rcu_read_unlock(); return &q->root_rl; } @@ -854,26 +797,32 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { + struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); + blkcg = bio_blkcg(bio); + + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); - bio_associate_create_blkg(q, bio); - blkg = bio->bi_blkg; + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -885,8 +834,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } @@ -983,7 +930,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, @@ -999,7 +945,6 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 093a818c5b6847..1dcf652ba0aa3e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,6 +178,7 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; + struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 9e8056ec20faab..d93e89761a8b42 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -51,6 +51,9 @@ struct bpf_reg_state { * PTR_TO_MAP_VALUE_OR_NULL */ struct bpf_map *map_ptr; + + /* Max size from any of the above. */ + unsigned long raw; }; /* Fixed part of pointer offset, pointer types only */ s32 off; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 9968332cceed0e..9d12757a65b018 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,8 +93,6 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index b1ce500fe8b3df..3e7dafb3ea8099 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -21,8 +21,6 @@ #define __SANITIZE_ADDRESS__ #endif -#define __no_sanitize_address __attribute__((no_sanitize("address"))) - /* * Not all versions of clang implement the the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements @@ -41,6 +39,3 @@ * compilers, like ICC. */ #define barrier() __asm__ __volatile__("" : : : "memory") -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -#define __assume_aligned(a, ...) \ - __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 90ddfefb6c2b12..c0f5db3a962174 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -68,31 +68,20 @@ */ #define uninitialized_var(x) x = x -#ifdef __CHECKER__ -#define __must_be_array(a) 0 -#else -/* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) -#endif - #ifdef RETPOLINE -#define __noretpoline __attribute__((indirect_branch("keep"))) +#define __noretpoline __attribute__((__indirect_branch__("keep"))) #endif #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define __optimize(level) __attribute__((__optimize__(level))) - #define __compiletime_object_size(obj) __builtin_object_size(obj, 0) -#ifndef __CHECKER__ -#define __compiletime_warning(message) __attribute__((warning(message))) -#define __compiletime_error(message) __attribute__((error(message))) +#define __compiletime_warning(message) __attribute__((__warning__(message))) +#define __compiletime_error(message) __attribute__((__error__(message))) -#ifdef LATENT_ENTROPY_PLUGIN +#if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif -#endif /* __CHECKER__ */ /* * calling noreturn functions, __builtin_unreachable() and __builtin_trap() @@ -107,10 +96,6 @@ * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer * control elsewhere. - * - * Early snapshots of gcc 4.5 don't support this and we can't detect - * this in the preprocessor, but we can live with this because they're - * unreleased. Really, we need to have autoconf for the kernel. */ #define unreachable() \ do { \ @@ -119,9 +104,6 @@ __builtin_unreachable(); \ } while (0) -/* Mark a function definition as prohibited from being cloned. */ -#define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) - #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) #define __randomize_layout __attribute__((randomize_layout)) #define __no_randomize_layout __attribute__((no_randomize_layout)) @@ -131,32 +113,6 @@ #endif /* - * When used with Link Time Optimization, gcc can optimize away C functions or - * variables which are referenced only from assembly code. __visible tells the - * optimizer that something else uses this function or variable, thus preventing - * this. - */ -#define __visible __attribute__((externally_visible)) - -/* gcc version specific checks */ - -#if GCC_VERSION >= 40900 && !defined(__CHECKER__) -/* - * __assume_aligned(n, k): Tell the optimizer that the returned - * pointer can be assumed to be k modulo n. The second argument is - * optional (default 0), so we use a variadic macro to make the - * shorthand. - * - * Beware: Do not apply this to functions which may return - * ERR_PTRs. Also, it is probably unwise to apply it to functions - * returning extra information in the low bits (but in that case the - * compiler should see some alignment anyway, when the return value is - * massaged by 'flags = ptr & 3; ptr &= ~3;'). - */ -#define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) -#endif - -/* * GCC 'asm goto' miscompiles certain code sequences: * * http://gcc.gnu.org/bugzilla/show_bug.cgi?id=58670 @@ -187,39 +143,22 @@ #define KASAN_ABI_VERSION 3 #endif -#if GCC_VERSION >= 40902 /* - * Tell the compiler that address safety instrumentation (KASAN) - * should not be applied to that function. - * Conflicts with inlining: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * Because __no_sanitize_address conflicts with inlining: + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * we do one or the other. */ -#define __no_sanitize_address __attribute__((no_sanitize_address)) #ifdef CONFIG_KASAN #define __no_sanitize_address_or_inline \ __no_sanitize_address __maybe_unused notrace #else #define __no_sanitize_address_or_inline inline #endif -#endif #if GCC_VERSION >= 50100 -/* - * Mark structures as requiring designated initializers. - * https://gcc.gnu.org/onlinedocs/gcc/Designated-Inits.html - */ -#define __designated_init __attribute__((designated_init)) #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif -#if !defined(__noclone) -#define __noclone /* not needed */ -#endif - -#if !defined(__no_sanitize_address) -#define __no_sanitize_address -#define __no_sanitize_address_or_inline inline -#endif - /* * Turn individual warnings and errors on and off locally, depending * on version. diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 4c7f9befa9f6c6..517bd14e122248 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -29,17 +29,8 @@ */ #define OPTIMIZER_HIDE_VAR(var) barrier() -/* Intel ECC compiler doesn't support __builtin_types_compatible_p() */ -#define __must_be_array(a) 0 - #endif /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ #define __builtin_bswap16 _bswap16 - -/* The following are for compatibility with GCC, from compiler-gcc.h, - * and may be redefined here because they should not be shared with other - * compilers, like clang. - */ -#define __visible __attribute__((externally_visible)) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4170fcee5adb30..18c80cfa4fc485 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -23,8 +23,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __branch_check__(x, expect, is_constant) ({ \ long ______r; \ static struct ftrace_likely_data \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_annotated_branch"))) \ + __aligned(4) \ + __section("_ftrace_annotated_branch") \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ @@ -59,8 +59,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, ({ \ int ______r; \ static struct ftrace_branch_data \ - __attribute__((__aligned__(4))) \ - __attribute__((section("_ftrace_branch"))) \ + __aligned(4) \ + __section("_ftrace_branch") \ ______f = { \ .func = __func__, \ .file = __FILE__, \ @@ -115,7 +115,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define ASM_UNREACHABLE #endif #ifndef unreachable -# define unreachable() do { annotate_reachable(); do { } while (1); } while (0) +# define unreachable() do { \ + annotate_unreachable(); \ + __builtin_unreachable(); \ +} while (0) #endif /* @@ -137,7 +140,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ - __attribute__((section("___kentry" "+" #sym ), used)) \ + __section("___kentry" "+" #sym ) \ = (unsigned long)&sym; #endif @@ -278,7 +281,7 @@ unsigned long read_word_at_a_time(const void *addr) * visible to the compiler. */ #define __ADDRESSABLE(sym) \ - static void * __attribute__((section(".discard.addressable"), used)) \ + static void * __section(".discard.addressable") __used \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** @@ -331,10 +334,6 @@ static inline void *offset_to_ptr(const int *off) #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ -#ifndef __optimize -# define __optimize(level) -#endif - /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 @@ -376,4 +375,7 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +/* &a[0] degrades to a pointer: a different type from an array */ +#define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) + #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h new file mode 100644 index 00000000000000..6b28c1b7310c01 --- /dev/null +++ b/include/linux/compiler_attributes.h @@ -0,0 +1,258 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_COMPILER_ATTRIBUTES_H +#define __LINUX_COMPILER_ATTRIBUTES_H + +/* + * The attributes in this file are unconditionally defined and they directly + * map to compiler attribute(s) -- except those that are 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). + * + * 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. + */ + +/* + * 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. + * + * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ + * depending on the compiler used to build it; however, these attributes have + * no semantic effects for sparse, so it does not matter. Also note that, + * in order to avoid sparse's warnings, even the unsupported ones must be + * defined to 0. + */ +#ifndef __has_attribute +# define __has_attribute(x) __GCC4_has_attribute_##x +# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___designated_init__ 0 +# define __GCC4_has_attribute___externally_visible__ 1 +# define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___optimize__ 1 +# define __GCC4_has_attribute___nonstring__ 0 +# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alias-function-attribute + */ +#define __alias(symbol) __attribute__((__alias__(#symbol))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-aligned-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-aligned-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-aligned-variable-attribute + */ +#define __aligned(x) __attribute__((__aligned__(x))) +#define __aligned_largest __attribute__((__aligned__)) + +/* + * Note: users of __always_inline currently do not write "inline" themselves, + * which seems to be required by gcc to apply the attribute according + * to its docs (and also "warning: always_inline function might not be + * inlinable [-Wattributes]" is emitted). + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-always_005finline-function-attribute + * clang: mentioned + */ +#define __always_inline inline __attribute__((__always_inline__)) + +/* + * The second argument is optional (default 0), so we use a variadic macro + * to make the shorthand. + * + * Beware: Do not apply this to functions which may return + * ERR_PTRs. Also, it is probably unwise to apply it to functions + * returning extra information in the low bits (but in that case the + * compiler should see some alignment anyway, when the return value is + * massaged by 'flags = ptr & 3; ptr &= ~3;'). + * + * Optional: only supported since gcc >= 4.9 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-assume_005faligned-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#assume-aligned + */ +#if __has_attribute(__assume_aligned__) +# define __assume_aligned(a, ...) __attribute__((__assume_aligned__(a, ## __VA_ARGS__))) +#else +# define __assume_aligned(a, ...) +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute + */ +#define __cold __attribute__((__cold__)) + +/* + * Note the long name. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute + */ +#define __attribute_const__ __attribute__((__const__)) + +/* + * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' + * attribute warnings entirely and for good") for more information. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-deprecated-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-deprecated-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-deprecated-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Enumerator-Attributes.html#index-deprecated-enumerator-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#deprecated + */ +#define __deprecated + +/* + * Optional: only supported since gcc >= 5.1 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-designated_005finit-type-attribute + */ +#if __has_attribute(__designated_init__) +# define __designated_init __attribute__((__designated_init__)) +#else +# define __designated_init +#endif + +/* + * Optional: not supported by clang + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-externally_005fvisible-function-attribute + */ +#if __has_attribute(__externally_visible__) +# define __visible __attribute__((__externally_visible__)) +#else +# define __visible +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-format-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#format + */ +#define __printf(a, b) __attribute__((__format__(printf, a, b))) +#define __scanf(a, b) __attribute__((__format__(scanf, a, b))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-gnu_005finline-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#gnu-inline + */ +#define __gnu_inline __attribute__((__gnu_inline__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + */ +#define __malloc __attribute__((__malloc__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-mode-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-mode-variable-attribute + */ +#define __mode(x) __attribute__((__mode__(x))) + +/* + * Optional: not supported by clang + * Note: icc does not recognize gcc's no-tracer + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noclone-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-optimize-function-attribute + */ +#if __has_attribute(__noclone__) +# if __has_attribute(__optimize__) +# define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) +# else +# define __noclone __attribute__((__noclone__)) +# endif +#else +# define __noclone +#endif + +/* + * Note the missing underscores. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute + * clang: mentioned + */ +#define noinline __attribute__((__noinline__)) + +/* + * Optional: only supported since gcc >= 8 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-nonstring-variable-attribute + */ +#if __has_attribute(__nonstring__) +# define __nonstring __attribute__((__nonstring__)) +#else +# define __nonstring +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn + * clang: https://clang.llvm.org/docs/AttributeReference.html#id1 + */ +#define __noreturn __attribute__((__noreturn__)) + +/* + * Optional: only supported since gcc >= 4.8 + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fsanitize_005faddress-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-sanitize-address-no-address-safety-analysis + */ +#if __has_attribute(__no_sanitize_address__) +# define __no_sanitize_address __attribute__((__no_sanitize_address__)) +#else +# define __no_sanitize_address +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute + * clang: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-packed-variable-attribute + */ +#define __packed __attribute__((__packed__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-pure-function-attribute + */ +#define __pure __attribute__((__pure__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-section-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-section-variable-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#section-declspec-allocate + */ +#define __section(S) __attribute__((__section__(#S))) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-unused-label-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#maybe-unused-unused + */ +#define __always_unused __attribute__((__unused__)) +#define __maybe_unused __attribute__((__unused__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-used-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-used-variable-attribute + */ +#define __used __attribute__((__used__)) + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute + */ +#define __weak __attribute__((__weak__)) + +#endif /* __LINUX_COMPILER_ATTRIBUTES_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 97cfe29b3f0adf..3439d7d0249aa5 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H @@ -54,6 +55,9 @@ extern void __chk_io_ptr(const volatile void __iomem *); #ifdef __KERNEL__ +/* Attributes */ +#include <linux/compiler_attributes.h> + /* Compiler specific macros. */ #ifdef __clang__ #include <linux/compiler-clang.h> @@ -78,12 +82,6 @@ extern void __chk_io_ptr(const volatile void __iomem *); #include <asm/compiler.h> #endif -/* - * Generic compiler-independent macros required for kernel - * build go below this comment. Actual compiler/compiler version - * specific implementations come from the above header files - */ - struct ftrace_branch_data { const char *func; const char *file; @@ -106,10 +104,6 @@ struct ftrace_likely_data { unsigned long constant; }; -/* Don't. Just don't. */ -#define __deprecated -#define __deprecated_for_modules - #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ @@ -119,10 +113,6 @@ struct ftrace_likely_data { * compilers. We don't consider that to be an error, so set them to nothing. * For example, some of them are for compiler specific plugins. */ -#ifndef __designated_init -# define __designated_init -#endif - #ifndef __latent_entropy # define __latent_entropy #endif @@ -140,17 +130,6 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif -#ifndef __visible -#define __visible -#endif - -/* - * Assume alignment of return value. - */ -#ifndef __assume_aligned -#define __assume_aligned(a, ...) -#endif - /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) @@ -159,14 +138,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -#ifndef __attribute_const__ -#define __attribute_const__ __attribute__((__const__)) -#endif - -#ifndef __noclone -#define __noclone -#endif - /* Helpers for emitting diagnostics in pragmas. */ #ifndef __diag #define __diag(string) @@ -186,43 +157,16 @@ struct ftrace_likely_data { #define __diag_error(compiler, version, option, comment) \ __diag_ ## compiler(version, error, option) -/* - * From the GCC manual: - * - * Many functions have no effects except the return value and their - * return value depends only on the parameters and/or global - * variables. Such a function can be subject to common subexpression - * elimination and loop optimization just as an arithmetic operator - * would be. - * [...] - */ -#define __pure __attribute__((pure)) -#define __aligned(x) __attribute__((aligned(x))) -#define __printf(a, b) __attribute__((format(printf, a, b))) -#define __scanf(a, b) __attribute__((format(scanf, a, b))) -#define __maybe_unused __attribute__((unused)) -#define __always_unused __attribute__((unused)) -#define __mode(x) __attribute__((mode(x))) -#define __malloc __attribute__((__malloc__)) -#define __used __attribute__((__used__)) -#define __noreturn __attribute__((noreturn)) -#define __packed __attribute__((packed)) -#define __weak __attribute__((weak)) -#define __alias(symbol) __attribute__((alias(#symbol))) -#define __cold __attribute__((cold)) -#define __section(S) __attribute__((__section__(#S))) - - #ifdef CONFIG_ENABLE_MUST_CHECK -#define __must_check __attribute__((warn_unused_result)) +#define __must_check __attribute__((__warn_unused_result__)) #else #define __must_check #endif -#if defined(CC_USING_HOTPATCH) && !defined(__CHECKER__) +#if defined(CC_USING_HOTPATCH) #define notrace __attribute__((hotpatch(0, 0))) #else -#define notrace __attribute__((no_instrument_function)) +#define notrace __attribute__((__no_instrument_function__)) #endif /* @@ -231,23 +175,11 @@ struct ftrace_likely_data { * stack and frame pointer being set up and there is no chance to * restore the lr register to the value before mcount was called. */ -#define __naked __attribute__((naked)) notrace +#define __naked __attribute__((__naked__)) notrace #define __compiler_offsetof(a, b) __builtin_offsetof(a, b) /* - * Feature detection for gnu_inline (gnu89 extern inline semantics). Either - * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics, - * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not - * defined so the gnu89 semantics are the default. - */ -#ifdef __GNUC_STDC_INLINE__ -# define __gnu_inline __attribute__((gnu_inline)) -#else -# define __gnu_inline -#endif - -/* * Force always-inline if the user requests it so via the .config. * GCC does not warn about unused static inline functions for * -Wunused-function. This turns out to avoid the need for complex #ifdef @@ -258,22 +190,20 @@ struct ftrace_likely_data { * semantics rather than c99. This prevents multiple symbol definition errors * of extern inline functions at link time. * A lot of inline functions can cause havoc with function tracing. + * Do not use __always_inline here, since currently it expands to inline again + * (which would break users of __always_inline). */ #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) || \ !defined(CONFIG_OPTIMIZE_INLINING) -#define inline \ - inline __attribute__((always_inline, unused)) notrace __gnu_inline +#define inline inline __attribute__((__always_inline__)) __gnu_inline \ + __maybe_unused notrace #else -#define inline inline __attribute__((unused)) notrace __gnu_inline +#define inline inline __gnu_inline \ + __maybe_unused notrace #endif #define __inline__ inline -#define __inline inline -#define noinline __attribute__((noinline)) - -#ifndef __always_inline -#define __always_inline inline __attribute__((always_inline)) -#endif +#define __inline inline /* * Rather then using noinline to prevent stack consumption, use diff --git a/include/linux/fs.h b/include/linux/fs.h index 8252df30b9a16a..c95c0807471fd1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1752,6 +1752,25 @@ struct block_device_operations; #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) +/* + * These flags control the behavior of the remap_file_range function pointer. + * If it is called with len == 0 that means "remap to end of source file". + * See Documentation/filesystems/vfs.txt for more details about this call. + * + * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request + */ +#define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) + +/* + * These flags signal that the caller is ok with altering various aspects of + * the behavior of the remap operation. The changes must be made by the + * implementation; the vfs remap helper functions can take advantage of them. + * Flags in this category exist to preserve the quirky behavior of the hoisted + * btrfs clone/dedupe ioctls. + */ +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; @@ -1790,10 +1809,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); - int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, - u64); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1856,21 +1874,21 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, - struct inode *dest, loff_t destoff, - loff_t len, bool *is_same); +extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len, unsigned int remap_flags); struct super_operations { @@ -2998,6 +3016,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *count, unsigned int remap_flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 24bcc5eec6b409..76f8db0b0e715c 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index c759d1cbcedd8d..a64f21a97369a5 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -37,7 +37,9 @@ struct in_device { unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; - unsigned char mr_qrv; + unsigned long mr_qi; /* Query Interval */ + unsigned long mr_qri; /* Query Response Interval */ + unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; unsigned char mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ diff --git a/include/linux/key-type.h b/include/linux/key-type.h index 05d8fb5a06c491..bc9af551fc8382 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -17,6 +17,9 @@ #ifdef CONFIG_KEYS +struct kernel_pkey_query; +struct kernel_pkey_params; + /* * key under-construction record * - passed to the request_key actor if supplied @@ -155,6 +158,14 @@ struct key_type { */ struct key_restriction *(*lookup_restriction)(const char *params); + /* Asymmetric key accessor functions. */ + int (*asym_query)(const struct kernel_pkey_params *params, + struct kernel_pkey_query *info); + int (*asym_eds_op)(struct kernel_pkey_params *params, + const void *in, void *out); + int (*asym_verify_signature)(struct kernel_pkey_params *params, + const void *in, const void *in2); + /* internal fields */ struct list_head link; /* link in types list */ struct lock_class_key lock_class; /* key->sem lock class */ diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h new file mode 100644 index 00000000000000..c7c48c79ce0e9f --- /dev/null +++ b/include/linux/keyctl.h @@ -0,0 +1,46 @@ +/* keyctl kernel bits + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef __LINUX_KEYCTL_H +#define __LINUX_KEYCTL_H + +#include <uapi/linux/keyctl.h> + +struct kernel_pkey_query { + __u32 supported_ops; /* Which ops are supported */ + __u32 key_size; /* Size of the key in bits */ + __u16 max_data_size; /* Maximum size of raw data to sign in bytes */ + __u16 max_sig_size; /* Maximum size of signature in bytes */ + __u16 max_enc_size; /* Maximum size of encrypted blob in bytes */ + __u16 max_dec_size; /* Maximum size of decrypted blob in bytes */ +}; + +enum kernel_pkey_operation { + kernel_pkey_encrypt, + kernel_pkey_decrypt, + kernel_pkey_sign, + kernel_pkey_verify, +}; + +struct kernel_pkey_params { + struct key *key; + const char *encoding; /* Encoding (eg. "oaep" or "raw" for none) */ + const char *hash_algo; /* Digest algorithm used (eg. "sha1") or NULL if N/A */ + char *info; /* Modified info string to be released later */ + __u32 in_len; /* Input data size */ + union { + __u32 out_len; /* Output buffer size (enc/dec/sign) */ + __u32 in2_len; /* 2nd input data size (verify) */ + }; + enum kernel_pkey_operation op : 8; +}; + +#endif /* __LINUX_KEYCTL_H */ diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af41659..bac395f1d00a0f 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/include/linux/notifier.h b/include/linux/notifier.h index f35c7bf7614302..0096a05395e380 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -122,8 +122,7 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ - static DEFINE_PER_CPU(struct srcu_data, \ - name##_head_srcu_data); \ + static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h new file mode 100644 index 00000000000000..53dfc25419603e --- /dev/null +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PLATFORM_DATA_X86_ASUS_WMI_H +#define __PLATFORM_DATA_X86_ASUS_WMI_H + +#include <linux/errno.h> +#include <linux/types.h> + +/* WMI Methods */ +#define ASUS_WMI_METHODID_SPEC 0x43455053 /* BIOS SPECification */ +#define ASUS_WMI_METHODID_SFBD 0x44424653 /* Set First Boot Device */ +#define ASUS_WMI_METHODID_GLCD 0x44434C47 /* Get LCD status */ +#define ASUS_WMI_METHODID_GPID 0x44495047 /* Get Panel ID?? (Resol) */ +#define ASUS_WMI_METHODID_QMOD 0x444F4D51 /* Quiet MODe */ +#define ASUS_WMI_METHODID_SPLV 0x4C425053 /* Set Panel Light Value */ +#define ASUS_WMI_METHODID_AGFN 0x4E464741 /* FaN? */ +#define ASUS_WMI_METHODID_SFUN 0x4E554653 /* FUNCtionalities */ +#define ASUS_WMI_METHODID_SDSP 0x50534453 /* Set DiSPlay output */ +#define ASUS_WMI_METHODID_GDSP 0x50534447 /* Get DiSPlay output */ +#define ASUS_WMI_METHODID_DEVP 0x50564544 /* DEVice Policy */ +#define ASUS_WMI_METHODID_OSVR 0x5256534F /* OS VeRsion */ +#define ASUS_WMI_METHODID_DSTS 0x53544344 /* Device STatuS */ +#define ASUS_WMI_METHODID_DSTS2 0x53545344 /* Device STatuS #2*/ +#define ASUS_WMI_METHODID_BSTS 0x53545342 /* Bios STatuS ? */ +#define ASUS_WMI_METHODID_DEVS 0x53564544 /* DEVice Set */ +#define ASUS_WMI_METHODID_CFVS 0x53564643 /* CPU Frequency Volt Set */ +#define ASUS_WMI_METHODID_KBFT 0x5446424B /* KeyBoard FilTer */ +#define ASUS_WMI_METHODID_INIT 0x54494E49 /* INITialize */ +#define ASUS_WMI_METHODID_HKEY 0x59454B48 /* Hot KEY ?? */ + +#define ASUS_WMI_UNSUPPORTED_METHOD 0xFFFFFFFE + +/* Wireless */ +#define ASUS_WMI_DEVID_HW_SWITCH 0x00010001 +#define ASUS_WMI_DEVID_WIRELESS_LED 0x00010002 +#define ASUS_WMI_DEVID_CWAP 0x00010003 +#define ASUS_WMI_DEVID_WLAN 0x00010011 +#define ASUS_WMI_DEVID_WLAN_LED 0x00010012 +#define ASUS_WMI_DEVID_BLUETOOTH 0x00010013 +#define ASUS_WMI_DEVID_GPS 0x00010015 +#define ASUS_WMI_DEVID_WIMAX 0x00010017 +#define ASUS_WMI_DEVID_WWAN3G 0x00010019 +#define ASUS_WMI_DEVID_UWB 0x00010021 + +/* Leds */ +/* 0x000200XX and 0x000400XX */ +#define ASUS_WMI_DEVID_LED1 0x00020011 +#define ASUS_WMI_DEVID_LED2 0x00020012 +#define ASUS_WMI_DEVID_LED3 0x00020013 +#define ASUS_WMI_DEVID_LED4 0x00020014 +#define ASUS_WMI_DEVID_LED5 0x00020015 +#define ASUS_WMI_DEVID_LED6 0x00020016 + +/* Backlight and Brightness */ +#define ASUS_WMI_DEVID_ALS_ENABLE 0x00050001 /* Ambient Light Sensor */ +#define ASUS_WMI_DEVID_BACKLIGHT 0x00050011 +#define ASUS_WMI_DEVID_BRIGHTNESS 0x00050012 +#define ASUS_WMI_DEVID_KBD_BACKLIGHT 0x00050021 +#define ASUS_WMI_DEVID_LIGHT_SENSOR 0x00050022 /* ?? */ +#define ASUS_WMI_DEVID_LIGHTBAR 0x00050025 + +/* Misc */ +#define ASUS_WMI_DEVID_CAMERA 0x00060013 + +/* Storage */ +#define ASUS_WMI_DEVID_CARDREADER 0x00080013 + +/* Input */ +#define ASUS_WMI_DEVID_TOUCHPAD 0x00100011 +#define ASUS_WMI_DEVID_TOUCHPAD_LED 0x00100012 + +/* Fan, Thermal */ +#define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 +#define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 + +/* Power */ +#define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 + +/* Deep S3 / Resume on LID open */ +#define ASUS_WMI_DEVID_LID_RESUME 0x00120031 + +/* DSTS masks */ +#define ASUS_WMI_DSTS_STATUS_BIT 0x00000001 +#define ASUS_WMI_DSTS_UNKNOWN_BIT 0x00000002 +#define ASUS_WMI_DSTS_PRESENCE_BIT 0x00010000 +#define ASUS_WMI_DSTS_USER_BIT 0x00020000 +#define ASUS_WMI_DSTS_BIOS_BIT 0x00040000 +#define ASUS_WMI_DSTS_BRIGHTNESS_MASK 0x000000FF +#define ASUS_WMI_DSTS_MAX_BRIGTH_MASK 0x0000FF00 +#define ASUS_WMI_DSTS_LIGHTBAR_MASK 0x0000000F + +#if IS_REACHABLE(CONFIG_ASUS_WMI) +int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval); +#else +static inline int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, + u32 *retval) +{ + return -ENODEV; +} +#endif + +#endif /* __PLATFORM_DATA_X86_ASUS_WMI_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 8f8a5418b627a2..a51c13c2b1a031 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1200,6 +1200,11 @@ struct task_struct { void *security; #endif +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK + unsigned long lowest_stack; + unsigned long prev_lowest_stack; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h new file mode 100644 index 00000000000000..3d5c3271a9a8cc --- /dev/null +++ b/include/linux/stackleak.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_STACKLEAK_H +#define _LINUX_STACKLEAK_H + +#include <linux/sched.h> +#include <linux/sched/task_stack.h> + +/* + * Check that the poison value points to the unused hole in the + * virtual memory map for your platform. + */ +#define STACKLEAK_POISON -0xBEEF +#define STACKLEAK_SEARCH_DEPTH 128 + +#ifdef CONFIG_GCC_PLUGIN_STACKLEAK +#include <asm/stacktrace.h> + +static inline void stackleak_task_init(struct task_struct *t) +{ + t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +# ifdef CONFIG_STACKLEAK_METRICS + t->prev_lowest_stack = t->lowest_stack; +# endif +} + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + +#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ +static inline void stackleak_task_init(struct task_struct *t) { } +#endif + +#endif diff --git a/include/linux/uio.h b/include/linux/uio.h index 422b1c01ee0de0..55ce99ddb912f9 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,15 +21,16 @@ struct kvec { size_t iov_len; }; -enum { +enum iter_type { ITER_IOVEC = 0, ITER_KVEC = 2, ITER_BVEC = 4, ITER_PIPE = 8, + ITER_DISCARD = 16, }; struct iov_iter { - int type; + unsigned int type; size_t iov_offset; size_t count; union { @@ -47,6 +48,41 @@ struct iov_iter { }; }; +static inline enum iter_type iov_iter_type(const struct iov_iter *i) +{ + return i->type & ~(READ | WRITE); +} + +static inline bool iter_is_iovec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_IOVEC; +} + +static inline bool iov_iter_is_kvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_KVEC; +} + +static inline bool iov_iter_is_bvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_BVEC; +} + +static inline bool iov_iter_is_pipe(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_PIPE; +} + +static inline bool iov_iter_is_discard(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_DISCARD; +} + +static inline unsigned char iov_iter_rw(const struct iov_iter *i) +{ + return i->type & (READ | WRITE); +} + /* * Total number of bytes covered by an iovec. * @@ -74,7 +110,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) } #define iov_for_each(iov, iter, start) \ - if (!((start).type & (ITER_BVEC | ITER_PIPE))) \ + if (iov_iter_type(start) == ITER_IOVEC || \ + iov_iter_type(start) == ITER_KVEC) \ for (iter = (start); \ (iter).count && \ ((iov = iov_iter_iovec(&(iter))), 1); \ @@ -181,14 +218,15 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); -void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, @@ -202,19 +240,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i) return i->count; } -static inline bool iter_is_iovec(const struct iov_iter *i) -{ - return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE)); -} - -/* - * Get one of READ or WRITE out of iter->type without any other flags OR'd in - * with it. - * - * The ?: is just for type safety. - */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) - /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f0b..fdfd04e348f698 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,8 +246,7 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. Must be called after the bio has been associated with - * a device. + * writeback context. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -258,7 +257,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); + bio_associate_blkcg(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index e2695c4bf35803..ddbba838d048df 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -13,7 +13,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); -struct sock *unix_peer_get(struct sock *); +struct sock *unix_peer_get(struct sock *sk); #define UNIX_HASH_SIZE 256 #define UNIX_HASH_BITS 8 @@ -40,7 +40,7 @@ struct unix_skb_parms { u32 consumed; } __randomize_layout; -#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) +#define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) #define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index d0a341bc45404b..33d291888ba9c1 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -54,6 +54,35 @@ enum afs_fs_operation { afs_FS_StoreData64 = 65538, /* AFS Store file data */ afs_FS_GiveUpAllCallBacks = 65539, /* AFS Give up all our callbacks on a server */ afs_FS_GetCapabilities = 65540, /* AFS Get FS server capabilities */ + + yfs_FS_FetchData = 130, /* YFS Fetch file data */ + yfs_FS_FetchACL = 64131, /* YFS Fetch file ACL */ + yfs_FS_FetchStatus = 64132, /* YFS Fetch file status */ + yfs_FS_StoreACL = 64134, /* YFS Store file ACL */ + yfs_FS_StoreStatus = 64135, /* YFS Store file status */ + yfs_FS_RemoveFile = 64136, /* YFS Remove a file */ + yfs_FS_CreateFile = 64137, /* YFS Create a file */ + yfs_FS_Rename = 64138, /* YFS Rename or move a file or directory */ + yfs_FS_Symlink = 64139, /* YFS Create a symbolic link */ + yfs_FS_Link = 64140, /* YFS Create a hard link */ + yfs_FS_MakeDir = 64141, /* YFS Create a directory */ + yfs_FS_RemoveDir = 64142, /* YFS Remove a directory */ + yfs_FS_GetVolumeStatus = 64149, /* YFS Get volume status information */ + yfs_FS_SetVolumeStatus = 64150, /* YFS Set volume status information */ + yfs_FS_SetLock = 64156, /* YFS Request a file lock */ + yfs_FS_ExtendLock = 64157, /* YFS Extend a file lock */ + yfs_FS_ReleaseLock = 64158, /* YFS Release a file lock */ + yfs_FS_Lookup = 64161, /* YFS lookup file in directory */ + yfs_FS_FlushCPS = 64165, + yfs_FS_FetchOpaqueACL = 64168, + yfs_FS_WhoAmI = 64170, + yfs_FS_RemoveACL = 64171, + yfs_FS_RemoveFile2 = 64173, + yfs_FS_StoreOpaqueACL2 = 64174, + yfs_FS_InlineBulkStatus = 64536, /* YFS Fetch multiple file statuses with errors */ + yfs_FS_FetchData64 = 64537, /* YFS Fetch file data */ + yfs_FS_StoreData64 = 64538, /* YFS Store file data */ + yfs_FS_UpdateSymlink = 64540, }; enum afs_vl_operation { @@ -84,6 +113,44 @@ enum afs_edit_dir_reason { afs_edit_dir_for_unlink, }; +enum afs_eproto_cause { + afs_eproto_bad_status, + afs_eproto_cb_count, + afs_eproto_cb_fid_count, + afs_eproto_file_type, + afs_eproto_ibulkst_cb_count, + afs_eproto_ibulkst_count, + afs_eproto_motd_len, + afs_eproto_offline_msg_len, + afs_eproto_volname_len, + afs_eproto_yvl_fsendpt4_len, + afs_eproto_yvl_fsendpt6_len, + afs_eproto_yvl_fsendpt_num, + afs_eproto_yvl_fsendpt_type, + afs_eproto_yvl_vlendpt4_len, + afs_eproto_yvl_vlendpt6_len, + afs_eproto_yvl_vlendpt_type, +}; + +enum afs_io_error { + afs_io_error_cm_reply, + afs_io_error_extract, + afs_io_error_fs_probe_fail, + afs_io_error_vl_lookup_fail, + afs_io_error_vl_probe_fail, +}; + +enum afs_file_error { + afs_file_error_dir_bad_magic, + afs_file_error_dir_big, + afs_file_error_dir_missing_page, + afs_file_error_dir_over_end, + afs_file_error_dir_small, + afs_file_error_dir_unmarked_ext, + afs_file_error_mntpt, + afs_file_error_writeback_fail, +}; + #endif /* end __AFS_DECLARE_TRACE_ENUMS_ONCE_ONLY */ /* @@ -119,7 +186,34 @@ enum afs_edit_dir_reason { EM(afs_FS_FetchData64, "FS.FetchData64") \ EM(afs_FS_StoreData64, "FS.StoreData64") \ EM(afs_FS_GiveUpAllCallBacks, "FS.GiveUpAllCallBacks") \ - E_(afs_FS_GetCapabilities, "FS.GetCapabilities") + EM(afs_FS_GetCapabilities, "FS.GetCapabilities") \ + EM(yfs_FS_FetchACL, "YFS.FetchACL") \ + EM(yfs_FS_FetchStatus, "YFS.FetchStatus") \ + EM(yfs_FS_StoreACL, "YFS.StoreACL") \ + EM(yfs_FS_StoreStatus, "YFS.StoreStatus") \ + EM(yfs_FS_RemoveFile, "YFS.RemoveFile") \ + EM(yfs_FS_CreateFile, "YFS.CreateFile") \ + EM(yfs_FS_Rename, "YFS.Rename") \ + EM(yfs_FS_Symlink, "YFS.Symlink") \ + EM(yfs_FS_Link, "YFS.Link") \ + EM(yfs_FS_MakeDir, "YFS.MakeDir") \ + EM(yfs_FS_RemoveDir, "YFS.RemoveDir") \ + EM(yfs_FS_GetVolumeStatus, "YFS.GetVolumeStatus") \ + EM(yfs_FS_SetVolumeStatus, "YFS.SetVolumeStatus") \ + EM(yfs_FS_SetLock, "YFS.SetLock") \ + EM(yfs_FS_ExtendLock, "YFS.ExtendLock") \ + EM(yfs_FS_ReleaseLock, "YFS.ReleaseLock") \ + EM(yfs_FS_Lookup, "YFS.Lookup") \ + EM(yfs_FS_FlushCPS, "YFS.FlushCPS") \ + EM(yfs_FS_FetchOpaqueACL, "YFS.FetchOpaqueACL") \ + EM(yfs_FS_WhoAmI, "YFS.WhoAmI") \ + EM(yfs_FS_RemoveACL, "YFS.RemoveACL") \ + EM(yfs_FS_RemoveFile2, "YFS.RemoveFile2") \ + EM(yfs_FS_StoreOpaqueACL2, "YFS.StoreOpaqueACL2") \ + EM(yfs_FS_InlineBulkStatus, "YFS.InlineBulkStatus") \ + EM(yfs_FS_FetchData64, "YFS.FetchData64") \ + EM(yfs_FS_StoreData64, "YFS.StoreData64") \ + E_(yfs_FS_UpdateSymlink, "YFS.UpdateSymlink") #define afs_vl_operations \ EM(afs_VL_GetEntryByNameU, "VL.GetEntryByNameU") \ @@ -146,6 +240,40 @@ enum afs_edit_dir_reason { EM(afs_edit_dir_for_symlink, "Symlnk") \ E_(afs_edit_dir_for_unlink, "Unlink") +#define afs_eproto_causes \ + EM(afs_eproto_bad_status, "BadStatus") \ + EM(afs_eproto_cb_count, "CbCount") \ + EM(afs_eproto_cb_fid_count, "CbFidCount") \ + EM(afs_eproto_file_type, "FileTYpe") \ + EM(afs_eproto_ibulkst_cb_count, "IBS.CbCount") \ + EM(afs_eproto_ibulkst_count, "IBS.FidCount") \ + EM(afs_eproto_motd_len, "MotdLen") \ + EM(afs_eproto_offline_msg_len, "OfflineMsgLen") \ + EM(afs_eproto_volname_len, "VolNameLen") \ + EM(afs_eproto_yvl_fsendpt4_len, "YVL.FsEnd4Len") \ + EM(afs_eproto_yvl_fsendpt6_len, "YVL.FsEnd6Len") \ + EM(afs_eproto_yvl_fsendpt_num, "YVL.FsEndCount") \ + EM(afs_eproto_yvl_fsendpt_type, "YVL.FsEndType") \ + EM(afs_eproto_yvl_vlendpt4_len, "YVL.VlEnd4Len") \ + EM(afs_eproto_yvl_vlendpt6_len, "YVL.VlEnd6Len") \ + E_(afs_eproto_yvl_vlendpt_type, "YVL.VlEndType") + +#define afs_io_errors \ + EM(afs_io_error_cm_reply, "CM_REPLY") \ + EM(afs_io_error_extract, "EXTRACT") \ + EM(afs_io_error_fs_probe_fail, "FS_PROBE_FAIL") \ + EM(afs_io_error_vl_lookup_fail, "VL_LOOKUP_FAIL") \ + E_(afs_io_error_vl_probe_fail, "VL_PROBE_FAIL") + +#define afs_file_errors \ + EM(afs_file_error_dir_bad_magic, "DIR_BAD_MAGIC") \ + EM(afs_file_error_dir_big, "DIR_BIG") \ + EM(afs_file_error_dir_missing_page, "DIR_MISSING_PAGE") \ + EM(afs_file_error_dir_over_end, "DIR_ENT_OVER_END") \ + EM(afs_file_error_dir_small, "DIR_SMALL") \ + EM(afs_file_error_dir_unmarked_ext, "DIR_UNMARKED_EXT") \ + EM(afs_file_error_mntpt, "MNTPT_READ_FAILED") \ + E_(afs_file_error_writeback_fail, "WRITEBACK_FAILED") /* * Export enum symbols via userspace. @@ -160,6 +288,9 @@ afs_fs_operations; afs_vl_operations; afs_edit_dir_ops; afs_edit_dir_reasons; +afs_eproto_causes; +afs_io_errors; +afs_file_errors; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -170,17 +301,16 @@ afs_edit_dir_reasons; #define EM(a, b) { a, b }, #define E_(a, b) { a, b } -TRACE_EVENT(afs_recv_data, - TP_PROTO(struct afs_call *call, unsigned count, unsigned offset, +TRACE_EVENT(afs_receive_data, + TP_PROTO(struct afs_call *call, struct iov_iter *iter, bool want_more, int ret), - TP_ARGS(call, count, offset, want_more, ret), + TP_ARGS(call, iter, want_more, ret), TP_STRUCT__entry( + __field(loff_t, remain ) __field(unsigned int, call ) __field(enum afs_call_state, state ) - __field(unsigned int, count ) - __field(unsigned int, offset ) __field(unsigned short, unmarshall ) __field(bool, want_more ) __field(int, ret ) @@ -190,17 +320,18 @@ TRACE_EVENT(afs_recv_data, __entry->call = call->debug_id; __entry->state = call->state; __entry->unmarshall = call->unmarshall; - __entry->count = count; - __entry->offset = offset; + __entry->remain = iov_iter_count(iter); __entry->want_more = want_more; __entry->ret = ret; ), - TP_printk("c=%08x s=%u u=%u %u/%u wm=%u ret=%d", + TP_printk("c=%08x r=%llu u=%u w=%u s=%u ret=%d", __entry->call, - __entry->state, __entry->unmarshall, - __entry->offset, __entry->count, - __entry->want_more, __entry->ret) + __entry->remain, + __entry->unmarshall, + __entry->want_more, + __entry->state, + __entry->ret) ); TRACE_EVENT(afs_notify_call, @@ -301,7 +432,7 @@ TRACE_EVENT(afs_make_fs_call, } ), - TP_printk("c=%08x %06x:%06x:%06x %s", + TP_printk("c=%08x %06llx:%06llx:%06x %s", __entry->call, __entry->fid.vid, __entry->fid.vnode, @@ -555,24 +686,70 @@ TRACE_EVENT(afs_edit_dir, ); TRACE_EVENT(afs_protocol_error, - TP_PROTO(struct afs_call *call, int error, const void *where), + TP_PROTO(struct afs_call *call, int error, enum afs_eproto_cause cause), + + TP_ARGS(call, error, cause), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(int, error ) + __field(enum afs_eproto_cause, cause ) + ), + + TP_fast_assign( + __entry->call = call ? call->debug_id : 0; + __entry->error = error; + __entry->cause = cause; + ), + + TP_printk("c=%08x r=%d %s", + __entry->call, __entry->error, + __print_symbolic(__entry->cause, afs_eproto_causes)) + ); + +TRACE_EVENT(afs_io_error, + TP_PROTO(unsigned int call, int error, enum afs_io_error where), TP_ARGS(call, error, where), TP_STRUCT__entry( __field(unsigned int, call ) __field(int, error ) - __field(const void *, where ) + __field(enum afs_io_error, where ) ), TP_fast_assign( - __entry->call = call ? call->debug_id : 0; + __entry->call = call; + __entry->error = error; + __entry->where = where; + ), + + TP_printk("c=%08x r=%d %s", + __entry->call, __entry->error, + __print_symbolic(__entry->where, afs_io_errors)) + ); + +TRACE_EVENT(afs_file_error, + TP_PROTO(struct afs_vnode *vnode, int error, enum afs_file_error where), + + TP_ARGS(vnode, error, where), + + TP_STRUCT__entry( + __field_struct(struct afs_fid, fid ) + __field(int, error ) + __field(enum afs_file_error, where ) + ), + + TP_fast_assign( + __entry->fid = vnode->fid; __entry->error = error; __entry->where = where; ), - TP_printk("c=%08x r=%d sp=%pSR", - __entry->call, __entry->error, __entry->where) + TP_printk("%llx:%llx:%x r=%d %s", + __entry->fid.vid, __entry->fid.vnode, __entry->fid.unique, + __entry->error, + __print_symbolic(__entry->where, afs_file_errors)) ); TRACE_EVENT(afs_cm_no_server, diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index 0f3cb13db8e93e..f45ee0f69c0c25 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -61,6 +61,11 @@ #define KEYCTL_INVALIDATE 21 /* invalidate a key */ #define KEYCTL_GET_PERSISTENT 22 /* get a user's persistent keyring */ #define KEYCTL_DH_COMPUTE 23 /* Compute Diffie-Hellman values */ +#define KEYCTL_PKEY_QUERY 24 /* Query public key parameters */ +#define KEYCTL_PKEY_ENCRYPT 25 /* Encrypt a blob using a public key */ +#define KEYCTL_PKEY_DECRYPT 26 /* Decrypt a blob using a public key */ +#define KEYCTL_PKEY_SIGN 27 /* Create a public key signature */ +#define KEYCTL_PKEY_VERIFY 28 /* Verify a public key signature */ #define KEYCTL_RESTRICT_KEYRING 29 /* Restrict keys allowed to link to a keyring */ /* keyctl structures */ @@ -82,4 +87,29 @@ struct keyctl_kdf_params { __u32 __spare[8]; }; +#define KEYCTL_SUPPORTS_ENCRYPT 0x01 +#define KEYCTL_SUPPORTS_DECRYPT 0x02 +#define KEYCTL_SUPPORTS_SIGN 0x04 +#define KEYCTL_SUPPORTS_VERIFY 0x08 + +struct keyctl_pkey_query { + __u32 supported_ops; /* Which ops are supported */ + __u32 key_size; /* Size of the key in bits */ + __u16 max_data_size; /* Maximum size of raw data to sign in bytes */ + __u16 max_sig_size; /* Maximum size of signature in bytes */ + __u16 max_enc_size; /* Maximum size of encrypted blob in bytes */ + __u16 max_dec_size; /* Maximum size of decrypted blob in bytes */ + __u32 __spare[10]; +}; + +struct keyctl_pkey_params { + __s32 key_id; /* Serial no. of public key to use */ + __u32 in_len; /* Input data size */ + union { + __u32 out_len; /* Output buffer size (encrypt/decrypt/sign) */ + __u32 in2_len; /* 2nd input data size (verify) */ + }; + __u32 __spare[7]; +}; + #endif /* _LINUX_KEYCTL_H */ diff --git a/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 13b8cb563892b7..a1966cd7b67749 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -34,15 +34,23 @@ #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */ #define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */ #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM 2 /* Deflate balloon on OOM */ +#define VIRTIO_BALLOON_F_FREE_PAGE_HINT 3 /* VQ to report free pages */ +#define VIRTIO_BALLOON_F_PAGE_POISON 4 /* Guest is using page poisoning */ /* Size of a PFN in the balloon interface. */ #define VIRTIO_BALLOON_PFN_SHIFT 12 +#define VIRTIO_BALLOON_CMD_ID_STOP 0 +#define VIRTIO_BALLOON_CMD_ID_DONE 1 struct virtio_balloon_config { /* Number of pages host wants Guest to give up. */ __u32 num_pages; /* Number of pages we've actually got in balloon. */ __u32 actual; + /* Free page report command id, readonly by guest */ + __u32 free_page_report_cmd_id; + /* Stores PAGE_POISON if page poisoning is in use */ + __u32 poison_val; }; #define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */ diff --git a/kernel/Makefile b/kernel/Makefile index 7a63d567fdb571..7343b3a9bff07d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -117,6 +117,10 @@ obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o +KASAN_SANITIZE_stackleak.o := n +KCOV_INSTRUMENT_stackleak.o := n + $(obj)/configs.o: $(obj)/config_data.h targets += config_data.gz diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 171a2c88e77ddd..1971ca325fb4e7 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2852,10 +2852,6 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = NOT_INIT; } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || fn->ret_type == RET_PTR_TO_MAP_VALUE) { - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - else - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -2868,7 +2864,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } regs[BPF_REG_0].map_ptr = meta.map_ptr; - regs[BPF_REG_0].id = ++env->id_gen; + if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; + } else { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; + } } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { int id = acquire_reference_state(env, insn_idx); if (id < 0) @@ -3046,7 +3047,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->umax_value = umax_ptr; dst_reg->var_off = ptr_reg->var_off; dst_reg->off = ptr_reg->off + smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. Note that off_reg->off @@ -3076,10 +3077,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_SUB: @@ -3108,7 +3110,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->var_off = ptr_reg->var_off; dst_reg->id = ptr_reg->id; dst_reg->off = ptr_reg->off - smin_val; - dst_reg->range = ptr_reg->range; + dst_reg->raw = ptr_reg->raw; break; } /* A new variable offset is created. If the subtrahend is known @@ -3134,11 +3136,12 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off); dst_reg->off = ptr_reg->off; + dst_reg->raw = ptr_reg->raw; if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->range = 0; + dst_reg->raw = 0; } break; case BPF_AND: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8b79318810ad5c..6aaf5dd5383bba 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -493,7 +493,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, } /** - * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * @@ -502,8 +502,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ -static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, - struct cgroup_subsys *ss) +static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); @@ -524,35 +524,6 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, } /** - * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem - * @cgrp: the cgroup of interest - * @ss: the subsystem of interest - * - * Find and get the effective css of @cgrp for @ss. The effective css is - * defined as the matching css of the nearest ancestor including self which - * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, - * the root css is returned, so this function always returns a valid css. - * - * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. - */ -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, - struct cgroup_subsys *ss) -{ - struct cgroup_subsys_state *css; - - do { - css = cgroup_css(cgrp, ss); - - if (css) - return css; - cgrp = cgroup_parent(cgrp); - } while (cgrp); - - return init_css_set.subsys[ss->id]; -} - -/** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest @@ -634,11 +605,10 @@ EXPORT_SYMBOL_GPL(of_css); * * Should be called under cgroup_[tree_]mutex. */ -#define for_each_e_css(css, ssid, cgrp) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((css) = cgroup_e_css_by_mask(cgrp, \ - cgroup_subsys[(ssid)]))) \ - ; \ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ + ; \ else /** @@ -1037,7 +1007,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ - template[i] = cgroup_e_css_by_mask(cgrp, ss); + template[i] = cgroup_e_css(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want @@ -3054,7 +3024,7 @@ static int cgroup_apply_control(struct cgroup *cgrp) return ret; /* - * At this point, cgroup_e_css_by_mask() results reflect the new csses + * At this point, cgroup_e_css() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ diff --git a/kernel/configs/kvm_guest.config b/kernel/configs/kvm_guest.config index 108fecc20fc148..208481d9109030 100644 --- a/kernel/configs/kvm_guest.config +++ b/kernel/configs/kvm_guest.config @@ -20,6 +20,7 @@ CONFIG_PARAVIRT=y CONFIG_KVM_GUEST=y CONFIG_S390_GUEST=y CONFIG_VIRTIO=y +CONFIG_VIRTIO_MENU=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BLK=y CONFIG_VIRTIO_CONSOLE=y diff --git a/kernel/fork.c b/kernel/fork.c index 8f82a3bdcb8fef..07cddff89c7b6b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -91,6 +91,7 @@ #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> +#include <linux/stackleak.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -1926,6 +1927,8 @@ static __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; + stackleak_task_init(p); + if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index c6a3b6851372c4..35cf0ad29718ff 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -25,8 +25,6 @@ #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/kernel.h> -#include <linux/kexec.h> -#include <linux/slab.h> #include <linux/syscalls.h> #include <linux/vmalloc.h> #include "kexec_internal.h" diff --git a/kernel/stackleak.c b/kernel/stackleak.c new file mode 100644 index 00000000000000..e42892926244de --- /dev/null +++ b/kernel/stackleak.c @@ -0,0 +1,132 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code fills the used part of the kernel stack with a poison value + * before returning to userspace. It's part of the STACKLEAK feature + * ported from grsecurity/PaX. + * + * Author: Alexander Popov <alex.popov@linux.com> + * + * STACKLEAK reduces the information which kernel stack leak bugs can + * reveal and blocks some uninitialized stack variable attacks. + */ + +#include <linux/stackleak.h> + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include <linux/jump_label.h> +#include <linux/sysctl.h> + +static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); + +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = 0; + int state = !static_branch_unlikely(&stack_erasing_bypass); + int prev_state = state; + + table->data = &state; + table->maxlen = sizeof(int); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + state = !!state; + if (ret || !write || state == prev_state) + return ret; + + if (state) + static_branch_disable(&stack_erasing_bypass); + else + static_branch_enable(&stack_erasing_bypass); + + pr_warn("stackleak: kernel stack erasing is %s\n", + state ? "enabled" : "disabled"); + return ret; +} + +#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) +#else +#define skip_erasing() false +#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ + +asmlinkage void stackleak_erase(void) +{ + /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ + unsigned long kstack_ptr = current->lowest_stack; + unsigned long boundary = (unsigned long)end_of_stack(current); + unsigned int poison_count = 0; + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + + if (skip_erasing()) + return; + + /* Check that 'lowest_stack' value is sane */ + if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) + kstack_ptr = boundary; + + /* Search for the poison value in the kernel stack */ + while (kstack_ptr > boundary && poison_count <= depth) { + if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON) + poison_count++; + else + poison_count = 0; + + kstack_ptr -= sizeof(unsigned long); + } + + /* + * One 'long int' at the bottom of the thread stack is reserved and + * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y). + */ + if (kstack_ptr == boundary) + kstack_ptr += sizeof(unsigned long); + +#ifdef CONFIG_STACKLEAK_METRICS + current->prev_lowest_stack = kstack_ptr; +#endif + + /* + * Now write the poison value to the kernel stack. Start from + * 'kstack_ptr' and move up till the new 'boundary'. We assume that + * the stack pointer doesn't change when we write poison. + */ + if (on_thread_stack()) + boundary = current_stack_pointer; + else + boundary = current_top_of_stack(); + + while (kstack_ptr < boundary) { + *(unsigned long *)kstack_ptr = STACKLEAK_POISON; + kstack_ptr += sizeof(unsigned long); + } + + /* Reset the 'lowest_stack' value for the next syscall */ + current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; +} + +void __used stackleak_track_stack(void) +{ + /* + * N.B. stackleak_erase() fills the kernel stack with the poison value, + * which has the register width. That code assumes that the value + * of 'lowest_stack' is aligned on the register width boundary. + * + * That is true for x86 and x86_64 because of the kernel stack + * alignment on these platforms (for details, see 'cc_stack_align' in + * arch/x86/Makefile). Take care of that when you port STACKLEAK to + * new platforms. + */ + unsigned long sp = (unsigned long)&sp; + + /* + * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than + * STACKLEAK_SEARCH_DEPTH makes the poison search in + * stackleak_erase() unreliable. Let's prevent that. + */ + BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH); + + if (sp < current->lowest_stack && + sp >= (unsigned long)task_stack_page(current) + + sizeof(unsigned long)) { + current->lowest_stack = sp; + } +} +EXPORT_SYMBOL(stackleak_track_stack); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cc02050fd0c493..5fc724e4e454c3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -66,7 +66,6 @@ #include <linux/kexec.h> #include <linux/bpf.h> #include <linux/mount.h> -#include <linux/pipe_fs_i.h> #include <linux/uaccess.h> #include <asm/processor.h> @@ -91,7 +90,9 @@ #ifdef CONFIG_CHR_DEV_SG #include <scsi/sg.h> #endif - +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include <linux/stackleak.h> +#endif #ifdef CONFIG_LOCKUP_DETECTOR #include <linux/nmi.h> #endif @@ -1233,6 +1234,17 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = &zero, + .extra2 = &one, + }, +#endif { } }; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fac0ddf8a8e225..2868d85f1fb1d3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_blkg) + if (!bio->bi_css) return NULL; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_get_kernfs_id(bio->bi_css->cgroup); } #else static union kernfs_node_id * diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c index b0875b327f5c3d..c3fd849d4a8f93 100644 --- a/kernel/trace/trace_printk.c +++ b/kernel/trace/trace_printk.c @@ -115,7 +115,7 @@ static int module_trace_bprintk_format_notify(struct notifier_block *self, * section, then we need to read the link list pointers. The trick is * we pass the address of the string to the seq function just like * we do for the kernel core formats. To get back the structure that - * holds the format, we simply use containerof() and then go to the + * holds the format, we simply use container_of() and then go to the * next format in the list. */ static const char ** diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 8be175df30753c..7ebccb5c16377e 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -83,6 +83,7 @@ const struct kvec *kvec; \ struct kvec v; \ iterate_kvec(i, n, v, kvec, skip, (K)) \ + } else if (unlikely(i->type & ITER_DISCARD)) { \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -114,6 +115,8 @@ } \ i->nr_segs -= kvec - i->kvec; \ i->kvec = kvec; \ + } else if (unlikely(i->type & ITER_DISCARD)) { \ + skip += n; \ } else { \ const struct iovec *iov; \ struct iovec v; \ @@ -428,17 +431,19 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); -void iov_iter_init(struct iov_iter *i, int direction, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { + WARN_ON(direction & ~(READ | WRITE)); + direction &= READ | WRITE; + /* It will get better. Eventually... */ if (uaccess_kernel()) { - direction |= ITER_KVEC; - i->type = direction; + i->type = ITER_KVEC | direction; i->kvec = (struct kvec *)iov; } else { - i->type = direction; + i->type = ITER_IOVEC | direction; i->iov = iov; } i->nr_segs = nr_segs; @@ -558,7 +563,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -658,7 +663,7 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -692,7 +697,7 @@ EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -712,7 +717,7 @@ EXPORT_SYMBOL(_copy_from_iter); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -739,7 +744,7 @@ EXPORT_SYMBOL(_copy_from_iter_full); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -773,7 +778,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache); size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -794,7 +799,7 @@ EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -836,7 +841,9 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; - } else if (likely(!(i->type & ITER_PIPE))) + } else if (unlikely(iov_iter_is_discard(i))) + return bytes; + else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); @@ -848,7 +855,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } @@ -888,7 +895,7 @@ static size_t pipe_zero(size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), @@ -908,7 +915,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, kunmap_atomic(kaddr); return 0; } - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; @@ -972,10 +979,14 @@ static void pipe_advance(struct iov_iter *i, size_t size) void iov_iter_advance(struct iov_iter *i, size_t size) { - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { pipe_advance(i, size); return; } + if (unlikely(iov_iter_is_discard(i))) { + i->count -= size; + return; + } iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -987,7 +998,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; int idx = i->idx; size_t off = i->iov_offset; @@ -1011,12 +1022,14 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) pipe_truncate(i); return; } + if (unlikely(iov_iter_is_discard(i))) + return; if (unroll <= i->iov_offset) { i->iov_offset -= unroll; return; } unroll -= i->iov_offset; - if (i->type & ITER_BVEC) { + if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; @@ -1049,23 +1062,25 @@ EXPORT_SYMBOL(iov_iter_revert); */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; - else if (i->type & ITER_BVEC) + if (unlikely(iov_iter_is_discard(i))) + return i->count; + else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); } EXPORT_SYMBOL(iov_iter_single_seg_count); -void iov_iter_kvec(struct iov_iter *i, int direction, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_KVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_KVEC | (direction & (READ | WRITE)); i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1073,12 +1088,12 @@ void iov_iter_kvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_kvec); -void iov_iter_bvec(struct iov_iter *i, int direction, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_BVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_BVEC | (direction & (READ | WRITE)); i->bvec = bvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1086,13 +1101,13 @@ void iov_iter_bvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_bvec); -void iov_iter_pipe(struct iov_iter *i, int direction, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { - BUG_ON(direction != ITER_PIPE); + BUG_ON(direction != READ); WARN_ON(pipe->nrbufs == pipe->buffers); - i->type = direction; + i->type = ITER_PIPE | READ; i->pipe = pipe; i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); i->iov_offset = 0; @@ -1101,12 +1116,30 @@ void iov_iter_pipe(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_pipe); +/** + * iov_iter_discard - Initialise an I/O iterator that discards data + * @i: The iterator to initialise. + * @direction: The direction of the transfer. + * @count: The size of the I/O buffer in bytes. + * + * Set up an I/O iterator that just discards everything that's written to it. + * It's only available as a READ iterator. + */ +void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) +{ + BUG_ON(direction != READ); + i->type = ITER_DISCARD | READ; + i->count = count; + i->iov_offset = 0; +} +EXPORT_SYMBOL(iov_iter_discard); + unsigned long iov_iter_alignment(const struct iov_iter *i) { unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx])) return size | i->iov_offset; return size; @@ -1125,7 +1158,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return ~0U; } @@ -1193,8 +1226,11 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); + if (unlikely(iov_iter_is_discard(i))) + return -EFAULT; + iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); @@ -1205,7 +1241,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, len = maxpages * PAGE_SIZE; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages); if (unlikely(res < 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; @@ -1270,8 +1306,11 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); + if (unlikely(iov_iter_is_discard(i))) + return -EFAULT; + iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); @@ -1283,7 +1322,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, p = get_pages_array(n); if (!p) return -ENOMEM; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p); if (unlikely(res < 0)) { kvfree(p); return res; @@ -1313,7 +1352,7 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return 0; } @@ -1355,7 +1394,7 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); return false; } @@ -1400,7 +1439,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } @@ -1442,8 +1481,10 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) if (!size) return 0; + if (unlikely(iov_iter_is_discard(i))) + return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; size_t off; int idx; @@ -1481,11 +1522,13 @@ EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; - if (unlikely(new->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } - if (new->type & ITER_BVEC) + if (unlikely(iov_iter_is_discard(new))) + return NULL; + if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); diff --git a/mm/filemap.c b/mm/filemap.c index 218d0b2ec82d15..81adec8ee02cc3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2049,7 +2049,7 @@ find_page: !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ - if (unlikely(iter->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; @@ -2825,6 +2825,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping, EXPORT_SYMBOL(read_cache_page_gfp); /* + * Don't operate on ranges the page cache doesn't support, and don't exceed the + * LFS limits. If pos is under the limit it becomes a short access. If it + * exceeds the limit we return -EFBIG. + */ +static int generic_access_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + struct inode *inode = file->f_mapping->host; + loff_t max_size = inode->i_sb->s_maxbytes; + + if (!(file->f_flags & O_LARGEFILE)) + max_size = MAX_NON_LFS; + + if (unlikely(pos >= max_size)) + return -EFBIG; + *count = min(*count, max_size - pos); + return 0; +} + +static int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + loff_t limit = rlimit(RLIMIT_FSIZE); + + if (limit != RLIM_INFINITY) { + if (pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + *count = min(*count, limit - pos); + } + + return generic_access_check_limits(file, pos, count); +} + +/* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. @@ -2835,8 +2871,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - unsigned long limit = rlimit(RLIMIT_FSIZE); - loff_t pos; + loff_t count; + int ret; if (!iov_iter_count(from)) return 0; @@ -2845,43 +2881,99 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); - pos = iocb->ki_pos; - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) return -EINVAL; - if (limit != RLIM_INFINITY) { - if (iocb->ki_pos >= limit) { - send_sig(SIGXFSZ, current, 0); - return -EFBIG; - } - iov_iter_truncate(from, limit - (unsigned long)pos); - } + count = iov_iter_count(from); + ret = generic_write_check_limits(file, iocb->ki_pos, &count); + if (ret) + return ret; + + iov_iter_truncate(from, count); + return iov_iter_count(from); +} +EXPORT_SYMBOL(generic_write_checks); + +/* + * Performs necessary checks before doing a clone. + * + * Can adjust amount of bytes to clone. + * Returns appropriate error code that caller should return or + * zero in case the clone should be allowed. + */ +int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t *req_count, unsigned int remap_flags) +{ + struct inode *inode_in = file_in->f_mapping->host; + struct inode *inode_out = file_out->f_mapping->host; + uint64_t count = *req_count; + uint64_t bcount; + loff_t size_in, size_out; + loff_t bs = inode_out->i_sb->s_blocksize; + int ret; + + /* The start of both ranges must be aligned to an fs block. */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) + return -EINVAL; + + /* Ensure offsets don't wrap. */ + if (pos_in + count < pos_in || pos_out + count < pos_out) + return -EINVAL; + + size_in = i_size_read(inode_in); + size_out = i_size_read(inode_out); + + /* Dedupe requires both ranges to be within EOF. */ + if ((remap_flags & REMAP_FILE_DEDUP) && + (pos_in >= size_in || pos_in + count > size_in || + pos_out >= size_out || pos_out + count > size_out)) + return -EINVAL; + + /* Ensure the infile range is within the infile. */ + if (pos_in >= size_in) + return -EINVAL; + count = min(count, size_in - (uint64_t)pos_in); + + ret = generic_access_check_limits(file_in, pos_in, &count); + if (ret) + return ret; + + ret = generic_write_check_limits(file_out, pos_out, &count); + if (ret) + return ret; /* - * LFS rule + * If the user wanted us to link to the infile's EOF, round up to the + * next block boundary for this check. + * + * Otherwise, make sure the count is also block-aligned, having + * already confirmed the starting offsets' block alignment. */ - if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS && - !(file->f_flags & O_LARGEFILE))) { - if (pos >= MAX_NON_LFS) - return -EFBIG; - iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos); + if (pos_in + count == size_in) { + bcount = ALIGN(size_in, bs) - pos_in; + } else { + if (!IS_ALIGNED(count, bs)) + count = ALIGN_DOWN(count, bs); + bcount = count; } + /* Don't allow overlapped cloning within the same file. */ + if (inode_in == inode_out && + pos_out + bcount > pos_in && + pos_out < pos_in + bcount) + return -EINVAL; + /* - * Are we about to exceed the fs block limit ? - * - * If we have written data it becomes a short write. If we have - * exceeded without writing data we send a signal and return EFBIG. - * Linus frestrict idea will clean these up nicely.. + * We shortened the request but the caller can't deal with that, so + * bounce the request back to userspace. */ - if (unlikely(pos >= inode->i_sb->s_maxbytes)) - return -EFBIG; + if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return -EINVAL; - iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos); - return iov_iter_count(from); + *req_count = count; + return 0; } -EXPORT_SYMBOL(generic_write_checks); int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4e4ef8fa479d53..55478ab3c83be3 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -629,21 +629,40 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + gfp_t this_node = 0; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - 0); - return GFP_TRANSHUGE_LIGHT; + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ @@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 54920cbc46bfdc..6e1469b80cb7d5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2593,7 +2593,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) struct mem_cgroup *memcg; int ret = 0; - if (memcg_kmem_bypass()) + if (mem_cgroup_disabled() || memcg_kmem_bypass()) return 0; memcg = get_mem_cgroup_from_current(); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 61972da38d93cb..2b2b3ccbbfb576 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -586,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; + cond_resched(); ret = __remove_section(zone, __pfn_to_section(pfn), map_offset, altmap); map_offset = 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cfd26d7e61a17f..5837a067124d89 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2040,32 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && - !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/page_io.c b/mm/page_io.c index a451ffa9491ca0..d4d1c89bcdddce 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, }; struct iov_iter from; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); @@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); - bio_associate_blkg_from_page(bio, page); + bio_associate_blkcg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); diff --git a/mm/page_poison.c b/mm/page_poison.c index f7e2a676365a10..f0c15e9017c022 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -17,6 +17,11 @@ static int __init early_page_poison_param(char *buf) } early_param("page_poison", early_page_poison_param); +/** + * page_poisoning_enabled - check if page poisoning is enabled + * + * Return true if page poisoning is enabled, or false if not. + */ bool page_poisoning_enabled(void) { /* @@ -29,6 +34,7 @@ bool page_poisoning_enabled(void) (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && debug_pagealloc_enabled())); } +EXPORT_SYMBOL_GPL(page_poisoning_enabled); static void poison_page(struct page *page) { diff --git a/mm/percpu.c b/mm/percpu.c index a6b74c6fe0becd..db86282fd02458 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2591,7 +2591,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); - if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) { + if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } diff --git a/mm/shmem.c b/mm/shmem.c index 56bf122e0bb4dd..ea26d7a0342d77 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); diff --git a/net/9p/client.c b/net/9p/client.c index 5f23e18eecc02f..2c9a17b9b46bb3 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2066,7 +2066,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) struct kvec kv = {.iov_base = data, .iov_len = count}; struct iov_iter to; - iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count); + iov_iter_kvec(&to, READ, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, (unsigned long long) offset, count); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index eb596c2ed546ca..b1d39cabf125a7 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -329,7 +329,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, if (!iov_iter_count(data)) return 0; - if (!(data->type & ITER_KVEC)) { + if (!iov_iter_is_kvec(data)) { int n; /* * We allow only p9_max_pages pinned. We wait for the diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4e2576fc0c5993..828e87fe802788 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, iv.iov_len = skb->len; memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len); err = l2cap_chan_send(chan, &msg, skb->len); if (err > 0) { diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 51c2cf2d8923ae..58fc6333d41225 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len); l2cap_chan_send(chan, &msg, total_len); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a1c1b7e8a45ca6..c822e626761bd0 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len); + iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len); l2cap_chan_send(chan, &msg, 1 + len); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 88e35830198cd3..57fcc6b4bf6e1d 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -513,7 +513,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) if (!buf) msg.msg_flags |= MSG_TRUNC; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -532,7 +532,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int r; BUG_ON(page_offset + length > PAGE_SIZE); - iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length); + iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -594,7 +594,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, else msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size); + iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size); ret = sock_sendmsg(sock, &msg); if (ret == -EAGAIN) ret = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f679c7a7d761a6..e01274bd5e3e21 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3600,6 +3600,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; } + if (dev->type != ARPHRD_ETHER) { + NL_SET_ERR_MSG(extack, "FDB add only supported for Ethernet devices"); + return -EINVAL; + } + addr = nla_data(tb[NDA_LLADDR]); err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); @@ -3704,6 +3709,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, return -EINVAL; } + if (dev->type != ARPHRD_ETHER) { + NL_SET_ERR_MSG(extack, "FDB delete only supported for Ethernet devices"); + return -EINVAL; + } + addr = nla_data(tb[NDA_LLADDR]); err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 4da39446da2d89..765b2b32c4a426 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -111,13 +111,10 @@ #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ -#define IGMP_V1_ROUTER_PRESENT_TIMEOUT (400*HZ) -#define IGMP_V2_ROUTER_PRESENT_TIMEOUT (400*HZ) #define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) #define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) +#define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) -#define IGMP_QUERY_ROBUSTNESS_VARIABLE 2 - #define IGMP_INITIAL_REPORT_DELAY (1) @@ -935,13 +932,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + - IGMP_V1_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + - IGMP_V2_ROUTER_PRESENT_TIMEOUT; + (in_dev->mr_qrv * in_dev->mr_qi) + + in_dev->mr_qri; } /* cancel the interface change timer */ in_dev->mr_ifc_count = 0; @@ -981,8 +980,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; - if (ih3->qrv) - in_dev->mr_qrv = ih3->qrv; + + /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently + * received value was zero, use the default or statically + * configured value. + */ + in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; + + /* RFC3376, 8.3. Query Response Interval: + * The number of seconds represented by the [Query Response + * Interval] must be less than the [Query Interval]. + */ + if (in_dev->mr_qri >= in_dev->mr_qi) + in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; + if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ @@ -1723,18 +1735,30 @@ void ip_mc_down(struct in_device *in_dev) ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } -void ip_mc_init_dev(struct in_device *in_dev) -{ #ifdef CONFIG_IP_MULTICAST +static void ip_mc_reset(struct in_device *in_dev) +{ struct net *net = dev_net(in_dev->dev); + + in_dev->mr_qi = IGMP_QUERY_INTERVAL; + in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; + in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; +} +#else +static void ip_mc_reset(struct in_device *in_dev) +{ +} #endif + +void ip_mc_init_dev(struct in_device *in_dev) +{ ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; #endif + ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1744,15 +1768,10 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); -#ifdef CONFIG_IP_MULTICAST - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; -#endif + ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index b7918d4caa300a..3b45fe530f91e2 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -145,6 +145,7 @@ msg_bytes_ready: ret = err; goto out; } + copied = -EAGAIN; } ret = copied; out: diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d4020c5e831d30..2526be6b3d9095 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) EnterFunction(7); /* Receive a packet */ - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index a70097ecf33c2b..865ecef6819690 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -3030,7 +3030,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, * is already present */ if (mac_proto != MAC_PROTO_NONE) return -EINVAL; - mac_proto = MAC_PROTO_NONE; + mac_proto = MAC_PROTO_ETHERNET; break; case OVS_ACTION_ATTR_POP_ETH: @@ -3038,7 +3038,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; if (vlan_tci & htons(VLAN_TAG_PRESENT)) return -EINVAL; - mac_proto = MAC_PROTO_ETHERNET; + mac_proto = MAC_PROTO_NONE; break; case OVS_ACTION_ATTR_PUSH_NSH: diff --git a/net/sctp/associola.c b/net/sctp/associola.c index a827a1f562bf32..6a28b96e779e68 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -499,8 +499,9 @@ void sctp_assoc_set_primary(struct sctp_association *asoc, void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer) { - struct list_head *pos; - struct sctp_transport *transport; + struct sctp_transport *transport; + struct list_head *pos; + struct sctp_chunk *ch; pr_debug("%s: association:%p addr:%pISpc\n", __func__, asoc, &peer->ipaddr.sa); @@ -564,7 +565,6 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, */ if (!list_empty(&peer->transmitted)) { struct sctp_transport *active = asoc->peer.active_path; - struct sctp_chunk *ch; /* Reset the transport of each chunk on this list */ list_for_each_entry(ch, &peer->transmitted, @@ -586,6 +586,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc, sctp_transport_hold(active); } + list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list) + if (ch->transport == peer) + ch->transport = NULL; + asoc->peer.transport_count--; sctp_transport_free(peer); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index fc0386e8ff2393..739f3e50120ddf 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -7083,14 +7083,15 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len, } policy = params.sprstat_policy; - if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL))) + if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || + ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); if (!asoc) goto out; - if (policy & SCTP_PR_SCTP_ALL) { + if (policy == SCTP_PR_SCTP_ALL) { params.sprstat_abandoned_unsent = 0; params.sprstat_abandoned_sent = 0; for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) { @@ -7142,7 +7143,8 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len, } policy = params.sprstat_policy; - if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL))) + if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) || + ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK))) goto out; asoc = sctp_id2assoc(sk, params.sprstat_assoc_id); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 52241d679cc91c..89c3a8c7859a3a 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, */ krflags = MSG_PEEK | MSG_WAITALL; smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, sizeof(struct smc_clc_msg_hdr)); len = sock_recvmsg(smc->clcsock, &msg, krflags); if (signal_pending(current)) { @@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { diff --git a/net/socket.c b/net/socket.c index 99c96851469f4c..593826e11a5376 100644 --- a/net/socket.c +++ b/net/socket.c @@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg); int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); @@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } @@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, mm_segment_t oldfs = get_fs(); int result; - iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, READ, vec, num, size); set_fs(KERNEL_DS); result = sock_recvmsg(sock, msg, flags); set_fs(oldfs); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 3b525accaa6857..986f3ed7d1a248 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -336,7 +336,7 @@ static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, rqstp->rq_xprt_hlen = 0; clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen); + iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen); if (base != 0) { iov_iter_advance(&msg.msg_iter, base); buflen -= base; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 1b51e04d356609..ae77c71c1f640c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -361,7 +361,7 @@ static ssize_t xs_read_kvec(struct socket *sock, struct msghdr *msg, int flags, struct kvec *kvec, size_t count, size_t seek) { - iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, kvec, 1, count); + iov_iter_kvec(&msg->msg_iter, READ, kvec, 1, count); return xs_sock_recvmsg(sock, msg, flags, seek); } @@ -370,7 +370,7 @@ xs_read_bvec(struct socket *sock, struct msghdr *msg, int flags, struct bio_vec *bvec, unsigned long nr, size_t count, size_t seek) { - iov_iter_bvec(&msg->msg_iter, READ | ITER_BVEC, bvec, nr, count); + iov_iter_bvec(&msg->msg_iter, READ, bvec, nr, count); return xs_sock_recvmsg(sock, msg, flags, seek); } diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 4bdea00571711d..efb16f69bd2c4c 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) iov.iov_base = &s; iov.iov_len = sizeof(s); msg.msg_name = NULL; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len); ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 276edbc04f3859..d753e362d2d9e6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, iov.iov_base = kaddr + offset; iov.iov_len = size; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); rc = tls_push_data(sk, &msg_iter, size, flags, TLS_RECORD_TYPE_DATA); kunmap(page); @@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter msg_iter; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0); return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 5cd88ba8acd175..7b1af8b59cd20e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; unsigned char record_type = TLS_RECORD_TYPE_DATA; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); size_t try_to_copy, copied = 0; struct sk_msg *msg_pl, *msg_en; @@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk, bool cmsg = false; int target, err = 0; long timeo; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); int num_async = 0; flags |= nonblock; diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig index 4a9ee2d83158ba..140270a13d54f7 100644 --- a/net/xfrm/Kconfig +++ b/net/xfrm/Kconfig @@ -8,7 +8,6 @@ config XFRM config XFRM_OFFLOAD bool - depends on XFRM config XFRM_ALGO tristate diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index ca21a35fa244e7..bb015551c2d9ae 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -140,17 +140,9 @@ cc-option-yn = $(call try-run,\ cc-disable-warning = $(call try-run,\ $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) -# cc-name -# Expands to either gcc or clang -cc-name = $(shell $(CC) -v 2>&1 | grep -q "clang version" && echo clang || echo gcc) - # cc-version cc-version = $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC)) -# cc-fullversion -cc-fullversion = $(shell $(CONFIG_SHELL) \ - $(srctree)/scripts/gcc-version.sh -p $(CC)) - # cc-ifversion # Usage: EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1) cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4)) diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 24b2fb1d12974d..768306add59131 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -29,6 +29,7 @@ warning-1 += $(call cc-option, -Wmissing-include-dirs) warning-1 += $(call cc-option, -Wunused-but-set-variable) warning-1 += $(call cc-option, -Wunused-const-variable) warning-1 += $(call cc-option, -Wpacked-not-aligned) +warning-1 += $(call cc-option, -Wstringop-truncation) warning-1 += $(call cc-disable-warning, missing-field-initializers) warning-1 += $(call cc-disable-warning, sign-compare) @@ -64,7 +65,7 @@ endif KBUILD_CFLAGS += $(warning) else -ifeq ($(cc-name),clang) +ifdef CONFIG_CC_IS_CLANG KBUILD_CFLAGS += $(call cc-disable-warning, initializer-overrides) KBUILD_CFLAGS += $(call cc-disable-warning, unused-value) KBUILD_CFLAGS += $(call cc-disable-warning, format) diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index 0a482f34157676..46c5c680980657 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -26,6 +26,16 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) \ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE) \ += -fplugin-arg-randomize_layout_plugin-performance-mode +gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak_plugin.so +gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ + += -DSTACKLEAK_PLUGIN +gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ + += -fplugin-arg-stackleak_plugin-track-min-size=$(CONFIG_STACKLEAK_TRACK_MIN_SIZE) +ifdef CONFIG_GCC_PLUGIN_STACKLEAK + DISABLE_STACKLEAK_PLUGIN += -fplugin-arg-stackleak_plugin-disable +endif +export DISABLE_STACKLEAK_PLUGIN + # All the plugin CFLAGS are collected here in case a build target needs to # filter them out of the KBUILD_CFLAGS. GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index cb0c889e13aa05..0d5c799688f0ae 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -139,4 +139,55 @@ config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE in structures. This reduces the performance hit of RANDSTRUCT at the cost of weakened randomization. +config GCC_PLUGIN_STACKLEAK + bool "Erase the kernel stack before returning from syscalls" + depends on GCC_PLUGINS + depends on HAVE_ARCH_STACKLEAK + help + This option makes the kernel erase the kernel stack before + returning from system calls. That reduces the information which + kernel stack leak bugs can reveal and blocks some uninitialized + stack variable attacks. + + The tradeoff is the performance impact: on a single CPU system kernel + compilation sees a 1% slowdown, other systems and workloads may vary + and you are advised to test this feature on your expected workload + before deploying it. + + This plugin was ported from grsecurity/PaX. More information at: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + +config STACKLEAK_TRACK_MIN_SIZE + int "Minimum stack frame size of functions tracked by STACKLEAK" + default 100 + range 0 4096 + depends on GCC_PLUGIN_STACKLEAK + help + The STACKLEAK gcc plugin instruments the kernel code for tracking + the lowest border of the kernel stack (and for some other purposes). + It inserts the stackleak_track_stack() call for the functions with + a stack frame size greater than or equal to this parameter. + If unsure, leave the default value 100. + +config STACKLEAK_METRICS + bool "Show STACKLEAK metrics in the /proc file system" + depends on GCC_PLUGIN_STACKLEAK + depends on PROC_FS + help + If this is set, STACKLEAK metrics for every task are available in + the /proc file system. In particular, /proc/<pid>/stack_depth + shows the maximum kernel stack consumption for the current and + previous syscalls. Although this information is not precise, it + can be useful for estimating the STACKLEAK performance impact for + your workloads. + +config STACKLEAK_RUNTIME_DISABLE + bool "Allow runtime disabling of kernel stack erasing" + depends on GCC_PLUGIN_STACKLEAK + help + This option provides 'stack_erasing' sysctl, which can be used in + runtime to control kernel stack erasing for kernels built with + CONFIG_GCC_PLUGIN_STACKLEAK. + endif diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c new file mode 100644 index 00000000000000..2f48da98b5d421 --- /dev/null +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -0,0 +1,427 @@ +/* + * Copyright 2011-2017 by the PaX Team <pageexec@freemail.hu> + * Modified by Alexander Popov <alex.popov@linux.com> + * Licensed under the GPL v2 + * + * Note: the choice of the license means that the compilation process is + * NOT 'eligible' as defined by gcc's library exception to the GPL v3, + * but for the kernel it doesn't matter since it doesn't link against + * any of the gcc libraries + * + * This gcc plugin is needed for tracking the lowest border of the kernel stack. + * It instruments the kernel code inserting stackleak_track_stack() calls: + * - after alloca(); + * - for the functions with a stack frame size greater than or equal + * to the "track-min-size" plugin parameter. + * + * This plugin is ported from grsecurity/PaX. For more information see: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + * + * Debugging: + * - use fprintf() to stderr, debug_generic_expr(), debug_gimple_stmt(), + * print_rtl() and print_simple_rtl(); + * - add "-fdump-tree-all -fdump-rtl-all" to the plugin CFLAGS in + * Makefile.gcc-plugins to see the verbose dumps of the gcc passes; + * - use gcc -E to understand the preprocessing shenanigans; + * - use gcc with enabled CFG/GIMPLE/SSA verification (--enable-checking). + */ + +#include "gcc-common.h" + +__visible int plugin_is_GPL_compatible; + +static int track_frame_size = -1; +static const char track_function[] = "stackleak_track_stack"; + +/* + * Mark these global variables (roots) for gcc garbage collector since + * they point to the garbage-collected memory. + */ +static GTY(()) tree track_function_decl; + +static struct plugin_info stackleak_plugin_info = { + .version = "201707101337", + .help = "track-min-size=nn\ttrack stack for functions with a stack frame size >= nn bytes\n" + "disable\t\tdo not activate the plugin\n" +}; + +static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) +{ + gimple stmt; + gcall *stackleak_track_stack; + cgraph_node_ptr node; + int frequency; + basic_block bb; + + /* Insert call to void stackleak_track_stack(void) */ + stmt = gimple_build_call(track_function_decl, 0); + stackleak_track_stack = as_a_gcall(stmt); + if (after) { + gsi_insert_after(gsi, stackleak_track_stack, + GSI_CONTINUE_LINKING); + } else { + gsi_insert_before(gsi, stackleak_track_stack, GSI_SAME_STMT); + } + + /* Update the cgraph */ + bb = gimple_bb(stackleak_track_stack); + node = cgraph_get_create_node(track_function_decl); + gcc_assert(node); + frequency = compute_call_stmt_bb_frequency(current_function_decl, bb); + cgraph_create_edge(cgraph_get_node(current_function_decl), node, + stackleak_track_stack, bb->count, frequency); +} + +static bool is_alloca(gimple stmt) +{ + if (gimple_call_builtin_p(stmt, BUILT_IN_ALLOCA)) + return true; + +#if BUILDING_GCC_VERSION >= 4007 + if (gimple_call_builtin_p(stmt, BUILT_IN_ALLOCA_WITH_ALIGN)) + return true; +#endif + + return false; +} + +/* + * Work with the GIMPLE representation of the code. Insert the + * stackleak_track_stack() call after alloca() and into the beginning + * of the function if it is not instrumented. + */ +static unsigned int stackleak_instrument_execute(void) +{ + basic_block bb, entry_bb; + bool prologue_instrumented = false, is_leaf = true; + gimple_stmt_iterator gsi; + + /* + * ENTRY_BLOCK_PTR is a basic block which represents possible entry + * point of a function. This block does not contain any code and + * has a CFG edge to its successor. + */ + gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + entry_bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); + + /* + * Loop through the GIMPLE statements in each of cfun basic blocks. + * cfun is a global variable which represents the function that is + * currently processed. + */ + FOR_EACH_BB_FN(bb, cfun) { + for (gsi = gsi_start_bb(bb); !gsi_end_p(gsi); gsi_next(&gsi)) { + gimple stmt; + + stmt = gsi_stmt(gsi); + + /* Leaf function is a function which makes no calls */ + if (is_gimple_call(stmt)) + is_leaf = false; + + if (!is_alloca(stmt)) + continue; + + /* Insert stackleak_track_stack() call after alloca() */ + stackleak_add_track_stack(&gsi, true); + if (bb == entry_bb) + prologue_instrumented = true; + } + } + + if (prologue_instrumented) + return 0; + + /* + * Special cases to skip the instrumentation. + * + * Taking the address of static inline functions materializes them, + * but we mustn't instrument some of them as the resulting stack + * alignment required by the function call ABI will break other + * assumptions regarding the expected (but not otherwise enforced) + * register clobbering ABI. + * + * Case in point: native_save_fl on amd64 when optimized for size + * clobbers rdx if it were instrumented here. + * + * TODO: any more special cases? + */ + if (is_leaf && + !TREE_PUBLIC(current_function_decl) && + DECL_DECLARED_INLINE_P(current_function_decl)) { + return 0; + } + + if (is_leaf && + !strncmp(IDENTIFIER_POINTER(DECL_NAME(current_function_decl)), + "_paravirt_", 10)) { + return 0; + } + + /* Insert stackleak_track_stack() call at the function beginning */ + bb = entry_bb; + if (!single_pred_p(bb)) { + /* gcc_assert(bb_loop_depth(bb) || + (bb->flags & BB_IRREDUCIBLE_LOOP)); */ + split_edge(single_succ_edge(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); + } + gsi = gsi_after_labels(bb); + stackleak_add_track_stack(&gsi, false); + + return 0; +} + +static bool large_stack_frame(void) +{ +#if BUILDING_GCC_VERSION >= 8000 + return maybe_ge(get_frame_size(), track_frame_size); +#else + return (get_frame_size() >= track_frame_size); +#endif +} + +/* + * Work with the RTL representation of the code. + * Remove the unneeded stackleak_track_stack() calls from the functions + * which don't call alloca() and don't have a large enough stack frame size. + */ +static unsigned int stackleak_cleanup_execute(void) +{ + rtx_insn *insn, *next; + + if (cfun->calls_alloca) + return 0; + + if (large_stack_frame()) + return 0; + + /* + * Find stackleak_track_stack() calls. Loop through the chain of insns, + * which is an RTL representation of the code for a function. + * + * The example of a matching insn: + * (call_insn 8 4 10 2 (call (mem (symbol_ref ("stackleak_track_stack") + * [flags 0x41] <function_decl 0x7f7cd3302a80 stackleak_track_stack>) + * [0 stackleak_track_stack S1 A8]) (0)) 675 {*call} (expr_list + * (symbol_ref ("stackleak_track_stack") [flags 0x41] <function_decl + * 0x7f7cd3302a80 stackleak_track_stack>) (expr_list (0) (nil))) (nil)) + */ + for (insn = get_insns(); insn; insn = next) { + rtx body; + + next = NEXT_INSN(insn); + + /* Check the expression code of the insn */ + if (!CALL_P(insn)) + continue; + + /* + * Check the expression code of the insn body, which is an RTL + * Expression (RTX) describing the side effect performed by + * that insn. + */ + body = PATTERN(insn); + + if (GET_CODE(body) == PARALLEL) + body = XVECEXP(body, 0, 0); + + if (GET_CODE(body) != CALL) + continue; + + /* + * Check the first operand of the call expression. It should + * be a mem RTX describing the needed subroutine with a + * symbol_ref RTX. + */ + body = XEXP(body, 0); + if (GET_CODE(body) != MEM) + continue; + + body = XEXP(body, 0); + if (GET_CODE(body) != SYMBOL_REF) + continue; + + if (SYMBOL_REF_DECL(body) != track_function_decl) + continue; + + /* Delete the stackleak_track_stack() call */ + delete_insn_and_edges(insn); +#if BUILDING_GCC_VERSION >= 4007 && BUILDING_GCC_VERSION < 8000 + if (GET_CODE(next) == NOTE && + NOTE_KIND(next) == NOTE_INSN_CALL_ARG_LOCATION) { + insn = next; + next = NEXT_INSN(insn); + delete_insn_and_edges(insn); + } +#endif + } + + return 0; +} + +static bool stackleak_gate(void) +{ + tree section; + + section = lookup_attribute("section", + DECL_ATTRIBUTES(current_function_decl)); + if (section && TREE_VALUE(section)) { + section = TREE_VALUE(TREE_VALUE(section)); + + if (!strncmp(TREE_STRING_POINTER(section), ".init.text", 10)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".devinit.text", 13)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".cpuinit.text", 13)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".meminit.text", 13)) + return false; + } + + return track_frame_size >= 0; +} + +/* Build the function declaration for stackleak_track_stack() */ +static void stackleak_start_unit(void *gcc_data __unused, + void *user_data __unused) +{ + tree fntype; + + /* void stackleak_track_stack(void) */ + fntype = build_function_type_list(void_type_node, NULL_TREE); + track_function_decl = build_fn_decl(track_function, fntype); + DECL_ASSEMBLER_NAME(track_function_decl); /* for LTO */ + TREE_PUBLIC(track_function_decl) = 1; + TREE_USED(track_function_decl) = 1; + DECL_EXTERNAL(track_function_decl) = 1; + DECL_ARTIFICIAL(track_function_decl) = 1; + DECL_PRESERVE_P(track_function_decl) = 1; +} + +/* + * Pass gate function is a predicate function that gets executed before the + * corresponding pass. If the return value is 'true' the pass gets executed, + * otherwise, it is skipped. + */ +static bool stackleak_instrument_gate(void) +{ + return stackleak_gate(); +} + +#define PASS_NAME stackleak_instrument +#define PROPERTIES_REQUIRED PROP_gimple_leh | PROP_cfg +#define TODO_FLAGS_START TODO_verify_ssa | TODO_verify_flow | TODO_verify_stmts +#define TODO_FLAGS_FINISH TODO_verify_ssa | TODO_verify_stmts | TODO_dump_func \ + | TODO_update_ssa | TODO_rebuild_cgraph_edges +#include "gcc-generate-gimple-pass.h" + +static bool stackleak_cleanup_gate(void) +{ + return stackleak_gate(); +} + +#define PASS_NAME stackleak_cleanup +#define TODO_FLAGS_FINISH TODO_dump_func +#include "gcc-generate-rtl-pass.h" + +/* + * Every gcc plugin exports a plugin_init() function that is called right + * after the plugin is loaded. This function is responsible for registering + * the plugin callbacks and doing other required initialization. + */ +__visible int plugin_init(struct plugin_name_args *plugin_info, + struct plugin_gcc_version *version) +{ + const char * const plugin_name = plugin_info->base_name; + const int argc = plugin_info->argc; + const struct plugin_argument * const argv = plugin_info->argv; + int i = 0; + + /* Extra GGC root tables describing our GTY-ed data */ + static const struct ggc_root_tab gt_ggc_r_gt_stackleak[] = { + { + .base = &track_function_decl, + .nelt = 1, + .stride = sizeof(track_function_decl), + .cb = >_ggc_mx_tree_node, + .pchw = >_pch_nx_tree_node + }, + LAST_GGC_ROOT_TAB + }; + + /* + * The stackleak_instrument pass should be executed before the + * "optimized" pass, which is the control flow graph cleanup that is + * performed just before expanding gcc trees to the RTL. In former + * versions of the plugin this new pass was inserted before the + * "tree_profile" pass, which is currently called "profile". + */ + PASS_INFO(stackleak_instrument, "optimized", 1, + PASS_POS_INSERT_BEFORE); + + /* + * The stackleak_cleanup pass should be executed after the + * "reload" pass, when the stack frame size is final. + */ + PASS_INFO(stackleak_cleanup, "reload", 1, PASS_POS_INSERT_AFTER); + + if (!plugin_default_version_check(version, &gcc_version)) { + error(G_("incompatible gcc/plugin versions")); + return 1; + } + + /* Parse the plugin arguments */ + for (i = 0; i < argc; i++) { + if (!strcmp(argv[i].key, "disable")) + return 0; + + if (!strcmp(argv[i].key, "track-min-size")) { + if (!argv[i].value) { + error(G_("no value supplied for option '-fplugin-arg-%s-%s'"), + plugin_name, argv[i].key); + return 1; + } + + track_frame_size = atoi(argv[i].value); + if (track_frame_size < 0) { + error(G_("invalid option argument '-fplugin-arg-%s-%s=%s'"), + plugin_name, argv[i].key, argv[i].value); + return 1; + } + } else { + error(G_("unknown option '-fplugin-arg-%s-%s'"), + plugin_name, argv[i].key); + return 1; + } + } + + /* Give the information about the plugin */ + register_callback(plugin_name, PLUGIN_INFO, NULL, + &stackleak_plugin_info); + + /* Register to be called before processing a translation unit */ + register_callback(plugin_name, PLUGIN_START_UNIT, + &stackleak_start_unit, NULL); + + /* Register an extra GCC garbage collector (GGC) root table */ + register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, + (void *)>_ggc_r_gt_stackleak); + + /* + * Hook into the Pass Manager to register new gcc passes. + * + * The stack frame size info is available only at the last RTL pass, + * when it's too late to insert complex code like a function call. + * So we register two gcc passes to instrument every function at first + * and remove the unneeded instrumentation later. + */ + register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, + &stackleak_instrument_pass_info); + register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, + &stackleak_cleanup_pass_info); + + return 0; +} diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 67ed9f6ccdf8f0..63b609243d0378 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -68,21 +68,7 @@ PHONY += $(simple-targets) $(simple-targets): $(obj)/conf $< $(silent) --$@ $(Kconfig) -PHONY += oldnoconfig silentoldconfig savedefconfig defconfig - -# oldnoconfig is an alias of olddefconfig, because people already are dependent -# on its behavior (sets new symbols to their default value but not 'n') with the -# counter-intuitive name. -oldnoconfig: olddefconfig - @echo " WARNING: \"oldnoconfig\" target will be removed after Linux 4.19" - @echo " Please use \"olddefconfig\" instead, which is an alias." - -# We do not expect manual invokcation of "silentoldcofig" (or "syncconfig"). -silentoldconfig: syncconfig - @echo " WARNING: \"silentoldconfig\" has been renamed to \"syncconfig\"" - @echo " and is now an internal implementation detail." - @echo " What you want is probably \"oldconfig\"." - @echo " \"silentoldconfig\" will be removed after Linux 4.19" +PHONY += savedefconfig defconfig savedefconfig: $(obj)/conf $< $(silent) --$@=defconfig $(Kconfig) diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c index 7b2b37260669e3..98e0c7a34699e9 100644 --- a/scripts/kconfig/conf.c +++ b/scripts/kconfig/conf.c @@ -460,12 +460,6 @@ static struct option long_opts[] = { {"randconfig", no_argument, NULL, randconfig}, {"listnewconfig", no_argument, NULL, listnewconfig}, {"olddefconfig", no_argument, NULL, olddefconfig}, - /* - * oldnoconfig is an alias of olddefconfig, because people already - * are dependent on its behavior(sets new symbols to their default - * value but not 'n') with the counter-intuitive name. - */ - {"oldnoconfig", no_argument, NULL, olddefconfig}, {NULL, 0, NULL, 0} }; @@ -480,7 +474,6 @@ static void conf_usage(const char *progname) printf(" --syncconfig Similar to oldconfig but generates configuration in\n" " include/{generated/,config/}\n"); printf(" --olddefconfig Same as oldconfig but sets new symbols to their default value\n"); - printf(" --oldnoconfig An alias of olddefconfig\n"); printf(" --defconfig <file> New config with default defined in <file>\n"); printf(" --savedefconfig <file> Save the minimal current configuration to <file>\n"); printf(" --allnoconfig New config where all options are answered with no\n"); diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index 67d13144763145..da66e7742282a6 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -33,12 +33,15 @@ usage() { echo " -n use allnoconfig instead of alldefconfig" echo " -r list redundant entries when merging fragments" echo " -O dir to put generated output files. Consider setting \$KCONFIG_CONFIG instead." + echo + echo "Used prefix: '$CONFIG_PREFIX'. You can redefine it with \$CONFIG_ environment variable." } RUNMAKE=true ALLTARGET=alldefconfig WARNREDUN=false OUTPUT=. +CONFIG_PREFIX=${CONFIG_-CONFIG_} while true; do case $1 in @@ -99,7 +102,8 @@ if [ ! -r "$INITFILE" ]; then fi MERGE_LIST=$* -SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(CONFIG_[a-zA-Z0-9_]*\)[= ].*/\2/p" +SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)[= ].*/\2/p" + TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX) echo "Using $INITFILE as base" diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c index e09fe4d7307cd0..8963203319ea40 100644 --- a/security/apparmor/apparmorfs.c +++ b/security/apparmor/apparmorfs.c @@ -1742,7 +1742,7 @@ static int ns_rmdir_op(struct inode *dir, struct dentry *dentry) if (error) return error; - parent = aa_get_ns(dir->i_private); + parent = aa_get_ns(dir->i_private); /* rmdir calls the generic securityfs functions to remove files * from the apparmor dir. It is up to the apparmor ns locking * to avoid races. diff --git a/security/apparmor/file.c b/security/apparmor/file.c index 4285943f7260f3..d0afed9ebd0ed9 100644 --- a/security/apparmor/file.c +++ b/security/apparmor/file.c @@ -496,7 +496,7 @@ static void update_file_ctx(struct aa_file_ctx *fctx, struct aa_label *label, /* update caching of label on file_ctx */ spin_lock(&fctx->lock); old = rcu_dereference_protected(fctx->label, - spin_is_locked(&fctx->lock)); + lockdep_is_held(&fctx->lock)); l = aa_label_merge(old, label, GFP_ATOMIC); if (l) { if (l != old) { diff --git a/security/apparmor/include/cred.h b/security/apparmor/include/cred.h index e287b7d0d4bebc..265ae6641a0644 100644 --- a/security/apparmor/include/cred.h +++ b/security/apparmor/include/cred.h @@ -151,6 +151,8 @@ static inline struct aa_label *begin_current_label_crit_section(void) { struct aa_label *label = aa_current_raw_label(); + might_sleep(); + if (label_is_stale(label)) { label = aa_get_newest_label(label); if (aa_replace_current_label(label) == 0) diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h index ec7228e857a90d..7334ac966d018d 100644 --- a/security/apparmor/include/net.h +++ b/security/apparmor/include/net.h @@ -83,6 +83,13 @@ struct aa_sk_ctx { __e; \ }) +struct aa_secmark { + u8 audit; + u8 deny; + u32 secid; + char *label; +}; + extern struct aa_sfs_entry aa_sfs_entry_network[]; void audit_net_cb(struct audit_buffer *ab, void *va); @@ -103,4 +110,7 @@ int aa_sk_perm(const char *op, u32 request, struct sock *sk); int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, struct socket *sock); +int apparmor_secmark_check(struct aa_label *label, char *op, u32 request, + u32 secid, struct sock *sk); + #endif /* __AA_NET_H */ diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h index ab64c6b5db5aca..8e6707c837befa 100644 --- a/security/apparmor/include/policy.h +++ b/security/apparmor/include/policy.h @@ -155,6 +155,9 @@ struct aa_profile { struct aa_rlimit rlimits; + int secmark_count; + struct aa_secmark *secmark; + struct aa_loaddata *rawdata; unsigned char *hash; char *dirname; diff --git a/security/apparmor/include/secid.h b/security/apparmor/include/secid.h index dee6fa3b6081e1..fa2062711b63e7 100644 --- a/security/apparmor/include/secid.h +++ b/security/apparmor/include/secid.h @@ -22,6 +22,9 @@ struct aa_label; /* secid value that will not be allocated */ #define AA_SECID_INVALID 0 +/* secid value that matches any other secid */ +#define AA_SECID_WILDCARD 1 + struct aa_label *aa_secid_to_label(u32 secid); int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen); int apparmor_secctx_to_secid(const char *secdata, u32 seclen, u32 *secid); diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 974affe505314b..76491e7f4177fa 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -90,10 +90,12 @@ const char *aa_splitn_fqname(const char *fqname, size_t n, const char **ns_name, const char *end = fqname + n; const char *name = skipn_spaces(fqname, n); - if (!name) - return NULL; *ns_name = NULL; *ns_len = 0; + + if (!name) + return NULL; + if (name[0] == ':') { char *split = strnchr(&name[1], end - &name[1], ':'); *ns_name = skipn_spaces(&name[1], end - &name[1]); diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index aa35939443c477..42446a216f3bcf 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -23,6 +23,8 @@ #include <linux/sysctl.h> #include <linux/audit.h> #include <linux/user_namespace.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> #include <net/sock.h> #include "include/apparmor.h" @@ -114,13 +116,13 @@ static int apparmor_ptrace_access_check(struct task_struct *child, struct aa_label *tracer, *tracee; int error; - tracer = begin_current_label_crit_section(); + tracer = __begin_current_label_crit_section(); tracee = aa_get_task_label(child); error = aa_may_ptrace(tracer, tracee, (mode & PTRACE_MODE_READ) ? AA_PTRACE_READ : AA_PTRACE_TRACE); aa_put_label(tracee); - end_current_label_crit_section(tracer); + __end_current_label_crit_section(tracer); return error; } @@ -130,11 +132,11 @@ static int apparmor_ptrace_traceme(struct task_struct *parent) struct aa_label *tracer, *tracee; int error; - tracee = begin_current_label_crit_section(); + tracee = __begin_current_label_crit_section(); tracer = aa_get_task_label(parent); error = aa_may_ptrace(tracer, tracee, AA_PTRACE_TRACE); aa_put_label(tracer); - end_current_label_crit_section(tracee); + __end_current_label_crit_section(tracee); return error; } @@ -1020,6 +1022,7 @@ static int apparmor_socket_shutdown(struct socket *sock, int how) return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock); } +#ifdef CONFIG_NETWORK_SECMARK /** * apparmor_socket_sock_recv_skb - check perms before associating skb to sk * @@ -1030,8 +1033,15 @@ static int apparmor_socket_shutdown(struct socket *sock, int how) */ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) { - return 0; + struct aa_sk_ctx *ctx = SK_CTX(sk); + + if (!skb->secmark) + return 0; + + return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE, + skb->secmark, sk); } +#endif static struct aa_label *sk_peer_label(struct sock *sk) @@ -1126,6 +1136,20 @@ static void apparmor_sock_graft(struct sock *sk, struct socket *parent) ctx->label = aa_get_current_label(); } +#ifdef CONFIG_NETWORK_SECMARK +static int apparmor_inet_conn_request(struct sock *sk, struct sk_buff *skb, + struct request_sock *req) +{ + struct aa_sk_ctx *ctx = SK_CTX(sk); + + if (!skb->secmark) + return 0; + + return apparmor_secmark_check(ctx->label, OP_CONNECT, AA_MAY_CONNECT, + skb->secmark, sk); +} +#endif + static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(ptrace_access_check, apparmor_ptrace_access_check), LSM_HOOK_INIT(ptrace_traceme, apparmor_ptrace_traceme), @@ -1177,12 +1201,17 @@ static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt), LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt), LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown), +#ifdef CONFIG_NETWORK_SECMARK LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb), +#endif LSM_HOOK_INIT(socket_getpeersec_stream, apparmor_socket_getpeersec_stream), LSM_HOOK_INIT(socket_getpeersec_dgram, apparmor_socket_getpeersec_dgram), LSM_HOOK_INIT(sock_graft, apparmor_sock_graft), +#ifdef CONFIG_NETWORK_SECMARK + LSM_HOOK_INIT(inet_conn_request, apparmor_inet_conn_request), +#endif LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank), LSM_HOOK_INIT(cred_free, apparmor_cred_free), @@ -1538,6 +1567,97 @@ static inline int apparmor_init_sysctl(void) } #endif /* CONFIG_SYSCTL */ +#if defined(CONFIG_NETFILTER) && defined(CONFIG_NETWORK_SECMARK) +static unsigned int apparmor_ip_postroute(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct aa_sk_ctx *ctx; + struct sock *sk; + + if (!skb->secmark) + return NF_ACCEPT; + + sk = skb_to_full_sk(skb); + if (sk == NULL) + return NF_ACCEPT; + + ctx = SK_CTX(sk); + if (!apparmor_secmark_check(ctx->label, OP_SENDMSG, AA_MAY_SEND, + skb->secmark, sk)) + return NF_ACCEPT; + + return NF_DROP_ERR(-ECONNREFUSED); + +} + +static unsigned int apparmor_ipv4_postroute(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return apparmor_ip_postroute(priv, skb, state); +} + +static unsigned int apparmor_ipv6_postroute(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + return apparmor_ip_postroute(priv, skb, state); +} + +static const struct nf_hook_ops apparmor_nf_ops[] = { + { + .hook = apparmor_ipv4_postroute, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_SELINUX_FIRST, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .hook = apparmor_ipv6_postroute, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP6_PRI_SELINUX_FIRST, + }, +#endif +}; + +static int __net_init apparmor_nf_register(struct net *net) +{ + int ret; + + ret = nf_register_net_hooks(net, apparmor_nf_ops, + ARRAY_SIZE(apparmor_nf_ops)); + return ret; +} + +static void __net_exit apparmor_nf_unregister(struct net *net) +{ + nf_unregister_net_hooks(net, apparmor_nf_ops, + ARRAY_SIZE(apparmor_nf_ops)); +} + +static struct pernet_operations apparmor_net_ops = { + .init = apparmor_nf_register, + .exit = apparmor_nf_unregister, +}; + +static int __init apparmor_nf_ip_init(void) +{ + int err; + + if (!apparmor_enabled) + return 0; + + err = register_pernet_subsys(&apparmor_net_ops); + if (err) + panic("Apparmor: register_pernet_subsys: error %d\n", err); + + return 0; +} +__initcall(apparmor_nf_ip_init); +#endif + static int __init apparmor_init(void) { int error; diff --git a/security/apparmor/net.c b/security/apparmor/net.c index bb24cfa0a164cb..c07fde444792d8 100644 --- a/security/apparmor/net.c +++ b/security/apparmor/net.c @@ -18,6 +18,7 @@ #include "include/label.h" #include "include/net.h" #include "include/policy.h" +#include "include/secid.h" #include "net_names.h" @@ -146,17 +147,20 @@ int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family, static int aa_label_sk_perm(struct aa_label *label, const char *op, u32 request, struct sock *sk) { - struct aa_profile *profile; - DEFINE_AUDIT_SK(sa, op, sk); + int error = 0; AA_BUG(!label); AA_BUG(!sk); - if (unconfined(label)) - return 0; + if (!unconfined(label)) { + struct aa_profile *profile; + DEFINE_AUDIT_SK(sa, op, sk); - return fn_for_each_confined(label, profile, - aa_profile_af_sk_perm(profile, &sa, request, sk)); + error = fn_for_each_confined(label, profile, + aa_profile_af_sk_perm(profile, &sa, request, sk)); + } + + return error; } int aa_sk_perm(const char *op, u32 request, struct sock *sk) @@ -185,3 +189,70 @@ int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request, return aa_label_sk_perm(label, op, request, sock->sk); } + +#ifdef CONFIG_NETWORK_SECMARK +static int apparmor_secmark_init(struct aa_secmark *secmark) +{ + struct aa_label *label; + + if (secmark->label[0] == '*') { + secmark->secid = AA_SECID_WILDCARD; + return 0; + } + + label = aa_label_strn_parse(&root_ns->unconfined->label, + secmark->label, strlen(secmark->label), + GFP_ATOMIC, false, false); + + if (IS_ERR(label)) + return PTR_ERR(label); + + secmark->secid = label->secid; + + return 0; +} + +static int aa_secmark_perm(struct aa_profile *profile, u32 request, u32 secid, + struct common_audit_data *sa, struct sock *sk) +{ + int i, ret; + struct aa_perms perms = { }; + + if (profile->secmark_count == 0) + return 0; + + for (i = 0; i < profile->secmark_count; i++) { + if (!profile->secmark[i].secid) { + ret = apparmor_secmark_init(&profile->secmark[i]); + if (ret) + return ret; + } + + if (profile->secmark[i].secid == secid || + profile->secmark[i].secid == AA_SECID_WILDCARD) { + if (profile->secmark[i].deny) + perms.deny = ALL_PERMS_MASK; + else + perms.allow = ALL_PERMS_MASK; + + if (profile->secmark[i].audit) + perms.audit = ALL_PERMS_MASK; + } + } + + aa_apply_modes_to_perms(profile, &perms); + + return aa_check_perms(profile, &perms, request, sa, audit_net_cb); +} + +int apparmor_secmark_check(struct aa_label *label, char *op, u32 request, + u32 secid, struct sock *sk) +{ + struct aa_profile *profile; + DEFINE_AUDIT_SK(sa, op, sk); + + return fn_for_each_confined(label, profile, + aa_secmark_perm(profile, request, secid, + &sa, sk)); +} +#endif diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c index 1590e2de4e841c..df9c5890a87891 100644 --- a/security/apparmor/policy.c +++ b/security/apparmor/policy.c @@ -231,6 +231,9 @@ void aa_free_profile(struct aa_profile *profile) for (i = 0; i < profile->xattr_count; i++) kzfree(profile->xattrs[i]); kzfree(profile->xattrs); + for (i = 0; i < profile->secmark_count; i++) + kzfree(profile->secmark[i].label); + kzfree(profile->secmark); kzfree(profile->dirname); aa_put_dfa(profile->xmatch); aa_put_dfa(profile->policy.dfa); diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c index 21cb384d712a28..379682e2a8d5db 100644 --- a/security/apparmor/policy_unpack.c +++ b/security/apparmor/policy_unpack.c @@ -292,6 +292,19 @@ fail: return 0; } +static bool unpack_u8(struct aa_ext *e, u8 *data, const char *name) +{ + if (unpack_nameX(e, AA_U8, name)) { + if (!inbounds(e, sizeof(u8))) + return 0; + if (data) + *data = get_unaligned((u8 *)e->pos); + e->pos += sizeof(u8); + return 1; + } + return 0; +} + static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name) { if (unpack_nameX(e, AA_U32, name)) { @@ -529,6 +542,49 @@ fail: return 0; } +static bool unpack_secmark(struct aa_ext *e, struct aa_profile *profile) +{ + void *pos = e->pos; + int i, size; + + if (unpack_nameX(e, AA_STRUCT, "secmark")) { + size = unpack_array(e, NULL); + + profile->secmark = kcalloc(size, sizeof(struct aa_secmark), + GFP_KERNEL); + if (!profile->secmark) + goto fail; + + profile->secmark_count = size; + + for (i = 0; i < size; i++) { + if (!unpack_u8(e, &profile->secmark[i].audit, NULL)) + goto fail; + if (!unpack_u8(e, &profile->secmark[i].deny, NULL)) + goto fail; + if (!unpack_strdup(e, &profile->secmark[i].label, NULL)) + goto fail; + } + if (!unpack_nameX(e, AA_ARRAYEND, NULL)) + goto fail; + if (!unpack_nameX(e, AA_STRUCTEND, NULL)) + goto fail; + } + + return 1; + +fail: + if (profile->secmark) { + for (i = 0; i < size; i++) + kfree(profile->secmark[i].label); + kfree(profile->secmark); + profile->secmark_count = 0; + } + + e->pos = pos; + return 0; +} + static bool unpack_rlimits(struct aa_ext *e, struct aa_profile *profile) { void *pos = e->pos; @@ -727,6 +783,11 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name) goto fail; } + if (!unpack_secmark(e, profile)) { + info = "failed to unpack profile secmark rules"; + goto fail; + } + if (unpack_nameX(e, AA_STRUCT, "policydb")) { /* generic policy dfa - optional and may be NULL */ info = "failed to unpack policydb"; diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c index 4ccec1bcf6f54f..05373d9a3d6af1 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -32,8 +32,7 @@ * secids - do not pin labels with a refcount. They rely on the label * properly updating/freeing them */ - -#define AA_FIRST_SECID 1 +#define AA_FIRST_SECID 2 static DEFINE_IDR(aa_secids); static DEFINE_SPINLOCK(secid_lock); diff --git a/security/keys/Makefile b/security/keys/Makefile index ef1581b337a3dc..9cef54064f6084 100644 --- a/security/keys/Makefile +++ b/security/keys/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_SYSCTL) += sysctl.o obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o obj-$(CONFIG_KEY_DH_OPERATIONS) += dh.o +obj-$(CONFIG_ASYMMETRIC_KEY_TYPE) += keyctl_pkey.o # # Key types diff --git a/security/keys/compat.c b/security/keys/compat.c index e87c89c0177c15..9482df601dc33d 100644 --- a/security/keys/compat.c +++ b/security/keys/compat.c @@ -141,6 +141,24 @@ COMPAT_SYSCALL_DEFINE5(keyctl, u32, option, return keyctl_restrict_keyring(arg2, compat_ptr(arg3), compat_ptr(arg4)); + case KEYCTL_PKEY_QUERY: + if (arg3 != 0) + return -EINVAL; + return keyctl_pkey_query(arg2, + compat_ptr(arg4), + compat_ptr(arg5)); + + case KEYCTL_PKEY_ENCRYPT: + case KEYCTL_PKEY_DECRYPT: + case KEYCTL_PKEY_SIGN: + return keyctl_pkey_e_d_s(option, + compat_ptr(arg2), compat_ptr(arg3), + compat_ptr(arg4), compat_ptr(arg5)); + + case KEYCTL_PKEY_VERIFY: + return keyctl_pkey_verify(compat_ptr(arg2), compat_ptr(arg3), + compat_ptr(arg4), compat_ptr(arg5)); + default: return -EOPNOTSUPP; } diff --git a/security/keys/internal.h b/security/keys/internal.h index 9f8208dc0e5582..74cb0ff42fedbc 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -298,6 +298,45 @@ static inline long compat_keyctl_dh_compute( #endif #endif +#ifdef CONFIG_ASYMMETRIC_KEY_TYPE +extern long keyctl_pkey_query(key_serial_t, + const char __user *, + struct keyctl_pkey_query __user *); + +extern long keyctl_pkey_verify(const struct keyctl_pkey_params __user *, + const char __user *, + const void __user *, const void __user *); + +extern long keyctl_pkey_e_d_s(int, + const struct keyctl_pkey_params __user *, + const char __user *, + const void __user *, void __user *); +#else +static inline long keyctl_pkey_query(key_serial_t id, + const char __user *_info, + struct keyctl_pkey_query __user *_res) +{ + return -EOPNOTSUPP; +} + +static inline long keyctl_pkey_verify(const struct keyctl_pkey_params __user *params, + const char __user *_info, + const void __user *_in, + const void __user *_in2) +{ + return -EOPNOTSUPP; +} + +static inline long keyctl_pkey_e_d_s(int op, + const struct keyctl_pkey_params __user *params, + const char __user *_info, + const void __user *_in, + void __user *_out) +{ + return -EOPNOTSUPP; +} +#endif + /* * Debugging key validation */ diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index 1ffe60bb2845f9..18619690ce77a9 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -1747,6 +1747,30 @@ SYSCALL_DEFINE5(keyctl, int, option, unsigned long, arg2, unsigned long, arg3, (const char __user *) arg3, (const char __user *) arg4); + case KEYCTL_PKEY_QUERY: + if (arg3 != 0) + return -EINVAL; + return keyctl_pkey_query((key_serial_t)arg2, + (const char __user *)arg4, + (struct keyctl_pkey_query *)arg5); + + case KEYCTL_PKEY_ENCRYPT: + case KEYCTL_PKEY_DECRYPT: + case KEYCTL_PKEY_SIGN: + return keyctl_pkey_e_d_s( + option, + (const struct keyctl_pkey_params __user *)arg2, + (const char __user *)arg3, + (const void __user *)arg4, + (void __user *)arg5); + + case KEYCTL_PKEY_VERIFY: + return keyctl_pkey_verify( + (const struct keyctl_pkey_params __user *)arg2, + (const char __user *)arg3, + (const void __user *)arg4, + (const void __user *)arg5); + default: return -EOPNOTSUPP; } diff --git a/security/keys/keyctl_pkey.c b/security/keys/keyctl_pkey.c new file mode 100644 index 00000000000000..783978842f13a7 --- /dev/null +++ b/security/keys/keyctl_pkey.c @@ -0,0 +1,323 @@ +/* Public-key operation keyctls + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/slab.h> +#include <linux/err.h> +#include <linux/key.h> +#include <linux/keyctl.h> +#include <linux/parser.h> +#include <linux/uaccess.h> +#include <keys/user-type.h> +#include "internal.h" + +static void keyctl_pkey_params_free(struct kernel_pkey_params *params) +{ + kfree(params->info); + key_put(params->key); +} + +enum { + Opt_err = -1, + Opt_enc, /* "enc=<encoding>" eg. "enc=oaep" */ + Opt_hash, /* "hash=<digest-name>" eg. "hash=sha1" */ +}; + +static const match_table_t param_keys = { + { Opt_enc, "enc=%s" }, + { Opt_hash, "hash=%s" }, + { Opt_err, NULL } +}; + +/* + * Parse the information string which consists of key=val pairs. + */ +static int keyctl_pkey_params_parse(struct kernel_pkey_params *params) +{ + unsigned long token_mask = 0; + substring_t args[MAX_OPT_ARGS]; + char *c = params->info, *p, *q; + int token; + + while ((p = strsep(&c, " \t"))) { + if (*p == '\0' || *p == ' ' || *p == '\t') + continue; + token = match_token(p, param_keys, args); + if (__test_and_set_bit(token, &token_mask)) + return -EINVAL; + q = args[0].from; + if (!q[0]) + return -EINVAL; + + switch (token) { + case Opt_enc: + params->encoding = q; + break; + + case Opt_hash: + params->hash_algo = q; + break; + + default: + return -EINVAL; + } + } + + return 0; +} + +/* + * Interpret parameters. Callers must always call the free function + * on params, even if an error is returned. + */ +static int keyctl_pkey_params_get(key_serial_t id, + const char __user *_info, + struct kernel_pkey_params *params) +{ + key_ref_t key_ref; + void *p; + int ret; + + memset(params, 0, sizeof(*params)); + params->encoding = "raw"; + + p = strndup_user(_info, PAGE_SIZE); + if (IS_ERR(p)) + return PTR_ERR(p); + params->info = p; + + ret = keyctl_pkey_params_parse(params); + if (ret < 0) + return ret; + + key_ref = lookup_user_key(id, 0, KEY_NEED_SEARCH); + if (IS_ERR(key_ref)) + return PTR_ERR(key_ref); + params->key = key_ref_to_ptr(key_ref); + + if (!params->key->type->asym_query) + return -EOPNOTSUPP; + + return 0; +} + +/* + * Get parameters from userspace. Callers must always call the free function + * on params, even if an error is returned. + */ +static int keyctl_pkey_params_get_2(const struct keyctl_pkey_params __user *_params, + const char __user *_info, + int op, + struct kernel_pkey_params *params) +{ + struct keyctl_pkey_params uparams; + struct kernel_pkey_query info; + int ret; + + memset(params, 0, sizeof(*params)); + params->encoding = "raw"; + + if (copy_from_user(&uparams, _params, sizeof(uparams)) != 0) + return -EFAULT; + + ret = keyctl_pkey_params_get(uparams.key_id, _info, params); + if (ret < 0) + return ret; + + ret = params->key->type->asym_query(params, &info); + if (ret < 0) + return ret; + + switch (op) { + case KEYCTL_PKEY_ENCRYPT: + case KEYCTL_PKEY_DECRYPT: + if (uparams.in_len > info.max_enc_size || + uparams.out_len > info.max_dec_size) + return -EINVAL; + break; + case KEYCTL_PKEY_SIGN: + case KEYCTL_PKEY_VERIFY: + if (uparams.in_len > info.max_sig_size || + uparams.out_len > info.max_data_size) + return -EINVAL; + break; + default: + BUG(); + } + + params->in_len = uparams.in_len; + params->out_len = uparams.out_len; + return 0; +} + +/* + * Query information about an asymmetric key. + */ +long keyctl_pkey_query(key_serial_t id, + const char __user *_info, + struct keyctl_pkey_query __user *_res) +{ + struct kernel_pkey_params params; + struct kernel_pkey_query res; + long ret; + + memset(¶ms, 0, sizeof(params)); + + ret = keyctl_pkey_params_get(id, _info, ¶ms); + if (ret < 0) + goto error; + + ret = params.key->type->asym_query(¶ms, &res); + if (ret < 0) + goto error; + + ret = -EFAULT; + if (copy_to_user(_res, &res, sizeof(res)) == 0 && + clear_user(_res->__spare, sizeof(_res->__spare)) == 0) + ret = 0; + +error: + keyctl_pkey_params_free(¶ms); + return ret; +} + +/* + * Encrypt/decrypt/sign + * + * Encrypt data, decrypt data or sign data using a public key. + * + * _info is a string of supplementary information in key=val format. For + * instance, it might contain: + * + * "enc=pkcs1 hash=sha256" + * + * where enc= specifies the encoding and hash= selects the OID to go in that + * particular encoding if required. If enc= isn't supplied, it's assumed that + * the caller is supplying raw values. + * + * If successful, the amount of data written into the output buffer is + * returned. + */ +long keyctl_pkey_e_d_s(int op, + const struct keyctl_pkey_params __user *_params, + const char __user *_info, + const void __user *_in, + void __user *_out) +{ + struct kernel_pkey_params params; + void *in, *out; + long ret; + + ret = keyctl_pkey_params_get_2(_params, _info, op, ¶ms); + if (ret < 0) + goto error_params; + + ret = -EOPNOTSUPP; + if (!params.key->type->asym_eds_op) + goto error_params; + + switch (op) { + case KEYCTL_PKEY_ENCRYPT: + params.op = kernel_pkey_encrypt; + break; + case KEYCTL_PKEY_DECRYPT: + params.op = kernel_pkey_decrypt; + break; + case KEYCTL_PKEY_SIGN: + params.op = kernel_pkey_sign; + break; + default: + BUG(); + } + + in = memdup_user(_in, params.in_len); + if (IS_ERR(in)) { + ret = PTR_ERR(in); + goto error_params; + } + + ret = -ENOMEM; + out = kmalloc(params.out_len, GFP_KERNEL); + if (!out) + goto error_in; + + ret = params.key->type->asym_eds_op(¶ms, in, out); + if (ret < 0) + goto error_out; + + if (copy_to_user(_out, out, ret) != 0) + ret = -EFAULT; + +error_out: + kfree(out); +error_in: + kfree(in); +error_params: + keyctl_pkey_params_free(¶ms); + return ret; +} + +/* + * Verify a signature. + * + * Verify a public key signature using the given key, or if not given, search + * for a matching key. + * + * _info is a string of supplementary information in key=val format. For + * instance, it might contain: + * + * "enc=pkcs1 hash=sha256" + * + * where enc= specifies the signature blob encoding and hash= selects the OID + * to go in that particular encoding. If enc= isn't supplied, it's assumed + * that the caller is supplying raw values. + * + * If successful, 0 is returned. + */ +long keyctl_pkey_verify(const struct keyctl_pkey_params __user *_params, + const char __user *_info, + const void __user *_in, + const void __user *_in2) +{ + struct kernel_pkey_params params; + void *in, *in2; + long ret; + + ret = keyctl_pkey_params_get_2(_params, _info, KEYCTL_PKEY_VERIFY, + ¶ms); + if (ret < 0) + goto error_params; + + ret = -EOPNOTSUPP; + if (!params.key->type->asym_verify_signature) + goto error_params; + + in = memdup_user(_in, params.in_len); + if (IS_ERR(in)) { + ret = PTR_ERR(in); + goto error_params; + } + + in2 = memdup_user(_in2, params.in2_len); + if (IS_ERR(in2)) { + ret = PTR_ERR(in2); + goto error_in; + } + + params.op = kernel_pkey_verify; + ret = params.key->type->asym_verify_signature(¶ms, in, in2); + + kfree(in2); +error_in: + kfree(in); +error_params: + keyctl_pkey_params_free(¶ms); + return ret; +} diff --git a/security/keys/trusted.c b/security/keys/trusted.c index b69d3b1777c25d..ff6789365a12fb 100644 --- a/security/keys/trusted.c +++ b/security/keys/trusted.c @@ -30,7 +30,7 @@ #include <linux/tpm.h> #include <linux/tpm_command.h> -#include "trusted.h" +#include <keys/trusted.h> static const char hmac_alg[] = "hmac(sha1)"; static const char hash_alg[] = "sha1"; @@ -121,7 +121,7 @@ out: /* * calculate authorization info fields to send to TPM */ -static int TSS_authhmac(unsigned char *digest, const unsigned char *key, +int TSS_authhmac(unsigned char *digest, const unsigned char *key, unsigned int keylen, unsigned char *h1, unsigned char *h2, unsigned char h3, ...) { @@ -168,11 +168,12 @@ out: kzfree(sdesc); return ret; } +EXPORT_SYMBOL_GPL(TSS_authhmac); /* * verify the AUTH1_COMMAND (Seal) result from TPM */ -static int TSS_checkhmac1(unsigned char *buffer, +int TSS_checkhmac1(unsigned char *buffer, const uint32_t command, const unsigned char *ononce, const unsigned char *key, @@ -249,6 +250,7 @@ out: kzfree(sdesc); return ret; } +EXPORT_SYMBOL_GPL(TSS_checkhmac1); /* * verify the AUTH2_COMMAND (unseal) result from TPM @@ -355,7 +357,7 @@ out: * For key specific tpm requests, we will generate and send our * own TPM command packets using the drivers send function. */ -static int trusted_tpm_send(unsigned char *cmd, size_t buflen) +int trusted_tpm_send(unsigned char *cmd, size_t buflen) { int rc; @@ -367,6 +369,7 @@ static int trusted_tpm_send(unsigned char *cmd, size_t buflen) rc = -EPERM; return rc; } +EXPORT_SYMBOL_GPL(trusted_tpm_send); /* * Lock a trusted key, by extending a selected PCR. @@ -425,7 +428,7 @@ static int osap(struct tpm_buf *tb, struct osapsess *s, /* * Create an object independent authorisation protocol (oiap) session */ -static int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) +int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) { int ret; @@ -442,6 +445,7 @@ static int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce) TPM_NONCE_SIZE); return 0; } +EXPORT_SYMBOL_GPL(oiap); struct tpm_digests { unsigned char encauth[SHA1_DIGEST_SIZE]; diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index fcd965f1d69e82..9be76c808fccf0 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -146,53 +146,22 @@ static int apply_constraint_to_size(struct snd_pcm_hw_params *params, struct snd_interval *s = hw_param_interval(params, rule->var); const struct snd_interval *r = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_RATE); - struct snd_interval t = { - .min = s->min, .max = s->max, .integer = 1, - }; + struct snd_interval t = {0}; + unsigned int step = 0; int i; for (i = 0; i < CIP_SFC_COUNT; ++i) { - unsigned int rate = amdtp_rate_table[i]; - unsigned int step = amdtp_syt_intervals[i]; - - if (!snd_interval_test(r, rate)) - continue; - - t.min = roundup(t.min, step); - t.max = rounddown(t.max, step); + if (snd_interval_test(r, amdtp_rate_table[i])) + step = max(step, amdtp_syt_intervals[i]); } - if (snd_interval_checkempty(&t)) - return -EINVAL; + t.min = roundup(s->min, step); + t.max = rounddown(s->max, step); + t.integer = 1; return snd_interval_refine(s, &t); } -static int apply_constraint_to_rate(struct snd_pcm_hw_params *params, - struct snd_pcm_hw_rule *rule) -{ - struct snd_interval *r = - hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE); - const struct snd_interval *s = hw_param_interval_c(params, rule->deps[0]); - struct snd_interval t = { - .min = UINT_MAX, .max = 0, .integer = 1, - }; - int i; - - for (i = 0; i < CIP_SFC_COUNT; ++i) { - unsigned int step = amdtp_syt_intervals[i]; - unsigned int rate = amdtp_rate_table[i]; - - if (s->min % step || s->max % step) - continue; - - t.min = min(t.min, rate); - t.max = max(t.max, rate); - } - - return snd_interval_refine(r, &t); -} - /** * amdtp_stream_add_pcm_hw_constraints - add hw constraints for PCM substream * @s: the AMDTP stream, which must be initialized. @@ -250,24 +219,16 @@ int amdtp_stream_add_pcm_hw_constraints(struct amdtp_stream *s, */ err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, apply_constraint_to_size, NULL, + SNDRV_PCM_HW_PARAM_PERIOD_SIZE, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) goto end; - err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, - apply_constraint_to_rate, NULL, - SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); - if (err < 0) - goto end; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, apply_constraint_to_size, NULL, + SNDRV_PCM_HW_PARAM_BUFFER_SIZE, SNDRV_PCM_HW_PARAM_RATE, -1); if (err < 0) goto end; - err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, - apply_constraint_to_rate, NULL, - SNDRV_PCM_HW_PARAM_BUFFER_SIZE, -1); - if (err < 0) - goto end; end: return err; } diff --git a/sound/firewire/dice/dice.c b/sound/firewire/dice/dice.c index 0f6dbcffe711d6..ed50b222d36ea0 100644 --- a/sound/firewire/dice/dice.c +++ b/sound/firewire/dice/dice.c @@ -240,8 +240,8 @@ static void dice_remove(struct fw_unit *unit) cancel_delayed_work_sync(&dice->dwork); if (dice->registered) { - /* No need to wait for releasing card object in this context. */ - snd_card_free_when_closed(dice->card); + // Block till all of ALSA character devices are released. + snd_card_free(dice->card); } mutex_destroy(&dice->mutex); diff --git a/sound/pci/ca0106/ca0106.h b/sound/pci/ca0106/ca0106.h index 04402c14cb2392..9847b669cf3cf0 100644 --- a/sound/pci/ca0106/ca0106.h +++ b/sound/pci/ca0106/ca0106.h @@ -582,7 +582,7 @@ #define SPI_PL_BIT_R_R (2<<7) /* right channel = right */ #define SPI_PL_BIT_R_C (3<<7) /* right channel = (L+R)/2 */ #define SPI_IZD_REG 2 -#define SPI_IZD_BIT (1<<4) /* infinite zero detect */ +#define SPI_IZD_BIT (0<<4) /* infinite zero detect */ #define SPI_FMT_REG 3 #define SPI_FMT_BIT_RJ (0<<0) /* right justified mode */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index b607be7236d3e5..d6e62e90e8d44d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2084,19 +2084,19 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog, prog->expected_attach_type = type; } -#define BPF_PROG_SEC_IMPL(string, ptype, eatype, atype) \ - { string, sizeof(string) - 1, ptype, eatype, atype } +#define BPF_PROG_SEC_IMPL(string, ptype, eatype, is_attachable, atype) \ + { string, sizeof(string) - 1, ptype, eatype, is_attachable, atype } /* Programs that can NOT be attached. */ -#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, -EINVAL) +#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0) /* Programs that can be attached. */ #define BPF_APROG_SEC(string, ptype, atype) \ - BPF_PROG_SEC_IMPL(string, ptype, 0, atype) + BPF_PROG_SEC_IMPL(string, ptype, 0, 1, atype) /* Programs that must specify expected attach type at load time. */ #define BPF_EAPROG_SEC(string, ptype, eatype) \ - BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype) + BPF_PROG_SEC_IMPL(string, ptype, eatype, 1, eatype) /* Programs that can be attached but attach type can't be identified by section * name. Kept for backward compatibility. @@ -2108,6 +2108,7 @@ static const struct { size_t len; enum bpf_prog_type prog_type; enum bpf_attach_type expected_attach_type; + int is_attachable; enum bpf_attach_type attach_type; } section_names[] = { BPF_PROG_SEC("socket", BPF_PROG_TYPE_SOCKET_FILTER), @@ -2198,7 +2199,7 @@ int libbpf_attach_type_by_name(const char *name, for (i = 0; i < ARRAY_SIZE(section_names); i++) { if (strncmp(name, section_names[i].sec, section_names[i].len)) continue; - if (section_names[i].attach_type == -EINVAL) + if (!section_names[i].is_attachable) return -EINVAL; *attach_type = section_names[i].attach_type; return 0; diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c index d3273b5b3173e1..ae8180b11d5fe6 100644 --- a/tools/testing/selftests/bpf/flow_dissector_load.c +++ b/tools/testing/selftests/bpf/flow_dissector_load.c @@ -11,6 +11,8 @@ #include <bpf/bpf.h> #include <bpf/libbpf.h> +#include "bpf_rlimit.h" + const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector"; const char *cfg_map_name = "jmp_table"; bool cfg_attach = true; diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh index 42544a969abc63..a9bc6f82abc163 100755 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh +++ b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh @@ -10,7 +10,7 @@ wait_for_ip() echo -n "Wait for testing link-local IP to become available " for _i in $(seq ${MAX_PING_TRIES}); do echo -n "." - if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then + if $PING6 -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then echo " OK" return fi @@ -58,5 +58,6 @@ BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o" BPF_PROG_SECTION="cgroup_id_logger" BPF_PROG_ID=0 PROG="${DIR}/test_skb_cgroup_id_user" +type ping6 >/dev/null 2>&1 && PING6="ping6" || PING6="ping -6" main diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh index 9832a875a82897..3b9fdb8094aa28 100755 --- a/tools/testing/selftests/bpf/test_sock_addr.sh +++ b/tools/testing/selftests/bpf/test_sock_addr.sh @@ -4,7 +4,8 @@ set -eu ping_once() { - ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1 + type ping${1} >/dev/null 2>&1 && PING="ping${1}" || PING="ping -${1}" + $PING -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1 } wait_for_ip() diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 36f3d3009d1a07..6f61df62f690c6 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -76,7 +76,7 @@ struct bpf_test { int fixup_percpu_cgroup_storage[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; - uint32_t retval; + uint32_t retval, retval_unpriv; enum { UNDEF, ACCEPT, @@ -3084,6 +3084,8 @@ static struct bpf_test tests[] = { .fixup_prog1 = { 2 }, .result = ACCEPT, .retval = 42, + /* Verifier rewrite for unpriv skips tail call here. */ + .retval_unpriv = 2, }, { "stack pointer arithmetic", @@ -6455,6 +6457,256 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map access: known scalar += value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: value_ptr += known scalar", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: unknown scalar += value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: value_ptr += unknown scalar", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: value_ptr += value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R0 pointer += pointer prohibited", + }, + { + "map access: known scalar -= value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R1 tried to subtract pointer from scalar", + }, + { + "map access: value_ptr -= known scalar", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R0 min value is outside of the array range", + }, + { + "map access: value_ptr -= known scalar, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_IMM(BPF_REG_1, 6), + BPF_MOV64_IMM(BPF_REG_2, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: unknown scalar -= value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R1 tried to subtract pointer from scalar", + }, + { + "map access: value_ptr -= unknown scalar", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R0 min value is negative", + }, + { + "map access: value_ptr -= unknown scalar, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_IMM(BPF_OR, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: value_ptr -= value_ptr", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R0 invalid mem access 'inv'", + .errstr_unpriv = "R0 pointer -= pointer prohibited", + }, + { "map lookup helper access to map", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -13899,6 +14151,33 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_map_type prog_type, } } +static int set_admin(bool admin) +{ + cap_t caps; + const cap_value_t cap_val = CAP_SYS_ADMIN; + int ret = -1; + + caps = cap_get_proc(); + if (!caps) { + perror("cap_get_proc"); + return -1; + } + if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val, + admin ? CAP_SET : CAP_CLEAR)) { + perror("cap_set_flag"); + goto out; + } + if (cap_set_proc(caps)) { + perror("cap_set_proc"); + goto out; + } + ret = 0; +out: + if (cap_free(caps)) + perror("cap_free"); + return ret; +} + static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { @@ -13907,6 +14186,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, struct bpf_insn *prog = test->insns; int map_fds[MAX_NR_MAPS]; const char *expected_err; + uint32_t expected_val; uint32_t retval; int i, err; @@ -13926,6 +14206,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, test->result_unpriv : test->result; expected_err = unpriv && test->errstr_unpriv ? test->errstr_unpriv : test->errstr; + expected_val = unpriv && test->retval_unpriv ? + test->retval_unpriv : test->retval; reject_from_alignment = fd_prog < 0 && (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) && @@ -13959,16 +14241,20 @@ static void do_test_single(struct bpf_test *test, bool unpriv, __u8 tmp[TEST_DATA_LEN << 2]; __u32 size_tmp = sizeof(tmp); + if (unpriv) + set_admin(true); err = bpf_prog_test_run(fd_prog, 1, test->data, sizeof(test->data), tmp, &size_tmp, &retval, NULL); + if (unpriv) + set_admin(false); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); goto fail_log; } - if (!err && retval != test->retval && - test->retval != POINTER_VALUE) { - printf("FAIL retval %d != %d\n", retval, test->retval); + if (!err && retval != expected_val && + expected_val != POINTER_VALUE) { + printf("FAIL retval %d != %d\n", retval, expected_val); goto fail_log; } } @@ -14011,33 +14297,6 @@ static bool is_admin(void) return (sysadmin == CAP_SET); } -static int set_admin(bool admin) -{ - cap_t caps; - const cap_value_t cap_val = CAP_SYS_ADMIN; - int ret = -1; - - caps = cap_get_proc(); - if (!caps) { - perror("cap_get_proc"); - return -1; - } - if (cap_set_flag(caps, CAP_EFFECTIVE, 1, &cap_val, - admin ? CAP_SET : CAP_CLEAR)) { - perror("cap_set_flag"); - goto out; - } - if (cap_set_proc(caps)) { - perror("cap_set_proc"); - goto out; - } - ret = 0; -out: - if (cap_free(caps)) - perror("cap_free"); - return ret; -} - static void get_unpriv_disabled() { char buf[2]; diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh index 0150bb2741eb1a..117f6f35d72fac 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_mc_aware.sh @@ -25,24 +25,24 @@ # Thus we set MTU to 10K on all involved interfaces. Then both unicast and # multicast traffic uses 8K frames. # -# +-----------------------+ +----------------------------------+ -# | H1 | | H2 | -# | | | unicast --> + $h2.111 | -# | | | traffic | 192.0.2.129/28 | -# | multicast | | | e-qos-map 0:1 | -# | traffic | | | | -# | $h1 + <----- | | + $h2 | -# +-----|-----------------+ +--------------|-------------------+ -# | | -# +-----|-------------------------------------------------|-------------------+ -# | + $swp1 + $swp2 | -# | | >1Gbps | >1Gbps | -# | +---|----------------+ +----------|----------------+ | -# | | + $swp1.1 | | + $swp2.111 | | +# +---------------------------+ +----------------------------------+ +# | H1 | | H2 | +# | | | unicast --> + $h2.111 | +# | multicast | | traffic | 192.0.2.129/28 | +# | traffic | | | e-qos-map 0:1 | +# | $h1 + <----- | | | | +# | 192.0.2.65/28 | | | + $h2 | +# +---------------|-----------+ +--------------|-------------------+ +# | | +# +---------------|---------------------------------------|-------------------+ +# | $swp1 + + $swp2 | +# | >1Gbps | | >1Gbps | +# | +-------------|------+ +----------|----------------+ | +# | | $swp1.1 + | | + $swp2.111 | | # | | BR1 | SW | BR111 | | -# | | + $swp3.1 | | + $swp3.111 | | -# | +---|----------------+ +----------|----------------+ | -# | \_________________________________________________/ | +# | | $swp3.1 + | | + $swp3.111 | | +# | +-------------|------+ +----------|----------------+ | +# | \_______________________________________/ | # | | | # | + $swp3 | # | | 1Gbps bottleneck | @@ -51,6 +51,7 @@ # | # +--|-----------------+ # | + $h3 H3 | +# | | 192.0.2.66/28 | # | | | # | + $h3.111 | # | 192.0.2.130/28 | @@ -59,6 +60,7 @@ ALL_TESTS=" ping_ipv4 test_mc_aware + test_uc_aware " lib_dir=$(dirname $0)/../../../net/forwarding @@ -68,14 +70,14 @@ source $lib_dir/lib.sh h1_create() { - simple_if_init $h1 + simple_if_init $h1 192.0.2.65/28 mtu_set $h1 10000 } h1_destroy() { mtu_restore $h1 - simple_if_fini $h1 + simple_if_fini $h1 192.0.2.65/28 } h2_create() @@ -97,7 +99,7 @@ h2_destroy() h3_create() { - simple_if_init $h3 + simple_if_init $h3 192.0.2.66/28 mtu_set $h3 10000 vlan_create $h3 111 v$h3 192.0.2.130/28 @@ -108,7 +110,7 @@ h3_destroy() vlan_destroy $h3 111 mtu_restore $h3 - simple_if_fini $h3 + simple_if_fini $h3 192.0.2.66/28 } switch_create() @@ -251,7 +253,7 @@ measure_uc_rate() # average ingress rate to somewhat mitigate this. local min_ingress=2147483648 - mausezahn $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \ + $MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \ -a own -b $h3mac -t udp -q & sleep 1 @@ -291,7 +293,7 @@ test_mc_aware() check_err $? "Could not get high enough UC-only ingress rate" local ucth1=${uc_rate[1]} - mausezahn $h1 -p 8000 -c 0 -a own -b bc -t udp -q & + $MZ $h1 -p 8000 -c 0 -a own -b bc -t udp -q & local d0=$(date +%s) local t0=$(ethtool_stats_get $h3 rx_octets_prio_0) @@ -311,7 +313,7 @@ test_mc_aware() ret = 100 * ($ucth1 - $ucth2) / $ucth1 if (ret > 0) { ret } else { 0 } ") - check_err $(bc <<< "$deg > 10") + check_err $(bc <<< "$deg > 25") local interval=$((d1 - d0)) local mc_ir=$(rate $u0 $u1 $interval) @@ -335,6 +337,51 @@ test_mc_aware() echo " egress UC throughput $(humanize ${uc_rate_2[1]})" echo " ingress MC throughput $(humanize $mc_ir)" echo " egress MC throughput $(humanize $mc_er)" + echo +} + +test_uc_aware() +{ + RET=0 + + $MZ $h2.111 -p 8000 -A 192.0.2.129 -B 192.0.2.130 -c 0 \ + -a own -b $h3mac -t udp -q & + + local d0=$(date +%s) + local t0=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u0=$(ethtool_stats_get $swp2 rx_octets_prio_1) + sleep 1 + + local attempts=50 + local passes=0 + local i + + for ((i = 0; i < attempts; ++i)); do + if $ARPING -c 1 -I $h1 -b 192.0.2.66 -q -w 0.1; then + ((passes++)) + fi + + sleep 0.1 + done + + local d1=$(date +%s) + local t1=$(ethtool_stats_get $h3 rx_octets_prio_1) + local u1=$(ethtool_stats_get $swp2 rx_octets_prio_1) + + local interval=$((d1 - d0)) + local uc_ir=$(rate $u0 $u1 $interval) + local uc_er=$(rate $t0 $t1 $interval) + + ((attempts == passes)) + check_err $? + + # Suppress noise from killing mausezahn. + { kill %% && wait; } 2>/dev/null + + log_test "MC performace under UC overload" + echo " ingress UC throughput $(humanize ${uc_ir})" + echo " egress UC throughput $(humanize ${uc_er})" + echo " sent $attempts BC ARPs, got $passes responses" } trap cleanup EXIT diff --git a/tools/testing/selftests/powerpc/cache_shape/Makefile b/tools/testing/selftests/powerpc/cache_shape/Makefile index ede4d3dae7505e..689f6c8ebcd8d6 100644 --- a/tools/testing/selftests/powerpc/cache_shape/Makefile +++ b/tools/testing/selftests/powerpc/cache_shape/Makefile @@ -1,12 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := cache_shape - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c +TEST_GEN_PROGS := cache_shape top_srcdir = ../../../../.. include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c diff --git a/tools/testing/selftests/powerpc/pmu/ebb/Makefile b/tools/testing/selftests/powerpc/pmu/ebb/Makefile index bd5dfa509272a7..23f4caf48ffc6b 100644 --- a/tools/testing/selftests/powerpc/pmu/ebb/Makefile +++ b/tools/testing/selftests/powerpc/pmu/ebb/Makefile @@ -5,6 +5,9 @@ noarg: # The EBB handler is 64-bit code and everything links against it CFLAGS += -m64 +# Toolchains may build PIE by default which breaks the assembly +LDFLAGS += -no-pie + TEST_GEN_PROGS := reg_access_test event_attributes_test cycles_test \ cycles_with_freeze_test pmc56_overflow_test \ ebb_vs_cpu_event_test cpu_event_vs_ebb_test \ diff --git a/tools/testing/selftests/powerpc/ptrace/Makefile b/tools/testing/selftests/powerpc/ptrace/Makefile index 9b35ca8e8f13d4..8d3f006c98cc39 100644 --- a/tools/testing/selftests/powerpc/ptrace/Makefile +++ b/tools/testing/selftests/powerpc/ptrace/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ +TEST_GEN_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ ptrace-tar ptrace-tm-tar ptrace-tm-spd-tar ptrace-vsx ptrace-tm-vsx \ ptrace-tm-spd-vsx ptrace-tm-spr ptrace-hwbreak ptrace-pkey core-pkey \ perf-hwbreak ptrace-syscall @@ -7,14 +7,9 @@ TEST_PROGS := ptrace-gpr ptrace-tm-gpr ptrace-tm-spd-gpr \ top_srcdir = ../../../../.. include ../../lib.mk -all: $(TEST_PROGS) - CFLAGS += -m64 -I../../../../../usr/include -I../tm -mhtm -fno-pie -ptrace-pkey core-pkey: child.h -ptrace-pkey core-pkey: LDLIBS += -pthread - -$(TEST_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h +$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: child.h +$(OUTPUT)/ptrace-pkey $(OUTPUT)/core-pkey: LDLIBS += -pthread -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c ../lib/reg.S ptrace.h diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c index 327fa943c7f366..dbdffa2e2c8248 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-gpr.c @@ -67,8 +67,8 @@ trans: "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) : [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2), [gpr_4]"i"(GPR_4), - [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "r" (&a), - [flt_2] "r" (&b), [flt_4] "r" (&d) + [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a), + [flt_4] "b" (&d) : "memory", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15", "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23", diff --git a/tools/testing/selftests/powerpc/security/Makefile b/tools/testing/selftests/powerpc/security/Makefile index 44690f1bb26ae1..85861c46b4457d 100644 --- a/tools/testing/selftests/powerpc/security/Makefile +++ b/tools/testing/selftests/powerpc/security/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0+ TEST_GEN_PROGS := rfi_flush +top_srcdir = ../../../../.. CFLAGS += -I../../../../../usr/include diff --git a/tools/testing/selftests/powerpc/security/rfi_flush.c b/tools/testing/selftests/powerpc/security/rfi_flush.c index 564ed45bbf731e..0a7d0afb26b885 100644 --- a/tools/testing/selftests/powerpc/security/rfi_flush.c +++ b/tools/testing/selftests/powerpc/security/rfi_flush.c @@ -49,6 +49,7 @@ int rfi_flush_test(void) struct perf_event_read v; __u64 l1d_misses_total = 0; unsigned long iterations = 100000, zero_size = 24 * 1024; + unsigned long l1d_misses_expected; int rfi_flush_org, rfi_flush; SKIP_IF(geteuid() != 0); @@ -71,6 +72,12 @@ int rfi_flush_test(void) iter = repetitions; + /* + * We expect to see l1d miss for each cacheline access when rfi_flush + * is set. Allow a small variation on this. + */ + l1d_misses_expected = iterations * (zero_size / CACHELINE_SIZE - 2); + again: FAIL_IF(perf_event_reset(fd)); @@ -78,10 +85,9 @@ again: FAIL_IF(read(fd, &v, sizeof(v)) != sizeof(v)); - /* Expect at least zero_size/CACHELINE_SIZE misses per iteration */ - if (v.l1d_misses >= (iterations * zero_size / CACHELINE_SIZE) && rfi_flush) + if (rfi_flush && v.l1d_misses >= l1d_misses_expected) passes++; - else if (v.l1d_misses < iterations && !rfi_flush) + else if (!rfi_flush && v.l1d_misses < (l1d_misses_expected / 2)) passes++; l1d_misses_total += v.l1d_misses; @@ -92,13 +98,15 @@ again: if (passes < repetitions) { printf("FAIL (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d failures]\n", rfi_flush, l1d_misses_total, rfi_flush ? '<' : '>', - rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations, + rfi_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, repetitions - passes, repetitions); rc = 1; } else printf("PASS (L1D misses with rfi_flush=%d: %llu %c %lu) [%d/%d pass]\n", rfi_flush, l1d_misses_total, rfi_flush ? '>' : '<', - rfi_flush ? (repetitions * iterations * zero_size / CACHELINE_SIZE) : iterations, + rfi_flush ? repetitions * l1d_misses_expected : + repetitions * l1d_misses_expected / 2, passes, repetitions); if (rfi_flush == rfi_flush_org) { diff --git a/tools/testing/selftests/powerpc/signal/Makefile b/tools/testing/selftests/powerpc/signal/Makefile index 1fca25c6ace067..209a958dca1276 100644 --- a/tools/testing/selftests/powerpc/signal/Makefile +++ b/tools/testing/selftests/powerpc/signal/Makefile @@ -1,15 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -TEST_PROGS := signal signal_tm - -all: $(TEST_PROGS) - -$(TEST_PROGS): ../harness.c ../utils.c signal.S +TEST_GEN_PROGS := signal signal_tm CFLAGS += -maltivec -signal_tm: CFLAGS += -mhtm +$(OUTPUT)/signal_tm: CFLAGS += -mhtm top_srcdir = ../../../../.. include ../../lib.mk -clean: - rm -f $(TEST_PROGS) *.o +$(TEST_GEN_PROGS): ../harness.c ../utils.c signal.S diff --git a/tools/testing/selftests/powerpc/switch_endian/Makefile b/tools/testing/selftests/powerpc/switch_endian/Makefile index fcd2dcb8972bab..bdc081afedb0f0 100644 --- a/tools/testing/selftests/powerpc/switch_endian/Makefile +++ b/tools/testing/selftests/powerpc/switch_endian/Makefile @@ -8,6 +8,7 @@ EXTRA_CLEAN = $(OUTPUT)/*.o $(OUTPUT)/check-reversed.S top_srcdir = ../../../../.. include ../../lib.mk +$(OUTPUT)/switch_endian_test: ASFLAGS += -I $(OUTPUT) $(OUTPUT)/switch_endian_test: $(OUTPUT)/check-reversed.S $(OUTPUT)/check-reversed.o: $(OUTPUT)/check.o diff --git a/tools/testing/selftests/powerpc/utils.c b/tools/testing/selftests/powerpc/utils.c index 43c342845be0ee..ed62f4153d3eb5 100644 --- a/tools/testing/selftests/powerpc/utils.c +++ b/tools/testing/selftests/powerpc/utils.c @@ -25,7 +25,6 @@ #include "utils.h" static char auxv[4096]; -extern unsigned int dscr_insn[]; int read_auxv(char *buf, ssize_t buf_size) { @@ -247,7 +246,8 @@ static void sigill_handler(int signr, siginfo_t *info, void *unused) ucontext_t *ctx = (ucontext_t *)unused; unsigned long *pc = &UCONTEXT_NIA(ctx); - if (*pc == (unsigned long)&dscr_insn) { + /* mtspr 3,RS to check for move to DSCR below */ + if ((*((unsigned int *)*pc) & 0xfc1fffff) == 0x7c0303a6) { if (!warned++) printf("WARNING: Skipping over dscr setup. Consider running 'ppc64_cpu --dscr=1' manually.\n"); *pc += 4; @@ -271,5 +271,5 @@ void set_dscr(unsigned long val) init = 1; } - asm volatile("dscr_insn: mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); + asm volatile("mtspr %1,%0" : : "r" (val), "i" (SPRN_DSCR)); } |