index.txt - File index, Mailing list and Links (this document)
-intel-pstate.txt - Intel pstate cpufreq driver specific file.
-
pcc-cpufreq.txt - PCC cpufreq driver specific file.
compatible = "st,stm32h743-rcc", "st,stm32-rcc";
reg = <0x58024400 0x400>;
#reset-cells = <1>;
- #clock-cells = <2>;
+ #clock-cells = <1>;
clocks = <&clk_hse>, <&clk_lse>, <&clk_i2s_ckin>;
st,syscfg = <&pwrcfg>;
compatible : Must be "ams,as3645a".
reg : The I2C address of the device. Typically 0x30.
+#address-cells : 1
+#size-cells : 0
-Required properties of the "flash" child node
-=============================================
+Required properties of the flash child node (0)
+===============================================
+reg: 0
flash-timeout-us: Flash timeout in microseconds. The value must be in
the range [100000, 850000] and divisible by 50000.
flash-max-microamp: Maximum flash current in microamperes. Has to be
and divisible by 50000.
-Optional properties of the "flash" child node
-=============================================
+Optional properties of the flash child node
+===========================================
label : The label of the flash LED.
-Required properties of the "indicator" child node
-=================================================
+Required properties of the indicator child node (1)
+===================================================
+reg: 1
led-max-microamp: Maximum indicator current. The allowed values are
2500, 5000, 7500 and 10000.
-Optional properties of the "indicator" child node
-=================================================
+Optional properties of the indicator child node
+===============================================
label : The label of the indicator LED.
=======
as3645a@30 {
+ #address-cells: 1
+ #size-cells: 0
reg = <0x30>;
compatible = "ams,as3645a";
- flash {
+ flash@0 {
+ reg = <0x0>;
flash-timeout-us = <150000>;
flash-max-microamp = <320000>;
led-max-microamp = <60000>;
ams,input-max-microamp = <1750000>;
label = "as3645a:flash";
};
- indicator {
+ indicator@1 {
+ reg = <0x1>;
led-max-microamp = <10000>;
label = "as3645a:indicator";
};
the firmware event log
- linux,sml-size : size of the memory allocated for the firmware event log
+Optional properties:
+
+- powered-while-suspended: present when the TPM is left powered on between
+ suspend and resume (makes the suspend/resume
+ callbacks do nothing).
+
Example (for OpenPower Systems with Nuvoton TPM 2.0 on I2C)
----------------------------------------------------------
This isn't an exhaustive list, but you should add new prefixes to it before
using them to avoid name-space collisions.
-abcn Abracon Corporation
abilis Abilis Systems
+abracon Abracon Corporation
actions Actions Semiconductor Co., Ltd.
active-semi Active-Semi International Inc
ad Avionic Design GmbH
Support for power domains is provided through the :c:member:`pm_domain` field of
|struct device|. This field is a pointer to an object of type
-|struct dev_pm_domain|, defined in :file:`include/linux/pm.h``, providing a set
+|struct dev_pm_domain|, defined in :file:`include/linux/pm.h`, providing a set
of power management callbacks analogous to the subsystem-level and device driver
callbacks that are executed for the given device during all power transitions,
instead of the respective subsystem-level callbacks. Specifically, if a
Jeff Layton (many, many fixes, as well as great work on the cifs Kerberos code)
Scott Lovenberg
Pavel Shilovsky (for great work adding SMB2 support, and various SMB3 features)
+Aurelien Aptel (for DFS SMB3 work and some key bug fixes)
+Ronnie Sahlberg (for SMB3 xattr work and bug fixes)
+Shirish Pargaonkar (for many ACL patches over the years)
+Sachin Prabhu (many bug fixes, including for reconnect, copy offload and security)
+
Test case and Bug Report contributors
-------------------------------------
-The CIFS VFS support for Linux supports many advanced network filesystem
-features such as hierarchical dfs like namespace, hardlinks, locking and more.
+This module supports the SMB3 family of advanced network protocols (as well
+as older dialects, originally called "CIFS" or SMB1).
+
+The CIFS VFS module for Linux supports many advanced network filesystem
+features such as hierarchical DFS like namespace, hardlinks, locking and more.
It was designed to comply with the SNIA CIFS Technical Reference (which
supersedes the 1992 X/Open SMB Standard) as well as to perform best practice
practical interoperability with Windows 2000, Windows XP, Samba and equivalent
servers. This code was developed in participation with the Protocol Freedom
-Information Foundation.
+Information Foundation. CIFS and now SMB3 has now become a defacto
+standard for interoperating between Macs and Windows and major NAS appliances.
Please see
http://protocolfreedom.org/ and
For questions or bug reports please contact:
sfrench@samba.org (sfrench@us.ibm.com)
+See the project page at: https://wiki.samba.org/index.php/LinuxCIFS_utils
+
Build instructions:
==================
-For Linux 2.4:
-1) Get the kernel source (e.g.from http://www.kernel.org)
-and download the cifs vfs source (see the project page
-at http://us1.samba.org/samba/Linux_CIFS_client.html)
-and change directory into the top of the kernel directory
-then patch the kernel (e.g. "patch -p1 < cifs_24.patch")
-to add the cifs vfs to your kernel configure options if
-it has not already been added (e.g. current SuSE and UL
-users do not need to apply the cifs_24.patch since the cifs vfs is
-already in the kernel configure menu) and then
-mkdir linux/fs/cifs and then copy the current cifs vfs files from
-the cifs download to your kernel build directory e.g.
-
- cp <cifs_download_dir>/fs/cifs/* to <kernel_download_dir>/fs/cifs
-
-2) make menuconfig (or make xconfig)
-3) select cifs from within the network filesystem choices
-4) save and exit
-5) make dep
-6) make modules (or "make" if CIFS VFS not to be built as a module)
-
-For Linux 2.6:
+For Linux:
1) Download the kernel (e.g. from http://www.kernel.org)
and change directory into the top of the kernel directory tree
(e.g. /usr/src/linux-2.5.73)
If you do not have the utility mount.cifs (in the Samba 3.0 source tree and on
the CIFS VFS web site) copy it to the same directory in which mount.smbfs and
similar files reside (usually /sbin). Although the helper software is not
-required, mount.cifs is recommended. Eventually the Samba 3.0 utility program
-"net" may also be helpful since it may someday provide easier mount syntax for
-users who are used to Windows e.g.
- net use <mount point> <UNC name or cifs URL>
+required, mount.cifs is recommended. Most distros include a "cifs-utils"
+package that includes this utility so it is recommended to install this.
+
Note that running the Winbind pam/nss module (logon service) on all of your
Linux clients is useful in mapping Uids and Gids consistently across the
domain to the proper network user. The mount.cifs mount helper can be
-trivially built from Samba 3.0 or later source e.g. by executing:
-
- gcc samba/source/client/mount.cifs.c -o mount.cifs
+found at cifs-utils.git on git.samba.org
If cifs is built as a module, then the size and number of network buffers
and maximum number of simultaneous requests to one server can be configured.
on kernel/fs/cifs/cifs.ko the list of configuration changes that can be made
at module initialization time (by running insmod cifs.ko) can be seen.
+Recommendations
+===============
+To improve security the SMB2.1 dialect or later (usually will get SMB3) is now
+the new default. To use old dialects (e.g. to mount Windows XP) use "vers=1.0"
+on mount (or vers=2.0 for Windows Vista). Note that the CIFS (vers=1.0) is
+much older and less secure than the default dialect SMB3 which includes
+many advanced security features such as downgrade attack detection
+and encrypted shares and stronger signing and authentication algorithms.
+There are additional mount options that may be helpful for SMB3 to get
+improved POSIX behavior (NB: can use vers=3.0 to force only SMB3, never 2.1):
+ "mfsymlinks" and "cifsacl" and "idsfromsid"
+
Allowing User Mounts
====================
To permit users to mount and unmount over directories they own is possible
by default. This can be changed, as with nfs and other filesystems,
by simply specifying "nosuid" among the mount options. For user mounts
though to be able to pass the suid flag to mount requires rebuilding
-mount.cifs with the following flag:
-
- gcc samba/source/client/mount.cifs.c -DCIFS_ALLOW_USR_SUID -o mount.cifs
+mount.cifs with the following flag: CIFS_ALLOW_USR_SUID
There is a corresponding manual page for cifs mounting in the Samba 3.0 and
later source tree in docs/manpages/mount.cifs.8
Use instructions:
================
Once the CIFS VFS support is built into the kernel or installed as a module
-(cifs.o), you can use mount syntax like the following to access Samba or Windows
-servers:
+(cifs.ko), you can use mount syntax like the following to access Samba or
+Mac or Windows servers:
- mount -t cifs //9.53.216.11/e$ /mnt -o user=myname,pass=mypassword
+ mount -t cifs //9.53.216.11/e$ /mnt -o username=myname,password=mypassword
Before -o the option -v may be specified to make the mount.cifs
mount helper display the mount steps more verbosely.
After -o the following commonly used cifs vfs specific options
are supported:
- user=<username>
- pass=<password>
+ username=<username>
domain=<domain name>
Other cifs mount options are described below. Use of TCP names (in addition to
filenames (ie those which contain valid Linux characters, which normally
would be forbidden for Windows/CIFS semantics) as long as the server is
configured for Unix Extensions (and the client has not disabled
-/proc/fs/cifs/LinuxExtensionsEnabled).
-
+/proc/fs/cifs/LinuxExtensionsEnabled). In addition the mount option
+"mapposix" can be used on CIFS (vers=1.0) to force the mapping of
+illegal Windows/NTFS/SMB characters to a remap range (this mount parm
+is the default for SMB3). This remap ("mapposix") range is also
+compatible with Mac (and "Services for Mac" on some older Windows).
CIFS VFS Mount Options
======================
A partial list of the supported mount options follows:
- user The user name to use when trying to establish
+ username The user name to use when trying to establish
the CIFS session.
password The user password. If the mount helper is
installed, the user will be prompted for password
-Version 2.03 August 1, 2014
+Version 2.04 September 13, 2017
A Partial List of Missing Features
==================================
is a partial list of the known problems and missing features:
a) SMB3 (and SMB3.02) missing optional features:
- - RDMA
+ - RDMA (started)
- multichannel (started)
- directory leases (improved metadata caching)
- T10 copy offload (copy chunk is only mechanism supported)
- - encrypted shares
b) improved sparse file support
c) Directory entry caching relies on a 1 second timer, rather than
-using FindNotify or equivalent. - (started)
+using Directory Leases
d) quota support (needs minor kernel change since quota calls
to make it to network filesystems or deviceless filesystems)
-e) improve support for very old servers (OS/2 and Win9x for example)
-Including support for changing the time remotely (utimes command).
+e) Better optimize open to reduce redundant opens (using reference
+counts more) and to improve use of compounding in SMB3 to reduce
+number of roundtrips.
-f) hook lower into the sockets api (as NFS/SunRPC does) to avoid the
-extra copy in/out of the socket buffers in some cases.
-
-g) Better optimize open (and pathbased setfilesize) to reduce the
-oplock breaks coming from windows srv. Piggyback identical file
-opens on top of each other by incrementing reference count rather
-than resending (helps reduce server resource utilization and avoid
-spurious oplock breaks).
-
-h) Add support for storing symlink info to Windows servers
-in the Extended Attribute format their SFU clients would recognize.
-
-i) Finish inotify support so kde and gnome file list windows
+f) Finish inotify support so kde and gnome file list windows
will autorefresh (partially complete by Asser). Needs minor kernel
vfs change to support removing D_NOTIFY on a file.
-j) Add GUI tool to configure /proc/fs/cifs settings and for display of
+g) Add GUI tool to configure /proc/fs/cifs settings and for display of
the CIFS statistics (started)
-k) implement support for security and trusted categories of xattrs
+h) implement support for security and trusted categories of xattrs
(requires minor protocol extension) to enable better support for SELINUX
-l) Implement O_DIRECT flag on open (already supported on mount)
+i) Implement O_DIRECT flag on open (already supported on mount)
-m) Create UID mapping facility so server UIDs can be mapped on a per
+j) Create UID mapping facility so server UIDs can be mapped on a per
mount or a per server basis to client UIDs or nobody if no mapping
-exists. This is helpful when Unix extensions are negotiated to
-allow better permission checking when UIDs differ on the server
-and client. Add new protocol request to the CIFS protocol
-standard for asking the server for the corresponding name of a
-particular uid.
+exists. Also better integration with winbind for resolving SID owners
+
+k) Add tools to take advantage of more smb3 specific ioctls and features
+
+l) encrypted file support
+
+m) improved stats gathering, tools (perhaps integration with nfsometer?)
-n) DOS attrs - returned as pseudo-xattr in Samba format (check VFAT and NTFS for this too)
+n) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed
+file attribute via chflags) and improve user space tools for managing and
+viewing them.
-o) mount check for unmatched uids
+o) mount helper GUI (to simplify the various configuration options on mount)
-p) Add support for new vfs entry point for fallocate
+p) autonegotiation of dialects (offering more than one dialect ie SMB3.02,
+SMB3, SMB2.1 not just SMB3).
-q) Add tools to take advantage of cifs/smb3 specific ioctls and features
-such as "CopyChunk" (fast server side file copy)
+q) Allow mount.cifs to be more verbose in reporting errors with dialect
+or unsupported feature errors.
-r) encrypted file support
+r) updating cifs documentation, and user guid.
-s) improved stats gathering, tools (perhaps integration with nfsometer?)
+s) Addressing bugs found by running a broader set of xfstests in standard
+file system xfstest suite.
-t) allow setting more NTFS/SMB3 file attributes remotely (currently limited to compressed
-file attribute via chflags)
+t) split cifs and smb3 support into separate modules so legacy (and less
+secure) CIFS dialect can be disabled in environments that don't need it
+and simplify the code.
-u) mount helper GUI (to simplify the various configuration options on mount)
+u) Finish up SMB3.1.1 dialect support
+v) POSIX Extensions for SMB3.1.1
KNOWN BUGS
====================================
- This is the client VFS module for the Common Internet File System
- (CIFS) protocol which is the successor to the Server Message Block
+ This is the client VFS module for the SMB3 NAS protocol as well
+ older dialects such as the Common Internet File System (CIFS)
+ protocol which was the successor to the Server Message Block
(SMB) protocol, the native file sharing mechanism for most early
PC operating systems. New and improved versions of CIFS are now
called SMB2 and SMB3. These dialects are also supported by the
CIFS VFS module. CIFS is fully supported by network
- file servers such as Windows 2000, 2003, 2008 and 2012
+ file servers such as Windows 2000, 2003, 2008, 2012 and 2016
as well by Samba (which provides excellent CIFS
- server support for Linux and many other operating systems), so
+ server support for Linux and many other operating systems), Apple
+ systems, as well as most Network Attached Storage vendors, so
this network filesystem client can mount to a wide variety of
servers.
The intent of this module is to provide the most advanced network
- file system function for CIFS compliant servers, including better
- POSIX compliance, secure per-user session establishment, high
- performance safe distributed caching (oplock), optional packet
+ file system function for SMB3 compliant servers, including advanced
+ security features, excellent parallelized high performance i/o, better
+ POSIX compliance, secure per-user session establishment, encryption,
+ high performance safe distributed caching (leases/oplocks), optional packet
signing, large files, Unicode support and other internationalization
improvements. Since both Samba server and this filesystem client support
- the CIFS Unix extensions, the combination can provide a reasonable
- alternative to NFSv4 for fileserving in some Linux to Linux environments,
- not just in Linux to Windows environments.
+ the CIFS Unix extensions (and in the future SMB3 POSIX extensions),
+ the combination can provide a reasonable alternative to other network and
+ cluster file systems for fileserving in some Linux to Linux environments,
+ not just in Linux to Windows (or Linux to Mac) environments.
This filesystem has an mount utility (mount.cifs) that can be obtained from
jeq #14, good /* __NR_rt_sigprocmask */
jeq #13, good /* __NR_rt_sigaction */
jeq #35, good /* __NR_nanosleep */
- bad: ret #0 /* SECCOMP_RET_KILL */
+ bad: ret #0 /* SECCOMP_RET_KILL_THREAD */
good: ret #0x7fff0000 /* SECCOMP_RET_ALLOW */
The above example code can be placed into a file (here called "foo"), and
2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
link-local address has been found.
+ DAD operation and mode on a given interface will be selected according
+ to the maximum value of conf/{all,interface}/accept_dad.
+
force_tllao - BOOLEAN
Enable sending the target link-layer address option even when
responding to a unicast neighbor solicitation.
optimistic_dad - BOOLEAN
Whether to perform Optimistic Duplicate Address Detection (RFC 4429).
- 0: disabled (default)
- 1: enabled
+ 0: disabled (default)
+ 1: enabled
+
+ Optimistic Duplicate Address Detection for the interface will be enabled
+ if at least one of conf/{all,interface}/optimistic_dad is set to 1,
+ it will be disabled otherwise.
use_optimistic - BOOLEAN
If enabled, do not classify optimistic addresses as deprecated during
source address selection. Preferred addresses will still be chosen
before optimistic addresses, subject to other ranking in the source
address selection algorithm.
- 0: disabled (default)
- 1: enabled
+ 0: disabled (default)
+ 1: enabled
+
+ This will be enabled if at least one of
+ conf/{all,interface}/use_optimistic is set to 1, disabled otherwise.
stable_secret - IPv6 address
This IPv6 address will be used as a secret to generate IPv6
with SR-IOV or soft switches, such as OVS, are possible.
- User-space tools
-
- user space |
- +-------------------------------------------------------------------+
- kernel | Netlink
- |
- +--------------+-------------------------------+
- | Network stack |
- | (Linux) |
- | |
- +----------------------------------------------+
+ User-space tools
+
+ user space |
+ +-------------------------------------------------------------------+
+ kernel | Netlink
+ |
+ +--------------+-------------------------------+
+ | Network stack |
+ | (Linux) |
+ | |
+ +----------------------------------------------+
sw1p2 sw1p4 sw1p6
- sw1p1 + sw1p3 + sw1p5 + eth1
- + | + | + | +
- | | | | | | |
- +--+----+----+----+-+--+----+---+ +-----+-----+
- | Switch driver | | mgmt |
- | (this document) | | driver |
- | | | |
- +--------------+----------------+ +-----------+
- |
- kernel | HW bus (eg PCI)
- +-------------------------------------------------------------------+
- hardware |
- +--------------+---+------------+
- | Switch device (sw1) |
- | +----+ +--------+
- | | v offloaded data path | mgmt port
- | | | |
- +--|----|----+----+----+----+---+
- | | | | | |
- + + + + + +
- p1 p2 p3 p4 p5 p6
-
- front-panel ports
+ sw1p1 + sw1p3 + sw1p5 + eth1
+ + | + | + | +
+ | | | | | | |
+ +--+----+----+----+----+----+---+ +-----+-----+
+ | Switch driver | | mgmt |
+ | (this document) | | driver |
+ | | | |
+ +--------------+----------------+ +-----------+
+ |
+ kernel | HW bus (eg PCI)
+ +-------------------------------------------------------------------+
+ hardware |
+ +--------------+----------------+
+ | Switch device (sw1) |
+ | +----+ +--------+
+ | | v offloaded data path | mgmt port
+ | | | |
+ +--|----|----+----+----+----+---+
+ | | | | | |
+ + + + + + +
+ p1 p2 p3 p4 p5 p6
+
+ front-panel ports
Fig 1.
- reboot-cmd [ SPARC only ]
- rtsig-max
- rtsig-nr
+- seccomp/ ==> Documentation/userspace-api/seccomp_filter.rst
- sem
- sem_next_id [ sysv ipc ]
- sg-big-buff [ generic SCSI device (sg) ]
A seccomp filter may return any of the following values. If multiple
filters exist, the return value for the evaluation of a given system
call will always use the highest precedent value. (For example,
-``SECCOMP_RET_KILL`` will always take precedence.)
+``SECCOMP_RET_KILL_PROCESS`` will always take precedence.)
In precedence order, they are:
-``SECCOMP_RET_KILL``:
+``SECCOMP_RET_KILL_PROCESS``:
+ Results in the entire process exiting immediately without executing
+ the system call. The exit status of the task (``status & 0x7f``)
+ will be ``SIGSYS``, not ``SIGKILL``.
+
+``SECCOMP_RET_KILL_THREAD``:
Results in the task exiting immediately without executing the
system call. The exit status of the task (``status & 0x7f``) will
be ``SIGSYS``, not ``SIGKILL``.
allow use of ptrace, even of other sandboxed processes, without
extreme care; ptracers can use this mechanism to escape.)
+``SECCOMP_RET_LOG``:
+ Results in the system call being executed after it is logged. This
+ should be used by application developers to learn which syscalls their
+ application needs without having to iterate through multiple test and
+ development cycles to build the list.
+
+ This action will only be logged if "log" is present in the
+ actions_logged sysctl string.
+
``SECCOMP_RET_ALLOW``:
Results in the system call being executed.
and a more generic example of a higher level macro interface for BPF
program generation.
+Sysctls
+=======
+Seccomp's sysctl files can be found in the ``/proc/sys/kernel/seccomp/``
+directory. Here's a description of each file in that directory:
+
+``actions_avail``:
+ A read-only ordered list of seccomp return values (refer to the
+ ``SECCOMP_RET_*`` macros above) in string form. The ordering, from
+ left-to-right, is the least permissive return value to the most
+ permissive return value.
+
+ The list represents the set of seccomp return values supported
+ by the kernel. A userspace program may use this list to
+ determine if the actions found in the ``seccomp.h``, when the
+ program was built, differs from the set of actions actually
+ supported in the current running kernel.
+
+``actions_logged``:
+ A read-write ordered list of seccomp return values (refer to the
+ ``SECCOMP_RET_*`` macros above) that are allowed to be logged. Writes
+ to the file do not need to be in ordered form but reads from the file
+ will be ordered in the same way as the actions_avail sysctl.
+
+ It is important to note that the value of ``actions_logged`` does not
+ prevent certain actions from being logged when the audit subsystem is
+ configured to audit a task. If the action is not found in
+ ``actions_logged`` list, the final decision on whether to audit the
+ action for that task is ultimately left up to the audit subsystem to
+ decide for all seccomp return values other than ``SECCOMP_RET_ALLOW``.
+
+ The ``allow`` string is not accepted in the ``actions_logged`` sysctl
+ as it is not possible to log ``SECCOMP_RET_ALLOW`` actions. Attempting
+ to write ``allow`` to the sysctl will result in an EINVAL being
+ returned.
Adding architecture support
===========================
S: Maintained
F: drivers/acpi/arm64
+ACPI PMIC DRIVERS
+M: "Rafael J. Wysocki" <rjw@rjwysocki.net>
+M: Len Brown <lenb@kernel.org>
+R: Andy Shevchenko <andy@infradead.org>
+R: Mika Westerberg <mika.westerberg@linux.intel.com>
+L: linux-acpi@vger.kernel.org
+Q: https://patchwork.kernel.org/project/linux-acpi/list/
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
+B: https://bugzilla.kernel.org
+S: Supported
+F: drivers/acpi/pmic/
+
ACPI THERMAL DRIVER
M: Zhang Rui <rui.zhang@intel.com>
L: linux-acpi@vger.kernel.org
F: drivers/scsi/bnx2i/
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
-M: Yuval Mintz <Yuval.Mintz@cavium.com>
M: Ariel Elior <ariel.elior@cavium.com>
M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
M: Stefan Schmidt <stefan@osg.samsung.com>
L: linux-wpan@vger.kernel.org
W: http://wpan.cakelab.org/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan-next.git
S: Maintained
F: net/ieee802154/
F: net/mac802154/
S: Maintained
F: drivers/media/rc/mtk-cir.c
+MEDIATEK PMIC LED DRIVER
+M: Sean Wang <sean.wang@mediatek.com>
+S: Maintained
+F: drivers/leds/leds-mt6323.c
+F: Documentation/devicetree/bindings/leds/leds-mt6323.txt
+
MEDIATEK ETHERNET DRIVER
M: Felix Fietkau <nbd@openwrt.org>
M: John Crispin <john@phrozen.org>
F: drivers/scsi/qedi/
QLOGIC QL4xxx ETHERNET DRIVER
-M: Yuval Mintz <Yuval.Mintz@cavium.com>
M: Ariel Elior <Ariel.Elior@cavium.com>
M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
VERSION = 4
PATCHLEVEL = 14
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
NAME = Fearless Coyote
# *DOCUMENTATION*
PHONY += kselftest
kselftest:
- $(Q)$(MAKE) -C tools/testing/selftests run_tests
+ $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests run_tests
PHONY += kselftest-clean
kselftest-clean:
- $(Q)$(MAKE) -C tools/testing/selftests clean
+ $(Q)$(MAKE) -C $(srctree)/tools/testing/selftests clean
PHONY += kselftest-merge
kselftest-merge:
#endif
-#define copy_segments(tsk, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->ret)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp)
usb1: ohci@00400000 {
num-ports = <3>;
- atmel,vbus-gpio = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>;
+ atmel,vbus-gpio = <0 /* &pioA PIN_PD20 GPIO_ACTIVE_HIGH */
+ &pioA PIN_PA27 GPIO_ACTIVE_HIGH
+ 0
+ >;
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb_default>;
status = "okay";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mikrobus2_uart>;
atmel,use-dma-rx;
- atmel-use-dma-tx;
+ atmel,use-dma-tx;
status = "okay";
};
uart4: serial@fc00c000 {
atmel,use-dma-rx;
atmel,use-dma-tx;
- pinctrl-name = "default";
+ pinctrl-names = "default";
pinctrl-0 = <&pinctrl_mikrobus1_uart>;
status = "okay";
};
};
pinctrl_led_gpio_default: led_gpio_default {
- pinmux = <PIN_PA27__GPIO>,
+ pinmux = <PIN_PA10__GPIO>,
<PIN_PB1__GPIO>,
<PIN_PA31__GPIO>;
bias-pull-up;
};
pinctrl_usb_default: usb_default {
- pinmux = <PIN_PA10__GPIO>,
+ pinmux = <PIN_PA27__GPIO>,
<PIN_PD19__GPIO>;
bias-disable;
};
red {
label = "red";
- gpios = <&pioA PIN_PA27 GPIO_ACTIVE_LOW>;
+ gpios = <&pioA PIN_PA10 GPIO_ACTIVE_HIGH>;
};
green {
label = "green";
- gpios = <&pioA PIN_PB1 GPIO_ACTIVE_LOW>;
+ gpios = <&pioA PIN_PB1 GPIO_ACTIVE_HIGH>;
};
blue {
label = "blue";
- gpios = <&pioA PIN_PA31 GPIO_ACTIVE_LOW>;
+ gpios = <&pioA PIN_PA31 GPIO_ACTIVE_HIGH>;
linux,default-trigger = "heartbeat";
};
};
compatible = "ti,da850-evm", "ti,da850";
model = "DA850/AM1808/OMAP-L138 EVM";
+ aliases {
+ serial0 = &serial0;
+ serial1 = &serial1;
+ serial2 = &serial2;
+ ethernet0 = ð0;
+ };
+
soc@1c00000 {
pmx_core: pinmux@14120 {
status = "okay";
clock-frequency = <400000>;
as3645a@30 {
+ #address-cells = <1>;
+ #size-cells = <0>;
reg = <0x30>;
compatible = "ams,as3645a";
- flash {
+ flash@0 {
+ reg = <0x0>;
flash-timeout-us = <150000>;
flash-max-microamp = <320000>;
led-max-microamp = <60000>;
- peak-current-limit = <1750000>;
+ ams,input-max-microamp = <1750000>;
};
- indicator {
+ indicator@1 {
+ reg = <0x1>;
led-max-microamp = <10000>;
};
};
CONFIG_BLK_DEV_SD=y
# CONFIG_SCSI_LOWLEVEL is not set
CONFIG_ATA=y
+CONFIG_PATA_FTIDE010=y
CONFIG_INPUT_EVDEV=y
CONFIG_KEYBOARD_GPIO=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_LEDS_TRIGGERS=y
CONFIG_LEDS_TRIGGER_HEARTBEAT=y
CONFIG_RTC_CLASS=y
-CONFIG_RTC_DRV_GEMINI=y
CONFIG_DMADEVICES=y
+CONFIG_AMBA_PL08X=y
# CONFIG_DNOTIFY is not set
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_LCD_TOSA=m
CONFIG_BACKLIGHT_PWM=m
CONFIG_BACKLIGHT_TOSA=m
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_BACKLIGHT_LCD_SUPPORT=y
CONFIG_BACKLIGHT_PWM=m
# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
CONFIG_FB_PXA_PARAMETERS=y
CONFIG_BACKLIGHT_LCD_SUPPORT=y
# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=m
+CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_UPROBE 3 /* breakpointed or singlestepping */
-#define TIF_FSCHECK 4 /* Check FS is USER_DS on return */
-#define TIF_SYSCALL_TRACE 5 /* syscall trace active */
-#define TIF_SYSCALL_AUDIT 6 /* syscall auditing active */
-#define TIF_SYSCALL_TRACEPOINT 7 /* syscall tracepoint instrumentation */
-#define TIF_SECCOMP 8 /* seccomp syscall filtering active */
+#define TIF_SYSCALL_TRACE 4 /* syscall trace active */
+#define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */
+#define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */
+#define TIF_SECCOMP 7 /* seccomp syscall filtering active */
#define TIF_NOHZ 12 /* in adaptive nohz mode */
#define TIF_USING_IWMMXT 17
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_UPROBE (1 << TIF_UPROBE)
-#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT)
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
/*
* Change these and you break ASM code in entry-common.S
*/
-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
- _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_FSCHECK)
+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+ _TIF_NOTIFY_RESUME | _TIF_UPROBE)
#endif /* __KERNEL__ */
#endif /* __ASM_ARM_THREAD_INFO_H */
{
current_thread_info()->addr_limit = fs;
modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
- /* On user-mode return, check fs is correct */
- set_thread_flag(TIF_FSCHECK);
}
#define segment_eq(a, b) ((a) == (b))
#include <asm/unistd.h>
#include <asm/ftrace.h>
#include <asm/unwind.h>
+#include <asm/memory.h>
#ifdef CONFIG_AEABI
#include <asm/unistd-oabi.h>
#endif
UNWIND(.fnstart )
UNWIND(.cantunwind )
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK
- bne fast_work_pending
- tst r1, #_TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
bne fast_work_pending
+
/* perform architecture specific actions before user return */
arch_ret_to_user r1, lr
UNWIND(.cantunwind )
str r0, [sp, #S_R0 + S_OFF]! @ save returned r0
disable_irq_notrace @ disable interrupts
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing
- tst r1, #_TIF_SYSCALL_WORK
- bne fast_work_pending
- tst r1, #_TIF_WORK_MASK
+ tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
beq no_work_pending
UNWIND(.fnend )
ENDPROC(ret_fast_syscall)
/* Slower path - fall through to work_pending */
-fast_work_pending:
#endif
tst r1, #_TIF_SYSCALL_WORK
ret_slow_syscall:
disable_irq_notrace @ disable interrupts
ENTRY(ret_to_user_from_irq)
+ ldr r2, [tsk, #TI_ADDR_LIMIT]
+ cmp r2, #TASK_SIZE
+ blne addr_limit_check_failed
ldr r1, [tsk, #TI_FLAGS]
tst r1, #_TIF_WORK_MASK
bne slow_work_pending
* Update the trace code with the current status.
*/
trace_hardirqs_off();
-
- /* Check valid user FS if needed */
- addr_limit_user_check();
-
do {
if (likely(thread_flags & _TIF_NEED_RESCHED)) {
schedule();
return page;
}
+
+/* Defer to generic check */
+asmlinkage void addr_limit_check_failed(void)
+{
+ addr_limit_user_check();
+}
}
pm_bu->suspended = 0;
- pm_bu->canary = virt_to_phys(&canary);
- pm_bu->resume = virt_to_phys(cpu_resume);
+ pm_bu->canary = __pa_symbol(&canary);
+ pm_bu->resume = __pa_symbol(cpu_resume);
return;
KBUILD_CFLAGS += $(call cc-option, -mpc-relative-literal-loads)
KBUILD_AFLAGS += $(lseinstr) $(brokengasinst)
+KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
+KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
+
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
CHECKFLAGS += -D__AARCH64EB__
AS += -EB
LD += -EB
+LDFLAGS += -maarch64linuxb
UTS_MACHINE := aarch64_be
else
KBUILD_CPPFLAGS += -mlittle-endian
CHECKFLAGS += -D__AARCH64EL__
AS += -EL
LD += -EL
+LDFLAGS += -maarch64linux
UTS_MACHINE := aarch64
endif
#ifndef __ASM_LINKAGE_H
#define __ASM_LINKAGE_H
-#define __ALIGN .align 4
-#define __ALIGN_STR ".align 4"
+#define __ALIGN .align 2
+#define __ALIGN_STR ".align 2"
#endif
/* Find an entry in the third-level page table. */
#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_phys(dir,addr) (pmd_page_paddr(*(dir)) + pte_index(addr) * sizeof(pte_t))
+#define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t))
#define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr))))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
}
EXPORT_SYMBOL(kernel_neon_end);
+#ifdef CONFIG_EFI
+
static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state);
static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
kernel_neon_end();
}
+#endif /* CONFIG_EFI */
+
#endif /* CONFIG_KERNEL_MODE_NEON */
#ifdef CONFIG_CPU_PM
* booted in EL1 or EL2 respectively.
*/
ENTRY(el2_setup)
+ msr SPsel, #1 // We want to use SP_EL{1,2}
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
b.eq 1f
*/
trace_hardirqs_off();
- /* Check valid user FS if needed */
- addr_limit_user_check();
-
do {
+ /* Check valid user FS if needed */
+ addr_limit_user_check();
+
if (thread_flags & _TIF_NEED_RESCHED) {
schedule();
} else {
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
- { do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
+ { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
{ do_bad, SIGBUS, 0, "unknown 8" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
{
}
-#define copy_segments(tsk, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-
/*
* saved kernel SP and DP of a blocked thread.
*/
extern asmlinkage void save_user_regs(struct user_context *target);
extern asmlinkage void *restore_user_regs(const struct user_context *target, ...);
-#define copy_segments(tsk, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-#define forget_segments() do { } while (0)
-
unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) ((tsk)->thread.frame0->pc)
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-/* Copy and release all segment info associated with a VM */
-extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
-extern void release_segments(struct mm_struct * mm);
-
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-
unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) ((tsk)->thread.lr)
#define KSTK_ESP(tsk) ((tsk)->thread.sp)
{
}
-#define copy_segments(tsk, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-
/*
* Return saved PC of a blocked thread.
*/
# Endianness selection
choice
prompt "Endianness selection"
- default CPU_BIG_ENDIAN
+ default CPU_LITTLE_ENDIAN
help
microblaze architectures can be configured for either little or
big endian formats. Be sure to select the appropriate mode.
generic-y += ioctl.h
generic-y += ioctls.h
generic-y += ipcbuf.h
+generic-y += kvm_para.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += param.h
unsigned long attrs)
{
#ifdef CONFIG_MMU
- unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+ unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
unsigned long pfn;
#include "pci.h"
static int (*ath79_pci_plat_dev_init)(struct pci_dev *dev);
-static const struct ath79_pci_irq *ath79_pci_irq_map __initdata;
-static unsigned ath79_pci_nr_irqs __initdata;
+static const struct ath79_pci_irq *ath79_pci_irq_map;
+static unsigned ath79_pci_nr_irqs;
-static const struct ath79_pci_irq ar71xx_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq ar71xx_pci_irq_map[] = {
{
.slot = 17,
.pin = 1,
}
};
-static const struct ath79_pci_irq ar724x_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq ar724x_pci_irq_map[] = {
{
.slot = 0,
.pin = 1,
}
};
-static const struct ath79_pci_irq qca955x_pci_irq_map[] __initconst = {
+static const struct ath79_pci_irq qca955x_pci_irq_map[] = {
{
.bus = 0,
.slot = 0,
},
};
-int __init pcibios_map_irq(const struct pci_dev *dev, uint8_t slot, uint8_t pin)
+int pcibios_map_irq(const struct pci_dev *dev, uint8_t slot, uint8_t pin)
{
int irq = -1;
int i;
#define __write_64bit_c0_split(source, sel, val) \
do { \
+ unsigned long long __tmp; \
unsigned long __flags; \
\
local_irq_save(__flags); \
if (sel == 0) \
__asm__ __volatile__( \
".set\tmips64\n\t" \
- "dsll\t%L0, %L0, 32\n\t" \
+ "dsll\t%L0, %L1, 32\n\t" \
"dsrl\t%L0, %L0, 32\n\t" \
- "dsll\t%M0, %M0, 32\n\t" \
+ "dsll\t%M0, %M1, 32\n\t" \
"or\t%L0, %L0, %M0\n\t" \
"dmtc0\t%L0, " #source "\n\t" \
".set\tmips0" \
- : : "r" (val)); \
+ : "=&r,r" (__tmp) \
+ : "r,0" (val)); \
else \
__asm__ __volatile__( \
".set\tmips64\n\t" \
- "dsll\t%L0, %L0, 32\n\t" \
+ "dsll\t%L0, %L1, 32\n\t" \
"dsrl\t%L0, %L0, 32\n\t" \
- "dsll\t%M0, %M0, 32\n\t" \
+ "dsll\t%M0, %M1, 32\n\t" \
"or\t%L0, %L0, %M0\n\t" \
"dmtc0\t%L0, " #source ", " #sel "\n\t" \
".set\tmips0" \
- : : "r" (val)); \
+ : "=&r,r" (__tmp) \
+ : "r,0" (val)); \
local_irq_restore(__flags); \
} while (0)
return -ENOENT;
}
- if ((unsigned int)event->cpu >= nr_cpumask_bits ||
- (event->cpu >= 0 && !cpu_online(event->cpu)))
+ if (event->cpu >= 0 && !cpu_online(event->cpu))
return -ENODEV;
if (!atomic_inc_not_zero(&active_events)) {
#define INTC PC104PLUS_INTC_IRQ
#define INTD PC104PLUS_INTD_IRQ
-static char irq_tab_capcella[][5] __initdata = {
+static char irq_tab_capcella[][5] = {
[11] = { -1, INT1, INT1, INT1, INT1 },
[12] = { -1, INT2, INT2, INT2, INT2 },
[14] = { -1, INTA, INTB, INTC, INTD }
};
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return irq_tab_capcella[slot][pin];
}
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C586_0,
qube_raq_via_board_id_fixup);
-static char irq_tab_qube1[] __initdata = {
+static char irq_tab_qube1[] = {
[COBALT_PCICONF_CPU] = 0,
[COBALT_PCICONF_ETH0] = QUBE1_ETH0_IRQ,
[COBALT_PCICONF_RAQSCSI] = SCSI_IRQ,
[COBALT_PCICONF_ETH1] = 0
};
-static char irq_tab_cobalt[] __initdata = {
+static char irq_tab_cobalt[] = {
[COBALT_PCICONF_CPU] = 0,
[COBALT_PCICONF_ETH0] = ETH0_IRQ,
[COBALT_PCICONF_RAQSCSI] = SCSI_IRQ,
[COBALT_PCICONF_ETH1] = ETH1_IRQ
};
-static char irq_tab_raq2[] __initdata = {
+static char irq_tab_raq2[] = {
[COBALT_PCICONF_CPU] = 0,
[COBALT_PCICONF_ETH0] = ETH0_IRQ,
[COBALT_PCICONF_RAQSCSI] = RAQ2_SCSI_IRQ,
[COBALT_PCICONF_ETH1] = ETH1_IRQ
};
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
if (cobalt_board_id <= COBALT_BRD_ID_QUBE1)
return irq_tab_qube1[slot];
*/
#define MAX_SLOT_NUM 10
-static unsigned char irq_map[][5] __initdata = {
+static unsigned char irq_map[][5] = {
[3] = {0, MARKEINS_PCI_IRQ_INTB, MARKEINS_PCI_IRQ_INTC,
MARKEINS_PCI_IRQ_INTD, 0,},
[4] = {0, MARKEINS_PCI_IRQ_INTA, 0, 0, 0,},
DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NEC, PCI_DEVICE_ID_NEC_EMMA2RH,
emma2rh_pci_host_fixup);
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return irq_map[slot][pin];
}
/* South bridge slot number is set by the pci probe process */
static u8 sb_slot = 5;
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int irq = 0;
#define INTB MACEPCI_SHARED0_IRQ
#define INTC MACEPCI_SHARED1_IRQ
#define INTD MACEPCI_SHARED2_IRQ
-static char irq_tab_mace[][5] __initdata = {
+static char irq_tab_mace[][5] = {
/* Dummy INT#A INT#B INT#C INT#D */
{0, 0, 0, 0, 0}, /* This is placeholder row - never used */
{0, SCSI0, SCSI0, SCSI0, SCSI0},
* irqs. I suppose a device without a pin A will thank us for doing it
* right if there exists such a broken piece of crap.
*/
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return irq_tab_mace[slot][pin];
}
#include <asm/txx9/pci.h>
#include <asm/txx9/jmr3927.h>
-int __init jmr3927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int jmr3927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
unsigned char irq = pin;
return 0;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return of_irq_parse_and_map_pci(dev, slot, pin);
}
#define PCID 7
/* all the pci device has the PCIA pin, check the datasheet. */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
/* INTA INTB INTC INTD */
{0, 0, 0, 0, 0}, /* 11: Unused */
{0, 0, 0, 0, 0}, /* 12: Unused */
{0, 0, 0, 0, 0}, /* 27: Unused */
};
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int virq;
pdev->vendor, pdev->device, pdev->irq);
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
print_fixup_info(dev);
return dev->irq;
static char pci_irq[5] = {
};
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
/* INTA INTB INTC INTD */
{0, 0, 0, 0, 0 }, /* 0: GT64120 PCI bridge */
{0, 0, 0, 0, 0 }, /* 1: Unused */
{0, PCID, PCIA, PCIB, PCIC } /* 21: PCI Slot 4 */
};
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int virq;
virq = irq_tab[slot][pin];
#include <asm/vr41xx/mpc30x.h>
-static const int internal_func_irqs[] __initconst = {
+static const int internal_func_irqs[] = {
VRC4173_CASCADE_IRQ,
VRC4173_AC97_IRQ,
VRC4173_USB_IRQ,
};
-static const int irq_tab_mpc30x[] __initconst = {
+static const int irq_tab_mpc30x[] = {
[12] = VRC4173_PCMCIA1_IRQ,
[13] = VRC4173_PCMCIA2_IRQ,
[29] = MQ200_IRQ,
};
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
if (slot == 30)
return internal_func_irqs[PCI_FUNC(dev->devfn)];
#if defined(CONFIG_PMC_MSP7120_GW)
/* Garibaldi Board IRQ wiring to PCI slots */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
/* INTA INTB INTC INTD */
{0, 0, 0, 0, 0 }, /* (AD[0]): Unused */
{0, 0, 0, 0, 0 }, /* (AD[1]): Unused */
#elif defined(CONFIG_PMC_MSP7120_EVAL)
/* MSP7120 Eval Board IRQ wiring to PCI slots */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
/* INTA INTB INTC INTD */
{0, 0, 0, 0, 0 }, /* (AD[0]): Unused */
{0, 0, 0, 0, 0 }, /* (AD[1]): Unused */
#else
/* Unknown board -- don't assign any IRQs */
-static char irq_tab[][5] __initdata = {
+static char irq_tab[][5] = {
/* INTA INTB INTC INTD */
{0, 0, 0, 0, 0 }, /* (AD[0]): Unused */
{0, 0, 0, 0, 0 }, /* (AD[1]): Unused */
* RETURNS: IRQ number
*
****************************************************************************/
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
#if !defined(CONFIG_PMC_MSP7120_GW) && !defined(CONFIG_PMC_MSP7120_EVAL)
printk(KERN_WARNING "PCI: unknown board, no PCI IRQs assigned.\n");
#include <asm/txx9/pci.h>
#include <asm/txx9/rbtx4927.h>
-int __init rbtx4927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int rbtx4927_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
unsigned char irq = pin;
#include <asm/txx9/pci.h>
#include <asm/txx9/rbtx4938.h>
-int __init rbtx4938_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int rbtx4938_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int irq = tx4938_pcic1_map_irq(dev, slot);
* seem to be a documentation error. At least on my RM200C the Cirrus
* Logic CL-GD5434 VGA is device 3.
*/
-static char irq_tab_rm200[8][5] __initdata = {
+static char irq_tab_rm200[8][5] = {
/* INTA INTB INTC INTD */
{ 0, 0, 0, 0, 0 }, /* EISA bridge */
{ SCSI, SCSI, SCSI, SCSI, SCSI }, /* SCSI */
*
* The VGA card is optional for RM300 systems.
*/
-static char irq_tab_rm300d[8][5] __initdata = {
+static char irq_tab_rm300d[8][5] = {
/* INTA INTB INTC INTD */
{ 0, 0, 0, 0, 0 }, /* EISA bridge */
{ SCSI, SCSI, SCSI, SCSI, SCSI }, /* SCSI */
{ 0, INTD, INTA, INTB, INTC }, /* Slot 4 */
};
-static char irq_tab_rm300e[5][5] __initdata = {
+static char irq_tab_rm300e[5][5] = {
/* INTA INTB INTC INTD */
{ 0, 0, 0, 0, 0 }, /* HOST bridge */
{ SCSI, SCSI, SCSI, SCSI, SCSI }, /* SCSI */
#define INTC PCIT_IRQ_INTC
#define INTD PCIT_IRQ_INTD
-static char irq_tab_pcit[13][5] __initdata = {
+static char irq_tab_pcit[13][5] = {
/* INTA INTB INTC INTD */
{ 0, 0, 0, 0, 0 }, /* HOST bridge */
{ SCSI0, SCSI0, SCSI0, SCSI0, SCSI0 }, /* SCSI */
{ 0, INTA, INTB, INTC, INTD }, /* Slot 5 */
};
-static char irq_tab_pcit_cplus[13][5] __initdata = {
+static char irq_tab_pcit_cplus[13][5] = {
/* INTA INTB INTC INTD */
{ 0, 0, 0, 0, 0 }, /* HOST bridge */
{ 0, INTB, INTC, INTD, INTA }, /* PCI Slot 9 */
return (csmsr & 0xa0) == 0x20;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
switch (sni_brd_type) {
case SNI_BRD_PCI_TOWER_CPLUS:
#include <asm/vr41xx/tb0219.h>
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int irq = -1;
#include <asm/vr41xx/giu.h>
#include <asm/vr41xx/tb0226.h>
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int irq = -1;
#include <asm/vr41xx/tb0287.h>
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
unsigned char bus;
int irq = -1;
arch_initcall(alchemy_pci_init);
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
struct alchemy_pci_context *ctx = dev->sysdata;
if (ctx && ctx->board_map_irq)
#include <linux/bcma/bcma.h>
#include <bcm47xx.h>
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return 0;
}
#define LASAT_IRQ_PCIC (LASAT_IRQ_BASE + 7)
#define LASAT_IRQ_PCID (LASAT_IRQ_BASE + 8)
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
switch (slot) {
case 1:
return 0;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
u16 cmd;
u32 val;
} s;
};
-int __initconst (*octeon_pcibios_map_irq)(const struct pci_dev *dev,
- u8 slot, u8 pin);
+int (*octeon_pcibios_map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
enum octeon_dma_bar_type octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_INVALID;
/**
* as it goes through each bridge.
* Returns Interrupt number for the device
*/
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
if (octeon_pcibios_map_irq)
return octeon_pcibios_map_irq(dev, slot, pin);
spin_unlock_irqrestore(&rt2880_pci_lock, flags);
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
u16 cmd;
int irq = -1;
return err;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return of_irq_parse_and_map_pci(dev, slot, pin);
}
return pciclk;
}
-int __init tx4938_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
+int tx4938_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
{
if (get_tx4927_pcicptr(dev->bus->sysdata) == tx4938_pcic1ptr) {
switch (slot) {
((pciclk + 50000) / 100000) % 10);
}
-int __init tx4939_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
+int tx4939_pcic1_map_irq(const struct pci_dev *dev, u8 slot)
{
if (get_tx4927_pcicptr(dev->bus->sysdata) == tx4939_pcic1ptr) {
switch (slot) {
return -1;
}
-int __init tx4939_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int tx4939_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
int irq = tx4939_pcic1_map_irq(dev, slot);
return PCI_SLOT(lnkdev->devfn) / 8;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
struct pci_dev *lnkdev;
int lnkfunc, node;
}
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
return get_irq_vector(dev);
}
* as it goes through each bridge.
* Returns Interrupt number for the device
*/
-int __init octeon_pcie_pcibios_map_irq(const struct pci_dev *dev,
- u8 slot, u8 pin)
+int octeon_pcie_pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
/*
* The EBH5600 board with the PCI to PCIe bridge mistakenly
#include <linux/smp.h>
#include <linux/interrupt.h>
+#include <asm/setup.h>
+
#ifdef CONFIG_MIPS_MT_SMP
#define MIPS_CPU_IPI_RESCHED_IRQ 0 /* SW int 0 for resched */
#define MIPS_CPU_IPI_CALL_IRQ 1 /* SW int 1 for call */
return 0;
}
-int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int (*txx9_pci_map_irq)(const struct pci_dev *dev, u8 slot, u8 pin);
+int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
- return txx9_board_vec->pci_map_irq(dev, slot, pin);
+ return txx9_pci_map_irq(dev, slot, pin);
}
char * (*txx9_board_pcibios_setup)(char *str) __initdata;
txx9_pci_err_action = TXX9_PCI_ERR_IGNORE;
return NULL;
}
+
+ txx9_pci_map_irq = txx9_board_vec->pci_map_irq;
+
return str;
}
}
#endif
-void release_segments(struct mm_struct *mm)
-{
-}
-
void machine_restart(char *cmd)
{
#ifdef CONFIG_KERNEL_DEBUGGER
{
}
-/*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
- */
-void copy_segments(struct task_struct *p, struct mm_struct *new_mm)
-{
-}
-
/*
* this gets called so that we can store lazy state into memory and copy the
* current task into the new thread.
endchoice
+config PARISC_SELF_EXTRACT
+ bool "Build kernel as self-extracting executable"
+ default y
+ help
+ Say Y if you want to build the parisc kernel as a kind of
+ self-extracting executable.
+
+ If you say N here, the kernel will be compressed with gzip
+ which can be loaded by the palo bootloader directly too.
+
+ If you don't know what to do here, say Y.
+
config SMP
bool "Symmetric multi-processing support"
---help---
bzImage: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
+ifdef CONFIG_PARISC_SELF_EXTRACT
vmlinuz: bzImage
$(OBJCOPY) $(boot)/bzImage $@
+else
+vmlinuz: vmlinux
+ @gzip -cf -9 $< > $@
+endif
install:
$(CONFIG_SHELL) $(src)/arch/parisc/install.sh \
KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
-KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs
+KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os
ifndef CONFIG_64BIT
KBUILD_CFLAGS += -mfast-indirect-calls
endif
/* Symbols defined by linker scripts */
extern char input_data[];
extern int input_len;
-extern __le32 output_len; /* at unaligned address, little-endian */
+/* output_len is inserted by the linker possibly at an unaligned address */
+extern __le32 output_len __aligned(1);
extern char _text, _end;
extern char _bss, _ebss;
extern char _startcode_end;
/* wrapper-functions from pdc.c */
int pdc_add_valid(unsigned long address);
+int pdc_instr(unsigned int *instr);
int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len);
int pdc_chassis_disp(unsigned long disp);
int pdc_chassis_warn(unsigned long *warn);
#ifndef __ASM_SMP_H
#define __ASM_SMP_H
+extern int init_per_cpu(int cpuid);
#if defined(CONFIG_SMP)
}
EXPORT_SYMBOL(pdc_add_valid);
+/**
+ * pdc_instr - Get instruction that invokes PDCE_CHECK in HPMC handler.
+ * @instr: Pointer to variable which will get instruction opcode.
+ *
+ * The return value is PDC_OK (0) in case call succeeded.
+ */
+int __init pdc_instr(unsigned int *instr)
+{
+ int retval;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pdc_lock, flags);
+ retval = mem_pdc_call(PDC_INSTR, 0UL, __pa(pdc_result));
+ convert_to_wide(pdc_result);
+ *instr = pdc_result[0];
+ spin_unlock_irqrestore(&pdc_lock, flags);
+
+ return retval;
+}
+
/**
* pdc_chassis_info - Return chassis information.
* @result: The return buffer.
#include <linux/memblock.h>
#include <linux/seq_file.h>
#include <linux/kthread.h>
+#include <linux/initrd.h>
#include <asm/pdc.h>
#include <asm/pdcpat.h>
}
for (i = 0; i < pdt_status.pdt_entries; i++) {
+ unsigned long addr;
+
report_mem_err(pdt_entry[i]);
+ addr = pdt_entry[i] & PDT_ADDR_PHYS_MASK;
+ if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) &&
+ addr >= initrd_start && addr < initrd_end)
+ pr_crit("CRITICAL: initrd possibly broken "
+ "due to bad memory!\n");
+
/* mark memory page bad */
memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE);
}
*
* o Enable CPU profiling hooks.
*/
-int init_per_cpu(int cpunum)
+int __init init_per_cpu(int cpunum)
{
int ret;
struct pdc_coproc_cfg coproc_cfg;
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
+#include <linux/start_kernel.h>
#include <asm/processor.h>
#include <asm/sections.h>
#include <asm/io.h>
#include <asm/setup.h>
#include <asm/unwind.h>
+#include <asm/smp.h>
static char __initdata command_line[COMMAND_LINE_SIZE];
}
#endif
-extern int init_per_cpu(int cpuid);
extern void collect_boot_cpu_data(void);
void __init setup_arch(char **cmdline_p)
}
arch_initcall(parisc_init);
-void start_parisc(void)
+void __init start_parisc(void)
{
- extern void start_kernel(void);
extern void early_trap_init(void);
int ret, cpunum;
static void __init
smp_cpu_init(int cpunum)
{
- extern int init_per_cpu(int); /* arch/parisc/kernel/processor.c */
extern void init_IRQ(void); /* arch/parisc/kernel/irq.c */
extern void start_cpu_itimer(void); /* arch/parisc/kernel/time.c */
/* Set modes and Enable floating point coprocessor */
- (void) init_per_cpu(cpunum);
+ init_per_cpu(cpunum);
disable_sr_hashing();
u32 check = 0;
u32 *ivap;
u32 *hpmcp;
- u32 length;
+ u32 length, instr;
if (strcmp((const char *)iva, "cows can fly"))
panic("IVT invalid");
for (i = 0; i < 8; i++)
*ivap++ = 0;
+ /*
+ * Use PDC_INSTR firmware function to get instruction that invokes
+ * PDCE_CHECK in HPMC handler. See programming note at page 1-31 of
+ * the PA 1.1 Firmware Architecture document.
+ */
+ if (pdc_instr(&instr) == PDC_OK)
+ ivap[0] = instr;
+
/* Compute Checksum for HPMC handler */
length = os_hpmc_size;
ivap[7] = length;
#include <linux/slab.h>
#include <linux/kallsyms.h>
#include <linux/sort.h>
+#include <linux/sched.h>
#include <linux/uaccess.h>
#include <asm/assembly.h>
info->prev_sp = sp - 64;
info->prev_ip = 0;
+
+ /* The stack is at the end inside the thread_union
+ * struct. If we reach data, we have reached the
+ * beginning of the stack and should stop unwinding. */
+ if (info->prev_sp >= (unsigned long) task_thread_info(info->t) &&
+ info->prev_sp < ((unsigned long) task_thread_info(info->t)
+ + THREAD_SZ_ALGN)) {
+ info->prev_sp = 0;
+ break;
+ }
+
if (get_user(tmp, (unsigned long *)(info->prev_sp - RP_OFFSET)))
break;
info->prev_ip = tmp;
#include <linux/interrupt.h>
#include <linux/extable.h>
#include <linux/uaccess.h>
+#include <linux/hugetlb.h>
#include <asm/traps.h>
struct task_struct *tsk;
struct mm_struct *mm;
unsigned long acc_type;
- int fault;
+ int fault = 0;
unsigned int flags;
if (faulthandler_disabled())
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
- else if (fault & VM_FAULT_SIGBUS)
+ else if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
+ VM_FAULT_HWPOISON_LARGE))
goto bad_area;
BUG();
}
if (user_mode(regs)) {
struct siginfo si;
-
- show_signal_msg(regs, code, address, tsk, vma);
+ unsigned int lsb = 0;
switch (code) {
case 15: /* Data TLB miss fault/Data page fault */
si.si_code = (code == 26) ? SEGV_ACCERR : SEGV_MAPERR;
break;
}
+
+#ifdef CONFIG_MEMORY_FAILURE
+ if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
+ printk(KERN_ERR
+ "MCE: Killing %s:%d due to hardware memory corruption fault at %08lx\n",
+ tsk->comm, tsk->pid, address);
+ si.si_signo = SIGBUS;
+ si.si_code = BUS_MCEERR_AR;
+ }
+#endif
+
+ /*
+ * Either small page or large page may be poisoned.
+ * In other words, VM_FAULT_HWPOISON_LARGE and
+ * VM_FAULT_HWPOISON are mutually exclusive.
+ */
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+ else if (fault & VM_FAULT_HWPOISON)
+ lsb = PAGE_SHIFT;
+ else
+ show_signal_msg(regs, code, address, tsk, vma);
+ si.si_addr_lsb = lsb;
+
si.si_errno = 0;
si.si_addr = (void __user *) address;
force_sig_info(si.si_signo, &si, current);
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQUENCER_OSS=m
CONFIG_SND_POWERMAC=m
CONFIG_SND_AOA=m
CONFIG_SND_AOA_FABRIC_LAYOUT=m
# CONFIG_LOGO_LINUX_CLUT224 is not set
CONFIG_SOUND=y
CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=y
CONFIG_SND_PCM_OSS=y
-CONFIG_SND_SEQUENCER_OSS=y
# CONFIG_SND_VERBOSE_PROCFS is not set
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQUENCER_OSS=y
# CONFIG_USB_SUPPORT is not set
CONFIG_RTC_CLASS=y
CONFIG_RTC_DRV_GENERIC=y
CONFIG_LOGO=y
CONFIG_SOUND=y
CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=y
CONFIG_SND_PCM_OSS=y
+CONFIG_SND_SEQUENCER=y
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_USB_AUDIO=y
CONFIG_SND_USB_USX2Y=y
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
CONFIG_SND_DUMMY=m
CONFIG_SND_POWERMAC=m
CONFIG_SND_AOA=m
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
CONFIG_SND_POWERMAC=m
CONFIG_SND_AOA=m
CONFIG_SND_AOA_FABRIC_LAYOUT=m
CONFIG_LOGO=y
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
CONFIG_HID_DRAGONRISE=y
CONFIG_HID_GYRATION=y
CONFIG_HID_TWINHAN=y
# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_SOUND=m
CONFIG_SND=m
-CONFIG_SND_SEQUENCER=m
-CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
-CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_DYNAMIC_MINORS=y
# CONFIG_SND_SUPPORT_OLD_API is not set
CONFIG_SND_VERBOSE_PRINTK=y
CONFIG_SND_DEBUG=y
CONFIG_SND_DEBUG_VERBOSE=y
CONFIG_SND_PCM_XRUN_DEBUG=y
+CONFIG_SND_SEQUENCER=m
+CONFIG_SND_SEQ_DUMMY=m
+CONFIG_SND_SEQUENCER_OSS=m
CONFIG_SND_DUMMY=m
CONFIG_SND_VIRMIDI=m
CONFIG_SND_MTPAV=m
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_SOUND=y
CONFIG_SND=y
-CONFIG_SND_SEQUENCER=y
+CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=y
CONFIG_SND_PCM_OSS=y
-CONFIG_SND_SEQUENCER_OSS=y
# CONFIG_SND_VERBOSE_PROCFS is not set
+CONFIG_SND_SEQUENCER=y
+CONFIG_SND_SEQUENCER_OSS=y
CONFIG_HID_APPLE=m
CONFIG_HID_WACOM=m
CONFIG_MMC=y
} else if ((ret = eeh_ops->init()))
return ret;
+ /* Initialize PHB PEs */
+ list_for_each_entry_safe(hose, tmp, &hose_list, list_node)
+ eeh_dev_phb_init_dynamic(hose);
+
/* Initialize EEH event */
ret = eeh_event_init();
if (ret)
/* EEH PE for PHB */
eeh_phb_pe_create(phb);
}
-
-/**
- * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
- *
- * Scan all the existing PHBs and create EEH devices for their OF
- * nodes and their children OF nodes
- */
-static int __init eeh_dev_phb_init(void)
-{
- struct pci_controller *phb, *tmp;
-
- list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
- eeh_dev_phb_init_dynamic(phb);
-
- return 0;
-}
-
-core_initcall(eeh_dev_phb_init);
* and that can be emulated.
*/
if (!is_conditional_branch(*p->ainsn.insn) &&
- analyse_instr(&op, ®s, *p->ainsn.insn))
+ analyse_instr(&op, ®s, *p->ainsn.insn) == 1) {
+ emulate_update_regs(®s, &op);
nip = regs.nip;
+ }
return nip;
}
* in the appropriate thread structures from live.
*/
- if (tsk != current)
+ if ((!cpu_has_feature(CPU_FTR_TM)) || (tsk != current))
return;
if (MSR_TM_SUSPENDED(mfmsr())) {
int machine_check_e500mc(struct pt_regs *regs)
{
unsigned long mcsr = mfspr(SPRN_MCSR);
+ unsigned long pvr = mfspr(SPRN_PVR);
unsigned long reason = mcsr;
int recoverable = 1;
* may still get logged and cause a machine check. We should
* only treat the non-write shadow case as non-recoverable.
*/
- if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
- recoverable = 0;
+ /* On e6500 core, L1 DCWS (Data cache write shadow mode) bit
+ * is not implemented but L1 data cache always runs in write
+ * shadow mode. Hence on data cache parity errors HW will
+ * automatically invalidate the L1 Data Cache.
+ */
+ if (PVR_VER(pvr) != PVR_VER_E6500) {
+ if (!(mfspr(SPRN_L1CSR2) & L1CSR2_DCWS))
+ recoverable = 0;
+ }
}
if (reason & MCSR_L2MMU_MHIT) {
BEGIN_FTR_SECTION
mtspr SPRN_PPR, r0
END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+
+/* Move canary into DSISR to check for later */
+BEGIN_FTR_SECTION
+ li r0, 0x7fff
+ mtspr SPRN_HDSISR, r0
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+
ld r0, VCPU_GPR(R0)(r4)
ld r4, VCPU_GPR(R4)(r4)
kvmppc_hdsi:
ld r3, VCPU_KVM(r9)
lbz r0, KVM_RADIX(r3)
- cmpwi r0, 0
mfspr r4, SPRN_HDAR
mfspr r6, SPRN_HDSISR
+BEGIN_FTR_SECTION
+ /* Look for DSISR canary. If we find it, retry instruction */
+ cmpdi r6, 0x7fff
+ beq 6f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+ cmpwi r0, 0
bne .Lradix_hdsi /* on radix, just save DAR/DSISR/ASDR */
/* HPTE not found fault or protection fault? */
andis. r0, r6, (DSISR_NOHPTE | DSISR_PROTFAULT)@h
: "r" (addr), "i" (-EFAULT), "0" (err))
static nokprobe_inline void set_cr0(const struct pt_regs *regs,
- struct instruction_op *op, int rd)
+ struct instruction_op *op)
{
- long val = regs->gpr[rd];
+ long val = op->val;
op->type |= SETCC;
op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000);
case 13: /* addic. */
imm = (short) instr;
add_with_carry(regs, op, rd, regs->gpr[ra], imm, 0);
- set_cr0(regs, op, rd);
+ set_cr0(regs, op);
return 1;
case 14: /* addi */
case 28: /* andi. */
op->val = regs->gpr[rd] & (unsigned short) instr;
- set_cr0(regs, op, ra);
+ set_cr0(regs, op);
goto logical_done_nocc;
case 29: /* andis. */
imm = (unsigned short) instr;
op->val = regs->gpr[rd] & (imm << 16);
- set_cr0(regs, op, ra);
+ set_cr0(regs, op);
goto logical_done_nocc;
#ifdef __powerpc64__
op->type = COMPUTE + SETCC;
imm = 0xf0000000UL;
val = regs->gpr[rd];
- op->val = regs->ccr;
+ op->ccval = regs->ccr;
for (sh = 0; sh < 8; ++sh) {
if (instr & (0x80000 >> sh))
- op->val = (op->val & ~imm) |
+ op->ccval = (op->ccval & ~imm) |
(val & imm);
imm >>= 4;
}
goto arith_done;
case 235: /* mullw */
- op->val = (unsigned int) regs->gpr[ra] *
- (unsigned int) regs->gpr[rb];
+ op->val = (long)(int) regs->gpr[ra] *
+ (int) regs->gpr[rb];
+
goto arith_done;
case 266: /* add */
logical_done:
if (instr & 1)
- set_cr0(regs, op, ra);
+ set_cr0(regs, op);
logical_done_nocc:
op->reg = ra;
op->type |= SETREG;
arith_done:
if (instr & 1)
- set_cr0(regs, op, rd);
+ set_cr0(regs, op);
compute_done:
op->reg = rd;
op->type |= SETREG;
u32 pmcs[MAX_HWEVENTS];
int i;
+ if (!ppmu) {
+ pr_info("Performance monitor hardware not registered.\n");
+ return;
+ }
+
if (!ppmu->n_counter)
return;
u64 pir = get_hard_smp_processor_id(cpu);
mtspr(SPRN_LPCR, lpcr_val);
- opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+
+ /*
+ * Program the LPCR via stop-api only if the deepest stop state
+ * can lose hypervisor context.
+ */
+ if (supported_cpuidle_states & OPAL_PM_LOSE_FULL_CONTEXT)
+ opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
}
/*
return rc;
}
- of_node_put(dn->parent);
return 0;
}
}
dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
- of_node_put(parent);
if (!dn) {
pr_warn("Failed call to configure-connector, drc index: %x\n",
drc_index);
dlpar_release_drc(drc_index);
+ of_node_put(parent);
return -EINVAL;
}
rc = dlpar_attach_node(dn, parent);
+
+ /* Regardless we are done with parent now */
+ of_node_put(parent);
+
if (rc) {
saved_rc = rc;
pr_warn("Failed to attach node %s, rc: %d, drc index: %x\n",
return -ENOENT;
dn = dlpar_configure_connector(drc_index, parent_dn);
- if (!dn)
+ if (!dn) {
+ of_node_put(parent_dn);
return -ENOENT;
+ }
rc = dlpar_attach_node(dn, parent_dn);
if (rc)
static inline void pmdp_invalidate(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp)
{
- pmdp_xchg_direct(vma->vm_mm, addr, pmdp, __pmd(_SEGMENT_ENTRY_EMPTY));
+ pmd_t pmd = __pmd(pmd_val(*pmdp) | _SEGMENT_ENTRY_INVALID);
+
+ pmdp_xchg_direct(vma->vm_mm, addr, pmdp, pmd);
}
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
#endif
}
-static int __init topology_setup(char *str)
-{
- bool enabled;
- int rc;
-
- rc = kstrtobool(str, &enabled);
- if (!rc && !enabled)
- S390_lowcore.machine_flags &= ~MACHINE_FLAG_TOPOLOGY;
- return rc;
-}
-early_param("topology", topology_setup);
-
static int __init disable_vector_extension(char *str)
{
S390_lowcore.machine_flags &= ~MACHINE_FLAG_VX;
}
/* Check online status of the CPU to which the event is pinned */
- if ((unsigned int)event->cpu >= nr_cpumask_bits ||
- (event->cpu >= 0 && !cpu_online(event->cpu)))
- return -ENODEV;
+ if (event->cpu >= 0) {
+ if ((unsigned int)event->cpu >= nr_cpumask_bits)
+ return -ENODEV;
+ if (!cpu_online(event->cpu))
+ return -ENODEV;
+ }
/* Force reset of idle/hv excludes regardless of what the
* user requested.
#include <linux/workqueue.h>
#include <linux/bootmem.h>
+#include <linux/uaccess.h>
+#include <linux/sysctl.h>
#include <linux/cpuset.h>
#include <linux/device.h>
#include <linux/export.h>
#define PTF_VERTICAL (1UL)
#define PTF_CHECK (2UL)
+enum {
+ TOPOLOGY_MODE_HW,
+ TOPOLOGY_MODE_SINGLE,
+ TOPOLOGY_MODE_PACKAGE,
+ TOPOLOGY_MODE_UNINITIALIZED
+};
+
struct mask_info {
struct mask_info *next;
unsigned char id;
cpumask_t mask;
};
+static int topology_mode = TOPOLOGY_MODE_UNINITIALIZED;
static void set_topology_timer(void);
static void topology_work_fn(struct work_struct *work);
static struct sysinfo_15_1_x *tl_info;
cpumask_t mask;
cpumask_copy(&mask, cpumask_of(cpu));
- if (!MACHINE_HAS_TOPOLOGY)
- return mask;
- for (; info; info = info->next) {
- if (cpumask_test_cpu(cpu, &info->mask))
- return info->mask;
+ switch (topology_mode) {
+ case TOPOLOGY_MODE_HW:
+ while (info) {
+ if (cpumask_test_cpu(cpu, &info->mask)) {
+ mask = info->mask;
+ break;
+ }
+ info = info->next;
+ }
+ if (cpumask_empty(&mask))
+ cpumask_copy(&mask, cpumask_of(cpu));
+ break;
+ case TOPOLOGY_MODE_PACKAGE:
+ cpumask_copy(&mask, cpu_present_mask);
+ break;
+ default:
+ /* fallthrough */
+ case TOPOLOGY_MODE_SINGLE:
+ cpumask_copy(&mask, cpumask_of(cpu));
+ break;
}
return mask;
}
int i;
cpumask_copy(&mask, cpumask_of(cpu));
- if (!MACHINE_HAS_TOPOLOGY)
+ if (topology_mode != TOPOLOGY_MODE_HW)
return mask;
cpu -= cpu % (smp_cpu_mtid + 1);
for (i = 0; i <= smp_cpu_mtid; i++)
{
int cpu;
- mutex_lock(&smp_cpu_state_mutex);
for_each_possible_cpu(cpu)
smp_cpu_set_polarization(cpu, POLARIZATION_HRZ);
- mutex_unlock(&smp_cpu_state_mutex);
}
static int ptf(unsigned long fc)
static void update_cpu_masks(void)
{
struct cpu_topology_s390 *topo;
- int cpu;
+ int cpu, id;
for_each_possible_cpu(cpu) {
topo = &cpu_topology[cpu];
topo->core_mask = cpu_group_map(&socket_info, cpu);
topo->book_mask = cpu_group_map(&book_info, cpu);
topo->drawer_mask = cpu_group_map(&drawer_info, cpu);
- if (!MACHINE_HAS_TOPOLOGY) {
+ if (topology_mode != TOPOLOGY_MODE_HW) {
+ id = topology_mode == TOPOLOGY_MODE_PACKAGE ? 0 : cpu;
topo->thread_id = cpu;
topo->core_id = cpu;
- topo->socket_id = cpu;
- topo->book_id = cpu;
- topo->drawer_id = cpu;
+ topo->socket_id = id;
+ topo->book_id = id;
+ topo->drawer_id = id;
if (cpu_present(cpu))
cpumask_set_cpu(cpu, &cpus_with_topology);
}
struct sysinfo_15_1_x *info = tl_info;
int rc = 0;
+ mutex_lock(&smp_cpu_state_mutex);
cpumask_clear(&cpus_with_topology);
if (MACHINE_HAS_TOPOLOGY) {
rc = 1;
update_cpu_masks();
if (!MACHINE_HAS_TOPOLOGY)
topology_update_polarization_simple();
+ mutex_unlock(&smp_cpu_state_mutex);
return rc;
}
schedule_work(&topology_work);
}
+static void topology_flush_work(void)
+{
+ flush_work(&topology_work);
+}
+
static void topology_timer_fn(unsigned long ignored)
{
if (ptf(PTF_CHECK))
struct sysinfo_15_1_x *info;
set_sched_topology(s390_topology);
+ if (topology_mode == TOPOLOGY_MODE_UNINITIALIZED) {
+ if (MACHINE_HAS_TOPOLOGY)
+ topology_mode = TOPOLOGY_MODE_HW;
+ else
+ topology_mode = TOPOLOGY_MODE_SINGLE;
+ }
if (!MACHINE_HAS_TOPOLOGY)
goto out;
tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE);
__arch_update_cpu_topology();
}
+static inline int topology_get_mode(int enabled)
+{
+ if (!enabled)
+ return TOPOLOGY_MODE_SINGLE;
+ return MACHINE_HAS_TOPOLOGY ? TOPOLOGY_MODE_HW : TOPOLOGY_MODE_PACKAGE;
+}
+
+static inline int topology_is_enabled(void)
+{
+ return topology_mode != TOPOLOGY_MODE_SINGLE;
+}
+
+static int __init topology_setup(char *str)
+{
+ bool enabled;
+ int rc;
+
+ rc = kstrtobool(str, &enabled);
+ if (rc)
+ return rc;
+ topology_mode = topology_get_mode(enabled);
+ return 0;
+}
+early_param("topology", topology_setup);
+
+static int topology_ctl_handler(struct ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ unsigned int len;
+ int new_mode;
+ char buf[2];
+
+ if (!*lenp || *ppos) {
+ *lenp = 0;
+ return 0;
+ }
+ if (!write) {
+ strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
+ ARRAY_SIZE(buf));
+ len = strnlen(buf, ARRAY_SIZE(buf));
+ if (len > *lenp)
+ len = *lenp;
+ if (copy_to_user(buffer, buf, len))
+ return -EFAULT;
+ goto out;
+ }
+ len = *lenp;
+ if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
+ return -EFAULT;
+ if (buf[0] != '0' && buf[0] != '1')
+ return -EINVAL;
+ mutex_lock(&smp_cpu_state_mutex);
+ new_mode = topology_get_mode(buf[0] == '1');
+ if (topology_mode != new_mode) {
+ topology_mode = new_mode;
+ topology_schedule_update();
+ }
+ mutex_unlock(&smp_cpu_state_mutex);
+ topology_flush_work();
+out:
+ *lenp = len;
+ *ppos += len;
+ return 0;
+}
+
+static struct ctl_table topology_ctl_table[] = {
+ {
+ .procname = "topology",
+ .mode = 0644,
+ .proc_handler = topology_ctl_handler,
+ },
+ { },
+};
+
+static struct ctl_table topology_dir_table[] = {
+ {
+ .procname = "s390",
+ .maxlen = 0,
+ .mode = 0555,
+ .child = topology_ctl_table,
+ },
+ { },
+};
+
static int __init topology_init(void)
{
if (MACHINE_HAS_TOPOLOGY)
set_topology_timer();
else
topology_update_polarization_simple();
+ register_sysctl_table(topology_dir_table);
return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
}
device_initcall(topology_init);
static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
- unsigned long mask, result;
struct page *head, *page;
+ unsigned long mask;
int refs;
- result = write ? 0 : _SEGMENT_ENTRY_PROTECT;
- mask = result | _SEGMENT_ENTRY_INVALID;
- if ((pmd_val(pmd) & mask) != result)
+ mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
+ if ((pmd_val(pmd) & mask) != 0)
return 0;
VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm) do { } while(0)
-#define release_segments(mm) do { } while(0)
-
/*
* FPU lazy state save handling.
*/
/* Free all resources held by a thread. */
extern void release_thread(struct task_struct *);
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm) do { } while (0)
-#define release_segments(mm) do { } while (0)
-#define forget_segments() do { } while (0)
/*
* FPU lazy state save handling.
*/
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=m
CONFIG_CRYPTO_LZO=m
CONFIG_IP_NF_MATCH_TTL=m
CONFIG_IP_NF_FILTER=y
CONFIG_IP_NF_TARGET_REJECT=y
-CONFIG_IP_NF_TARGET_ULOG=m
CONFIG_IP_NF_MANGLE=m
CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_TTL=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_TEA=m
CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_ZLIB=m
CONFIG_CRYPTO_LZO=m
CONFIG_CRC_CCITT=m
CONFIG_CRC7=m
{
char *endp;
unsigned long long maxnodemem;
- long node;
+ unsigned long node;
node = str ? simple_strtoul(str, &endp, 0) : INT_MAX;
if (node >= MAX_NUMNODES || *endp != ':')
{
}
-static inline void mm_copy_segments(struct mm_struct *from_mm,
- struct mm_struct *new_mm)
-{
-}
-
#define init_stack (init_thread_union.stack)
/*
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
};
-static void __init timer_setup(void)
+static void __init um_timer_setup(void)
{
int err;
void __init time_init(void)
{
timer_set_signal_handler();
- late_time_init = timer_setup;
+ late_time_init = um_timer_setup;
}
#define s3 ((16 + 2 + (3 * 256)) * 4)
/* register macros */
-#define CTX %rdi
+#define CTX %r12
#define RIO %rsi
#define RX0 %rax
#define RX2bh %ch
#define RX3bh %dh
-#define RT0 %rbp
+#define RT0 %rdi
#define RT1 %rsi
#define RT2 %r8
#define RT3 %r9
-#define RT0d %ebp
+#define RT0d %edi
#define RT1d %esi
#define RT2d %r8d
#define RT3d %r9d
ENTRY(__blowfish_enc_blk)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
* %rcx: bool, if true: xor output
*/
- movq %rbp, %r11;
+ movq %r12, %r11;
+ movq %rdi, CTX;
movq %rsi, %r10;
movq %rdx, RIO;
round_enc(14);
add_roundkey_enc(16);
- movq %r11, %rbp;
+ movq %r11, %r12;
movq %r10, RIO;
test %cl, %cl;
ENTRY(blowfish_dec_blk)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
- movq %rbp, %r11;
+ movq %r12, %r11;
+ movq %rdi, CTX;
movq %rsi, %r10;
movq %rdx, RIO;
movq %r10, RIO;
write_block();
- movq %r11, %rbp;
+ movq %r11, %r12;
ret;
ENDPROC(blowfish_dec_blk)
ENTRY(__blowfish_enc_blk_4way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
* %rcx: bool, if true: xor output
*/
- pushq %rbp;
+ pushq %r12;
pushq %rbx;
pushq %rcx;
- preload_roundkey_enc(0);
-
+ movq %rdi, CTX
movq %rsi, %r11;
movq %rdx, RIO;
+ preload_roundkey_enc(0);
+
read_block4();
round_enc4(0);
round_enc4(14);
add_preloaded_roundkey4();
- popq %rbp;
+ popq %r12;
movq %r11, RIO;
- test %bpl, %bpl;
+ test %r12b, %r12b;
jnz .L__enc_xor4;
write_block4();
popq %rbx;
- popq %rbp;
+ popq %r12;
ret;
.L__enc_xor4:
xor_block4();
popq %rbx;
- popq %rbp;
+ popq %r12;
ret;
ENDPROC(__blowfish_enc_blk_4way)
ENTRY(blowfish_dec_blk_4way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
- pushq %rbp;
+ pushq %r12;
pushq %rbx;
- preload_roundkey_dec(17);
- movq %rsi, %r11;
+ movq %rdi, CTX;
+ movq %rsi, %r11
movq %rdx, RIO;
+ preload_roundkey_dec(17);
read_block4();
round_dec4(17);
write_block4();
popq %rbx;
- popq %rbp;
+ popq %r12;
ret;
ENDPROC(blowfish_dec_blk_4way)
#define RCD1bh %dh
#define RT0 %rsi
-#define RT1 %rbp
+#define RT1 %r12
#define RT2 %r8
#define RT0d %esi
-#define RT1d %ebp
+#define RT1d %r12d
#define RT2d %r8d
#define RT2bl %r8b
#define RXOR %r9
-#define RRBP %r10
+#define RR12 %r10
#define RDST %r11
#define RXORd %r9d
* %rdx: src
* %rcx: bool xor
*/
- movq %rbp, RRBP;
+ movq %r12, RR12;
movq %rcx, RXOR;
movq %rsi, RDST;
enc_outunpack(mov, RT1);
- movq RRBP, %rbp;
+ movq RR12, %r12;
ret;
.L__enc_xor:
enc_outunpack(xor, RT1);
- movq RRBP, %rbp;
+ movq RR12, %r12;
ret;
ENDPROC(__camellia_enc_blk)
movl $24, RXORd;
cmovel RXORd, RT2d; /* max */
- movq %rbp, RRBP;
+ movq %r12, RR12;
movq %rsi, RDST;
movq %rdx, RIO;
dec_outunpack();
- movq RRBP, %rbp;
+ movq RR12, %r12;
ret;
ENDPROC(camellia_dec_blk)
*/
pushq %rbx;
- movq %rbp, RRBP;
+ movq %r12, RR12;
movq %rcx, RXOR;
movq %rsi, RDST;
movq %rdx, RIO;
enc_outunpack2(mov, RT2);
- movq RRBP, %rbp;
+ movq RR12, %r12;
popq %rbx;
ret;
.L__enc2_xor:
enc_outunpack2(xor, RT2);
- movq RRBP, %rbp;
+ movq RR12, %r12;
popq %rbx;
ret;
ENDPROC(__camellia_enc_blk_2way)
cmovel RXORd, RT2d; /* max */
movq %rbx, RXOR;
- movq %rbp, RRBP;
+ movq %r12, RR12;
movq %rsi, RDST;
movq %rdx, RIO;
dec_outunpack2();
- movq RRBP, %rbp;
+ movq RR12, %r12;
movq RXOR, %rbx;
ret;
ENDPROC(camellia_dec_blk_2way)
/**********************************************************************
16-way AVX cast5
**********************************************************************/
-#define CTX %rdi
+#define CTX %r15
#define RL1 %xmm0
#define RR1 %xmm1
#define RTMP %xmm15
-#define RID1 %rbp
-#define RID1d %ebp
+#define RID1 %rdi
+#define RID1d %edi
#define RID2 %rsi
#define RID2d %esi
.align 16
__cast5_enc_blk16:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RL1: blocks 1 and 2
* RR1: blocks 3 and 4
* RL2: blocks 5 and 6
* RR4: encrypted blocks 15 and 16
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
.L__skip_enc:
popq %rbx;
- popq %rbp;
+ popq %r15;
vmovdqa .Lbswap_mask, RKM;
.align 16
__cast5_dec_blk16:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RL1: encrypted blocks 1 and 2
* RR1: encrypted blocks 3 and 4
* RL2: encrypted blocks 5 and 6
* RR4: decrypted blocks 15 and 16
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
vmovdqa .Lbswap_mask, RKM;
popq %rbx;
- popq %rbp;
+ popq %r15;
outunpack_blocks(RR1, RL1, RTMP, RX, RKM);
outunpack_blocks(RR2, RL2, RTMP, RX, RKM);
ENTRY(cast5_ecb_enc_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
vmovdqu (0*4*4)(%rdx), RL1;
vmovdqu RR4, (6*4*4)(%r11);
vmovdqu RL4, (7*4*4)(%r11);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast5_ecb_enc_16way)
ENTRY(cast5_ecb_dec_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+
+ movq %rdi, CTX;
movq %rsi, %r11;
vmovdqu (0*4*4)(%rdx), RL1;
vmovdqu RR4, (6*4*4)(%r11);
vmovdqu RL4, (7*4*4)(%r11);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast5_ecb_dec_16way)
ENTRY(cast5_cbc_dec_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
vmovdqu RR4, (6*16)(%r11);
vmovdqu RL4, (7*16)(%r11);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast5_cbc_dec_16way)
ENTRY(cast5_ctr_16way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
* %rcx: iv (big endian, 64bit)
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
vmovdqu RR4, (6*16)(%r11);
vmovdqu RL4, (7*16)(%r11);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast5_ctr_16way)
/**********************************************************************
8-way AVX cast6
**********************************************************************/
-#define CTX %rdi
+#define CTX %r15
#define RA1 %xmm0
#define RB1 %xmm1
#define RTMP %xmm15
-#define RID1 %rbp
-#define RID1d %ebp
+#define RID1 %rdi
+#define RID1d %edi
#define RID2 %rsi
#define RID2d %esi
.align 8
__cast6_enc_blk8:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: blocks
* output:
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
QBAR(11);
popq %rbx;
- popq %rbp;
+ popq %r15;
vmovdqa .Lbswap_mask, RKM;
.align 8
__cast6_dec_blk8:
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: encrypted blocks
* output:
* RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2: decrypted blocks
*/
- pushq %rbp;
+ pushq %r15;
pushq %rbx;
+ movq %rdi, CTX;
+
vmovdqa .Lbswap_mask, RKM;
vmovd .Lfirst_mask, R1ST;
vmovd .L32_mask, R32;
QBAR(0);
popq %rbx;
- popq %rbp;
+ popq %r15;
vmovdqa .Lbswap_mask, RKM;
outunpack_blocks(RA1, RB1, RC1, RD1, RTMP, RX, RKRF, RKM);
ENTRY(cast6_ecb_enc_8way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast6_ecb_enc_8way)
ENTRY(cast6_ecb_dec_8way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
load_8way(%rdx, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
store_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast6_ecb_dec_8way)
ENTRY(cast6_cbc_dec_8way)
/* input:
- * %rdi: ctx, CTX
+ * %rdi: ctx
* %rsi: dst
* %rdx: src
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15;
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
store_cbc_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast6_cbc_dec_8way)
* %rcx: iv (little endian, 128bit)
*/
FRAME_BEGIN
-
pushq %r12;
+ pushq %r15
+ movq %rdi, CTX;
movq %rsi, %r11;
movq %rdx, %r12;
store_ctr_8way(%r12, %r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
popq %r12;
-
FRAME_END
ret;
ENDPROC(cast6_ctr_8way)
* %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX
movq %rsi, %r11;
/* regs <= src, dst <= IVs, regs <= regs xor IVs */
/* dst <= regs xor IVs(in dst) */
store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast6_xts_enc_8way)
* %rcx: iv (t ⊕ αⁿ ∈ GF(2¹²⁸))
*/
FRAME_BEGIN
+ pushq %r15;
+ movq %rdi, CTX
movq %rsi, %r11;
/* regs <= src, dst <= IVs, regs <= regs xor IVs */
/* dst <= regs xor IVs(in dst) */
store_xts_8way(%r11, RA1, RB1, RC1, RD1, RA2, RB2, RC2, RD2);
+ popq %r15;
FRAME_END
ret;
ENDPROC(cast6_xts_dec_8way)
#define RW2bh %ch
#define RT0 %r15
-#define RT1 %rbp
+#define RT1 %rsi
#define RT2 %r14
#define RT3 %rdx
#define RT0d %r15d
-#define RT1d %ebp
+#define RT1d %esi
#define RT2d %r14d
#define RT3d %edx
* %rsi: dst
* %rdx: src
*/
- pushq %rbp;
pushq %rbx;
pushq %r12;
pushq %r13;
pushq %r14;
pushq %r15;
+ pushq %rsi; /* dst */
+
read_block(%rdx, RL0, RR0);
initial_permutation(RL0, RR0);
round1(32+15, RL0, RR0, dummy2);
final_permutation(RR0, RL0);
+
+ popq %rsi /* dst */
write_block(%rsi, RR0, RL0);
popq %r15;
popq %r13;
popq %r12;
popq %rbx;
- popq %rbp;
ret;
ENDPROC(des3_ede_x86_64_crypt_blk)
* %rdx: src (3 blocks)
*/
- pushq %rbp;
pushq %rbx;
pushq %r12;
pushq %r13;
pushq %r14;
pushq %r15;
+ pushq %rsi /* dst */
+
/* load input */
movl 0 * 4(%rdx), RL0d;
movl 1 * 4(%rdx), RR0d;
bswapl RR2d;
bswapl RL2d;
+ popq %rsi /* dst */
movl RR0d, 0 * 4(%rsi);
movl RL0d, 1 * 4(%rsi);
movl RR1d, 2 * 4(%rsi);
popq %r13;
popq %r12;
popq %rbx;
- popq %rbp;
ret;
ENDPROC(des3_ede_x86_64_crypt_blk_3way)
#define REG_RE %rdx
#define REG_RTA %r12
#define REG_RTB %rbx
-#define REG_T1 %ebp
+#define REG_T1 %r11d
#define xmm_mov vmovups
#define avx2_zeroupper vzeroupper
#define RND_F1 1
ENTRY(\name)
push %rbx
- push %rbp
push %r12
push %r13
push %r14
pop %r14
pop %r13
pop %r12
- pop %rbp
pop %rbx
ret
#define REG_A %ecx
#define REG_B %esi
#define REG_C %edi
-#define REG_D %ebp
+#define REG_D %r12d
#define REG_E %edx
#define REG_T1 %eax
ENTRY(\name)
push %rbx
- push %rbp
push %r12
+ push %rbp
+ mov %rsp, %rbp
- mov %rsp, %r12
sub $64, %rsp # allocate workspace
and $~15, %rsp # align stack
xor %rax, %rax
rep stosq
- mov %r12, %rsp # deallocate workspace
-
- pop %r12
+ mov %rbp, %rsp # deallocate workspace
pop %rbp
+ pop %r12
pop %rbx
ret
c = %ecx
d = %r8d
e = %edx
-TBL = %rbp
+TBL = %r12
a = %eax
b = %ebx
ENTRY(sha256_transform_avx)
.align 32
pushq %rbx
- pushq %rbp
+ pushq %r12
pushq %r13
pushq %r14
pushq %r15
- pushq %r12
+ pushq %rbp
+ movq %rsp, %rbp
- mov %rsp, %r12
subq $STACK_SIZE, %rsp # allocate stack space
and $~15, %rsp # align stack pointer
done_hash:
- mov %r12, %rsp
-
- popq %r12
+ mov %rbp, %rsp
+ popq %rbp
popq %r15
popq %r14
popq %r13
- popq %rbp
+ popq %r12
popq %rbx
ret
ENDPROC(sha256_transform_avx)
e = %edx # clobbers NUM_BLKS
y3 = %esi # clobbers INP
-
-TBL = %rbp
SRND = CTX # SRND is same register as CTX
a = %eax
ENTRY(sha256_transform_rorx)
.align 32
pushq %rbx
- pushq %rbp
pushq %r12
pushq %r13
pushq %r14
mov CTX, _CTX(%rsp)
loop0:
- lea K256(%rip), TBL
-
## Load first 16 dwords from two blocks
VMOVDQ 0*32(INP),XTMP0
VMOVDQ 1*32(INP),XTMP1
.align 16
loop1:
- vpaddd 0*32(TBL, SRND), X0, XFER
+ vpaddd K256+0*32(SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 0*32
- vpaddd 1*32(TBL, SRND), X0, XFER
+ vpaddd K256+1*32(SRND), X0, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 1*32
- vpaddd 2*32(TBL, SRND), X0, XFER
+ vpaddd K256+2*32(SRND), X0, XFER
vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 2*32
- vpaddd 3*32(TBL, SRND), X0, XFER
+ vpaddd K256+3*32(SRND), X0, XFER
vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
FOUR_ROUNDS_AND_SCHED _XFER + 3*32
loop2:
## Do last 16 rounds with no scheduling
- vpaddd 0*32(TBL, SRND), X0, XFER
+ vpaddd K256+0*32(SRND), X0, XFER
vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 0*32
- vpaddd 1*32(TBL, SRND), X1, XFER
+
+ vpaddd K256+1*32(SRND), X1, XFER
vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
DO_4ROUNDS _XFER + 1*32
add $2*32, SRND
ja done_hash
do_last_block:
- #### do last block
- lea K256(%rip), TBL
-
VMOVDQ 0*16(INP),XWORD0
VMOVDQ 1*16(INP),XWORD1
VMOVDQ 2*16(INP),XWORD2
popq %r14
popq %r13
popq %r12
- popq %rbp
popq %rbx
ret
ENDPROC(sha256_transform_rorx)
c = %ecx
d = %r8d
e = %edx
-TBL = %rbp
+TBL = %r12
a = %eax
b = %ebx
ENTRY(sha256_transform_ssse3)
.align 32
pushq %rbx
- pushq %rbp
+ pushq %r12
pushq %r13
pushq %r14
pushq %r15
- pushq %r12
+ pushq %rbp
+ mov %rsp, %rbp
- mov %rsp, %r12
subq $STACK_SIZE, %rsp
and $~15, %rsp
done_hash:
- mov %r12, %rsp
-
- popq %r12
+ mov %rbp, %rsp
+ popq %rbp
popq %r15
popq %r14
popq %r13
- popq %rbp
+ popq %r12
popq %rbx
ret
BYTE_FLIP_MASK = %ymm9
-# 1st arg
-CTX = %rdi
+# 1st arg is %rdi, which is saved to the stack and accessed later via %r12
+CTX1 = %rdi
+CTX2 = %r12
# 2nd arg
INP = %rsi
# 3rd arg
e = %rdx
y3 = %rsi
-TBL = %rbp
+TBL = %rdi # clobbers CTX1
a = %rax
b = %rbx
h = %r11
old_h = %r11
-T1 = %r12
+T1 = %r12 # clobbers CTX2
y0 = %r13
y1 = %r14
y2 = %r15
-y4 = %r12
-
# Local variables (stack frame)
XFER_SIZE = 4*8
SRND_SIZE = 1*8
INP_SIZE = 1*8
INPEND_SIZE = 1*8
+CTX_SIZE = 1*8
RSPSAVE_SIZE = 1*8
-GPRSAVE_SIZE = 6*8
+GPRSAVE_SIZE = 5*8
frame_XFER = 0
frame_SRND = frame_XFER + XFER_SIZE
frame_INP = frame_SRND + SRND_SIZE
frame_INPEND = frame_INP + INP_SIZE
-frame_RSPSAVE = frame_INPEND + INPEND_SIZE
+frame_CTX = frame_INPEND + INPEND_SIZE
+frame_RSPSAVE = frame_CTX + CTX_SIZE
frame_GPRSAVE = frame_RSPSAVE + RSPSAVE_SIZE
frame_size = frame_GPRSAVE + GPRSAVE_SIZE
mov %rax, frame_RSPSAVE(%rsp)
# Save GPRs
- mov %rbp, frame_GPRSAVE(%rsp)
- mov %rbx, 8*1+frame_GPRSAVE(%rsp)
- mov %r12, 8*2+frame_GPRSAVE(%rsp)
- mov %r13, 8*3+frame_GPRSAVE(%rsp)
- mov %r14, 8*4+frame_GPRSAVE(%rsp)
- mov %r15, 8*5+frame_GPRSAVE(%rsp)
+ mov %rbx, 8*0+frame_GPRSAVE(%rsp)
+ mov %r12, 8*1+frame_GPRSAVE(%rsp)
+ mov %r13, 8*2+frame_GPRSAVE(%rsp)
+ mov %r14, 8*3+frame_GPRSAVE(%rsp)
+ mov %r15, 8*4+frame_GPRSAVE(%rsp)
shl $7, NUM_BLKS # convert to bytes
jz done_hash
mov NUM_BLKS, frame_INPEND(%rsp)
## load initial digest
- mov 8*0(CTX),a
- mov 8*1(CTX),b
- mov 8*2(CTX),c
- mov 8*3(CTX),d
- mov 8*4(CTX),e
- mov 8*5(CTX),f
- mov 8*6(CTX),g
- mov 8*7(CTX),h
+ mov 8*0(CTX1), a
+ mov 8*1(CTX1), b
+ mov 8*2(CTX1), c
+ mov 8*3(CTX1), d
+ mov 8*4(CTX1), e
+ mov 8*5(CTX1), f
+ mov 8*6(CTX1), g
+ mov 8*7(CTX1), h
+
+ # save %rdi (CTX) before it gets clobbered
+ mov %rdi, frame_CTX(%rsp)
vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
subq $1, frame_SRND(%rsp)
jne loop2
- addm 8*0(CTX),a
- addm 8*1(CTX),b
- addm 8*2(CTX),c
- addm 8*3(CTX),d
- addm 8*4(CTX),e
- addm 8*5(CTX),f
- addm 8*6(CTX),g
- addm 8*7(CTX),h
+ mov frame_CTX(%rsp), CTX2
+ addm 8*0(CTX2), a
+ addm 8*1(CTX2), b
+ addm 8*2(CTX2), c
+ addm 8*3(CTX2), d
+ addm 8*4(CTX2), e
+ addm 8*5(CTX2), f
+ addm 8*6(CTX2), g
+ addm 8*7(CTX2), h
mov frame_INP(%rsp), INP
add $128, INP
done_hash:
# Restore GPRs
- mov frame_GPRSAVE(%rsp) ,%rbp
- mov 8*1+frame_GPRSAVE(%rsp) ,%rbx
- mov 8*2+frame_GPRSAVE(%rsp) ,%r12
- mov 8*3+frame_GPRSAVE(%rsp) ,%r13
- mov 8*4+frame_GPRSAVE(%rsp) ,%r14
- mov 8*5+frame_GPRSAVE(%rsp) ,%r15
+ mov 8*0+frame_GPRSAVE(%rsp), %rbx
+ mov 8*1+frame_GPRSAVE(%rsp), %r12
+ mov 8*2+frame_GPRSAVE(%rsp), %r13
+ mov 8*3+frame_GPRSAVE(%rsp), %r14
+ mov 8*4+frame_GPRSAVE(%rsp), %r15
# Restore Stack Pointer
mov frame_RSPSAVE(%rsp), %rsp
#define RT %xmm14
#define RR %xmm15
-#define RID1 %rbp
-#define RID1d %ebp
+#define RID1 %r13
+#define RID1d %r13d
#define RID2 %rsi
#define RID2d %esi
vmovdqu w(CTX), RK1;
- pushq %rbp;
+ pushq %r13;
pushq %rbx;
pushq %rcx;
popq %rcx;
popq %rbx;
- popq %rbp;
+ popq %r13;
outunpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
outunpack_blocks(RC2, RD2, RA2, RB2, RK1, RX0, RY0, RK2);
vmovdqu (w+4*4)(CTX), RK1;
- pushq %rbp;
+ pushq %r13;
pushq %rbx;
inpack_blocks(RC1, RD1, RA1, RB1, RK1, RX0, RY0, RK2);
vmovdqu (w)(CTX), RK1;
popq %rbx;
- popq %rbp;
+ popq %r13;
outunpack_blocks(RA1, RB1, RC1, RD1, RK1, RX0, RY0, RK2);
outunpack_blocks(RA2, RB2, RC2, RD2, RK1, RX0, RY0, RK2);
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT, glm_cstates),
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_DENVERTON, glm_cstates),
+
+ X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GEMINI_LAKE, glm_cstates),
{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_DENVERTON, hsw_rapl_init),
+
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GEMINI_LAKE, hsw_rapl_init),
{},
};
static struct intel_uncore_type skx_uncore_iio = {
.name = "iio",
.num_counters = 4,
- .num_boxes = 5,
+ .num_boxes = 6,
.perf_ctr_bits = 48,
.event_ctl = SKX_IIO0_MSR_PMON_CTL0,
.perf_ctr = SKX_IIO0_MSR_PMON_CTR0,
static struct intel_uncore_type skx_uncore_irp = {
.name = "irp",
.num_counters = 2,
- .num_boxes = 5,
+ .num_boxes = 6,
.perf_ctr_bits = 48,
.event_ctl = SKX_IRP0_MSR_PMON_CTL0,
.perf_ctr = SKX_IRP0_MSR_PMON_CTR0,
case INTEL_FAM6_ATOM_SILVERMONT1:
case INTEL_FAM6_ATOM_SILVERMONT2:
case INTEL_FAM6_ATOM_AIRMONT:
+
+ case INTEL_FAM6_ATOM_GOLDMONT:
+ case INTEL_FAM6_ATOM_DENVERTON:
+
+ case INTEL_FAM6_ATOM_GEMINI_LAKE:
+
+ case INTEL_FAM6_XEON_PHI_KNL:
+ case INTEL_FAM6_XEON_PHI_KNM:
if (idx == PERF_MSR_SMI)
return true;
break;
ksig->ka.sa.sa_restorer)
sp = (unsigned long) ksig->ka.sa.sa_restorer;
- if (fpu->fpstate_active) {
+ if (fpu->initialized) {
unsigned long fx_aligned, math_size;
sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size);
#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \
output, input...) \
{ \
- register void *__sp asm(_ASM_SP); \
asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
"call %P[new2]", feature2) \
- : output, "+r" (__sp) \
+ : output, ASM_CALL_CONSTRAINT \
: [old] "i" (oldfunc), [new1] "i" (newfunc1), \
[new2] "i" (newfunc2), ## input); \
}
# define __ASM_FORM_COMMA(x) " " #x ","
#endif
-#ifdef CONFIG_X86_32
+#ifndef __x86_64__
+/* 32 bit */
# define __ASM_SEL(a,b) __ASM_FORM(a)
# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
#else
+/* 64 bit */
# define __ASM_SEL(a,b) __ASM_FORM(b)
# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
#endif
/* For C file, we already have NOKPROBE_SYMBOL macro */
#endif
+#ifndef __ASSEMBLY__
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction. Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function. If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif
+
#endif /* _ASM_X86_ASM_H */
/*
* High level FPU state handling functions:
*/
-extern void fpu__activate_curr(struct fpu *fpu);
-extern void fpu__activate_fpstate_read(struct fpu *fpu);
-extern void fpu__activate_fpstate_write(struct fpu *fpu);
-extern void fpu__current_fpstate_write_begin(void);
-extern void fpu__current_fpstate_write_end(void);
+extern void fpu__initialize(struct fpu *fpu);
+extern void fpu__prepare_read(struct fpu *fpu);
+extern void fpu__prepare_write(struct fpu *fpu);
extern void fpu__save(struct fpu *fpu);
extern void fpu__restore(struct fpu *fpu);
extern int fpu__restore_sig(void __user *buf, int ia32_frame);
err; \
})
-#define check_insn(insn, output, input...) \
-({ \
- int err; \
+#define kernel_insn(insn, output, input...) \
asm volatile("1:" #insn "\n\t" \
"2:\n" \
- ".section .fixup,\"ax\"\n" \
- "3: movl $-1,%[err]\n" \
- " jmp 2b\n" \
- ".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
- : [err] "=r" (err), output \
- : "0"(0), input); \
- err; \
-})
+ _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_fprestore) \
+ : output : input)
static inline int copy_fregs_to_user(struct fregs_state __user *fx)
{
static inline void copy_kernel_to_fxregs(struct fxregs_state *fx)
{
- int err;
-
if (IS_ENABLED(CONFIG_X86_32)) {
- err = check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+ kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
} else {
if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) {
- err = check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
+ kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
} else {
/* See comment in copy_fxregs_to_kernel() below. */
- err = check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
+ kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx));
}
}
- /* Copying from a kernel buffer to FPU registers should never fail: */
- WARN_ON_FPU(err);
}
static inline int copy_user_to_fxregs(struct fxregs_state __user *fx)
static inline void copy_kernel_to_fregs(struct fregs_state *fx)
{
- int err = check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
-
- WARN_ON_FPU(err);
+ kernel_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
}
static inline int copy_user_to_fregs(struct fregs_state __user *fx)
* Use XRSTORS to restore context if it is enabled. XRSTORS supports compact
* XSAVE area format.
*/
-#define XSTATE_XRESTORE(st, lmask, hmask, err) \
+#define XSTATE_XRESTORE(st, lmask, hmask) \
asm volatile(ALTERNATIVE(XRSTOR, \
XRSTORS, X86_FEATURE_XSAVES) \
"\n" \
- "xor %[err], %[err]\n" \
"3:\n" \
- ".pushsection .fixup,\"ax\"\n" \
- "4: movl $-2, %[err]\n" \
- "jmp 3b\n" \
- ".popsection\n" \
- _ASM_EXTABLE(661b, 4b) \
- : [err] "=r" (err) \
+ _ASM_EXTABLE_HANDLE(661b, 3b, ex_handler_fprestore)\
+ : \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
else
XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
- /* We should never fault when copying from a kernel buffer: */
+ /*
+ * We should never fault when copying from a kernel buffer, and the FPU
+ * state we set at boot time should be valid.
+ */
WARN_ON_FPU(err);
}
u32 hmask = mask >> 32;
int err;
- WARN_ON(!alternatives_patched);
+ WARN_ON_FPU(!alternatives_patched);
XSTATE_XSAVE(xstate, lmask, hmask, err);
{
u32 lmask = mask;
u32 hmask = mask >> 32;
- int err;
-
- XSTATE_XRESTORE(xstate, lmask, hmask, err);
- /* We should never fault when copying from a kernel buffer: */
- WARN_ON_FPU(err);
+ XSTATE_XRESTORE(xstate, lmask, hmask);
}
/*
*/
static inline void fpregs_deactivate(struct fpu *fpu)
{
- WARN_ON_FPU(!fpu->fpregs_active);
-
- fpu->fpregs_active = 0;
this_cpu_write(fpu_fpregs_owner_ctx, NULL);
trace_x86_fpu_regs_deactivated(fpu);
}
static inline void fpregs_activate(struct fpu *fpu)
{
- WARN_ON_FPU(fpu->fpregs_active);
-
- fpu->fpregs_active = 1;
this_cpu_write(fpu_fpregs_owner_ctx, fpu);
trace_x86_fpu_regs_activated(fpu);
}
-/*
- * The question "does this thread have fpu access?"
- * is slightly racy, since preemption could come in
- * and revoke it immediately after the test.
- *
- * However, even in that very unlikely scenario,
- * we can just assume we have FPU access - typically
- * to save the FP state - we'll just take a #NM
- * fault and get the FPU access back.
- */
-static inline int fpregs_active(void)
-{
- return current->thread.fpu.fpregs_active;
-}
-
/*
* FPU state switching for scheduling.
*
static inline void
switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
- if (old_fpu->fpregs_active) {
+ if (old_fpu->initialized) {
if (!copy_fpregs_to_fpstate(old_fpu))
old_fpu->last_cpu = -1;
else
old_fpu->last_cpu = cpu;
/* But leave fpu_fpregs_owner_ctx! */
- old_fpu->fpregs_active = 0;
trace_x86_fpu_regs_deactivated(old_fpu);
} else
old_fpu->last_cpu = -1;
static inline void switch_fpu_finish(struct fpu *new_fpu, int cpu)
{
bool preload = static_cpu_has(X86_FEATURE_FPU) &&
- new_fpu->fpstate_active;
+ new_fpu->initialized;
if (preload) {
if (!fpregs_state_valid(new_fpu, cpu))
struct fpu *fpu = ¤t->thread.fpu;
preempt_disable();
- if (!fpregs_active())
- fpregs_activate(fpu);
+ fpregs_activate(fpu);
preempt_enable();
}
/* Default value for fxregs_state.mxcsr: */
#define MXCSR_DEFAULT 0x1f80
+/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */
+#define MXCSR_AND_FLAGS_SIZE sizeof(u64)
+
/*
* Software based FPU emulation state. This is arbitrary really,
* it matches the x87 format to make it easier to understand:
unsigned int last_cpu;
/*
- * @fpstate_active:
+ * @initialized:
*
- * This flag indicates whether this context is active: if the task
+ * This flag indicates whether this context is initialized: if the task
* is not running then we can restore from this context, if the task
* is running then we should save into this context.
*/
- unsigned char fpstate_active;
-
- /*
- * @fpregs_active:
- *
- * This flag determines whether a given context is actively
- * loaded into the FPU's registers and that those registers
- * represent the task's current FPU state.
- *
- * Note the interaction with fpstate_active:
- *
- * # task does not use the FPU:
- * fpstate_active == 0
- *
- * # task uses the FPU and regs are active:
- * fpstate_active == 1 && fpregs_active == 1
- *
- * # the regs are inactive but still match fpstate:
- * fpstate_active == 1 && fpregs_active == 0 && fpregs_owner == fpu
- *
- * The third state is what we use for the lazy restore optimization
- * on lazy-switching CPUs.
- */
- unsigned char fpregs_active;
+ unsigned char initialized;
/*
* @state:
void *get_xsave_addr(struct xregs_state *xsave, int xstate);
const void *get_xsave_field_ptr(int xstate_field);
int using_compacted_format(void);
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
- void __user *ubuf, struct xregs_state *xsave);
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
- struct xregs_state *xsave);
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset, unsigned int size);
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf);
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf);
+
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+extern int validate_xstate_header(const struct xstate_header *hdr);
+
#endif
return __pkru_allows_pkey(vma_pkey(vma), write);
}
+/*
+ * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
+ * bits. This serves two purposes. It prevents a nasty situation in
+ * which PCID-unaware code saves CR3, loads some other value (with PCID
+ * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
+ * the saved ASID was nonzero. It also means that any bugs involving
+ * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
+ * deterministically.
+ */
+
+static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
+{
+ if (static_cpu_has(X86_FEATURE_PCID)) {
+ VM_WARN_ON_ONCE(asid > 4094);
+ return __sme_pa(mm->pgd) | (asid + 1);
+ } else {
+ VM_WARN_ON_ONCE(asid != 0);
+ return __sme_pa(mm->pgd);
+ }
+}
+
+static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
+{
+ VM_WARN_ON_ONCE(asid > 4094);
+ return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
+}
/*
* This can be used from process context to figure out what the value of
*/
static inline unsigned long __get_current_cr3_fast(void)
{
- unsigned long cr3 = __pa(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd);
-
- if (static_cpu_has(X86_FEATURE_PCID))
- cr3 |= this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+ unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+ this_cpu_read(cpu_tlbstate.loaded_mm_asid));
/* For now, be very restrictive about when this can be called. */
VM_WARN_ON(in_nmi() || preemptible());
u64 input_address = input ? virt_to_phys(input) : 0;
u64 output_address = output ? virt_to_phys(output) : 0;
u64 hv_status;
- register void *__sp asm(_ASM_SP);
#ifdef CONFIG_X86_64
if (!hv_hypercall_pg)
__asm__ __volatile__("mov %4, %%r8\n"
"call *%5"
- : "=a" (hv_status), "+r" (__sp),
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input_address)
: "r" (output_address), "m" (hv_hypercall_pg)
: "cc", "memory", "r8", "r9", "r10", "r11");
__asm__ __volatile__("call *%7"
: "=A" (hv_status),
- "+c" (input_address_lo), "+r" (__sp)
+ "+c" (input_address_lo), ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input_address_hi),
"D"(output_address_hi), "S"(output_address_lo),
static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
{
u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
- register void *__sp asm(_ASM_SP);
#ifdef CONFIG_X86_64
{
__asm__ __volatile__("call *%4"
- : "=a" (hv_status), "+r" (__sp),
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
"+c" (control), "+d" (input1)
: "m" (hv_hypercall_pg)
: "cc", "r8", "r9", "r10", "r11");
__asm__ __volatile__ ("call *%5"
: "=A"(hv_status),
"+c"(input1_lo),
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
: "A" (control),
"b" (input1_hi),
"m" (hv_hypercall_pg)
*/
#ifdef CONFIG_X86_32
#define PVOP_VCALL_ARGS \
- unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; \
- register void *__sp asm("esp")
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
/* [re]ax isn't an arg, but the return val */
#define PVOP_VCALL_ARGS \
unsigned long __edi = __edi, __esi = __esi, \
- __edx = __edx, __ecx = __ecx, __eax = __eax; \
- register void *__sp asm("rsp")
+ __edx = __edx, __ecx = __ecx, __eax = __eax;
+
#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
asm volatile(pre \
paravirt_alt(PARAVIRT_CALL) \
post \
- : call_clbr, "+r" (__sp) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
#ifdef CONFIG_PREEMPT
extern asmlinkage void ___preempt_schedule(void);
-# define __preempt_schedule() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule" : "+r"(__sp)); \
-})
+# define __preempt_schedule() \
+ asm volatile ("call ___preempt_schedule" : ASM_CALL_CONSTRAINT)
extern asmlinkage void preempt_schedule(void);
extern asmlinkage void ___preempt_schedule_notrace(void);
-# define __preempt_schedule_notrace() \
-({ \
- register void *__sp asm(_ASM_SP); \
- asm volatile ("call ___preempt_schedule_notrace" : "+r"(__sp)); \
-})
+# define __preempt_schedule_notrace() \
+ asm volatile ("call ___preempt_schedule_notrace" : ASM_CALL_CONSTRAINT)
+
extern asmlinkage void preempt_schedule_notrace(void);
#endif
* Like all of Linux's memory ordering operations, this is a
* compiler barrier as well.
*/
- register void *__sp asm(_ASM_SP);
-
#ifdef CONFIG_X86_32
asm volatile (
"pushfl\n\t"
"pushl $1f\n\t"
"iret\n\t"
"1:"
- : "+r" (__sp) : : "memory");
+ : ASM_CALL_CONSTRAINT : : "memory");
#else
unsigned int tmp;
"iretq\n\t"
UNWIND_HINT_RESTORE
"1:"
- : "=&r" (tmp), "+r" (__sp) : : "cc", "memory");
+ : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory");
#endif
}
({ \
long tmp; \
struct rw_semaphore* ret; \
- register void *__sp asm(_ASM_SP); \
\
asm volatile("# beginning down_write\n\t" \
LOCK_PREFIX " xadd %1,(%4)\n\t" \
" call " slow_path "\n" \
"1:\n" \
"# ending down_write" \
- : "+m" (sem->count), "=d" (tmp), "=a" (ret), "+r" (__sp) \
+ : "+m" (sem->count), "=d" (tmp), \
+ "=a" (ret), ASM_CALL_CONSTRAINT \
: "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
: "memory", "cc"); \
ret; \
*/
#ifndef __ASSEMBLY__
-static inline unsigned long current_stack_pointer(void)
-{
- unsigned long sp;
-#ifdef CONFIG_X86_64
- asm("mov %%rsp,%0" : "=g" (sp));
-#else
- asm("mov %%esp,%0" : "=g" (sp));
-#endif
- return sp;
-}
-
/*
* Walks up the stack frames to make sure that the specified object is
* entirely contained by a single stack frame.
TP_STRUCT__entry(
__field(struct fpu *, fpu)
- __field(bool, fpregs_active)
- __field(bool, fpstate_active)
+ __field(bool, initialized)
__field(u64, xfeatures)
__field(u64, xcomp_bv)
),
TP_fast_assign(
__entry->fpu = fpu;
- __entry->fpregs_active = fpu->fpregs_active;
- __entry->fpstate_active = fpu->fpstate_active;
+ __entry->initialized = fpu->initialized;
if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
__entry->xfeatures = fpu->state.xsave.header.xfeatures;
__entry->xcomp_bv = fpu->state.xsave.header.xcomp_bv;
}
),
- TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d xfeatures: %llx xcomp_bv: %llx",
+ TP_printk("x86/fpu: %p initialized: %d xfeatures: %llx xcomp_bv: %llx",
__entry->fpu,
- __entry->fpregs_active,
- __entry->fpstate_active,
+ __entry->initialized,
__entry->xfeatures,
__entry->xcomp_bv
)
({ \
int __ret_gu; \
register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
- register void *__sp asm(_ASM_SP); \
__chk_user_ptr(ptr); \
might_fault(); \
asm volatile("call __get_user_%P4" \
- : "=a" (__ret_gu), "=r" (__val_gu), "+r" (__sp) \
+ : "=a" (__ret_gu), "=r" (__val_gu), \
+ ASM_CALL_CONSTRAINT \
: "0" (ptr), "i" (sizeof(*(ptr)))); \
(x) = (__force __typeof__(*(ptr))) __val_gu; \
__builtin_expect(__ret_gu, 0); \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
: "=r" (retval), "=&A"(x) \
- : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \
+ : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
})
register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
- register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; \
- register void *__sp asm(_ASM_SP);
+ register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
-#define __HYPERCALL_0PARAM "=r" (__res), "+r" (__sp)
+#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT
#define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1)
#define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2)
#define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3)
MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
struct desc_struct desc)
{
- u32 *p = (u32 *) &desc;
-
mcl->op = __HYPERVISOR_update_descriptor;
if (sizeof(maddr) == sizeof(long)) {
mcl->args[0] = maddr;
mcl->args[1] = *(unsigned long *)&desc;
} else {
+ u32 *p = (u32 *)&desc;
+
mcl->args[0] = maddr;
mcl->args[1] = maddr >> 32;
mcl->args[2] = *p++;
}
}
+static void init_amd_zn(struct cpuinfo_x86 *c)
+{
+ /*
+ * Fix erratum 1076: CPB feature bit not being set in CPUID. It affects
+ * all up to and including B1.
+ */
+ if (c->x86_model <= 1 && c->x86_mask <= 1)
+ set_cpu_cap(c, X86_FEATURE_CPB);
+}
+
static void init_amd(struct cpuinfo_x86 *c)
{
early_init_amd(c);
case 0x10: init_amd_gh(c); break;
case 0x12: init_amd_ln(c); break;
case 0x15: init_amd_bd(c); break;
+ case 0x17: init_amd_zn(c); break;
}
/* Enable workaround for FXSAVE leak */
void __init check_bugs(void)
{
-#ifdef CONFIG_X86_32
- /*
- * Regardless of whether PCID is enumerated, the SDM says
- * that it can't be enabled in 32-bit mode.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
-#endif
-
identify_boot_cpu();
if (!IS_ENABLED(CONFIG_SMP)) {
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
fpu__init_system(c);
+
+#ifdef CONFIG_X86_32
+ /*
+ * Regardless of whether PCID is enumerated, the SDM says
+ * that it can't be enabled in 32-bit mode.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
+#endif
}
void __init early_cpu_init(void)
kernel_fpu_disable();
- if (fpu->fpregs_active) {
+ if (fpu->initialized) {
/*
* Ignore return value -- we don't care if reg state
* is clobbered.
{
struct fpu *fpu = ¤t->thread.fpu;
- if (fpu->fpregs_active)
+ if (fpu->initialized)
copy_kernel_to_fpregs(&fpu->state);
kernel_fpu_enable();
preempt_disable();
trace_x86_fpu_before_save(fpu);
- if (fpu->fpregs_active) {
+ if (fpu->initialized) {
if (!copy_fpregs_to_fpstate(fpu)) {
copy_kernel_to_fpregs(&fpu->state);
}
int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu)
{
- dst_fpu->fpregs_active = 0;
dst_fpu->last_cpu = -1;
- if (!src_fpu->fpstate_active || !static_cpu_has(X86_FEATURE_FPU))
+ if (!src_fpu->initialized || !static_cpu_has(X86_FEATURE_FPU))
return 0;
WARN_ON_FPU(src_fpu != ¤t->thread.fpu);
/*
* Save current FPU registers directly into the child
* FPU context, without any memory-to-memory copying.
- * In lazy mode, if the FPU context isn't loaded into
- * fpregs, CR0.TS will be set and do_device_not_available
- * will load the FPU context.
*
- * We have to do all this with preemption disabled,
- * mostly because of the FNSAVE case, because in that
- * case we must not allow preemption in the window
- * between the FNSAVE and us marking the context lazy.
- *
- * It shouldn't be an issue as even FNSAVE is plenty
- * fast in terms of critical section length.
+ * ( The function 'fails' in the FNSAVE case, which destroys
+ * register contents so we have to copy them back. )
*/
- preempt_disable();
if (!copy_fpregs_to_fpstate(dst_fpu)) {
- memcpy(&src_fpu->state, &dst_fpu->state,
- fpu_kernel_xstate_size);
-
+ memcpy(&src_fpu->state, &dst_fpu->state, fpu_kernel_xstate_size);
copy_kernel_to_fpregs(&src_fpu->state);
}
- preempt_enable();
trace_x86_fpu_copy_src(src_fpu);
trace_x86_fpu_copy_dst(dst_fpu);
* Activate the current task's in-memory FPU context,
* if it has not been used before:
*/
-void fpu__activate_curr(struct fpu *fpu)
+void fpu__initialize(struct fpu *fpu)
{
WARN_ON_FPU(fpu != ¤t->thread.fpu);
- if (!fpu->fpstate_active) {
+ if (!fpu->initialized) {
fpstate_init(&fpu->state);
trace_x86_fpu_init_state(fpu);
trace_x86_fpu_activate_state(fpu);
/* Safe to do for the current task: */
- fpu->fpstate_active = 1;
+ fpu->initialized = 1;
}
}
-EXPORT_SYMBOL_GPL(fpu__activate_curr);
+EXPORT_SYMBOL_GPL(fpu__initialize);
/*
* This function must be called before we read a task's fpstate.
*
- * If the task has not used the FPU before then initialize its
- * fpstate.
+ * There's two cases where this gets called:
+ *
+ * - for the current task (when coredumping), in which case we have
+ * to save the latest FPU registers into the fpstate,
+ *
+ * - or it's called for stopped tasks (ptrace), in which case the
+ * registers were already saved by the context-switch code when
+ * the task scheduled out - we only have to initialize the registers
+ * if they've never been initialized.
*
* If the task has used the FPU before then save it.
*/
-void fpu__activate_fpstate_read(struct fpu *fpu)
+void fpu__prepare_read(struct fpu *fpu)
{
- /*
- * If fpregs are active (in the current CPU), then
- * copy them to the fpstate:
- */
- if (fpu->fpregs_active) {
+ if (fpu == ¤t->thread.fpu) {
fpu__save(fpu);
} else {
- if (!fpu->fpstate_active) {
+ if (!fpu->initialized) {
fpstate_init(&fpu->state);
trace_x86_fpu_init_state(fpu);
trace_x86_fpu_activate_state(fpu);
/* Safe to do for current and for stopped child tasks: */
- fpu->fpstate_active = 1;
+ fpu->initialized = 1;
}
}
}
/*
* This function must be called before we write a task's fpstate.
*
- * If the task has used the FPU before then unlazy it.
+ * If the task has used the FPU before then invalidate any cached FPU registers.
* If the task has not used the FPU before then initialize its fpstate.
*
* After this function call, after registers in the fpstate are
* modified and the child task has woken up, the child task will
* restore the modified FPU state from the modified context. If we
- * didn't clear its lazy status here then the lazy in-registers
+ * didn't clear its cached status here then the cached in-registers
* state pending on its former CPU could be restored, corrupting
* the modifications.
*/
-void fpu__activate_fpstate_write(struct fpu *fpu)
+void fpu__prepare_write(struct fpu *fpu)
{
/*
* Only stopped child tasks can be used to modify the FPU
*/
WARN_ON_FPU(fpu == ¤t->thread.fpu);
- if (fpu->fpstate_active) {
- /* Invalidate any lazy state: */
+ if (fpu->initialized) {
+ /* Invalidate any cached state: */
__fpu_invalidate_fpregs_state(fpu);
} else {
fpstate_init(&fpu->state);
trace_x86_fpu_activate_state(fpu);
/* Safe to do for stopped child tasks: */
- fpu->fpstate_active = 1;
+ fpu->initialized = 1;
}
}
-/*
- * This function must be called before we write the current
- * task's fpstate.
- *
- * This call gets the current FPU register state and moves
- * it in to the 'fpstate'. Preemption is disabled so that
- * no writes to the 'fpstate' can occur from context
- * swiches.
- *
- * Must be followed by a fpu__current_fpstate_write_end().
- */
-void fpu__current_fpstate_write_begin(void)
-{
- struct fpu *fpu = ¤t->thread.fpu;
-
- /*
- * Ensure that the context-switching code does not write
- * over the fpstate while we are doing our update.
- */
- preempt_disable();
-
- /*
- * Move the fpregs in to the fpu's 'fpstate'.
- */
- fpu__activate_fpstate_read(fpu);
-
- /*
- * The caller is about to write to 'fpu'. Ensure that no
- * CPU thinks that its fpregs match the fpstate. This
- * ensures we will not be lazy and skip a XRSTOR in the
- * future.
- */
- __fpu_invalidate_fpregs_state(fpu);
-}
-
-/*
- * This function must be paired with fpu__current_fpstate_write_begin()
- *
- * This will ensure that the modified fpstate gets placed back in
- * the fpregs if necessary.
- *
- * Note: This function may be called whether or not an _actual_
- * write to the fpstate occurred.
- */
-void fpu__current_fpstate_write_end(void)
-{
- struct fpu *fpu = ¤t->thread.fpu;
-
- /*
- * 'fpu' now has an updated copy of the state, but the
- * registers may still be out of date. Update them with
- * an XRSTOR if they are active.
- */
- if (fpregs_active())
- copy_kernel_to_fpregs(&fpu->state);
-
- /*
- * Our update is done and the fpregs/fpstate are in sync
- * if necessary. Context switches can happen again.
- */
- preempt_enable();
-}
-
/*
* 'fpu__restore()' is called to copy FPU registers from
* the FPU fpstate to the live hw registers and to activate
*/
void fpu__restore(struct fpu *fpu)
{
- fpu__activate_curr(fpu);
+ fpu__initialize(fpu);
/* Avoid __kernel_fpu_begin() right after fpregs_activate() */
kernel_fpu_disable();
{
preempt_disable();
- if (fpu->fpregs_active) {
- /* Ignore delayed exceptions from user space */
- asm volatile("1: fwait\n"
- "2:\n"
- _ASM_EXTABLE(1b, 2b));
- fpregs_deactivate(fpu);
+ if (fpu == ¤t->thread.fpu) {
+ if (fpu->initialized) {
+ /* Ignore delayed exceptions from user space */
+ asm volatile("1: fwait\n"
+ "2:\n"
+ _ASM_EXTABLE(1b, 2b));
+ fpregs_deactivate(fpu);
+ }
}
- fpu->fpstate_active = 0;
+ fpu->initialized = 0;
trace_x86_fpu_dropped(fpu);
* Make sure fpstate is cleared and initialized.
*/
if (static_cpu_has(X86_FEATURE_FPU)) {
- fpu__activate_curr(fpu);
+ preempt_disable();
+ fpu__initialize(fpu);
user_fpu_begin();
copy_init_fpstate_to_fpregs();
+ preempt_enable();
}
}
WARN_ON_FPU(!on_boot_cpu);
on_boot_cpu = 0;
- WARN_ON_FPU(current->thread.fpu.fpstate_active);
+ WARN_ON_FPU(current->thread.fpu.initialized);
}
/*
{
struct fpu *target_fpu = &target->thread.fpu;
- return target_fpu->fpstate_active ? regset->n : 0;
+ return target_fpu->initialized ? regset->n : 0;
}
int regset_xregset_fpregs_active(struct task_struct *target, const struct user_regset *regset)
{
struct fpu *target_fpu = &target->thread.fpu;
- if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->fpstate_active)
+ if (boot_cpu_has(X86_FEATURE_FXSR) && target_fpu->initialized)
return regset->n;
else
return 0;
if (!boot_cpu_has(X86_FEATURE_FXSR))
return -ENODEV;
- fpu__activate_fpstate_read(fpu);
+ fpu__prepare_read(fpu);
fpstate_sanitize_xstate(fpu);
return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
if (!boot_cpu_has(X86_FEATURE_FXSR))
return -ENODEV;
- fpu__activate_fpstate_write(fpu);
+ fpu__prepare_write(fpu);
fpstate_sanitize_xstate(fpu);
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
xsave = &fpu->state.xsave;
- fpu__activate_fpstate_read(fpu);
+ fpu__prepare_read(fpu);
if (using_compacted_format()) {
- ret = copyout_from_xsaves(pos, count, kbuf, ubuf, xsave);
+ if (kbuf)
+ ret = copy_xstate_to_kernel(kbuf, xsave, pos, count);
+ else
+ ret = copy_xstate_to_user(ubuf, xsave, pos, count);
} else {
fpstate_sanitize_xstate(fpu);
/*
xsave = &fpu->state.xsave;
- fpu__activate_fpstate_write(fpu);
+ fpu__prepare_write(fpu);
- if (boot_cpu_has(X86_FEATURE_XSAVES))
- ret = copyin_to_xsaves(kbuf, ubuf, xsave);
- else
+ if (using_compacted_format()) {
+ if (kbuf)
+ ret = copy_kernel_to_xstate(xsave, kbuf);
+ else
+ ret = copy_user_to_xstate(xsave, ubuf);
+ } else {
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1);
-
- /*
- * In case of failure, mark all states as init:
- */
- if (ret)
- fpstate_init(&fpu->state);
+ if (!ret)
+ ret = validate_xstate_header(&xsave->header);
+ }
/*
* mxcsr reserved bits must be masked to zero for security reasons.
*/
xsave->i387.mxcsr &= mxcsr_feature_mask;
- xsave->header.xfeatures &= xfeatures_mask;
+
/*
- * These bits must be zero.
+ * In case of failure, mark all states as init:
*/
- memset(&xsave->header.reserved, 0, 48);
+ if (ret)
+ fpstate_init(&fpu->state);
return ret;
}
struct fpu *fpu = &target->thread.fpu;
struct user_i387_ia32_struct env;
- fpu__activate_fpstate_read(fpu);
+ fpu__prepare_read(fpu);
if (!boot_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_get(target, regset, pos, count, kbuf, ubuf);
struct user_i387_ia32_struct env;
int ret;
- fpu__activate_fpstate_write(fpu);
+ fpu__prepare_write(fpu);
fpstate_sanitize_xstate(fpu);
if (!boot_cpu_has(X86_FEATURE_FPU))
struct fpu *fpu = &tsk->thread.fpu;
int fpvalid;
- fpvalid = fpu->fpstate_active;
+ fpvalid = fpu->initialized;
if (fpvalid)
fpvalid = !fpregs_get(tsk, NULL,
0, sizeof(struct user_i387_ia32_struct),
*/
int copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
{
- struct xregs_state *xsave = ¤t->thread.fpu.state.xsave;
+ struct fpu *fpu = ¤t->thread.fpu;
+ struct xregs_state *xsave = &fpu->state.xsave;
struct task_struct *tsk = current;
int ia32_fxstate = (buf != buf_fx);
sizeof(struct user_i387_ia32_struct), NULL,
(struct _fpstate_32 __user *) buf) ? -1 : 1;
- if (fpregs_active() || using_compacted_format()) {
+ if (fpu->initialized || using_compacted_format()) {
/* Save the live register state to the user directly. */
if (copy_fpregs_to_sigframe(buf_fx))
return -1;
/* Update the thread's fxstate to save the fsave header. */
if (ia32_fxstate)
- copy_fxregs_to_kernel(&tsk->thread.fpu);
+ copy_fxregs_to_kernel(fpu);
} else {
/*
* It is a *bug* if kernel uses compacted-format for xsave
return -1;
}
- fpstate_sanitize_xstate(&tsk->thread.fpu);
+ fpstate_sanitize_xstate(fpu);
if (__copy_to_user(buf_fx, xsave, fpu_user_xstate_size))
return -1;
}
struct xstate_header *header = &xsave->header;
if (use_xsave()) {
- /* These bits must be zero. */
- memset(header->reserved, 0, 48);
+ /*
+ * Note: we don't need to zero the reserved bits in the
+ * xstate_header here because we either didn't copy them at all,
+ * or we checked earlier that they aren't set.
+ */
/*
* Init the state that is not present in the memory
if (fx_only)
header->xfeatures = XFEATURE_MASK_FPSSE;
else
- header->xfeatures &= (xfeatures_mask & xfeatures);
+ header->xfeatures &= xfeatures;
}
if (use_fxsr()) {
if (!access_ok(VERIFY_READ, buf, size))
return -EACCES;
- fpu__activate_curr(fpu);
+ fpu__initialize(fpu);
if (!static_cpu_has(X86_FEATURE_FPU))
return fpregs_soft_set(current, NULL,
/*
* For 32-bit frames with fxstate, copy the user state to the
* thread's fpu state, reconstruct fxstate from the fsave
- * header. Sanitize the copied state etc.
+ * header. Validate and sanitize the copied state.
*/
struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
/*
- * Drop the current fpu which clears fpu->fpstate_active. This ensures
+ * Drop the current fpu which clears fpu->initialized. This ensures
* that any context-switch during the copy of the new state,
* avoids the intermediate state from getting restored/saved.
* Thus avoiding the new restored state from getting corrupted.
* We will be ready to restore/save the state only after
- * fpu->fpstate_active is again set.
+ * fpu->initialized is again set.
*/
fpu__drop(fpu);
if (using_compacted_format()) {
- err = copyin_to_xsaves(NULL, buf_fx,
- &fpu->state.xsave);
+ err = copy_user_to_xstate(&fpu->state.xsave, buf_fx);
} else {
- err = __copy_from_user(&fpu->state.xsave,
- buf_fx, state_size);
+ err = __copy_from_user(&fpu->state.xsave, buf_fx, state_size);
+
+ if (!err && state_size > offsetof(struct xregs_state, header))
+ err = validate_xstate_header(&fpu->state.xsave.header);
}
if (err || __copy_from_user(&env, buf, sizeof(env))) {
sanitize_restored_xstate(tsk, &env, xfeatures, fx_only);
}
- fpu->fpstate_active = 1;
+ fpu->initialized = 1;
preempt_disable();
fpu__restore(fpu);
preempt_enable();
return boot_cpu_has(X86_FEATURE_XSAVES);
}
+/* Validate an xstate header supplied by userspace (ptrace or sigreturn) */
+int validate_xstate_header(const struct xstate_header *hdr)
+{
+ /* No unknown or supervisor features may be set */
+ if (hdr->xfeatures & (~xfeatures_mask | XFEATURE_MASK_SUPERVISOR))
+ return -EINVAL;
+
+ /* Userspace must use the uncompacted format */
+ if (hdr->xcomp_bv)
+ return -EINVAL;
+
+ /*
+ * If 'reserved' is shrunken to add a new field, make sure to validate
+ * that new field here!
+ */
+ BUILD_BUG_ON(sizeof(hdr->reserved) != 48);
+
+ /* No reserved bits may be set */
+ if (memchr_inv(hdr->reserved, 0, sizeof(hdr->reserved)))
+ return -EINVAL;
+
+ return 0;
+}
+
static void __xstate_dump_leaves(void)
{
int i;
{
struct fpu *fpu = ¤t->thread.fpu;
- if (!fpu->fpstate_active)
+ if (!fpu->initialized)
return NULL;
/*
* fpu__save() takes the CPU's xstate registers
}
#endif /* ! CONFIG_ARCH_HAS_PKEYS */
+/*
+ * Weird legacy quirk: SSE and YMM states store information in the
+ * MXCSR and MXCSR_FLAGS fields of the FP area. That means if the FP
+ * area is marked as unused in the xfeatures header, we need to copy
+ * MXCSR and MXCSR_FLAGS if either SSE or YMM are in use.
+ */
+static inline bool xfeatures_mxcsr_quirk(u64 xfeatures)
+{
+ if (!(xfeatures & (XFEATURE_MASK_SSE|XFEATURE_MASK_YMM)))
+ return false;
+
+ if (xfeatures & XFEATURE_MASK_FP)
+ return false;
+
+ return true;
+}
+
/*
* This is similar to user_regset_copyout(), but will not add offset to
* the source data pointer or increment pos, count, kbuf, and ubuf.
*/
-static inline int xstate_copyout(unsigned int pos, unsigned int count,
- void *kbuf, void __user *ubuf,
- const void *data, const int start_pos,
- const int end_pos)
+static inline void
+__copy_xstate_to_kernel(void *kbuf, const void *data,
+ unsigned int offset, unsigned int size, unsigned int size_total)
{
- if ((count == 0) || (pos < start_pos))
- return 0;
+ if (offset < size_total) {
+ unsigned int copy = min(size, size_total - offset);
- if (end_pos < 0 || pos < end_pos) {
- unsigned int copy = (end_pos < 0 ? count : min(count, end_pos - pos));
+ memcpy(kbuf + offset, data, copy);
+ }
+}
- if (kbuf) {
- memcpy(kbuf + pos, data, copy);
- } else {
- if (__copy_to_user(ubuf + pos, data, copy))
- return -EFAULT;
+/*
+ * Convert from kernel XSAVES compacted format to standard format and copy
+ * to a kernel-space ptrace buffer.
+ *
+ * It supports partial copy but pos always starts from zero. This is called
+ * from xstateregs_get() and there we check the CPU has XSAVES.
+ */
+int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
+{
+ unsigned int offset, size;
+ struct xstate_header header;
+ int i;
+
+ /*
+ * Currently copy_regset_to_user() starts from pos 0:
+ */
+ if (unlikely(offset_start != 0))
+ return -EFAULT;
+
+ /*
+ * The destination is a ptrace buffer; we put in only user xstates:
+ */
+ memset(&header, 0, sizeof(header));
+ header.xfeatures = xsave->header.xfeatures;
+ header.xfeatures &= ~XFEATURE_MASK_SUPERVISOR;
+
+ /*
+ * Copy xregs_state->header:
+ */
+ offset = offsetof(struct xregs_state, header);
+ size = sizeof(header);
+
+ __copy_xstate_to_kernel(kbuf, &header, offset, size, size_total);
+
+ for (i = 0; i < XFEATURE_MAX; i++) {
+ /*
+ * Copy only in-use xstates:
+ */
+ if ((header.xfeatures >> i) & 1) {
+ void *src = __raw_xsave_addr(xsave, 1 << i);
+
+ offset = xstate_offsets[i];
+ size = xstate_sizes[i];
+
+ /* The next component has to fit fully into the output buffer: */
+ if (offset + size > size_total)
+ break;
+
+ __copy_xstate_to_kernel(kbuf, src, offset, size, size_total);
}
+
+ }
+
+ if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+ offset = offsetof(struct fxregs_state, mxcsr);
+ size = MXCSR_AND_FLAGS_SIZE;
+ __copy_xstate_to_kernel(kbuf, &xsave->i387.mxcsr, offset, size, size_total);
+ }
+
+ /*
+ * Fill xsave->i387.sw_reserved value for ptrace frame:
+ */
+ offset = offsetof(struct fxregs_state, sw_reserved);
+ size = sizeof(xstate_fx_sw_bytes);
+
+ __copy_xstate_to_kernel(kbuf, xstate_fx_sw_bytes, offset, size, size_total);
+
+ return 0;
+}
+
+static inline int
+__copy_xstate_to_user(void __user *ubuf, const void *data, unsigned int offset, unsigned int size, unsigned int size_total)
+{
+ if (!size)
+ return 0;
+
+ if (offset < size_total) {
+ unsigned int copy = min(size, size_total - offset);
+
+ if (__copy_to_user(ubuf + offset, data, copy))
+ return -EFAULT;
}
return 0;
}
/*
* Convert from kernel XSAVES compacted format to standard format and copy
- * to a ptrace buffer. It supports partial copy but pos always starts from
+ * to a user-space buffer. It supports partial copy but pos always starts from
* zero. This is called from xstateregs_get() and there we check the CPU
* has XSAVES.
*/
-int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
- void __user *ubuf, struct xregs_state *xsave)
+int copy_xstate_to_user(void __user *ubuf, struct xregs_state *xsave, unsigned int offset_start, unsigned int size_total)
{
unsigned int offset, size;
int ret, i;
/*
* Currently copy_regset_to_user() starts from pos 0:
*/
- if (unlikely(pos != 0))
+ if (unlikely(offset_start != 0))
return -EFAULT;
/*
offset = offsetof(struct xregs_state, header);
size = sizeof(header);
- ret = xstate_copyout(offset, size, kbuf, ubuf, &header, 0, count);
-
+ ret = __copy_xstate_to_user(ubuf, &header, offset, size, size_total);
if (ret)
return ret;
offset = xstate_offsets[i];
size = xstate_sizes[i];
- ret = xstate_copyout(offset, size, kbuf, ubuf, src, 0, count);
+ /* The next component has to fit fully into the output buffer: */
+ if (offset + size > size_total)
+ break;
+ ret = __copy_xstate_to_user(ubuf, src, offset, size, size_total);
if (ret)
return ret;
-
- if (offset + size >= count)
- break;
}
}
+ if (xfeatures_mxcsr_quirk(header.xfeatures)) {
+ offset = offsetof(struct fxregs_state, mxcsr);
+ size = MXCSR_AND_FLAGS_SIZE;
+ __copy_xstate_to_user(ubuf, &xsave->i387.mxcsr, offset, size, size_total);
+ }
+
/*
* Fill xsave->i387.sw_reserved value for ptrace frame:
*/
offset = offsetof(struct fxregs_state, sw_reserved);
size = sizeof(xstate_fx_sw_bytes);
- ret = xstate_copyout(offset, size, kbuf, ubuf, xstate_fx_sw_bytes, 0, count);
-
+ ret = __copy_xstate_to_user(ubuf, xstate_fx_sw_bytes, offset, size, size_total);
if (ret)
return ret;
}
/*
- * Convert from a ptrace standard-format buffer to kernel XSAVES format
- * and copy to the target thread. This is called from xstateregs_set() and
- * there we check the CPU has XSAVES and a whole standard-sized buffer
- * exists.
+ * Convert from a ptrace standard-format kernel buffer to kernel XSAVES format
+ * and copy to the target thread. This is called from xstateregs_set().
*/
-int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
- struct xregs_state *xsave)
+int copy_kernel_to_xstate(struct xregs_state *xsave, const void *kbuf)
{
unsigned int offset, size;
int i;
- u64 xfeatures;
- u64 allowed_features;
+ struct xstate_header hdr;
offset = offsetof(struct xregs_state, header);
- size = sizeof(xfeatures);
+ size = sizeof(hdr);
- if (kbuf) {
- memcpy(&xfeatures, kbuf + offset, size);
- } else {
- if (__copy_from_user(&xfeatures, ubuf + offset, size))
- return -EFAULT;
+ memcpy(&hdr, kbuf + offset, size);
+
+ if (validate_xstate_header(&hdr))
+ return -EINVAL;
+
+ for (i = 0; i < XFEATURE_MAX; i++) {
+ u64 mask = ((u64)1 << i);
+
+ if (hdr.xfeatures & mask) {
+ void *dst = __raw_xsave_addr(xsave, 1 << i);
+
+ offset = xstate_offsets[i];
+ size = xstate_sizes[i];
+
+ memcpy(dst, kbuf + offset, size);
+ }
+ }
+
+ if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+ offset = offsetof(struct fxregs_state, mxcsr);
+ size = MXCSR_AND_FLAGS_SIZE;
+ memcpy(&xsave->i387.mxcsr, kbuf + offset, size);
}
/*
- * Reject if the user sets any disabled or supervisor features:
+ * The state that came in from userspace was user-state only.
+ * Mask all the user states out of 'xfeatures':
+ */
+ xsave->header.xfeatures &= XFEATURE_MASK_SUPERVISOR;
+
+ /*
+ * Add back in the features that came in from userspace:
*/
- allowed_features = xfeatures_mask & ~XFEATURE_MASK_SUPERVISOR;
+ xsave->header.xfeatures |= hdr.xfeatures;
- if (xfeatures & ~allowed_features)
+ return 0;
+}
+
+/*
+ * Convert from a ptrace or sigreturn standard-format user-space buffer to
+ * kernel XSAVES format and copy to the target thread. This is called from
+ * xstateregs_set(), as well as potentially from the sigreturn() and
+ * rt_sigreturn() system calls.
+ */
+int copy_user_to_xstate(struct xregs_state *xsave, const void __user *ubuf)
+{
+ unsigned int offset, size;
+ int i;
+ struct xstate_header hdr;
+
+ offset = offsetof(struct xregs_state, header);
+ size = sizeof(hdr);
+
+ if (__copy_from_user(&hdr, ubuf + offset, size))
+ return -EFAULT;
+
+ if (validate_xstate_header(&hdr))
return -EINVAL;
for (i = 0; i < XFEATURE_MAX; i++) {
u64 mask = ((u64)1 << i);
- if (xfeatures & mask) {
+ if (hdr.xfeatures & mask) {
void *dst = __raw_xsave_addr(xsave, 1 << i);
offset = xstate_offsets[i];
size = xstate_sizes[i];
- if (kbuf) {
- memcpy(dst, kbuf + offset, size);
- } else {
- if (__copy_from_user(dst, ubuf + offset, size))
- return -EFAULT;
- }
+ if (__copy_from_user(dst, ubuf + offset, size))
+ return -EFAULT;
}
}
+ if (xfeatures_mxcsr_quirk(hdr.xfeatures)) {
+ offset = offsetof(struct fxregs_state, mxcsr);
+ size = MXCSR_AND_FLAGS_SIZE;
+ if (__copy_from_user(&xsave->i387.mxcsr, ubuf + offset, size))
+ return -EFAULT;
+ }
+
/*
* The state that came in from userspace was user-state only.
* Mask all the user states out of 'xfeatures':
/*
* Add back in the features that came in from userspace:
*/
- xsave->header.xfeatures |= xfeatures;
+ xsave->header.xfeatures |= hdr.xfeatures;
return 0;
}
static inline void *current_stack(void)
{
- return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+ return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
}
static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
/* Save the next esp at the bottom of the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer();
+ *prev_esp = current_stack_pointer;
if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
/* Push the previous esp onto the stack */
prev_esp = (u32 *)irqstk;
- *prev_esp = current_stack_pointer();
+ *prev_esp = current_stack_pointer;
call_on_stack(__do_softirq, isp);
}
return 0;
out_clean_nodes:
- for (j = i - 1; j > 0; j--)
+ for (j = i - 1; j >= 0; j--)
cleanup_setup_data_node(*(kobjp + j));
kfree(kobjp);
out_setup_data_kobj:
n.token = token;
n.cpu = smp_processor_id();
- n.halted = is_idle_task(current) || preempt_count() > 1;
+ n.halted = is_idle_task(current) || preempt_count() > 1 ||
+ rcu_preempt_depth();
init_swait_queue_head(&n.wq);
hlist_add_head(&n.link, &b->list);
raw_spin_unlock(&b->lock);
sp = (unsigned long) ka->sa.sa_restorer;
}
- if (fpu->fpstate_active) {
+ if (fpu->initialized) {
sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32),
&buf_fx, &math_size);
*fpstate = (void __user *)sp;
return (void __user *)-1L;
/* save i387 and extended state */
- if (fpu->fpstate_active &&
+ if (fpu->initialized &&
copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size) < 0)
return (void __user *)-1L;
/*
* Ensure the signal handler starts with the new fpu state.
*/
- if (fpu->fpstate_active)
+ if (fpu->initialized)
fpu__clear(fpu);
}
signal_setup_done(failed, ksig, stepping);
*/
if (boot_cpu_has(X86_FEATURE_PCID))
__write_cr4(__read_cr4() | X86_CR4_PCIDE);
- cpu_init();
- x86_cpuinit.early_percpu_clock_init();
- preempt_disable();
- smp_callin();
-
- enable_start_cpu0 = 0;
#ifdef CONFIG_X86_32
/* switch away from the initial page table */
__flush_tlb_all();
#endif
+ cpu_init();
+ x86_cpuinit.early_percpu_clock_init();
+ preempt_disable();
+ smp_callin();
+
+ enable_start_cpu0 = 0;
+
/* otherwise gcc will move up smp_processor_id before the cpu_init */
barrier();
/*
* from double_fault.
*/
BUG_ON((unsigned long)(current_top_of_stack() -
- current_stack_pointer()) >= THREAD_SIZE);
+ current_stack_pointer) >= THREAD_SIZE);
preempt_enable_no_resched();
}
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (efer & EFER_LMA) {
u64 maxphyaddr;
- u32 eax = 0x80000008;
+ u32 eax, ebx, ecx, edx;
- if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL,
- NULL, false))
+ eax = 0x80000008;
+ ecx = 0;
+ if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx,
+ &edx, false))
maxphyaddr = eax & 0xff;
else
maxphyaddr = 36;
static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *))
{
- register void *__sp asm(_ASM_SP);
ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF;
if (!(ctxt->d & ByteOp))
asm("push %[flags]; popf; call *%[fastop]; pushf; pop %[flags]\n"
: "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags),
- [fastop]"+S"(fop), "+r"(__sp)
+ [fastop]"+S"(fop), ASM_CALL_CONSTRAINT
: "c"(ctxt->src2.val));
ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK);
int cpu;
bool launched;
bool nmi_known_unmasked;
+ unsigned long vmcs_host_cr3; /* May not match real cr3 */
+ unsigned long vmcs_host_cr4; /* May not match real cr4 */
struct list_head loaded_vmcss_on_cpu_link;
};
int gs_ldt_reload_needed;
int fs_reload_needed;
u64 msr_host_bndcfgs;
- unsigned long vmcs_host_cr3; /* May not match real cr3 */
- unsigned long vmcs_host_cr4; /* May not match real cr4 */
} host_state;
struct {
int vm86_active;
struct pi_desc old, new;
unsigned int dest;
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ /*
+ * In case of hot-plug or hot-unplug, we may have to undo
+ * vmx_vcpu_pi_put even if there is no assigned device. And we
+ * always keep PI.NDST up to date for simplicity: it makes the
+ * code easier, and CPU migration is not a fast path.
+ */
+ if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+ return;
+
+ /*
+ * First handle the simple case where no cmpxchg is necessary; just
+ * allow posting non-urgent interrupts.
+ *
+ * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+ * PI.NDST: pi_post_block will do it for us and the wakeup_handler
+ * expects the VCPU to be on the blocked_vcpu_list that matches
+ * PI.NDST.
+ */
+ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
+ vcpu->cpu == cpu) {
+ pi_clear_sn(pi_desc);
return;
+ }
+ /* The full case. */
do {
old.control = new.control = pi_desc->control;
- /*
- * If 'nv' field is POSTED_INTR_WAKEUP_VECTOR, there
- * are two possible cases:
- * 1. After running 'pre_block', context switch
- * happened. For this case, 'sn' was set in
- * vmx_vcpu_put(), so we need to clear it here.
- * 2. After running 'pre_block', we were blocked,
- * and woken up by some other guy. For this case,
- * we don't need to do anything, 'pi_post_block'
- * will do everything for us. However, we cannot
- * check whether it is case #1 or case #2 here
- * (maybe, not needed), so we also clear sn here,
- * I think it is not a big deal.
- */
- if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR) {
- if (vcpu->cpu != cpu) {
- dest = cpu_physical_id(cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
- }
+ dest = cpu_physical_id(cpu);
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- }
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
- /* Allow posting non-urgent interrupts */
new.sn = 0;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
}
static void decache_tsc_multiplier(struct vcpu_vmx *vmx)
int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
if (vcpu->mode == IN_GUEST_MODE) {
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
/*
- * Currently, we don't support urgent interrupt,
- * all interrupts are recognized as non-urgent
- * interrupt, so we cannot post interrupts when
- * 'SN' is set.
+ * The vector of interrupt to be delivered to vcpu had
+ * been set in PIR before this function.
+ *
+ * Following cases will be reached in this block, and
+ * we always send a notification event in all cases as
+ * explained below.
+ *
+ * Case 1: vcpu keeps in non-root mode. Sending a
+ * notification event posts the interrupt to vcpu.
*
- * If the vcpu is in guest mode, it means it is
- * running instead of being scheduled out and
- * waiting in the run queue, and that's the only
- * case when 'SN' is set currently, warning if
- * 'SN' is set.
+ * Case 2: vcpu exits to root mode and is still
+ * runnable. PIR will be synced to vIRR before the
+ * next vcpu entry. Sending a notification event in
+ * this case has no effect, as vcpu is not in root
+ * mode.
+ *
+ * Case 3: vcpu exits to root mode and is blocked.
+ * vcpu_block() has already synced PIR to vIRR and
+ * never blocks vcpu if vIRR is not cleared. Therefore,
+ * a blocked vcpu here does not wait for any requested
+ * interrupts in PIR, and sending a notification event
+ * which has no effect is safe here.
*/
- WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
return true;
*/
cr3 = __read_cr3();
vmcs_writel(HOST_CR3, cr3); /* 22.2.3 FIXME: shadow tables */
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
/* Save the most likely value for this task's CR4 in the VMCS. */
cr4 = cr4_read_shadow();
vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
#ifdef CONFIG_X86_64
static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
{
u32 exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- register void *__sp asm(_ASM_SP);
if ((exit_intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK))
== (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR)) {
#ifdef CONFIG_X86_64
[sp]"=&r"(tmp),
#endif
- "+r"(__sp)
+ ASM_CALL_CONSTRAINT
:
[entry]"r"(entry),
[ss]"i"(__KERNEL_DS),
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
cr3 = __get_current_cr3_fast();
- if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+ if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
vmcs_writel(HOST_CR3, cr3);
- vmx->host_state.vmcs_host_cr3 = cr3;
+ vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
}
cr4 = cr4_read_shadow();
- if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+ if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
vmcs_writel(HOST_CR4, cr4);
- vmx->host_state.vmcs_host_cr4 = cr4;
+ vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
}
/* When single-stepping over STI and MOV SS, we must clear the
vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+ /*
+ * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+ * or POSTED_INTR_WAKEUP_VECTOR.
+ */
+ vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+ vmx->pi_desc.sn = 1;
+
return &vmx->vcpu;
free_vmcs:
WARN_ON(!is_guest_mode(vcpu));
- if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code)) {
+ if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+ !to_vmx(vcpu)->nested.nested_run_pending) {
vmcs12->vm_exit_intr_error_code = fault->error_code;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
}
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+ struct pi_desc old, new;
+ unsigned int dest;
+
+ do {
+ old.control = new.control = pi_desc->control;
+ WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+ "Wakeup handler not enabled while the VCPU is blocked\n");
+
+ dest = cpu_physical_id(vcpu->cpu);
+
+ if (x2apic_enabled())
+ new.ndst = dest;
+ else
+ new.ndst = (dest << 8) & 0xFF00;
+
+ /* set 'NV' to 'notification vector' */
+ new.nv = POSTED_INTR_VECTOR;
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
+
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_del(&vcpu->blocked_vcpu_list);
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ vcpu->pre_pcpu = -1;
+ }
+}
+
/*
* This routine does the following things for vCPU which is going
* to be blocked if VT-d PI is enabled.
*/
static int pi_pre_block(struct kvm_vcpu *vcpu)
{
- unsigned long flags;
unsigned int dest;
struct pi_desc old, new;
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
!kvm_vcpu_apicv_active(vcpu))
return 0;
- vcpu->pre_pcpu = vcpu->cpu;
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_add_tail(&vcpu->blocked_vcpu_list,
- &per_cpu(blocked_vcpu_on_cpu,
- vcpu->pre_pcpu));
- spin_unlock_irqrestore(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+ vcpu->pre_pcpu = vcpu->cpu;
+ spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ list_add_tail(&vcpu->blocked_vcpu_list,
+ &per_cpu(blocked_vcpu_on_cpu,
+ vcpu->pre_pcpu));
+ spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+ }
do {
old.control = new.control = pi_desc->control;
- /*
- * We should not block the vCPU if
- * an interrupt is posted for it.
- */
- if (pi_test_on(pi_desc) == 1) {
- spin_lock_irqsave(&per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
-
- return 1;
- }
-
WARN((pi_desc->sn == 1),
"Warning: SN field of posted-interrupts "
"is set before blocking\n");
/* set 'NV' to 'wakeup vector' */
new.nv = POSTED_INTR_WAKEUP_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
+ } while (cmpxchg64(&pi_desc->control, old.control,
+ new.control) != old.control);
- return 0;
+ /* We should not block the vCPU if an interrupt is posted for it. */
+ if (pi_test_on(pi_desc) == 1)
+ __pi_post_block(vcpu);
+
+ local_irq_enable();
+ return (vcpu->pre_pcpu == -1);
}
static int vmx_pre_block(struct kvm_vcpu *vcpu)
static void pi_post_block(struct kvm_vcpu *vcpu)
{
- struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct pi_desc old, new;
- unsigned int dest;
- unsigned long flags;
-
- if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
- !irq_remapping_cap(IRQ_POSTING_CAP) ||
- !kvm_vcpu_apicv_active(vcpu))
+ if (vcpu->pre_pcpu == -1)
return;
- do {
- old.control = new.control = pi_desc->control;
-
- dest = cpu_physical_id(vcpu->cpu);
-
- if (x2apic_enabled())
- new.ndst = dest;
- else
- new.ndst = (dest << 8) & 0xFF00;
-
- /* Allow posting non-urgent interrupts */
- new.sn = 0;
-
- /* set 'NV' to 'notification vector' */
- new.nv = POSTED_INTR_VECTOR;
- } while (cmpxchg(&pi_desc->control, old.control,
- new.control) != old.control);
-
- if(vcpu->pre_pcpu != -1) {
- spin_lock_irqsave(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- list_del(&vcpu->blocked_vcpu_list);
- spin_unlock_irqrestore(
- &per_cpu(blocked_vcpu_on_cpu_lock,
- vcpu->pre_pcpu), flags);
- vcpu->pre_pcpu = -1;
- }
+ WARN_ON(irqs_disabled());
+ local_irq_disable();
+ __pi_post_block(vcpu);
+ local_irq_enable();
}
static void vmx_post_block(struct kvm_vcpu *vcpu)
if (set)
ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- else {
- /* suppress notification event before unposting */
- pi_set_sn(vcpu_to_pi_desc(vcpu));
+ else
ret = irq_set_vcpu_affinity(host_irq, NULL);
- pi_clear_sn(vcpu_to_pi_desc(vcpu));
- }
if (ret < 0) {
printk(KERN_INFO "%s: failed to update PI IRTE\n",
int r;
sigset_t sigsaved;
- fpu__activate_curr(fpu);
+ fpu__initialize(fpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
struct desc_struct code_descriptor;
struct fpu *fpu = ¤t->thread.fpu;
- fpu__activate_curr(fpu);
+ fpu__initialize(fpu);
#ifdef RE_ENTRANT_CHECKING
if (emulating) {
#include <linux/uaccess.h>
#include <linux/sched/debug.h>
+#include <asm/fpu/internal.h>
#include <asm/traps.h>
#include <asm/kdebug.h>
}
EXPORT_SYMBOL_GPL(ex_handler_refcount);
+/*
+ * Handler for when we fail to restore a task's FPU state. We should never get
+ * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * should always be valid. However, past bugs have allowed userspace to set
+ * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
+ * These caused XRSTOR to fail when switching to the task, leaking the FPU
+ * registers of the task previously executing on the CPU. Mitigate this class
+ * of vulnerability by restoring from the initial state (essentially, zeroing
+ * out all the FPU registers) if we can't restore from the task's FPU state.
+ */
+bool ex_handler_fprestore(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr)
+{
+ regs->ip = ex_fixup_addr(fixup);
+
+ WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
+ (void *)instruction_pointer(regs));
+
+ __copy_kernel_to_fpregs(&init_fpstate, -1);
+ return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+
bool ex_handler_ext(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
* 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really
* faulted on a pte with its pkey=4.
*/
-static void fill_sig_info_pkey(int si_code, siginfo_t *info,
- struct vm_area_struct *vma)
+static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey)
{
/* This is effectively an #ifdef */
if (!boot_cpu_has(X86_FEATURE_OSPKE))
* valid VMA, so we should never reach this without a
* valid VMA.
*/
- if (!vma) {
+ if (!pkey) {
WARN_ONCE(1, "PKU fault with no VMA passed in");
info->si_pkey = 0;
return;
* absolutely guranteed to be 100% accurate because of
* the race explained above.
*/
- info->si_pkey = vma_pkey(vma);
+ info->si_pkey = *pkey;
}
static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
- struct task_struct *tsk, struct vm_area_struct *vma,
- int fault)
+ struct task_struct *tsk, u32 *pkey, int fault)
{
unsigned lsb = 0;
siginfo_t info;
lsb = PAGE_SHIFT;
info.si_addr_lsb = lsb;
- fill_sig_info_pkey(si_code, &info, vma);
+ fill_sig_info_pkey(si_code, &info, pkey);
force_sig_info(si_signo, &info, tsk);
}
struct task_struct *tsk = current;
unsigned long flags;
int sig;
- /* No context means no VMA to pass down */
- struct vm_area_struct *vma = NULL;
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs, X86_TRAP_PF)) {
/* XXX: hwpoison faults will set the wrong code. */
force_sig_info_fault(signal, si_code, address,
- tsk, vma, 0);
+ tsk, NULL, 0);
}
/*
if (is_vmalloc_addr((void *)address) &&
(((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
- register void *__sp asm("rsp");
unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
/*
* We're likely to be running with very little stack space
asm volatile ("movq %[stack], %%rsp\n\t"
"call handle_stack_overflow\n\t"
"1: jmp 1b"
- : "+r" (__sp)
+ : ASM_CALL_CONSTRAINT
: "D" ("kernel stack overflow (page fault)"),
"S" (regs), "d" (address),
[stack] "rm" (stack));
static void
__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- int si_code)
+ unsigned long address, u32 *pkey, int si_code)
{
struct task_struct *tsk = current;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_PF;
- force_sig_info_fault(SIGSEGV, si_code, address, tsk, vma, 0);
+ force_sig_info_fault(SIGSEGV, si_code, address, tsk, pkey, 0);
return;
}
static noinline void
bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma)
+ unsigned long address, u32 *pkey)
{
- __bad_area_nosemaphore(regs, error_code, address, vma, SEGV_MAPERR);
+ __bad_area_nosemaphore(regs, error_code, address, pkey, SEGV_MAPERR);
}
static void
unsigned long address, struct vm_area_struct *vma, int si_code)
{
struct mm_struct *mm = current->mm;
+ u32 pkey;
+
+ if (vma)
+ pkey = vma_pkey(vma);
/*
* Something tried to access memory that isn't in our memory map..
*/
up_read(&mm->mmap_sem);
- __bad_area_nosemaphore(regs, error_code, address, vma, si_code);
+ __bad_area_nosemaphore(regs, error_code, address,
+ (vma) ? &pkey : NULL, si_code);
}
static noinline void
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
- struct vm_area_struct *vma, unsigned int fault)
+ u32 *pkey, unsigned int fault)
{
struct task_struct *tsk = current;
int code = BUS_ADRERR;
code = BUS_MCEERR_AR;
}
#endif
- force_sig_info_fault(SIGBUS, code, address, tsk, vma, fault);
+ force_sig_info_fault(SIGBUS, code, address, tsk, pkey, fault);
}
static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
- unsigned long address, struct vm_area_struct *vma,
- unsigned int fault)
+ unsigned long address, u32 *pkey, unsigned int fault)
{
if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
no_context(regs, error_code, address, 0, 0);
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
- do_sigbus(regs, error_code, address, vma, fault);
+ do_sigbus(regs, error_code, address, pkey, fault);
else if (fault & VM_FAULT_SIGSEGV)
- bad_area_nosemaphore(regs, error_code, address, vma);
+ bad_area_nosemaphore(regs, error_code, address, pkey);
else
BUG();
}
struct mm_struct *mm;
int fault, major = 0;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ u32 pkey;
tsk = current;
mm = tsk->mm;
return;
}
+ pkey = vma_pkey(vma);
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
- mm_fault_error(regs, error_code, address, vma, fault);
+ mm_fault_error(regs, error_code, address, &pkey, fault);
return;
}
* published by the Free Software Foundation.
*/
+#define DISABLE_BRANCH_PROFILING
+
#include <linux/linkage.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
#include <asm/mmu_context.h> /* vma_pkey() */
-#include <asm/fpu/internal.h> /* fpregs_active() */
int __execute_only_pkey(struct mm_struct *mm)
{
*/
preempt_disable();
if (!need_to_set_mm_pkey &&
- fpregs_active() &&
+ current->thread.fpu.initialized &&
!__pkru_allows_read(read_pkru(), execute_only_pkey)) {
preempt_enable();
return execute_only_pkey;
* isn't free.
*/
#ifdef CONFIG_DEBUG_VM
- if (WARN_ON_ONCE(__read_cr3() !=
- (__sme_pa(real_prev->pgd) | prev_asid))) {
+ if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) {
/*
* If we were to BUG here, we'd be very likely to kill
* the system so hard that we don't see the call trace.
*/
this_cpu_write(cpu_tlbstate.ctxs[prev_asid].tlb_gen,
next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | prev_asid);
+ write_cr3(build_cr3(next, prev_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
}
* mapped in the new pgd, we'll double-fault. Forcibly
* map it.
*/
- unsigned int index = pgd_index(current_stack_pointer());
+ unsigned int index = pgd_index(current_stack_pointer);
pgd_t *pgd = next->pgd + index;
if (unlikely(pgd_none(*pgd)))
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(__sme_pa(next->pgd) | new_asid);
+ write_cr3(build_cr3(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(__sme_pa(next->pgd) | new_asid | CR3_NOFLUSH);
+ write_cr3(build_cr3_noflush(next, new_asid));
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
!(cr4_read_shadow() & X86_CR4_PCIDE));
/* Force ASID 0 and force a TLB flush. */
- write_cr3(cr3 & ~CR3_PCID_MASK);
+ write_cr3(build_cr3(mm, 0));
/* Reinitialize tlbstate. */
this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0);
* from _brk_limit way up to the max_pfn_mapped (which is the end of
* the ramdisk). We continue on, erasing PMD entries that point to page
* tables - do note that they are accessible at this stage via __va.
- * For good measure we also round up to the PMD - which means that if
+ * As Xen is aligning the memory end to a 4MB boundary, for good
+ * measure we also round up to PMD_SIZE * 2 - which means that if
* anybody is using __ka address to the initial boot-stack - and try
* to use it - they are going to crash. The xen_start_info has been
* taken care of already in xen_setup_kernel_pagetable. */
addr = xen_start_info->pt_base;
- size = roundup(xen_start_info->nr_pt_frames * PAGE_SIZE, PMD_SIZE);
+ size = xen_start_info->nr_pt_frames * PAGE_SIZE;
- xen_cleanhighmap(addr, addr + size);
+ xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2));
xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base));
-#ifdef DEBUG
- /* This is superfluous and is not necessary, but you know what
- * lets do it. The MODULES_VADDR -> MODULES_END should be clear of
- * anything at this stage. */
- xen_cleanhighmap(MODULES_VADDR, roundup(MODULES_VADDR, PUD_SIZE) - 1);
-#endif
}
#endif
* not the first page table in the page table pool.
* Iterate through the initial page tables to find the real page table base.
*/
-static phys_addr_t xen_find_pt_base(pmd_t *pmd)
+static phys_addr_t __init xen_find_pt_base(pmd_t *pmd)
{
phys_addr_t pt_base, paddr;
unsigned pmdidx;
/* Free all resources held by a thread. */
#define release_thread(thread) do { } while(0)
-/* Copy and release all segment info associated with a VM */
-#define copy_segments(p, mm) do { } while(0)
-#define release_segments(mm) do { } while(0)
-#define forget_segments() do { } while (0)
-
extern unsigned long get_wchan(struct task_struct *p);
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
kobject_init(&q->kobj, &blk_queue_ktype);
+#ifdef CONFIG_BLK_DEV_IO_TRACE
+ mutex_init(&q->blk_trace_mutex);
+#endif
mutex_init(&q->sysfs_lock);
spin_lock_init(&q->__queue_lock);
failjob_rls_rqst_payload:
kfree(job->request_payload.sg_list);
failjob_rls_job:
- kfree(job);
return -ENOMEM;
}
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
- struct request_queue *q = dev_to_disk(dev)->queue;
+ struct request_queue *q = part_to_disk(p)->queue;
unsigned int inflight[2];
int cpu;
struct af_alg_ctx *ctx = ask->private;
struct af_alg_tsgl *sgl;
struct scatterlist *sg;
- unsigned int i, j;
+ unsigned int i, j = 0;
while (!list_empty(&ctx->tsgl_list)) {
sgl = list_first_entry(&ctx->tsgl_list, struct af_alg_tsgl,
list);
sg = sgl->sg;
- for (i = 0, j = 0; i < sgl->cur; i++) {
+ for (i = 0; i < sgl->cur; i++) {
size_t plen = min_t(size_t, used, sg[i].length);
struct page *page = sg_page(sg + i);
{
if (!drbg)
return;
- kzfree(drbg->V);
- drbg->Vbuf = NULL;
- kzfree(drbg->C);
- drbg->Cbuf = NULL;
+ kzfree(drbg->Vbuf);
+ drbg->V = NULL;
+ kzfree(drbg->Cbuf);
+ drbg->C = NULL;
kzfree(drbg->scratchpadbuf);
drbg->scratchpadbuf = NULL;
drbg->reseed_ctr = 0;
for (i = 0; i < wdat->entries; i++) {
const struct acpi_generic_address *gas;
struct resource_entry *rentry;
- struct resource res;
+ struct resource res = {};
bool found;
gas = &entries[i].register_region;
}
ghes_do_proc(ghes, ghes->estatus);
+out:
+ ghes_clear_estatus(ghes);
+
+ if (rc == -ENOENT)
+ return rc;
+
/*
* GHESv2 type HEST entries introduce support for error acknowledgment,
* so only acknowledge the error if this support is present.
*/
- if (is_hest_type_generic_v2(ghes)) {
- rc = ghes_ack_error(ghes->generic_v2);
- if (rc)
- return rc;
- }
-out:
- ghes_clear_estatus(ghes);
+ if (is_hest_type_generic_v2(ghes))
+ return ghes_ack_error(ghes->generic_v2);
+
return rc;
}
struct fwnode_handle *child)
{
const struct acpi_device *adev = to_acpi_device_node(fwnode);
- struct acpi_device *child_adev = NULL;
const struct list_head *head;
struct list_head *next;
if (!child || is_acpi_device_node(child)) {
+ struct acpi_device *child_adev;
+
if (adev)
head = &adev->children;
else
goto nondev;
if (child) {
- child_adev = to_acpi_device_node(child);
- next = child_adev->node.next;
+ adev = to_acpi_device_node(child);
+ next = adev->node.next;
if (next == head) {
child = NULL;
goto nondev;
const struct acpi_data_node *data = to_acpi_data_node(fwnode);
struct acpi_data_node *dn;
- if (child_adev)
- head = &child_adev->data.subnodes;
+ if (adev)
+ head = &adev->data.subnodes;
else if (data)
head = &data->data.subnodes;
else
DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops);
DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops);
const struct fwnode_operations acpi_static_fwnode_ops;
+
+bool is_acpi_device_node(const struct fwnode_handle *fwnode)
+{
+ return !IS_ERR_OR_NULL(fwnode) &&
+ fwnode->ops == &acpi_device_fwnode_ops;
+}
+EXPORT_SYMBOL(is_acpi_device_node);
+
+bool is_acpi_data_node(const struct fwnode_handle *fwnode)
+{
+ return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops;
+}
+EXPORT_SYMBOL(is_acpi_data_node);
struct dma_coherent_mem *mem = rmem->priv;
int ret;
- if (!mem)
- return -ENODEV;
-
- ret = dma_init_coherent_memory(rmem->base, rmem->base, rmem->size,
- DMA_MEMORY_EXCLUSIVE, &mem);
-
- if (ret) {
- pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
- &rmem->base, (unsigned long)rmem->size / SZ_1M);
- return ret;
+ if (!mem) {
+ ret = dma_init_coherent_memory(rmem->base, rmem->base,
+ rmem->size,
+ DMA_MEMORY_EXCLUSIVE, &mem);
+ if (ret) {
+ pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return ret;
+ }
}
mem->use_dev_dma_pfn_offset = true;
rmem->priv = mem;
{
spin_lock_irq(&dev->power.lock);
dev->power.no_pm_callbacks =
- (!dev->bus || pm_ops_is_empty(dev->bus->pm)) &&
- (!dev->class || pm_ops_is_empty(dev->class->pm)) &&
+ (!dev->bus || (pm_ops_is_empty(dev->bus->pm) &&
+ !dev->bus->suspend && !dev->bus->resume)) &&
+ (!dev->class || (pm_ops_is_empty(dev->class->pm) &&
+ !dev->class->suspend && !dev->class->resume)) &&
(!dev->type || pm_ops_is_empty(dev->type->pm)) &&
(!dev->pm_domain || pm_ops_is_empty(&dev->pm_domain->ops)) &&
- (!dev->driver || pm_ops_is_empty(dev->driver->pm));
+ (!dev->driver || (pm_ops_is_empty(dev->driver->pm) &&
+ !dev->driver->suspend && !dev->driver->resume));
spin_unlock_irq(&dev->power.lock);
}
opp->available = availability_req;
+ dev_pm_opp_get(opp);
+ mutex_unlock(&opp_table->lock);
+
/* Notify the change of the OPP availability */
if (availability_req)
blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
blocking_notifier_call_chain(&opp_table->head,
OPP_EVENT_DISABLE, opp);
+ dev_pm_opp_put(opp);
+ goto put_table;
+
unlock:
mutex_unlock(&opp_table->lock);
+put_table:
dev_pm_opp_put_opp_table(opp_table);
return r;
}
mutex_unlock(&dev_pm_qos_sysfs_mtx);
}
-static bool dev_pm_qos_invalid_request(struct device *dev,
- struct dev_pm_qos_request *req)
+static bool dev_pm_qos_invalid_req_type(struct device *dev,
+ enum dev_pm_qos_req_type type)
{
- return !req || (req->type == DEV_PM_QOS_LATENCY_TOLERANCE
- && !dev->power.set_latency_tolerance);
+ return type == DEV_PM_QOS_LATENCY_TOLERANCE &&
+ !dev->power.set_latency_tolerance;
}
static int __dev_pm_qos_add_request(struct device *dev,
{
int ret = 0;
- if (!dev || dev_pm_qos_invalid_request(dev, req))
+ if (!dev || !req || dev_pm_qos_invalid_req_type(dev, type))
return -EINVAL;
if (WARN(dev_pm_qos_request_active(req),
if (!brd)
return -ENODEV;
- page = brd_insert_page(brd, PFN_PHYS(pgoff) / 512);
+ page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
if (!page)
return -ENOSPC;
*kaddr = page_address(page);
struct loop_cmd {
struct kthread_work work;
struct request *rq;
- union {
- bool use_aio; /* use AIO interface to handle I/O */
- atomic_t ref; /* only for aio */
- };
+ bool use_aio; /* use AIO interface to handle I/O */
+ atomic_t ref; /* only for aio */
long ret;
struct kiocb iocb;
struct bio_vec *bvec;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ /* The block layer will pass back some non-nbd ioctls in case we have
+ * special handling for them, but we don't so just return an error.
+ */
+ if (_IOC_TYPE(cmd) != 0xab)
+ return -EINVAL;
+
mutex_lock(&nbd->config_lock);
/* Don't allow ioctl operations on a nbd device that was created with
goto out;
}
- msleep(TPM_TIMEOUT); /* CHECK */
+ tpm_msleep(TPM_TIMEOUT);
rmb();
} while (time_before(jiffies, stop));
dev_info(
&chip->dev, HW_ERR
"TPM command timed out during continue self test");
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
continue;
}
}
if (rc != TPM_WARN_DOING_SELFTEST)
return rc;
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
} while (--loops > 0);
return rc;
}
} else {
do {
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
status = chip->ops->status(chip);
if ((status & mask) == mask)
return 0;
*/
if (rc != TPM_WARN_RETRY)
break;
- msleep(TPM_TIMEOUT_RETRY);
+ tpm_msleep(TPM_TIMEOUT_RETRY);
}
if (rc)
enum tpm_timeout {
TPM_TIMEOUT = 5, /* msecs */
- TPM_TIMEOUT_RETRY = 100 /* msecs */
+ TPM_TIMEOUT_RETRY = 100, /* msecs */
+ TPM_TIMEOUT_RANGE_US = 300 /* usecs */
};
/* TPM addresses */
int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout,
wait_queue_head_t *queue, bool check_cancel);
+static inline void tpm_msleep(unsigned int delay_msec)
+{
+ usleep_range(delay_msec * 1000,
+ (delay_msec * 1000) + TPM_TIMEOUT_RANGE_US);
+};
+
struct tpm_chip *tpm_chip_find_get(int chip_num);
__must_check int tpm_try_get_ops(struct tpm_chip *chip);
void tpm_put_ops(struct tpm_chip *chip);
if (rc != TPM2_RC_TESTING)
break;
- msleep(delay_msec);
+ tpm_msleep(delay_msec);
}
return rc;
SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL)
};
-static struct acpi_device_id crb_device_ids[] = {
+static const struct acpi_device_id crb_device_ids[] = {
{"MSFT0101", 0},
{"", 0},
};
static const char tpm_ibmvtpm_driver_name[] = "tpm_ibmvtpm";
-static struct vio_device_id tpm_ibmvtpm_device_table[] = {
+static const struct vio_device_id tpm_ibmvtpm_device_table[] = {
{ "IBM,vtpm", "IBM,vtpm"},
{ "", "" }
};
MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table);
/**
+ *
+ * ibmvtpm_send_crq_word - Send a CRQ request
+ * @vdev: vio device struct
+ * @w1: pre-constructed first word of tpm crq (second word is reserved)
+ *
+ * Return:
+ * 0 - Success
+ * Non-zero - Failure
+ */
+static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1)
+{
+ return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, 0);
+}
+
+/**
+ *
* ibmvtpm_send_crq - Send a CRQ request
*
* @vdev: vio device struct
- * @w1: first word
- * @w2: second word
+ * @valid: Valid field
+ * @msg: Type field
+ * @len: Length field
+ * @data: Data field
+ *
+ * The ibmvtpm crq is defined as follows:
+ *
+ * Byte | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7
+ * -----------------------------------------------------------------------
+ * Word0 | Valid | Type | Length | Data
+ * -----------------------------------------------------------------------
+ * Word1 | Reserved
+ * -----------------------------------------------------------------------
+ *
+ * Which matches the following structure (on bigendian host):
+ *
+ * struct ibmvtpm_crq {
+ * u8 valid;
+ * u8 msg;
+ * __be16 len;
+ * __be32 data;
+ * __be64 reserved;
+ * } __attribute__((packed, aligned(8)));
+ *
+ * However, the value is passed in a register so just compute the numeric value
+ * to load into the register avoiding byteswap altogether. Endian only affects
+ * memory loads and stores - registers are internally represented the same.
*
* Return:
- * 0 -Sucess
+ * 0 (H_SUCCESS) - Success
* Non-zero - Failure
*/
-static int ibmvtpm_send_crq(struct vio_dev *vdev, u64 w1, u64 w2)
+static int ibmvtpm_send_crq(struct vio_dev *vdev,
+ u8 valid, u8 msg, u16 len, u32 data)
{
- return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, w1, w2);
+ u64 w1 = ((u64)valid << 56) | ((u64)msg << 48) | ((u64)len << 32) |
+ (u64)data;
+ return ibmvtpm_send_crq_word(vdev, w1);
}
/**
static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
{
struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
- struct ibmvtpm_crq crq;
- __be64 *word = (__be64 *)&crq;
int rc, sig;
if (!ibmvtpm->rtce_buf) {
spin_lock(&ibmvtpm->rtce_lock);
ibmvtpm->res_len = 0;
memcpy((void *)ibmvtpm->rtce_buf, (void *)buf, count);
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_TPM_COMMAND;
- crq.len = cpu_to_be16(count);
- crq.data = cpu_to_be32(ibmvtpm->rtce_dma_handle);
/*
* set the processing flag before the Hcall, since we may get the
*/
ibmvtpm->tpm_processing_cmd = true;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, be64_to_cpu(word[0]),
- be64_to_cpu(word[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_TPM_COMMAND,
+ count, ibmvtpm->rtce_dma_handle);
if (rc != H_SUCCESS) {
dev_err(ibmvtpm->dev, "tpm_ibmvtpm_send failed rc=%d\n", rc);
rc = 0;
*/
static int ibmvtpm_crq_get_rtce_size(struct ibmvtpm_dev *ibmvtpm)
{
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_GET_RTCE_BUFFER_SIZE;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_GET_RTCE_BUFFER_SIZE, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_rtce_size failed rc=%d\n", rc);
*/
static int ibmvtpm_crq_get_version(struct ibmvtpm_dev *ibmvtpm)
{
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_GET_VERSION;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_GET_VERSION, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_get_version failed rc=%d\n", rc);
{
int rc;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_COMP_CMD, 0);
+ rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_COMP_CMD);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_send_init_complete failed rc=%d\n", rc);
{
int rc;
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, INIT_CRQ_CMD, 0);
+ rc = ibmvtpm_send_crq_word(ibmvtpm->vdev, INIT_CRQ_CMD);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"ibmvtpm_crq_send_init failed rc=%d\n", rc);
{
struct tpm_chip *chip = dev_get_drvdata(dev);
struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
- struct ibmvtpm_crq crq;
- u64 *buf = (u64 *) &crq;
int rc = 0;
- crq.valid = (u8)IBMVTPM_VALID_CMD;
- crq.msg = (u8)VTPM_PREPARE_TO_SUSPEND;
-
- rc = ibmvtpm_send_crq(ibmvtpm->vdev, cpu_to_be64(buf[0]),
- cpu_to_be64(buf[1]));
+ rc = ibmvtpm_send_crq(ibmvtpm->vdev,
+ IBMVTPM_VALID_CMD, VTPM_PREPARE_TO_SUSPEND, 0, 0);
if (rc != H_SUCCESS)
dev_err(ibmvtpm->dev,
"tpm_ibmvtpm_suspend failed rc=%d\n", rc);
/* check the status-register if wait_for_bit is set */
if (status & 1 << wait_for_bit)
break;
- msleep(TPM_MSLEEP_TIME);
+ tpm_msleep(TPM_MSLEEP_TIME);
}
if (i == TPM_MAX_TRIES) { /* timeout occurs */
if (wait_for_bit == STAT_XFE)
wait_and_send(chip, TPM_CTRL_WTX);
wait_and_send(chip, 0x00);
wait_and_send(chip, 0x00);
- msleep(TPM_WTX_MSLEEP_TIME);
+ tpm_msleep(TPM_WTX_MSLEEP_TIME);
}
static void tpm_wtx_abort(struct tpm_chip *chip)
wait_and_send(chip, 0x00);
wait_and_send(chip, 0x00);
number_of_wtx = 0;
- msleep(TPM_WTX_MSLEEP_TIME);
+ tpm_msleep(TPM_WTX_MSLEEP_TIME);
}
static int tpm_inf_recv(struct tpm_chip *chip, u8 * buf, size_t count)
if (access & TPM_ACCESS_VALID)
return 0;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
return -1;
}
do {
if (check_locality(chip, l))
return l;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
}
return -1;
burstcnt = (value >> 8) & 0xFFFF;
if (burstcnt)
return burstcnt;
- msleep(TPM_TIMEOUT);
+ tpm_msleep(TPM_TIMEOUT);
} while (time_before(jiffies, stop));
return -EBUSY;
}
priv->irq = irq;
chip->flags |= TPM_CHIP_FLAG_IRQ;
if (!priv->irq_tested)
- msleep(1);
+ tpm_msleep(1);
if (!priv->irq_tested)
disable_interrupts(chip);
priv->irq_tested = true;
return 0;
}
-static struct clock_event_device numachip2_clockevent = {
+static const struct clock_event_device numachip2_clockevent __initconst = {
.name = "numachip2",
.rating = 400,
.set_next_event = numachip2_set_next_event,
return -readl(sched_clk_base + TIMER_VALUE);
}
-static int integrator_clocksource_init(unsigned long inrate,
- void __iomem *base)
+static int __init integrator_clocksource_init(unsigned long inrate,
+ void __iomem *base)
{
u32 ctrl = TIMER_CTRL_ENABLE | TIMER_CTRL_PERIODIC;
unsigned long rate = inrate;
* platforms using "operating-points-v2" property.
*/
static const struct of_device_id blacklist[] __initconst = {
+ { .compatible = "calxeda,highbank", },
+ { .compatible = "calxeda,ecx-2000", },
+
+ { .compatible = "marvell,armadaxp", },
+
+ { .compatible = "nvidia,tegra124", },
+
+ { .compatible = "st,stih407", },
+ { .compatible = "st,stih410", },
+
+ { .compatible = "sigma,tango4", },
+
+ { .compatible = "ti,am33xx", },
+ { .compatible = "ti,am43", },
+ { .compatible = "ti,dra7", },
+
{ }
};
static const struct of_device_id ti_cpufreq_of_match[] = {
{ .compatible = "ti,am33xx", .data = &am3x_soc_data, },
- { .compatible = "ti,am4372", .data = &am4x_soc_data, },
+ { .compatible = "ti,am43", .data = &am4x_soc_data, },
{ .compatible = "ti,dra7", .data = &dra7_soc_data },
{},
};
ret = dt_init_idle_driver(drv, arm_idle_state_match, 1);
if (ret <= 0) {
ret = ret ? : -ENODEV;
- goto out_fail;
+ goto init_fail;
}
ret = cpuidle_register_driver(drv);
if (ret) {
pr_err("Failed to register cpuidle driver\n");
- goto out_fail;
+ goto init_fail;
}
/*
}
return 0;
+init_fail:
+ kfree(drv);
out_fail:
while (--cpu >= 0) {
dev = per_cpu(cpuidle_devices, cpu);
config CRYPTO_DEV_FSL_CAAM
tristate "Freescale CAAM-Multicore driver backend"
depends on FSL_SOC || ARCH_MXC || ARCH_LAYERSCAPE
+ select SOC_BUS
help
Enables the driver module for Freescale's Cryptographic Accelerator
and Assurance Module (CAAM), also known as the SEC version 4 (SEC4).
To compile this as a module, choose M here: the module
will be called caamrng.
-config CRYPTO_DEV_FSL_CAAM_IMX
- def_bool SOC_IMX6 || SOC_IMX7D
- depends on CRYPTO_DEV_FSL_CAAM
-
config CRYPTO_DEV_FSL_CAAM_DEBUG
bool "Enable debug output in CAAM driver"
depends on CRYPTO_DEV_FSL_CAAM
#include <linux/device.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
+#include <linux/sys_soc.h>
#include "compat.h"
#include "regs.h"
EXPORT_SYMBOL(caam_little_end);
bool caam_dpaa2;
EXPORT_SYMBOL(caam_dpaa2);
+bool caam_imx;
+EXPORT_SYMBOL(caam_imx);
#ifdef CONFIG_CAAM_QI
#include "qi.h"
* i.MX targets tend to have clock control subsystems that can
* enable/disable clocking to our device.
*/
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
static inline struct clk *caam_drv_identify_clk(struct device *dev,
char *clk_name)
{
- return devm_clk_get(dev, clk_name);
+ return caam_imx ? devm_clk_get(dev, clk_name) : NULL;
}
-#else
-static inline struct clk *caam_drv_identify_clk(struct device *dev,
- char *clk_name)
-{
- return NULL;
-}
-#endif
/*
* Descriptor to instantiate RNG State Handle 0 in normal mode and
{
int ret, ring, gen_sk, ent_delay = RTSDCTL_ENT_DLY_MIN;
u64 caam_id;
+ static const struct soc_device_attribute imx_soc[] = {
+ {.family = "Freescale i.MX"},
+ {},
+ };
struct device *dev;
struct device_node *nprop, *np;
struct caam_ctrl __iomem *ctrl;
dev_set_drvdata(dev, ctrlpriv);
nprop = pdev->dev.of_node;
+ caam_imx = (bool)soc_device_match(imx_soc);
+
/* Enable clocking */
clk = caam_drv_identify_clk(&pdev->dev, "ipg");
if (IS_ERR(clk)) {
*/
extern bool caam_little_end;
+extern bool caam_imx;
#define caam_to_cpu(len) \
static inline u##len caam##len ## _to_cpu(u##len val) \
#else /* CONFIG_64BIT */
static inline void wr_reg64(void __iomem *reg, u64 data)
{
-#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
- if (caam_little_end) {
+ if (!caam_imx && caam_little_end) {
wr_reg32((u32 __iomem *)(reg) + 1, data >> 32);
wr_reg32((u32 __iomem *)(reg), data);
- } else
-#endif
- {
+ } else {
wr_reg32((u32 __iomem *)(reg), data >> 32);
wr_reg32((u32 __iomem *)(reg) + 1, data);
}
static inline u64 rd_reg64(void __iomem *reg)
{
-#ifndef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
- if (caam_little_end)
+ if (!caam_imx && caam_little_end)
return ((u64)rd_reg32((u32 __iomem *)(reg) + 1) << 32 |
(u64)rd_reg32((u32 __iomem *)(reg)));
- else
-#endif
- return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
- (u64)rd_reg32((u32 __iomem *)(reg) + 1));
+
+ return ((u64)rd_reg32((u32 __iomem *)(reg)) << 32 |
+ (u64)rd_reg32((u32 __iomem *)(reg) + 1));
}
#endif /* CONFIG_64BIT */
+static inline u64 cpu_to_caam_dma64(dma_addr_t value)
+{
+ if (caam_imx)
+ return (((u64)cpu_to_caam32(lower_32_bits(value)) << 32) |
+ (u64)cpu_to_caam32(upper_32_bits(value)));
+
+ return cpu_to_caam64(value);
+}
+
+static inline u64 caam_dma64_to_cpu(u64 value)
+{
+ if (caam_imx)
+ return (((u64)caam32_to_cpu(lower_32_bits(value)) << 32) |
+ (u64)caam32_to_cpu(upper_32_bits(value)));
+
+ return caam64_to_cpu(value);
+}
+
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-#ifdef CONFIG_SOC_IMX7D
-#define cpu_to_caam_dma(value) \
- (((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
- (u64)cpu_to_caam32(upper_32_bits(value)))
-#define caam_dma_to_cpu(value) \
- (((u64)caam32_to_cpu(lower_32_bits(value)) << 32) | \
- (u64)caam32_to_cpu(upper_32_bits(value)))
-#else
-#define cpu_to_caam_dma(value) cpu_to_caam64(value)
-#define caam_dma_to_cpu(value) caam64_to_cpu(value)
-#endif /* CONFIG_SOC_IMX7D */
+#define cpu_to_caam_dma(value) cpu_to_caam_dma64(value)
+#define caam_dma_to_cpu(value) caam_dma64_to_cpu(value)
#else
#define cpu_to_caam_dma(value) cpu_to_caam32(value)
#define caam_dma_to_cpu(value) caam32_to_cpu(value)
-#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT */
-
-#ifdef CONFIG_CRYPTO_DEV_FSL_CAAM_IMX
-#define cpu_to_caam_dma64(value) \
- (((u64)cpu_to_caam32(lower_32_bits(value)) << 32) | \
- (u64)cpu_to_caam32(upper_32_bits(value)))
-#else
-#define cpu_to_caam_dma64(value) cpu_to_caam64(value)
-#endif
+#endif /* CONFIG_ARCH_DMA_ADDR_T_64BIT */
/*
* jr_outentry
struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
struct safexcel_crypto_priv *priv = ctx->priv;
struct skcipher_request req;
- struct safexcel_inv_result result = { 0 };
+ struct safexcel_inv_result result = {};
int ring = ctx->base.ring;
memset(&req, 0, sizeof(struct skcipher_request));
struct safexcel_ahash_ctx *ctx = crypto_tfm_ctx(tfm);
struct safexcel_crypto_priv *priv = ctx->priv;
struct ahash_request req;
- struct safexcel_inv_result result = { 0 };
+ struct safexcel_inv_result result = {};
int ring = ctx->base.ring;
memset(&req, 0, sizeof(struct ahash_request));
req_ctx->swinit = 0;
} else {
desc->ptr[1] = zero_entry;
- /* Indicate next op is not the first. */
- req_ctx->first = 0;
}
+ /* Indicate next op is not the first. */
+ req_ctx->first = 0;
/* HMAC key */
if (ctx->keylen)
sg_count = edesc->src_nents ?: 1;
if (is_sec1 && sg_count > 1)
- sg_copy_to_buffer(areq->src, sg_count, edesc->buf, length);
+ sg_copy_to_buffer(req_ctx->psrc, sg_count, edesc->buf, length);
else
sg_count = dma_map_sg(dev, req_ctx->psrc, sg_count,
DMA_TO_DEVICE);
t_alg->algt.alg.hash.final = ahash_final;
t_alg->algt.alg.hash.finup = ahash_finup;
t_alg->algt.alg.hash.digest = ahash_digest;
- t_alg->algt.alg.hash.setkey = ahash_setkey;
+ if (!strncmp(alg->cra_name, "hmac", 4))
+ t_alg->algt.alg.hash.setkey = ahash_setkey;
t_alg->algt.alg.hash.import = ahash_import;
t_alg->algt.alg.hash.export = ahash_export;
NUM_BANKS(ADDR_SURF_2_BANK);
for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
- } else if (adev->asic_type == CHIP_OLAND || adev->asic_type == CHIP_HAINAN) {
+ } else if (adev->asic_type == CHIP_OLAND) {
+ tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[1] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[2] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[3] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_128B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[4] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[5] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(split_equal_to_row_size) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[6] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(split_equal_to_row_size) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[7] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(split_equal_to_row_size) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[8] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_LINEAR_ALIGNED) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[9] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[10] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[11] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[12] = MICRO_TILE_MODE(ADDR_SURF_DISPLAY_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[13] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_1D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_64B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[14] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[15] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[16] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[17] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P4_8x16) |
+ TILE_SPLIT(split_equal_to_row_size) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[21] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_2) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[22] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_4) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_4);
+ tilemode[23] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_256B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_2) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[24] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_512B) |
+ NUM_BANKS(ADDR_SURF_16_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_2);
+ tilemode[25] = MICRO_TILE_MODE(ADDR_SURF_THIN_MICRO_TILING) |
+ ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
+ PIPE_CONFIG(ADDR_SURF_P8_32x32_8x16) |
+ TILE_SPLIT(ADDR_SURF_TILE_SPLIT_1KB) |
+ NUM_BANKS(ADDR_SURF_8_BANK) |
+ BANK_WIDTH(ADDR_SURF_BANK_WIDTH_1) |
+ BANK_HEIGHT(ADDR_SURF_BANK_HEIGHT_1) |
+ MACRO_TILE_ASPECT(ADDR_SURF_MACRO_ASPECT_1);
+ for (reg_offset = 0; reg_offset < num_tile_mode_states; reg_offset++)
+ WREG32(mmGB_TILE_MODE0 + reg_offset, tilemode[reg_offset]);
+ } else if (adev->asic_type == CHIP_HAINAN) {
tilemode[0] = MICRO_TILE_MODE(ADDR_SURF_DEPTH_MICRO_TILING) |
ARRAY_MODE(ARRAY_2D_TILED_THIN1) |
PIPE_CONFIG(ADDR_SURF_P2) |
int err = 0;
dev = kfd_device_by_id(args->gpu_id);
+ if (!dev)
+ return -EINVAL;
dev->kfd2kgd->get_tile_config(dev->kgd, &config);
struct kfd_event *ev)
{
if (p->signal_event_count == KFD_SIGNAL_EVENT_LIMIT) {
- pr_warn("Signal event wasn't created because limit was reached\n");
+ if (!p->signal_event_limit_reached) {
+ pr_warn("Signal event wasn't created because limit was reached\n");
+ p->signal_event_limit_reached = true;
+ }
return -ENOMEM;
}
{
if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
kq->mqd->destroy_mqd(kq->mqd,
- NULL,
- false,
+ kq->queue->mqd,
+ KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS,
kq->queue->pipe,
kq->queue->queue);
uint32_t wptr, rptr;
unsigned int *queue_address;
+ /* When rptr == wptr, the buffer is empty.
+ * When rptr == wptr + 1, the buffer is full.
+ * It is always rptr that advances to the position of wptr, rather than
+ * the opposite. So we can only use up to queue_size_dwords - 1 dwords.
+ */
rptr = *kq->rptr_kernel;
wptr = *kq->wptr_kernel;
queue_address = (unsigned int *)kq->pq_kernel_addr;
pr_debug("wptr: %d\n", wptr);
pr_debug("queue_address 0x%p\n", queue_address);
- available_size = (rptr - 1 - wptr + queue_size_dwords) %
+ available_size = (rptr + queue_size_dwords - 1 - wptr) %
queue_size_dwords;
- if (packet_size_in_dwords >= queue_size_dwords ||
- packet_size_in_dwords >= available_size) {
+ if (packet_size_in_dwords > available_size) {
/*
* make sure calling functions know
* acquire_packet_buffer() failed
}
if (wptr + packet_size_in_dwords >= queue_size_dwords) {
+ /* make sure after rolling back to position 0, there is
+ * still enough space.
+ */
+ if (packet_size_in_dwords >= rptr) {
+ *buffer_ptr = NULL;
+ return -ENOMEM;
+ }
+ /* fill nops, roll back and start at position 0 */
while (wptr > 0) {
queue_address[wptr] = kq->nop_packet;
wptr = (wptr + 1) % queue_size_dwords;
struct list_head signal_event_pages;
u32 next_nonsignal_event_id;
size_t signal_event_count;
+ bool signal_event_limit_reached;
};
/**
int num_queues = 0;
struct queue *cur;
- memset(&q_properties, 0, sizeof(struct queue_properties));
memcpy(&q_properties, properties, sizeof(struct queue_properties));
q = NULL;
kq = NULL;
void etnaviv_gem_free_object(struct drm_gem_object *obj)
{
struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
+ struct etnaviv_drm_private *priv = obj->dev->dev_private;
struct etnaviv_vram_mapping *mapping, *tmp;
/* object should not be active */
WARN_ON(is_active(etnaviv_obj));
+ mutex_lock(&priv->gem_lock);
list_del(&etnaviv_obj->gem_node);
+ mutex_unlock(&priv->gem_lock);
list_for_each_entry_safe(mapping, tmp, &etnaviv_obj->vram_list,
obj_node) {
cmdbuf->user_size = ALIGN(args->stream_size, 8);
ret = etnaviv_gpu_submit(gpu, submit, cmdbuf);
- if (ret == 0)
- cmdbuf = NULL;
+ if (ret)
+ goto out;
+
+ cmdbuf = NULL;
if (args->flags & ETNA_SUBMIT_FENCE_FD_OUT) {
/*
#include <linux/clk.h>
#include <linux/component.h>
#include <linux/iopoll.h>
+#include <linux/irq.h>
#include <linux/mfd/syscon.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
static int exynos_drm_suspend(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- struct drm_connector *connector;
- struct drm_connector_list_iter conn_iter;
+ struct exynos_drm_private *private = drm_dev->dev_private;
if (pm_runtime_suspended(dev) || !drm_dev)
return 0;
- drm_connector_list_iter_begin(drm_dev, &conn_iter);
- drm_for_each_connector_iter(connector, &conn_iter) {
- int old_dpms = connector->dpms;
-
- if (connector->funcs->dpms)
- connector->funcs->dpms(connector, DRM_MODE_DPMS_OFF);
-
- /* Set the old mode back to the connector for resume */
- connector->dpms = old_dpms;
+ drm_kms_helper_poll_disable(drm_dev);
+ exynos_drm_fbdev_suspend(drm_dev);
+ private->suspend_state = drm_atomic_helper_suspend(drm_dev);
+ if (IS_ERR(private->suspend_state)) {
+ exynos_drm_fbdev_resume(drm_dev);
+ drm_kms_helper_poll_enable(drm_dev);
+ return PTR_ERR(private->suspend_state);
}
- drm_connector_list_iter_end(&conn_iter);
return 0;
}
static int exynos_drm_resume(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- struct drm_connector *connector;
- struct drm_connector_list_iter conn_iter;
+ struct exynos_drm_private *private = drm_dev->dev_private;
if (pm_runtime_suspended(dev) || !drm_dev)
return 0;
- drm_connector_list_iter_begin(drm_dev, &conn_iter);
- drm_for_each_connector_iter(connector, &conn_iter) {
- if (connector->funcs->dpms) {
- int dpms = connector->dpms;
-
- connector->dpms = DRM_MODE_DPMS_OFF;
- connector->funcs->dpms(connector, dpms);
- }
- }
- drm_connector_list_iter_end(&conn_iter);
+ drm_atomic_helper_resume(drm_dev, private->suspend_state);
+ exynos_drm_fbdev_resume(drm_dev);
+ drm_kms_helper_poll_enable(drm_dev);
return 0;
}
*/
struct exynos_drm_private {
struct drm_fb_helper *fb_helper;
+ struct drm_atomic_state *suspend_state;
struct device *dma_dev;
void *mapping;
#include <drm/drm_crtc_helper.h>
#include <drm/exynos_drm.h>
+#include <linux/console.h>
+
#include "exynos_drm_drv.h"
#include "exynos_drm_fb.h"
#include "exynos_drm_fbdev.h"
drm_fb_helper_hotplug_event(fb_helper);
}
+
+void exynos_drm_fbdev_suspend(struct drm_device *dev)
+{
+ struct exynos_drm_private *private = dev->dev_private;
+
+ console_lock();
+ drm_fb_helper_set_suspend(private->fb_helper, 1);
+ console_unlock();
+}
+
+void exynos_drm_fbdev_resume(struct drm_device *dev)
+{
+ struct exynos_drm_private *private = dev->dev_private;
+
+ console_lock();
+ drm_fb_helper_set_suspend(private->fb_helper, 0);
+ console_unlock();
+}
void exynos_drm_fbdev_fini(struct drm_device *dev);
void exynos_drm_fbdev_restore_mode(struct drm_device *dev);
void exynos_drm_output_poll_changed(struct drm_device *dev);
+void exynos_drm_fbdev_suspend(struct drm_device *drm);
+void exynos_drm_fbdev_resume(struct drm_device *drm);
#else
#define exynos_drm_output_poll_changed (NULL)
+static inline void exynos_drm_fbdev_suspend(struct drm_device *drm)
+{
+}
+
+static inline void exynos_drm_fbdev_resume(struct drm_device *drm)
+{
+}
+
#endif
#endif
struct drm_device *dev = encoder->dev;
struct drm_connector *connector;
struct drm_display_mode *m;
+ struct drm_connector_list_iter conn_iter;
int mode_ok;
drm_mode_set_crtcinfo(adjusted_mode, 0);
- list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+ drm_connector_list_iter_begin(dev, &conn_iter);
+ drm_for_each_connector_iter(connector, &conn_iter) {
if (connector->encoder == encoder)
break;
}
+ if (connector)
+ drm_connector_get(connector);
+ drm_connector_list_iter_end(&conn_iter);
- if (connector->encoder != encoder)
+ if (!connector)
return true;
mode_ok = hdmi_mode_valid(connector, adjusted_mode);
if (mode_ok == MODE_OK)
- return true;
+ goto cleanup;
/*
* Find the most suitable mode and copy it to adjusted_mode.
}
}
+cleanup:
+ drm_connector_put(connector);
+
return true;
}
static int emulate_pci_bar_write(struct intel_vgpu *vgpu, unsigned int offset,
void *p_data, unsigned int bytes)
{
- unsigned int bar_index =
- (rounddown(offset, 8) % PCI_BASE_ADDRESS_0) / 8;
u32 new = *(u32 *)(p_data);
bool lo = IS_ALIGNED(offset, 8);
u64 size;
int ret = 0;
bool mmio_enabled =
vgpu_cfg_space(vgpu)[PCI_COMMAND] & PCI_COMMAND_MEMORY;
+ struct intel_vgpu_pci_bar *bars = vgpu->cfg_space.bar;
- if (WARN_ON(bar_index >= INTEL_GVT_PCI_BAR_MAX))
- return -EINVAL;
-
+ /*
+ * Power-up software can determine how much address
+ * space the device requires by writing a value of
+ * all 1's to the register and then reading the value
+ * back. The device will return 0's in all don't-care
+ * address bits.
+ */
if (new == 0xffffffff) {
- /*
- * Power-up software can determine how much address
- * space the device requires by writing a value of
- * all 1's to the register and then reading the value
- * back. The device will return 0's in all don't-care
- * address bits.
- */
- size = vgpu->cfg_space.bar[bar_index].size;
- if (lo) {
- new = rounddown(new, size);
- } else {
- u32 val = vgpu_cfg_space(vgpu)[rounddown(offset, 8)];
- /* for 32bit mode bar it returns all-0 in upper 32
- * bit, for 64bit mode bar it will calculate the
- * size with lower 32bit and return the corresponding
- * value
+ switch (offset) {
+ case PCI_BASE_ADDRESS_0:
+ case PCI_BASE_ADDRESS_1:
+ size = ~(bars[INTEL_GVT_PCI_BAR_GTTMMIO].size -1);
+ intel_vgpu_write_pci_bar(vgpu, offset,
+ size >> (lo ? 0 : 32), lo);
+ /*
+ * Untrap the BAR, since guest hasn't configured a
+ * valid GPA
*/
- if (val & PCI_BASE_ADDRESS_MEM_TYPE_64)
- new &= (~(size-1)) >> 32;
- else
- new = 0;
- }
- /*
- * Unmapp & untrap the BAR, since guest hasn't configured a
- * valid GPA
- */
- switch (bar_index) {
- case INTEL_GVT_PCI_BAR_GTTMMIO:
ret = trap_gttmmio(vgpu, false);
break;
- case INTEL_GVT_PCI_BAR_APERTURE:
+ case PCI_BASE_ADDRESS_2:
+ case PCI_BASE_ADDRESS_3:
+ size = ~(bars[INTEL_GVT_PCI_BAR_APERTURE].size -1);
+ intel_vgpu_write_pci_bar(vgpu, offset,
+ size >> (lo ? 0 : 32), lo);
ret = map_aperture(vgpu, false);
break;
+ default:
+ /* Unimplemented BARs */
+ intel_vgpu_write_pci_bar(vgpu, offset, 0x0, false);
}
- intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
} else {
- /*
- * Unmapp & untrap the old BAR first, since guest has
- * re-configured the BAR
- */
- switch (bar_index) {
- case INTEL_GVT_PCI_BAR_GTTMMIO:
- ret = trap_gttmmio(vgpu, false);
+ switch (offset) {
+ case PCI_BASE_ADDRESS_0:
+ case PCI_BASE_ADDRESS_1:
+ /*
+ * Untrap the old BAR first, since guest has
+ * re-configured the BAR
+ */
+ trap_gttmmio(vgpu, false);
+ intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
+ ret = trap_gttmmio(vgpu, mmio_enabled);
break;
- case INTEL_GVT_PCI_BAR_APERTURE:
- ret = map_aperture(vgpu, false);
+ case PCI_BASE_ADDRESS_2:
+ case PCI_BASE_ADDRESS_3:
+ map_aperture(vgpu, false);
+ intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
+ ret = map_aperture(vgpu, mmio_enabled);
break;
- }
- intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
- /* Track the new BAR */
- if (mmio_enabled) {
- switch (bar_index) {
- case INTEL_GVT_PCI_BAR_GTTMMIO:
- ret = trap_gttmmio(vgpu, true);
- break;
- case INTEL_GVT_PCI_BAR_APERTURE:
- ret = map_aperture(vgpu, true);
- break;
- }
+ default:
+ intel_vgpu_write_pci_bar(vgpu, offset, new, lo);
}
}
return ret;
}
switch (rounddown(offset, 4)) {
- case PCI_BASE_ADDRESS_0:
- case PCI_BASE_ADDRESS_1:
- case PCI_BASE_ADDRESS_2:
- case PCI_BASE_ADDRESS_3:
+ case PCI_BASE_ADDRESS_0 ... PCI_BASE_ADDRESS_5:
if (WARN_ON(!IS_ALIGNED(offset, 4)))
return -EINVAL;
return emulate_pci_bar_write(vgpu, offset, p_data, bytes);
struct intel_gvt *gvt = vgpu->gvt;
const struct intel_gvt_device_info *info = &gvt->device_info;
u16 *gmch_ctl;
- int i;
memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
info->cfg_space_size);
*/
memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
+ memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_4, 0, 8);
memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
- for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
- vgpu->cfg_space.bar[i].size = pci_resource_len(
- gvt->dev_priv->drm.pdev, i * 2);
- vgpu->cfg_space.bar[i].tracked = false;
- }
+ vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size =
+ pci_resource_len(gvt->dev_priv->drm.pdev, 0);
+ vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size =
+ pci_resource_len(gvt->dev_priv->drm.pdev, 2);
}
/**
pipe);
int position;
int vbl_start, vbl_end, hsync_start, htotal, vtotal;
- bool in_vbl = true;
unsigned long irqflags;
if (WARN_ON(!mode->crtc_clock)) {
spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
- in_vbl = position >= vbl_start && position < vbl_end;
-
/*
* While in vblank, position will be negative
* counting up towards 0 at vbl_end. And outside
if (mode_cmd->handles[i] != mode_cmd->handles[0]) {
DRM_DEBUG_KMS("bad plane %d handle\n", i);
- return -EINVAL;
+ goto err;
}
stride_alignment = intel_fb_stride_alignment(fb, i);
struct intel_crtc_state *old_crtc_state,
struct drm_connector_state *old_conn_state)
{
- struct drm_device *dev = encoder->base.dev;
- struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
enum port port;
intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
intel_panel_disable_backlight(old_conn_state);
- /*
- * Disable Device ready before the port shutdown in order
- * to avoid split screen
- */
- if (IS_BROXTON(dev_priv)) {
- for_each_dsi_port(port, intel_dsi->ports)
- I915_WRITE(MIPI_DEVICE_READY(port), 0);
- }
-
/*
* According to the spec we should send SHUTDOWN before
* MIPI_SEQ_DISPLAY_OFF only for v3+ VBTs, but field testing
if (!panel->backlight.max)
return -ENODEV;
+ panel->backlight.min = get_backlight_min_vbt(connector);
+
val = bxt_get_backlight(connector);
val = intel_panel_compute_brightness(connector, val);
panel->backlight.level = clamp(val, panel->backlight.min,
if (!panel->backlight.max)
return -ENODEV;
+ panel->backlight.min = get_backlight_min_vbt(connector);
+
val = bxt_get_backlight(connector);
val = intel_panel_compute_brightness(connector, val);
panel->backlight.level = clamp(val, panel->backlight.min,
.y2 = qfb->base.height
};
- if (!old_state->fb) {
- qxl_io_log(qdev,
- "create primary fb: %dx%d,%d,%d\n",
- bo->surf.width, bo->surf.height,
- bo->surf.stride, bo->surf.format);
+ if (old_state->fb) {
+ qfb_old = to_qxl_framebuffer(old_state->fb);
+ bo_old = gem_to_qxl_bo(qfb_old->obj);
+ } else {
+ bo_old = NULL;
+ }
- qxl_io_create_primary(qdev, 0, bo);
- bo->is_primary = true;
+ if (bo == bo_old)
return;
- } else {
- qfb_old = to_qxl_framebuffer(old_state->fb);
- bo_old = gem_to_qxl_bo(qfb_old->obj);
+ if (bo_old && bo_old->is_primary) {
+ qxl_io_destroy_primary(qdev);
bo_old->is_primary = false;
}
- bo->is_primary = true;
+ if (!bo->is_primary) {
+ qxl_io_create_primary(qdev, 0, bo);
+ bo->is_primary = true;
+ }
qxl_draw_dirty_fb(qdev, qfb, bo, 0, 0, &norect, 1, 1);
}
{
struct qxl_device *qdev = plane->dev->dev_private;
- if (old_state->fb)
- { struct qxl_framebuffer *qfb =
+ if (old_state->fb) {
+ struct qxl_framebuffer *qfb =
to_qxl_framebuffer(old_state->fb);
struct qxl_bo *bo = gem_to_qxl_bo(qfb->obj);
- qxl_io_destroy_primary(qdev);
- bo->is_primary = false;
+ if (bo->is_primary) {
+ qxl_io_destroy_primary(qdev);
+ bo->is_primary = false;
+ }
}
}
struct drm_gem_object *obj;
struct qxl_bo *user_bo;
- if (!plane->state->fb) {
- /* we never executed prepare_fb, so there's nothing to
+ if (!old_state->fb) {
+ /*
+ * we never executed prepare_fb, so there's nothing to
* unpin.
*/
return;
}
- obj = to_qxl_framebuffer(plane->state->fb)->obj;
+ obj = to_qxl_framebuffer(old_state->fb)->obj;
user_bo = gem_to_qxl_bo(obj);
qxl_bo_unpin(user_bo);
}
radeon_agp_suspend(rdev);
pci_save_state(dev->pdev);
- if (freeze && rdev->family >= CHIP_CEDAR) {
+ if (freeze && rdev->family >= CHIP_CEDAR && !(rdev->flags & RADEON_IS_IGP)) {
rdev->asic->asic_reset(rdev, true);
pci_restore_state(dev->pdev);
} else if (suspend) {
bool "Allwinner A10 HDMI CEC Support"
depends on DRM_SUN4I_HDMI
select CEC_CORE
- depends on CEC_PIN
+ select CEC_PIN
help
Choose this option if you have an Allwinner SoC with an HDMI
controller and want to use CEC.
#include <drm/drm_connector.h>
#include <drm/drm_encoder.h>
-#include <media/cec.h>
+#include <media/cec-pin.h>
#define SUN4I_HDMI_CTRL_REG 0x004
#define SUN4I_HDMI_CTRL_ENABLE BIT(31)
/* This part must be outside protection */
#undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_PATH ../../drivers/gpu/drm/tegra
#define TRACE_INCLUDE_FILE trace
#include <trace/define_trace.h>
atomic_set(&qp->qp_sec->error_list_count, 0);
init_completion(&qp->qp_sec->error_complete);
ret = security_ib_alloc_security(&qp->qp_sec->security);
- if (ret)
+ if (ret) {
kfree(qp->qp_sec);
+ qp->qp_sec = NULL;
+ }
return ret;
}
resp.raw_packet_caps = attr.raw_packet_caps;
resp.response_length += sizeof(resp.raw_packet_caps);
- if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps))
+ if (ucore->outlen < resp.response_length + sizeof(resp.tm_caps))
goto end;
- resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size;
- resp.xrq_caps.max_num_tags = attr.xrq_caps.max_num_tags;
- resp.xrq_caps.max_ops = attr.xrq_caps.max_ops;
- resp.xrq_caps.max_sge = attr.xrq_caps.max_sge;
- resp.xrq_caps.flags = attr.xrq_caps.flags;
- resp.response_length += sizeof(resp.xrq_caps);
+ resp.tm_caps.max_rndv_hdr_size = attr.tm_caps.max_rndv_hdr_size;
+ resp.tm_caps.max_num_tags = attr.tm_caps.max_num_tags;
+ resp.tm_caps.max_ops = attr.tm_caps.max_ops;
+ resp.tm_caps.max_sge = attr.tm_caps.max_sge;
+ resp.tm_caps.flags = attr.tm_caps.flags;
+ resp.response_length += sizeof(resp.tm_caps);
end:
err = ib_copy_to_udata(ucore, &resp, resp.response_length);
return err;
*/
if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
if (attr.qp_state >= IB_QPS_INIT) {
- if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+ if (rdma_port_get_link_layer(qp->device, attr.port_num) !=
IB_LINK_LAYER_INFINIBAND)
return true;
goto lid_check;
/* Can't get a quick answer, iterate over all ports */
for (port = 0; port < qp->device->phys_port_cnt; port++)
- if (qp->device->get_link_layer(qp->device, port) !=
+ if (rdma_port_get_link_layer(qp->device, port) !=
IB_LINK_LAYER_INFINIBAND)
num_eth_ports++;
struct ib_device ibdev;
struct list_head list;
unsigned long flags;
-#define BNXT_RE_FLAG_NETDEV_REGISTERED 0
-#define BNXT_RE_FLAG_IBDEV_REGISTERED 1
-#define BNXT_RE_FLAG_GOT_MSIX 2
-#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 8
-#define BNXT_RE_FLAG_QOS_WORK_REG 16
+#define BNXT_RE_FLAG_NETDEV_REGISTERED 0
+#define BNXT_RE_FLAG_IBDEV_REGISTERED 1
+#define BNXT_RE_FLAG_GOT_MSIX 2
+#define BNXT_RE_FLAG_HAVE_L2_REF 3
+#define BNXT_RE_FLAG_RCFW_CHANNEL_EN 4
+#define BNXT_RE_FLAG_QOS_WORK_REG 5
+#define BNXT_RE_FLAG_TASK_IN_PROG 6
struct net_device *netdev;
unsigned int version, major, minor;
struct bnxt_en_dev *en_dev;
struct delayed_work worker;
u8 cur_prio_map;
+ u8 active_speed;
+ u8 active_width;
/* FP Notification Queue (CQ & SRQ) */
struct tasklet_struct nq_task;
port_attr->sm_sl = 0;
port_attr->subnet_timeout = 0;
port_attr->init_type_reply = 0;
- /* call the underlying netdev's ethtool hooks to query speed settings
- * for which we acquire rtnl_lock _only_ if it's registered with
- * IB stack to avoid race in the NETDEV_UNREG path
- */
- if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
- if (ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
- &port_attr->active_width))
- return -EINVAL;
+ port_attr->active_speed = rdev->active_speed;
+ port_attr->active_width = rdev->active_width;
+
return 0;
}
struct bnxt_re_gid_ctx *ctx, **ctx_tbl;
struct bnxt_re_dev *rdev = to_bnxt_re_dev(ibdev, ibdev);
struct bnxt_qplib_sgid_tbl *sgid_tbl = &rdev->qplib_res.sgid_tbl;
+ struct bnxt_qplib_gid *gid_to_del;
/* Delete the entry from the hardware */
ctx = *context;
if (sgid_tbl && sgid_tbl->active) {
if (ctx->idx >= sgid_tbl->max)
return -EINVAL;
+ gid_to_del = &sgid_tbl->tbl[ctx->idx];
+ /* DEL_GID is called in WQ context(netdevice_event_work_handler)
+ * or via the ib_unregister_device path. In the former case QP1
+ * may not be destroyed yet, in which case just return as FW
+ * needs that entry to be present and will fail it's deletion.
+ * We could get invoked again after QP1 is destroyed OR get an
+ * ADD_GID call with a different GID value for the same index
+ * where we issue MODIFY_GID cmd to update the GID entry -- TBD
+ */
+ if (ctx->idx == 0 &&
+ rdma_link_local_addr((struct in6_addr *)gid_to_del) &&
+ ctx->refcnt == 1 && rdev->qp1_sqp) {
+ dev_dbg(rdev_to_dev(rdev),
+ "Trying to delete GID0 while QP1 is alive\n");
+ return -EFAULT;
+ }
ctx->refcnt--;
if (!ctx->refcnt) {
- rc = bnxt_qplib_del_sgid(sgid_tbl,
- &sgid_tbl->tbl[ctx->idx],
- true);
+ rc = bnxt_qplib_del_sgid(sgid_tbl, gid_to_del, true);
if (rc) {
dev_err(rdev_to_dev(rdev),
"Failed to remove GID: %#x", rc);
kfree(rdev->sqp_ah);
kfree(rdev->qp1_sqp);
+ rdev->qp1_sqp = NULL;
+ rdev->sqp_ah = NULL;
}
if (!IS_ERR_OR_NULL(qp->rumem))
qp->qplib_qp.modify_flags |=
CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
qp->qplib_qp.path_mtu = __from_ib_mtu(qp_attr->path_mtu);
+ qp->qplib_qp.mtu = ib_mtu_enum_to_int(qp_attr->path_mtu);
} else if (qp_attr->qp_state == IB_QPS_RTR) {
qp->qplib_qp.modify_flags |=
CMDQ_MODIFY_QP_MODIFY_MASK_PATH_MTU;
qp->qplib_qp.path_mtu =
__from_ib_mtu(iboe_get_mtu(rdev->netdev->mtu));
+ qp->qplib_qp.mtu =
+ ib_mtu_enum_to_int(iboe_get_mtu(rdev->netdev->mtu));
}
if (qp_attr_mask & IB_QP_TIMEOUT) {
{
struct bnxt_re_qp *qp = container_of(ib_qp, struct bnxt_re_qp, ib_qp);
struct bnxt_re_dev *rdev = qp->rdev;
- struct bnxt_qplib_qp qplib_qp;
+ struct bnxt_qplib_qp *qplib_qp;
int rc;
- memset(&qplib_qp, 0, sizeof(struct bnxt_qplib_qp));
- qplib_qp.id = qp->qplib_qp.id;
- qplib_qp.ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
+ qplib_qp = kzalloc(sizeof(*qplib_qp), GFP_KERNEL);
+ if (!qplib_qp)
+ return -ENOMEM;
+
+ qplib_qp->id = qp->qplib_qp.id;
+ qplib_qp->ah.host_sgid_index = qp->qplib_qp.ah.host_sgid_index;
- rc = bnxt_qplib_query_qp(&rdev->qplib_res, &qplib_qp);
+ rc = bnxt_qplib_query_qp(&rdev->qplib_res, qplib_qp);
if (rc) {
dev_err(rdev_to_dev(rdev), "Failed to query HW QP");
- return rc;
+ goto out;
}
- qp_attr->qp_state = __to_ib_qp_state(qplib_qp.state);
- qp_attr->en_sqd_async_notify = qplib_qp.en_sqd_async_notify ? 1 : 0;
- qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp.access);
- qp_attr->pkey_index = qplib_qp.pkey_index;
- qp_attr->qkey = qplib_qp.qkey;
+ qp_attr->qp_state = __to_ib_qp_state(qplib_qp->state);
+ qp_attr->en_sqd_async_notify = qplib_qp->en_sqd_async_notify ? 1 : 0;
+ qp_attr->qp_access_flags = __to_ib_access_flags(qplib_qp->access);
+ qp_attr->pkey_index = qplib_qp->pkey_index;
+ qp_attr->qkey = qplib_qp->qkey;
qp_attr->ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
- rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp.ah.flow_label,
- qplib_qp.ah.host_sgid_index,
- qplib_qp.ah.hop_limit,
- qplib_qp.ah.traffic_class);
- rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp.ah.dgid.data);
- rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp.ah.sl);
- ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp.ah.dmac);
- qp_attr->path_mtu = __to_ib_mtu(qplib_qp.path_mtu);
- qp_attr->timeout = qplib_qp.timeout;
- qp_attr->retry_cnt = qplib_qp.retry_cnt;
- qp_attr->rnr_retry = qplib_qp.rnr_retry;
- qp_attr->min_rnr_timer = qplib_qp.min_rnr_timer;
- qp_attr->rq_psn = qplib_qp.rq.psn;
- qp_attr->max_rd_atomic = qplib_qp.max_rd_atomic;
- qp_attr->sq_psn = qplib_qp.sq.psn;
- qp_attr->max_dest_rd_atomic = qplib_qp.max_dest_rd_atomic;
- qp_init_attr->sq_sig_type = qplib_qp.sig_type ? IB_SIGNAL_ALL_WR :
- IB_SIGNAL_REQ_WR;
- qp_attr->dest_qp_num = qplib_qp.dest_qpn;
+ rdma_ah_set_grh(&qp_attr->ah_attr, NULL, qplib_qp->ah.flow_label,
+ qplib_qp->ah.host_sgid_index,
+ qplib_qp->ah.hop_limit,
+ qplib_qp->ah.traffic_class);
+ rdma_ah_set_dgid_raw(&qp_attr->ah_attr, qplib_qp->ah.dgid.data);
+ rdma_ah_set_sl(&qp_attr->ah_attr, qplib_qp->ah.sl);
+ ether_addr_copy(qp_attr->ah_attr.roce.dmac, qplib_qp->ah.dmac);
+ qp_attr->path_mtu = __to_ib_mtu(qplib_qp->path_mtu);
+ qp_attr->timeout = qplib_qp->timeout;
+ qp_attr->retry_cnt = qplib_qp->retry_cnt;
+ qp_attr->rnr_retry = qplib_qp->rnr_retry;
+ qp_attr->min_rnr_timer = qplib_qp->min_rnr_timer;
+ qp_attr->rq_psn = qplib_qp->rq.psn;
+ qp_attr->max_rd_atomic = qplib_qp->max_rd_atomic;
+ qp_attr->sq_psn = qplib_qp->sq.psn;
+ qp_attr->max_dest_rd_atomic = qplib_qp->max_dest_rd_atomic;
+ qp_init_attr->sq_sig_type = qplib_qp->sig_type ? IB_SIGNAL_ALL_WR :
+ IB_SIGNAL_REQ_WR;
+ qp_attr->dest_qp_num = qplib_qp->dest_qpn;
qp_attr->cap.max_send_wr = qp->qplib_qp.sq.max_wqe;
qp_attr->cap.max_send_sge = qp->qplib_qp.sq.max_sge;
qp_attr->cap.max_inline_data = qp->qplib_qp.max_inline_data;
qp_init_attr->cap = qp_attr->cap;
- return 0;
+out:
+ kfree(qplib_qp);
+ return rc;
}
/* Routine for sending QP1 packets for RoCE V1 an V2
switch (wr->opcode) {
case IB_WR_ATOMIC_CMP_AND_SWP:
wqe->type = BNXT_QPLIB_SWQE_TYPE_ATOMIC_CMP_AND_SWP;
+ wqe->atomic.cmp_data = atomic_wr(wr)->compare_add;
wqe->atomic.swap_data = atomic_wr(wr)->swap;
break;
case IB_WR_ATOMIC_FETCH_AND_ADD:
return rc;
}
- if (mr->npages && mr->pages) {
+ if (mr->pages) {
rc = bnxt_qplib_free_fast_reg_page_list(&rdev->qplib_res,
&mr->qplib_frpl);
kfree(mr->pages);
}
}
set_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags);
+ ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+ &rdev->active_width);
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_PORT_ACTIVE);
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, IB_EVENT_GID_CHANGE);
else if (netif_carrier_ok(rdev->netdev))
bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1,
IB_EVENT_PORT_ACTIVE);
+ ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed,
+ &rdev->active_width);
break;
default:
break;
}
+ smp_mb__before_atomic();
+ clear_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
kfree(re_work);
}
break;
case NETDEV_UNREGISTER:
+ /* netdev notifier will call NETDEV_UNREGISTER again later since
+ * we are still holding the reference to the netdev
+ */
+ if (test_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags))
+ goto exit;
bnxt_re_ib_unreg(rdev, false);
bnxt_re_remove_one(rdev);
bnxt_re_dev_unreg(rdev);
re_work->vlan_dev = (real_dev == netdev ?
NULL : netdev);
INIT_WORK(&re_work->work, bnxt_re_task);
+ set_bit(BNXT_RE_FLAG_TASK_IN_PROG, &rdev->flags);
queue_work(bnxt_re_wq, &re_work->work);
}
}
static void __exit bnxt_re_mod_exit(void)
{
+ struct bnxt_re_dev *rdev;
+ LIST_HEAD(to_be_deleted);
+
+ mutex_lock(&bnxt_re_dev_lock);
+ /* Free all adapter allocated resources */
+ if (!list_empty(&bnxt_re_dev_list))
+ list_splice_init(&bnxt_re_dev_list, &to_be_deleted);
+ mutex_unlock(&bnxt_re_dev_lock);
+
+ list_for_each_entry(rdev, &to_be_deleted, list) {
+ dev_info(rdev_to_dev(rdev), "Unregistering Device");
+ bnxt_re_dev_stop(rdev);
+ bnxt_re_ib_unreg(rdev, true);
+ bnxt_re_remove_one(rdev);
+ bnxt_re_dev_unreg(rdev);
+ }
unregister_netdevice_notifier(&bnxt_re_netdev_notifier);
if (bnxt_re_wq)
destroy_workqueue(bnxt_re_wq);
return -EINVAL;
}
+ if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags))
+ return -ETIMEDOUT;
+
/* Cmdq are in 16-byte units, each request can consume 1 or more
* cmdqe
*/
/* timed out */
dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec",
cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+ set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags);
return rc;
}
unsigned long *cmdq_bitmap;
u32 bmap_size;
unsigned long flags;
-#define FIRMWARE_INITIALIZED_FLAG 1
+#define FIRMWARE_INITIALIZED_FLAG BIT(0)
#define FIRMWARE_FIRST_FLAG BIT(31)
+#define FIRMWARE_TIMED_OUT BIT(3)
wait_queue_head_t waitq;
int (*aeq_handler)(struct bnxt_qplib_rcfw *,
struct creq_func_event *);
unsigned int stid = GET_TID(rpl);
struct c4iw_listen_ep *ep = get_ep_from_stid(dev, stid);
+ if (!ep) {
+ pr_debug("%s stid %d lookup failure!\n", __func__, stid);
+ goto out;
+ }
pr_debug("%s ep %p\n", __func__, ep);
c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
c4iw_put_ep(&ep->com);
+out:
return 0;
}
c4iw_put_ep(&child_ep->com);
reject:
reject_cr(dev, hwtid, skb);
+out:
if (parent_ep)
c4iw_put_ep(&parent_ep->com);
-out:
return 0;
}
cm_id->provider_data = ep;
goto out;
}
-
+ remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid,
ep->com.local_addr.ss_family);
fail2:
static int thermal_init(struct hfi1_devdata *dd);
static void update_statusp(struct hfi1_pportdata *ppd, u32 state);
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+ int msecs);
static int wait_logical_linkstate(struct hfi1_pportdata *ppd, u32 state,
int msecs);
static void log_state_transition(struct hfi1_pportdata *ppd, u32 state);
u64 regs[CCE_NUM_INT_CSRS];
u32 bit;
int i;
+ irqreturn_t handled = IRQ_NONE;
this_cpu_inc(*dd->int_counter);
for_each_set_bit(bit, (unsigned long *)®s[0],
CCE_NUM_INT_CSRS * 64) {
is_interrupt(dd, bit);
+ handled = IRQ_HANDLED;
}
- return IRQ_HANDLED;
+ return handled;
}
static irqreturn_t sdma_interrupt(int irq, void *data)
write_csr(dd, dd->hfi1_id ? ASIC_QSFP2_MASK : ASIC_QSFP1_MASK, mask);
}
-void reset_qsfp(struct hfi1_pportdata *ppd)
+int reset_qsfp(struct hfi1_pportdata *ppd)
{
struct hfi1_devdata *dd = ppd->dd;
u64 mask, qsfp_mask;
* for alarms and warnings
*/
set_qsfp_int_n(ppd, 1);
+
+ /*
+ * After the reset, AOC transmitters are enabled by default. They need
+ * to be turned off to complete the QSFP setup before they can be
+ * enabled again.
+ */
+ return set_qsfp_tx(ppd, 0);
}
static int handle_qsfp_error_conditions(struct hfi1_pportdata *ppd,
{
struct hfi1_devdata *dd = ppd->dd;
u32 previous_state;
+ int offline_state_ret;
int ret;
update_lcb_cache(dd);
ppd->offline_disabled_reason =
HFI1_ODR_MASK(OPA_LINKDOWN_REASON_TRANSIENT);
- /*
- * Wait for offline transition. It can take a while for
- * the link to go down.
- */
- ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 10000);
- if (ret < 0)
- return ret;
-
- /*
- * Now in charge of LCB - must be after the physical state is
- * offline.quiet and before host_link_state is changed.
- */
- set_host_lcb_access(dd);
- write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
-
- /* make sure the logical state is also down */
- ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
- if (ret)
- force_logical_link_state_down(ppd);
-
- ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+ offline_state_ret = wait_phys_link_offline_substates(ppd, 10000);
+ if (offline_state_ret < 0)
+ return offline_state_ret;
+ /* Disabling AOC transmitters */
if (ppd->port_type == PORT_TYPE_QSFP &&
ppd->qsfp_info.limiting_active &&
qsfp_mod_present(ppd)) {
}
}
+ /*
+ * Wait for the offline.Quiet transition if it hasn't happened yet. It
+ * can take a while for the link to go down.
+ */
+ if (offline_state_ret != PLS_OFFLINE_QUIET) {
+ ret = wait_physical_linkstate(ppd, PLS_OFFLINE, 30000);
+ if (ret < 0)
+ return ret;
+ }
+
+ /*
+ * Now in charge of LCB - must be after the physical state is
+ * offline.quiet and before host_link_state is changed.
+ */
+ set_host_lcb_access(dd);
+ write_csr(dd, DC_LCB_ERR_EN, ~0ull); /* watch LCB errors */
+
+ /* make sure the logical state is also down */
+ ret = wait_logical_linkstate(ppd, IB_PORT_DOWN, 1000);
+ if (ret)
+ force_logical_link_state_down(ppd);
+
+ ppd->host_link_state = HLS_LINK_COOLDOWN; /* LCB access allowed */
+
/*
* The LNI has a mandatory wait time after the physical state
* moves to Offline.Quiet. The wait time may be different
& (HLS_DN_POLL | HLS_VERIFY_CAP | HLS_GOING_UP)) {
/* went down while attempting link up */
check_lni_states(ppd);
+
+ /* The QSFP doesn't need to be reset on LNI failure */
+ ppd->qsfp_info.reset_needed = 0;
}
/* the active link width (downgrade) is 0 on link down */
return 0;
}
+/*
+ * wait_phys_link_offline_quiet_substates - wait for any offline substate
+ * @ppd: port device
+ * @msecs: the number of milliseconds to wait
+ *
+ * Wait up to msecs milliseconds for any offline physical link
+ * state change to occur.
+ * Returns 0 if at least one state is reached, otherwise -ETIMEDOUT.
+ */
+static int wait_phys_link_offline_substates(struct hfi1_pportdata *ppd,
+ int msecs)
+{
+ u32 read_state;
+ unsigned long timeout;
+
+ timeout = jiffies + msecs_to_jiffies(msecs);
+ while (1) {
+ read_state = read_physical_state(ppd->dd);
+ if ((read_state & 0xF0) == PLS_OFFLINE)
+ break;
+ if (time_after(jiffies, timeout)) {
+ dd_dev_err(ppd->dd,
+ "timeout waiting for phy link offline.quiet substates. Read state 0x%x, %dms\n",
+ read_state, msecs);
+ return -ETIMEDOUT;
+ }
+ usleep_range(1950, 2050); /* sleep 2ms-ish */
+ }
+
+ log_state_transition(ppd, read_state);
+ return read_state;
+}
+
#define CLEAR_STATIC_RATE_CONTROL_SMASK(r) \
(r &= ~SEND_CTXT_CHECK_ENABLE_DISALLOW_PBC_STATIC_RATE_CONTROL_SMASK)
#define PLS_OFFLINE_READY_TO_QUIET_LT 0x92
#define PLS_OFFLINE_REPORT_FAILURE 0x93
#define PLS_OFFLINE_READY_TO_QUIET_BCC 0x94
+#define PLS_OFFLINE_QUIET_DURATION 0x95
#define PLS_POLLING 0x20
#define PLS_POLLING_QUIET 0x20
#define PLS_POLLING_ACTIVE 0x21
void handle_link_bounce(struct work_struct *work);
void handle_start_link(struct work_struct *work);
void handle_sma_message(struct work_struct *work);
-void reset_qsfp(struct hfi1_pportdata *ppd);
+int reset_qsfp(struct hfi1_pportdata *ppd);
void qsfp_event(struct work_struct *work);
void start_freeze_handling(struct hfi1_pportdata *ppd, int flags);
int send_idle_sma(struct hfi1_devdata *dd, u64 message);
return ret;
}
-/* magic character sequence that trails an image */
+/* magic character sequence that begins an image */
+#define IMAGE_START_MAGIC "APO="
+
+/* magic character sequence that might trail an image */
#define IMAGE_TRAIL_MAGIC "egamiAPO"
/* EPROM file types */
{
void *buffer;
void *p;
+ u32 length;
int ret;
buffer = kmalloc(P1_SIZE, GFP_KERNEL);
return ret;
}
- /* scan for image magic that may trail the actual data */
- p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
- if (!p) {
+ /* config partition is valid only if it starts with IMAGE_START_MAGIC */
+ if (memcmp(buffer, IMAGE_START_MAGIC, strlen(IMAGE_START_MAGIC))) {
kfree(buffer);
return -ENOENT;
}
+ /* scan for image magic that may trail the actual data */
+ p = strnstr(buffer, IMAGE_TRAIL_MAGIC, P1_SIZE);
+ if (p)
+ length = p - buffer;
+ else
+ length = P1_SIZE;
+
*data = buffer;
- *size = p - buffer;
+ *size = length;
return 0;
}
switch (ret) {
case 0:
ret = setup_base_ctxt(fd, uctxt);
- if (uctxt->subctxt_cnt) {
- /*
- * Base context is done (successfully or not), notify
- * anybody using a sub-context that is waiting for
- * this completion.
- */
- clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
- wake_up(&uctxt->wait);
- }
+ if (ret)
+ deallocate_ctxt(uctxt);
break;
case 1:
ret = complete_subctxt(fd);
/* Now allocate the RcvHdr queue and eager buffers. */
ret = hfi1_create_rcvhdrq(dd, uctxt);
if (ret)
- return ret;
+ goto done;
ret = hfi1_setup_eagerbufs(uctxt);
if (ret)
- goto setup_failed;
+ goto done;
/* If sub-contexts are enabled, do the appropriate setup */
if (uctxt->subctxt_cnt)
ret = setup_subctxt(uctxt);
if (ret)
- goto setup_failed;
+ goto done;
ret = hfi1_alloc_ctxt_rcv_groups(uctxt);
if (ret)
- goto setup_failed;
+ goto done;
ret = init_user_ctxt(fd, uctxt);
if (ret)
- goto setup_failed;
+ goto done;
user_init(uctxt);
fd->uctxt = uctxt;
hfi1_rcd_get(uctxt);
- return 0;
+done:
+ if (uctxt->subctxt_cnt) {
+ /*
+ * On error, set the failed bit so sub-contexts will clean up
+ * correctly.
+ */
+ if (ret)
+ set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
-setup_failed:
- /* Set the failed bit so sub-context init can do the right thing */
- set_bit(HFI1_CTXT_BASE_FAILED, &uctxt->event_flags);
- deallocate_ctxt(uctxt);
+ /*
+ * Base context is done (successfully or not), notify anybody
+ * using a sub-context that is waiting for this completion.
+ */
+ clear_bit(HFI1_CTXT_BASE_UNINIT, &uctxt->event_flags);
+ wake_up(&uctxt->wait);
+ }
return ret;
}
/*
* Code to adjust PCIe capabilities.
*/
-static int tune_pcie_caps(struct hfi1_devdata *);
+static void tune_pcie_caps(struct hfi1_devdata *);
/*
* Do all the common PCIe setup and initialization.
*/
int request_msix(struct hfi1_devdata *dd, u32 msireq)
{
- int nvec, ret;
+ int nvec;
nvec = pci_alloc_irq_vectors(dd->pcidev, 1, msireq,
PCI_IRQ_MSIX | PCI_IRQ_LEGACY);
return nvec;
}
- ret = tune_pcie_caps(dd);
- if (ret) {
- dd_dev_err(dd, "tune_pcie_caps() failed: %d\n", ret);
- pci_free_irq_vectors(dd->pcidev);
- return ret;
- }
+ tune_pcie_caps(dd);
/* check for legacy IRQ */
if (nvec == 1 && !dd->pcidev->msix_enabled)
module_param_named(aspm, aspm_mode, uint, S_IRUGO);
MODULE_PARM_DESC(aspm, "PCIe ASPM: 0: disable, 1: enable, 2: dynamic");
-static int tune_pcie_caps(struct hfi1_devdata *dd)
+static void tune_pcie_caps(struct hfi1_devdata *dd)
{
struct pci_dev *parent;
u16 rc_mpss, rc_mps, ep_mpss, ep_mps;
* Turn on extended tags in DevCtl in case the BIOS has turned it off
* to improve WFR SDMA bandwidth
*/
- ret = pcie_capability_read_word(dd->pcidev,
- PCI_EXP_DEVCTL, &ectl);
- if (ret) {
- dd_dev_err(dd, "Unable to read from PCI config\n");
- return ret;
- }
-
- if (!(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
+ ret = pcie_capability_read_word(dd->pcidev, PCI_EXP_DEVCTL, &ectl);
+ if ((!ret) && !(ectl & PCI_EXP_DEVCTL_EXT_TAG)) {
dd_dev_info(dd, "Enabling PCIe extended tags\n");
ectl |= PCI_EXP_DEVCTL_EXT_TAG;
ret = pcie_capability_write_word(dd->pcidev,
PCI_EXP_DEVCTL, ectl);
- if (ret) {
- dd_dev_err(dd, "Unable to write to PCI config\n");
- return ret;
- }
+ if (ret)
+ dd_dev_info(dd, "Unable to write to PCI config\n");
}
/* Find out supported and configured values for parent (root) */
parent = dd->pcidev->bus->self;
* The driver cannot perform the tuning if it does not have
* access to the upstream component.
*/
- if (!parent)
- return -EINVAL;
+ if (!parent) {
+ dd_dev_info(dd, "Parent not found\n");
+ return;
+ }
if (!pci_is_root_bus(parent->bus)) {
dd_dev_info(dd, "Parent not root\n");
- return -EINVAL;
+ return;
+ }
+ if (!pci_is_pcie(parent)) {
+ dd_dev_info(dd, "Parent is not PCI Express capable\n");
+ return;
+ }
+ if (!pci_is_pcie(dd->pcidev)) {
+ dd_dev_info(dd, "PCI device is not PCI Express capable\n");
+ return;
}
-
- if (!pci_is_pcie(parent) || !pci_is_pcie(dd->pcidev))
- return -EINVAL;
rc_mpss = parent->pcie_mpss;
rc_mps = ffs(pcie_get_mps(parent)) - 8;
/* Find out supported and configured values for endpoint (us) */
ep_mrrs = max_mrrs;
pcie_set_readrq(dd->pcidev, ep_mrrs);
}
-
- return 0;
}
/* End of PCIe capability tuning */
* reuse of stale settings established in our previous pass through.
*/
if (ppd->qsfp_info.reset_needed) {
- reset_qsfp(ppd);
+ ret = reset_qsfp(ppd);
+ if (ret)
+ return ret;
refresh_qsfp_cache(ppd, &ppd->qsfp_info);
} else {
ppd->qsfp_info.reset_needed = 1;
CEQ_CREATED,
ILQ_CREATED,
IEQ_CREATED,
- INET_NOTIFIER,
IP_ADDR_REGISTERED,
RDMA_DEV_REGISTERED
};
}
/**
- * listen_port_in_use - determine if port is in use
- * @port: Listen port number
+ * i40iw_port_in_use - determine if port is in use
+ * @port: port number
+ * @active_side: flag for listener side vs active side
*/
-static bool i40iw_listen_port_in_use(struct i40iw_cm_core *cm_core, u16 port)
+static bool i40iw_port_in_use(struct i40iw_cm_core *cm_core, u16 port, bool active_side)
{
struct i40iw_cm_listener *listen_node;
+ struct i40iw_cm_node *cm_node;
unsigned long flags;
bool ret = false;
- spin_lock_irqsave(&cm_core->listen_list_lock, flags);
- list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
- if (listen_node->loc_port == port) {
- ret = true;
- break;
+ if (active_side) {
+ /* search connected node list */
+ spin_lock_irqsave(&cm_core->ht_lock, flags);
+ list_for_each_entry(cm_node, &cm_core->connected_nodes, list) {
+ if (cm_node->loc_port == port) {
+ ret = true;
+ break;
+ }
+ }
+ if (!ret)
+ clear_bit(port, cm_core->active_side_ports);
+ spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+ } else {
+ spin_lock_irqsave(&cm_core->listen_list_lock, flags);
+ list_for_each_entry(listen_node, &cm_core->listen_nodes, list) {
+ if (listen_node->loc_port == port) {
+ ret = true;
+ break;
+ }
}
+ spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
}
- spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
+
return ret;
}
spin_unlock_irqrestore(&cm_core->listen_list_lock, flags);
if (listener->iwdev) {
- if (apbvt_del && !i40iw_listen_port_in_use(cm_core, listener->loc_port))
+ if (apbvt_del && !i40iw_port_in_use(cm_core, listener->loc_port, false))
i40iw_manage_apbvt(listener->iwdev,
listener->loc_port,
I40IW_MANAGE_APBVT_DEL);
if (cm_node->listener) {
i40iw_dec_refcnt_listen(cm_core, cm_node->listener, 0, true);
} else {
- if (!i40iw_listen_port_in_use(cm_core, cm_node->loc_port) &&
- cm_node->apbvt_set) {
+ if (!i40iw_port_in_use(cm_core, cm_node->loc_port, true) && cm_node->apbvt_set) {
i40iw_manage_apbvt(cm_node->iwdev,
cm_node->loc_port,
I40IW_MANAGE_APBVT_DEL);
- i40iw_get_addr_info(cm_node, &nfo);
- if (cm_node->qhash_set) {
- i40iw_manage_qhash(cm_node->iwdev,
- &nfo,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
- cm_node->qhash_set = 0;
- }
+ cm_node->apbvt_set = 0;
+ }
+ i40iw_get_addr_info(cm_node, &nfo);
+ if (cm_node->qhash_set) {
+ i40iw_manage_qhash(cm_node->iwdev,
+ &nfo,
+ I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+ I40IW_QHASH_MANAGE_TYPE_DELETE,
+ NULL,
+ false);
+ cm_node->qhash_set = 0;
}
}
tcp_info->snd_mss = cpu_to_le32(((u32)cm_node->tcp_cntxt.mss));
if (cm_node->vlan_id < VLAN_TAG_PRESENT) {
tcp_info->insert_vlan_tag = true;
- tcp_info->vlan_tag = cpu_to_le16(cm_node->vlan_id);
+ tcp_info->vlan_tag = cpu_to_le16(((u16)cm_node->user_pri << I40IW_VLAN_PRIO_SHIFT) |
+ cm_node->vlan_id);
}
if (cm_node->ipv4) {
tcp_info->src_port = cpu_to_le16(cm_node->loc_port);
struct sockaddr_in *raddr;
struct sockaddr_in6 *laddr6;
struct sockaddr_in6 *raddr6;
- bool qhash_set = false;
- int apbvt_set = 0;
- int err = 0;
- enum i40iw_status_code status;
+ int ret = 0;
+ unsigned long flags;
ibqp = i40iw_get_qp(cm_id->device, conn_param->qpn);
if (!ibqp)
cm_info.user_pri = rt_tos2priority(cm_id->tos);
i40iw_debug(&iwdev->sc_dev, I40IW_DEBUG_DCB, "%s TOS:[%d] UP:[%d]\n",
__func__, cm_id->tos, cm_info.user_pri);
- if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
- (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
- raddr6->sin6_addr.in6_u.u6_addr32,
- sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
- status = i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_ADD,
- NULL,
- true);
- if (status)
- return -EINVAL;
- qhash_set = true;
- }
- status = i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD);
- if (status) {
- i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
- return -EINVAL;
- }
-
- apbvt_set = 1;
cm_id->add_ref(cm_id);
cm_node = i40iw_create_cm_node(&iwdev->cm_core, iwdev,
conn_param->private_data_len,
&cm_info);
if (IS_ERR(cm_node)) {
- err = PTR_ERR(cm_node);
- goto err_out;
+ ret = PTR_ERR(cm_node);
+ cm_id->rem_ref(cm_id);
+ return ret;
+ }
+
+ if ((cm_info.ipv4 && (laddr->sin_addr.s_addr != raddr->sin_addr.s_addr)) ||
+ (!cm_info.ipv4 && memcmp(laddr6->sin6_addr.in6_u.u6_addr32,
+ raddr6->sin6_addr.in6_u.u6_addr32,
+ sizeof(laddr6->sin6_addr.in6_u.u6_addr32)))) {
+ if (i40iw_manage_qhash(iwdev, &cm_info, I40IW_QHASH_TYPE_TCP_ESTABLISHED,
+ I40IW_QHASH_MANAGE_TYPE_ADD, NULL, true)) {
+ ret = -EINVAL;
+ goto err;
+ }
+ cm_node->qhash_set = true;
}
+ spin_lock_irqsave(&iwdev->cm_core.ht_lock, flags);
+ if (!test_and_set_bit(cm_info.loc_port, iwdev->cm_core.active_side_ports)) {
+ spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+ if (i40iw_manage_apbvt(iwdev, cm_info.loc_port, I40IW_MANAGE_APBVT_ADD)) {
+ ret = -EINVAL;
+ goto err;
+ }
+ } else {
+ spin_unlock_irqrestore(&iwdev->cm_core.ht_lock, flags);
+ }
+
+ cm_node->apbvt_set = true;
i40iw_record_ird_ord(cm_node, (u16)conn_param->ird, (u16)conn_param->ord);
if (cm_node->send_rdma0_op == SEND_RDMA_READ_ZERO &&
!cm_node->ord_size)
cm_node->ord_size = 1;
- cm_node->apbvt_set = apbvt_set;
- cm_node->qhash_set = qhash_set;
iwqp->cm_node = cm_node;
cm_node->iwqp = iwqp;
iwqp->cm_id = cm_id;
if (cm_node->state != I40IW_CM_STATE_OFFLOADED) {
cm_node->state = I40IW_CM_STATE_SYN_SENT;
- err = i40iw_send_syn(cm_node, 0);
- if (err) {
- i40iw_rem_ref_cm_node(cm_node);
- goto err_out;
- }
+ ret = i40iw_send_syn(cm_node, 0);
+ if (ret)
+ goto err;
}
i40iw_debug(cm_node->dev,
cm_node->rem_port,
cm_node,
cm_node->cm_id);
+
return 0;
-err_out:
+err:
if (cm_info.ipv4)
i40iw_debug(&iwdev->sc_dev,
I40IW_DEBUG_CM,
"Api - connect() FAILED: dest addr=%pI6",
cm_info.rem_addr);
- if (qhash_set)
- i40iw_manage_qhash(iwdev,
- &cm_info,
- I40IW_QHASH_TYPE_TCP_ESTABLISHED,
- I40IW_QHASH_MANAGE_TYPE_DELETE,
- NULL,
- false);
-
- if (apbvt_set && !i40iw_listen_port_in_use(&iwdev->cm_core,
- cm_info.loc_port))
- i40iw_manage_apbvt(iwdev,
- cm_info.loc_port,
- I40IW_MANAGE_APBVT_DEL);
+ i40iw_rem_ref_cm_node(cm_node);
cm_id->rem_ref(cm_id);
iwdev->cm_core.stats_connect_errs++;
- return err;
+ return ret;
}
/**
#define I40IW_HW_IRD_SETTING_32 32
#define I40IW_HW_IRD_SETTING_64 64
+#define MAX_PORTS 65536
+#define I40IW_VLAN_PRIO_SHIFT 13
+
enum ietf_mpa_flags {
IETF_MPA_FLAGS_MARKERS = 0x80, /* receive Markers */
IETF_MPA_FLAGS_CRC = 0x40, /* receive Markers */
spinlock_t ht_lock; /* manage hash table */
spinlock_t listen_list_lock; /* listen list */
+ unsigned long active_side_ports[BITS_TO_LONGS(MAX_PORTS)];
+
u64 stats_nodes_created;
u64 stats_nodes_destroyed;
u64 stats_listen_created;
.notifier_call = i40iw_net_event
};
-static atomic_t i40iw_notifiers_registered;
-
/**
* i40iw_find_i40e_handler - find a handler given a client info
* @ldev: pointer to a client info
*/
static void i40iw_register_notifiers(void)
{
- if (atomic_inc_return(&i40iw_notifiers_registered) == 1) {
- register_inetaddr_notifier(&i40iw_inetaddr_notifier);
- register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
- register_netevent_notifier(&i40iw_net_notifier);
- }
+ register_inetaddr_notifier(&i40iw_inetaddr_notifier);
+ register_inet6addr_notifier(&i40iw_inetaddr6_notifier);
+ register_netevent_notifier(&i40iw_net_notifier);
+}
+
+/**
+ * i40iw_unregister_notifiers - unregister tcp ip notifiers
+ */
+
+static void i40iw_unregister_notifiers(void)
+{
+ unregister_netevent_notifier(&i40iw_net_notifier);
+ unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
+ unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
}
/**
u32 i;
u32 size;
+ if (!ldev->msix_count) {
+ i40iw_pr_err("No MSI-X vectors\n");
+ return I40IW_ERR_CONFIG;
+ }
+
iwdev->msix_count = ldev->msix_count;
size = sizeof(struct i40iw_msix_vector) * iwdev->msix_count;
if (!iwdev->reset)
i40iw_del_macip_entry(iwdev, (u8)iwdev->mac_ip_table_idx);
/* fallthrough */
- case INET_NOTIFIER:
- if (!atomic_dec_return(&i40iw_notifiers_registered)) {
- unregister_netevent_notifier(&i40iw_net_notifier);
- unregister_inetaddr_notifier(&i40iw_inetaddr_notifier);
- unregister_inet6addr_notifier(&i40iw_inetaddr6_notifier);
- }
/* fallthrough */
case PBLE_CHUNK_MEM:
i40iw_destroy_pble_pool(dev, iwdev->pble_rsrc);
status = i40iw_save_msix_info(iwdev, ldev);
if (status)
- goto exit;
+ return status;
iwdev->hw.dev_context = (void *)ldev->pcidev;
iwdev->hw.hw_addr = ldev->hw_addr;
status = i40iw_allocate_dma_mem(&iwdev->hw,
break;
iwdev->init_state = PBLE_CHUNK_MEM;
iwdev->virtchnl_wq = alloc_ordered_workqueue("iwvch", WQ_MEM_RECLAIM);
- i40iw_register_notifiers();
- iwdev->init_state = INET_NOTIFIER;
status = i40iw_add_mac_ip(iwdev);
if (status)
break;
i40iw_client.type = I40E_CLIENT_IWARP;
spin_lock_init(&i40iw_handler_lock);
ret = i40e_register_client(&i40iw_client);
+ i40iw_register_notifiers();
+
return ret;
}
*/
static void __exit i40iw_exit_module(void)
{
+ i40iw_unregister_notifiers();
i40e_unregister_client(&i40iw_client);
}
return NOTIFY_DONE;
iwdev = &hdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
netdev = iwdev->ldev->netdev;
return NOTIFY_DONE;
iwdev = &hdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
netdev = iwdev->ldev->netdev;
if (!iwhdl)
return NOTIFY_DONE;
iwdev = &iwhdl->device;
- if (iwdev->init_state < INET_NOTIFIER)
+ if (iwdev->init_state < IP_ADDR_REGISTERED || iwdev->closing)
return NOTIFY_DONE;
p = (__be32 *)neigh->primary_key;
i40iw_copy_ip_ntohl(local_ipaddr, p);
iwqp->hw_tcp_state = I40IW_TCP_STATE_CLOSED;
iwqp->last_aeq = I40IW_AE_RESET_SENT;
spin_unlock_irqrestore(&iwqp->lock, flags);
+ i40iw_cm_disconn(iwqp);
}
+ } else {
+ spin_lock_irqsave(&iwqp->lock, flags);
+ if (iwqp->cm_id) {
+ if (atomic_inc_return(&iwqp->close_timer_started) == 1) {
+ iwqp->cm_id->add_ref(iwqp->cm_id);
+ i40iw_schedule_cm_timer(iwqp->cm_node,
+ (struct i40iw_puda_buf *)iwqp,
+ I40IW_TIMER_TYPE_CLOSE, 1, 0);
+ }
+ }
+ spin_unlock_irqrestore(&iwqp->lock, flags);
}
}
return 0;
}
if (MLX5_CAP_GEN(mdev, tag_matching)) {
- props->xrq_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
- props->xrq_caps.max_num_tags =
+ props->tm_caps.max_rndv_hdr_size = MLX5_TM_MAX_RNDV_MSG_SIZE;
+ props->tm_caps.max_num_tags =
(1 << MLX5_CAP_GEN(mdev, log_tag_matching_list_sz)) - 1;
- props->xrq_caps.flags = IB_TM_CAP_RC;
- props->xrq_caps.max_ops =
+ props->tm_caps.flags = IB_TM_CAP_RC;
+ props->tm_caps.max_ops =
1 << MLX5_CAP_GEN(mdev, log_max_qp_sz);
- props->xrq_caps.max_sge = MLX5_TM_MAX_SGE;
+ props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
}
if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
if (!dbg)
return -ENOMEM;
+ dev->delay_drop.dbg = dbg;
+
dbg->dir_debugfs =
debugfs_create_dir("delay_drop",
dev->mdev->priv.dbg_root);
if (!dbg->dir_debugfs)
- return -ENOMEM;
+ goto out_debugfs;
dbg->events_cnt_debugfs =
debugfs_create_atomic_t("num_timeout_events", 0400,
if (!dbg->timeout_debugfs)
goto out_debugfs;
- dev->delay_drop.dbg = dbg;
-
return 0;
out_debugfs:
{
unsigned long tmp;
unsigned long m;
- int i, k;
- u64 base = 0;
- int p = 0;
- int skip;
- int mask;
- u64 len;
- u64 pfn;
+ u64 base = ~0, p = 0;
+ u64 len, pfn;
+ int i = 0;
struct scatterlist *sg;
int entry;
unsigned long page_shift = umem->page_shift;
m = find_first_bit(&tmp, BITS_PER_LONG);
if (max_page_shift)
m = min_t(unsigned long, max_page_shift - page_shift, m);
- skip = 1 << m;
- mask = skip - 1;
- i = 0;
+
for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
len = sg_dma_len(sg) >> page_shift;
pfn = sg_dma_address(sg) >> page_shift;
- for (k = 0; k < len; k++) {
- if (!(i & mask)) {
- tmp = (unsigned long)pfn;
- m = min_t(unsigned long, m, find_first_bit(&tmp, BITS_PER_LONG));
- skip = 1 << m;
- mask = skip - 1;
- base = pfn;
- p = 0;
- } else {
- if (base + p != pfn) {
- tmp = (unsigned long)p;
- m = find_first_bit(&tmp, BITS_PER_LONG);
- skip = 1 << m;
- mask = skip - 1;
- base = pfn;
- p = 0;
- }
- }
- p++;
- i++;
+ if (base + p != pfn) {
+ /* If either the offset or the new
+ * base are unaligned update m
+ */
+ tmp = (unsigned long)(pfn | p);
+ if (!IS_ALIGNED(tmp, 1 << m))
+ m = find_first_bit(&tmp, BITS_PER_LONG);
+
+ base = pfn;
+ p = 0;
}
+
+ p += len;
+ i += len;
}
if (i) {
#define MLX5_UMR_ALIGN 2048
-static int clean_mr(struct mlx5_ib_mr *mr);
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
static int mr_cache_max_order(struct mlx5_ib_dev *dev);
static int unreg_umr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr);
err = mlx5_ib_update_xlt(mr, 0, ncont, page_shift,
update_xlt_flags);
+
if (err) {
- mlx5_ib_dereg_mr(&mr->ibmr);
+ dereg_mr(dev, mr);
return ERR_PTR(err);
}
}
err = mr_umem_get(pd, addr, len, access_flags, &mr->umem,
&npages, &page_shift, &ncont, &order);
if (err < 0) {
- clean_mr(mr);
+ clean_mr(dev, mr);
return err;
}
}
if (err) {
mlx5_ib_warn(dev, "Failed to rereg UMR\n");
ib_umem_release(mr->umem);
- clean_mr(mr);
+ clean_mr(dev, mr);
return err;
}
}
}
}
-static int clean_mr(struct mlx5_ib_mr *mr)
+static int clean_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
{
- struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
int allocated_from_cache = mr->allocated_from_cache;
int err;
return 0;
}
-int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+static int dereg_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
{
- struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
- struct mlx5_ib_mr *mr = to_mmr(ibmr);
int npages = mr->npages;
struct ib_umem *umem = mr->umem;
}
#endif
- clean_mr(mr);
+ clean_mr(dev, mr);
if (umem) {
ib_umem_release(umem);
return 0;
}
+int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
+{
+ struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+ struct mlx5_ib_mr *mr = to_mmr(ibmr);
+
+ return dereg_mr(dev, mr);
+}
+
struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd,
enum ib_mr_type mr_type,
u32 max_num_sg)
mr->ibmr.iova);
set_wqe_32bit_value(wqe->wqe_words,
NES_IWARP_SQ_FMR_WQE_LENGTH_LOW_IDX,
- mr->ibmr.length);
+ lower_32_bits(mr->ibmr.length));
set_wqe_32bit_value(wqe->wqe_words,
NES_IWARP_SQ_FMR_WQE_LENGTH_HIGH_IDX, 0);
set_wqe_32bit_value(wqe->wqe_words,
mr->npages * 8);
nes_debug(NES_DBG_IW_TX, "SQ_REG_MR: iova_start: %llx, "
- "length: %d, rkey: %0x, pgl_paddr: %llx, "
+ "length: %lld, rkey: %0x, pgl_paddr: %llx, "
"page_list_len: %u, wqe_misc: %x\n",
(unsigned long long) mr->ibmr.iova,
mr->ibmr.length,
case OCRDMA_MBX_ADDI_STATUS_INSUFFICIENT_RESOURCES:
err_num = -EAGAIN;
break;
+ default:
+ err_num = -EFAULT;
}
+ break;
default:
err_num = -EFAULT;
}
return (enum ib_wc_status)status;
}
-static inline int pvrdma_wc_opcode_to_ib(int opcode)
-{
- return opcode;
+static inline int pvrdma_wc_opcode_to_ib(unsigned int opcode)
+{
+ switch (opcode) {
+ case PVRDMA_WC_SEND:
+ return IB_WC_SEND;
+ case PVRDMA_WC_RDMA_WRITE:
+ return IB_WC_RDMA_WRITE;
+ case PVRDMA_WC_RDMA_READ:
+ return IB_WC_RDMA_READ;
+ case PVRDMA_WC_COMP_SWAP:
+ return IB_WC_COMP_SWAP;
+ case PVRDMA_WC_FETCH_ADD:
+ return IB_WC_FETCH_ADD;
+ case PVRDMA_WC_LOCAL_INV:
+ return IB_WC_LOCAL_INV;
+ case PVRDMA_WC_FAST_REG_MR:
+ return IB_WC_REG_MR;
+ case PVRDMA_WC_MASKED_COMP_SWAP:
+ return IB_WC_MASKED_COMP_SWAP;
+ case PVRDMA_WC_MASKED_FETCH_ADD:
+ return IB_WC_MASKED_FETCH_ADD;
+ case PVRDMA_WC_RECV:
+ return IB_WC_RECV;
+ case PVRDMA_WC_RECV_RDMA_WITH_IMM:
+ return IB_WC_RECV_RDMA_WITH_IMM;
+ default:
+ return IB_WC_SEND;
+ }
}
static inline int pvrdma_wc_flags_to_ib(int flags)
wc->status != IB_WC_WR_FLUSH_ERR) {
struct ipoib_neigh *neigh;
- if (wc->status != IB_WC_RNR_RETRY_EXC_ERR)
- ipoib_warn(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
- wc->status, wr_id, wc->vendor_err);
+ /* IB_WC[_RNR]_RETRY_EXC_ERR error is part of the life cycle,
+ * so don't make waves.
+ */
+ if (wc->status == IB_WC_RNR_RETRY_EXC_ERR ||
+ wc->status == IB_WC_RETRY_EXC_ERR)
+ ipoib_dbg(priv,
+ "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+ __func__, wc->status, wr_id, wc->vendor_err);
else
- ipoib_dbg(priv, "failed cm send event (status=%d, wrid=%d vend_err %x)\n",
- wc->status, wr_id, wc->vendor_err);
+ ipoib_warn(priv,
+ "%s: failed cm send event (status=%d, wrid=%d vend_err 0x%x)\n",
+ __func__, wc->status, wr_id, wc->vendor_err);
spin_lock_irqsave(&priv->lock, flags);
neigh = tx->neigh;
*/
priv->dev->broadcast[8] = priv->pkey >> 8;
priv->dev->broadcast[9] = priv->pkey & 0xff;
-
- /*
- * Update the broadcast address in the priv->broadcast object,
- * in case it already exists, otherwise no one will do that.
- */
- if (priv->broadcast) {
- spin_lock_irq(&priv->lock);
- memcpy(priv->broadcast->mcmember.mgid.raw,
- priv->dev->broadcast + 4,
- sizeof(union ib_gid));
- spin_unlock_irq(&priv->lock);
- }
-
return 0;
}
{
struct ipoib_dev_priv *priv;
struct ib_port_attr attr;
+ struct rdma_netdev *rn;
int result = -ENOMEM;
priv = ipoib_intf_alloc(hca, port, format);
ipoib_dev_cleanup(priv->dev);
device_init_failed:
- free_netdev(priv->dev);
+ rn = netdev_priv(priv->dev);
+ rn->free_rdma_netdev(priv->dev);
kfree(priv);
alloc_mem_failed:
return;
list_for_each_entry_safe(priv, tmp, dev_list, list) {
- struct rdma_netdev *rn = netdev_priv(priv->dev);
+ struct rdma_netdev *parent_rn = netdev_priv(priv->dev);
ib_unregister_event_handler(&priv->event_handler);
flush_workqueue(ipoib_workqueue);
unregister_netdev(priv->dev);
mutex_unlock(&priv->sysfs_mutex);
- rn->free_rdma_netdev(priv->dev);
+ parent_rn->free_rdma_netdev(priv->dev);
+
+ list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
+ struct rdma_netdev *child_rn;
- list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list)
+ child_rn = netdev_priv(cpriv->dev);
+ child_rn->free_rdma_netdev(cpriv->dev);
kfree(cpriv);
+ }
kfree(priv);
}
return restart_syscall();
}
- priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
- if (!priv) {
+ if (!down_write_trylock(&ppriv->vlan_rwsem)) {
rtnl_unlock();
mutex_unlock(&ppriv->sysfs_mutex);
- return -ENOMEM;
+ return restart_syscall();
}
- down_write(&ppriv->vlan_rwsem);
+ priv = ipoib_intf_alloc(ppriv->ca, ppriv->port, intf_name);
+ if (!priv) {
+ result = -ENOMEM;
+ goto out;
+ }
/*
* First ensure this isn't a duplicate. We check the parent device and
rtnl_unlock();
mutex_unlock(&ppriv->sysfs_mutex);
- if (result) {
- free_netdev(priv->dev);
+ if (result && priv) {
+ struct rdma_netdev *rn;
+
+ rn = netdev_priv(priv->dev);
+ rn->free_rdma_netdev(priv->dev);
kfree(priv);
}
return restart_syscall();
}
- down_write(&ppriv->vlan_rwsem);
+ if (!down_write_trylock(&ppriv->vlan_rwsem)) {
+ rtnl_unlock();
+ mutex_unlock(&ppriv->sysfs_mutex);
+ return restart_syscall();
+ }
+
list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
if (priv->pkey == pkey &&
priv->child_type == IPOIB_LEGACY_CHILD) {
mutex_unlock(&ppriv->sysfs_mutex);
if (dev) {
- free_netdev(dev);
+ struct rdma_netdev *rn;
+
+ rn = netdev_priv(dev);
+ rn->free_rdma_netdev(priv->dev);
kfree(priv);
return 0;
}
{
int i;
- iser_err("page vec npages %d data length %d\n",
+ iser_err("page vec npages %d data length %lld\n",
page_vec->npages, page_vec->fake_mr.length);
for (i = 0; i < page_vec->npages; i++)
iser_err("vec[%d]: %llx\n", i, page_vec->pages[i]);
EXPORT_SYMBOL_GPL(input_ff_erase);
/*
- * flush_effects - erase all effects owned by a file handle
+ * input_ff_flush - erase all effects owned by a file handle
+ * @dev: input device to erase effect from
+ * @file: purported owner of the effects
+ *
+ * This function erases all force-feedback effects associated with
+ * the given owner from specified device. Note that @file may be %NULL,
+ * in which case all effects will be erased.
*/
-static int flush_effects(struct input_dev *dev, struct file *file)
+int input_ff_flush(struct input_dev *dev, struct file *file)
{
struct ff_device *ff = dev->ff;
int i;
return 0;
}
+EXPORT_SYMBOL_GPL(input_ff_flush);
/**
* input_ff_event() - generic handler for force-feedback events
mutex_init(&ff->mutex);
dev->ff = ff;
- dev->flush = flush_effects;
+ dev->flush = input_ff_flush;
dev->event = input_ff_event;
__set_bit(EV_FF, dev->evbit);
uinput_request_alloc_id(udev, request));
}
-static void uinput_request_done(struct uinput_device *udev,
- struct uinput_request *request)
+static void uinput_request_release_slot(struct uinput_device *udev,
+ unsigned int id)
{
/* Mark slot as available */
- udev->requests[request->id] = NULL;
- wake_up(&udev->requests_waitq);
+ spin_lock(&udev->requests_lock);
+ udev->requests[id] = NULL;
+ spin_unlock(&udev->requests_lock);
- complete(&request->done);
+ wake_up(&udev->requests_waitq);
}
static int uinput_request_send(struct uinput_device *udev,
static int uinput_request_submit(struct uinput_device *udev,
struct uinput_request *request)
{
- int error;
+ int retval;
- error = uinput_request_reserve_slot(udev, request);
- if (error)
- return error;
+ retval = uinput_request_reserve_slot(udev, request);
+ if (retval)
+ return retval;
- error = uinput_request_send(udev, request);
- if (error) {
- uinput_request_done(udev, request);
- return error;
- }
+ retval = uinput_request_send(udev, request);
+ if (retval)
+ goto out;
wait_for_completion(&request->done);
- return request->retval;
+ retval = request->retval;
+
+ out:
+ uinput_request_release_slot(udev, request->id);
+ return retval;
}
/*
request = udev->requests[i];
if (request) {
request->retval = -ENODEV;
- uinput_request_done(udev, request);
+ complete(&request->done);
}
}
return uinput_request_submit(udev, &request);
}
+static int uinput_dev_flush(struct input_dev *dev, struct file *file)
+{
+ /*
+ * If we are called with file == NULL that means we are tearing
+ * down the device, and therefore we can not handle FF erase
+ * requests: either we are handling UI_DEV_DESTROY (and holding
+ * the udev->mutex), or the file descriptor is closed and there is
+ * nobody on the other side anymore.
+ */
+ return file ? input_ff_flush(dev, file) : 0;
+}
+
static void uinput_destroy_device(struct uinput_device *udev)
{
const char *name, *phys;
dev->ff->playback = uinput_dev_playback;
dev->ff->set_gain = uinput_dev_set_gain;
dev->ff->set_autocenter = uinput_dev_set_autocenter;
+ /*
+ * The standard input_ff_flush() implementation does
+ * not quite work for uinput as we can't reasonably
+ * handle FF requests during device teardown.
+ */
+ dev->flush = uinput_dev_flush;
}
error = input_register_device(udev->dev);
}
req->retval = ff_up.retval;
- uinput_request_done(udev, req);
+ complete(&req->done);
goto out;
case UI_END_FF_ERASE:
}
req->retval = ff_erase.retval;
- uinput_request_done(udev, req);
+ complete(&req->done);
goto out;
}
}
/* Wait for F/W to update one page ROM data. */
- msleep(20);
+ msleep(35);
error = elan_i2c_read_cmd(client, ETP_I2C_IAP_CTRL_CMD, val);
if (error) {
config IPMMU_VMSA
bool "Renesas VMSA-compatible IPMMU"
depends on ARM || IOMMU_DMA
- depends on ARCH_RENESAS || COMPILE_TEST
+ depends on ARCH_RENESAS || (COMPILE_TEST && !GENERIC_ATOMIC64)
select IOMMU_API
select IOMMU_IO_PGTABLE_LPAE
select ARM_DMA_USE_IOMMU
config QCOM_IOMMU
# Note: iommu drivers cannot (yet?) be built as modules
bool "Qualcomm IOMMU Support"
- depends on ARCH_QCOM || COMPILE_TEST
+ depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64)
+ depends on HAS_DMA
select IOMMU_API
select IOMMU_IO_PGTABLE_LPAE
select ARM_DMA_USE_IOMMU
hi = readl(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET + 4);
entry = (((u64) hi) << 32) + lo;
if (last_entry && last_entry != entry) {
- pr_err("IOMMU:%d should use the same dev table as others!/n",
+ pr_err("IOMMU:%d should use the same dev table as others!\n",
iommu->index);
return false;
}
old_devtb_size = ((entry & ~PAGE_MASK) + 1) << 12;
if (old_devtb_size != dev_table_size) {
- pr_err("The device table size of IOMMU:%d is not expected!/n",
+ pr_err("The device table size of IOMMU:%d is not expected!\n",
iommu->index);
return false;
}
old_devtb_phys = entry & PAGE_MASK;
if (old_devtb_phys >= 0x100000000ULL) {
- pr_err("The address of old device table is above 4G, not trustworthy!/n");
+ pr_err("The address of old device table is above 4G, not trustworthy!\n");
return false;
}
old_devtb = memremap(old_devtb_phys, dev_table_size, MEMREMAP_WB);
old_dev_tbl_cpy = (void *)__get_free_pages(gfp_flag,
get_order(dev_table_size));
if (old_dev_tbl_cpy == NULL) {
- pr_err("Failed to allocate memory for copying old device table!/n");
+ pr_err("Failed to allocate memory for copying old device table!\n");
return false;
}
#define dmar_parse_one_rhsa dmar_res_noop
#endif
-static void __init
+static void
dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
{
struct acpi_dmar_hardware_unit *drhd;
static void __arm_v7s_pte_sync(arm_v7s_iopte *ptep, int num_entries,
struct io_pgtable_cfg *cfg)
{
- if (!(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA))
+ if (cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)
return;
dma_sync_single_for_device(cfg->iommu_dev, __arm_v7s_dma_addr(ptep),
int ret;
spin_lock_irqsave(&dom->pgtlock, flags);
- ret = dom->iop->map(dom->iop, iova, paddr, size, prot);
+ ret = dom->iop->map(dom->iop, iova, paddr & DMA_BIT_MASK(32),
+ size, prot);
spin_unlock_irqrestore(&dom->pgtlock, flags);
return ret;
err = of_iommu_xlate(info->dev, &iommu_spec);
of_node_put(iommu_spec.np);
- if (err)
- return err;
-
- return info->np == pdev->bus->dev.of_node;
+ return err;
}
const struct iommu_ops *of_iommu_configure(struct device *dev,
{
const __be32 *cell;
u64 hwid;
- int i;
+ int cpu;
cell = of_get_property(dn, "reg", NULL);
if (!cell)
if (hwid & ~MPIDR_HWID_BITMASK)
return -1;
- for (i = 0; i < num_possible_cpus(); i++)
- if (cpu_logical_map(i) == hwid)
- return i;
+ for_each_possible_cpu(cpu)
+ if (cpu_logical_map(cpu) == hwid)
+ return cpu;
return -1;
}
{
struct its_cmd_info info = {
.cmd_type = MAP_VLPI,
- .map = map,
+ {
+ .map = map,
+ },
};
/*
{
struct its_cmd_info info = {
.cmd_type = GET_VLPI,
- .map = map,
+ {
+ .map = map,
+ },
};
return irq_set_vcpu_affinity(irq, &info);
{
struct its_cmd_info info = {
.cmd_type = inv ? PROP_UPDATE_AND_INV_VLPI : PROP_UPDATE_VLPI,
- .config = config,
+ {
+ .config = config,
+ },
};
return irq_set_vcpu_affinity(irq, &info);
{
unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
- write_gic_rmask(BIT(intr));
+ write_gic_rmask(intr);
gic_clear_pcpu_masks(intr);
}
static void gic_unmask_irq(struct irq_data *d)
{
- struct cpumask *affinity = irq_data_get_affinity_mask(d);
unsigned int intr = GIC_HWIRQ_TO_SHARED(d->hwirq);
unsigned int cpu;
- write_gic_smask(BIT(intr));
+ write_gic_smask(intr);
gic_clear_pcpu_masks(intr);
- cpu = cpumask_first_and(affinity, cpu_online_mask);
+ cpu = cpumask_first(irq_data_get_effective_affinity_mask(d));
set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
}
irq_hw_number_t hw, unsigned int cpu)
{
int intr = GIC_HWIRQ_TO_SHARED(hw);
+ struct irq_data *data;
unsigned long flags;
+ data = irq_get_irq_data(virq);
+
spin_lock_irqsave(&gic_lock, flags);
write_gic_map_pin(intr, GIC_MAP_PIN_MAP_TO_PIN | gic_cpu_pin);
write_gic_map_vp(intr, BIT(mips_cm_vp_id(cpu)));
gic_clear_pcpu_masks(intr);
set_bit(intr, per_cpu_ptr(pcpu_masks, cpu));
+ irq_data_update_effective_affinity(data, cpumask_of(cpu));
spin_unlock_irqrestore(&gic_lock, flags);
return 0;
/* Find the first available CPU vector. */
i = 0;
- reserved = (C_SW0 | C_SW1) >> __fls(C_SW0);
+ reserved = (C_SW0 | C_SW1) >> __ffs(C_SW0);
while (!of_property_read_u32_index(node, "mti,reserved-cpu-vectors",
i++, &cpu_vec))
reserved |= BIT(cpu_vec);
gicconfig = read_gic_config();
gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
- gic_shared_intrs >>= __fls(GIC_CONFIG_NUMINTERRUPTS);
+ gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
gic_shared_intrs = (gic_shared_intrs + 1) * 8;
gic_vpes = gicconfig & GIC_CONFIG_PVPS;
- gic_vpes >>= __fls(GIC_CONFIG_PVPS);
+ gic_vpes >>= __ffs(GIC_CONFIG_PVPS);
gic_vpes = gic_vpes + 1;
if (cpu_has_veic) {
for (i = 0; i < gic_shared_intrs; i++) {
change_gic_pol(i, GIC_POL_ACTIVE_HIGH);
change_gic_trig(i, GIC_TRIG_LEVEL);
- write_gic_rmask(BIT(i));
+ write_gic_rmask(i);
}
for (i = 0; i < gic_vpes; i++) {
isdn_net_local *lp;
struct ippp_struct *is;
int proto;
- unsigned char protobuf[4];
is = file->private_data;
if (!lp)
printk(KERN_DEBUG "isdn_ppp_write: lp == NULL\n");
else {
- /*
- * Don't reset huptimer for
- * LCP packets. (Echo requests).
- */
- if (copy_from_user(protobuf, buf, 4))
- return -EFAULT;
- proto = PPP_PROTOCOL(protobuf);
- if (proto != PPP_LCP)
- lp->huptimer = 0;
+ if (lp->isdn_device < 0 || lp->isdn_channel < 0) {
+ unsigned char protobuf[4];
+ /*
+ * Don't reset huptimer for
+ * LCP packets. (Echo requests).
+ */
+ if (copy_from_user(protobuf, buf, 4))
+ return -EFAULT;
+
+ proto = PPP_PROTOCOL(protobuf);
+ if (proto != PPP_LCP)
+ lp->huptimer = 0;
- if (lp->isdn_device < 0 || lp->isdn_channel < 0)
return 0;
+ }
if ((dev->drv[lp->isdn_device]->flags & DRV_FLAG_RUNNING) &&
lp->dialstate == 0 &&
(lp->flags & ISDN_NET_CONNECTED)) {
unsigned short hl;
struct sk_buff *skb;
+ unsigned char *cpy_buf;
/*
* we need to reserve enough space in front of
* sk_buff. old call to dev_alloc_skb only reserved
return count;
}
skb_reserve(skb, hl);
- if (copy_from_user(skb_put(skb, count), buf, count))
+ cpy_buf = skb_put(skb, count);
+ if (copy_from_user(cpy_buf, buf, count))
{
kfree_skb(skb);
return -EFAULT;
}
+
+ /*
+ * Don't reset huptimer for
+ * LCP packets. (Echo requests).
+ */
+ proto = PPP_PROTOCOL(cpy_buf);
+ if (proto != PPP_LCP)
+ lp->huptimer = 0;
+
if (is->debug & 0x40) {
printk(KERN_DEBUG "ppp xmit: len %d\n", (int) skb->len);
isdn_ppp_frame_log("xmit", skb->data, skb->len, 32, is->unit, lp->ppp_slot);
#define AS_PEAK_mA_TO_REG(a) \
((min_t(u32, AS_PEAK_mA_MAX, a) - 1250) / 250)
+/* LED numbers for Devicetree */
+#define AS_LED_FLASH 0
+#define AS_LED_INDICATOR 1
+
enum as_mode {
AS_MODE_EXT_TORCH = 0 << AS_CONTROL_MODE_SETTING_SHIFT,
AS_MODE_INDICATOR = 1 << AS_CONTROL_MODE_SETTING_SHIFT,
struct device_node *node)
{
struct as3645a_config *cfg = &flash->cfg;
+ struct device_node *child;
const char *name;
int rval;
- flash->flash_node = of_get_child_by_name(node, "flash");
+ for_each_child_of_node(node, child) {
+ u32 id = 0;
+
+ of_property_read_u32(child, "reg", &id);
+
+ switch (id) {
+ case AS_LED_FLASH:
+ flash->flash_node = of_node_get(child);
+ break;
+ case AS_LED_INDICATOR:
+ flash->indicator_node = of_node_get(child);
+ break;
+ default:
+ dev_warn(&flash->client->dev,
+ "unknown LED %u encountered, ignoring\n", id);
+ break;
+ }
+ }
+
if (!flash->flash_node) {
dev_err(&flash->client->dev, "can't find flash node\n");
return -ENODEV;
of_property_read_u32(flash->flash_node, "voltage-reference",
&cfg->voltage_reference);
- of_property_read_u32(flash->flash_node, "peak-current-limit",
+ of_property_read_u32(flash->flash_node, "ams,input-max-microamp",
&cfg->peak);
cfg->peak = AS_PEAK_mA_TO_REG(cfg->peak);
- flash->indicator_node = of_get_child_by_name(node, "indicator");
if (!flash->indicator_node) {
dev_warn(&flash->client->dev,
"can't find indicator node\n");
as3645a_set_control(flash, AS_MODE_EXT_TORCH, false);
v4l2_flash_release(flash->vf);
+ v4l2_flash_release(flash->vfind);
led_classdev_flash_unregister(&flash->fled);
led_classdev_unregister(&flash->iled_cdev);
if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
return DM_MAPIO_REQUEUE;
- mddev->pers->make_request(mddev, bio);
+ md_handle_request(mddev, bio);
return DM_MAPIO_SUBMITTED;
}
* call has finished, the bio has been linked into some internal structure
* and so is visible to ->quiesce(), so we don't need the refcount any more.
*/
+void md_handle_request(struct mddev *mddev, struct bio *bio)
+{
+check_suspended:
+ rcu_read_lock();
+ if (mddev->suspended) {
+ DEFINE_WAIT(__wait);
+ for (;;) {
+ prepare_to_wait(&mddev->sb_wait, &__wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!mddev->suspended)
+ break;
+ rcu_read_unlock();
+ schedule();
+ rcu_read_lock();
+ }
+ finish_wait(&mddev->sb_wait, &__wait);
+ }
+ atomic_inc(&mddev->active_io);
+ rcu_read_unlock();
+
+ if (!mddev->pers->make_request(mddev, bio)) {
+ atomic_dec(&mddev->active_io);
+ wake_up(&mddev->sb_wait);
+ goto check_suspended;
+ }
+
+ if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+ wake_up(&mddev->sb_wait);
+}
+EXPORT_SYMBOL(md_handle_request);
+
static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
{
const int rw = bio_data_dir(bio);
bio_endio(bio);
return BLK_QC_T_NONE;
}
-check_suspended:
- rcu_read_lock();
- if (mddev->suspended) {
- DEFINE_WAIT(__wait);
- for (;;) {
- prepare_to_wait(&mddev->sb_wait, &__wait,
- TASK_UNINTERRUPTIBLE);
- if (!mddev->suspended)
- break;
- rcu_read_unlock();
- schedule();
- rcu_read_lock();
- }
- finish_wait(&mddev->sb_wait, &__wait);
- }
- atomic_inc(&mddev->active_io);
- rcu_read_unlock();
/*
* save the sectors now since our bio can
sectors = bio_sectors(bio);
/* bio could be mergeable after passing to underlayer */
bio->bi_opf &= ~REQ_NOMERGE;
- if (!mddev->pers->make_request(mddev, bio)) {
- atomic_dec(&mddev->active_io);
- wake_up(&mddev->sb_wait);
- goto check_suspended;
- }
+
+ md_handle_request(mddev, bio);
cpu = part_stat_lock();
part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
part_stat_unlock();
- if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
- wake_up(&mddev->sb_wait);
-
return BLK_QC_T_NONE;
}
struct mddev *mddev = container_of(ws, struct mddev, flush_work);
struct bio *bio = mddev->flush_bio;
+ /*
+ * must reset flush_bio before calling into md_handle_request to avoid a
+ * deadlock, because other bios passed md_handle_request suspend check
+ * could wait for this and below md_handle_request could wait for those
+ * bios because of suspend check
+ */
+ mddev->flush_bio = NULL;
+ wake_up(&mddev->sb_wait);
+
if (bio->bi_iter.bi_size == 0)
/* an empty barrier - all done */
bio_endio(bio);
else {
bio->bi_opf &= ~REQ_PREFLUSH;
- mddev->pers->make_request(mddev, bio);
+ md_handle_request(mddev, bio);
}
-
- mddev->flush_bio = NULL;
- wake_up(&mddev->sb_wait);
}
void md_flush_request(struct mddev *mddev, struct bio *bio)
extern int md_rdev_init(struct md_rdev *rdev);
extern void md_rdev_clear(struct md_rdev *rdev);
+extern void md_handle_request(struct mddev *mddev, struct bio *bio);
extern void mddev_suspend(struct mddev *mddev);
extern void mddev_resume(struct mddev *mddev);
extern struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
spin_unlock(&head->batch_head->batch_lock);
goto unlock_out;
}
+ /*
+ * We must assign batch_head of this stripe within the
+ * batch_lock, otherwise clear_batch_ready of batch head
+ * stripe could clear BATCH_READY bit of this stripe and
+ * this stripe->batch_head doesn't get assigned, which
+ * could confuse clear_batch_ready for this stripe
+ */
+ sh->batch_head = head->batch_head;
/*
* at this point, head's BATCH_READY could be cleared, but we
*/
list_add(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_head->batch_lock);
-
- sh->batch_head = head->batch_head;
} else {
head->batch_head = head;
sh->batch_head = head->batch_head;
set_mask_bits(&sh->state, ~(STRIPE_EXPAND_SYNC_FLAGS |
(1 << STRIPE_PREREAD_ACTIVE) |
- (1 << STRIPE_DEGRADED)),
+ (1 << STRIPE_DEGRADED) |
+ (1 << STRIPE_ON_UNPLUG_LIST)),
head_sh->state & (1 << STRIPE_INSYNC));
sh->check_state = head_sh->check_state;
raid5_store_group_thread_cnt(struct mddev *mddev, const char *page, size_t len)
{
struct r5conf *conf;
- unsigned long new;
+ unsigned int new;
int err;
struct r5worker_group *new_groups, *old_groups;
int group_cnt, worker_cnt_per_group;
if (len >= PAGE_SIZE)
return -EINVAL;
- if (kstrtoul(page, 10, &new))
+ if (kstrtouint(page, 10, &new))
+ return -EINVAL;
+ /* 8192 should be big enough */
+ if (new > 8192)
return -EINVAL;
err = mddev_lock(mddev);
if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
+ /*
+ * mmc_init_request() depends on card->bouncesz so it must be calculated
+ * before blk_init_allocated_queue() starts allocating requests.
+ */
+ card->bouncesz = mmc_queue_calc_bouncesz(host);
+
mq->card = card;
mq->queue = blk_alloc_queue(GFP_KERNEL);
if (!mq->queue)
if (mmc_can_erase(card))
mmc_queue_setup_discard(mq->queue, card);
- card->bouncesz = mmc_queue_calc_bouncesz(host);
if (card->bouncesz) {
blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512);
blk_queue_max_segments(mq->queue, card->bouncesz / 512);
comment "MMC/SD/SDIO Host Controller Drivers"
config MMC_DEBUG
- bool "MMC host drivers debugginG"
+ bool "MMC host drivers debugging"
depends on MMC != n
help
This is an option for use by developers; most people should
*
* Copyright (C) 2016 Cavium Inc.
*/
+#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
#include <linux/mmc/mmc.h>
for (i = 0; i < CAVIUM_MAX_MMC; i++) {
if (host->slot[i])
cvm_mmc_of_slot_remove(host->slot[i]);
- if (host->slot_pdev[i])
+ if (host->slot_pdev[i]) {
+ get_device(&host->slot_pdev[i]->dev);
of_platform_device_destroy(&host->slot_pdev[i]->dev, NULL);
+ put_device(&host->slot_pdev[i]->dev);
+ }
}
clk_disable_unprepare(host->clk);
return ret;
enum {
INTEL_DSM_FNS = 0,
+ INTEL_DSM_V18_SWITCH = 3,
INTEL_DSM_DRV_STRENGTH = 9,
INTEL_DSM_D3_RETUNE = 10,
};
sdhci_writel(host, val, INTEL_HS400_ES_REG);
}
+static void sdhci_intel_voltage_switch(struct sdhci_host *host)
+{
+ struct sdhci_pci_slot *slot = sdhci_priv(host);
+ struct intel_host *intel_host = sdhci_pci_priv(slot);
+ struct device *dev = &slot->chip->pdev->dev;
+ u32 result = 0;
+ int err;
+
+ err = intel_dsm(intel_host, dev, INTEL_DSM_V18_SWITCH, &result);
+ pr_debug("%s: %s DSM error %d result %u\n",
+ mmc_hostname(host->mmc), __func__, err, result);
+}
+
static const struct sdhci_ops sdhci_intel_byt_ops = {
.set_clock = sdhci_set_clock,
.set_power = sdhci_intel_set_power,
.reset = sdhci_reset,
.set_uhs_signaling = sdhci_set_uhs_signaling,
.hw_reset = sdhci_pci_hw_reset,
+ .voltage_switch = sdhci_intel_voltage_switch,
};
static void byt_read_dsm(struct sdhci_pci_slot *slot)
#define CMDREQ_TIMEOUT 5000
-#ifdef CONFIG_MMC_DEBUG
-
-#define STATUS_TO_TEXT(a, status, i) \
- do { \
- if ((status) & TMIO_STAT_##a) { \
- if ((i)++) \
- printk(KERN_DEBUG " | "); \
- printk(KERN_DEBUG #a); \
- } \
- } while (0)
-
-static void pr_debug_status(u32 status)
-{
- int i = 0;
-
- pr_debug("status: %08x = ", status);
- STATUS_TO_TEXT(CARD_REMOVE, status, i);
- STATUS_TO_TEXT(CARD_INSERT, status, i);
- STATUS_TO_TEXT(SIGSTATE, status, i);
- STATUS_TO_TEXT(WRPROTECT, status, i);
- STATUS_TO_TEXT(CARD_REMOVE_A, status, i);
- STATUS_TO_TEXT(CARD_INSERT_A, status, i);
- STATUS_TO_TEXT(SIGSTATE_A, status, i);
- STATUS_TO_TEXT(CMD_IDX_ERR, status, i);
- STATUS_TO_TEXT(STOPBIT_ERR, status, i);
- STATUS_TO_TEXT(ILL_FUNC, status, i);
- STATUS_TO_TEXT(CMD_BUSY, status, i);
- STATUS_TO_TEXT(CMDRESPEND, status, i);
- STATUS_TO_TEXT(DATAEND, status, i);
- STATUS_TO_TEXT(CRCFAIL, status, i);
- STATUS_TO_TEXT(DATATIMEOUT, status, i);
- STATUS_TO_TEXT(CMDTIMEOUT, status, i);
- STATUS_TO_TEXT(RXOVERFLOW, status, i);
- STATUS_TO_TEXT(TXUNDERRUN, status, i);
- STATUS_TO_TEXT(RXRDY, status, i);
- STATUS_TO_TEXT(TXRQ, status, i);
- STATUS_TO_TEXT(ILL_ACCESS, status, i);
- printk("\n");
-}
-
-#else
-#define pr_debug_status(s) do { } while (0)
-#endif
-
static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
{
struct tmio_mmc_host *host = mmc_priv(mmc);
status = sd_ctrl_read16_and_16_as_32(host, CTL_STATUS);
ireg = status & TMIO_MASK_IRQ & ~host->sdcard_irq_mask;
- pr_debug_status(status);
- pr_debug_status(ireg);
-
/* Clear the status except the interrupt status */
sd_ctrl_write32_as_16_and_16(host, CTL_STATUS, TMIO_MASK_IRQ);
slave->mtd.erasesize = parent->erasesize;
}
+ /*
+ * Slave erasesize might differ from the master one if the master
+ * exposes several regions with different erasesize. Adjust
+ * wr_alignment accordingly.
+ */
+ if (!(slave->mtd.flags & MTD_NO_ERASE))
+ wr_alignment = slave->mtd.erasesize;
+
tmp = slave->offset;
remainder = do_div(tmp, wr_alignment);
if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) {
size += (req->ecc.strength + 1) * sizeof(u16);
/* Reserve space for mu, dmu and delta. */
size = ALIGN(size, sizeof(s32));
- size += (req->ecc.strength + 1) * sizeof(s32);
+ size += (req->ecc.strength + 1) * sizeof(s32) * 3;
user = kzalloc(size, GFP_KERNEL);
if (!user)
}
res = clk_prepare_enable(host->clk);
if (res)
- goto err_exit1;
+ goto err_put_clk;
nand_chip->cmd_ctrl = lpc32xx_nand_cmd_ctrl;
nand_chip->dev_ready = lpc32xx_nand_device_ready;
dma_release_channel(host->dma_chan);
err_exit2:
clk_disable_unprepare(host->clk);
+err_put_clk:
clk_put(host->clk);
err_exit1:
lpc32xx_wp_enable(host);
static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
struct mtd_oob_ops *ops)
{
- int chipnr, realpage, page, blockmask, column;
+ int chipnr, realpage, page, column;
struct nand_chip *chip = mtd_to_nand(mtd);
uint32_t writelen = ops->len;
realpage = (int)(to >> chip->page_shift);
page = realpage & chip->pagemask;
- blockmask = (1 << (chip->phys_erase_shift - chip->page_shift)) - 1;
/* Invalidate the page cache, when we write to the cached page */
if (to <= ((loff_t)chip->pagebuf << chip->page_shift) &&
* @nor: pointer to a 'struct spi_nor'
* @addr: offset in the SFDP area to start reading data from
* @len: number of bytes to read
- * @buf: buffer where the SFDP data are copied into
+ * @buf: buffer where the SFDP data are copied into (dma-safe memory)
*
* Whatever the actual numbers of bytes for address and dummy cycles are
* for (Fast) Read commands, the Read SFDP (5Ah) instruction is always
return ret;
}
+/**
+ * spi_nor_read_sfdp_dma_unsafe() - read Serial Flash Discoverable Parameters.
+ * @nor: pointer to a 'struct spi_nor'
+ * @addr: offset in the SFDP area to start reading data from
+ * @len: number of bytes to read
+ * @buf: buffer where the SFDP data are copied into
+ *
+ * Wrap spi_nor_read_sfdp() using a kmalloc'ed bounce buffer as @buf is now not
+ * guaranteed to be dma-safe.
+ *
+ * Return: -ENOMEM if kmalloc() fails, the return code of spi_nor_read_sfdp()
+ * otherwise.
+ */
+static int spi_nor_read_sfdp_dma_unsafe(struct spi_nor *nor, u32 addr,
+ size_t len, void *buf)
+{
+ void *dma_safe_buf;
+ int ret;
+
+ dma_safe_buf = kmalloc(len, GFP_KERNEL);
+ if (!dma_safe_buf)
+ return -ENOMEM;
+
+ ret = spi_nor_read_sfdp(nor, addr, len, dma_safe_buf);
+ memcpy(buf, dma_safe_buf, len);
+ kfree(dma_safe_buf);
+
+ return ret;
+}
+
struct sfdp_parameter_header {
u8 id_lsb;
u8 minor;
bfpt_header->length * sizeof(u32));
addr = SFDP_PARAM_HEADER_PTP(bfpt_header);
memset(&bfpt, 0, sizeof(bfpt));
- err = spi_nor_read_sfdp(nor, addr, len, &bfpt);
+ err = spi_nor_read_sfdp_dma_unsafe(nor, addr, len, &bfpt);
if (err < 0)
return err;
params->size = bfpt.dwords[BFPT_DWORD(2)];
if (params->size & BIT(31)) {
params->size &= ~BIT(31);
+
+ /*
+ * Prevent overflows on params->size. Anyway, a NOR of 2^64
+ * bits is unlikely to exist so this error probably means
+ * the BFPT we are reading is corrupted/wrong.
+ */
+ if (params->size > 63)
+ return -EINVAL;
+
params->size = 1ULL << params->size;
} else {
params->size++;
int i, err;
/* Get the SFDP header. */
- err = spi_nor_read_sfdp(nor, 0, sizeof(header), &header);
+ err = spi_nor_read_sfdp_dma_unsafe(nor, 0, sizeof(header), &header);
if (err < 0)
return err;
netif_dbg(priv, hw, priv->netdev, "updated MIB counters\n");
}
+static void bcm_sysport_update_tx_stats(struct bcm_sysport_priv *priv,
+ u64 *tx_bytes, u64 *tx_packets)
+{
+ struct bcm_sysport_tx_ring *ring;
+ u64 bytes = 0, packets = 0;
+ unsigned int start;
+ unsigned int q;
+
+ for (q = 0; q < priv->netdev->num_tx_queues; q++) {
+ ring = &priv->tx_rings[q];
+ do {
+ start = u64_stats_fetch_begin_irq(&priv->syncp);
+ bytes = ring->bytes;
+ packets = ring->packets;
+ } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
+
+ *tx_bytes += bytes;
+ *tx_packets += packets;
+ }
+}
+
static void bcm_sysport_get_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
struct u64_stats_sync *syncp = &priv->syncp;
struct bcm_sysport_tx_ring *ring;
+ u64 tx_bytes = 0, tx_packets = 0;
unsigned int start;
int i, j;
- if (netif_running(dev))
+ if (netif_running(dev)) {
bcm_sysport_update_mib_counters(priv);
+ bcm_sysport_update_tx_stats(priv, &tx_bytes, &tx_packets);
+ stats64->tx_bytes = tx_bytes;
+ stats64->tx_packets = tx_packets;
+ }
for (i = 0, j = 0; i < BCM_SYSPORT_STATS_LEN; i++) {
const struct bcm_sysport_stats *s;
continue;
p += s->stat_offset;
- if (s->stat_sizeof == sizeof(u64))
+ if (s->stat_sizeof == sizeof(u64) &&
+ s->type == BCM_SYSPORT_STAT_NETDEV64) {
do {
start = u64_stats_fetch_begin_irq(syncp);
data[i] = *(u64 *)p;
} while (u64_stats_fetch_retry_irq(syncp, start));
- else
+ } else
data[i] = *(u32 *)p;
j++;
}
{
struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_stats64 *stats64 = &priv->stats64;
- struct bcm_sysport_tx_ring *ring;
- u64 tx_packets = 0, tx_bytes = 0;
unsigned int start;
- unsigned int q;
netdev_stats_to_stats64(stats, &dev->stats);
- for (q = 0; q < dev->num_tx_queues; q++) {
- ring = &priv->tx_rings[q];
- do {
- start = u64_stats_fetch_begin_irq(&priv->syncp);
- tx_bytes = ring->bytes;
- tx_packets = ring->packets;
- } while (u64_stats_fetch_retry_irq(&priv->syncp, start));
-
- stats->tx_bytes += tx_bytes;
- stats->tx_packets += tx_packets;
- }
-
- stats64->tx_bytes = stats->tx_bytes;
- stats64->tx_packets = stats->tx_packets;
+ bcm_sysport_update_tx_stats(priv, &stats->tx_bytes,
+ &stats->tx_packets);
do {
start = u64_stats_fetch_begin_irq(&priv->syncp);
{
int rc = 0;
+ if (!is_classid_clsact_ingress(cls_flower->common.classid) ||
+ cls_flower->common.chain_index)
+ return -EOPNOTSUPP;
+
switch (cls_flower->command) {
case TC_CLSFLOWER_REPLACE:
rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
#define FEC_ENET_TS_AVAIL ((uint)0x00010000)
#define FEC_ENET_TS_TIMER ((uint)0x00008000)
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER)
-#define FEC_NAPI_IMASK (FEC_ENET_MII | FEC_ENET_TS_TIMER)
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
+#define FEC_NAPI_IMASK FEC_ENET_MII
#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
/* ENET interrupt coalescing macro define */
if (int_events == 0)
return false;
- if (int_events & FEC_ENET_RXF)
+ if (int_events & FEC_ENET_RXF_0)
fep->work_rx |= (1 << 2);
if (int_events & FEC_ENET_RXF_1)
fep->work_rx |= (1 << 0);
if (int_events & FEC_ENET_RXF_2)
fep->work_rx |= (1 << 1);
- if (int_events & FEC_ENET_TXF)
+ if (int_events & FEC_ENET_TXF_0)
fep->work_tx |= (1 << 2);
if (int_events & FEC_ENET_TXF_1)
fep->work_tx |= (1 << 0);
}
if (fep->ptp_clock)
- fec_ptp_check_pps_event(fep);
-
+ if (fec_ptp_check_pps_event(fep))
+ ret = IRQ_HANDLED;
return ret;
}
}
static int hnae3_match_n_instantiate(struct hnae3_client *client,
- struct hnae3_ae_dev *ae_dev,
- bool is_reg, bool *matched)
+ struct hnae3_ae_dev *ae_dev, bool is_reg)
{
int ret;
- *matched = false;
-
/* check if this client matches the type of ae_dev */
if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
return 0;
}
- /* there is a match of client and dev */
- *matched = true;
/* now, (un-)instantiate client by calling lower layer */
if (is_reg) {
{
struct hnae3_client *client_tmp;
struct hnae3_ae_dev *ae_dev;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
/* if the client could not be initialized on current port, for
* any error reasons, move on to next available port
*/
- ret = hnae3_match_n_instantiate(client, ae_dev, true, &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed for port\n");
void hnae3_unregister_client(struct hnae3_client *client)
{
struct hnae3_ae_dev *ae_dev;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* un-initialize the client on every matched port */
list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false, &matched);
+ hnae3_match_n_instantiate(client, ae_dev, false);
}
list_del(&client->node);
const struct pci_device_id *id;
struct hnae3_ae_dev *ae_dev;
struct hnae3_client *client;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true,
- &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed\n");
- if (matched)
- break;
}
}
const struct pci_device_id *id;
struct hnae3_ae_dev *ae_dev;
struct hnae3_client *client;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_dev */
/* check the client list for the match with this ae_dev type and
* un-initialize the figure out client instance
*/
- list_for_each_entry(client, &hnae3_client_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false,
- &matched);
- if (matched)
- break;
- }
+ list_for_each_entry(client, &hnae3_client_list, node)
+ hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
const struct pci_device_id *id;
struct hnae3_ae_algo *ae_algo;
struct hnae3_client *client;
- bool matched;
int ret = 0;
mutex_lock(&hnae3_common_lock);
* initialize the figure out client instance
*/
list_for_each_entry(client, &hnae3_client_list, node) {
- ret = hnae3_match_n_instantiate(client, ae_dev, true,
- &matched);
+ ret = hnae3_match_n_instantiate(client, ae_dev, true);
if (ret)
dev_err(&ae_dev->pdev->dev,
"match and instantiation failed\n");
- if (matched)
- break;
}
out_err:
const struct pci_device_id *id;
struct hnae3_ae_algo *ae_algo;
struct hnae3_client *client;
- bool matched;
mutex_lock(&hnae3_common_lock);
/* Check if there are matched ae_algo */
if (!id)
continue;
- list_for_each_entry(client, &hnae3_client_list, node) {
- hnae3_match_n_instantiate(client, ae_dev, false,
- &matched);
- if (matched)
- break;
- }
+ list_for_each_entry(client, &hnae3_client_list, node)
+ hnae3_match_n_instantiate(client, ae_dev, false);
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
#define HNAE3_CLASS_NAME_SIZE 16
#define HNAE3_DEV_INITED_B 0x0
-#define HNAE_DEV_SUPPORT_ROCE_B 0x1
+#define HNAE3_DEV_SUPPORT_ROCE_B 0x1
+#define HNAE3_DEV_SUPPORT_DCB_B 0x2
+
+#define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
+ BIT(HNAE3_DEV_SUPPORT_ROCE_B))
+
+#define hnae3_dev_roce_supported(hdev) \
+ hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+
+#define hnae3_dev_dcb_supported(hdev) \
+ hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
#define ring_ptr_move_fw(ring, p) \
((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
struct hnae3_tc_info {
u16 tqp_offset; /* TQP offset from base TQP */
u16 tqp_count; /* Total TQPs */
- u8 up; /* user priority */
u8 tc; /* TC index */
bool enable; /* If this TC is enable or not */
};
#define HNAE3_MAX_TC 8
+#define HNAE3_MAX_USER_PRIO 8
struct hnae3_knic_private_info {
struct net_device *netdev; /* Set by KNIC client when init instance */
u16 rss_size; /* Allocated RSS queues */
u16 num_desc;
u8 num_tc; /* Total number of enabled TCs */
+ u8 prio_tc[HNAE3_MAX_USER_PRIO]; /* TC indexed by prio */
struct hnae3_tc_info tc_info[HNAE3_MAX_TC]; /* Idx of array is HW TC */
u16 num_tqps; /* total number of TQPs in this handle */
u8 rsv[18];
};
-#define HCLGE_VECTOR_ELEMENTS_PER_CMD 11
+#define HCLGE_VECTOR_ELEMENTS_PER_CMD 10
enum hclge_int_type {
HCLGE_INT_TX,
#define HCLGE_INT_TYPE_S 0
#define HCLGE_INT_TYPE_M 0x3
#define HCLGE_TQP_ID_S 2
-#define HCLGE_TQP_ID_M (0x3fff << HCLGE_TQP_ID_S)
+#define HCLGE_TQP_ID_M (0x7ff << HCLGE_TQP_ID_S)
+#define HCLGE_INT_GL_IDX_S 13
+#define HCLGE_INT_GL_IDX_M (0x3 << HCLGE_INT_GL_IDX_S)
__le16 tqp_type_and_id[HCLGE_VECTOR_ELEMENTS_PER_CMD];
+ u8 vfid;
+ u8 rsv;
};
#define HCLGE_TC_NUM 8
struct hclge_rx_priv_buff {
__le16 buf_num[HCLGE_TC_NUM];
- u8 rsv[8];
+ __le16 shared_buf;
+ u8 rsv[6];
};
struct hclge_query_version {
#define HCLGE_DEFAULT_TX_BUF 0x4000 /* 16k bytes */
#define HCLGE_TOTAL_PKT_BUF 0x108000 /* 1.03125M bytes */
#define HCLGE_DEFAULT_DV 0xA000 /* 40k byte */
+#define HCLGE_DEFAULT_NON_DCB_DV 0x7800 /* 30K byte */
#define HCLGE_TYPE_CRQ 0
#define HCLGE_TYPE_CSQ 1
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
- /* Required last entry */
- {0, }
-};
-
-static const struct pci_device_id roce_pci_tbl[] = {
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
- /* Required last entry */
+ /* required last entry */
{0, }
};
hdev->num_tqps = __le16_to_cpu(req->tqp_num);
hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
- if (hnae_get_bit(hdev->ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B)) {
+ if (hnae3_dev_roce_supported(hdev)) {
hdev->num_roce_msix =
hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
hdev->base_tqp_pid = 0;
hdev->rss_size_max = 1;
hdev->rx_buf_len = cfg.rx_buf_len;
- for (i = 0; i < ETH_ALEN; i++)
- hdev->hw.mac.mac_addr[i] = cfg.mac_addr[i];
+ ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr);
hdev->hw.mac.media_type = cfg.media_type;
+ hdev->hw.mac.phy_addr = cfg.phy_addr;
hdev->num_desc = cfg.tqp_desc_num;
hdev->tm_info.num_pg = 1;
hdev->tm_info.num_tc = cfg.tc_num;
tc_num = hclge_get_tc_num(hdev);
pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
- shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+ if (hnae3_dev_dcb_supported(hdev))
+ shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+ else
+ shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV;
+
shared_buf_tc = pfc_enable_num * hdev->mps +
(tc_num - pfc_enable_num) * hdev->mps / 2 +
hdev->mps;
struct hclge_priv_buf *priv;
int i;
+ /* When DCB is not supported, rx private
+ * buffer is not allocated.
+ */
+ if (!hnae3_dev_dcb_supported(hdev)) {
+ if (!hclge_is_rx_buf_ok(hdev, rx_all))
+ return -ENOMEM;
+
+ return 0;
+ }
+
/* step 1, try to alloc private buffer for all enabled tc */
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
priv = &hdev->priv_buf[i];
priv->wl.high = 2 * hdev->mps;
priv->buf_size = priv->wl.high;
}
+ } else {
+ priv->enable = 0;
+ priv->wl.low = 0;
+ priv->wl.high = 0;
+ priv->buf_size = 0;
}
}
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
priv = &hdev->priv_buf[i];
- if (hdev->hw_tc_map & BIT(i))
- priv->enable = 1;
+ priv->enable = 0;
+ priv->wl.low = 0;
+ priv->wl.high = 0;
+ priv->buf_size = 0;
+
+ if (!(hdev->hw_tc_map & BIT(i)))
+ continue;
+
+ priv->enable = 1;
if (hdev->tm_info.hw_pfc_map & BIT(i)) {
priv->wl.low = 128;
cpu_to_le16(true << HCLGE_TC0_PRI_BUF_EN_B);
}
+ req->shared_buf =
+ cpu_to_le16((hdev->s_buf.buf_size >> HCLGE_BUF_UNIT_S) |
+ (1 << HCLGE_TC0_PRI_BUF_EN_B));
+
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret) {
dev_err(&hdev->pdev->dev,
return ret;
}
- ret = hclge_rx_priv_wl_config(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "could not configure rx private waterline %d\n", ret);
- return ret;
- }
+ if (hnae3_dev_dcb_supported(hdev)) {
+ ret = hclge_rx_priv_wl_config(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "could not configure rx private waterline %d\n",
+ ret);
+ return ret;
+ }
- ret = hclge_common_thrd_config(hdev);
- if (ret) {
- dev_err(&hdev->pdev->dev,
- "could not configure common threshold %d\n", ret);
- return ret;
+ ret = hclge_common_thrd_config(hdev);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "could not configure common threshold %d\n",
+ ret);
+ return ret;
+ }
}
ret = hclge_common_wl_config(hdev);
u16 tc_valid[HCLGE_MAX_TC_NUM];
u16 tc_size[HCLGE_MAX_TC_NUM];
u32 *rss_indir = NULL;
+ u16 rss_size = 0, roundup_size;
const u8 *key;
int i, ret, j;
for (j = 0; j < hdev->num_vmdq_vport + 1; j++) {
for (i = 0; i < HCLGE_RSS_IND_TBL_SIZE; i++) {
vport[j].rss_indirection_tbl[i] =
- i % hdev->rss_size_max;
+ i % vport[j].alloc_rss_size;
+
+ /* vport 0 is for PF */
+ if (j != 0)
+ continue;
+
+ rss_size = vport[j].alloc_rss_size;
rss_indir[i] = vport[j].rss_indirection_tbl[i];
}
}
if (ret)
goto err;
+ /* Each TC have the same queue size, and tc_size set to hardware is
+ * the log2 of roundup power of two of rss_size, the acutal queue
+ * size is limited by indirection table.
+ */
+ if (rss_size > HCLGE_RSS_TC_SIZE_7 || rss_size == 0) {
+ dev_err(&hdev->pdev->dev,
+ "Configure rss tc size failed, invalid TC_SIZE = %d\n",
+ rss_size);
+ return -EINVAL;
+ }
+
+ roundup_size = roundup_pow_of_two(rss_size);
+ roundup_size = ilog2(roundup_size);
+
for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
- if (hdev->hw_tc_map & BIT(i))
- tc_valid[i] = 1;
- else
- tc_valid[i] = 0;
+ tc_valid[i] = 0;
- switch (hdev->rss_size_max) {
- case HCLGE_RSS_TC_SIZE_0:
- tc_size[i] = 0;
- break;
- case HCLGE_RSS_TC_SIZE_1:
- tc_size[i] = 1;
- break;
- case HCLGE_RSS_TC_SIZE_2:
- tc_size[i] = 2;
- break;
- case HCLGE_RSS_TC_SIZE_3:
- tc_size[i] = 3;
- break;
- case HCLGE_RSS_TC_SIZE_4:
- tc_size[i] = 4;
- break;
- case HCLGE_RSS_TC_SIZE_5:
- tc_size[i] = 5;
- break;
- case HCLGE_RSS_TC_SIZE_6:
- tc_size[i] = 6;
- break;
- case HCLGE_RSS_TC_SIZE_7:
- tc_size[i] = 7;
- break;
- default:
- break;
- }
- tc_offset[i] = hdev->rss_size_max * i;
+ if (!(hdev->hw_tc_map & BIT(i)))
+ continue;
+
+ tc_valid[i] = 1;
+ tc_size[i] = roundup_size;
+ tc_offset[i] = rss_size * i;
}
+
ret = hclge_set_rss_tc_mode(hdev, tc_valid, tc_size, tc_offset);
err:
hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
HCLGE_TQP_ID_S, node->tqp_index);
+ hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+ HCLGE_INT_GL_IDX_S,
+ hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+ req->vfid = vport->vport_id;
if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
hnae_set_field(req->tqp_type_and_id[i], HCLGE_TQP_ID_M,
HCLGE_TQP_ID_S, node->tqp_index);
+ hnae_set_field(req->tqp_type_and_id[i], HCLGE_INT_GL_IDX_M,
+ HCLGE_INT_GL_IDX_S,
+ hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
req->tqp_type_and_id[i] = cpu_to_le16(req->tqp_type_and_id[i]);
+ req->vfid = vport->vport_id;
if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
}
i = 0;
hclge_cmd_setup_basic_desc(&desc,
- HCLGE_OPC_ADD_RING_TO_VECTOR,
+ HCLGE_OPC_DEL_RING_TO_VECTOR,
false);
req->int_vector_id = vector_id;
}
{
#define HCLGE_VLAN_TYPE_VF_TABLE 0
#define HCLGE_VLAN_TYPE_PORT_TABLE 1
+ struct hnae3_handle *handle;
int ret;
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_VF_TABLE,
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_VLAN_TYPE_PORT_TABLE,
true);
+ if (ret)
+ return ret;
- return ret;
+ handle = &hdev->vport[0].nic;
+ return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
}
static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
goto err;
if (hdev->roce_client &&
- hnae_get_bit(hdev->ae_dev->flag,
- HNAE_DEV_SUPPORT_ROCE_B)) {
+ hnae3_dev_roce_supported(hdev)) {
struct hnae3_client *rc = hdev->roce_client;
ret = hclge_init_roce_base_info(vport);
break;
case HNAE3_CLIENT_ROCE:
- if (hnae_get_bit(hdev->ae_dev->flag,
- HNAE_DEV_SUPPORT_ROCE_B)) {
+ if (hnae3_dev_roce_supported(hdev)) {
hdev->roce_client = client;
vport->roce.client = client;
}
static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
{
struct pci_dev *pdev = ae_dev->pdev;
- const struct pci_device_id *id;
struct hclge_dev *hdev;
int ret;
hdev->ae_dev = ae_dev;
ae_dev->priv = hdev;
- id = pci_match_id(roce_pci_tbl, ae_dev->pdev);
- if (id)
- hnae_set_bit(ae_dev->flag, HNAE_DEV_SUPPORT_ROCE_B, 1);
-
ret = hclge_pci_init(hdev);
if (ret) {
dev_err(&pdev->dev, "PCI init failed\n");
return ret;
}
- ret = hclge_rss_init_hw(hdev);
- if (ret) {
- dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
- return ret;
- }
-
ret = hclge_init_vlan_config(hdev);
if (ret) {
dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
return ret;
}
+ ret = hclge_rss_init_hw(hdev);
+ if (ret) {
+ dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret);
+ return ret;
+ }
+
setup_timer(&hdev->service_timer, hclge_service_timer,
(unsigned long)hdev);
INIT_WORK(&hdev->service_task, hclge_service_task);
struct hclge_tc_info {
u8 tc_id;
u8 tc_sch_mode; /* 0: sp; 1: dwrr */
- u8 up;
u8 pgid;
u32 bw_limit;
};
u8 num_tc;
u8 num_pg; /* It must be 1 if vNET-Base schd */
u8 pg_dwrr[HCLGE_PG_NUM];
+ u8 prio_tc[HNAE3_MAX_USER_PRIO];
struct hclge_pg_info pg_info[HCLGE_PG_NUM];
struct hclge_tc_info tc_info[HNAE3_MAX_TC];
enum hclge_fc_mode fc_mode;
u8 rss_hash_key[HCLGE_RSS_KEY_SIZE]; /* User configured hash keys */
/* User configured lookup table entries */
u8 rss_indirection_tbl[HCLGE_RSS_IND_TBL_SIZE];
+ u16 alloc_rss_size;
u16 qs_offset;
u16 bw_limit; /* VSI BW Limit (0 = disabled) */
{
u8 tc;
- for (tc = 0; tc < hdev->tm_info.num_tc; tc++)
- if (hdev->tm_info.tc_info[tc].up == pri_id)
- break;
+ tc = hdev->tm_info.prio_tc[pri_id];
if (tc >= hdev->tm_info.num_tc)
return -EINVAL;
hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, false);
- for (pri_id = 0; pri_id < hdev->tm_info.num_tc; pri_id++) {
+ for (pri_id = 0; pri_id < HNAE3_MAX_USER_PRIO; pri_id++) {
ret = hclge_fill_pri_array(hdev, pri, pri_id);
if (ret)
return ret;
shap_cfg_cmd->pg_id = pg_id;
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
- hclge_tm_set_feild(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_B, ir_b);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_U, ir_u);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, IR_S, ir_s);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_B, bs_b);
+ hclge_tm_set_field(shap_cfg_cmd->pg_shapping_para, BS_S, bs_s);
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
shap_cfg_cmd->pri_id = pri_id;
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
- hclge_tm_set_feild(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_B, ir_b);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_U, ir_u);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, IR_S, ir_s);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_B, bs_b);
+ hclge_tm_set_field(shap_cfg_cmd->pri_shapping_para, BS_S, bs_s);
return hclge_cmd_send(&hdev->hw, &desc, 1);
}
kinfo->num_tqps / kinfo->num_tc);
vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id;
vport->dwrr = 100; /* 100 percent as init */
+ vport->alloc_rss_size = kinfo->rss_size;
for (i = 0; i < kinfo->num_tc; i++) {
if (hdev->hw_tc_map & BIT(i)) {
kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
kinfo->tc_info[i].tqp_count = kinfo->rss_size;
kinfo->tc_info[i].tc = i;
- kinfo->tc_info[i].up = hdev->tm_info.tc_info[i].up;
} else {
/* Set to default queue if TC is disable */
kinfo->tc_info[i].enable = false;
kinfo->tc_info[i].tqp_offset = 0;
kinfo->tc_info[i].tqp_count = 1;
kinfo->tc_info[i].tc = 0;
- kinfo->tc_info[i].up = 0;
}
}
+
+ memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc,
+ FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc));
}
static void hclge_tm_vport_info_update(struct hclge_dev *hdev)
for (i = 0; i < hdev->tm_info.num_tc; i++) {
hdev->tm_info.tc_info[i].tc_id = i;
hdev->tm_info.tc_info[i].tc_sch_mode = HCLGE_SCH_MODE_DWRR;
- hdev->tm_info.tc_info[i].up = i;
hdev->tm_info.tc_info[i].pgid = 0;
hdev->tm_info.tc_info[i].bw_limit =
hdev->tm_info.pg_info[0].bw_limit;
}
+ for (i = 0; i < HNAE3_MAX_USER_PRIO; i++)
+ hdev->tm_info.prio_tc[i] =
+ (i >= hdev->tm_info.num_tc) ? 0 : i;
+
hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
}
if (ret)
return ret;
+ /* Only DCB-supported dev supports qset back pressure setting */
+ if (!hnae3_dev_dcb_supported(hdev))
+ return 0;
+
for (i = 0; i < hdev->tm_info.num_tc; i++) {
ret = hclge_tm_qs_bp_cfg(hdev, i);
if (ret)
u32 rsvd1;
};
-#define hclge_tm_set_feild(dest, string, val) \
+#define hclge_tm_set_field(dest, string, val) \
hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH), val)
-#define hclge_tm_get_feild(src, string) \
+#define hclge_tm_get_field(src, string) \
hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
(HCLGE_TM_SHAP_##string##_LSH))
static const struct pci_device_id hns3_pci_tbl[] = {
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_GE), 0},
{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC), 0},
- {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC), 0},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_25GE_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_50GE_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
+ {PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
+ HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
/* required last entry */
{0, }
};
}
ae_dev->pdev = pdev;
+ ae_dev->flag = ent->driver_data;
ae_dev->dev_type = HNAE3_DEV_KNIC;
pci_set_drvdata(pdev, ae_dev);
eth_hw_addr_random(netdev);
dev_warn(priv->dev, "using random MAC address %pM\n",
netdev->dev_addr);
- /* Also copy this new MAC address into hdev */
- if (h->ae_algo->ops->set_mac_addr)
- h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
}
+
+ if (h->ae_algo->ops->set_mac_addr)
+ h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr);
+
}
static void hns3_nic_set_priv_ops(struct net_device *netdev)
unsigned long flags;
MAL_DBG2(mal, "poll(%d)" NL, budget);
- again:
+
/* Process TX skbs */
list_for_each(l, &mal->poll_list) {
struct mal_commac *mc =
spin_lock_irqsave(&mal->lock, flags);
mal_disable_eob_irq(mal);
spin_unlock_irqrestore(&mal->lock, flags);
- goto again;
}
mc->ops->poll_tx(mc->dev);
}
static int emac_get_sset_count(struct net_device *netdev, int sset)
{
switch (sset) {
+ case ETH_SS_PRIV_FLAGS:
+ return 1;
case ETH_SS_STATS:
return EMAC_STATS_LEN;
default:
unsigned int i;
switch (stringset) {
+ case ETH_SS_PRIV_FLAGS:
+ strcpy(data, "single-pause-mode");
+ break;
+
case ETH_SS_STATS:
for (i = 0; i < EMAC_STATS_LEN; i++) {
strlcpy(data, emac_ethtool_stat_strings[i],
return EMAC_MAX_REG_SIZE * sizeof(u32);
}
+#define EMAC_PRIV_ENABLE_SINGLE_PAUSE BIT(0)
+
+static int emac_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+ struct emac_adapter *adpt = netdev_priv(netdev);
+
+ adpt->single_pause_mode = !!(flags & EMAC_PRIV_ENABLE_SINGLE_PAUSE);
+
+ if (netif_running(netdev))
+ return emac_reinit_locked(adpt);
+
+ return 0;
+}
+
+static u32 emac_get_priv_flags(struct net_device *netdev)
+{
+ struct emac_adapter *adpt = netdev_priv(netdev);
+
+ return adpt->single_pause_mode ? EMAC_PRIV_ENABLE_SINGLE_PAUSE : 0;
+}
+
static const struct ethtool_ops emac_ethtool_ops = {
.get_link_ksettings = phy_ethtool_get_link_ksettings,
.set_link_ksettings = phy_ethtool_set_link_ksettings,
.get_regs_len = emac_get_regs_len,
.get_regs = emac_get_regs,
+
+ .set_priv_flags = emac_set_priv_flags,
+ .get_priv_flags = emac_get_priv_flags,
};
void emac_set_ethtool_ops(struct net_device *netdev)
mac &= ~(HUGEN | VLAN_STRIP | TPAUSE | SIMR | HUGE | MULTI_ALL |
DEBUG_MODE | SINGLE_PAUSE_MODE);
+ /* Enable single-pause-frame mode if requested.
+ *
+ * If enabled, the EMAC will send a single pause frame when the RX
+ * queue is full. This normally leads to packet loss because
+ * the pause frame disables the remote MAC only for 33ms (the quanta),
+ * and then the remote MAC continues sending packets even though
+ * the RX queue is still full.
+ *
+ * If disabled, the EMAC sends a pause frame every 31ms until the RX
+ * queue is no longer full. Normally, this is the preferred
+ * method of operation. However, when the system is hung (e.g.
+ * cores are halted), the EMAC interrupt handler is never called
+ * and so the RX queue fills up quickly and stays full. The resuling
+ * non-stop "flood" of pause frames sometimes has the effect of
+ * disabling nearby switches. In some cases, other nearby switches
+ * are also affected, shutting down the entire network.
+ *
+ * The user can enable or disable single-pause-frame mode
+ * via ethtool.
+ */
+ mac |= adpt->single_pause_mode ? SINGLE_PAUSE_MODE : 0;
+
writel_relaxed(csr1, adpt->csr + EMAC_EMAC_WRAPPER_CSR1);
writel_relaxed(mac, adpt->base + EMAC_MAC_CTRL);
/* default to automatic flow control */
adpt->automatic = true;
+
+ /* Disable single-pause-frame mode by default */
+ adpt->single_pause_mode = false;
}
/* Get the clock */
bool tx_flow_control;
bool rx_flow_control;
+ /* True == use single-pause-frame mode. */
+ bool single_pause_mode;
+
/* Ring parameter */
u8 tpd_burst;
u8 rfd_burst;
if (likely(RTL_R16(IntrStatus) & RxAckBits))
work_done += rtl8139_rx(dev, tp, budget);
- if (work_done < budget && napi_complete_done(napi, work_done)) {
+ if (work_done < budget) {
unsigned long flags;
spin_lock_irqsave(&tp->lock, flags);
- RTL_W16_F(IntrMask, rtl8139_intr_mask);
+ if (napi_complete_done(napi, work_done))
+ RTL_W16_F(IntrMask, rtl8139_intr_mask);
spin_unlock_irqrestore(&tp->lock, flags);
}
spin_unlock(&tp->rx_lock);
{ .compatible = "allwinner,sun8i-h3-emac" },
{ .compatible = "allwinner,sun8i-v3s-emac" },
{ .compatible = "allwinner,sun50i-a64-emac" },
+ {},
};
/* If phy-handle property is passed from DT, use it as the PHY */
u32 num_chn;
u32 send_sections;
u32 recv_sections;
+ u32 send_section_size;
+ u32 recv_section_size;
};
enum rndis_device_state {
net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
- net_device->recv_section_size = NETVSC_RECV_SECTION_SIZE;
- net_device->send_section_size = NETVSC_SEND_SECTION_SIZE;
-
init_completion(&net_device->channel_init_wait);
init_waitqueue_head(&net_device->subchan_open);
INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
int ret = 0;
/* Get receive buffer area. */
- buf_size = device_info->recv_sections * net_device->recv_section_size;
+ buf_size = device_info->recv_sections * device_info->recv_section_size;
buf_size = roundup(buf_size, PAGE_SIZE);
net_device->recv_buf = vzalloc(buf_size);
goto cleanup;
/* Now setup the send buffer. */
- buf_size = device_info->send_sections * net_device->send_section_size;
+ buf_size = device_info->send_sections * device_info->send_section_size;
buf_size = round_up(buf_size, PAGE_SIZE);
net_device->send_buf = vzalloc(buf_size);
device_info.num_chn = count;
device_info.ring_size = ring_size;
device_info.send_sections = nvdev->send_section_cnt;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = nvdev->recv_section_cnt;
+ device_info.recv_section_size = nvdev->recv_section_size;
rndis_filter_device_remove(dev, nvdev);
device_info.ring_size = ring_size;
device_info.num_chn = nvdev->num_chn;
device_info.send_sections = nvdev->send_section_cnt;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = nvdev->recv_section_cnt;
+ device_info.recv_section_size = nvdev->recv_section_size;
rndis_filter_device_remove(hdev, nvdev);
device_info.num_chn = nvdev->num_chn;
device_info.ring_size = ring_size;
device_info.send_sections = new_tx;
+ device_info.send_section_size = nvdev->send_section_size;
device_info.recv_sections = new_rx;
+ device_info.recv_section_size = nvdev->recv_section_size;
netif_device_detach(ndev);
was_opened = rndis_filter_opened(nvdev);
device_info.ring_size = ring_size;
device_info.num_chn = VRSS_CHANNEL_DEFAULT;
device_info.send_sections = NETVSC_DEFAULT_TX;
+ device_info.send_section_size = NETVSC_SEND_SECTION_SIZE;
device_info.recv_sections = NETVSC_DEFAULT_RX;
+ device_info.recv_section_size = NETVSC_RECV_SECTION_SIZE;
nvdev = rndis_filter_device_add(dev, &device_info);
if (IS_ERR(nvdev)) {
endif
-menuconfig PHYLIB
- tristate "PHY Device support and infrastructure"
- depends on NETDEVICES
- select MDIO_DEVICE
- help
- Ethernet controllers are usually attached to PHY
- devices. This option provides infrastructure for
- managing PHY devices.
-
config PHYLINK
tristate
depends on NETDEVICES
configuration links, PHYs, and Serdes links with MAC level
autonegotiation modes.
+menuconfig PHYLIB
+ tristate "PHY Device support and infrastructure"
+ depends on NETDEVICES
+ select MDIO_DEVICE
+ help
+ Ethernet controllers are usually attached to PHY
+ devices. This option provides infrastructure for
+ managing PHY devices.
+
if PHYLIB
config SWPHY
cmd->base.port = PORT_BNC;
else
cmd->base.port = PORT_MII;
-
+ cmd->base.transceiver = phy_is_internal(phydev) ?
+ XCVR_INTERNAL : XCVR_EXTERNAL;
cmd->base.phy_address = phydev->mdio.addr;
cmd->base.autoneg = phydev->autoneg;
cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
{
const char *drv_name = phydev->drv ? phydev->drv->name : "unbound";
char *irq_str;
- char irq_num[4];
+ char irq_num[8];
switch(phydev->irq) {
case PHY_POLL:
priv->phy_drv->read_status(phydev);
val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
- val &= XILINX_GMII2RGMII_SPEED_MASK;
+ val &= ~XILINX_GMII2RGMII_SPEED_MASK;
if (phydev->speed == SPEED_1000)
val |= BMCR_SPEED1000;
struct ethtool_eeprom *ee, u8 *data)
{
struct lan78xx_net *dev = netdev_priv(netdev);
+ int ret;
+
+ ret = usb_autopm_get_interface(dev->intf);
+ if (ret)
+ return ret;
ee->magic = LAN78XX_EEPROM_MAGIC;
- return lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+ ret = lan78xx_read_raw_eeprom(dev, ee->offset, ee->len, data);
+
+ usb_autopm_put_interface(dev->intf);
+
+ return ret;
}
static int lan78xx_ethtool_set_eeprom(struct net_device *netdev,
struct ethtool_eeprom *ee, u8 *data)
{
struct lan78xx_net *dev = netdev_priv(netdev);
+ int ret;
+
+ ret = usb_autopm_get_interface(dev->intf);
+ if (ret)
+ return ret;
- /* Allow entire eeprom update only */
- if ((ee->magic == LAN78XX_EEPROM_MAGIC) &&
- (ee->offset == 0) &&
- (ee->len == 512) &&
- (data[0] == EEPROM_INDICATOR))
- return lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
+ /* Invalid EEPROM_INDICATOR at offset zero will result in a failure
+ * to load data from EEPROM
+ */
+ if (ee->magic == LAN78XX_EEPROM_MAGIC)
+ ret = lan78xx_write_raw_eeprom(dev, ee->offset, ee->len, data);
else if ((ee->magic == LAN78XX_OTP_MAGIC) &&
(ee->offset == 0) &&
(ee->len == 512) &&
(data[0] == OTP_INDICATOR_1))
- return lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
+ ret = lan78xx_write_raw_otp(dev, ee->offset, ee->len, data);
+
+ usb_autopm_put_interface(dev->intf);
- return -EINVAL;
+ return ret;
}
static void lan78xx_get_strings(struct net_device *netdev, u32 stringset,
/* LAN7801 only has RGMII mode */
if (dev->chipid == ID_REV_CHIP_ID_7801_)
buf &= ~MAC_CR_GMII_EN_;
- buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
ret = lan78xx_write_reg(dev, MAC_CR, buf);
ret = lan78xx_read_reg(dev, MAC_TX, &buf);
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_namespace_index *nsindex;
+ /*
+ * If any of the DIMMs do not support labels the only
+ * possible BTT format is v1.
+ */
+ if (!ndd) {
+ loop_bitmask = 0;
+ break;
+ }
+
nsindex = to_namespace_index(ndd, ndd->ns_current);
if (nsindex == NULL)
loop_bitmask |= 1;
return false;
if (nvme_req(req)->status & NVME_SC_DNR)
return false;
- if (jiffies - req->start_time >= req->timeout)
- return false;
if (nvme_req(req)->retries >= nvme_max_retries)
return false;
return true;
container_of(work, struct nvme_ctrl, async_event_work);
spin_lock_irq(&ctrl->lock);
- while (ctrl->event_limit > 0) {
+ while (ctrl->state == NVME_CTRL_LIVE && ctrl->event_limit > 0) {
int aer_idx = --ctrl->event_limit;
spin_unlock_irq(&ctrl->lock);
/*FALLTHRU*/
case NVME_SC_ABORT_REQ:
++ctrl->event_limit;
- queue_work(nvme_wq, &ctrl->async_event_work);
+ if (ctrl->state == NVME_CTRL_LIVE)
+ queue_work(nvme_wq, &ctrl->async_event_work);
break;
default:
break;
nvme_queue_scan(ctrl);
break;
case NVME_AER_NOTICE_FW_ACT_STARTING:
- schedule_work(&ctrl->fw_act_work);
+ queue_work(nvme_wq, &ctrl->fw_act_work);
break;
default:
dev_warn(ctrl->device, "async event result %08x\n", result);
opts->queue_size = NVMF_DEF_QUEUE_SIZE;
opts->nr_io_queues = num_online_cpus();
opts->reconnect_delay = NVMF_DEF_RECONNECT_DELAY;
+ opts->kato = NVME_DEFAULT_KATO;
options = o = kstrdup(buf, GFP_KERNEL);
if (!options)
goto out;
}
- if (opts->discovery_nqn) {
- pr_err("Discovery controllers cannot accept keep_alive_tmo != 0\n");
- ret = -EINVAL;
- goto out;
- }
-
if (token < 0) {
pr_err("Invalid keep_alive_tmo %d\n", token);
ret = -EINVAL;
goto out;
- } else if (token == 0) {
+ } else if (token == 0 && !opts->discovery_nqn) {
/* Allowed for debug */
pr_warn("keep_alive_tmo 0 won't execute keep alives!!!\n");
}
opts->kato = token;
+
+ if (opts->discovery_nqn && opts->kato) {
+ pr_err("Discovery controllers cannot accept KATO != 0\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
break;
case NVMF_OPT_CTRL_LOSS_TMO:
if (match_int(args, &token)) {
uuid_copy(&opts->host->id, &hostid);
out:
- if (!opts->discovery_nqn && !opts->kato)
- opts->kato = NVME_DEFAULT_KATO;
kfree(options);
return ret;
}
if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
else if (freq->status)
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
/*
* For the linux implementation, if we have an unsuccesful
*/
if (freq->transferred_length !=
be32_to_cpu(op->cmd_iu.data_len)) {
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
result.u64 = 0;
freq->transferred_length ||
op->rsp_iu.status_code ||
sqe->common.command_id != cqe->command_id)) {
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
result = cqe->result;
break;
default:
- status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_INTERNAL << 1);
goto done;
}
* as well as those by FC-NVME spec.
*/
WARN_ON_ONCE(sqe->common.metadata);
- WARN_ON_ONCE(sqe->common.dptr.prp1);
- WARN_ON_ONCE(sqe->common.dptr.prp2);
sqe->common.flags |= NVME_CMD_SGL_METABUF;
/*
- * format SQE DPTR field per FC-NVME rules
- * type=data block descr; subtype=offset;
- * offset is currently 0.
+ * format SQE DPTR field per FC-NVME rules:
+ * type=0x5 Transport SGL Data Block Descriptor
+ * subtype=0xA Transport-specific value
+ * address=0
+ * length=length of the data series
*/
- sqe->rw.dptr.sgl.type = NVME_SGL_FMT_OFFSET;
+ sqe->rw.dptr.sgl.type = (NVME_TRANSPORT_SGL_DATA_DESC << 4) |
+ NVME_SGL_FMT_TRANSPORT_A;
sqe->rw.dptr.sgl.length = cpu_to_le32(data_len);
sqe->rw.dptr.sgl.addr = 0;
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/once.h>
#include <linux/pci.h>
#include <linux/poison.h>
#include <linux/t10-pi.h>
}
#endif
+static void nvme_print_sgl(struct scatterlist *sgl, int nents)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ dma_addr_t phys = sg_phys(sg);
+ pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
+ "dma_address:%pad dma_length:%d\n",
+ i, &phys, sg->offset, sg->length, &sg_dma_address(sg),
+ sg_dma_len(sg));
+ }
+}
+
static blk_status_t nvme_setup_prps(struct nvme_dev *dev, struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
return BLK_STS_OK;
bad_sgl:
- if (WARN_ONCE(1, "Invalid SGL for payload:%d nents:%d\n",
- blk_rq_payload_bytes(req), iod->nents)) {
- for_each_sg(iod->sg, sg, iod->nents, i) {
- dma_addr_t phys = sg_phys(sg);
- pr_warn("sg[%d] phys_addr:%pad offset:%d length:%d "
- "dma_address:%pad dma_length:%d\n", i, &phys,
- sg->offset, sg->length,
- &sg_dma_address(sg),
- sg_dma_len(sg));
- }
- }
+ WARN(DO_ONCE(nvme_print_sgl, iod->sg, iod->nents),
+ "Invalid SGL for payload:%d nents:%d\n",
+ blk_rq_payload_bytes(req), iod->nents);
return BLK_STS_IOERR;
-
}
static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
if (result < 0)
goto release_cq;
+ nvme_init_queue(nvmeq, qid);
result = queue_request_irq(nvmeq);
if (result < 0)
goto release_sq;
- nvme_init_queue(nvmeq, qid);
return result;
release_sq:
return result;
nvmeq->cq_vector = 0;
+ nvme_init_queue(nvmeq, 0);
result = queue_request_irq(nvmeq);
if (result) {
nvmeq->cq_vector = -1;
if (result)
goto out;
- nvme_init_queue(dev->queues[0], 0);
result = nvme_alloc_admin_tags(dev);
if (result)
goto out;
}
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
- WARN_ON_ONCE(!changed);
+ if (!changed) {
+ /* state change failure is ok if we're in DELETING state */
+ WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
+ return;
+ }
+
ctrl->ctrl.nr_reconnects = 0;
nvme_start_ctrl(&ctrl->ctrl);
struct nvme_rdma_ctrl *ctrl = container_of(work,
struct nvme_rdma_ctrl, err_work);
- nvme_stop_ctrl(&ctrl->ctrl);
+ nvme_stop_keep_alive(&ctrl->ctrl);
if (ctrl->ctrl.queue_count > 1) {
nvme_stop_queues(&ctrl->ctrl);
if (status)
nvmet_set_status(req, status);
- /* XXX: need to fill in something useful for sq_head */
- req->rsp->sq_head = 0;
- if (likely(req->sq)) /* may happen during early failure */
- req->rsp->sq_id = cpu_to_le16(req->sq->qid);
+ if (req->sq->size)
+ req->sq->sqhd = (req->sq->sqhd + 1) % req->sq->size;
+ req->rsp->sq_head = cpu_to_le16(req->sq->sqhd);
+ req->rsp->sq_id = cpu_to_le16(req->sq->qid);
req->rsp->command_id = req->cmd->common.command_id;
if (req->ns)
void nvmet_sq_setup(struct nvmet_ctrl *ctrl, struct nvmet_sq *sq,
u16 qid, u16 size)
{
+ sq->sqhd = 0;
sq->qid = qid;
sq->size = size;
pr_warn("queue already connected!\n");
return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
}
+ if (!sqsize) {
+ pr_warn("queue size zero!\n");
+ return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
+ }
- nvmet_cq_setup(ctrl, req->cq, qid, sqsize);
- nvmet_sq_setup(ctrl, req->sq, qid, sqsize);
+ /* note: convert queue size from 0's-based value to 1's-based value */
+ nvmet_cq_setup(ctrl, req->cq, qid, sqsize + 1);
+ nvmet_sq_setup(ctrl, req->sq, qid, sqsize + 1);
return 0;
}
u32 a_id;
struct nvmet_fc_tgtport *tgtport;
struct list_head a_list;
- struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES];
+ struct nvmet_fc_tgt_queue *queues[NVMET_NR_QUEUES + 1];
struct kref ref;
};
unsigned long flags;
int ret;
- if (qid >= NVMET_NR_QUEUES)
+ if (qid > NVMET_NR_QUEUES)
return NULL;
queue = kzalloc((sizeof(*queue) +
u16 qid = nvmet_fc_getqueueid(connection_id);
unsigned long flags;
+ if (qid > NVMET_NR_QUEUES)
+ return NULL;
+
spin_lock_irqsave(&tgtport->lock, flags);
list_for_each_entry(assoc, &tgtport->assoc_list, a_list) {
if (association_id == assoc->association_id) {
int i;
spin_lock_irqsave(&tgtport->lock, flags);
- for (i = NVMET_NR_QUEUES - 1; i >= 0; i--) {
+ for (i = NVMET_NR_QUEUES; i >= 0; i--) {
queue = assoc->queues[i];
if (queue) {
if (!nvmet_fc_tgt_q_get(queue))
spin_lock_irqsave(&fod->flock, flags);
fod->writedataactive = false;
spin_unlock_irqrestore(&fod->flock, flags);
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
} else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
fcpreq->fcp_error = ret;
fcpreq->transferred_length = 0;
/* if in the middle of an io and we need to tear down */
if (abort) {
if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
return true;
}
fod->abort = true;
spin_unlock(&fod->flock);
- nvmet_req_complete(&fod->req,
- NVME_SC_FC_TRANSPORT_ERROR);
+ nvmet_req_complete(&fod->req, NVME_SC_INTERNAL);
return;
}
{
struct nvmet_fc_tgtport *tgtport = port->priv;
unsigned long flags;
+ bool matched = false;
spin_lock_irqsave(&nvmet_fc_tgtlock, flags);
if (tgtport->port == port) {
- nvmet_fc_tgtport_put(tgtport);
+ matched = true;
tgtport->port = NULL;
}
spin_unlock_irqrestore(&nvmet_fc_tgtlock, flags);
+
+ if (matched)
+ nvmet_fc_tgtport_put(tgtport);
}
static struct nvmet_fabrics_ops nvmet_fc_tgt_fcp_ops = {
struct fcloop_lport *lport;
struct list_head nport_list;
struct kref ref;
- struct completion rport_unreg_done;
- struct completion tport_unreg_done;
u64 node_name;
u64 port_name;
u32 port_role;
tfcp_req->aborted = true;
spin_unlock(&tfcp_req->reqlock);
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+ tfcp_req->status = NVME_SC_INTERNAL;
/*
* nothing more to do. If io wasn't active, the transport should
schedule_work(&inireq->iniwork);
}
+static void
+fcloop_nport_free(struct kref *ref)
+{
+ struct fcloop_nport *nport =
+ container_of(ref, struct fcloop_nport, ref);
+ unsigned long flags;
+
+ spin_lock_irqsave(&fcloop_lock, flags);
+ list_del(&nport->nport_list);
+ spin_unlock_irqrestore(&fcloop_lock, flags);
+
+ kfree(nport);
+}
+
+static void
+fcloop_nport_put(struct fcloop_nport *nport)
+{
+ kref_put(&nport->ref, fcloop_nport_free);
+}
+
+static int
+fcloop_nport_get(struct fcloop_nport *nport)
+{
+ return kref_get_unless_zero(&nport->ref);
+}
+
static void
fcloop_localport_delete(struct nvme_fc_local_port *localport)
{
{
struct fcloop_rport *rport = remoteport->private;
- /* release any threads waiting for the unreg to complete */
- complete(&rport->nport->rport_unreg_done);
+ fcloop_nport_put(rport->nport);
}
static void
{
struct fcloop_tport *tport = targetport->private;
- /* release any threads waiting for the unreg to complete */
- complete(&tport->nport->tport_unreg_done);
+ fcloop_nport_put(tport->nport);
}
#define FCLOOP_HW_QUEUES 4
goto out_free_opts;
}
+ memset(&pinfo, 0, sizeof(pinfo));
pinfo.node_name = opts->wwnn;
pinfo.port_name = opts->wwpn;
pinfo.port_role = opts->roles;
return ret ? ret : count;
}
-static void
-fcloop_nport_free(struct kref *ref)
-{
- struct fcloop_nport *nport =
- container_of(ref, struct fcloop_nport, ref);
- unsigned long flags;
-
- spin_lock_irqsave(&fcloop_lock, flags);
- list_del(&nport->nport_list);
- spin_unlock_irqrestore(&fcloop_lock, flags);
-
- kfree(nport);
-}
-
-static void
-fcloop_nport_put(struct fcloop_nport *nport)
-{
- kref_put(&nport->ref, fcloop_nport_free);
-}
-
-static int
-fcloop_nport_get(struct fcloop_nport *nport)
-{
- return kref_get_unless_zero(&nport->ref);
-}
-
static struct fcloop_nport *
fcloop_alloc_nport(const char *buf, size_t count, bool remoteport)
{
if (!nport)
return -EIO;
+ memset(&pinfo, 0, sizeof(pinfo));
pinfo.node_name = nport->node_name;
pinfo.port_name = nport->port_name;
pinfo.port_role = nport->port_role;
}
static int
-__wait_remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
+__remoteport_unreg(struct fcloop_nport *nport, struct fcloop_rport *rport)
{
- int ret;
-
if (!rport)
return -EALREADY;
- init_completion(&nport->rport_unreg_done);
-
- ret = nvme_fc_unregister_remoteport(rport->remoteport);
- if (ret)
- return ret;
-
- wait_for_completion(&nport->rport_unreg_done);
-
- fcloop_nport_put(nport);
-
- return ret;
+ return nvme_fc_unregister_remoteport(rport->remoteport);
}
static ssize_t
if (!nport)
return -ENOENT;
- ret = __wait_remoteport_unreg(nport, rport);
+ ret = __remoteport_unreg(nport, rport);
return ret ? ret : count;
}
}
static int
-__wait_targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
+__targetport_unreg(struct fcloop_nport *nport, struct fcloop_tport *tport)
{
- int ret;
-
if (!tport)
return -EALREADY;
- init_completion(&nport->tport_unreg_done);
-
- ret = nvmet_fc_unregister_targetport(tport->targetport);
- if (ret)
- return ret;
-
- wait_for_completion(&nport->tport_unreg_done);
-
- fcloop_nport_put(nport);
-
- return ret;
+ return nvmet_fc_unregister_targetport(tport->targetport);
}
static ssize_t
if (!nport)
return -ENOENT;
- ret = __wait_targetport_unreg(nport, tport);
+ ret = __targetport_unreg(nport, tport);
return ret ? ret : count;
}
spin_unlock_irqrestore(&fcloop_lock, flags);
- ret = __wait_targetport_unreg(nport, tport);
+ ret = __targetport_unreg(nport, tport);
if (ret)
pr_warn("%s: Failed deleting target port\n", __func__);
- ret = __wait_remoteport_unreg(nport, rport);
+ ret = __remoteport_unreg(nport, rport);
if (ret)
pr_warn("%s: Failed deleting remote port\n", __func__);
struct percpu_ref ref;
u16 qid;
u16 size;
+ u16 sqhd;
struct completion free_done;
struct completion confirm_done;
};
return ret;
}
-static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test)
+static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq)
{
- u8 irq;
u8 msi_count;
struct pci_epf *epf = epf_test->epf;
struct pci_epc *epc = epf->epc;
reg->status |= STATUS_IRQ_RAISED;
msi_count = pci_epc_get_msi(epc);
- irq = (reg->command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
if (irq > msi_count || msi_count <= 0)
pci_epc_raise_irq(epc, PCI_EPC_IRQ_LEGACY, 0);
else
reg->command = 0;
reg->status = 0;
+ irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
+
if (command & COMMAND_RAISE_LEGACY_IRQ) {
reg->status = STATUS_IRQ_RAISED;
pci_epc_raise_irq(epc, PCI_EPC_IRQ_LEGACY, 0);
reg->status |= STATUS_WRITE_FAIL;
else
reg->status |= STATUS_WRITE_SUCCESS;
- pci_epf_test_raise_irq(epf_test);
+ pci_epf_test_raise_irq(epf_test, irq);
goto reset_handler;
}
reg->status |= STATUS_READ_SUCCESS;
else
reg->status |= STATUS_READ_FAIL;
- pci_epf_test_raise_irq(epf_test);
+ pci_epf_test_raise_irq(epf_test, irq);
goto reset_handler;
}
reg->status |= STATUS_COPY_SUCCESS;
else
reg->status |= STATUS_COPY_FAIL;
- pci_epf_test_raise_irq(epf_test);
+ pci_epf_test_raise_irq(epf_test, irq);
goto reset_handler;
}
if (command & COMMAND_RAISE_MSI_IRQ) {
msi_count = pci_epc_get_msi(epc);
- irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
if (irq > msi_count || msi_count <= 0)
goto reset_handler;
reg->status = STATUS_IRQ_RAISED;
const char *buf, size_t count)
{
struct pci_dev *pdev = to_pci_dev(dev);
- char *driver_override, *old = pdev->driver_override, *cp;
+ char *driver_override, *old, *cp;
/* We need to keep extra room for a newline */
if (count >= (PAGE_SIZE - 1))
if (cp)
*cp = '\0';
+ device_lock(dev);
+ old = pdev->driver_override;
if (strlen(driver_override)) {
pdev->driver_override = driver_override;
} else {
kfree(driver_override);
pdev->driver_override = NULL;
}
+ device_unlock(dev);
kfree(old);
struct device_attribute *attr, char *buf)
{
struct pci_dev *pdev = to_pci_dev(dev);
+ ssize_t len;
- return snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+ device_lock(dev);
+ len = snprintf(buf, PAGE_SIZE, "%s\n", pdev->driver_override);
+ device_unlock(dev);
+ return len;
}
static DEVICE_ATTR_RW(driver_override);
ret = armpmu_register(pmu);
if (ret) {
pr_warn("Failed to register PMU for CPU%d\n", cpu);
+ kfree(pmu->name);
return ret;
}
}
{
struct acpi_device *device = bl_get_data(b);
- if (b->props.power == FB_BLANK_POWERDOWN)
- call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3);
- else
- call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0);
+ if (fext) {
+ if (b->props.power == FB_BLANK_POWERDOWN)
+ call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x3);
+ else
+ call_fext_func(fext, FUNC_BACKLIGHT, 0x1, 0x4, 0x0);
+ }
return set_lcd_level(device, b->props.brightness);
}
dasd_schedule_device_bh(device);
if (device->block) {
dasd_schedule_block_bh(device->block);
- blk_mq_run_hw_queues(device->block->request_queue, true);
+ if (device->block->request_queue)
+ blk_mq_run_hw_queues(device->block->request_queue,
+ true);
}
}
EXPORT_SYMBOL_GPL(dasd_generic_handle_state_change);
dasd_schedule_device_bh(device);
if (device->block) {
dasd_schedule_block_bh(device->block);
- blk_mq_run_hw_queues(device->block->request_queue, true);
+ if (device->block->request_queue)
+ blk_mq_run_hw_queues(device->block->request_queue,
+ true);
}
if (!device->stopped)
if (device->block) {
dasd_schedule_block_bh(device->block);
- blk_mq_run_hw_queues(device->block->request_queue, true);
+ if (device->block->request_queue)
+ blk_mq_run_hw_queues(device->block->request_queue,
+ true);
}
clear_bit(DASD_FLAG_SUSPENDED, &device->flags);
static void scm_request_finish(struct scm_request *scmrq)
{
struct scm_blk_dev *bdev = scmrq->bdev;
- int *error;
+ blk_status_t *error;
int i;
for (i = 0; i < nr_requests_per_io && scmrq->request[i]; i++) {
static void scm_blk_request_done(struct request *req)
{
- int *error = blk_mq_rq_to_pdu(req);
+ blk_status_t *error = blk_mq_rq_to_pdu(req);
blk_mq_end_request(req, *error);
}
atomic_set(&bdev->queued_reqs, 0);
bdev->tag_set.ops = &scm_mq_ops;
- bdev->tag_set.cmd_size = sizeof(int);
+ bdev->tag_set.cmd_size = sizeof(blk_status_t);
bdev->tag_set.nr_hw_queues = nr_requests;
bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
static int recovery_check(struct device *dev, void *data)
{
struct ccw_device *cdev = to_ccwdev(dev);
+ struct subchannel *sch;
int *redo = data;
spin_lock_irq(cdev->ccwlock);
switch (cdev->private->state) {
+ case DEV_STATE_ONLINE:
+ sch = to_subchannel(cdev->dev.parent);
+ if ((sch->schib.pmcw.pam & sch->opm) == sch->vpm)
+ break;
+ /* fall through */
case DEV_STATE_DISCONNECTED:
CIO_MSG_EVENT(3, "recovery: trigger 0.%x.%04x\n",
cdev->private->dev_id.ssid,
}
spin_unlock_irq(&recovery_lock);
} else
- CIO_MSG_EVENT(4, "recovery: end\n");
+ CIO_MSG_EVENT(3, "recovery: end\n");
}
static DECLARE_WORK(recovery_work, recovery_work_func);
schedule_work(&recovery_work);
}
-static void ccw_device_schedule_recovery(void)
+void ccw_device_schedule_recovery(void)
{
unsigned long flags;
- CIO_MSG_EVENT(4, "recovery: schedule\n");
+ CIO_MSG_EVENT(3, "recovery: schedule\n");
spin_lock_irqsave(&recovery_lock, flags);
if (!timer_pending(&recovery_timer) || (recovery_phase != 0)) {
recovery_phase = 0;
void ccw_device_set_notoper(struct ccw_device *cdev);
void ccw_device_set_timeout(struct ccw_device *, int);
+void ccw_device_schedule_recovery(void);
/* Channel measurement facility related */
void retry_set_schib(struct ccw_device *cdev);
}
}
+static void ccw_device_handle_broken_paths(struct ccw_device *cdev)
+{
+ struct subchannel *sch = to_subchannel(cdev->dev.parent);
+ u8 broken_paths = (sch->schib.pmcw.pam & sch->opm) ^ sch->vpm;
+
+ if (broken_paths && (cdev->private->path_broken_mask != broken_paths))
+ ccw_device_schedule_recovery();
+
+ cdev->private->path_broken_mask = broken_paths;
+}
+
void ccw_device_verify_done(struct ccw_device *cdev, int err)
{
struct subchannel *sch;
memset(&cdev->private->irb, 0, sizeof(struct irb));
}
ccw_device_report_path_events(cdev);
+ ccw_device_handle_broken_paths(cdev);
break;
case -ETIME:
case -EUSERS:
not operable */
u8 path_gone_mask; /* mask of paths, that became unavailable */
u8 path_new_mask; /* mask of paths, that became available */
+ u8 path_broken_mask; /* mask of paths, which were found to be
+ unusable */
struct {
unsigned int fast:1; /* post with "channel end" */
unsigned int repall:1; /* report every interrupt status */
int status;
dresp = (struct aac_mount *) fib_data(fibptr);
- if (!(fibptr->dev->supplement_adapter_info.supported_options2 &
- AAC_OPTION_VARIABLE_BLOCK_SIZE))
+ if (!aac_supports_2T(fibptr->dev)) {
dresp->mnt[0].capacityhigh = 0;
- if ((le32_to_cpu(dresp->status) != ST_OK) ||
- (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) {
- _aac_probe_container2(context, fibptr);
- return;
+ if ((le32_to_cpu(dresp->status) == ST_OK) &&
+ (le32_to_cpu(dresp->mnt[0].vol) != CT_NONE)) {
+ _aac_probe_container2(context, fibptr);
+ return;
+ }
}
scsicmd = (struct scsi_cmnd *) context;
return 0;
}
+static inline int aac_supports_2T(struct aac_dev *dev)
+{
+ return (dev->adapter_info.options & AAC_OPT_NEW_COMM_64);
+}
+
char * get_container_type(unsigned type);
extern int numacb;
extern char aac_driver_version[];
bus = aac_logical_to_phys(scmd_channel(cmd));
cid = scmd_id(cmd);
- info = &aac->hba_map[bus][cid];
- if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS ||
- info->devtype != AAC_DEVTYPE_NATIVE_RAW)
+
+ if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS)
return FAILED;
- if (info->reset_state > 0)
+ info = &aac->hba_map[bus][cid];
+
+ if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
+ info->reset_state > 0)
return FAILED;
pr_err("%s: Host adapter reset request. SCSI hang ?\n",
bus = aac_logical_to_phys(scmd_channel(cmd));
cid = scmd_id(cmd);
- info = &aac->hba_map[bus][cid];
- if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS ||
- info->devtype != AAC_DEVTYPE_NATIVE_RAW)
+
+ if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS)
return FAILED;
- if (info->reset_state > 0)
+ info = &aac->hba_map[bus][cid];
+
+ if (info->devtype != AAC_DEVTYPE_NATIVE_RAW &&
+ info->reset_state > 0)
return FAILED;
pr_err("%s: Host adapter reset request. SCSI hang ?\n",
aac_set_intx_mode(dev);
src_writel(dev, MUnit.IDR, IOP_SRC_RESET_MASK);
+
+ msleep(5000);
}
static void aac_send_hardware_soft_reset(struct aac_dev *dev)
* Params : SCpnt - command causing reset
* Returns : one of SCSI_RESET_ macros
*/
-int acornscsi_host_reset(struct Scsi_Host *shpnt)
+int acornscsi_host_reset(struct scsi_cmnd *SCpnt)
{
- AS_Host *host = (AS_Host *)shpnt->hostdata;
+ AS_Host *host = (AS_Host *)SCpnt->device->host->hostdata;
struct scsi_cmnd *SCptr;
host->stats.resets += 1;
printk(KERN_WARNING "acornscsi_reset: ");
print_sbic_status(asr, ssr, host->scsi.phase);
- for (devidx = 0; devidx < 9; devidx ++) {
+ for (devidx = 0; devidx < 9; devidx++)
acornscsi_dumplog(host, devidx);
}
#endif
"Extents and RPI headers enabled.\n");
}
mempool_free(mboxq, phba->mbox_mem_pool);
+ rc = -EIO;
goto out_free_bsmbx;
}
wcqe->total_data_placed);
nCmd->transferred_length = 0;
nCmd->rcv_rsplen = 0;
- nCmd->status = NVME_SC_FC_TRANSPORT_ERROR;
+ nCmd->status = NVME_SC_INTERNAL;
}
}
goto rel;
if (unlikely(res == QLA_FUNCTION_FAILED))
- fd->status = NVME_SC_FC_TRANSPORT_ERROR;
+ fd->status = NVME_SC_INTERNAL;
else
fd->status = 0;
if (sshdr.asc == 0x20 || /* Invalid command operation code */
sshdr.asc == 0x21 || /* Logical block address out of range */
sshdr.asc == 0x24 || /* Invalid field in cdb */
- sshdr.asc == 0x26) { /* Parameter value invalid */
+ sshdr.asc == 0x26 || /* Parameter value invalid */
+ sshdr.asc == 0x27) { /* Write protected */
set_host_byte(scmd, DID_TARGET_FAILURE);
}
return SUCCESS;
list_for_each_entry(rport, &fc_host->rports, peers) {
- if ((rport->port_state == FC_PORTSTATE_BLOCKED) &&
+ if ((rport->port_state == FC_PORTSTATE_BLOCKED ||
+ rport->port_state == FC_PORTSTATE_NOTPRESENT) &&
(rport->channel == channel)) {
switch (fc_host->tgtid_bind_type) {
memcpy(&rport->port_name, &ids->port_name,
sizeof(rport->port_name));
rport->port_id = ids->port_id;
- rport->roles = ids->roles;
rport->port_state = FC_PORTSTATE_ONLINE;
rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
fci->f->dd_fcrport_size);
spin_unlock_irqrestore(shost->host_lock, flags);
- if (ids->roles & FC_PORT_ROLE_FCP_TARGET) {
- scsi_target_unblock(&rport->dev, SDEV_RUNNING);
-
- /* initiate a scan of the target */
- spin_lock_irqsave(shost->host_lock, flags);
- rport->flags |= FC_RPORT_SCAN_PENDING;
- scsi_queue_work(shost, &rport->scan_work);
- spin_unlock_irqrestore(shost->host_lock, flags);
- }
+ fc_remote_port_rolechg(rport, ids->roles);
return rport;
}
}
static enum blk_eh_timer_return
fc_bsg_job_timeout(struct request *req)
{
- struct bsg_job *job = (void *) req->special;
+ struct bsg_job *job = blk_mq_rq_to_pdu(req);
struct Scsi_Host *shost = fc_bsg_to_shost(job);
struct fc_rport *rport = fc_bsg_to_rport(job);
struct fc_internal *i = to_fc_internal(shost->transportt);
uint32_t group;
nlh = nlmsg_hdr(skb);
- if (nlh->nlmsg_len < sizeof(*nlh) ||
+ if (nlh->nlmsg_len < sizeof(*nlh) + sizeof(*ev) ||
skb->len < nlh->nlmsg_len) {
break;
}
sd_config_discard(sdkp, SD_LBP_WS16);
else if (sdkp->lbpws10)
sd_config_discard(sdkp, SD_LBP_WS10);
- else if (sdkp->lbpu && sdkp->max_unmap_blocks)
- sd_config_discard(sdkp, SD_LBP_UNMAP);
else
sd_config_discard(sdkp, SD_LBP_DISABLE);
}
return max_sectors << 9;
}
+static void
+sg_fill_request_table(Sg_fd *sfp, sg_req_info_t *rinfo)
+{
+ Sg_request *srp;
+ int val;
+ unsigned int ms;
+
+ val = 0;
+ list_for_each_entry(srp, &sfp->rq_list, entry) {
+ if (val > SG_MAX_QUEUE)
+ break;
+ rinfo[val].req_state = srp->done + 1;
+ rinfo[val].problem =
+ srp->header.masked_status &
+ srp->header.host_status &
+ srp->header.driver_status;
+ if (srp->done)
+ rinfo[val].duration =
+ srp->header.duration;
+ else {
+ ms = jiffies_to_msecs(jiffies);
+ rinfo[val].duration =
+ (ms > srp->header.duration) ?
+ (ms - srp->header.duration) : 0;
+ }
+ rinfo[val].orphan = srp->orphan;
+ rinfo[val].sg_io_owned = srp->sg_io_owned;
+ rinfo[val].pack_id = srp->header.pack_id;
+ rinfo[val].usr_ptr = srp->header.usr_ptr;
+ val++;
+ }
+}
+
static long
sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
{
return -EFAULT;
else {
sg_req_info_t *rinfo;
- unsigned int ms;
- rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
- GFP_KERNEL);
+ rinfo = kzalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE,
+ GFP_KERNEL);
if (!rinfo)
return -ENOMEM;
read_lock_irqsave(&sfp->rq_list_lock, iflags);
- val = 0;
- list_for_each_entry(srp, &sfp->rq_list, entry) {
- if (val >= SG_MAX_QUEUE)
- break;
- memset(&rinfo[val], 0, SZ_SG_REQ_INFO);
- rinfo[val].req_state = srp->done + 1;
- rinfo[val].problem =
- srp->header.masked_status &
- srp->header.host_status &
- srp->header.driver_status;
- if (srp->done)
- rinfo[val].duration =
- srp->header.duration;
- else {
- ms = jiffies_to_msecs(jiffies);
- rinfo[val].duration =
- (ms > srp->header.duration) ?
- (ms - srp->header.duration) : 0;
- }
- rinfo[val].orphan = srp->orphan;
- rinfo[val].sg_io_owned = srp->sg_io_owned;
- rinfo[val].pack_id = srp->header.pack_id;
- rinfo[val].usr_ptr = srp->header.usr_ptr;
- val++;
- }
+ sg_fill_request_table(sfp, rinfo);
read_unlock_irqrestore(&sfp->rq_list_lock, iflags);
result = __copy_to_user(p, rinfo,
SZ_SG_REQ_INFO * SG_MAX_QUEUE);
static int bar_write(struct pci_dev *dev, int offset, u32 value, void *data)
{
struct pci_bar_info *bar = data;
+ unsigned int pos = (offset - PCI_BASE_ADDRESS_0) / 4;
+ const struct resource *res = dev->resource;
+ u32 mask;
if (unlikely(!bar)) {
pr_warn(DRV_NAME ": driver data not found for %s\n",
/* A write to obtain the length must happen as a 32-bit write.
* This does not (yet) support writing individual bytes
*/
- if (value == ~0)
+ if (res[pos].flags & IORESOURCE_IO)
+ mask = ~PCI_BASE_ADDRESS_IO_MASK;
+ else if (pos && (res[pos - 1].flags & IORESOURCE_MEM_64))
+ mask = 0;
+ else
+ mask = ~PCI_BASE_ADDRESS_MEM_MASK;
+ if ((value | mask) == ~0U)
bar->which = 1;
else {
u32 tmpval;
return err;
}
-static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
- grant_ref_t *gnt_refs,
- unsigned int nr_grefs,
- void **vaddr)
-{
- struct xenbus_map_node *node;
- struct vm_struct *area;
- pte_t *ptes[XENBUS_MAX_RING_GRANTS];
- phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
- int err = GNTST_okay;
- int i;
- bool leaked;
-
- *vaddr = NULL;
-
- if (nr_grefs > XENBUS_MAX_RING_GRANTS)
- return -EINVAL;
-
- node = kzalloc(sizeof(*node), GFP_KERNEL);
- if (!node)
- return -ENOMEM;
-
- area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes);
- if (!area) {
- kfree(node);
- return -ENOMEM;
- }
-
- for (i = 0; i < nr_grefs; i++)
- phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr;
-
- err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles,
- phys_addrs,
- GNTMAP_host_map | GNTMAP_contains_pte,
- &leaked);
- if (err)
- goto failed;
-
- node->nr_handles = nr_grefs;
- node->pv.area = area;
-
- spin_lock(&xenbus_valloc_lock);
- list_add(&node->next, &xenbus_valloc_pages);
- spin_unlock(&xenbus_valloc_lock);
-
- *vaddr = area->addr;
- return 0;
-
-failed:
- if (!leaked)
- free_vm_area(area);
- else
- pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs);
-
- kfree(node);
- return err;
-}
-
struct map_ring_valloc_hvm
{
unsigned int idx;
}
EXPORT_SYMBOL_GPL(xenbus_unmap_ring_vfree);
+#ifdef CONFIG_XEN_PV
+static int xenbus_map_ring_valloc_pv(struct xenbus_device *dev,
+ grant_ref_t *gnt_refs,
+ unsigned int nr_grefs,
+ void **vaddr)
+{
+ struct xenbus_map_node *node;
+ struct vm_struct *area;
+ pte_t *ptes[XENBUS_MAX_RING_GRANTS];
+ phys_addr_t phys_addrs[XENBUS_MAX_RING_GRANTS];
+ int err = GNTST_okay;
+ int i;
+ bool leaked;
+
+ *vaddr = NULL;
+
+ if (nr_grefs > XENBUS_MAX_RING_GRANTS)
+ return -EINVAL;
+
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
+ if (!node)
+ return -ENOMEM;
+
+ area = alloc_vm_area(XEN_PAGE_SIZE * nr_grefs, ptes);
+ if (!area) {
+ kfree(node);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < nr_grefs; i++)
+ phys_addrs[i] = arbitrary_virt_to_machine(ptes[i]).maddr;
+
+ err = __xenbus_map_ring(dev, gnt_refs, nr_grefs, node->handles,
+ phys_addrs,
+ GNTMAP_host_map | GNTMAP_contains_pte,
+ &leaked);
+ if (err)
+ goto failed;
+
+ node->nr_handles = nr_grefs;
+ node->pv.area = area;
+
+ spin_lock(&xenbus_valloc_lock);
+ list_add(&node->next, &xenbus_valloc_pages);
+ spin_unlock(&xenbus_valloc_lock);
+
+ *vaddr = area->addr;
+ return 0;
+
+failed:
+ if (!leaked)
+ free_vm_area(area);
+ else
+ pr_alert("leaking VM area %p size %u page(s)", area, nr_grefs);
+
+ kfree(node);
+ return err;
+}
+
static int xenbus_unmap_ring_vfree_pv(struct xenbus_device *dev, void *vaddr)
{
struct xenbus_map_node *node;
return err;
}
+static const struct xenbus_ring_ops ring_ops_pv = {
+ .map = xenbus_map_ring_valloc_pv,
+ .unmap = xenbus_unmap_ring_vfree_pv,
+};
+#endif
+
struct unmap_ring_vfree_hvm
{
unsigned int idx;
}
EXPORT_SYMBOL_GPL(xenbus_read_driver_state);
-static const struct xenbus_ring_ops ring_ops_pv = {
- .map = xenbus_map_ring_valloc_pv,
- .unmap = xenbus_unmap_ring_vfree_pv,
-};
-
static const struct xenbus_ring_ops ring_ops_hvm = {
.map = xenbus_map_ring_valloc_hvm,
.unmap = xenbus_unmap_ring_vfree_hvm,
void __init xenbus_ring_ops_init(void)
{
+#ifdef CONFIG_XEN_PV
if (!xen_feature(XENFEAT_auto_translated_physmap))
ring_ops = &ring_ops_pv;
else
+#endif
ring_ops = &ring_ops_hvm;
}
struct inode *inode;
struct page *page;
unsigned long index;
- int ret;
+ unsigned int mirror = btrfs_io_bio(bio)->mirror_num;
+ int ret = 0;
if (bio->bi_status)
cb->errors = 1;
if (!refcount_dec_and_test(&cb->pending_bios))
goto out;
+ /*
+ * Record the correct mirror_num in cb->orig_bio so that
+ * read-repair can work properly.
+ */
+ ASSERT(btrfs_io_bio(cb->orig_bio));
+ btrfs_io_bio(cb->orig_bio)->mirror_num = mirror;
+ cb->mirror_num = mirror;
+
+ /*
+ * Some IO in this cb have failed, just skip checksum as there
+ * is no way it could be correct.
+ */
+ if (cb->errors == 1)
+ goto csum_failed;
+
inode = cb->inode;
ret = check_compressed_csum(BTRFS_I(inode), cb,
(u64)bio->bi_iter.bi_sector << 9);
#define BTRFS_FS_OPEN 5
#define BTRFS_FS_QUOTA_ENABLED 6
#define BTRFS_FS_QUOTA_ENABLING 7
-#define BTRFS_FS_QUOTA_DISABLING 8
#define BTRFS_FS_UPDATE_UUID_TREE_GEN 9
#define BTRFS_FS_CREATING_FREE_SPACE_TREE 10
#define BTRFS_FS_BTREE_ERR 11
u64 flags;
do_barriers = !btrfs_test_opt(fs_info, NOBARRIER);
- backup_super_roots(fs_info);
+
+ /*
+ * max_mirrors == 0 indicates we're from commit_transaction,
+ * not from fsync where the tree roots in fs_info have not
+ * been consistent on disk.
+ */
+ if (max_mirrors == 0)
+ backup_super_roots(fs_info);
sb = fs_info->super_for_commit;
dev_item = &sb->dev_item;
unsigned int write_flags = 0;
unsigned long nr_written = 0;
- if (wbc->sync_mode == WB_SYNC_ALL)
- write_flags = REQ_SYNC;
+ write_flags = wbc_to_write_flags(wbc);
trace___extent_writepage(page, inode, wbc);
unsigned long i, num_pages;
unsigned long bio_flags = 0;
unsigned long start, end;
- unsigned int write_flags = (epd->sync_io ? REQ_SYNC : 0) | REQ_META;
+ unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
int ret = 0;
clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
if (epd->bio) {
int ret;
- bio_set_op_attrs(epd->bio, REQ_OP_WRITE,
- epd->sync_io ? REQ_SYNC : 0);
-
ret = submit_one_bio(epd->bio, 0, epd->bio_flags);
BUG_ON(ret < 0); /* -ENOMEM */
epd->bio = NULL;
const u64 offset,
const u64 bytes)
{
+ unsigned long index = offset >> PAGE_SHIFT;
+ unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
+ struct page *page;
+
+ while (index <= end_index) {
+ page = find_get_page(inode->i_mapping, index);
+ index++;
+ if (!page)
+ continue;
+ ClearPagePrivate2(page);
+ put_page(page);
+ }
return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
bytes - PAGE_SIZE, false);
}
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
blk_status_t err = bio->bi_status;
- if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
+ if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
err = btrfs_subio_endio_read(inode, io_bio, err);
- if (!err)
- bio->bi_status = 0;
- }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
kfree(dip);
- dio_bio->bi_status = bio->bi_status;
+ dio_bio->bi_status = err;
dio_end_io(dio_bio);
if (io_bio->end_io)
btrfs_work_func_t func;
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
+ u64 last_offset;
int ret;
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
}
again:
+ last_offset = ordered_offset;
ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
&ordered_offset,
ordered_bytes,
btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
btrfs_queue_work(wq, &ordered->work);
out_test:
+ /*
+ * If btrfs_dec_test_ordered_pending does not find any ordered extent
+ * in the range, we can exit.
+ */
+ if (ordered_offset == last_offset)
+ return;
/*
* our bio might span multiple ordered extents. If we haven't
* completed the accounting for the whole dio, go back and try again
}
mutex_unlock(&fs_devices->device_list_mutex);
- fi_args->nodesize = fs_info->super_copy->nodesize;
- fi_args->sectorsize = fs_info->super_copy->sectorsize;
- fi_args->clone_alignment = fs_info->super_copy->sectorsize;
+ fi_args->nodesize = fs_info->nodesize;
+ fi_args->sectorsize = fs_info->sectorsize;
+ fi_args->clone_alignment = fs_info->sectorsize;
if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
ret = -EFAULT;
out:
if (ret)
btrfs_cmp_data_free(cmp);
- return 0;
+ return ret;
}
static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp)
ret = PTR_ERR(new_root);
goto out;
}
+ if (!is_fstree(new_root->objectid)) {
+ ret = -ENOENT;
+ goto out;
+ }
path = btrfs_alloc_path();
if (!path) {
}
ret = 0;
out:
- set_bit(BTRFS_FS_QUOTA_DISABLING, &root->fs_info->flags);
btrfs_free_path(path);
return ret;
}
if (!fs_info->quota_root)
goto out;
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- set_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags);
btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
}
}
ret = del_qgroup_item(trans, quota_root, qgroupid);
+ if (ret && ret != -ENOENT)
+ goto out;
while (!list_empty(&qgroup->groups)) {
list = list_first_entry(&qgroup->groups,
if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags))
set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- if (test_and_clear_bit(BTRFS_FS_QUOTA_DISABLING, &fs_info->flags))
- clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
spin_lock(&fs_info->qgroup_lock);
while (!list_empty(&fs_info->dirty_qgroups)) {
while (!list_empty(list)) {
reloc_root = list_entry(list->next, struct btrfs_root,
root_list);
+ __del_reloc_root(reloc_root);
free_extent_buffer(reloc_root->node);
free_extent_buffer(reloc_root->commit_root);
reloc_root->node = NULL;
reloc_root->commit_root = NULL;
- __del_reloc_root(reloc_root);
}
}
} else {
btrfs_warn(sctx->send_root->fs_info, "unexpected inode type %o",
(int)(mode & S_IFMT));
- ret = -ENOTSUPP;
+ ret = -EOPNOTSUPP;
goto out;
}
struct extent_map *em, *n;
struct list_head extents;
struct extent_map_tree *tree = &inode->extent_tree;
+ u64 logged_start, logged_end;
u64 test_gen;
int ret = 0;
int num = 0;
down_write(&inode->dio_sem);
write_lock(&tree->lock);
test_gen = root->fs_info->last_trans_committed;
+ logged_start = start;
+ logged_end = end;
list_for_each_entry_safe(em, n, &tree->modified_extents, list) {
list_del_init(&em->list);
-
/*
* Just an arbitrary number, this can be really CPU intensive
* once we start getting a lot of extents, and really once we
if (em->generation <= test_gen)
continue;
+
+ if (em->start < logged_start)
+ logged_start = em->start;
+ if ((em->start + em->len - 1) > logged_end)
+ logged_end = em->start + em->len - 1;
+
/* Need a ref to keep it from getting evicted from cache */
refcount_inc(&em->refs);
set_bit(EXTENT_FLAG_LOGGING, &em->flags);
}
list_sort(NULL, &extents, extent_cmp);
- btrfs_get_logged_extents(inode, logged_list, start, end);
+ btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
/*
* Some ordered extents started by fsync might have completed
* before we could collect them into the list logged_list, which
map_length = length;
btrfs_bio_counter_inc_blocked(fs_info);
- ret = __btrfs_map_block(fs_info, bio_op(bio), logical,
+ ret = __btrfs_map_block(fs_info, btrfs_op(bio), logical,
&map_length, &bbio, mirror_num, 1);
if (ret) {
btrfs_bio_counter_dec(fs_info);
#include <linux/sched.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
-#include <linux/utsname.h>
#include <linux/ratelimit.h>
#include "super.h"
void *p;
const char* metadata[][2] = {
- {"hostname", utsname()->nodename},
- {"kernel_version", utsname()->release},
+ {"hostname", mdsc->nodename},
+ {"kernel_version", init_utsname()->release},
{"entity_id", opt->name ? : ""},
{"root", fsopt->server_path ? : "/"},
{NULL, NULL}
init_rwsem(&mdsc->pool_perm_rwsem);
mdsc->pool_perm_tree = RB_ROOT;
+ strncpy(mdsc->nodename, utsname()->nodename,
+ sizeof(mdsc->nodename) - 1);
return 0;
}
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/refcount.h>
+#include <linux/utsname.h>
#include <linux/ceph/types.h>
#include <linux/ceph/messenger.h>
struct rw_semaphore pool_perm_rwsem;
struct rb_root pool_perm_tree;
+
+ char nodename[__NEW_UTS_LEN + 1];
};
extern const char *ceph_mds_op_name(int op);
if ((ses->serverDomain == NULL) ||
(ses->serverOS == NULL) ||
(ses->serverNOS == NULL)) {
- seq_printf(m, "\n%d) entry for %s not fully "
- "displayed\n\t", i, ses->serverName);
+ seq_printf(m, "\n%d) Name: %s Uses: %d Capability: 0x%x\tSession Status: %d\t",
+ i, ses->serverName, ses->ses_count,
+ ses->capabilities, ses->status);
+ if (ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
+ seq_printf(m, "Guest\t");
+ else if (ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+ seq_printf(m, "Anonymous\t");
} else {
seq_printf(m,
"\n%d) Name: %s Domain: %s Uses: %d OS:"
seq_puts(s, ",nocase");
if (tcon->retry)
seq_puts(s, ",hard");
+ else
+ seq_puts(s, ",soft");
if (tcon->use_persistent)
seq_puts(s, ",persistenthandles");
else if (tcon->use_resilient)
exit_cifs_idmap();
#endif
#ifdef CONFIG_CIFS_UPCALL
- unregister_key_type(&cifs_spnego_key_type);
+ exit_cifs_spnego();
#endif
cifs_destroy_request_bufs();
cifs_destroy_mids();
extern const struct export_operations cifs_export_ops;
#endif /* CONFIG_CIFS_NFSD_EXPORT */
-#define CIFS_VERSION "2.09"
+#define CIFS_VERSION "2.10"
#endif /* _CIFSFS_H */
#ifdef CONFIG_CIFS_SMB311
Smb_311,
#endif /* SMB311 */
+ Smb_3any,
+ Smb_default,
Smb_version_err
};
#define SMB21_VERSION_STRING "2.1"
extern struct smb_version_operations smb21_operations;
extern struct smb_version_values smb21_values;
+#define SMBDEFAULT_VERSION_STRING "default"
+extern struct smb_version_values smbdefault_values;
+#define SMB3ANY_VERSION_STRING "3"
+extern struct smb_version_values smb3any_values;
#define SMB30_VERSION_STRING "3.0"
extern struct smb_version_operations smb30_operations;
extern struct smb_version_values smb30_values;
{ Smb_311, SMB311_VERSION_STRING },
{ Smb_311, ALT_SMB311_VERSION_STRING },
#endif /* SMB311 */
+ { Smb_3any, SMB3ANY_VERSION_STRING },
+ { Smb_default, SMBDEFAULT_VERSION_STRING },
{ Smb_version_err, NULL }
};
vol->vals = &smb311_values;
break;
#endif /* SMB311 */
+ case Smb_3any:
+ vol->ops = &smb30_operations; /* currently identical with 3.0 */
+ vol->vals = &smb3any_values;
+ break;
+ case Smb_default:
+ vol->ops = &smb30_operations; /* currently identical with 3.0 */
+ vol->vals = &smbdefault_values;
+ break;
default:
cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value);
return 1;
vol->actimeo = CIFS_DEF_ACTIMEO;
- /* FIXME: add autonegotiation for SMB3 or later rather than just SMB3 */
- vol->ops = &smb30_operations; /* both secure and accepted widely */
- vol->vals = &smb30_values;
+ /* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */
+ vol->ops = &smb30_operations;
+ vol->vals = &smbdefault_values;
vol->echo_interval = SMB_ECHO_INTERVAL_DEFAULT;
if (got_version == false)
pr_warn("No dialect specified on mount. Default has changed to "
- "a more secure dialect, SMB3 (vers=3.0), from CIFS "
+ "a more secure dialect, SMB2.1 or later (e.g. SMB3), from CIFS "
"(SMB1). To use the less secure SMB1 dialect to access "
- "old servers which do not support SMB3 specify vers=1.0"
- " on mount. For somewhat newer servers such as Windows "
- "7 try vers=2.1.\n");
+ "old servers which do not support SMB3 (or SMB2.1) specify vers=1.0"
+ " on mount.\n");
kfree(mountdata_copy);
return 0;
if (vol->nosharesock)
return 0;
+ /* BB update this for smb3any and default case */
if ((server->vals != vol->vals) || (server->ops != vol->ops))
return 0;
cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n",
server->sec_mode, server->capabilities, server->timeAdj);
+ if (ses->auth_key.response) {
+ cifs_dbg(VFS, "Free previous auth_key.response = %p\n",
+ ses->auth_key.response);
+ kfree(ses->auth_key.response);
+ ses->auth_key.response = NULL;
+ ses->auth_key.len = 0;
+ }
+
if (server->ops->sess_setup)
rc = server->ops->sess_setup(xid, ses, nls_info);
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
+ /* O_SYNC also has bit for O_DSYNC so following check picks up either */
+ if (f_flags & O_SYNC)
+ create_options |= CREATE_WRITE_THROUGH;
+
+ if (f_flags & O_DIRECT)
+ create_options |= CREATE_NO_BUFFER;
+
oparms.tcon = tcon;
oparms.cifs_sb = cifs_sb;
oparms.desired_access = desired_access;
struct cifs_tcon *tcon;
unsigned int num, max_num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
- int types[] = {LOCKING_ANDX_LARGE_FILES,
- LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
+ static const int types[] = {
+ LOCKING_ANDX_LARGE_FILES,
+ LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
+ };
int i;
xid = get_xid();
unsigned int xid)
{
int rc = 0, stored_rc;
- int types[] = {LOCKING_ANDX_LARGE_FILES,
- LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
+ static const int types[] = {
+ LOCKING_ANDX_LARGE_FILES,
+ LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES
+ };
unsigned int i;
unsigned int max_num, num, max_buf;
LOCKING_ANDX_RANGE *buf, *cur;
fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
fattr->cf_mtime = cifs_NTtimeToUnix(info->LastModificationTime);
fattr->cf_ctime = cifs_NTtimeToUnix(info->LastStatusChange);
+ /* old POSIX extensions don't get create time */
+
fattr->cf_mode = le64_to_cpu(info->Permissions);
/*
stat->blksize = CIFS_MAX_MSGSIZE;
stat->ino = CIFS_I(inode)->uniqueid;
+ /* old CIFS Unix Extensions doesn't return create time */
+ if (CIFS_I(inode)->createtime) {
+ stat->result_mask |= STATX_BTIME;
+ stat->btime =
+ cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
+ }
+
+ stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
+ if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_COMPRESSED)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (CIFS_I(inode)->cifsAttrs & FILE_ATTRIBUTE_ENCRYPTED)
+ stat->attributes |= STATX_ATTR_ENCRYPTED;
+
/*
* If on a multiuser mount without unix extensions or cifsacl being
* enabled, and the admin hasn't overridden them, set the ownership
return rc;
}
+#ifdef CONFIG_CIFS_XATTR
static ssize_t
move_smb2_ea_to_cifs(char *dst, size_t dst_size,
struct smb2_file_full_ea_info *src, size_t src_size,
return rc;
}
+#endif
static bool
smb2_can_echo(struct TCP_Server_Info *server)
.create_lease_size = sizeof(struct create_lease),
};
+struct smb_version_values smb3any_values = {
+ .version_string = SMB3ANY_VERSION_STRING,
+ .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */
+ .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
+ .large_lock_type = 0,
+ .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
+ .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
+ .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
+ .header_size = sizeof(struct smb2_hdr),
+ .max_header_size = MAX_SMB2_HDR_SIZE,
+ .read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
+ .lock_cmd = SMB2_LOCK,
+ .cap_unix = 0,
+ .cap_nt_find = SMB2_NT_FIND,
+ .cap_large_files = SMB2_LARGE_FILES,
+ .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease_v2),
+};
+
+struct smb_version_values smbdefault_values = {
+ .version_string = SMBDEFAULT_VERSION_STRING,
+ .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */
+ .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
+ .large_lock_type = 0,
+ .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
+ .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
+ .unlock_lock_type = SMB2_LOCKFLAG_UNLOCK,
+ .header_size = sizeof(struct smb2_hdr),
+ .max_header_size = MAX_SMB2_HDR_SIZE,
+ .read_rsp_size = sizeof(struct smb2_read_rsp) - 1,
+ .lock_cmd = SMB2_LOCK,
+ .cap_unix = 0,
+ .cap_nt_find = SMB2_NT_FIND,
+ .cap_large_files = SMB2_LARGE_FILES,
+ .signing_enabled = SMB2_NEGOTIATE_SIGNING_ENABLED | SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
+ .create_lease_size = sizeof(struct create_lease_v2),
+};
+
struct smb_version_values smb30_values = {
.version_string = SMB30_VERSION_STRING,
.protocol_id = SMB30_PROT_ID,
build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt);
req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT);
req->NegotiateContextCount = cpu_to_le16(2);
- inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2
+ inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context)
+ sizeof(struct smb2_encryption_neg_context)); /* calculate hash */
}
#else
req->hdr.sync_hdr.SessionId = 0;
- req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
-
- req->DialectCount = cpu_to_le16(1); /* One vers= at a time for now */
- inc_rfc1001_len(req, 2);
+ if (strcmp(ses->server->vals->version_string,
+ SMB3ANY_VERSION_STRING) == 0) {
+ req->Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+ req->Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+ req->DialectCount = cpu_to_le16(2);
+ inc_rfc1001_len(req, 4);
+ } else if (strcmp(ses->server->vals->version_string,
+ SMBDEFAULT_VERSION_STRING) == 0) {
+ req->Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+ req->Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+ req->Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+ req->DialectCount = cpu_to_le16(3);
+ inc_rfc1001_len(req, 6);
+ } else {
+ /* otherwise send specific dialect */
+ req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
+ req->DialectCount = cpu_to_le16(1);
+ inc_rfc1001_len(req, 2);
+ }
/* only one of SMB2 signing flags may be set in SMB2 request */
if (ses->sign)
*/
if (rc == -EOPNOTSUPP) {
cifs_dbg(VFS, "Dialect not supported by server. Consider "
- "specifying vers=1.0 or vers=2.1 on mount for accessing"
+ "specifying vers=1.0 or vers=2.0 on mount for accessing"
" older servers\n");
goto neg_exit;
} else if (rc != 0)
goto neg_exit;
+ if (strcmp(ses->server->vals->version_string,
+ SMB3ANY_VERSION_STRING) == 0) {
+ if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
+ cifs_dbg(VFS,
+ "SMB2 dialect returned but not requested\n");
+ return -EIO;
+ } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
+ cifs_dbg(VFS,
+ "SMB2.1 dialect returned but not requested\n");
+ return -EIO;
+ }
+ } else if (strcmp(ses->server->vals->version_string,
+ SMBDEFAULT_VERSION_STRING) == 0) {
+ if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID)) {
+ cifs_dbg(VFS,
+ "SMB2 dialect returned but not requested\n");
+ return -EIO;
+ } else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
+ /* ops set to 3.0 by default for default so update */
+ ses->server->ops = &smb21_operations;
+ }
+ } else if (le16_to_cpu(rsp->DialectRevision) !=
+ ses->server->vals->protocol_id) {
+ /* if requested single dialect ensure returned dialect matched */
+ cifs_dbg(VFS, "Illegal 0x%x dialect returned: not requested\n",
+ le16_to_cpu(rsp->DialectRevision));
+ return -EIO;
+ }
+
cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode);
- /* BB we may eventually want to match the negotiated vs. requested
- dialect, even though we are only requesting one at a time */
if (rsp->DialectRevision == cpu_to_le16(SMB20_PROT_ID))
cifs_dbg(FYI, "negotiated smb2.0 dialect\n");
else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID))
}
server->dialect = le16_to_cpu(rsp->DialectRevision);
+ /* BB: add check that dialect was valid given dialect(s) we asked for */
+
/* SMB2 only has an extended negflavor */
server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
/* set it to the maximum buffer size value we can send with 1 credit */
struct validate_negotiate_info_req vneg_inbuf;
struct validate_negotiate_info_rsp *pneg_rsp;
u32 rsplen;
+ u32 inbuflen; /* max of 4 dialects */
cifs_dbg(FYI, "validate negotiate\n");
/*
* validation ioctl must be signed, so no point sending this if we
- * can not sign it. We could eventually change this to selectively
+ * can not sign it (ie are not known user). Even if signing is not
+ * required (enabled but not negotiated), in those cases we selectively
* sign just this, the first and only signed request on a connection.
- * This is good enough for now since a user who wants better security
- * would also enable signing on the mount. Having validation of
- * negotiate info for signed connections helps reduce attack vectors
+ * Having validation of negotiate info helps reduce attack vectors.
*/
- if (tcon->ses->server->sign == false)
+ if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST)
return 0; /* validation requires signing */
+ if (tcon->ses->user_name == NULL) {
+ cifs_dbg(FYI, "Can't validate negotiate: null user mount\n");
+ return 0; /* validation requires signing */
+ }
+
+ if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL)
+ cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n");
+
vneg_inbuf.Capabilities =
cpu_to_le32(tcon->ses->server->vals->req_capabilities);
memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid,
else
vneg_inbuf.SecurityMode = 0;
- vneg_inbuf.DialectCount = cpu_to_le16(1);
- vneg_inbuf.Dialects[0] =
- cpu_to_le16(tcon->ses->server->vals->protocol_id);
+
+ if (strcmp(tcon->ses->server->vals->version_string,
+ SMB3ANY_VERSION_STRING) == 0) {
+ vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID);
+ vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID);
+ vneg_inbuf.DialectCount = cpu_to_le16(2);
+ /* structure is big enough for 3 dialects, sending only 2 */
+ inbuflen = sizeof(struct validate_negotiate_info_req) - 2;
+ } else if (strcmp(tcon->ses->server->vals->version_string,
+ SMBDEFAULT_VERSION_STRING) == 0) {
+ vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID);
+ vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID);
+ vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID);
+ vneg_inbuf.DialectCount = cpu_to_le16(3);
+ /* structure is big enough for 3 dialects */
+ inbuflen = sizeof(struct validate_negotiate_info_req);
+ } else {
+ /* otherwise specific dialect was requested */
+ vneg_inbuf.Dialects[0] =
+ cpu_to_le16(tcon->ses->server->vals->protocol_id);
+ vneg_inbuf.DialectCount = cpu_to_le16(1);
+ /* structure is big enough for 3 dialects, sending only 1 */
+ inbuflen = sizeof(struct validate_negotiate_info_req) - 4;
+ }
rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
while (sess_data->func)
sess_data->func(sess_data);
+ if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign))
+ cifs_dbg(VFS, "signing requested but authenticated as guest\n");
rc = sess_data->result;
out:
kfree(sess_data);
struct cifs_tcon *tcon = oparms->tcon;
struct cifs_ses *ses = tcon->ses;
struct kvec iov[4];
- struct kvec rsp_iov;
+ struct kvec rsp_iov = {NULL, 0};
int resp_buftype;
int uni_path_len;
__le16 *copy_path = NULL;
if (rc != 0) {
cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
- if (err_buf)
+ if (err_buf && rsp)
*err_buf = kmemdup(rsp, get_rfc1002_length(rsp) + 4,
GFP_KERNEL);
goto creat_exit;
__u8 Guid[SMB2_CLIENT_GUID_SIZE];
__le16 SecurityMode;
__le16 DialectCount;
- __le16 Dialects[1]; /* dialect (someday maybe list) client asked for */
+ __le16 Dialects[3]; /* BB expand this if autonegotiate > 3 dialects */
} __packed;
struct validate_negotiate_info_rsp {
{
loff_t offset = dio->iocb->ki_pos;
ssize_t transferred = 0;
+ int err;
/*
* AIO submission can race with bio completion to get here while
if (ret == 0)
ret = transferred;
+ /*
+ * Try again to invalidate clean pages which might have been cached by
+ * non-direct readahead, or faulted in by get_user_pages() if the source
+ * of the write was an mmap'ed region of the file we're writing. Either
+ * one is a pretty crazy thing to do, so we don't support it 100%. If
+ * this invalidation fails, tough, the write still worked...
+ */
+ if (ret > 0 && dio->op == REQ_OP_WRITE &&
+ dio->inode->i_mapping->nrpages) {
+ err = invalidate_inode_pages2_range(dio->inode->i_mapping,
+ offset >> PAGE_SHIFT,
+ (offset + ret - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(err);
+ }
+
if (dio->end_io) {
- int err;
// XXX: ki_pos??
err = dio->end_io(dio->iocb, offset, ret, dio->private);
struct dio *dio = bio->bi_private;
unsigned long remaining;
unsigned long flags;
+ bool defer_completion = false;
/* cleanup the bio */
dio_bio_complete(dio, bio);
spin_unlock_irqrestore(&dio->bio_lock, flags);
if (remaining == 0) {
- if (dio->result && dio->defer_completion) {
+ /*
+ * Defer completion when defer_completion is set or
+ * when the inode has pages mapped and this is AIO write.
+ * We need to invalidate those pages because there is a
+ * chance they contain stale data in the case buffered IO
+ * went in between AIO submission and completion into the
+ * same region.
+ */
+ if (dio->result)
+ defer_completion = dio->defer_completion ||
+ (dio->op == REQ_OP_WRITE &&
+ dio->inode->i_mapping->nrpages);
+ if (defer_completion) {
INIT_WORK(&dio->complete_work, dio_aio_complete_work);
queue_work(dio->inode->i_sb->s_dio_done_wq,
&dio->complete_work);
* For AIO O_(D)SYNC writes we need to defer completions to a workqueue
* so that we can call ->fsync.
*/
- if (dio->is_async && iov_iter_rw(iter) == WRITE &&
- ((iocb->ki_filp->f_flags & O_DSYNC) ||
- IS_SYNC(iocb->ki_filp->f_mapping->host))) {
- retval = dio_set_defer_completion(dio);
+ if (dio->is_async && iov_iter_rw(iter) == WRITE) {
+ retval = 0;
+ if ((iocb->ki_filp->f_flags & O_DSYNC) ||
+ IS_SYNC(iocb->ki_filp->f_mapping->host))
+ retval = dio_set_defer_completion(dio);
+ else if (!dio->inode->i_sb->s_dio_done_wq) {
+ /*
+ * In case of AIO write racing with buffered read we
+ * need to defer completion. We can't decide this now,
+ * however the workqueue needs to be initialized here.
+ */
+ retval = sb_init_dio_done_wq(dio->inode->i_sb);
+ }
if (retval) {
/*
* We grab i_mutex only for reads so we don't have
* specific si_codes. In that case use SI_SIGIO instead
* to remove the ambiguity.
*/
- if (sig_specific_sicodes(signum))
+ if ((signum != SIGPOLL) && sig_specific_sicodes(signum))
si.si_code = SI_SIGIO;
/* Make sure we are called with one of the POLL_*
{
struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;
- int ret;
-
- if (gi->last_pos <= *pos)
- n = (*pos - gi->last_pos);
- ret = rhashtable_walk_start(&gi->hti);
- if (ret)
+ rhashtable_walk_enter(&gl_hash_table, &gi->hti);
+ if (rhashtable_walk_start(&gi->hti) != 0)
return NULL;
do {
} while (gi->gl && n--);
gi->last_pos = *pos;
+
return gi->gl;
}
(*pos)++;
gi->last_pos = *pos;
gfs2_glock_iter_next(gi);
+
return gi->gl;
}
gi->gl = NULL;
rhashtable_walk_stop(&gi->hti);
+ rhashtable_walk_exit(&gi->hti);
}
static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
struct gfs2_glock_iter *gi = seq->private;
gi->sdp = inode->i_private;
- gi->last_pos = 0;
seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
if (seq->buf)
seq->size = GFS2_SEQ_GOODSIZE;
gi->gl = NULL;
- rhashtable_walk_enter(&gl_hash_table, &gi->hti);
}
return ret;
}
struct gfs2_glock_iter *gi = seq->private;
gi->gl = NULL;
- rhashtable_walk_exit(&gi->hti);
return seq_release_private(inode, file);
}
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
+ struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
+ /*
+ * Try again to invalidate clean pages which might have been cached by
+ * non-direct readahead, or faulted in by get_user_pages() if the source
+ * of the write was an mmap'ed region of the file we're writing. Either
+ * one is a pretty crazy thing to do, so we don't support it 100%. If
+ * this invalidation fails, tough, the write still worked...
+ */
+ if (!dio->error &&
+ (dio->flags & IOMAP_DIO_WRITE) && inode->i_mapping->nrpages) {
+ ret = invalidate_inode_pages2_range(inode->i_mapping,
+ iocb->ki_pos >> PAGE_SHIFT,
+ (iocb->ki_pos + dio->size - 1) >> PAGE_SHIFT);
+ WARN_ON_ONCE(ret);
+ }
+
if (dio->end_io) {
ret = dio->end_io(iocb,
dio->error ? dio->error : dio->size,
WARN_ON_ONCE(ret);
ret = 0;
+ if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+ !inode->i_sb->s_dio_done_wq) {
+ ret = sb_init_dio_done_wq(inode->i_sb);
+ if (ret < 0)
+ goto out_free_dio;
+ }
+
inode_dio_begin(inode);
blk_start_plug(&plug);
if (ret < 0)
iomap_dio_set_error(dio, ret);
- if (ret >= 0 && iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
- !inode->i_sb->s_dio_done_wq) {
- ret = sb_init_dio_done_wq(inode->i_sb);
- if (ret < 0)
- iomap_dio_set_error(dio, ret);
- }
-
if (!atomic_dec_and_test(&dio->ref)) {
if (!is_sync_kiocb(iocb))
return -EIOCBQUEUED;
ret = iomap_dio_complete(dio);
- /*
- * Try again to invalidate clean pages which might have been cached by
- * non-direct readahead, or faulted in by get_user_pages() if the source
- * of the write was an mmap'ed region of the file we're writing. Either
- * one is a pretty crazy thing to do, so we don't support it 100%. If
- * this invalidation fails, tough, the write still worked...
- */
- if (iov_iter_rw(iter) == WRITE) {
- int err = invalidate_inode_pages2_range(mapping,
- start >> PAGE_SHIFT, end >> PAGE_SHIFT);
- WARN_ON_ONCE(err);
- }
-
return ret;
out_free_dio:
if (sbi->s_fmode != ISOFS_INVALID_MODE)
seq_printf(m, ",fmode=%o", sbi->s_fmode);
+#ifdef CONFIG_JOLIET
if (sbi->s_nls_iocharset &&
strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0)
seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset);
+#endif
return 0;
}
#include <linux/mman.h>
#include <linux/sched/mm.h>
#include <linux/sched/numa_balancing.h>
+#include <linux/sched/task_stack.h>
#include <linux/sched/task.h>
#include <linux/sched/cputime.h>
#include <linux/proc_fs.h>
* simple bit tests.
*/
static const char * const task_state_array[] = {
- "R (running)", /* 0 */
- "S (sleeping)", /* 1 */
- "D (disk sleep)", /* 2 */
- "T (stopped)", /* 4 */
- "t (tracing stop)", /* 8 */
- "X (dead)", /* 16 */
- "Z (zombie)", /* 32 */
+
+ /* states in TASK_REPORT: */
+ "R (running)", /* 0x00 */
+ "S (sleeping)", /* 0x01 */
+ "D (disk sleep)", /* 0x02 */
+ "T (stopped)", /* 0x04 */
+ "t (tracing stop)", /* 0x08 */
+ "X (dead)", /* 0x10 */
+ "Z (zombie)", /* 0x20 */
+ "P (parked)", /* 0x40 */
+
+ /* states beyond TASK_REPORT: */
+ "I (idle)", /* 0x80 */
};
static inline const char *get_task_state(struct task_struct *tsk)
{
- unsigned int state = (tsk->state | tsk->exit_state) & TASK_REPORT;
-
- /*
- * Parked tasks do not run; they sit in __kthread_parkme().
- * Without this check, we would report them as running, which is
- * clearly wrong, so we report them as sleeping instead.
- */
- if (tsk->state == TASK_PARKED)
- state = TASK_INTERRUPTIBLE;
-
- BUILD_BUG_ON(1 + ilog2(TASK_REPORT) != ARRAY_SIZE(task_state_array)-1);
-
- return task_state_array[fls(state)];
+ BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != ARRAY_SIZE(task_state_array));
+ return task_state_array[__get_task_state(tsk)];
}
static inline int get_task_umask(struct task_struct *tsk)
* esp and eip are intentionally zeroed out. There is no
* non-racy way to read them without freezing the task.
* Programs that need reliable values can use ptrace(2).
+ *
+ * The only exception is if the task is core dumping because
+ * a program is not able to use ptrace(2) in that case. It is
+ * safe because the task has stopped executing permanently.
*/
+ if (permitted && (task->flags & PF_DUMPCORE)) {
+ eip = KSTK_EIP(task);
+ esp = KSTK_ESP(task);
+ }
}
get_task_comm(tcomm, task);
ret = dquot_add_space(transfer_to[cnt], cur_space, rsv_space, 0,
&warn_to[cnt]);
if (ret) {
+ spin_lock(&transfer_to[cnt]->dq_dqb_lock);
dquot_decr_inodes(transfer_to[cnt], inode_usage);
+ spin_unlock(&transfer_to[cnt]->dq_dqb_lock);
goto over_quota;
}
}
if (!dquot->dq_off) {
alloc = true;
down_write(&dqopt->dqio_sem);
+ } else {
+ down_read(&dqopt->dqio_sem);
}
ret = qtree_write_dquot(
sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv,
dquot);
if (alloc)
up_write(&dqopt->dqio_sem);
+ else
+ up_read(&dqopt->dqio_sem);
return ret;
}
* In the generic case the entire file is data, so as long as
* offset isn't at the end of the file then the offset is data.
*/
- if (offset >= eof)
+ if ((unsigned long long)offset >= eof)
return -ENXIO;
break;
case SEEK_HOLE:
* There is a virtual hole at the end of the file, so as long as
* offset isn't i_size or larger, return i_size.
*/
- if (offset >= eof)
+ if ((unsigned long long)offset >= eof)
return -ENXIO;
offset = eof;
break;
trace_xfs_ag_resv_free(pag, type, 0);
resv = xfs_perag_resv(pag, type);
- pag->pag_mount->m_ag_max_usable += resv->ar_asked;
+ if (pag->pag_agno == 0)
+ pag->pag_mount->m_ag_max_usable += resv->ar_asked;
/*
* AGFL blocks are always considered "free", so whatever
* was reserved at mount time must be given back at umount.
return error;
}
- mp->m_ag_max_usable -= ask;
+ /*
+ * Reduce the maximum per-AG allocation length by however much we're
+ * trying to reserve for an AG. Since this is a filesystem-wide
+ * counter, we only make the adjustment for AG 0. This assumes that
+ * there aren't any AGs hungrier for per-AG reservation than AG 0.
+ */
+ if (pag->pag_agno == 0)
+ mp->m_ag_max_usable -= ask;
resv = xfs_perag_resv(pag, type);
resv->ar_asked = ask;
#include "xfs_rmap.h"
#include "xfs_ag_resv.h"
#include "xfs_refcount.h"
-#include "xfs_rmap_btree.h"
#include "xfs_icache.h"
int maxrecs; /* maximum record count at this level */
xfs_mount_t *mp; /* mount structure */
xfs_filblks_t rval; /* return value */
- xfs_filblks_t orig_len;
mp = ip->i_mount;
-
- /* Calculate the worst-case size of the bmbt. */
- orig_len = len;
maxrecs = mp->m_bmap_dmxr[0];
for (level = 0, rval = 0;
level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
len += maxrecs - 1;
do_div(len, maxrecs);
rval += len;
- if (len == 1) {
- rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
+ if (len == 1)
+ return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
level - 1;
- break;
- }
if (level == 0)
maxrecs = mp->m_bmap_dmxr[1];
}
-
- /* Calculate the worst-case size of the rmapbt. */
- if (xfs_sb_version_hasrmapbt(&mp->m_sb))
- rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) +
- mp->m_rmap_maxlevels;
-
return rval;
}
error = xfs_reflink_end_cow(ip, offset, size);
break;
case XFS_IO_UNWRITTEN:
- error = xfs_iomap_write_unwritten(ip, offset, size);
+ /* writeback should never update isize */
+ error = xfs_iomap_write_unwritten(ip, offset, size, false);
break;
default:
ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
return error;
/*
- * The extent shiting code works on extent granularity. So, if
+ * Clean out anything hanging around in the cow fork now that
+ * we've flushed all the dirty data out to disk to avoid having
+ * CoW extents at the wrong offsets.
+ */
+ if (xfs_is_reflink_inode(ip)) {
+ error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
+ true);
+ if (error)
+ return error;
+ }
+
+ /*
+ * The extent shifting code works on extent granularity. So, if
* stop_fsb is not the starting block of extent, we need to split
* the extent at stop_fsb.
*/
int size;
int offset;
- total_nr_pages = bp->b_page_count;
-
/* skip the pages in the buffer before the start offset */
page_index = 0;
offset = *buf_offset;
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
+ xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx",
bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
__return_address, bp->b_ops->name, bp->b_bn);
xfs_off_t count,
bool *did_zero)
{
- return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
+ return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
}
int
*/
spin_lock(&ip->i_flags_lock);
if (iocb->ki_pos > i_size_read(inode)) {
- bool zero = false;
-
spin_unlock(&ip->i_flags_lock);
if (!drained_dio) {
if (*iolock == XFS_IOLOCK_SHARED) {
drained_dio = true;
goto restart;
}
- error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), &zero);
+ error = xfs_zero_eof(ip, iocb->ki_pos, i_size_read(inode), NULL);
if (error)
return error;
} else
struct inode *inode = file_inode(iocb->ki_filp);
struct xfs_inode *ip = XFS_I(inode);
loff_t offset = iocb->ki_pos;
- bool update_size = false;
int error = 0;
trace_xfs_end_io_direct_write(ip, offset, size);
if (size <= 0)
return size;
+ if (flags & IOMAP_DIO_COW) {
+ error = xfs_reflink_end_cow(ip, offset, size);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Unwritten conversion updates the in-core isize after extent
+ * conversion but before updating the on-disk size. Updating isize any
+ * earlier allows a racing dio read to find unwritten extents before
+ * they are converted.
+ */
+ if (flags & IOMAP_DIO_UNWRITTEN)
+ return xfs_iomap_write_unwritten(ip, offset, size, true);
+
/*
* We need to update the in-core inode size here so that we don't end up
* with the on-disk inode size being outside the in-core inode size. We
spin_lock(&ip->i_flags_lock);
if (offset + size > i_size_read(inode)) {
i_size_write(inode, offset + size);
- update_size = true;
- }
- spin_unlock(&ip->i_flags_lock);
-
- if (flags & IOMAP_DIO_COW) {
- error = xfs_reflink_end_cow(ip, offset, size);
- if (error)
- return error;
- }
-
- if (flags & IOMAP_DIO_UNWRITTEN)
- error = xfs_iomap_write_unwritten(ip, offset, size);
- else if (update_size)
+ spin_unlock(&ip->i_flags_lock);
error = xfs_setfilesize(ip, offset, size);
+ } else {
+ spin_unlock(&ip->i_flags_lock);
+ }
return error;
}
goto out;
/*
- * Clear the reflink flag if we truncated everything.
+ * Clear the reflink flag if there are no data fork blocks and
+ * there are no extents staged in the cow fork.
*/
- if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) {
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+ if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) {
+ if (ip->i_d.di_nblocks == 0)
+ ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
}
*/
iip = INODE_ITEM(blip);
if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
- lip->li_flags & XFS_LI_FAILED)
+ (blip->li_flags & XFS_LI_FAILED))
need_ail++;
blip = next;
int *join_flags)
{
struct inode *inode = VFS_I(ip);
+ struct super_block *sb = inode->i_sb;
int error;
*join_flags = 0;
if (fa->fsx_xflags & FS_XFLAG_DAX) {
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
return -EINVAL;
- if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+ if (bdev_dax_supported(sb, sb->s_blocksize) < 0)
return -EINVAL;
}
xfs_iomap_write_unwritten(
xfs_inode_t *ip,
xfs_off_t offset,
- xfs_off_t count)
+ xfs_off_t count,
+ bool update_isize)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb;
xfs_trans_t *tp;
xfs_bmbt_irec_t imap;
struct xfs_defer_ops dfops;
+ struct inode *inode = VFS_I(ip);
xfs_fsize_t i_size;
uint resblks;
int error;
i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
if (i_size > offset + count)
i_size = offset + count;
-
+ if (update_isize && i_size > i_size_read(inode))
+ i_size_write(inode, i_size);
i_size = xfs_new_eof(ip, i_size);
if (i_size) {
ip->i_d.di_size = i_size;
struct xfs_bmbt_irec *, int);
int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
struct xfs_bmbt_irec *);
(end - 1) >> PAGE_SHIFT);
WARN_ON_ONCE(error);
- error = xfs_iomap_write_unwritten(ip, start, length);
+ error = xfs_iomap_write_unwritten(ip, start, length, false);
if (error)
goto out_drop_iolock;
}
"DAX and reflink have not been tested together!");
}
+ if (mp->m_flags & XFS_MOUNT_DISCARD) {
+ struct request_queue *q = bdev_get_queue(sb->s_bdev);
+
+ if (!blk_queue_discard(q)) {
+ xfs_warn(mp, "mounting with \"discard\" option, but "
+ "the device does not support discard");
+ mp->m_flags &= ~XFS_MOUNT_DISCARD;
+ }
+ }
+
if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
if (mp->m_sb.sb_rblocks) {
xfs_alert(mp,
extern const struct fwnode_operations acpi_data_fwnode_ops;
extern const struct fwnode_operations acpi_static_fwnode_ops;
+bool is_acpi_device_node(const struct fwnode_handle *fwnode);
+bool is_acpi_data_node(const struct fwnode_handle *fwnode);
+
static inline bool is_acpi_node(const struct fwnode_handle *fwnode)
{
- return !IS_ERR_OR_NULL(fwnode) &&
- (fwnode->ops == &acpi_device_fwnode_ops
- || fwnode->ops == &acpi_data_fwnode_ops);
-}
-
-static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode)
-{
- return !IS_ERR_OR_NULL(fwnode) &&
- fwnode->ops == &acpi_device_fwnode_ops;
+ return (is_acpi_device_node(fwnode) || is_acpi_data_node(fwnode));
}
#define to_acpi_device_node(__fwnode) \
NULL; \
})
-static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode)
-{
- return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops;
-}
-
#define to_acpi_data_node(__fwnode) \
({ \
typeof(__fwnode) __to_acpi_data_node_fwnode = __fwnode; \
static inline void audit_seccomp(unsigned long syscall, long signr, int code)
{
- if (!audit_enabled)
- return;
-
- /* Force a record to be reported if a signal was delivered. */
- if (signr || unlikely(!audit_dummy_context()))
+ if (audit_enabled && unlikely(!audit_dummy_context()))
__audit_seccomp(syscall, signr, code);
}
int node;
#ifdef CONFIG_BLK_DEV_IO_TRACE
struct blk_trace *blk_trace;
+ struct mutex blk_trace_mutex;
#endif
/*
* for flush operations
#include <linux/types.h>
+/*
+ * CPU-up CPU-down
+ *
+ * BP AP BP AP
+ *
+ * OFFLINE OFFLINE
+ * | ^
+ * v |
+ * BRINGUP_CPU->AP_OFFLINE BRINGUP_CPU <- AP_IDLE_DEAD (idle thread/play_dead)
+ * | AP_OFFLINE
+ * v (IRQ-off) ,---------------^
+ * AP_ONLNE | (stop_machine)
+ * | TEARDOWN_CPU <- AP_ONLINE_IDLE
+ * | ^
+ * v |
+ * AP_ACTIVE AP_ACTIVE
+ */
+
enum cpuhp_state {
- CPUHP_OFFLINE,
+ CPUHP_INVALID = -1,
+ CPUHP_OFFLINE = 0,
CPUHP_CREATE_THREADS,
CPUHP_PERF_PREPARE,
CPUHP_PERF_X86_PREPARE,
* @driver_data: Private pointer for driver specific info.
* @links: Links to suppliers and consumers of this device.
* @power: For device power management.
- * See Documentation/power/admin-guide/devices.rst for details.
+ * See Documentation/driver-api/pm/devices.rst for details.
* @pm_domain: Provide callbacks that are executed during system suspend,
* hibernation, system resume and during runtime PM transitions
* along with subsystem-level and driver-level callbacks.
int input_ff_upload(struct input_dev *dev, struct ff_effect *effect, struct file *file);
int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
+int input_ff_flush(struct input_dev *dev, struct file *file);
int input_ff_create_memless(struct input_dev *dev, void *data,
int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
* @map: map a physically contiguous memory region to an iommu domain
* @unmap: unmap a physically contiguous memory region from an iommu domain
* @map_sg: map a scatter-gather list of physically contiguous memory chunks
+ * to an iommu domain
* @flush_tlb_all: Synchronously flush all hardware TLBs for this domain
* @tlb_range_add: Add a given iova range to the flush queue for this domain
* @tlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
* queue
- * to an iommu domain
* @iova_to_phys: translate iova to physical address
* @add_device: add device to iommu grouping
* @remove_device: remove device from iommu grouping
static inline
struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
{
- if (!cpumask_empty(d->common->effective_affinity))
- return d->common->effective_affinity;
-
- return d->common->affinity;
+ return d->common->effective_affinity;
}
static inline void irq_data_update_effective_affinity(struct irq_data *d,
const struct cpumask *m)
#define KEY_FLAG_BUILTIN 8 /* set if key is built in to the kernel */
#define KEY_FLAG_ROOT_CAN_INVAL 9 /* set if key can be invalidated by root without permission */
#define KEY_FLAG_KEEP 10 /* set if key should not be removed */
+#define KEY_FLAG_UID_KEYRING 11 /* set if key is a user or user session keyring */
/* the key type and key description string
* - the desc is used to match a key against search criteria
#define KEY_ALLOC_NOT_IN_QUOTA 0x0002 /* not in quota */
#define KEY_ALLOC_BUILT_IN 0x0004 /* Key is built into kernel */
#define KEY_ALLOC_BYPASS_RESTRICTION 0x0008 /* Override the check on restricted keyrings */
+#define KEY_ALLOC_UID_KEYRING 0x0010 /* allocating a user or user session keyring */
extern void key_revoke(struct key *key);
extern void key_invalidate(struct key *key);
* indicating an FC transport Aborted status.
* Entrypoint is Mandatory.
*
- * @defer_rcv: Called by the transport to signal the LLLD that it has
- * begun processing of a previously received NVME CMD IU. The LLDD
- * is now free to re-use the rcv buffer associated with the
- * nvmefc_tgt_fcp_req.
- *
* @max_hw_queues: indicates the maximum number of hw queues the LLDD
* supports for cpu affinitization.
* Value is Mandatory. Must be at least 1.
* outstanding operation (if there was one) to complete, then will
* call the fcp_req_release() callback to return the command's
* exchange context back to the LLDD.
+ * Entrypoint is Mandatory.
*
* @fcp_req_release: Called by the transport to return a nvmefc_tgt_fcp_req
* to the LLDD after all operations on the fcp operation are complete.
* This may be due to the command completing or upon completion of
* abort cleanup.
+ * Entrypoint is Mandatory.
+ *
+ * @defer_rcv: Called by the transport to signal the LLLD that it has
+ * begun processing of a previously received NVME CMD IU. The LLDD
+ * is now free to re-use the rcv buffer associated with the
+ * nvmefc_tgt_fcp_req.
+ * Entrypoint is Optional.
*
* @max_hw_queues: indicates the maximum number of hw queues the LLDD
* supports for cpu affinitization.
*
* @NVME_SGL_FMT_ADDRESS: absolute address of the data block
* @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block
+ * @NVME_SGL_FMT_TRANSPORT_A: transport defined format, value 0xA
* @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation
* request subtype
*/
enum {
NVME_SGL_FMT_ADDRESS = 0x00,
NVME_SGL_FMT_OFFSET = 0x01,
+ NVME_SGL_FMT_TRANSPORT_A = 0x0A,
NVME_SGL_FMT_INVALIDATE = 0x0f,
};
*
* For struct nvme_keyed_sgl_desc:
* @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor
+ *
+ * Transport-specific SGL types:
+ * @NVME_TRANSPORT_SGL_DATA_DESC: Transport SGL data dlock descriptor
*/
enum {
NVME_SGL_FMT_DATA_DESC = 0x00,
NVME_SGL_FMT_SEG_DESC = 0x02,
NVME_SGL_FMT_LAST_SEG_DESC = 0x03,
NVME_KEY_SGL_FMT_DATA_DESC = 0x04,
+ NVME_TRANSPORT_SGL_DATA_DESC = 0x05,
};
struct nvme_sgl_desc {
NVME_SC_UNWRITTEN_BLOCK = 0x287,
NVME_SC_DNR = 0x4000,
-
-
- /*
- * FC Transport-specific error status values for NVME commands
- *
- * Transport-specific status code values must be in the range 0xB0..0xBF
- */
-
- /* Generic FC failure - catchall */
- NVME_SC_FC_TRANSPORT_ERROR = 0x00B0,
-
- /* I/O failure due to FC ABTS'd */
- NVME_SC_FC_TRANSPORT_ABORTED = 0x00B1,
};
struct nvme_completion {
extern struct platform_device *of_device_alloc(struct device_node *np,
const char *bus_id,
struct device *parent);
+#ifdef CONFIG_OF
extern struct platform_device *of_find_device_by_node(struct device_node *np);
+#else
+static inline struct platform_device *of_find_device_by_node(struct device_node *np)
+{
+ return NULL;
+}
+#endif
/* Platform devices and busses creation */
extern struct platform_device *of_platform_device_create(struct device_node *np,
#define dev_is_pci(d) (false)
#define dev_is_pf(d) (false)
+static inline bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags)
+{ return false; }
#endif /* CONFIG_PCI */
/* Include architecture-dependent settings and functions */
*/
/* Used in tsk->state: */
-#define TASK_RUNNING 0
-#define TASK_INTERRUPTIBLE 1
-#define TASK_UNINTERRUPTIBLE 2
-#define __TASK_STOPPED 4
-#define __TASK_TRACED 8
+#define TASK_RUNNING 0x0000
+#define TASK_INTERRUPTIBLE 0x0001
+#define TASK_UNINTERRUPTIBLE 0x0002
+#define __TASK_STOPPED 0x0004
+#define __TASK_TRACED 0x0008
/* Used in tsk->exit_state: */
-#define EXIT_DEAD 16
-#define EXIT_ZOMBIE 32
+#define EXIT_DEAD 0x0010
+#define EXIT_ZOMBIE 0x0020
#define EXIT_TRACE (EXIT_ZOMBIE | EXIT_DEAD)
/* Used in tsk->state again: */
-#define TASK_DEAD 64
-#define TASK_WAKEKILL 128
-#define TASK_WAKING 256
-#define TASK_PARKED 512
-#define TASK_NOLOAD 1024
-#define TASK_NEW 2048
-#define TASK_STATE_MAX 4096
-
-#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWPNn"
+#define TASK_PARKED 0x0040
+#define TASK_DEAD 0x0080
+#define TASK_WAKEKILL 0x0100
+#define TASK_WAKING 0x0200
+#define TASK_NOLOAD 0x0400
+#define TASK_NEW 0x0800
+#define TASK_STATE_MAX 0x1000
/* Convenience macros for the sake of set_current_state: */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
/* get_task_state(): */
#define TASK_REPORT (TASK_RUNNING | TASK_INTERRUPTIBLE | \
TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
- __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
+ __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
+ TASK_PARKED)
#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0)
return task_pgrp_nr_ns(tsk, &init_pid_ns);
}
-static inline char task_state_to_char(struct task_struct *task)
+#define TASK_REPORT_IDLE (TASK_REPORT + 1)
+#define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
+
+static inline unsigned int __get_task_state(struct task_struct *tsk)
+{
+ unsigned int tsk_state = READ_ONCE(tsk->state);
+ unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
+
+ BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
+
+ if (tsk_state == TASK_IDLE)
+ state = TASK_REPORT_IDLE;
+
+ return fls(state);
+}
+
+static inline char __task_state_to_char(unsigned int state)
{
- const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
- unsigned long state = task->state;
+ static const char state_char[] = "RSDTtXZPI";
- state = state ? __ffs(state) + 1 : 0;
+ BUILD_BUG_ON(1 + ilog2(TASK_REPORT_MAX) != sizeof(state_char) - 1);
- /* Make sure the string lines up properly with the number of task states: */
- BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1);
+ return state_char[state];
+}
- return state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?';
+static inline char task_state_to_char(struct task_struct *tsk)
+{
+ return __task_state_to_char(__get_task_state(tsk));
}
/**
#include <uapi/linux/seccomp.h>
-#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC)
+#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \
+ SECCOMP_FILTER_FLAG_LOG)
#ifdef CONFIG_SECCOMP
} \
static inline long SYSC##name(__MAP(x,__SC_DECL,__VA_ARGS__))
-#ifdef TIF_FSCHECK
/*
* Called before coming back to user-mode. Returning to user-mode with an
* address limit different than USER_DS can allow to overwrite kernel memory.
*/
static inline void addr_limit_user_check(void)
{
-
+#ifdef TIF_FSCHECK
if (!test_thread_flag(TIF_FSCHECK))
return;
+#endif
- BUG_ON(!segment_eq(get_fs(), USER_DS));
+ if (CHECK_DATA_CORRUPTION(!segment_eq(get_fs(), USER_DS),
+ "Invalid address limit on user-mode return"))
+ force_sig(SIGKILL, current);
+
+#ifdef TIF_FSCHECK
clear_thread_flag(TIF_FSCHECK);
-}
#endif
+}
asmlinkage long sys32_quotactl(unsigned int cmd, const char __user *special,
qid_t id, void __user *addr);
#define setup_pinned_deferrable_timer_on_stack(timer, fn, data) \
__setup_timer_on_stack((timer), (fn), (data), TIMER_DEFERRABLE | TIMER_PINNED)
+#define TIMER_DATA_TYPE unsigned long
+#define TIMER_FUNC_TYPE void (*)(TIMER_DATA_TYPE)
+
+static inline void timer_setup(struct timer_list *timer,
+ void (*callback)(struct timer_list *),
+ unsigned int flags)
+{
+ __setup_timer(timer, (TIMER_FUNC_TYPE)callback,
+ (TIMER_DATA_TYPE)timer, flags);
+}
+
+#define from_timer(var, callback_timer, timer_fieldname) \
+ container_of(callback_timer, typeof(*var), timer_fieldname)
+
/**
* timer_pending - is a timer pending?
* @timer: the timer in question
int perf_refcount;
struct hlist_head __percpu *perf_events;
struct bpf_prog *prog;
+ struct perf_event *bpf_prog_owner;
int (*perf_perm)(struct trace_event_call *,
struct perf_event *);
static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
if (dst)
- atomic_inc(&dst->__refcnt);
+ dst_hold(dst);
return dst;
}
__skb_dst_copy(nskb, oskb->_skb_refdst);
}
-/**
- * skb_dst_force - makes sure skb dst is refcounted
- * @skb: buffer
- *
- * If dst is not yet refcounted, let's do it
- */
-static inline void skb_dst_force(struct sk_buff *skb)
-{
- if (skb_dst_is_noref(skb)) {
- WARN_ON(!rcu_read_lock_held());
- skb->_skb_refdst &= ~SKB_DST_NOREF;
- dst_clone(skb_dst(skb));
- }
-}
-
/**
* dst_hold_safe - Take a reference on a dst if possible
* @dst: pointer to dst entry
}
/**
- * skb_dst_force_safe - makes sure skb dst is refcounted
+ * skb_dst_force - makes sure skb dst is refcounted
* @skb: buffer
*
* If dst is not yet refcounted and not destroyed, grab a ref on it.
*/
-static inline void skb_dst_force_safe(struct sk_buff *skb)
+static inline void skb_dst_force(struct sk_buff *skb)
{
if (skb_dst_is_noref(skb)) {
struct dst_entry *dst = skb_dst(skb);
+ WARN_ON(!rcu_read_lock_held());
if (!dst_hold_safe(dst))
dst = NULL;
rcu_read_lock();
err = ip_route_input_noref(skb, dst, src, tos, devin);
if (!err) {
- skb_dst_force_safe(skb);
+ skb_dst_force(skb);
if (!skb_dst(skb))
err = -EINVAL;
}
static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
/* dont let skb dst not refcounted, we are going to leave rcu lock */
- skb_dst_force_safe(skb);
+ skb_dst_force(skb);
if (!sk->sk_backlog.tail)
sk->sk_backlog.head = skb;
int min_tso_segs);
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
int nonagle);
-bool tcp_may_send_now(struct sock *sk);
int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs);
void tcp_retransmit_timer(struct sock *sk);
IB_TM_CAP_RC = 1 << 0,
};
-struct ib_xrq_caps {
+struct ib_tm_caps {
/* Max size of RNDV header */
u32 max_rndv_hdr_size;
/* Max number of entries in tag matching list */
struct ib_rss_caps rss_caps;
u32 max_wq_type_rq;
u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */
- struct ib_xrq_caps xrq_caps;
+ struct ib_tm_caps tm_caps;
};
enum ib_mtu {
u32 lkey;
u32 rkey;
u64 iova;
- u32 length;
+ u64 length;
unsigned int page_size;
bool need_inval;
union {
* Preemption ignores task state, therefore preempted tasks are always
* RUNNING (we will not have dequeued if state != RUNNING).
*/
- return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
+ if (preempt)
+ return TASK_STATE_MAX;
+
+ return __get_task_state(p);
}
#endif /* CREATE_TRACE_POINTS */
TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
- __entry->prev_state & (TASK_STATE_MAX-1) ?
- __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
- { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
- { 16, "Z" }, { 32, "X" }, { 64, "x" },
- { 128, "K" }, { 256, "W" }, { 512, "P" },
- { 1024, "N" }) : "R",
+
+ (__entry->prev_state & (TASK_REPORT_MAX - 1)) ?
+ __print_flags(__entry->prev_state & (TASK_REPORT_MAX - 1), "|",
+ { 0x01, "S" }, { 0x02, "D" }, { 0x04, "T" },
+ { 0x08, "t" }, { 0x10, "X" }, { 0x20, "Z" },
+ { 0x40, "P" }, { 0x80, "I" }) :
+ "R",
+
__entry->prev_state & TASK_STATE_MAX ? "+" : "",
__entry->next_comm, __entry->next_pid, __entry->next_prio)
);
* %ethtool_link_mode_bit_indices for the link modes, and other
* link features that the link partner advertised through
* autonegotiation; 0 if unknown or not applicable. Read-only.
+ * @transceiver: Used to distinguish different possible PHY types,
+ * reported consistently by PHYLIB. Read-only.
*
* If autonegotiation is disabled, the speed and @duplex represent the
* fixed link mode and are writable if the driver supports multiple
__u8 eth_tp_mdix;
__u8 eth_tp_mdix_ctrl;
__s8 link_mode_masks_nwords;
- __u32 reserved[8];
+ __u8 transceiver;
+ __u8 reserved1[3];
+ __u32 reserved[7];
__u32 link_mode_masks[0];
/* layout of link_mode_masks fields:
* __u32 map_supported[link_mode_masks_nwords];
#ifndef KFD_IOCTL_H_INCLUDED
#define KFD_IOCTL_H_INCLUDED
-#include <linux/types.h>
+#include <drm/drm.h>
#include <linux/ioctl.h>
#define KFD_IOCTL_MAJOR_VERSION 1
#define KFD_IOCTL_MINOR_VERSION 1
struct kfd_ioctl_get_version_args {
- uint32_t major_version; /* from KFD */
- uint32_t minor_version; /* from KFD */
+ __u32 major_version; /* from KFD */
+ __u32 minor_version; /* from KFD */
};
/* For kfd_ioctl_create_queue_args.queue_type. */
#define KFD_MAX_QUEUE_PRIORITY 15
struct kfd_ioctl_create_queue_args {
- uint64_t ring_base_address; /* to KFD */
- uint64_t write_pointer_address; /* from KFD */
- uint64_t read_pointer_address; /* from KFD */
- uint64_t doorbell_offset; /* from KFD */
-
- uint32_t ring_size; /* to KFD */
- uint32_t gpu_id; /* to KFD */
- uint32_t queue_type; /* to KFD */
- uint32_t queue_percentage; /* to KFD */
- uint32_t queue_priority; /* to KFD */
- uint32_t queue_id; /* from KFD */
-
- uint64_t eop_buffer_address; /* to KFD */
- uint64_t eop_buffer_size; /* to KFD */
- uint64_t ctx_save_restore_address; /* to KFD */
- uint64_t ctx_save_restore_size; /* to KFD */
+ __u64 ring_base_address; /* to KFD */
+ __u64 write_pointer_address; /* from KFD */
+ __u64 read_pointer_address; /* from KFD */
+ __u64 doorbell_offset; /* from KFD */
+
+ __u32 ring_size; /* to KFD */
+ __u32 gpu_id; /* to KFD */
+ __u32 queue_type; /* to KFD */
+ __u32 queue_percentage; /* to KFD */
+ __u32 queue_priority; /* to KFD */
+ __u32 queue_id; /* from KFD */
+
+ __u64 eop_buffer_address; /* to KFD */
+ __u64 eop_buffer_size; /* to KFD */
+ __u64 ctx_save_restore_address; /* to KFD */
+ __u64 ctx_save_restore_size; /* to KFD */
};
struct kfd_ioctl_destroy_queue_args {
- uint32_t queue_id; /* to KFD */
- uint32_t pad;
+ __u32 queue_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_update_queue_args {
- uint64_t ring_base_address; /* to KFD */
+ __u64 ring_base_address; /* to KFD */
- uint32_t queue_id; /* to KFD */
- uint32_t ring_size; /* to KFD */
- uint32_t queue_percentage; /* to KFD */
- uint32_t queue_priority; /* to KFD */
+ __u32 queue_id; /* to KFD */
+ __u32 ring_size; /* to KFD */
+ __u32 queue_percentage; /* to KFD */
+ __u32 queue_priority; /* to KFD */
};
/* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
#define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
struct kfd_ioctl_set_memory_policy_args {
- uint64_t alternate_aperture_base; /* to KFD */
- uint64_t alternate_aperture_size; /* to KFD */
+ __u64 alternate_aperture_base; /* to KFD */
+ __u64 alternate_aperture_size; /* to KFD */
- uint32_t gpu_id; /* to KFD */
- uint32_t default_policy; /* to KFD */
- uint32_t alternate_policy; /* to KFD */
- uint32_t pad;
+ __u32 gpu_id; /* to KFD */
+ __u32 default_policy; /* to KFD */
+ __u32 alternate_policy; /* to KFD */
+ __u32 pad;
};
/*
*/
struct kfd_ioctl_get_clock_counters_args {
- uint64_t gpu_clock_counter; /* from KFD */
- uint64_t cpu_clock_counter; /* from KFD */
- uint64_t system_clock_counter; /* from KFD */
- uint64_t system_clock_freq; /* from KFD */
+ __u64 gpu_clock_counter; /* from KFD */
+ __u64 cpu_clock_counter; /* from KFD */
+ __u64 system_clock_counter; /* from KFD */
+ __u64 system_clock_freq; /* from KFD */
- uint32_t gpu_id; /* to KFD */
- uint32_t pad;
+ __u32 gpu_id; /* to KFD */
+ __u32 pad;
};
#define NUM_OF_SUPPORTED_GPUS 7
struct kfd_process_device_apertures {
- uint64_t lds_base; /* from KFD */
- uint64_t lds_limit; /* from KFD */
- uint64_t scratch_base; /* from KFD */
- uint64_t scratch_limit; /* from KFD */
- uint64_t gpuvm_base; /* from KFD */
- uint64_t gpuvm_limit; /* from KFD */
- uint32_t gpu_id; /* from KFD */
- uint32_t pad;
+ __u64 lds_base; /* from KFD */
+ __u64 lds_limit; /* from KFD */
+ __u64 scratch_base; /* from KFD */
+ __u64 scratch_limit; /* from KFD */
+ __u64 gpuvm_base; /* from KFD */
+ __u64 gpuvm_limit; /* from KFD */
+ __u32 gpu_id; /* from KFD */
+ __u32 pad;
};
struct kfd_ioctl_get_process_apertures_args {
process_apertures[NUM_OF_SUPPORTED_GPUS];/* from KFD */
/* from KFD, should be in the range [1 - NUM_OF_SUPPORTED_GPUS] */
- uint32_t num_of_nodes;
- uint32_t pad;
+ __u32 num_of_nodes;
+ __u32 pad;
};
#define MAX_ALLOWED_NUM_POINTS 100
#define MAX_ALLOWED_WAC_BUFF_SIZE 128
struct kfd_ioctl_dbg_register_args {
- uint32_t gpu_id; /* to KFD */
- uint32_t pad;
+ __u32 gpu_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_dbg_unregister_args {
- uint32_t gpu_id; /* to KFD */
- uint32_t pad;
+ __u32 gpu_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_dbg_address_watch_args {
- uint64_t content_ptr; /* a pointer to the actual content */
- uint32_t gpu_id; /* to KFD */
- uint32_t buf_size_in_bytes; /*including gpu_id and buf_size */
+ __u64 content_ptr; /* a pointer to the actual content */
+ __u32 gpu_id; /* to KFD */
+ __u32 buf_size_in_bytes; /*including gpu_id and buf_size */
};
struct kfd_ioctl_dbg_wave_control_args {
- uint64_t content_ptr; /* a pointer to the actual content */
- uint32_t gpu_id; /* to KFD */
- uint32_t buf_size_in_bytes; /*including gpu_id and buf_size */
+ __u64 content_ptr; /* a pointer to the actual content */
+ __u32 gpu_id; /* to KFD */
+ __u32 buf_size_in_bytes; /*including gpu_id and buf_size */
};
/* Matching HSA_EVENTTYPE */
#define KFD_SIGNAL_EVENT_LIMIT 256
struct kfd_ioctl_create_event_args {
- uint64_t event_page_offset; /* from KFD */
- uint32_t event_trigger_data; /* from KFD - signal events only */
- uint32_t event_type; /* to KFD */
- uint32_t auto_reset; /* to KFD */
- uint32_t node_id; /* to KFD - only valid for certain
+ __u64 event_page_offset; /* from KFD */
+ __u32 event_trigger_data; /* from KFD - signal events only */
+ __u32 event_type; /* to KFD */
+ __u32 auto_reset; /* to KFD */
+ __u32 node_id; /* to KFD - only valid for certain
event types */
- uint32_t event_id; /* from KFD */
- uint32_t event_slot_index; /* from KFD */
+ __u32 event_id; /* from KFD */
+ __u32 event_slot_index; /* from KFD */
};
struct kfd_ioctl_destroy_event_args {
- uint32_t event_id; /* to KFD */
- uint32_t pad;
+ __u32 event_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_set_event_args {
- uint32_t event_id; /* to KFD */
- uint32_t pad;
+ __u32 event_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_reset_event_args {
- uint32_t event_id; /* to KFD */
- uint32_t pad;
+ __u32 event_id; /* to KFD */
+ __u32 pad;
};
struct kfd_memory_exception_failure {
- uint32_t NotPresent; /* Page not present or supervisor privilege */
- uint32_t ReadOnly; /* Write access to a read-only page */
- uint32_t NoExecute; /* Execute access to a page marked NX */
- uint32_t pad;
+ __u32 NotPresent; /* Page not present or supervisor privilege */
+ __u32 ReadOnly; /* Write access to a read-only page */
+ __u32 NoExecute; /* Execute access to a page marked NX */
+ __u32 pad;
};
/* memory exception data*/
struct kfd_hsa_memory_exception_data {
struct kfd_memory_exception_failure failure;
- uint64_t va;
- uint32_t gpu_id;
- uint32_t pad;
+ __u64 va;
+ __u32 gpu_id;
+ __u32 pad;
};
/* Event data*/
union {
struct kfd_hsa_memory_exception_data memory_exception_data;
}; /* From KFD */
- uint64_t kfd_event_data_ext; /* pointer to an extension structure
+ __u64 kfd_event_data_ext; /* pointer to an extension structure
for future exception types */
- uint32_t event_id; /* to KFD */
- uint32_t pad;
+ __u32 event_id; /* to KFD */
+ __u32 pad;
};
struct kfd_ioctl_wait_events_args {
- uint64_t events_ptr; /* pointed to struct
+ __u64 events_ptr; /* pointed to struct
kfd_event_data array, to KFD */
- uint32_t num_events; /* to KFD */
- uint32_t wait_for_all; /* to KFD */
- uint32_t timeout; /* to KFD */
- uint32_t wait_result; /* from KFD */
+ __u32 num_events; /* to KFD */
+ __u32 wait_for_all; /* to KFD */
+ __u32 timeout; /* to KFD */
+ __u32 wait_result; /* from KFD */
};
struct kfd_ioctl_set_scratch_backing_va_args {
#define SECCOMP_MODE_FILTER 2 /* uses user-supplied filter. */
/* Valid operations for seccomp syscall. */
-#define SECCOMP_SET_MODE_STRICT 0
-#define SECCOMP_SET_MODE_FILTER 1
+#define SECCOMP_SET_MODE_STRICT 0
+#define SECCOMP_SET_MODE_FILTER 1
+#define SECCOMP_GET_ACTION_AVAIL 2
/* Valid flags for SECCOMP_SET_MODE_FILTER */
#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_LOG 2
/*
* All BPF programs must return a 32-bit value.
* The bottom 16-bits are for optional return data.
- * The upper 16-bits are ordered from least permissive values to most.
+ * The upper 16-bits are ordered from least permissive values to most,
+ * as a signed value (so 0x8000000 is negative).
*
* The ordering ensures that a min_t() over composed return values always
* selects the least permissive choice.
*/
-#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
-#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
-#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
-#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
-#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
+#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
+#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
/* Masks for the return value sections. */
+#define SECCOMP_RET_ACTION_FULL 0xffff0000U
#define SECCOMP_RET_ACTION 0x7fff0000U
#define SECCOMP_RET_DATA 0x0000ffffU
struct ib_uverbs_rss_caps rss_caps;
__u32 max_wq_type_rq;
__u32 raw_packet_caps;
- struct ib_uverbs_tm_caps xrq_caps;
+ struct ib_uverbs_tm_caps tm_caps;
};
struct ib_uverbs_query_port {
BUG();
}
-/* TODO: this shouldn't be here but it is because the frontend drivers
- * are using it (its rolled in headers) even though we won't hit the code path.
- * So for right now just punt with this.
- */
-static inline pte_t *lookup_address(unsigned long address, unsigned int *level)
-{
- BUG();
- return NULL;
-}
-
extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count);
info.shm_swp = ip->shm_swp;
info.swap_attempts = ip->swap_attempts;
info.swap_successes = ip->swap_successes;
- return copy_to_user(up, &info, sizeof(info));
+ return copy_to_user(uip, &info, sizeof(info));
}
static int copy_compat_shmid_to_user(void __user *buf, struct shmid64_ds *in,
err = shmctl_stat(ns, shmid, cmd, &sem64);
if (err < 0)
return err;
- if (copy_compat_shmid_to_user(&sem64, uptr, version))
+ if (copy_compat_shmid_to_user(uptr, &sem64, version))
err = -EFAULT;
return err;
static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
{
struct bpf_dtab *dtab;
+ int err = -EINVAL;
u64 cost;
- int err;
/* check sanity of attributes */
if (attr->max_entries == 0 || attr->key_size != 4 ||
if (err)
goto free_dtab;
+ err = -ENOMEM;
+
/* A per cpu bitfield with a bit per possible net device */
dtab->flush_needed = __alloc_percpu(dev_map_bitmap_size(attr),
__alignof__(unsigned long));
free_dtab:
free_percpu(dtab->flush_needed);
kfree(dtab);
- return ERR_PTR(-ENOMEM);
+ return ERR_PTR(err);
}
static void dev_map_free(struct bpf_map *map)
static void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock)
{
+ unsigned long flags;
+
if (do_idr_lock)
- spin_lock_bh(&map_idr_lock);
+ spin_lock_irqsave(&map_idr_lock, flags);
else
__acquire(&map_idr_lock);
idr_remove(&map_idr, map->id);
if (do_idr_lock)
- spin_unlock_bh(&map_idr_lock);
+ spin_unlock_irqrestore(&map_idr_lock, flags);
else
__release(&map_idr_lock);
}
}
if (insn->imm == BPF_FUNC_redirect_map) {
- u64 addr = (unsigned long)prog;
+ /* Note, we cannot use prog directly as imm as subsequent
+ * rewrites would still change the prog pointer. The only
+ * stable address we can use is aux, which also works with
+ * prog clones during blinding.
+ */
+ u64 addr = (unsigned long)prog->aux;
struct bpf_insn r4_ld[] = {
BPF_LD_IMM64(BPF_REG_4, addr),
*insn,
* @bringup: Single callback bringup or teardown selector
* @cb_state: The state for a single callback (install/uninstall)
* @result: Result of the operation
- * @done: Signal completion to the issuer of the task
+ * @done_up: Signal completion to the issuer of the task for cpu-up
+ * @done_down: Signal completion to the issuer of the task for cpu-down
*/
struct cpuhp_cpu_state {
enum cpuhp_state state;
enum cpuhp_state target;
+ enum cpuhp_state fail;
#ifdef CONFIG_SMP
struct task_struct *thread;
bool should_run;
bool single;
bool bringup;
struct hlist_node *node;
+ struct hlist_node *last;
enum cpuhp_state cb_state;
int result;
- struct completion done;
+ struct completion done_up;
+ struct completion done_down;
#endif
};
-static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
+static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
+ .fail = CPUHP_INVALID,
+};
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
-static struct lock_class_key cpuhp_state_key;
-static struct lockdep_map cpuhp_state_lock_map =
- STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key);
+static struct lockdep_map cpuhp_state_up_map =
+ STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
+static struct lockdep_map cpuhp_state_down_map =
+ STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
+
+
+static void inline cpuhp_lock_acquire(bool bringup)
+{
+ lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
+}
+
+static void inline cpuhp_lock_release(bool bringup)
+{
+ lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
+}
+#else
+
+static void inline cpuhp_lock_acquire(bool bringup) { }
+static void inline cpuhp_lock_release(bool bringup) { }
+
#endif
/**
/**
* cpuhp_invoke_callback _ Invoke the callbacks for a given state
* @cpu: The cpu for which the callback should be invoked
- * @step: The step in the state machine
+ * @state: The state to do callbacks for
* @bringup: True if the bringup callback should be invoked
+ * @node: For multi-instance, do a single entry callback for install/remove
+ * @lastp: For multi-instance rollback, remember how far we got
*
* Called from cpu hotplug and from the state register machinery.
*/
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
- bool bringup, struct hlist_node *node)
+ bool bringup, struct hlist_node *node,
+ struct hlist_node **lastp)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
struct cpuhp_step *step = cpuhp_get_step(state);
int (*cb)(unsigned int cpu);
int ret, cnt;
+ if (st->fail == state) {
+ st->fail = CPUHP_INVALID;
+
+ if (!(bringup ? step->startup.single : step->teardown.single))
+ return 0;
+
+ return -EAGAIN;
+ }
+
if (!step->multi_instance) {
+ WARN_ON_ONCE(lastp && *lastp);
cb = bringup ? step->startup.single : step->teardown.single;
if (!cb)
return 0;
/* Single invocation for instance add/remove */
if (node) {
+ WARN_ON_ONCE(lastp && *lastp);
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
/* State transition. Invoke on all instances */
cnt = 0;
hlist_for_each(node, &step->list) {
+ if (lastp && node == *lastp)
+ break;
+
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
- if (ret)
- goto err;
+ if (ret) {
+ if (!lastp)
+ goto err;
+
+ *lastp = node;
+ return ret;
+ }
cnt++;
}
+ if (lastp)
+ *lastp = NULL;
return 0;
err:
/* Rollback the instances if one failed */
hlist_for_each(node, &step->list) {
if (!cnt--)
break;
- cbm(cpu, node);
+
+ trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+ ret = cbm(cpu, node);
+ trace_cpuhp_exit(cpu, st->state, state, ret);
+ /*
+ * Rollback must not fail,
+ */
+ WARN_ON_ONCE(ret);
}
return ret;
}
#ifdef CONFIG_SMP
+static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
+{
+ struct completion *done = bringup ? &st->done_up : &st->done_down;
+ wait_for_completion(done);
+}
+
+static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
+{
+ struct completion *done = bringup ? &st->done_up : &st->done_down;
+ complete(done);
+}
+
+/*
+ * The former STARTING/DYING states, ran with IRQs disabled and must not fail.
+ */
+static bool cpuhp_is_atomic_state(enum cpuhp_state state)
+{
+ return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
+}
+
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);
bool cpuhp_tasks_frozen;
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
#endif /* CONFIG_HOTPLUG_CPU */
-static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st);
+static inline enum cpuhp_state
+cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
+{
+ enum cpuhp_state prev_state = st->state;
+
+ st->rollback = false;
+ st->last = NULL;
+
+ st->target = target;
+ st->single = false;
+ st->bringup = st->state < target;
+
+ return prev_state;
+}
+
+static inline void
+cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
+{
+ st->rollback = true;
+
+ /*
+ * If we have st->last we need to undo partial multi_instance of this
+ * state first. Otherwise start undo at the previous state.
+ */
+ if (!st->last) {
+ if (st->bringup)
+ st->state--;
+ else
+ st->state++;
+ }
+
+ st->target = prev_state;
+ st->bringup = !st->bringup;
+}
+
+/* Regular hotplug invocation of the AP hotplug thread */
+static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
+{
+ if (!st->single && st->state == st->target)
+ return;
+
+ st->result = 0;
+ /*
+ * Make sure the above stores are visible before should_run becomes
+ * true. Paired with the mb() above in cpuhp_thread_fun()
+ */
+ smp_mb();
+ st->should_run = true;
+ wake_up_process(st->thread);
+ wait_for_ap_thread(st, st->bringup);
+}
+
+static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target)
+{
+ enum cpuhp_state prev_state;
+ int ret;
+
+ prev_state = cpuhp_set_state(st, target);
+ __cpuhp_kick_ap(st);
+ if ((ret = st->result)) {
+ cpuhp_reset_state(st, prev_state);
+ __cpuhp_kick_ap(st);
+ }
+
+ return ret;
+}
static int bringup_wait_for_ap(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
- wait_for_completion(&st->done);
+ wait_for_ap_thread(st, true);
if (WARN_ON_ONCE((!cpu_online(cpu))))
return -ECANCELED;
stop_machine_unpark(cpu);
kthread_unpark(st->thread);
- /* Should we go further up ? */
- if (st->target > CPUHP_AP_ONLINE_IDLE) {
- __cpuhp_kick_ap_work(st);
- wait_for_completion(&st->done);
- }
- return st->result;
+ if (st->target <= CPUHP_AP_ONLINE_IDLE)
+ return 0;
+
+ return cpuhp_kick_ap(st, st->target);
}
static int bringup_cpu(unsigned int cpu)
/*
* Hotplug state machine related functions
*/
-static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
- for (st->state++; st->state < st->target; st->state++) {
- struct cpuhp_step *step = cpuhp_get_step(st->state);
-
- if (!step->skip_onerr)
- cpuhp_invoke_callback(cpu, st->state, true, NULL);
- }
-}
-
-static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
- enum cpuhp_state target)
-{
- enum cpuhp_state prev_state = st->state;
- int ret = 0;
-
- for (; st->state > target; st->state--) {
- ret = cpuhp_invoke_callback(cpu, st->state, false, NULL);
- if (ret) {
- st->target = prev_state;
- undo_cpu_down(cpu, st);
- break;
- }
- }
- return ret;
-}
static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
{
struct cpuhp_step *step = cpuhp_get_step(st->state);
if (!step->skip_onerr)
- cpuhp_invoke_callback(cpu, st->state, false, NULL);
+ cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
}
}
while (st->state < target) {
st->state++;
- ret = cpuhp_invoke_callback(cpu, st->state, true, NULL);
+ ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
if (ret) {
st->target = prev_state;
undo_cpu_up(cpu, st);
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
- init_completion(&st->done);
+ init_completion(&st->done_up);
+ init_completion(&st->done_down);
}
static int cpuhp_should_run(unsigned int cpu)
return st->should_run;
}
-/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */
-static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
- enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
-
- return cpuhp_down_callbacks(cpu, st, target);
-}
-
-/* Execute the online startup callbacks. Used to be CPU_ONLINE */
-static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
-{
- return cpuhp_up_callbacks(cpu, st, st->target);
-}
-
/*
* Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
* callbacks when a state gets [un]installed at runtime.
+ *
+ * Each invocation of this function by the smpboot thread does a single AP
+ * state callback.
+ *
+ * It has 3 modes of operation:
+ * - single: runs st->cb_state
+ * - up: runs ++st->state, while st->state < st->target
+ * - down: runs st->state--, while st->state > st->target
+ *
+ * When complete or on error, should_run is cleared and the completion is fired.
*/
static void cpuhp_thread_fun(unsigned int cpu)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
- int ret = 0;
+ bool bringup = st->bringup;
+ enum cpuhp_state state;
/*
- * Paired with the mb() in cpuhp_kick_ap_work and
- * cpuhp_invoke_ap_callback, so the work set is consistent visible.
+ * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
+ * that if we see ->should_run we also see the rest of the state.
*/
smp_mb();
- if (!st->should_run)
+
+ if (WARN_ON_ONCE(!st->should_run))
return;
- st->should_run = false;
+ cpuhp_lock_acquire(bringup);
- lock_map_acquire(&cpuhp_state_lock_map);
- /* Single callback invocation for [un]install ? */
if (st->single) {
- if (st->cb_state < CPUHP_AP_ONLINE) {
- local_irq_disable();
- ret = cpuhp_invoke_callback(cpu, st->cb_state,
- st->bringup, st->node);
- local_irq_enable();
+ state = st->cb_state;
+ st->should_run = false;
+ } else {
+ if (bringup) {
+ st->state++;
+ state = st->state;
+ st->should_run = (st->state < st->target);
+ WARN_ON_ONCE(st->state > st->target);
} else {
- ret = cpuhp_invoke_callback(cpu, st->cb_state,
- st->bringup, st->node);
+ state = st->state;
+ st->state--;
+ st->should_run = (st->state > st->target);
+ WARN_ON_ONCE(st->state < st->target);
}
- } else if (st->rollback) {
- BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
+ }
+
+ WARN_ON_ONCE(!cpuhp_is_ap_state(state));
- undo_cpu_down(cpu, st);
- st->rollback = false;
+ if (st->rollback) {
+ struct cpuhp_step *step = cpuhp_get_step(state);
+ if (step->skip_onerr)
+ goto next;
+ }
+
+ if (cpuhp_is_atomic_state(state)) {
+ local_irq_disable();
+ st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
+ local_irq_enable();
+
+ /*
+ * STARTING/DYING must not fail!
+ */
+ WARN_ON_ONCE(st->result);
} else {
- /* Cannot happen .... */
- BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
-
- /* Regular hotplug work */
- if (st->state < st->target)
- ret = cpuhp_ap_online(cpu, st);
- else if (st->state > st->target)
- ret = cpuhp_ap_offline(cpu, st);
+ st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
+ }
+
+ if (st->result) {
+ /*
+ * If we fail on a rollback, we're up a creek without no
+ * paddle, no way forward, no way back. We loose, thanks for
+ * playing.
+ */
+ WARN_ON_ONCE(st->rollback);
+ st->should_run = false;
}
- lock_map_release(&cpuhp_state_lock_map);
- st->result = ret;
- complete(&st->done);
+
+next:
+ cpuhp_lock_release(bringup);
+
+ if (!st->should_run)
+ complete_ap_thread(st, bringup);
}
/* Invoke a single callback on a remote cpu */
struct hlist_node *node)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+ int ret;
if (!cpu_online(cpu))
return 0;
- lock_map_acquire(&cpuhp_state_lock_map);
- lock_map_release(&cpuhp_state_lock_map);
+ cpuhp_lock_acquire(false);
+ cpuhp_lock_release(false);
+
+ cpuhp_lock_acquire(true);
+ cpuhp_lock_release(true);
/*
* If we are up and running, use the hotplug thread. For early calls
* we invoke the thread function directly.
*/
if (!st->thread)
- return cpuhp_invoke_callback(cpu, state, bringup, node);
+ return cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
+ st->rollback = false;
+ st->last = NULL;
+
+ st->node = node;
+ st->bringup = bringup;
st->cb_state = state;
st->single = true;
- st->bringup = bringup;
- st->node = node;
- /*
- * Make sure the above stores are visible before should_run becomes
- * true. Paired with the mb() above in cpuhp_thread_fun()
- */
- smp_mb();
- st->should_run = true;
- wake_up_process(st->thread);
- wait_for_completion(&st->done);
- return st->result;
-}
+ __cpuhp_kick_ap(st);
-/* Regular hotplug invocation of the AP hotplug thread */
-static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
-{
- st->result = 0;
- st->single = false;
/*
- * Make sure the above stores are visible before should_run becomes
- * true. Paired with the mb() above in cpuhp_thread_fun()
+ * If we failed and did a partial, do a rollback.
*/
- smp_mb();
- st->should_run = true;
- wake_up_process(st->thread);
+ if ((ret = st->result) && st->last) {
+ st->rollback = true;
+ st->bringup = !bringup;
+
+ __cpuhp_kick_ap(st);
+ }
+
+ return ret;
}
static int cpuhp_kick_ap_work(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
- enum cpuhp_state state = st->state;
+ enum cpuhp_state prev_state = st->state;
+ int ret;
+
+ cpuhp_lock_acquire(false);
+ cpuhp_lock_release(false);
+
+ cpuhp_lock_acquire(true);
+ cpuhp_lock_release(true);
+
+ trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
+ ret = cpuhp_kick_ap(st, st->target);
+ trace_cpuhp_exit(cpu, st->state, prev_state, ret);
- trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
- lock_map_acquire(&cpuhp_state_lock_map);
- lock_map_release(&cpuhp_state_lock_map);
- __cpuhp_kick_ap_work(st);
- wait_for_completion(&st->done);
- trace_cpuhp_exit(cpu, st->state, state, st->result);
- return st->result;
+ return ret;
}
static struct smp_hotplug_thread cpuhp_threads = {
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
int err, cpu = smp_processor_id();
+ int ret;
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
st->state--;
/* Invoke the former CPU_DYING callbacks */
- for (; st->state > target; st->state--)
- cpuhp_invoke_callback(cpu, st->state, false, NULL);
+ for (; st->state > target; st->state--) {
+ ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
+ /*
+ * DYING must not fail!
+ */
+ WARN_ON_ONCE(ret);
+ }
/* Give up timekeeping duties */
tick_handover_do_timer();
*
* Wait for the stop thread to go away.
*/
- wait_for_completion(&st->done);
+ wait_for_ap_thread(st, false);
BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
/* Interrupts are moved away from the dying cpu, reenable alloc/free */
{
struct cpuhp_cpu_state *st = arg;
- complete(&st->done);
+ complete_ap_thread(st, false);
}
void cpuhp_report_idle_dead(void)
cpuhp_complete_idle_dead, st, 0);
}
-#else
-#define takedown_cpu NULL
-#endif
+static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
+{
+ for (st->state++; st->state < st->target; st->state++) {
+ struct cpuhp_step *step = cpuhp_get_step(st->state);
-#ifdef CONFIG_HOTPLUG_CPU
+ if (!step->skip_onerr)
+ cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
+ }
+}
+
+static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
+ enum cpuhp_state target)
+{
+ enum cpuhp_state prev_state = st->state;
+ int ret = 0;
+
+ for (; st->state > target; st->state--) {
+ ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
+ if (ret) {
+ st->target = prev_state;
+ undo_cpu_down(cpu, st);
+ break;
+ }
+ }
+ return ret;
+}
/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
cpuhp_tasks_frozen = tasks_frozen;
- prev_state = st->state;
- st->target = target;
+ prev_state = cpuhp_set_state(st, target);
/*
* If the current CPU state is in the range of the AP hotplug thread,
* then we need to kick the thread.
*/
if (st->state > CPUHP_TEARDOWN_CPU) {
+ st->target = max((int)target, CPUHP_TEARDOWN_CPU);
ret = cpuhp_kick_ap_work(cpu);
/*
* The AP side has done the error rollback already. Just
*/
if (st->state > CPUHP_TEARDOWN_CPU)
goto out;
+
+ st->target = target;
}
/*
* The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
*/
ret = cpuhp_down_callbacks(cpu, st, target);
if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
- st->target = prev_state;
- st->rollback = true;
- cpuhp_kick_ap_work(cpu);
+ cpuhp_reset_state(st, prev_state);
+ __cpuhp_kick_ap(st);
}
out:
cpu_maps_update_done();
return err;
}
+
int cpu_down(unsigned int cpu)
{
return do_cpu_down(cpu, CPUHP_OFFLINE);
}
EXPORT_SYMBOL(cpu_down);
+
+#else
+#define takedown_cpu NULL
#endif /*CONFIG_HOTPLUG_CPU*/
/**
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
+ int ret;
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
while (st->state < target) {
st->state++;
- cpuhp_invoke_callback(cpu, st->state, true, NULL);
+ ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
+ /*
+ * STARTING must not fail!
+ */
+ WARN_ON_ONCE(ret);
}
}
return;
st->state = CPUHP_AP_ONLINE_IDLE;
- complete(&st->done);
+ complete_ap_thread(st, true);
}
/* Requires cpu_add_remove_lock to be held */
cpuhp_tasks_frozen = tasks_frozen;
- st->target = target;
+ cpuhp_set_state(st, target);
/*
* If the current CPU state is in the range of the AP hotplug thread,
* then we need to kick the thread once more.
struct cpuhp_step *sp = cpuhp_get_step(state);
int ret;
+ /*
+ * If there's nothing to do, we done.
+ * Relies on the union for multi_instance.
+ */
if ((bringup && !sp->startup.single) ||
(!bringup && !sp->teardown.single))
return 0;
if (cpuhp_is_ap_state(state))
ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
else
- ret = cpuhp_invoke_callback(cpu, state, bringup, node);
+ ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#else
- ret = cpuhp_invoke_callback(cpu, state, bringup, node);
+ ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#endif
BUG_ON(ret && !bringup);
return ret;
}
static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
+
+static ssize_t write_cpuhp_fail(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+ struct cpuhp_step *sp;
+ int fail, ret;
+
+ ret = kstrtoint(buf, 10, &fail);
+ if (ret)
+ return ret;
+
+ /*
+ * Cannot fail STARTING/DYING callbacks.
+ */
+ if (cpuhp_is_atomic_state(fail))
+ return -EINVAL;
+
+ /*
+ * Cannot fail anything that doesn't have callbacks.
+ */
+ mutex_lock(&cpuhp_state_mutex);
+ sp = cpuhp_get_step(fail);
+ if (!sp->startup.single && !sp->teardown.single)
+ ret = -EINVAL;
+ mutex_unlock(&cpuhp_state_mutex);
+ if (ret)
+ return ret;
+
+ st->fail = fail;
+
+ return count;
+}
+
+static ssize_t show_cpuhp_fail(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
+
+ return sprintf(buf, "%d\n", st->fail);
+}
+
+static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);
+
static struct attribute *cpuhp_cpu_attrs[] = {
&dev_attr_state.attr,
&dev_attr_target.attr,
+ &dev_attr_fail.attr,
NULL
};
}
}
event->tp_event->prog = prog;
+ event->tp_event->bpf_prog_owner = event;
return 0;
}
return;
prog = event->tp_event->prog;
- if (prog) {
+ if (prog && event->tp_event->bpf_prog_owner == event) {
event->tp_event->prog = NULL;
bpf_prog_put(prog);
}
return NULL;
}
+static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+{
+ if (rb->aux_overwrite)
+ return false;
+
+ if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+ rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
+ return true;
+ }
+
+ return false;
+}
+
/*
* Commit the data written by hardware into the ring buffer by adjusting
* aux_head and posting a PERF_RECORD_AUX into the perf buffer. It is the
}
rb->user_page->aux_head = rb->aux_head;
- if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+ if (rb_need_aux_wakeup(rb))
wakeup = true;
- rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
- }
if (wakeup) {
if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
rb->aux_head += size;
rb->user_page->aux_head = rb->aux_head;
- if (rb->aux_head - rb->aux_wakeup >= rb->aux_watermark) {
+ if (rb_need_aux_wakeup(rb)) {
perf_output_wakeup(handle);
- rb->aux_wakeup = rounddown(rb->aux_head, rb->aux_watermark);
handle->wakeup = rb->aux_wakeup + rb->aux_watermark;
}
struct waitid_info info = {.status = 0};
long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL);
int signo = 0;
+
if (err > 0) {
signo = SIGCHLD;
err = 0;
- }
-
- if (!err) {
if (ru && copy_to_user(ru, &r, sizeof(struct rusage)))
return -EFAULT;
}
if (err > 0) {
signo = SIGCHLD;
err = 0;
- }
-
- if (!err && uru) {
- /* kernel_waitid() overwrites everything in ru */
- if (COMPAT_USE_64BIT_TIME)
- err = copy_to_user(uru, &ru, sizeof(ru));
- else
- err = put_compat_rusage(&ru, uru);
- if (err)
- return -EFAULT;
+ if (uru) {
+ /* kernel_waitid() overwrites everything in ru */
+ if (COMPAT_USE_64BIT_TIME)
+ err = copy_to_user(uru, &ru, sizeof(ru));
+ else
+ err = put_compat_rusage(&ru, uru);
+ if (err)
+ return -EFAULT;
+ }
}
if (!infop)
int __kernel_text_address(unsigned long addr)
{
- if (core_kernel_text(addr))
- return 1;
- if (is_module_text_address(addr))
- return 1;
- if (is_ftrace_trampoline(addr))
- return 1;
- if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
- return 1;
- if (is_bpf_text_address(addr))
+ if (kernel_text_address(addr))
return 1;
/*
* There might be init symbols in saved stacktraces.
int kernel_text_address(unsigned long addr)
{
+ bool no_rcu;
+ int ret = 1;
+
if (core_kernel_text(addr))
return 1;
+
+ /*
+ * If a stack dump happens while RCU is not watching, then
+ * RCU needs to be notified that it requires to start
+ * watching again. This can happen either by tracing that
+ * triggers a stack trace, or a WARN() that happens during
+ * coming back from idle, or cpu on or offlining.
+ *
+ * is_module_text_address() as well as the kprobe slots
+ * and is_bpf_text_address() require RCU to be watching.
+ */
+ no_rcu = !rcu_is_watching();
+
+ /* Treat this like an NMI as it can happen anywhere */
+ if (no_rcu)
+ rcu_nmi_enter();
+
if (is_module_text_address(addr))
- return 1;
+ goto out;
if (is_ftrace_trampoline(addr))
- return 1;
+ goto out;
if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
- return 1;
+ goto out;
if (is_bpf_text_address(addr))
- return 1;
- return 0;
+ goto out;
+ ret = 0;
+out:
+ if (no_rcu)
+ rcu_nmi_exit();
+
+ return ret;
}
/*
/*
* Drops a reference to the pi_state object and frees or caches it
* when the last reference is gone.
- *
- * Must be called with the hb lock held.
*/
static void put_pi_state(struct futex_pi_state *pi_state)
{
* and has cleaned up the pi_state already
*/
if (pi_state->owner) {
- raw_spin_lock_irq(&pi_state->owner->pi_lock);
- list_del_init(&pi_state->list);
- raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+ struct task_struct *owner;
- rt_mutex_proxy_unlock(&pi_state->pi_mutex, pi_state->owner);
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ owner = pi_state->owner;
+ if (owner) {
+ raw_spin_lock(&owner->pi_lock);
+ list_del_init(&pi_state->list);
+ raw_spin_unlock(&owner->pi_lock);
+ }
+ rt_mutex_proxy_unlock(&pi_state->pi_mutex, owner);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
}
- if (current->pi_state_cache)
+ if (current->pi_state_cache) {
kfree(pi_state);
- else {
+ } else {
/*
* pi_state->list is already empty.
* clear pi_state->owner.
raw_spin_unlock_irq(&curr->pi_lock);
spin_lock(&hb->lock);
-
- raw_spin_lock_irq(&curr->pi_lock);
+ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+ raw_spin_lock(&curr->pi_lock);
/*
* We dropped the pi-lock, so re-check whether this
* task still owns the PI-state:
*/
if (head->next != next) {
+ raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
continue;
}
WARN_ON(list_empty(&pi_state->list));
list_del_init(&pi_state->list);
pi_state->owner = NULL;
- raw_spin_unlock_irq(&curr->pi_lock);
+ raw_spin_unlock(&curr->pi_lock);
get_pi_state(pi_state);
+ raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
rt_mutex_futex_unlock(&pi_state->pi_mutex);
WARN_ON(!list_empty(&pi_state->list));
list_add(&pi_state->list, &p->pi_state_list);
+ /*
+ * Assignment without holding pi_state->pi_mutex.wait_lock is safe
+ * because there is no concurrency as the object is not published yet.
+ */
pi_state->owner = p;
raw_spin_unlock_irq(&p->pi_lock);
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(&hb->lock);
+ /* drops pi_state->pi_mutex.wait_lock */
ret = wake_futex_pi(uaddr, uval, pi_state);
put_pi_state(pi_state);
irqd_clr_managed_shutdown(d);
- if (cpumask_any_and(aff, cpu_online_mask) > nr_cpu_ids) {
+ if (cpumask_any_and(aff, cpu_online_mask) >= nr_cpu_ids) {
/*
* Catch code which fiddles with enable_irq() on a managed
* and potentially shutdown IRQ. Chained interrupt
/* Calc pointer to the next generic chip */
tmp += sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
}
- d->name = name;
return 0;
}
EXPORT_SYMBOL_GPL(__irq_alloc_domain_generic_chips);
struct irq_desc *desc;
struct irq_domain *domain;
struct radix_tree_iter iter;
- void **slot;
+ void __rcu **slot;
int i;
seq_printf(m, " %-16s %-6s %-10s %-10s %s\n",
/* The irq_data was moved, fix the revmap to refer to the new location */
static void irq_domain_fix_revmap(struct irq_data *d)
{
- void **slot;
+ void __rcu **slot;
if (d->hwirq < d->domain->revmap_size)
return; /* Not using radix tree. */
#endif
action = __free_irq(irq, dev_id);
+
+ if (!action)
+ return NULL;
+
devname = action->name;
kfree(action);
return devname;
unsigned long flags;
DEFINE_WAKE_Q(wake_q);
+ /*
+ * __rwsem_down_write_failed_common(sem)
+ * rwsem_optimistic_spin(sem)
+ * osq_unlock(sem->osq)
+ * ...
+ * atomic_long_add_return(&sem->count)
+ *
+ * - VS -
+ *
+ * __up_write()
+ * if (atomic_long_sub_return_release(&sem->count) < 0)
+ * rwsem_wake(sem)
+ * osq_is_locked(&sem->osq)
+ *
+ * And __up_write() must observe !osq_is_locked() when it observes the
+ * atomic_long_add_return() in order to not miss a wakeup.
+ *
+ * This boils down to:
+ *
+ * [S.rel] X = 1 [RmW] r0 = (Y += 0)
+ * MB RMB
+ * [RmW] Y += 1 [L] r1 = X
+ *
+ * exists (r0=1 /\ r1=0)
+ */
+ smp_rmb();
+
/*
* If a spinner is present, it is not necessary to do the wakeup.
* Try to do wakeup only if the trylock succeeds to minimize
RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
rdtp->dynticks_nesting < 1);
if (rdtp->dynticks_nesting <= 1) {
RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
rdtp = this_cpu_ptr(&rcu_dynticks);
+
+ /* Page faults can happen in NMI handlers, so check... */
+ if (READ_ONCE(rdtp->dynticks_nmi_nesting))
+ return;
+
oldval = rdtp->dynticks_nesting;
rdtp->dynticks_nesting++;
WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
put_task_stack(p);
}
+static inline bool
+state_filter_match(unsigned long state_filter, struct task_struct *p)
+{
+ /* no filter, everything matches */
+ if (!state_filter)
+ return true;
+
+ /* filter, but doesn't match */
+ if (!(p->state & state_filter))
+ return false;
+
+ /*
+ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
+ * TASK_KILLABLE).
+ */
+ if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
+ return false;
+
+ return true;
+}
+
+
void show_state_filter(unsigned long state_filter)
{
struct task_struct *g, *p;
*/
touch_nmi_watchdog();
touch_all_softlockup_watchdogs();
- if (!state_filter || (p->state & state_filter))
+ if (state_filter_match(state_filter, p))
sched_show_task(p);
}
}
#endif
-static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
-
static void
print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
{
#include <linux/audit.h>
#include <linux/compat.h>
#include <linux/coredump.h>
+#include <linux/kmemleak.h>
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
#include <linux/seccomp.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
+#include <linux/sysctl.h>
#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER
#include <asm/syscall.h>
* get/put helpers should be used when accessing an instance
* outside of a lifetime-guarded section. In general, this
* is only needed for handling filters shared across tasks.
+ * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged
* @prev: points to a previously installed, or inherited, filter
* @prog: the BPF program to evaluate
*
*/
struct seccomp_filter {
refcount_t usage;
+ bool log;
struct seccomp_filter *prev;
struct bpf_prog *prog;
};
/**
* seccomp_run_filters - evaluates all seccomp filters against @sd
* @sd: optional seccomp data to be passed to filters
+ * @match: stores struct seccomp_filter that resulted in the return value,
+ * unless filter returned SECCOMP_RET_ALLOW, in which case it will
+ * be unchanged.
*
* Returns valid seccomp BPF response codes.
*/
-static u32 seccomp_run_filters(const struct seccomp_data *sd)
+#define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL)))
+static u32 seccomp_run_filters(const struct seccomp_data *sd,
+ struct seccomp_filter **match)
{
struct seccomp_data sd_local;
u32 ret = SECCOMP_RET_ALLOW;
/* Ensure unexpected behavior doesn't result in failing open. */
if (unlikely(WARN_ON(f == NULL)))
- return SECCOMP_RET_KILL;
+ return SECCOMP_RET_KILL_PROCESS;
if (!sd) {
populate_seccomp_data(&sd_local);
for (; f; f = f->prev) {
u32 cur_ret = BPF_PROG_RUN(f->prog, sd);
- if ((cur_ret & SECCOMP_RET_ACTION) < (ret & SECCOMP_RET_ACTION))
+ if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) {
ret = cur_ret;
+ *match = f;
+ }
}
return ret;
}
return ret;
}
+ /* Set log flag, if present. */
+ if (flags & SECCOMP_FILTER_FLAG_LOG)
+ filter->log = true;
+
/*
* If there is an existing filter, make it the prev and don't drop its
* task reference.
return 0;
}
+void __get_seccomp_filter(struct seccomp_filter *filter)
+{
+ /* Reference count is bounded by the number of total processes. */
+ refcount_inc(&filter->usage);
+}
+
/* get_seccomp_filter - increments the reference count of the filter on @tsk */
void get_seccomp_filter(struct task_struct *tsk)
{
struct seccomp_filter *orig = tsk->seccomp.filter;
if (!orig)
return;
- /* Reference count is bounded by the number of total processes. */
- refcount_inc(&orig->usage);
+ __get_seccomp_filter(orig);
}
static inline void seccomp_filter_free(struct seccomp_filter *filter)
}
}
-/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
-void put_seccomp_filter(struct task_struct *tsk)
+static void __put_seccomp_filter(struct seccomp_filter *orig)
{
- struct seccomp_filter *orig = tsk->seccomp.filter;
/* Clean up single-reference branches iteratively. */
while (orig && refcount_dec_and_test(&orig->usage)) {
struct seccomp_filter *freeme = orig;
}
}
+/* put_seccomp_filter - decrements the ref count of tsk->seccomp.filter */
+void put_seccomp_filter(struct task_struct *tsk)
+{
+ __put_seccomp_filter(tsk->seccomp.filter);
+}
+
static void seccomp_init_siginfo(siginfo_t *info, int syscall, int reason)
{
memset(info, 0, sizeof(*info));
}
#endif /* CONFIG_SECCOMP_FILTER */
+/* For use with seccomp_actions_logged */
+#define SECCOMP_LOG_KILL_PROCESS (1 << 0)
+#define SECCOMP_LOG_KILL_THREAD (1 << 1)
+#define SECCOMP_LOG_TRAP (1 << 2)
+#define SECCOMP_LOG_ERRNO (1 << 3)
+#define SECCOMP_LOG_TRACE (1 << 4)
+#define SECCOMP_LOG_LOG (1 << 5)
+#define SECCOMP_LOG_ALLOW (1 << 6)
+
+static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS |
+ SECCOMP_LOG_KILL_THREAD |
+ SECCOMP_LOG_TRAP |
+ SECCOMP_LOG_ERRNO |
+ SECCOMP_LOG_TRACE |
+ SECCOMP_LOG_LOG;
+
+static inline void seccomp_log(unsigned long syscall, long signr, u32 action,
+ bool requested)
+{
+ bool log = false;
+
+ switch (action) {
+ case SECCOMP_RET_ALLOW:
+ break;
+ case SECCOMP_RET_TRAP:
+ log = requested && seccomp_actions_logged & SECCOMP_LOG_TRAP;
+ break;
+ case SECCOMP_RET_ERRNO:
+ log = requested && seccomp_actions_logged & SECCOMP_LOG_ERRNO;
+ break;
+ case SECCOMP_RET_TRACE:
+ log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE;
+ break;
+ case SECCOMP_RET_LOG:
+ log = seccomp_actions_logged & SECCOMP_LOG_LOG;
+ break;
+ case SECCOMP_RET_KILL_THREAD:
+ log = seccomp_actions_logged & SECCOMP_LOG_KILL_THREAD;
+ break;
+ case SECCOMP_RET_KILL_PROCESS:
+ default:
+ log = seccomp_actions_logged & SECCOMP_LOG_KILL_PROCESS;
+ }
+
+ /*
+ * Force an audit message to be emitted when the action is RET_KILL_*,
+ * RET_LOG, or the FILTER_FLAG_LOG bit was set and the action is
+ * allowed to be logged by the admin.
+ */
+ if (log)
+ return __audit_seccomp(syscall, signr, action);
+
+ /*
+ * Let the audit subsystem decide if the action should be audited based
+ * on whether the current task itself is being audited.
+ */
+ return audit_seccomp(syscall, signr, action);
+}
+
/*
* Secure computing mode 1 allows only read/write/exit/sigreturn.
* To be fully secure this must be combined with rlimit
#ifdef SECCOMP_DEBUG
dump_stack();
#endif
- audit_seccomp(this_syscall, SIGKILL, SECCOMP_RET_KILL);
+ seccomp_log(this_syscall, SIGKILL, SECCOMP_RET_KILL_THREAD, true);
do_exit(SIGKILL);
}
const bool recheck_after_trace)
{
u32 filter_ret, action;
+ struct seccomp_filter *match = NULL;
int data;
/*
*/
rmb();
- filter_ret = seccomp_run_filters(sd);
+ filter_ret = seccomp_run_filters(sd, &match);
data = filter_ret & SECCOMP_RET_DATA;
- action = filter_ret & SECCOMP_RET_ACTION;
+ action = filter_ret & SECCOMP_RET_ACTION_FULL;
switch (action) {
case SECCOMP_RET_ERRNO:
return 0;
+ case SECCOMP_RET_LOG:
+ seccomp_log(this_syscall, 0, action, true);
+ return 0;
+
case SECCOMP_RET_ALLOW:
+ /*
+ * Note that the "match" filter will always be NULL for
+ * this action since SECCOMP_RET_ALLOW is the starting
+ * state in seccomp_run_filters().
+ */
return 0;
- case SECCOMP_RET_KILL:
+ case SECCOMP_RET_KILL_THREAD:
+ case SECCOMP_RET_KILL_PROCESS:
default:
- audit_seccomp(this_syscall, SIGSYS, action);
+ seccomp_log(this_syscall, SIGSYS, action, true);
/* Dump core only if this is the last remaining thread. */
- if (get_nr_threads(current) == 1) {
+ if (action == SECCOMP_RET_KILL_PROCESS ||
+ get_nr_threads(current) == 1) {
siginfo_t info;
/* Show the original registers in the dump. */
seccomp_init_siginfo(&info, this_syscall, data);
do_coredump(&info);
}
- do_exit(SIGSYS);
+ if (action == SECCOMP_RET_KILL_PROCESS)
+ do_group_exit(SIGSYS);
+ else
+ do_exit(SIGSYS);
}
unreachable();
skip:
- audit_seccomp(this_syscall, 0, action);
+ seccomp_log(this_syscall, 0, action, match ? match->log : false);
return -1;
}
#else
}
#endif
+static long seccomp_get_action_avail(const char __user *uaction)
+{
+ u32 action;
+
+ if (copy_from_user(&action, uaction, sizeof(action)))
+ return -EFAULT;
+
+ switch (action) {
+ case SECCOMP_RET_KILL_PROCESS:
+ case SECCOMP_RET_KILL_THREAD:
+ case SECCOMP_RET_TRAP:
+ case SECCOMP_RET_ERRNO:
+ case SECCOMP_RET_TRACE:
+ case SECCOMP_RET_LOG:
+ case SECCOMP_RET_ALLOW:
+ break;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return 0;
+}
+
/* Common entry point for both prctl and syscall. */
static long do_seccomp(unsigned int op, unsigned int flags,
const char __user *uargs)
return seccomp_set_mode_strict();
case SECCOMP_SET_MODE_FILTER:
return seccomp_set_mode_filter(flags, uargs);
+ case SECCOMP_GET_ACTION_AVAIL:
+ if (flags != 0)
+ return -EINVAL;
+
+ return seccomp_get_action_avail(uargs);
default:
return -EINVAL;
}
if (!data)
goto out;
- get_seccomp_filter(task);
+ __get_seccomp_filter(filter);
spin_unlock_irq(&task->sighand->siglock);
if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
ret = -EFAULT;
- put_seccomp_filter(task);
+ __put_seccomp_filter(filter);
return ret;
out:
return ret;
}
#endif
+
+#ifdef CONFIG_SYSCTL
+
+/* Human readable action names for friendly sysctl interaction */
+#define SECCOMP_RET_KILL_PROCESS_NAME "kill_process"
+#define SECCOMP_RET_KILL_THREAD_NAME "kill_thread"
+#define SECCOMP_RET_TRAP_NAME "trap"
+#define SECCOMP_RET_ERRNO_NAME "errno"
+#define SECCOMP_RET_TRACE_NAME "trace"
+#define SECCOMP_RET_LOG_NAME "log"
+#define SECCOMP_RET_ALLOW_NAME "allow"
+
+static const char seccomp_actions_avail[] =
+ SECCOMP_RET_KILL_PROCESS_NAME " "
+ SECCOMP_RET_KILL_THREAD_NAME " "
+ SECCOMP_RET_TRAP_NAME " "
+ SECCOMP_RET_ERRNO_NAME " "
+ SECCOMP_RET_TRACE_NAME " "
+ SECCOMP_RET_LOG_NAME " "
+ SECCOMP_RET_ALLOW_NAME;
+
+struct seccomp_log_name {
+ u32 log;
+ const char *name;
+};
+
+static const struct seccomp_log_name seccomp_log_names[] = {
+ { SECCOMP_LOG_KILL_PROCESS, SECCOMP_RET_KILL_PROCESS_NAME },
+ { SECCOMP_LOG_KILL_THREAD, SECCOMP_RET_KILL_THREAD_NAME },
+ { SECCOMP_LOG_TRAP, SECCOMP_RET_TRAP_NAME },
+ { SECCOMP_LOG_ERRNO, SECCOMP_RET_ERRNO_NAME },
+ { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME },
+ { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME },
+ { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME },
+ { }
+};
+
+static bool seccomp_names_from_actions_logged(char *names, size_t size,
+ u32 actions_logged)
+{
+ const struct seccomp_log_name *cur;
+ bool append_space = false;
+
+ for (cur = seccomp_log_names; cur->name && size; cur++) {
+ ssize_t ret;
+
+ if (!(actions_logged & cur->log))
+ continue;
+
+ if (append_space) {
+ ret = strscpy(names, " ", size);
+ if (ret < 0)
+ return false;
+
+ names += ret;
+ size -= ret;
+ } else
+ append_space = true;
+
+ ret = strscpy(names, cur->name, size);
+ if (ret < 0)
+ return false;
+
+ names += ret;
+ size -= ret;
+ }
+
+ return true;
+}
+
+static bool seccomp_action_logged_from_name(u32 *action_logged,
+ const char *name)
+{
+ const struct seccomp_log_name *cur;
+
+ for (cur = seccomp_log_names; cur->name; cur++) {
+ if (!strcmp(cur->name, name)) {
+ *action_logged = cur->log;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static bool seccomp_actions_logged_from_names(u32 *actions_logged, char *names)
+{
+ char *name;
+
+ *actions_logged = 0;
+ while ((name = strsep(&names, " ")) && *name) {
+ u32 action_logged = 0;
+
+ if (!seccomp_action_logged_from_name(&action_logged, name))
+ return false;
+
+ *actions_logged |= action_logged;
+ }
+
+ return true;
+}
+
+static int seccomp_actions_logged_handler(struct ctl_table *ro_table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ char names[sizeof(seccomp_actions_avail)];
+ struct ctl_table table;
+ int ret;
+
+ if (write && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ memset(names, 0, sizeof(names));
+
+ if (!write) {
+ if (!seccomp_names_from_actions_logged(names, sizeof(names),
+ seccomp_actions_logged))
+ return -EINVAL;
+ }
+
+ table = *ro_table;
+ table.data = names;
+ table.maxlen = sizeof(names);
+ ret = proc_dostring(&table, write, buffer, lenp, ppos);
+ if (ret)
+ return ret;
+
+ if (write) {
+ u32 actions_logged;
+
+ if (!seccomp_actions_logged_from_names(&actions_logged,
+ table.data))
+ return -EINVAL;
+
+ if (actions_logged & SECCOMP_LOG_ALLOW)
+ return -EINVAL;
+
+ seccomp_actions_logged = actions_logged;
+ }
+
+ return 0;
+}
+
+static struct ctl_path seccomp_sysctl_path[] = {
+ { .procname = "kernel", },
+ { .procname = "seccomp", },
+ { }
+};
+
+static struct ctl_table seccomp_sysctl_table[] = {
+ {
+ .procname = "actions_avail",
+ .data = (void *) &seccomp_actions_avail,
+ .maxlen = sizeof(seccomp_actions_avail),
+ .mode = 0444,
+ .proc_handler = proc_dostring,
+ },
+ {
+ .procname = "actions_logged",
+ .mode = 0644,
+ .proc_handler = seccomp_actions_logged_handler,
+ },
+ { }
+};
+
+static int __init seccomp_sysctl_init(void)
+{
+ struct ctl_table_header *hdr;
+
+ hdr = register_sysctl_paths(seccomp_sysctl_path, seccomp_sysctl_table);
+ if (!hdr)
+ pr_warn("seccomp: sysctl registration failed\n");
+ else
+ kmemleak_not_leak(hdr);
+
+ return 0;
+}
+
+device_initcall(seccomp_sysctl_init)
+
+#endif /* CONFIG_SYSCTL */
.data = &sysctl_sched_time_avg,
.maxlen = sizeof(unsigned int),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &one,
},
#ifdef CONFIG_SCHEDSTATS
{
}
EXPORT_SYMBOL_GPL(blk_trace_startstop);
+/*
+ * When reading or writing the blktrace sysfs files, the references to the
+ * opened sysfs or device files should prevent the underlying block device
+ * from being removed. So no further delete protection is really needed.
+ */
+
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
* @bdev: the block device
if (!q)
return -ENXIO;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
switch (cmd) {
case BLKTRACESETUP:
break;
}
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
return ret;
}
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
if (attr == &dev_attr_enable) {
ret = sprintf(buf, "%u\n", !!q->blk_trace);
ret = sprintf(buf, "%llu\n", q->blk_trace->end_lba);
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
if (q == NULL)
goto out_bdput;
- mutex_lock(&bdev->bd_mutex);
+ mutex_lock(&q->blk_trace_mutex);
if (attr == &dev_attr_enable) {
if (value)
}
out_unlock_bdev:
- mutex_unlock(&bdev->bd_mutex);
+ mutex_unlock(&q->blk_trace_mutex);
out_bdput:
bdput(bdev);
out:
/* If this file was open for write, then erase contents */
if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
int cpu = tracing_get_cpu(inode);
+ struct trace_buffer *trace_buf = &tr->trace_buffer;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+ if (tr->current_trace->print_max)
+ trace_buf = &tr->max_buffer;
+#endif
if (cpu == RING_BUFFER_ALL_CPUS)
- tracing_reset_online_cpus(&tr->trace_buffer);
+ tracing_reset_online_cpus(trace_buf);
else
- tracing_reset(&tr->trace_buffer, cpu);
+ tracing_reset(trace_buf, cpu);
}
if (file->f_mode & FMODE_READ) {
if (t == tr->current_trace)
goto out;
+ /* Some tracers won't work on kernel command line */
+ if (system_state < SYSTEM_RUNNING && t->noboot) {
+ pr_warn("Tracer '%s' is not allowed on command line, ignored\n",
+ t->name);
+ goto out;
+ }
+
/* Some tracers are only allowed for the top level buffer */
if (!trace_ok_for_array(t, tr)) {
ret = -EINVAL;
*
* iter->pos will be 0 if we haven't read anything.
*/
- if (!tracing_is_on() && iter->pos)
+ if (!tracer_tracing_is_on(iter->tr) && iter->pos)
break;
mutex_unlock(&iter->mutex);
#ifdef CONFIG_TRACER_MAX_TRACE
bool use_max_tr;
#endif
+ /* True if tracer cannot be enabled in kernel param */
+ bool noboot;
};
.close = mmio_close,
.read = mmio_read,
.print_line = mmio_print_line,
+ .noboot = true,
};
__init static int init_mmio_trace(void)
return !trace_seq_has_overflowed(s);
}
-static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
-
-static int task_state_char(unsigned long state)
-{
- int bit = state ? __ffs(state) + 1 : 0;
-
- return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
-}
-
/**
* ftrace_find_event - find a registered event
* @type: the type of event to look for
trace_assign_type(field, iter->ent);
- T = task_state_char(field->next_state);
- S = task_state_char(field->prev_state);
+ T = __task_state_to_char(field->next_state);
+ S = __task_state_to_char(field->prev_state);
trace_find_cmdline(field->next_pid, comm);
trace_seq_printf(&iter->seq,
" %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n",
trace_assign_type(field, iter->ent);
if (!S)
- S = task_state_char(field->prev_state);
- T = task_state_char(field->next_state);
+ S = __task_state_to_char(field->prev_state);
+ T = __task_state_to_char(field->next_state);
trace_seq_printf(&iter->seq, "%d %d %c %d %d %d %c\n",
field->prev_pid,
field->prev_prio,
trace_assign_type(field, iter->ent);
if (!S)
- S = task_state_char(field->prev_state);
- T = task_state_char(field->next_state);
+ S = __task_state_to_char(field->prev_state);
+ T = __task_state_to_char(field->next_state);
SEQ_PUT_HEX_FIELD(s, field->prev_pid);
SEQ_PUT_HEX_FIELD(s, field->prev_prio);
entry = ring_buffer_event_data(event);
entry->prev_pid = prev->pid;
entry->prev_prio = prev->prio;
- entry->prev_state = prev->state;
+ entry->prev_state = __get_task_state(prev);
entry->next_pid = next->pid;
entry->next_prio = next->prio;
- entry->next_state = next->state;
+ entry->next_state = __get_task_state(next);
entry->next_cpu = task_cpu(next);
if (!call_filter_check_discard(call, entry, buffer, event))
entry = ring_buffer_event_data(event);
entry->prev_pid = curr->pid;
entry->prev_prio = curr->prio;
- entry->prev_state = curr->state;
+ entry->prev_state = __get_task_state(curr);
entry->next_pid = wakee->pid;
entry->next_prio = wakee->prio;
- entry->next_state = wakee->state;
+ entry->next_state = __get_task_state(wakee);
entry->next_cpu = task_cpu(wakee);
if (!call_filter_check_discard(call, entry, buffer, event))
if (in_nmi())
return;
- /*
- * There's a slight chance that we are tracing inside the
- * RCU infrastructure, and rcu_irq_enter() will not work
- * as expected.
- */
- if (unlikely(rcu_irq_enter_disabled()))
- return;
-
local_irq_save(flags);
arch_spin_lock(&stack_trace_max_lock);
- /*
- * RCU may not be watching, make it see us.
- * The stack trace code uses rcu_sched.
- */
- rcu_irq_enter();
-
/* In case another CPU set the tracer_frame on us */
if (unlikely(!frame_size))
this_size -= tracer_frame;
}
out:
- rcu_irq_exit();
arch_spin_unlock(&stack_trace_max_lock);
local_irq_restore(flags);
}
range 0 8192
default 0 if KASAN
default 2048 if GCC_PLUGIN_LATENT_ENTROPY
- default 1024 if !64BIT
+ default 1280 if (!64BIT && PARISC)
+ default 1024 if (!64BIT && !PARISC)
default 2048 if 64BIT
help
Tell gcc to warn at build time for stack frames larger than this.
static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
{
- size_t v = n + offset;
- if (likely(n <= v && v <= (PAGE_SIZE << compound_order(page))))
+ struct page *head = compound_head(page);
+ size_t v = n + offset + page_address(page) - page_address(head);
+
+ if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
return true;
WARN_ON(1);
return false;
* rhashtable_walk_start - Start a hash table walk
* @iter: Hash table iterator
*
- * Start a hash table walk. Note that we take the RCU lock in all
- * cases including when we return an error. So you must always call
- * rhashtable_walk_stop to clean up.
+ * Start a hash table walk at the current iterator position. Note that we take
+ * the RCU lock in all cases including when we return an error. So you must
+ * always call rhashtable_walk_stop to clean up.
*
* Returns zero if successful.
*
* rhashtable_walk_stop - Finish a hash table walk
* @iter: Hash table iterator
*
- * Finish a hash table walk.
+ * Finish a hash table walk. Does not reset the iterator to the start of the
+ * hash table.
*/
void rhashtable_walk_stop(struct rhashtable_iter *iter)
__releases(RCU)
* we're writing. Either one is a pretty crazy thing to do,
* so we don't support it 100%. If this invalidation
* fails, tough, the write still worked...
+ *
+ * Most of the time we do not need this since dio_complete() will do
+ * the invalidation for us. However there are some file systems that
+ * do not end up with dio_complete() being called, so let's not break
+ * them by removing it completely
*/
- invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
+ if (mapping->nrpages)
+ invalidate_inode_pages2_range(mapping,
+ pos >> PAGE_SHIFT, end);
if (written > 0) {
pos += written;
Provide extensive information about internal Bluetooth states
in debugfs.
-config BT_LEGACY_IOCTL
- bool "Enable legacy ioctl interfaces"
- depends on BT && BT_BREDR
- default y
- help
- Enable support for legacy ioctl interfaces. This is only needed
- for old and deprecated applications using direct ioctl calls for
- controller management. Since Linux 3.4 all configuration and
- setup is done via mgmt interface and this is no longer needed.
-
source "drivers/bluetooth/Kconfig"
return 0;
}
-#ifdef CONFIG_BT_LEGACY_IOCTL
static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg)
{
bdaddr_t bdaddr;
release_sock(sk);
return err;
}
-#endif
static int hci_sock_bind(struct socket *sock, struct sockaddr *addr,
int addr_len)
.getname = hci_sock_getname,
.sendmsg = hci_sock_sendmsg,
.recvmsg = hci_sock_recvmsg,
-#ifdef CONFIG_BT_LEGACY_IOCTL
.ioctl = hci_sock_ioctl,
-#else
- .ioctl = sock_no_ioctl,
-#endif
.poll = datagram_poll,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid);
if (pg) {
- for (i = 0; i < raw->size; i++) {
- for (j = 0; j < pg->pg_upmap_items.len; j++) {
- int from = pg->pg_upmap_items.from_to[j][0];
- int to = pg->pg_upmap_items.from_to[j][1];
-
- if (from == raw->osds[i]) {
- if (!(to != CRUSH_ITEM_NONE &&
- to < osdmap->max_osd &&
- osdmap->osd_weight[to] == 0))
- raw->osds[i] = to;
+ /*
+ * Note: this approach does not allow a bidirectional swap,
+ * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1].
+ */
+ for (i = 0; i < pg->pg_upmap_items.len; i++) {
+ int from = pg->pg_upmap_items.from_to[i][0];
+ int to = pg->pg_upmap_items.from_to[i][1];
+ int pos = -1;
+ bool exists = false;
+
+ /* make sure replacement doesn't already appear */
+ for (j = 0; j < raw->size; j++) {
+ int osd = raw->osds[j];
+
+ if (osd == to) {
+ exists = true;
break;
}
+ /* ignore mapping if target is marked out */
+ if (osd == from && pos < 0 &&
+ !(to != CRUSH_ITEM_NONE &&
+ to < osdmap->max_osd &&
+ osdmap->osd_weight[to] == 0)) {
+ pos = j;
+ }
}
+ if (!exists && pos >= 0)
+ raw->osds[pos] = to;
}
}
}
ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen);
}
+ /*
+ * check the length of messages copied in is the same as the
+ * what we get from the first loop
+ */
+ if ((char *)kcmsg - (char *)kcmsg_base != kcmlen)
+ goto Einval;
+
/* Ok, looks like we made it. Hook it up and return success. */
kmsg->msg_control = kcmsg_base;
kmsg->msg_controllen = kcmlen;
goto again;
}
out_unlock:
- if (pt_prev)
- pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+ if (pt_prev) {
+ if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC))
+ pt_prev->func(skb2, skb->dev, pt_prev, skb->dev);
+ else
+ kfree_skb(skb2);
+ }
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(dev_queue_xmit_nit);
__skb_pull(skb, off);
else if (off < 0)
__skb_push(skb, -off);
+ skb->mac_header += off;
switch (act) {
case XDP_REDIRECT:
= link_ksettings->base.eth_tp_mdix;
legacy_settings->eth_tp_mdix_ctrl
= link_ksettings->base.eth_tp_mdix_ctrl;
+ legacy_settings->transceiver
+ = link_ksettings->base.transceiver;
return retval;
}
u32 flags;
struct bpf_map *map;
struct bpf_map *map_to_flush;
- const struct bpf_prog *map_owner;
+ unsigned long map_owner;
};
static DEFINE_PER_CPU(struct redirect_info, redirect_info);
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
+ unsigned long aux)
+{
+ return (unsigned long)xdp_prog->aux != aux;
+}
+
static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
- const struct bpf_prog *map_owner = ri->map_owner;
+ unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
ri->ifindex = 0;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
- if (unlikely(map_owner != xdp_prog)) {
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
err = -EFAULT;
map = NULL;
goto err;
struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
- const struct bpf_prog *map_owner = ri->map_owner;
+ unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
ri->ifindex = 0;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
if (map) {
- if (unlikely(map_owner != xdp_prog)) {
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
err = -EFAULT;
map = NULL;
goto err;
ri->ifindex = ifindex;
ri->flags = flags;
ri->map = NULL;
- ri->map_owner = NULL;
+ ri->map_owner = 0;
return XDP_REDIRECT;
}
};
BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
- const struct bpf_prog *, map_owner)
+ unsigned long, map_owner)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
#if IS_ENABLED(CONFIG_IPV6)
if (tb->fast_sk_family == AF_INET6)
return ipv6_rcv_saddr_equal(&tb->fast_v6_rcv_saddr,
- &sk->sk_v6_rcv_saddr,
+ inet6_rcv_saddr(sk),
tb->fast_rcv_saddr,
sk->sk_rcv_saddr,
tb->fast_ipv6_only,
goto fail_unlock;
}
success:
- if (!hlist_empty(&tb->owners)) {
+ if (hlist_empty(&tb->owners)) {
tb->fastreuse = reuse;
if (sk->sk_reuseport) {
tb->fastreuseport = FASTREUSEPORT_ANY;
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
tb->fastuid = uid;
tb->fast_rcv_saddr = sk->sk_rcv_saddr;
tb->fast_ipv6_only = ipv6_only_sock(sk);
+ tb->fast_sk_family = sk->sk_family;
#if IS_ENABLED(CONFIG_IPV6)
tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
#endif
return !after(end_seq, tcp_wnd_end(tp));
}
-/* This checks if the data bearing packet SKB (usually tcp_send_head(sk))
- * should be put on the wire right now. If so, it returns the number of
- * packets allowed by the congestion window.
- */
-static unsigned int tcp_snd_test(const struct sock *sk, struct sk_buff *skb,
- unsigned int cur_mss, int nonagle)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- unsigned int cwnd_quota;
-
- tcp_init_tso_segs(skb, cur_mss);
-
- if (!tcp_nagle_test(tp, skb, cur_mss, nonagle))
- return 0;
-
- cwnd_quota = tcp_cwnd_test(tp, skb);
- if (cwnd_quota && !tcp_snd_wnd_test(tp, skb, cur_mss))
- cwnd_quota = 0;
-
- return cwnd_quota;
-}
-
-/* Test if sending is allowed right now. */
-bool tcp_may_send_now(struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb = tcp_send_head(sk);
-
- return skb &&
- tcp_snd_test(sk, skb, tcp_current_mss(sk),
- (tcp_skb_is_last(sk, skb) ?
- tp->nonagle : TCP_NAGLE_PUSH));
-}
-
/* Trim TSO SKB to LEN bytes, put the remaining data into a new packet
* which is put after SKB on the list. It is very much like
* tcp_fragment() except that it may make several kinds of assumptions
goto done;
}
+ /* data was not sent, this is our new send_head */
+ sk->sk_send_head = syn_data;
+ tp->packets_out -= tcp_skb_pcount(syn_data);
+
fallback:
/* Send a regular SYN with Fast Open cookie request option */
if (fo->cookie.len > 0)
*/
tp->snd_nxt = tp->write_seq;
tp->pushed_seq = tp->write_seq;
+ buff = tcp_send_head(sk);
+ if (unlikely(buff)) {
+ tp->snd_nxt = TCP_SKB_CB(buff)->seq;
+ tp->pushed_seq = TCP_SKB_CB(buff)->seq;
+ }
TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
/* Timer for repeating the SYN until an answer. */
return 0;
}
-static inline bool ipv6_use_optimistic_addr(struct inet6_dev *idev)
+static bool ipv6_use_optimistic_addr(struct net *net,
+ struct inet6_dev *idev)
{
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- return idev && idev->cnf.optimistic_dad && idev->cnf.use_optimistic;
+ if (!idev)
+ return false;
+ if (!net->ipv6.devconf_all->optimistic_dad && !idev->cnf.optimistic_dad)
+ return false;
+ if (!net->ipv6.devconf_all->use_optimistic && !idev->cnf.use_optimistic)
+ return false;
+
+ return true;
#else
return false;
#endif
/* Rule 3: Avoid deprecated and optimistic addresses */
u8 avoid = IFA_F_DEPRECATED;
- if (!ipv6_use_optimistic_addr(score->ifa->idev))
+ if (!ipv6_use_optimistic_addr(net, score->ifa->idev))
avoid |= IFA_F_OPTIMISTIC;
ret = ipv6_saddr_preferred(score->addr_type) ||
!(score->ifa->flags & avoid);
int max_addresses = in6_dev->cnf.max_addresses;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (in6_dev->cnf.optimistic_dad &&
+ if ((net->ipv6.devconf_all->optimistic_dad ||
+ in6_dev->cnf.optimistic_dad) &&
!net->ipv6.devconf_all->forwarding && sllao)
addr_flags |= IFA_F_OPTIMISTIC;
#endif
u32 addr_flags = flags | IFA_F_PERMANENT;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
- if (idev->cnf.optimistic_dad &&
+ if ((dev_net(idev->dev)->ipv6.devconf_all->optimistic_dad ||
+ idev->cnf.optimistic_dad) &&
!dev_net(idev->dev)->ipv6.devconf_all->forwarding)
addr_flags |= IFA_F_OPTIMISTIC;
#endif
goto out;
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
+ dev_net(dev)->ipv6.devconf_all->accept_dad < 1 ||
idev->cnf.accept_dad < 1 ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
*/
if (ifp->flags & IFA_F_OPTIMISTIC) {
ip6_ins_rt(ifp->rt);
- if (ipv6_use_optimistic_addr(idev)) {
+ if (ipv6_use_optimistic_addr(dev_net(dev), idev)) {
/* Because optimistic nodes can use this address,
* notify listeners. If DAD fails, RTM_DELADDR is sent.
*/
action = DAD_ABORT;
ifp->state = INET6_IFADDR_STATE_POSTDAD;
- if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6 &&
+ if ((dev_net(idev->dev)->ipv6.devconf_all->accept_dad > 1 ||
+ idev->cnf.accept_dad > 1) &&
+ !idev->cnf.disable_ipv6 &&
!(ifp->flags & IFA_F_STABLE_PRIVACY)) {
struct in6_addr addr;
/* Don't send DELADDR notification for TENTATIVE address,
* since NEWADDR notification is sent only after removing
- * TENTATIVE flag.
+ * TENTATIVE flag, if DAD has not failed.
*/
- if (ifa->flags & IFA_F_TENTATIVE && event == RTM_DELADDR)
+ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) &&
+ event == RTM_DELADDR)
return;
skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC);
}
static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
- unsigned short type,
- const void *daddr, const void *saddr, unsigned int len)
+ unsigned short type, const void *daddr,
+ const void *saddr, unsigned int len)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct ipv6hdr *ipv6h = skb_push(skb, t->hlen);
- __be16 *p = (__be16 *)(ipv6h+1);
+ struct ipv6hdr *ipv6h;
+ __be16 *p;
- ip6_flow_hdr(ipv6h, 0,
- ip6_make_flowlabel(dev_net(dev), skb,
- t->fl.u.ip6.flowlabel, true,
- &t->fl.u.ip6));
+ ipv6h = skb_push(skb, t->hlen + sizeof(*ipv6h));
+ ip6_flow_hdr(ipv6h, 0, ip6_make_flowlabel(dev_net(dev), skb,
+ t->fl.u.ip6.flowlabel,
+ true, &t->fl.u.ip6));
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = NEXTHDR_GRE;
ipv6h->saddr = t->parms.laddr;
ipv6h->daddr = t->parms.raddr;
- p[0] = t->parms.o_flags;
- p[1] = htons(type);
+ p = (__be16 *)(ipv6h + 1);
+ p[0] = t->parms.o_flags;
+ p[1] = htons(type);
/*
* Set the source hardware address.
{
int err;
+ if (!ipv6_mod_enabled())
+ return -EOPNOTSUPP;
+
err = register_pernet_device(&ip6_tnl_net_ops);
if (err < 0)
goto out_pernet;
*/
offset = skb_transport_offset(skb);
skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+ csum = skb->csum;
skb->ip_summed = CHECKSUM_NONE;
static int
mtype_head(struct ip_set *set, struct sk_buff *skb)
{
- const struct htype *h = set->data;
+ struct htype *h = set->data;
const struct htable *t;
struct nlattr *nested;
size_t memsize;
u8 htable_bits;
+ /* If any members have expired, set->elements will be wrong
+ * mytype_expire function will update it with the right count.
+ * we do not hold set->lock here, so grab it first.
+ * set->elements can still be incorrect in the case of a huge set,
+ * because elements might time out during the listing.
+ */
+ if (SET_WITH_TIMEOUT(set)) {
+ spin_lock_bh(&set->lock);
+ mtype_expire(set, h);
+ spin_unlock_bh(&set->lock);
+ }
+
rcu_read_lock_bh();
t = rcu_dereference_bh_nfnl(h->table);
memsize = mtype_ahash_memsize(h, t) + set->ext_size;
srchash = hash_by_src(net,
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- lock = &nf_nat_locks[srchash % ARRAY_SIZE(nf_nat_locks)];
+ lock = &nf_nat_locks[srchash % CONNTRACK_LOCKS];
spin_lock_bh(lock);
hlist_add_head_rcu(&ct->nat_bysource,
&nf_nat_bysource[srchash]);
unsigned int h;
h = hash_by_src(nf_ct_net(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- spin_lock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+ spin_lock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
hlist_del_rcu(&ct->nat_bysource);
- spin_unlock_bh(&nf_nat_locks[h % ARRAY_SIZE(nf_nat_locks)]);
+ spin_unlock_bh(&nf_nat_locks[h % CONNTRACK_LOCKS]);
}
static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
/* Leave them the same for the moment. */
nf_nat_htable_size = nf_conntrack_htable_size;
- if (nf_nat_htable_size < ARRAY_SIZE(nf_nat_locks))
- nf_nat_htable_size = ARRAY_SIZE(nf_nat_locks);
+ if (nf_nat_htable_size < CONNTRACK_LOCKS)
+ nf_nat_htable_size = CONNTRACK_LOCKS;
nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
if (!nf_nat_bysource)
return ret;
}
- for (i = 0; i < ARRAY_SIZE(nf_nat_locks); i++)
+ for (i = 0; i < CONNTRACK_LOCKS; i++)
spin_lock_init(&nf_nat_locks[i]);
nf_ct_helper_expectfn_register(&follow_master_nat);
mutex_lock(&fanout_mutex);
- err = -EINVAL;
- if (!po->running)
- goto out;
-
err = -EALREADY;
if (po->fanout)
goto out;
list_add(&match->list, &fanout_list);
}
err = -EINVAL;
- if (match->type == type &&
+
+ spin_lock(&po->bind_lock);
+ if (po->running &&
+ match->type == type &&
match->prot_hook.type == po->prot_hook.type &&
match->prot_hook.dev == po->prot_hook.dev) {
err = -ENOSPC;
err = 0;
}
}
+ spin_unlock(&po->bind_lock);
+
+ if (err && !refcount_read(&match->sk_ref)) {
+ list_del(&match->list);
+ kfree(match);
+ }
+
out:
if (err && rollover) {
kfree(rollover);
if (!tc_flags_valid(fnew->flags)) {
err = -EINVAL;
- goto errout;
+ goto errout_idr;
}
}
err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
if (err)
- goto errout;
+ goto errout_idr;
err = fl_check_assign_mask(head, &mask);
if (err)
- goto errout;
+ goto errout_idr;
if (!tc_skip_sw(fnew->flags)) {
if (!fold && fl_lookup(head, &fnew->mkey)) {
err = -EEXIST;
- goto errout;
+ goto errout_idr;
}
err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
head->ht_params);
if (err)
- goto errout;
+ goto errout_idr;
}
if (!tc_skip_hw(fnew->flags)) {
&mask.key,
fnew);
if (err)
- goto errout;
+ goto errout_idr;
}
if (!tc_in_hw(fnew->flags))
kfree(tb);
return 0;
+errout_idr:
+ if (fnew->handle)
+ idr_remove_ext(&head->handle_idr, fnew->handle);
errout:
tcf_exts_destroy(&fnew->exts);
kfree(fnew);
if (tc_skip_sw(head->flags))
return -1;
+ *res = head->res;
return tcf_exts_exec(skb, &head->exts, res);
}
qdisc->gso_skb = NULL;
}
qdisc->q.qlen = 0;
+ qdisc->qstats.backlog = 0;
}
EXPORT_SYMBOL(qdisc_reset);
}
if (cl != NULL) {
+ int old_flags;
+
if (parentid) {
if (cl->cl_parent &&
cl->cl_parent->cl_common.classid != parentid)
}
sch_tree_lock(sch);
+ old_flags = cl->cl_flags;
+
if (rsc != NULL)
hfsc_change_rsc(cl, rsc, cur_time);
if (fsc != NULL)
hfsc_change_usc(cl, usc, cur_time);
if (cl->qdisc->q.qlen != 0) {
- if (cl->cl_flags & HFSC_RSC)
- update_ed(cl, qdisc_peek_len(cl->qdisc));
- if (cl->cl_flags & HFSC_FSC)
- update_vf(cl, 0, cur_time);
+ int len = qdisc_peek_len(cl->qdisc);
+
+ if (cl->cl_flags & HFSC_RSC) {
+ if (old_flags & HFSC_RSC)
+ update_ed(cl, len);
+ else
+ init_ed(cl, len);
+ }
+
+ if (cl->cl_flags & HFSC_FSC) {
+ if (old_flags & HFSC_FSC)
+ update_vf(cl, 0, cur_time);
+ else
+ init_vf(cl, len);
+ }
}
sch_tree_unlock(sch);
__be32 *subnet, u8 *prefix_len)
{
struct dst_entry *dst = sk_dst_get(clcsock->sk);
+ struct in_device *in_dev;
struct sockaddr_in addr;
int rc = -ENOENT;
int len;
/* get address to which the internal TCP socket is bound */
kernel_getsockname(clcsock, (struct sockaddr *)&addr, &len);
/* analyze IPv4 specific data of net_device belonging to TCP socket */
- for_ifa(dst->dev->ip_ptr) {
- if (ifa->ifa_address != addr.sin_addr.s_addr)
+ rcu_read_lock();
+ in_dev = __in_dev_get_rcu(dst->dev);
+ for_ifa(in_dev) {
+ if (!inet_ifa_match(addr.sin_addr.s_addr, ifa))
continue;
*prefix_len = inet_mask_len(ifa->ifa_mask);
*subnet = ifa->ifa_address & ifa->ifa_mask;
rc = 0;
break;
- } endfor_ifa(dst->dev->ip_ptr);
+ } endfor_ifa(in_dev);
+ rcu_read_unlock();
out_rel:
dst_release(dst);
/* RDMA setup failed, switch back to TCP */
smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(smc, reason_code, 0);
+ rc = smc_clc_send_decline(smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
rc = local_contact;
if (rc == -ENOMEM)
reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
- else if (rc == -ENOLINK)
- reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */
goto decline_rdma;
}
link = &new_smc->conn.lgr->lnk[SMC_SINGLE_LINK];
smc_conn_free(&new_smc->conn);
new_smc->use_fallback = true;
if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) {
- rc = smc_clc_send_decline(new_smc, reason_code, 0);
+ rc = smc_clc_send_decline(new_smc, reason_code);
if (rc < sizeof(struct smc_clc_msg_decline))
goto out_err;
}
atomic_t sndbuf_space; /* remaining space in sndbuf */
u16 tx_cdc_seq; /* sequence # for CDC send */
spinlock_t send_lock; /* protect wr_sends */
- struct work_struct tx_work; /* retry of smc_cdc_msg_send */
+ struct delayed_work tx_work; /* retry of smc_cdc_msg_send */
struct smc_host_cdc_msg local_rx_ctrl; /* filled during event_handl.
* .prod cf. TCP rcv_nxt
}
if (clcm->type == SMC_CLC_DECLINE) {
reason_code = SMC_CLC_DECL_REPLY;
- if (ntohl(((struct smc_clc_msg_decline *)buf)->peer_diagnosis)
- == SMC_CLC_DECL_SYNCERR)
+ if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
smc->conn.lgr->sync_err = true;
+ smc_lgr_terminate(smc->conn.lgr);
+ }
}
out:
}
/* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
{
struct smc_clc_msg_decline dclc;
struct msghdr msg;
dclc.hdr.type = SMC_CLC_DECLINE;
dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
dclc.hdr.version = SMC_CLC_V1;
- dclc.hdr.flag = out_of_sync ? 1 : 0;
+ dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid));
dclc.peer_diagnosis = htonl(peer_diag_info);
memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
u8 expected_type);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info,
- u8 out_of_sync);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
u8 ibport);
int smc_clc_send_confirm(struct smc_sock *smc);
{
struct smc_cdc_conn_state_flags *txflags =
&smc->conn.local_tx_ctrl.conn_state_flags;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct smc_connection *conn = &smc->conn;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER) &&
- !(current->flags & PF_EXITING))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_state == SMC_ACTIVE) {
/* send close request */
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
if (sk->sk_err != ECONNABORTED) {
/* confirm close from peer */
/* peer sending PeerConnectionClosed will cause transition */
break;
case SMC_PROCESSABORT:
- cancel_work_sync(&conn->tx_work);
+ release_sock(sk);
+ cancel_delayed_work_sync(&conn->tx_work);
+ lock_sock(sk);
smc_close_abort(conn);
sk->sk_state = SMC_CLOSED;
smc_close_wait_tx_pends(smc);
int smc_close_shutdown_write(struct smc_sock *smc)
{
struct smc_connection *conn = &smc->conn;
- long timeout = SMC_MAX_STREAM_WAIT_TIMEOUT;
struct sock *sk = &smc->sk;
int old_state;
+ long timeout;
int rc = 0;
- if (sock_flag(sk, SOCK_LINGER))
- timeout = sk->sk_lingertime;
+ timeout = current->flags & PF_EXITING ?
+ 0 : sock_flag(sk, SOCK_LINGER) ?
+ sk->sk_lingertime : SMC_MAX_STREAM_WAIT_TIMEOUT;
again:
old_state = sk->sk_state;
case SMC_ACTIVE:
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* send close wr request */
rc = smc_close_wr(conn);
if (!smc_cdc_rxed_any_close(conn))
smc_close_stream_wait(smc, timeout);
release_sock(sk);
- cancel_work_sync(&conn->tx_work);
+ cancel_delayed_work_sync(&conn->tx_work);
lock_sock(sk);
/* confirm close from peer */
rc = smc_close_wr(conn);
#include "smc_cdc.h"
#include "smc_close.h"
-#define SMC_LGR_NUM_INCR 256
-#define SMC_LGR_FREE_DELAY (600 * HZ)
+#define SMC_LGR_NUM_INCR 256
+#define SMC_LGR_FREE_DELAY_SERV (600 * HZ)
+#define SMC_LGR_FREE_DELAY_CLNT (SMC_LGR_FREE_DELAY_SERV + 10)
static u32 smc_lgr_num; /* unique link group number */
__smc_lgr_unregister_conn(conn);
}
write_unlock_bh(&lgr->conns_lock);
- if (reduced && !lgr->conns_num)
- schedule_delayed_work(&lgr->free_work, SMC_LGR_FREE_DELAY);
+ if (!reduced || lgr->conns_num)
+ return;
+ /* client link group creation always follows the server link group
+ * creation. For client use a somewhat higher removal delay time,
+ * otherwise there is a risk of out-of-sync link groups.
+ */
+ mod_delayed_work(system_wq, &lgr->free_work,
+ lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
+ SMC_LGR_FREE_DELAY_SERV);
}
static void smc_lgr_free_work(struct work_struct *work)
ndev = smcibdev->ibdev->get_netdev(smcibdev->ibdev, ibport);
if (ndev) {
memcpy(&smcibdev->mac, ndev->dev_addr, ETH_ALEN);
+ dev_put(ndev);
} else if (!rc) {
memcpy(&smcibdev->mac[ibport - 1][0],
&smcibdev->gid[ibport - 1].raw[8], 3);
sizeof(new_pnetelem->ndev->name)) ||
smc_pnet_same_ibname(pnetelem,
new_pnetelem->smcibdev->ibdev->name,
- new_pnetelem->ib_port))
+ new_pnetelem->ib_port)) {
+ dev_put(pnetelem->ndev);
goto found;
+ }
}
list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist);
rc = 0;
read_done = sock_intr_errno(timeo);
break;
}
+ if (!timeo)
+ return -EAGAIN;
}
if (!atomic_read(&conn->bytes_to_rcv)) {
#include "smc_cdc.h"
#include "smc_tx.h"
+#define SMC_TX_WORK_DELAY HZ
+
/***************************** sndbuf producer *******************************/
/* callback implementation for sk.sk_write_space()
goto out_unlock;
}
rc = 0;
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
}
goto out_unlock;
}
*/
static void smc_tx_work(struct work_struct *work)
{
- struct smc_connection *conn = container_of(work,
+ struct smc_connection *conn = container_of(to_delayed_work(work),
struct smc_connection,
tx_work);
struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
if (!rc)
rc = smc_cdc_msg_send(conn, wr_buf, pend);
if (rc < 0) {
- schedule_work(&conn->tx_work);
+ schedule_delayed_work(&conn->tx_work,
+ SMC_TX_WORK_DELAY);
return;
}
smc_curs_write(&conn->rx_curs_confirmed,
void smc_tx_init(struct smc_sock *smc)
{
smc->sk.sk_write_space = smc_tx_write_space;
- INIT_WORK(&smc->conn.tx_work, smc_tx_work);
+ INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
spin_lock_init(&smc->conn.send_lock);
}
int rc;
ib_req_notify_cq(link->smcibdev->roce_cq_send,
- IB_CQ_SOLICITED_MASK | IB_CQ_REPORT_MISSED_EVENTS);
+ IB_CQ_NEXT_COMP | IB_CQ_REPORT_MISSED_EVENTS);
pend = container_of(priv, struct smc_wr_tx_pend, priv);
rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
&failed_wr);
if (unlikely(n != mw->mw_nents))
goto out_mapmr_err;
- dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n",
+ dprintk("RPC: %s: Using frmr %p to map %u segments (%llu bytes)\n",
__func__, frmr, mw->mw_nents, mr->length);
key = (u8)(mr->rkey & 0x000000FF);
if (err)
return err;
+ if (!setup.chandef.chan)
+ return -EINVAL;
+
err = validate_beacon_tx_rate(rdev, setup.chandef.chan->band,
&setup.beacon_rate);
if (err)
if (err)
return err;
+ if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
+ !tb[NL80211_REKEY_DATA_KCK])
+ return -EINVAL;
if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
return -ERANGE;
if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN)
endif
ifdef CONFIG_GCOV_KERNEL
objtool_args += --no-unreachable
+else
+objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable)
endif
# 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
compile_to_dts() {
dtx="$1"
+ dtc_include="$2"
if [ -d "${dtx}" ] ; then
# ----- input is DTS (source)
if ( cpp ${cpp_flags} -x assembler-with-cpp ${dtx} \
- | ${DTC} -I dts ) ; then
+ | ${DTC} ${dtc_include} -I dts ) ; then
return
fi
cpp_flags="\
-nostdinc \
- -I${srctree}/arch/${ARCH}/boot/dts \
-I${srctree}/scripts/dtc/include-prefixes \
- -I${srctree}/drivers/of/testcase-data \
-undef -D__DTS__"
-dtc_flags="\
- -i ${srctree}/arch/${ARCH}/boot/dts/ \
- -i ${srctree}/kernel/dts \
- ${dtx_path_1_dtc_include} \
- ${dtx_path_2_dtc_include}"
-
-DTC="${DTC} ${dtc_flags} -O dts -qq -f ${dtc_sort} -o -"
+DTC="\
+ ${DTC} \
+ -i ${srctree}/scripts/dtc/include-prefixes \
+ -O dts -qq -f ${dtc_sort} -o -"
# ----- do the diff or decompile
if (( ${cmd_diff} )) ; then
diff ${diff_flags} --label "${dtx_file_1}" --label "${dtx_file_2}" \
- <(compile_to_dts "${dtx_file_1}") \
- <(compile_to_dts "${dtx_file_2}")
+ <(compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}") \
+ <(compile_to_dts "${dtx_file_2}" "${dtx_path_2_dtc_include}")
else
- compile_to_dts "${dtx_file_1}"
+ compile_to_dts "${dtx_file_1}" "${dtx_path_1_dtc_include}"
fi
+++ /dev/null
-if [ ! -f .version ]
-then
- echo 1
-else
- expr 0`cat .version` + 1
-fi
$(MAKE) clean
$(CONFIG_SHELL) $(MKSPEC) >$(objtree)/kernel.spec
$(call cmd,src_tar,$(KERNELPATH),kernel.spec)
- $(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
- mv -f $(objtree)/.tmp_version $(objtree)/.version
rpmbuild $(RPMOPTS) --target $(UTS_MACHINE) -ta $(KERNELPATH).tar.gz
rm $(KERNELPATH).tar.gz kernel.spec
binrpm-pkg: FORCE
$(MAKE) KBUILD_SRC=
$(CONFIG_SHELL) $(MKSPEC) prebuilt > $(objtree)/binkernel.spec
- $(CONFIG_SHELL) $(srctree)/scripts/mkversion > $(objtree)/.tmp_version
- mv -f $(objtree)/.tmp_version $(objtree)/.version
-
rpmbuild $(RPMOPTS) --define "_builddir $(objtree)" --target \
$(UTS_MACHINE) -bb $(objtree)/binkernel.spec
rm binkernel.spec
fi
sourcename=$KDEB_SOURCENAME
tmpdir="$objtree/debian/tmp"
-fwdir="$objtree/debian/fwtmp"
kernel_headers_dir="$objtree/debian/hdrtmp"
libc_headers_dir="$objtree/debian/headertmp"
dbg_dir="$objtree/debian/dbgtmp"
packagename=linux-image-$version
-fwpackagename=linux-firmware-image-$version
kernel_headers_packagename=linux-headers-$version
libc_headers_packagename=linux-libc-dev
dbg_packagename=$packagename-dbg
BUILD_DEBUG="$(grep -s '^CONFIG_DEBUG_INFO=y' $KCONFIG_CONFIG || true)"
# Setup the directory structure
-rm -rf "$tmpdir" "$fwdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files
+rm -rf "$tmpdir" "$kernel_headers_dir" "$libc_headers_dir" "$dbg_dir" $objtree/debian/files
mkdir -m 755 -p "$tmpdir/DEBIAN"
mkdir -p "$tmpdir/lib" "$tmpdir/boot"
-mkdir -p "$fwdir/lib/firmware/$version/"
mkdir -p "$kernel_headers_dir/lib/modules/$version/"
# Build and install the kernel
cat <<EOF >> debian/control
Package: $packagename
-Suggests: $fwpackagename
Architecture: any
Description: Linux kernel, version $version
This package contains the Linux kernel, modules and corresponding other
This is useful for people who need to build external modules
EOF
-# Do we have firmware? Move it out of the way and build it into a package.
-if [ -e "$tmpdir/lib/firmware" ]; then
- mv "$tmpdir/lib/firmware"/* "$fwdir/lib/firmware/$version/"
- rmdir "$tmpdir/lib/firmware"
-
- cat <<EOF >> debian/control
-
-Package: $fwpackagename
-Architecture: all
-Description: Linux kernel firmware, version $version
- This package contains firmware from the Linux kernel, version $version.
-EOF
-
- create_package "$fwpackagename" "$fwdir"
-fi
-
cat <<EOF >> debian/control
Package: $libc_headers_packagename
echo "Name: kernel"
echo "Summary: The Linux Kernel"
echo "Version: $__KERNELRELEASE"
-# we need to determine the NEXT version number so that uname and
-# rpm -q will agree
-echo "Release: `. $srctree/scripts/mkversion`"
+echo "Release: $(cat .version 2>/dev/null || echo 1)"
echo "License: GPL"
echo "Group: System Environment/Kernel"
echo "Vendor: The Linux Community"
echo "%build"
if ! $PREBUILT; then
-echo "make clean && make %{?_smp_mflags}"
+echo "make clean && make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release}"
echo ""
fi
echo "%else"
echo 'mkdir -p $RPM_BUILD_ROOT/boot $RPM_BUILD_ROOT/lib/modules'
echo "%endif"
-echo 'mkdir -p $RPM_BUILD_ROOT'"/lib/firmware/$KERNELRELEASE"
-echo 'INSTALL_MOD_PATH=$RPM_BUILD_ROOT make %{?_smp_mflags} KBUILD_SRC= mod-fw= modules_install'
-echo 'INSTALL_FW_PATH=$RPM_BUILD_ROOT'"/lib/firmware/$KERNELRELEASE"
-echo 'make INSTALL_FW_PATH=$INSTALL_FW_PATH' firmware_install
+echo 'INSTALL_MOD_PATH=$RPM_BUILD_ROOT make %{?_smp_mflags} KBUILD_SRC= modules_install'
echo "%ifarch ia64"
echo 'cp $KBUILD_IMAGE $RPM_BUILD_ROOT'"/boot/efi/vmlinuz-$KERNELRELEASE"
echo 'ln -s '"efi/vmlinuz-$KERNELRELEASE" '$RPM_BUILD_ROOT'"/boot/"
echo 'rm -f $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE/build"
echo 'rm -f $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE/source"
echo "mkdir -p "'$RPM_BUILD_ROOT'"/usr/src/kernels/$KERNELRELEASE"
-echo "EXCLUDES=\"$RCS_TAR_IGNORE --exclude .tmp_versions --exclude=*vmlinux* --exclude=*.o --exclude=*.ko --exclude=*.cmd --exclude=Documentation --exclude=firmware --exclude .config.old --exclude .missing-syscalls.d\""
+echo "EXCLUDES=\"$RCS_TAR_IGNORE --exclude .tmp_versions --exclude=*vmlinux* --exclude=*.o --exclude=*.ko --exclude=*.cmd --exclude=Documentation --exclude .config.old --exclude .missing-syscalls.d\""
echo "tar "'$EXCLUDES'" -cf- . | (cd "'$RPM_BUILD_ROOT'"/usr/src/kernels/$KERNELRELEASE;tar xvf -)"
echo 'cd $RPM_BUILD_ROOT'"/lib/modules/$KERNELRELEASE"
echo "ln -sf /usr/src/kernels/$KERNELRELEASE build"
echo "/lib/modules/$KERNELRELEASE"
echo "%exclude /lib/modules/$KERNELRELEASE/build"
echo "%exclude /lib/modules/$KERNELRELEASE/source"
-echo "/lib/firmware/$KERNELRELEASE"
echo "/boot/*"
echo ""
echo "%files headers"
#
# Generated include files
#
+net_names.h
capability_names.h
rlim_names.h
apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \
path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \
- resource.o secid.o file.o policy_ns.o label.o
+ resource.o secid.o file.o policy_ns.o label.o mount.o net.o
apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o
-clean-files := capability_names.h rlim_names.h
+clean-files := capability_names.h rlim_names.h net_names.h
+# Build a lower case string table of address family names
+# Transform lines from
+# #define AF_LOCAL 1 /* POSIX name for AF_UNIX */
+# #define AF_INET 2 /* Internet IP Protocol */
+# to
+# [1] = "local",
+# [2] = "inet",
+#
+# and build the securityfs entries for the mapping.
+# Transforms lines from
+# #define AF_INET 2 /* Internet IP Protocol */
+# to
+# #define AA_SFS_AF_MASK "local inet"
+quiet_cmd_make-af = GEN $@
+cmd_make-af = echo "static const char *address_family_names[] = {" > $@ ;\
+ sed $< >>$@ -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+ 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+ echo "};" >> $@ ;\
+ printf '%s' '\#define AA_SFS_AF_MASK "' >> $@ ;\
+ sed -r -n -e "/AF_MAX/d" -e "/AF_LOCAL/d" -e "/AF_ROUTE/d" -e \
+ 's/^\#define[ \t]+AF_([A-Z0-9_]+)[ \t]+([0-9]+)(.*)/\L\1/p'\
+ $< | tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+# Build a lower case string table of sock type names
+# Transform lines from
+# SOCK_STREAM = 1,
+# to
+# [1] = "stream",
+quiet_cmd_make-sock = GEN $@
+cmd_make-sock = echo "static const char *sock_type_names[] = {" >> $@ ;\
+ sed $^ >>$@ -r -n \
+ -e 's/^\tSOCK_([A-Z0-9_]+)[\t]+=[ \t]+([0-9]+)(.*)/[\2] = "\L\1",/p';\
+ echo "};" >> $@
# Build a lower case string table of capability names
# Transforms lines from
tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
$(obj)/capability.o : $(obj)/capability_names.h
+$(obj)/net.o : $(obj)/net_names.h
$(obj)/resource.o : $(obj)/rlim_names.h
$(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \
$(src)/Makefile
$(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \
$(src)/Makefile
$(call cmd,make-rlim)
+$(obj)/net_names.h : $(srctree)/include/linux/socket.h \
+ $(srctree)/include/linux/net.h \
+ $(src)/Makefile
+ $(call cmd,make-af)
+ $(call cmd,make-sock)
#include "include/audit.h"
#include "include/context.h"
#include "include/crypto.h"
+#include "include/ipc.h"
#include "include/policy_ns.h"
#include "include/label.h"
#include "include/policy.h"
inode_lock(dir);
dentry = lookup_one_len(name, parent, strlen(name));
- if (IS_ERR(dentry))
+ if (IS_ERR(dentry)) {
+ error = PTR_ERR(dentry);
goto fail_lock;
+ }
if (d_really_is_positive(dentry)) {
error = -EEXIST;
{
int i;
+ AA_BUG(!old);
+ AA_BUG(!new);
+ AA_BUG(!mutex_is_locked(&profiles_ns(old)->lock));
+
for (i = 0; i < AAFS_PROF_SIZEOF; i++) {
new->dents[i] = old->dents[i];
if (new->dents[i])
struct dentry *dent = NULL, *dir;
int error;
+ AA_BUG(!profile);
+ AA_BUG(!mutex_is_locked(&profiles_ns(profile)->lock));
+
if (!parent) {
struct aa_profile *p;
p = aa_deref_parent(profile);
if (!ns)
return;
+ AA_BUG(!mutex_is_locked(&ns->lock));
list_for_each_entry(child, &ns->base.profiles, base.list)
__aafs_profile_rmdir(child);
{
struct aa_ns *parent, *next;
+ AA_BUG(!root);
+ AA_BUG(!ns);
+ AA_BUG(ns != root && !mutex_is_locked(&ns->parent->lock));
+
/* is next namespace a child */
if (!list_empty(&ns->sub_ns)) {
next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list);
static struct aa_profile *__first_profile(struct aa_ns *root,
struct aa_ns *ns)
{
+ AA_BUG(!root);
+ AA_BUG(ns && !mutex_is_locked(&ns->lock));
+
for (; ns; ns = __next_ns(root, ns)) {
if (!list_empty(&ns->base.profiles))
return list_first_entry(&ns->base.profiles,
struct aa_profile *parent;
struct aa_ns *ns = p->ns;
+ AA_BUG(!mutex_is_locked(&profiles_ns(p)->lock));
+
/* is next profile a child */
if (!list_empty(&p->base.profiles))
return list_first_entry(&p->base.profiles, typeof(*p),
{ }
};
+static struct aa_sfs_entry aa_sfs_entry_signal[] = {
+ AA_SFS_FILE_STRING("mask", AA_SFS_SIG_MASK),
+ { }
+};
+
static struct aa_sfs_entry aa_sfs_entry_domain[] = {
AA_SFS_FILE_BOOLEAN("change_hat", 1),
AA_SFS_FILE_BOOLEAN("change_hatv", 1),
{ }
};
+static struct aa_sfs_entry aa_sfs_entry_mount[] = {
+ AA_SFS_FILE_STRING("mask", "mount umount pivot_root"),
+ { }
+};
+
static struct aa_sfs_entry aa_sfs_entry_ns[] = {
AA_SFS_FILE_BOOLEAN("profile", 1),
- AA_SFS_FILE_BOOLEAN("pivot_root", 1),
+ AA_SFS_FILE_BOOLEAN("pivot_root", 0),
{ }
};
AA_SFS_DIR("policy", aa_sfs_entry_policy),
AA_SFS_DIR("domain", aa_sfs_entry_domain),
AA_SFS_DIR("file", aa_sfs_entry_file),
+ AA_SFS_DIR("network", aa_sfs_entry_network),
+ AA_SFS_DIR("mount", aa_sfs_entry_mount),
AA_SFS_DIR("namespaces", aa_sfs_entry_ns),
AA_SFS_FILE_U64("capability", VFS_CAP_FLAGS_MASK),
AA_SFS_DIR("rlimit", aa_sfs_entry_rlimit),
AA_SFS_DIR("caps", aa_sfs_entry_caps),
AA_SFS_DIR("ptrace", aa_sfs_entry_ptrace),
+ AA_SFS_DIR("signal", aa_sfs_entry_signal),
AA_SFS_DIR("query", aa_sfs_entry_query),
{ }
};
static struct aa_sfs_entry aa_sfs_entry_apparmor[] = {
- AA_SFS_FILE_FOPS(".access", 0640, &aa_sfs_access),
+ AA_SFS_FILE_FOPS(".access", 0666, &aa_sfs_access),
AA_SFS_FILE_FOPS(".stacked", 0444, &seq_ns_stacked_fops),
AA_SFS_FILE_FOPS(".ns_stacked", 0444, &seq_ns_nsstacked_fops),
- AA_SFS_FILE_FOPS(".ns_level", 0666, &seq_ns_level_fops),
- AA_SFS_FILE_FOPS(".ns_name", 0640, &seq_ns_name_fops),
- AA_SFS_FILE_FOPS("profiles", 0440, &aa_sfs_profiles_fops),
+ AA_SFS_FILE_FOPS(".ns_level", 0444, &seq_ns_level_fops),
+ AA_SFS_FILE_FOPS(".ns_name", 0444, &seq_ns_name_fops),
+ AA_SFS_FILE_FOPS("profiles", 0444, &aa_sfs_profiles_fops),
AA_SFS_DIR("features", aa_sfs_entry_features),
{ }
};
*
* Returns: refcounted label, or NULL on failure (MAYBE NULL)
*/
-static struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
- const char **name)
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+ const char **name)
{
struct aa_label *label = NULL;
u32 xtype = xindex & AA_X_TYPE_MASK;
#include "include/context.h"
#include "include/file.h"
#include "include/match.h"
+#include "include/net.h"
#include "include/path.h"
#include "include/policy.h"
#include "include/label.h"
return error;
}
+static int __file_sock_perm(const char *op, struct aa_label *label,
+ struct aa_label *flabel, struct file *file,
+ u32 request, u32 denied)
+{
+ struct socket *sock = (struct socket *) file->private_data;
+ int error;
+
+ AA_BUG(!sock);
+
+ /* revalidation due to label out of date. No revocation at this time */
+ if (!denied && aa_label_is_subset(flabel, label))
+ return 0;
+
+ /* TODO: improve to skip profiles cached in flabel */
+ error = aa_sock_file_perm(label, op, request, sock);
+ if (denied) {
+ /* TODO: improve to skip profiles checked above */
+ /* check every profile in file label to is cached */
+ last_error(error, aa_sock_file_perm(flabel, op, request, sock));
+ }
+ if (!error)
+ update_file_ctx(file_ctx(file), label, request);
+
+ return error;
+}
+
/**
* aa_file_perm - do permission revalidation check & audit for @file
* @op: operation being checked
error = __file_path_perm(op, label, flabel, file, request,
denied);
+ else if (S_ISSOCK(file_inode(file)->i_mode))
+ error = __file_sock_perm(op, label, flabel, file, request,
+ denied);
done:
rcu_read_unlock();
#define AA_CLASS_NET 4
#define AA_CLASS_RLIMITS 5
#define AA_CLASS_DOMAIN 6
+#define AA_CLASS_MOUNT 7
#define AA_CLASS_PTRACE 9
+#define AA_CLASS_SIGNAL 10
#define AA_CLASS_LABEL 16
#define AA_CLASS_LAST AA_CLASS_LABEL
#define OP_FMPROT "file_mprotect"
#define OP_INHERIT "file_inherit"
+#define OP_PIVOTROOT "pivotroot"
+#define OP_MOUNT "mount"
+#define OP_UMOUNT "umount"
+
#define OP_CREATE "create"
#define OP_POST_CREATE "post_create"
#define OP_BIND "bind"
#define OP_SHUTDOWN "socket_shutdown"
#define OP_PTRACE "ptrace"
+#define OP_SIGNAL "signal"
#define OP_EXEC "exec"
/* these entries require a custom callback fn */
struct {
struct aa_label *peer;
- struct {
- const char *target;
- kuid_t ouid;
- } fs;
+ union {
+ struct {
+ kuid_t ouid;
+ const char *target;
+ } fs;
+ struct {
+ int type, protocol;
+ struct sock *peer_sk;
+ void *addr;
+ int addrlen;
+ } net;
+ int signal;
+ struct {
+ int rlim;
+ unsigned long max;
+ } rlim;
+ };
};
struct {
- const char *name;
- long pos;
+ struct aa_profile *profile;
const char *ns;
+ long pos;
} iface;
struct {
- int rlim;
- unsigned long max;
- } rlim;
+ const char *src_name;
+ const char *type;
+ const char *trans;
+ const char *data;
+ unsigned long flags;
+ } mnt;
};
};
#include <linux/binfmts.h>
#include <linux/types.h>
+#include "label.h"
+
#ifndef __AA_DOMAIN_H
#define __AA_DOMAIN_H
#define AA_CHANGE_ONEXEC 4
#define AA_CHANGE_STACK 8
+struct aa_label *x_table_lookup(struct aa_profile *profile, u32 xindex,
+ const char **name);
+
int apparmor_bprm_set_creds(struct linux_binprm *bprm);
void aa_free_domain_entries(struct aa_domain *domain);
#define AA_PTRACE_PERM_MASK (AA_PTRACE_READ | AA_PTRACE_TRACE | \
AA_MAY_BE_READ | AA_MAY_BE_TRACED)
+#define AA_SIGNAL_PERM_MASK (MAY_READ | MAY_WRITE)
+
+#define AA_SFS_SIG_MASK "hup int quit ill trap abrt bus fpe kill usr1 " \
+ "segv usr2 pipe alrm term stkflt chld cont stop stp ttin ttou urg " \
+ "xcpu xfsz vtalrm prof winch io pwr sys emt lost"
int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee,
u32 request);
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig);
#endif /* __AA_IPC_H */
#define FLAG_SHOW_MODE 1
#define FLAG_VIEW_SUBNS 2
#define FLAG_HIDDEN_UNCONFINED 4
+#define FLAG_ABS_ROOT 8
int aa_label_snxprint(char *str, size_t size, struct aa_ns *view,
struct aa_label *label, int flags);
int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label,
--- /dev/null
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright 2017 Canonical Ltd.
+ *
+ * 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.
+ */
+
+#ifndef __AA_MOUNT_H
+#define __AA_MOUNT_H
+
+#include <linux/fs.h>
+#include <linux/path.h>
+
+#include "domain.h"
+#include "policy.h"
+
+/* mount perms */
+#define AA_MAY_PIVOTROOT 0x01
+#define AA_MAY_MOUNT 0x02
+#define AA_MAY_UMOUNT 0x04
+#define AA_AUDIT_DATA 0x40
+#define AA_MNT_CONT_MATCH 0x40
+
+#define AA_MS_IGNORE_MASK (MS_KERNMOUNT | MS_NOSEC | MS_ACTIVE | MS_BORN)
+
+int aa_remount(struct aa_label *label, const struct path *path,
+ unsigned long flags, void *data);
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+ const char *old_name, unsigned long flags);
+
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+ unsigned long flags);
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+ const char *old_name);
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+ const struct path *path, const char *type, unsigned long flags,
+ void *data);
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags);
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+ const struct path *new_path);
+
+#endif /* __AA_MOUNT_H */
--- /dev/null
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * 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.
+ */
+
+#ifndef __AA_NET_H
+#define __AA_NET_H
+
+#include <net/sock.h>
+#include <linux/path.h>
+
+#include "apparmorfs.h"
+#include "label.h"
+#include "perms.h"
+#include "policy.h"
+
+#define AA_MAY_SEND AA_MAY_WRITE
+#define AA_MAY_RECEIVE AA_MAY_READ
+
+#define AA_MAY_SHUTDOWN AA_MAY_DELETE
+
+#define AA_MAY_CONNECT AA_MAY_OPEN
+#define AA_MAY_ACCEPT 0x00100000
+
+#define AA_MAY_BIND 0x00200000
+#define AA_MAY_LISTEN 0x00400000
+
+#define AA_MAY_SETOPT 0x01000000
+#define AA_MAY_GETOPT 0x02000000
+
+#define NET_PERMS_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \
+ AA_MAY_SHUTDOWN | AA_MAY_BIND | AA_MAY_LISTEN | \
+ AA_MAY_CONNECT | AA_MAY_ACCEPT | AA_MAY_SETATTR | \
+ AA_MAY_GETATTR | AA_MAY_SETOPT | AA_MAY_GETOPT)
+
+#define NET_FS_PERMS (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CREATE | \
+ AA_MAY_SHUTDOWN | AA_MAY_CONNECT | AA_MAY_RENAME |\
+ AA_MAY_SETATTR | AA_MAY_GETATTR | AA_MAY_CHMOD | \
+ AA_MAY_CHOWN | AA_MAY_CHGRP | AA_MAY_LOCK | \
+ AA_MAY_MPROT)
+
+#define NET_PEER_MASK (AA_MAY_SEND | AA_MAY_RECEIVE | AA_MAY_CONNECT | \
+ AA_MAY_ACCEPT)
+struct aa_sk_ctx {
+ struct aa_label *label;
+ struct aa_label *peer;
+ struct path path;
+};
+
+#define SK_CTX(X) ((X)->sk_security)
+#define SOCK_ctx(X) SOCK_INODE(X)->i_security
+#define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \
+ struct lsm_network_audit NAME ## _net = { .sk = (SK), \
+ .family = (F)}; \
+ DEFINE_AUDIT_DATA(NAME, \
+ ((SK) && (F) != AF_UNIX) ? LSM_AUDIT_DATA_NET : \
+ LSM_AUDIT_DATA_NONE, \
+ OP); \
+ NAME.u.net = &(NAME ## _net); \
+ aad(&NAME)->net.type = (T); \
+ aad(&NAME)->net.protocol = (P)
+
+#define DEFINE_AUDIT_SK(NAME, OP, SK) \
+ DEFINE_AUDIT_NET(NAME, OP, SK, (SK)->sk_family, (SK)->sk_type, \
+ (SK)->sk_protocol)
+
+/* struct aa_net - network confinement data
+ * @allow: basic network families permissions
+ * @audit: which network permissions to force audit
+ * @quiet: which network permissions to quiet rejects
+ */
+struct aa_net {
+ u16 allow[AF_MAX];
+ u16 audit[AF_MAX];
+ u16 quiet[AF_MAX];
+};
+
+
+extern struct aa_sfs_entry aa_sfs_entry_network[];
+
+void audit_net_cb(struct audit_buffer *ab, void *va);
+int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa,
+ u32 request, u16 family, int type);
+int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family,
+ int type, int protocol);
+static inline int aa_profile_af_sk_perm(struct aa_profile *profile,
+ struct common_audit_data *sa,
+ u32 request,
+ struct sock *sk)
+{
+ return aa_profile_af_perm(profile, sa, request, sk->sk_family,
+ sk->sk_type);
+}
+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);
+
+
+static inline void aa_free_net_rules(struct aa_net *new)
+{
+ /* NOP */
+}
+
+#endif /* __AA_NET_H */
void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask);
-void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask);
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+ u32 mask);
void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
- u32 chrsmask, const char **names, u32 namesmask);
+ u32 chrsmask, const char * const *names, u32 namesmask);
void aa_apply_modes_to_perms(struct aa_profile *profile,
struct aa_perms *perms);
void aa_compute_perms(struct aa_dfa *dfa, unsigned int state,
#include "file.h"
#include "lib.h"
#include "label.h"
+#include "net.h"
#include "perms.h"
#include "resource.h"
* @policy: general match rules governing policy
* @file: The set of rules governing basic file access and domain transitions
* @caps: capabilities for the profile
+ * @net: network controls for the profile
* @rlimits: rlimits for the profile
*
* @dents: dentries for the profiles file entries in apparmorfs
struct aa_policydb policy;
struct aa_file_rules file;
struct aa_caps caps;
+ struct aa_net net;
struct aa_rlimit rlimits;
struct aa_loaddata *rawdata;
return 0;
}
+static inline unsigned int PROFILE_MEDIATES_AF(struct aa_profile *profile,
+ u16 AF) {
+ unsigned int state = PROFILE_MEDIATES(profile, AA_CLASS_NET);
+ u16 be_af = cpu_to_be16(AF);
+
+ if (!state)
+ return 0;
+ return aa_dfa_match_len(profile->policy.dfa, state, (char *) &be_af, 2);
+}
+
/**
* aa_get_profile - increment refcount on profile @p
* @p: profile (MAYBE NULL)
--- /dev/null
+#include <linux/signal.h>
+
+#define SIGUNKNOWN 0
+#define MAXMAPPED_SIG 35
+/* provide a mapping of arch signal to internal signal # for mediation
+ * those that are always an alias SIGCLD for SIGCLHD and SIGPOLL for SIGIO
+ * map to the same entry those that may/or may not get a separate entry
+ */
+static const int sig_map[MAXMAPPED_SIG] = {
+ [0] = MAXMAPPED_SIG, /* existence test */
+ [SIGHUP] = 1,
+ [SIGINT] = 2,
+ [SIGQUIT] = 3,
+ [SIGILL] = 4,
+ [SIGTRAP] = 5, /* -, 5, - */
+ [SIGABRT] = 6, /* SIGIOT: -, 6, - */
+ [SIGBUS] = 7, /* 10, 7, 10 */
+ [SIGFPE] = 8,
+ [SIGKILL] = 9,
+ [SIGUSR1] = 10, /* 30, 10, 16 */
+ [SIGSEGV] = 11,
+ [SIGUSR2] = 12, /* 31, 12, 17 */
+ [SIGPIPE] = 13,
+ [SIGALRM] = 14,
+ [SIGTERM] = 15,
+#ifdef SIGSTKFLT
+ [SIGSTKFLT] = 16, /* -, 16, - */
+#endif
+ [SIGCHLD] = 17, /* 20, 17, 18. SIGCHLD -, -, 18 */
+ [SIGCONT] = 18, /* 19, 18, 25 */
+ [SIGSTOP] = 19, /* 17, 19, 23 */
+ [SIGTSTP] = 20, /* 18, 20, 24 */
+ [SIGTTIN] = 21, /* 21, 21, 26 */
+ [SIGTTOU] = 22, /* 22, 22, 27 */
+ [SIGURG] = 23, /* 16, 23, 21 */
+ [SIGXCPU] = 24, /* 24, 24, 30 */
+ [SIGXFSZ] = 25, /* 25, 25, 31 */
+ [SIGVTALRM] = 26, /* 26, 26, 28 */
+ [SIGPROF] = 27, /* 27, 27, 29 */
+ [SIGWINCH] = 28, /* 28, 28, 20 */
+ [SIGIO] = 29, /* SIGPOLL: 23, 29, 22 */
+ [SIGPWR] = 30, /* 29, 30, 19. SIGINFO 29, -, - */
+#ifdef SIGSYS
+ [SIGSYS] = 31, /* 12, 31, 12. often SIG LOST/UNUSED */
+#endif
+#ifdef SIGEMT
+ [SIGEMT] = 32, /* 7, - , 7 */
+#endif
+#if defined(SIGLOST) && SIGPWR != SIGLOST /* sparc */
+ [SIGLOST] = 33, /* unused on Linux */
+#endif
+#if defined(SIGUNUSED) && \
+ defined(SIGLOST) && defined(SIGSYS) && SIGLOST != SIGSYS
+ [SIGUNUSED] = 34, /* -, 31, - */
+#endif
+};
+
+/* this table is ordered post sig_map[sig] mapping */
+static const char *const sig_names[MAXMAPPED_SIG + 1] = {
+ "unknown",
+ "hup",
+ "int",
+ "quit",
+ "ill",
+ "trap",
+ "abrt",
+ "bus",
+ "fpe",
+ "kill",
+ "usr1",
+ "segv",
+ "usr2",
+ "pipe",
+ "alrm",
+ "term",
+ "stkflt",
+ "chld",
+ "cont",
+ "stop",
+ "stp",
+ "ttin",
+ "ttou",
+ "urg",
+ "xcpu",
+ "xfsz",
+ "vtalrm",
+ "prof",
+ "winch",
+ "io",
+ "pwr",
+ "sys",
+ "emt",
+ "lost",
+ "unused",
+
+ "exists", /* always last existence test mapped to MAXMAPPED_SIG */
+};
+
#include "include/context.h"
#include "include/policy.h"
#include "include/ipc.h"
+#include "include/sig_names.h"
/**
* audit_ptrace_mask - convert mask to permission string
}
+static inline int map_signal_num(int sig)
+{
+ if (sig > SIGRTMAX)
+ return SIGUNKNOWN;
+ else if (sig >= SIGRTMIN)
+ return sig - SIGRTMIN + 128; /* rt sigs mapped to 128 */
+ else if (sig <= MAXMAPPED_SIG)
+ return sig_map[sig];
+ return SIGUNKNOWN;
+}
+
+/**
+ * audit_file_mask - convert mask to permission string
+ * @buffer: buffer to write string to (NOT NULL)
+ * @mask: permission mask to convert
+ */
+static void audit_signal_mask(struct audit_buffer *ab, u32 mask)
+{
+ if (mask & MAY_READ)
+ audit_log_string(ab, "receive");
+ if (mask & MAY_WRITE)
+ audit_log_string(ab, "send");
+}
+
+/**
+ * audit_cb - call back for signal specific audit fields
+ * @ab: audit_buffer (NOT NULL)
+ * @va: audit struct to audit values of (NOT NULL)
+ */
+static void audit_signal_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ if (aad(sa)->request & AA_SIGNAL_PERM_MASK) {
+ audit_log_format(ab, " requested_mask=");
+ audit_signal_mask(ab, aad(sa)->request);
+ if (aad(sa)->denied & AA_SIGNAL_PERM_MASK) {
+ audit_log_format(ab, " denied_mask=");
+ audit_signal_mask(ab, aad(sa)->denied);
+ }
+ }
+ if (aad(sa)->signal <= MAXMAPPED_SIG)
+ audit_log_format(ab, " signal=%s", sig_names[aad(sa)->signal]);
+ else
+ audit_log_format(ab, " signal=rtmin+%d",
+ aad(sa)->signal - 128);
+ audit_log_format(ab, " peer=");
+ aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer,
+ FLAGS_NONE, GFP_ATOMIC);
+}
+
+/* TODO: update to handle compound name&name2, conditionals */
+static void profile_match_signal(struct aa_profile *profile, const char *label,
+ int signal, struct aa_perms *perms)
+{
+ unsigned int state;
+
+ /* TODO: secondary cache check <profile, profile, perm> */
+ state = aa_dfa_next(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_SIGNAL],
+ signal);
+ state = aa_dfa_match(profile->policy.dfa, state, label);
+ aa_compute_perms(profile->policy.dfa, state, perms);
+}
+
+static int profile_signal_perm(struct aa_profile *profile,
+ struct aa_profile *peer, u32 request,
+ struct common_audit_data *sa)
+{
+ struct aa_perms perms;
+
+ if (profile_unconfined(profile) ||
+ !PROFILE_MEDIATES(profile, AA_CLASS_SIGNAL))
+ return 0;
+
+ aad(sa)->peer = &peer->label;
+ profile_match_signal(profile, peer->base.hname, aad(sa)->signal,
+ &perms);
+ aa_apply_modes_to_perms(profile, &perms);
+ return aa_check_perms(profile, &perms, request, sa, audit_signal_cb);
+}
+
+static int aa_signal_cross_perm(struct aa_profile *sender,
+ struct aa_profile *target,
+ struct common_audit_data *sa)
+{
+ return xcheck(profile_signal_perm(sender, target, MAY_WRITE, sa),
+ profile_signal_perm(target, sender, MAY_READ, sa));
+}
+
+int aa_may_signal(struct aa_label *sender, struct aa_label *target, int sig)
+{
+ DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, OP_SIGNAL);
+
+ aad(&sa)->signal = map_signal_num(sig);
+ return xcheck_labels_profiles(sender, target, aa_signal_cross_perm,
+ &sa);
+}
/* p->label will not updated any more as p is dead */
aa_put_label(rcu_dereference_protected(proxy->label, true));
memset(proxy, 0, sizeof(*proxy));
- proxy->label = (struct aa_label *) PROXY_POISON;
+ RCU_INIT_POINTER(proxy->label, (struct aa_label *)PROXY_POISON);
kfree(proxy);
}
}
* cached label name is present and visible
* @label->hname only exists if label is namespace hierachical
*/
-static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label)
+static inline bool use_label_hname(struct aa_ns *ns, struct aa_label *label,
+ int flags)
{
- if (label->hname && labels_ns(label) == ns)
+ if (label->hname && (!ns || labels_ns(label) == ns) &&
+ !(flags & ~FLAG_SHOW_MODE))
return true;
return false;
view = profiles_ns(profile);
if (view != profile->ns &&
- (!prev_ns || (prev_ns && *prev_ns != profile->ns))) {
+ (!prev_ns || (*prev_ns != profile->ns))) {
if (prev_ns)
*prev_ns = profile->ns;
ns_name = aa_ns_name(view, profile->ns,
AA_BUG(!str && size != 0);
AA_BUG(!label);
- if (!ns)
+ if (flags & FLAG_ABS_ROOT) {
+ ns = root_ns;
+ len = snprintf(str, size, "=");
+ update_for_len(total, len, size, str);
+ } else if (!ns) {
ns = labels_ns(label);
+ }
label_for_each(i, label, profile) {
if (aa_ns_visible(ns, profile->ns, flags & FLAG_VIEW_SUBNS)) {
AA_BUG(!ab);
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label) || display_mode(ns, label, flags)) {
+ if (!use_label_hname(ns, label, flags) ||
+ display_mode(ns, label, flags)) {
len = aa_label_asxprint(&name, ns, label, flags, gfp);
if (len == -1) {
AA_DEBUG("label print error");
AA_BUG(!f);
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label)) {
+ if (!use_label_hname(ns, label, flags)) {
char *str;
int len;
{
AA_BUG(!label);
- if (!ns)
- ns = labels_ns(label);
-
- if (!use_label_hname(ns, label)) {
+ if (!use_label_hname(ns, label, flags)) {
char *str;
int len;
if (*str == '&')
str++;
}
+ if (*str == '=')
+ base = &root_ns->unconfined->label;
+
error = vec_setup(profile, vec, len, gfp);
if (error)
return ERR_PTR(error);
*str = '\0';
}
-void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask)
+void aa_audit_perm_names(struct audit_buffer *ab, const char * const *names,
+ u32 mask)
{
const char *fmt = "%s";
unsigned int i, perm = 1;
}
void aa_audit_perm_mask(struct audit_buffer *ab, u32 mask, const char *chrs,
- u32 chrsmask, const char **names, u32 namesmask)
+ u32 chrsmask, const char * const *names, u32 namesmask)
{
char str[33];
#include "include/context.h"
#include "include/file.h"
#include "include/ipc.h"
+#include "include/net.h"
#include "include/path.h"
#include "include/label.h"
#include "include/policy.h"
#include "include/policy_ns.h"
#include "include/procattr.h"
+#include "include/mount.h"
/* Flag indicating whether initialization completed */
int apparmor_initialized;
!(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0);
}
+static int apparmor_sb_mount(const char *dev_name, const struct path *path,
+ const char *type, unsigned long flags, void *data)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ /* Discard magic */
+ if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+ flags &= ~MS_MGC_MSK;
+
+ flags &= ~AA_MS_IGNORE_MASK;
+
+ label = __begin_current_label_crit_section();
+ if (!unconfined(label)) {
+ if (flags & MS_REMOUNT)
+ error = aa_remount(label, path, flags, data);
+ else if (flags & MS_BIND)
+ error = aa_bind_mount(label, path, dev_name, flags);
+ else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE |
+ MS_UNBINDABLE))
+ error = aa_mount_change_type(label, path, flags);
+ else if (flags & MS_MOVE)
+ error = aa_move_mount(label, path, dev_name);
+ else
+ error = aa_new_mount(label, dev_name, path, type,
+ flags, data);
+ }
+ __end_current_label_crit_section(label);
+
+ return error;
+}
+
+static int apparmor_sb_umount(struct vfsmount *mnt, int flags)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = __begin_current_label_crit_section();
+ if (!unconfined(label))
+ error = aa_umount(label, mnt, flags);
+ __end_current_label_crit_section(label);
+
+ return error;
+}
+
+static int apparmor_sb_pivotroot(const struct path *old_path,
+ const struct path *new_path)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = aa_get_current_label();
+ if (!unconfined(label))
+ error = aa_pivotroot(label, old_path, new_path);
+ aa_put_label(label);
+
+ return error;
+}
+
static int apparmor_getprocattr(struct task_struct *task, char *name,
char **value)
{
return error;
}
+static int apparmor_task_kill(struct task_struct *target, struct siginfo *info,
+ int sig, u32 secid)
+{
+ struct aa_label *cl, *tl;
+ int error;
+
+ if (secid)
+ /* TODO: after secid to label mapping is done.
+ * Dealing with USB IO specific behavior
+ */
+ return 0;
+ cl = __begin_current_label_crit_section();
+ tl = aa_get_task_label(target);
+ error = aa_may_signal(cl, tl, sig);
+ aa_put_label(tl);
+ __end_current_label_crit_section(cl);
+
+ return error;
+}
+
+/**
+ * apparmor_sk_alloc_security - allocate and attach the sk_security field
+ */
+static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
+{
+ struct aa_sk_ctx *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), flags);
+ if (!ctx)
+ return -ENOMEM;
+
+ SK_CTX(sk) = ctx;
+
+ return 0;
+}
+
+/**
+ * apparmor_sk_free_security - free the sk_security field
+ */
+static void apparmor_sk_free_security(struct sock *sk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ SK_CTX(sk) = NULL;
+ aa_put_label(ctx->label);
+ aa_put_label(ctx->peer);
+ path_put(&ctx->path);
+ kfree(ctx);
+}
+
+/**
+ * apparmor_clone_security - clone the sk_security field
+ */
+static void apparmor_sk_clone_security(const struct sock *sk,
+ struct sock *newsk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+ struct aa_sk_ctx *new = SK_CTX(newsk);
+
+ new->label = aa_get_label(ctx->label);
+ new->peer = aa_get_label(ctx->peer);
+ new->path = ctx->path;
+ path_get(&new->path);
+}
+
+static int aa_sock_create_perm(struct aa_label *label, int family, int type,
+ int protocol)
+{
+ AA_BUG(!label);
+ AA_BUG(in_interrupt());
+
+ return aa_af_perm(label, OP_CREATE, AA_MAY_CREATE, family, type,
+ protocol);
+}
+
+
+/**
+ * apparmor_socket_create - check perms before creating a new socket
+ */
+static int apparmor_socket_create(int family, int type, int protocol, int kern)
+{
+ struct aa_label *label;
+ int error = 0;
+
+ label = begin_current_label_crit_section();
+ if (!(kern || unconfined(label)))
+ error = aa_sock_create_perm(label, family, type, protocol);
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+/**
+ * apparmor_socket_post_create - setup the per-socket security struct
+ *
+ * Note:
+ * - kernel sockets currently labeled unconfined but we may want to
+ * move to a special kernel label
+ * - socket may not have sk here if created with sock_create_lite or
+ * sock_alloc. These should be accept cases which will be handled in
+ * sock_graft.
+ */
+static int apparmor_socket_post_create(struct socket *sock, int family,
+ int type, int protocol, int kern)
+{
+ struct aa_label *label;
+
+ if (kern) {
+ struct aa_ns *ns = aa_get_current_ns();
+
+ label = aa_get_label(ns_unconfined(ns));
+ aa_put_ns(ns);
+ } else
+ label = aa_get_current_label();
+
+ if (sock->sk) {
+ struct aa_sk_ctx *ctx = SK_CTX(sock->sk);
+
+ aa_put_label(ctx->label);
+ ctx->label = aa_get_label(label);
+ }
+ aa_put_label(label);
+
+ return 0;
+}
+
+/**
+ * apparmor_socket_bind - check perms before bind addr to socket
+ */
+static int apparmor_socket_bind(struct socket *sock,
+ struct sockaddr *address, int addrlen)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!address);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_BIND, AA_MAY_BIND, sock->sk);
+}
+
+/**
+ * apparmor_socket_connect - check perms before connecting @sock to @address
+ */
+static int apparmor_socket_connect(struct socket *sock,
+ struct sockaddr *address, int addrlen)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!address);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_CONNECT, AA_MAY_CONNECT, sock->sk);
+}
+
+/**
+ * apparmor_socket_list - check perms before allowing listen
+ */
+static int apparmor_socket_listen(struct socket *sock, int backlog)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_LISTEN, AA_MAY_LISTEN, sock->sk);
+}
+
+/**
+ * apparmor_socket_accept - check perms before accepting a new connection.
+ *
+ * Note: while @newsock is created and has some information, the accept
+ * has not been done.
+ */
+static int apparmor_socket_accept(struct socket *sock, struct socket *newsock)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!newsock);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(OP_ACCEPT, AA_MAY_ACCEPT, sock->sk);
+}
+
+static int aa_sock_msg_perm(const char *op, u32 request, struct socket *sock,
+ struct msghdr *msg, int size)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(!msg);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_socket_sendmsg - check perms before sending msg to another socket
+ */
+static int apparmor_socket_sendmsg(struct socket *sock,
+ struct msghdr *msg, int size)
+{
+ return aa_sock_msg_perm(OP_SENDMSG, AA_MAY_SEND, sock, msg, size);
+}
+
+/**
+ * apparmor_socket_recvmsg - check perms before receiving a message
+ */
+static int apparmor_socket_recvmsg(struct socket *sock,
+ struct msghdr *msg, int size, int flags)
+{
+ return aa_sock_msg_perm(OP_RECVMSG, AA_MAY_RECEIVE, sock, msg, size);
+}
+
+/* revaliation, get/set attr, shutdown */
+static int aa_sock_perm(const char *op, u32 request, struct socket *sock)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_socket_getsockname - check perms before getting the local address
+ */
+static int apparmor_socket_getsockname(struct socket *sock)
+{
+ return aa_sock_perm(OP_GETSOCKNAME, AA_MAY_GETATTR, sock);
+}
+
+/**
+ * apparmor_socket_getpeername - check perms before getting remote address
+ */
+static int apparmor_socket_getpeername(struct socket *sock)
+{
+ return aa_sock_perm(OP_GETPEERNAME, AA_MAY_GETATTR, sock);
+}
+
+/* revaliation, get/set attr, opt */
+static int aa_sock_opt_perm(const char *op, u32 request, struct socket *sock,
+ int level, int optname)
+{
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+ AA_BUG(in_interrupt());
+
+ return aa_sk_perm(op, request, sock->sk);
+}
+
+/**
+ * apparmor_getsockopt - check perms before getting socket options
+ */
+static int apparmor_socket_getsockopt(struct socket *sock, int level,
+ int optname)
+{
+ return aa_sock_opt_perm(OP_GETSOCKOPT, AA_MAY_GETOPT, sock,
+ level, optname);
+}
+
+/**
+ * apparmor_setsockopt - check perms before setting socket options
+ */
+static int apparmor_socket_setsockopt(struct socket *sock, int level,
+ int optname)
+{
+ return aa_sock_opt_perm(OP_SETSOCKOPT, AA_MAY_SETOPT, sock,
+ level, optname);
+}
+
+/**
+ * apparmor_socket_shutdown - check perms before shutting down @sock conn
+ */
+static int apparmor_socket_shutdown(struct socket *sock, int how)
+{
+ return aa_sock_perm(OP_SHUTDOWN, AA_MAY_SHUTDOWN, sock);
+}
+
+/**
+ * apparmor_socket_sock_recv_skb - check perms before associating skb to sk
+ *
+ * Note: can not sleep may be called with locks held
+ *
+ * dont want protocol specific in __skb_recv_datagram()
+ * to deny an incoming connection socket_sock_rcv_skb()
+ */
+static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ return 0;
+}
+
+
+static struct aa_label *sk_peer_label(struct sock *sk)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ if (ctx->peer)
+ return ctx->peer;
+
+ return ERR_PTR(-ENOPROTOOPT);
+}
+
+/**
+ * apparmor_socket_getpeersec_stream - get security context of peer
+ *
+ * Note: for tcp only valid if using ipsec or cipso on lan
+ */
+static int apparmor_socket_getpeersec_stream(struct socket *sock,
+ char __user *optval,
+ int __user *optlen,
+ unsigned int len)
+{
+ char *name;
+ int slen, error = 0;
+ struct aa_label *label;
+ struct aa_label *peer;
+
+ label = begin_current_label_crit_section();
+ peer = sk_peer_label(sock->sk);
+ if (IS_ERR(peer)) {
+ error = PTR_ERR(peer);
+ goto done;
+ }
+ slen = aa_label_asxprint(&name, labels_ns(label), peer,
+ FLAG_SHOW_MODE | FLAG_VIEW_SUBNS |
+ FLAG_HIDDEN_UNCONFINED, GFP_KERNEL);
+ /* don't include terminating \0 in slen, it breaks some apps */
+ if (slen < 0) {
+ error = -ENOMEM;
+ } else {
+ if (slen > len) {
+ error = -ERANGE;
+ } else if (copy_to_user(optval, name, slen)) {
+ error = -EFAULT;
+ goto out;
+ }
+ if (put_user(slen, optlen))
+ error = -EFAULT;
+out:
+ kfree(name);
+
+ }
+
+done:
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+/**
+ * apparmor_socket_getpeersec_dgram - get security label of packet
+ * @sock: the peer socket
+ * @skb: packet data
+ * @secid: pointer to where to put the secid of the packet
+ *
+ * Sets the netlabel socket state on sk from parent
+ */
+static int apparmor_socket_getpeersec_dgram(struct socket *sock,
+ struct sk_buff *skb, u32 *secid)
+
+{
+ /* TODO: requires secid support */
+ return -ENOPROTOOPT;
+}
+
+/**
+ * apparmor_sock_graft - Initialize newly created socket
+ * @sk: child sock
+ * @parent: parent socket
+ *
+ * Note: could set off of SOCK_CTX(parent) but need to track inode and we can
+ * just set sk security information off of current creating process label
+ * Labeling of sk for accept case - probably should be sock based
+ * instead of task, because of the case where an implicitly labeled
+ * socket is shared by different tasks.
+ */
+static void apparmor_sock_graft(struct sock *sk, struct socket *parent)
+{
+ struct aa_sk_ctx *ctx = SK_CTX(sk);
+
+ if (!ctx->label)
+ ctx->label = aa_get_current_label();
+}
+
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),
LSM_HOOK_INIT(capget, apparmor_capget),
LSM_HOOK_INIT(capable, apparmor_capable),
+ LSM_HOOK_INIT(sb_mount, apparmor_sb_mount),
+ LSM_HOOK_INIT(sb_umount, apparmor_sb_umount),
+ LSM_HOOK_INIT(sb_pivotroot, apparmor_sb_pivotroot),
+
LSM_HOOK_INIT(path_link, apparmor_path_link),
LSM_HOOK_INIT(path_unlink, apparmor_path_unlink),
LSM_HOOK_INIT(path_symlink, apparmor_path_symlink),
LSM_HOOK_INIT(getprocattr, apparmor_getprocattr),
LSM_HOOK_INIT(setprocattr, apparmor_setprocattr),
+ LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security),
+ LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security),
+ LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security),
+
+ LSM_HOOK_INIT(socket_create, apparmor_socket_create),
+ LSM_HOOK_INIT(socket_post_create, apparmor_socket_post_create),
+ LSM_HOOK_INIT(socket_bind, apparmor_socket_bind),
+ LSM_HOOK_INIT(socket_connect, apparmor_socket_connect),
+ LSM_HOOK_INIT(socket_listen, apparmor_socket_listen),
+ LSM_HOOK_INIT(socket_accept, apparmor_socket_accept),
+ LSM_HOOK_INIT(socket_sendmsg, apparmor_socket_sendmsg),
+ LSM_HOOK_INIT(socket_recvmsg, apparmor_socket_recvmsg),
+ LSM_HOOK_INIT(socket_getsockname, apparmor_socket_getsockname),
+ LSM_HOOK_INIT(socket_getpeername, apparmor_socket_getpeername),
+ LSM_HOOK_INIT(socket_getsockopt, apparmor_socket_getsockopt),
+ LSM_HOOK_INIT(socket_setsockopt, apparmor_socket_setsockopt),
+ LSM_HOOK_INIT(socket_shutdown, apparmor_socket_shutdown),
+ LSM_HOOK_INIT(socket_sock_rcv_skb, apparmor_socket_sock_rcv_skb),
+ 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),
+
LSM_HOOK_INIT(cred_alloc_blank, apparmor_cred_alloc_blank),
LSM_HOOK_INIT(cred_free, apparmor_cred_free),
LSM_HOOK_INIT(cred_prepare, apparmor_cred_prepare),
LSM_HOOK_INIT(bprm_committed_creds, apparmor_bprm_committed_creds),
LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit),
+ LSM_HOOK_INIT(task_kill, apparmor_task_kill),
};
/*
--- /dev/null
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * 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.
+ */
+
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/mount.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+
+static void audit_mnt_flags(struct audit_buffer *ab, unsigned long flags)
+{
+ if (flags & MS_RDONLY)
+ audit_log_format(ab, "ro");
+ else
+ audit_log_format(ab, "rw");
+ if (flags & MS_NOSUID)
+ audit_log_format(ab, ", nosuid");
+ if (flags & MS_NODEV)
+ audit_log_format(ab, ", nodev");
+ if (flags & MS_NOEXEC)
+ audit_log_format(ab, ", noexec");
+ if (flags & MS_SYNCHRONOUS)
+ audit_log_format(ab, ", sync");
+ if (flags & MS_REMOUNT)
+ audit_log_format(ab, ", remount");
+ if (flags & MS_MANDLOCK)
+ audit_log_format(ab, ", mand");
+ if (flags & MS_DIRSYNC)
+ audit_log_format(ab, ", dirsync");
+ if (flags & MS_NOATIME)
+ audit_log_format(ab, ", noatime");
+ if (flags & MS_NODIRATIME)
+ audit_log_format(ab, ", nodiratime");
+ if (flags & MS_BIND)
+ audit_log_format(ab, flags & MS_REC ? ", rbind" : ", bind");
+ if (flags & MS_MOVE)
+ audit_log_format(ab, ", move");
+ if (flags & MS_SILENT)
+ audit_log_format(ab, ", silent");
+ if (flags & MS_POSIXACL)
+ audit_log_format(ab, ", acl");
+ if (flags & MS_UNBINDABLE)
+ audit_log_format(ab, flags & MS_REC ? ", runbindable" :
+ ", unbindable");
+ if (flags & MS_PRIVATE)
+ audit_log_format(ab, flags & MS_REC ? ", rprivate" :
+ ", private");
+ if (flags & MS_SLAVE)
+ audit_log_format(ab, flags & MS_REC ? ", rslave" :
+ ", slave");
+ if (flags & MS_SHARED)
+ audit_log_format(ab, flags & MS_REC ? ", rshared" :
+ ", shared");
+ if (flags & MS_RELATIME)
+ audit_log_format(ab, ", relatime");
+ if (flags & MS_I_VERSION)
+ audit_log_format(ab, ", iversion");
+ if (flags & MS_STRICTATIME)
+ audit_log_format(ab, ", strictatime");
+ if (flags & MS_NOUSER)
+ audit_log_format(ab, ", nouser");
+}
+
+/**
+ * audit_cb - call back for mount specific audit fields
+ * @ab: audit_buffer (NOT NULL)
+ * @va: audit struct to audit values of (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ if (aad(sa)->mnt.type) {
+ audit_log_format(ab, " fstype=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.type);
+ }
+ if (aad(sa)->mnt.src_name) {
+ audit_log_format(ab, " srcname=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.src_name);
+ }
+ if (aad(sa)->mnt.trans) {
+ audit_log_format(ab, " trans=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.trans);
+ }
+ if (aad(sa)->mnt.flags) {
+ audit_log_format(ab, " flags=\"");
+ audit_mnt_flags(ab, aad(sa)->mnt.flags);
+ audit_log_format(ab, "\"");
+ }
+ if (aad(sa)->mnt.data) {
+ audit_log_format(ab, " options=");
+ audit_log_untrustedstring(ab, aad(sa)->mnt.data);
+ }
+}
+
+/**
+ * audit_mount - handle the auditing of mount operations
+ * @profile: the profile being enforced (NOT NULL)
+ * @op: operation being mediated (NOT NULL)
+ * @name: name of object being mediated (MAYBE NULL)
+ * @src_name: src_name of object being mediated (MAYBE_NULL)
+ * @type: type of filesystem (MAYBE_NULL)
+ * @trans: name of trans (MAYBE NULL)
+ * @flags: filesystem idependent mount flags
+ * @data: filesystem mount flags
+ * @request: permissions requested
+ * @perms: the permissions computed for the request (NOT NULL)
+ * @info: extra information message (MAYBE NULL)
+ * @error: 0 if operation allowed else failure error code
+ *
+ * Returns: %0 or error on failure
+ */
+static int audit_mount(struct aa_profile *profile, const char *op,
+ const char *name, const char *src_name,
+ const char *type, const char *trans,
+ unsigned long flags, const void *data, u32 request,
+ struct aa_perms *perms, const char *info, int error)
+{
+ int audit_type = AUDIT_APPARMOR_AUTO;
+ DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, op);
+
+ if (likely(!error)) {
+ u32 mask = perms->audit;
+
+ if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
+ mask = 0xffff;
+
+ /* mask off perms that are not being force audited */
+ request &= mask;
+
+ if (likely(!request))
+ return 0;
+ audit_type = AUDIT_APPARMOR_AUDIT;
+ } else {
+ /* only report permissions that were denied */
+ request = request & ~perms->allow;
+
+ if (request & perms->kill)
+ audit_type = AUDIT_APPARMOR_KILL;
+
+ /* quiet known rejects, assumes quiet and kill do not overlap */
+ if ((request & perms->quiet) &&
+ AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+ AUDIT_MODE(profile) != AUDIT_ALL)
+ request &= ~perms->quiet;
+
+ if (!request)
+ return error;
+ }
+
+ aad(&sa)->name = name;
+ aad(&sa)->mnt.src_name = src_name;
+ aad(&sa)->mnt.type = type;
+ aad(&sa)->mnt.trans = trans;
+ aad(&sa)->mnt.flags = flags;
+ if (data && (perms->audit & AA_AUDIT_DATA))
+ aad(&sa)->mnt.data = data;
+ aad(&sa)->info = info;
+ aad(&sa)->error = error;
+
+ return aa_audit(audit_type, profile, &sa, audit_cb);
+}
+
+/**
+ * match_mnt_flags - Do an ordered match on mount flags
+ * @dfa: dfa to match against
+ * @state: state to start in
+ * @flags: mount flags to match against
+ *
+ * Mount flags are encoded as an ordered match. This is done instead of
+ * checking against a simple bitmask, to allow for logical operations
+ * on the flags.
+ *
+ * Returns: next state after flags match
+ */
+static unsigned int match_mnt_flags(struct aa_dfa *dfa, unsigned int state,
+ unsigned long flags)
+{
+ unsigned int i;
+
+ for (i = 0; i <= 31 ; ++i) {
+ if ((1 << i) & flags)
+ state = aa_dfa_next(dfa, state, i + 1);
+ }
+
+ return state;
+}
+
+/**
+ * compute_mnt_perms - compute mount permission associated with @state
+ * @dfa: dfa to match against (NOT NULL)
+ * @state: state match finished in
+ *
+ * Returns: mount permissions
+ */
+static struct aa_perms compute_mnt_perms(struct aa_dfa *dfa,
+ unsigned int state)
+{
+ struct aa_perms perms;
+
+ perms.kill = 0;
+ perms.allow = dfa_user_allow(dfa, state);
+ perms.audit = dfa_user_audit(dfa, state);
+ perms.quiet = dfa_user_quiet(dfa, state);
+ perms.xindex = dfa_user_xindex(dfa, state);
+
+ return perms;
+}
+
+static const char * const mnt_info_table[] = {
+ "match succeeded",
+ "failed mntpnt match",
+ "failed srcname match",
+ "failed type match",
+ "failed flags match",
+ "failed data match"
+};
+
+/*
+ * Returns 0 on success else element that match failed in, this is the
+ * index into the mnt_info_table above
+ */
+static int do_match_mnt(struct aa_dfa *dfa, unsigned int start,
+ const char *mntpnt, const char *devname,
+ const char *type, unsigned long flags,
+ void *data, bool binary, struct aa_perms *perms)
+{
+ unsigned int state;
+
+ AA_BUG(!dfa);
+ AA_BUG(!perms);
+
+ state = aa_dfa_match(dfa, start, mntpnt);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 1;
+
+ if (devname)
+ state = aa_dfa_match(dfa, state, devname);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 2;
+
+ if (type)
+ state = aa_dfa_match(dfa, state, type);
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 3;
+
+ state = match_mnt_flags(dfa, state, flags);
+ if (!state)
+ return 4;
+ *perms = compute_mnt_perms(dfa, state);
+ if (perms->allow & AA_MAY_MOUNT)
+ return 0;
+
+ /* only match data if not binary and the DFA flags data is expected */
+ if (data && !binary && (perms->allow & AA_MNT_CONT_MATCH)) {
+ state = aa_dfa_null_transition(dfa, state);
+ if (!state)
+ return 4;
+
+ state = aa_dfa_match(dfa, state, data);
+ if (!state)
+ return 5;
+ *perms = compute_mnt_perms(dfa, state);
+ if (perms->allow & AA_MAY_MOUNT)
+ return 0;
+ }
+
+ /* failed at end of flags match */
+ return 4;
+}
+
+
+static int path_flags(struct aa_profile *profile, const struct path *path)
+{
+ AA_BUG(!profile);
+ AA_BUG(!path);
+
+ return profile->path_flags |
+ (S_ISDIR(path->dentry->d_inode->i_mode) ? PATH_IS_DIR : 0);
+}
+
+/**
+ * match_mnt_path_str - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devnme: string for the devname/src_name (MAY BE NULL OR ERRPTR)
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ * @devinfo: error str if (IS_ERR(@devname))
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt_path_str(struct aa_profile *profile,
+ const struct path *mntpath, char *buffer,
+ const char *devname, const char *type,
+ unsigned long flags, void *data, bool binary,
+ const char *devinfo)
+{
+ struct aa_perms perms = { };
+ const char *mntpnt = NULL, *info = NULL;
+ int pos, error;
+
+ AA_BUG(!profile);
+ AA_BUG(!mntpath);
+ AA_BUG(!buffer);
+
+ error = aa_path_name(mntpath, path_flags(profile, mntpath), buffer,
+ &mntpnt, &info, profile->disconnected);
+ if (error)
+ goto audit;
+ if (IS_ERR(devname)) {
+ error = PTR_ERR(devname);
+ devname = NULL;
+ info = devinfo;
+ goto audit;
+ }
+
+ error = -EACCES;
+ pos = do_match_mnt(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ mntpnt, devname, type, flags, data, binary, &perms);
+ if (pos) {
+ info = mnt_info_table[pos];
+ goto audit;
+ }
+ error = 0;
+
+audit:
+ return audit_mount(profile, OP_MOUNT, mntpnt, devname, type, NULL,
+ flags, data, AA_MAY_MOUNT, &perms, info, error);
+}
+
+/**
+ * match_mnt - handle path matching for mount
+ * @profile: the confining profile
+ * @mntpath: for the mntpnt (NOT NULL)
+ * @buffer: buffer to be used to lookup mntpath
+ * @devpath: path devname/src_name (MAYBE NULL)
+ * @devbuffer: buffer to be used to lookup devname/src_name
+ * @type: string for the dev type (MAYBE NULL)
+ * @flags: mount flags to match
+ * @data: fs mount data (MAYBE NULL)
+ * @binary: whether @data is binary
+ *
+ * Returns: 0 on success else error
+ */
+static int match_mnt(struct aa_profile *profile, const struct path *path,
+ char *buffer, struct path *devpath, char *devbuffer,
+ const char *type, unsigned long flags, void *data,
+ bool binary)
+{
+ const char *devname = NULL, *info = NULL;
+ int error = -EACCES;
+
+ AA_BUG(!profile);
+ AA_BUG(devpath && !devbuffer);
+
+ if (devpath) {
+ error = aa_path_name(devpath, path_flags(profile, devpath),
+ devbuffer, &devname, &info,
+ profile->disconnected);
+ if (error)
+ devname = ERR_PTR(error);
+ }
+
+ return match_mnt_path_str(profile, path, buffer, devname, type, flags,
+ data, binary, info);
+}
+
+int aa_remount(struct aa_label *label, const struct path *path,
+ unsigned long flags, void *data)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ bool binary;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ binary = path->dentry->d_sb->s_type->fs_flags & FS_BINARY_MOUNTDATA;
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, NULL, NULL, NULL,
+ flags, data, binary));
+ put_buffers(buffer);
+
+ return error;
+}
+
+int aa_bind_mount(struct aa_label *label, const struct path *path,
+ const char *dev_name, unsigned long flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *old_buffer = NULL;
+ struct path old_path;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (!dev_name || !*dev_name)
+ return -EINVAL;
+
+ flags &= MS_REC | MS_BIND;
+
+ error = kern_path(dev_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
+ if (error)
+ return error;
+
+ get_buffers(buffer, old_buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, &old_path, old_buffer,
+ NULL, flags, NULL, false));
+ put_buffers(buffer, old_buffer);
+ path_put(&old_path);
+
+ return error;
+}
+
+int aa_mount_change_type(struct aa_label *label, const struct path *path,
+ unsigned long flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ /* These are the flags allowed by do_change_type() */
+ flags &= (MS_REC | MS_SILENT | MS_SHARED | MS_PRIVATE | MS_SLAVE |
+ MS_UNBINDABLE);
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, NULL, NULL, NULL,
+ flags, NULL, false));
+ put_buffers(buffer);
+
+ return error;
+}
+
+int aa_move_mount(struct aa_label *label, const struct path *path,
+ const char *orig_name)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *old_buffer = NULL;
+ struct path old_path;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (!orig_name || !*orig_name)
+ return -EINVAL;
+
+ error = kern_path(orig_name, LOOKUP_FOLLOW, &old_path);
+ if (error)
+ return error;
+
+ get_buffers(buffer, old_buffer);
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, &old_path, old_buffer,
+ NULL, MS_MOVE, NULL, false));
+ put_buffers(buffer, old_buffer);
+ path_put(&old_path);
+
+ return error;
+}
+
+int aa_new_mount(struct aa_label *label, const char *dev_name,
+ const struct path *path, const char *type, unsigned long flags,
+ void *data)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL, *dev_buffer = NULL;
+ bool binary = true;
+ int error;
+ int requires_dev = 0;
+ struct path tmp_path, *dev_path = NULL;
+
+ AA_BUG(!label);
+ AA_BUG(!path);
+
+ if (type) {
+ struct file_system_type *fstype;
+
+ fstype = get_fs_type(type);
+ if (!fstype)
+ return -ENODEV;
+ binary = fstype->fs_flags & FS_BINARY_MOUNTDATA;
+ requires_dev = fstype->fs_flags & FS_REQUIRES_DEV;
+ put_filesystem(fstype);
+
+ if (requires_dev) {
+ if (!dev_name || !*dev_name)
+ return -ENOENT;
+
+ error = kern_path(dev_name, LOOKUP_FOLLOW, &tmp_path);
+ if (error)
+ return error;
+ dev_path = &tmp_path;
+ }
+ }
+
+ get_buffers(buffer, dev_buffer);
+ if (dev_path) {
+ error = fn_for_each_confined(label, profile,
+ match_mnt(profile, path, buffer, dev_path, dev_buffer,
+ type, flags, data, binary));
+ } else {
+ error = fn_for_each_confined(label, profile,
+ match_mnt_path_str(profile, path, buffer, dev_name,
+ type, flags, data, binary, NULL));
+ }
+ put_buffers(buffer, dev_buffer);
+ if (dev_path)
+ path_put(dev_path);
+
+ return error;
+}
+
+static int profile_umount(struct aa_profile *profile, struct path *path,
+ char *buffer)
+{
+ struct aa_perms perms = { };
+ const char *name = NULL, *info = NULL;
+ unsigned int state;
+ int error;
+
+ AA_BUG(!profile);
+ AA_BUG(!path);
+
+ error = aa_path_name(path, path_flags(profile, path), buffer, &name,
+ &info, profile->disconnected);
+ if (error)
+ goto audit;
+
+ state = aa_dfa_match(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ name);
+ perms = compute_mnt_perms(profile->policy.dfa, state);
+ if (AA_MAY_UMOUNT & ~perms.allow)
+ error = -EACCES;
+
+audit:
+ return audit_mount(profile, OP_UMOUNT, name, NULL, NULL, NULL, 0, NULL,
+ AA_MAY_UMOUNT, &perms, info, error);
+}
+
+int aa_umount(struct aa_label *label, struct vfsmount *mnt, int flags)
+{
+ struct aa_profile *profile;
+ char *buffer = NULL;
+ int error;
+ struct path path = { .mnt = mnt, .dentry = mnt->mnt_root };
+
+ AA_BUG(!label);
+ AA_BUG(!mnt);
+
+ get_buffers(buffer);
+ error = fn_for_each_confined(label, profile,
+ profile_umount(profile, &path, buffer));
+ put_buffers(buffer);
+
+ return error;
+}
+
+/* helper fn for transition on pivotroot
+ *
+ * Returns: label for transition or ERR_PTR. Does not return NULL
+ */
+static struct aa_label *build_pivotroot(struct aa_profile *profile,
+ const struct path *new_path,
+ char *new_buffer,
+ const struct path *old_path,
+ char *old_buffer)
+{
+ const char *old_name, *new_name = NULL, *info = NULL;
+ const char *trans_name = NULL;
+ struct aa_perms perms = { };
+ unsigned int state;
+ int error;
+
+ AA_BUG(!profile);
+ AA_BUG(!new_path);
+ AA_BUG(!old_path);
+
+ if (profile_unconfined(profile))
+ return aa_get_newest_label(&profile->label);
+
+ error = aa_path_name(old_path, path_flags(profile, old_path),
+ old_buffer, &old_name, &info,
+ profile->disconnected);
+ if (error)
+ goto audit;
+ error = aa_path_name(new_path, path_flags(profile, new_path),
+ new_buffer, &new_name, &info,
+ profile->disconnected);
+ if (error)
+ goto audit;
+
+ error = -EACCES;
+ state = aa_dfa_match(profile->policy.dfa,
+ profile->policy.start[AA_CLASS_MOUNT],
+ new_name);
+ state = aa_dfa_null_transition(profile->policy.dfa, state);
+ state = aa_dfa_match(profile->policy.dfa, state, old_name);
+ perms = compute_mnt_perms(profile->policy.dfa, state);
+
+ if (AA_MAY_PIVOTROOT & perms.allow)
+ error = 0;
+
+audit:
+ error = audit_mount(profile, OP_PIVOTROOT, new_name, old_name,
+ NULL, trans_name, 0, NULL, AA_MAY_PIVOTROOT,
+ &perms, info, error);
+ if (error)
+ return ERR_PTR(error);
+
+ return aa_get_newest_label(&profile->label);
+}
+
+int aa_pivotroot(struct aa_label *label, const struct path *old_path,
+ const struct path *new_path)
+{
+ struct aa_profile *profile;
+ struct aa_label *target = NULL;
+ char *old_buffer = NULL, *new_buffer = NULL, *info = NULL;
+ int error;
+
+ AA_BUG(!label);
+ AA_BUG(!old_path);
+ AA_BUG(!new_path);
+
+ get_buffers(old_buffer, new_buffer);
+ target = fn_label_build(label, profile, GFP_ATOMIC,
+ build_pivotroot(profile, new_path, new_buffer,
+ old_path, old_buffer));
+ if (!target) {
+ info = "label build failed";
+ error = -ENOMEM;
+ goto fail;
+ } else if (!IS_ERR(target)) {
+ error = aa_replace_current_label(target);
+ if (error) {
+ /* TODO: audit target */
+ aa_put_label(target);
+ goto out;
+ }
+ } else
+ /* already audited error */
+ error = PTR_ERR(target);
+out:
+ put_buffers(old_buffer, new_buffer);
+
+ return error;
+
+fail:
+ /* TODO: add back in auditing of new_name and old_name */
+ error = fn_for_each(label, profile,
+ audit_mount(profile, OP_PIVOTROOT, NULL /*new_name */,
+ NULL /* old_name */,
+ NULL, NULL,
+ 0, NULL, AA_MAY_PIVOTROOT, &nullperms, info,
+ error));
+ goto out;
+}
--- /dev/null
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor network mediation
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2017 Canonical Ltd.
+ *
+ * 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.
+ */
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/label.h"
+#include "include/net.h"
+#include "include/policy.h"
+
+#include "net_names.h"
+
+
+struct aa_sfs_entry aa_sfs_entry_network[] = {
+ AA_SFS_FILE_STRING("af_mask", AA_SFS_AF_MASK),
+ { }
+};
+
+static const char * const net_mask_names[] = {
+ "unknown",
+ "send",
+ "receive",
+ "unknown",
+
+ "create",
+ "shutdown",
+ "connect",
+ "unknown",
+
+ "setattr",
+ "getattr",
+ "setcred",
+ "getcred",
+
+ "chmod",
+ "chown",
+ "chgrp",
+ "lock",
+
+ "mmap",
+ "mprot",
+ "unknown",
+ "unknown",
+
+ "accept",
+ "bind",
+ "listen",
+ "unknown",
+
+ "setopt",
+ "getopt",
+ "unknown",
+ "unknown",
+
+ "unknown",
+ "unknown",
+ "unknown",
+ "unknown",
+};
+
+
+/* audit callback for net specific fields */
+void audit_net_cb(struct audit_buffer *ab, void *va)
+{
+ struct common_audit_data *sa = va;
+
+ audit_log_format(ab, " family=");
+ if (address_family_names[sa->u.net->family])
+ audit_log_string(ab, address_family_names[sa->u.net->family]);
+ else
+ audit_log_format(ab, "\"unknown(%d)\"", sa->u.net->family);
+ audit_log_format(ab, " sock_type=");
+ if (sock_type_names[aad(sa)->net.type])
+ audit_log_string(ab, sock_type_names[aad(sa)->net.type]);
+ else
+ audit_log_format(ab, "\"unknown(%d)\"", aad(sa)->net.type);
+ audit_log_format(ab, " protocol=%d", aad(sa)->net.protocol);
+
+ if (aad(sa)->request & NET_PERMS_MASK) {
+ audit_log_format(ab, " requested_mask=");
+ aa_audit_perm_mask(ab, aad(sa)->request, NULL, 0,
+ net_mask_names, NET_PERMS_MASK);
+
+ if (aad(sa)->denied & NET_PERMS_MASK) {
+ audit_log_format(ab, " denied_mask=");
+ aa_audit_perm_mask(ab, aad(sa)->denied, NULL, 0,
+ net_mask_names, NET_PERMS_MASK);
+ }
+ }
+ if (aad(sa)->peer) {
+ audit_log_format(ab, " peer=");
+ aa_label_xaudit(ab, labels_ns(aad(sa)->label), aad(sa)->peer,
+ FLAGS_NONE, GFP_ATOMIC);
+ }
+}
+
+
+/* Generic af perm */
+int aa_profile_af_perm(struct aa_profile *profile, struct common_audit_data *sa,
+ u32 request, u16 family, int type)
+{
+ struct aa_perms perms = { };
+
+ AA_BUG(family >= AF_MAX);
+ AA_BUG(type < 0 || type >= SOCK_MAX);
+
+ if (profile_unconfined(profile))
+ return 0;
+
+ perms.allow = (profile->net.allow[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ perms.audit = (profile->net.audit[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ perms.quiet = (profile->net.quiet[family] & (1 << type)) ?
+ ALL_PERMS_MASK : 0;
+ aa_apply_modes_to_perms(profile, &perms);
+
+ return aa_check_perms(profile, &perms, request, sa, audit_net_cb);
+}
+
+int aa_af_perm(struct aa_label *label, const char *op, u32 request, u16 family,
+ int type, int protocol)
+{
+ struct aa_profile *profile;
+ DEFINE_AUDIT_NET(sa, op, NULL, family, type, protocol);
+
+ return fn_for_each_confined(label, profile,
+ aa_profile_af_perm(profile, &sa, request, family,
+ type));
+}
+
+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);
+
+ AA_BUG(!label);
+ AA_BUG(!sk);
+
+ if (unconfined(label))
+ return 0;
+
+ return fn_for_each_confined(label, profile,
+ aa_profile_af_sk_perm(profile, &sa, request, sk));
+}
+
+int aa_sk_perm(const char *op, u32 request, struct sock *sk)
+{
+ struct aa_label *label;
+ int error;
+
+ AA_BUG(!sk);
+ AA_BUG(in_interrupt());
+
+ /* TODO: switch to begin_current_label ???? */
+ label = begin_current_label_crit_section();
+ error = aa_label_sk_perm(label, op, request, sk);
+ end_current_label_crit_section(label);
+
+ return error;
+}
+
+
+int aa_sock_file_perm(struct aa_label *label, const char *op, u32 request,
+ struct socket *sock)
+{
+ AA_BUG(!label);
+ AA_BUG(!sock);
+ AA_BUG(!sock->sk);
+
+ return aa_label_sk_perm(label, op, request, sock->sk);
+}
return NULL;
}
-/**
- * aa_new_null_profile - create or find a null-X learning profile
- * @parent: profile that caused this profile to be created (NOT NULL)
- * @hat: true if the null- learning profile is a hat
- * @base: name to base the null profile off of
- * @gfp: type of allocation
- *
- * Find/Create a null- complain mode profile used in learning mode. The
- * name of the profile is unique and follows the format of parent//null-XXX.
- * where XXX is based on the @name or if that fails or is not supplied
- * a unique number
- *
- * null profiles are added to the profile list but the list does not
- * hold a count on them so that they are automatically released when
- * not in use.
- *
- * Returns: new refcounted profile else NULL on failure
- */
-struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
- const char *base, gfp_t gfp)
-{
- struct aa_profile *profile;
- char *name;
-
- AA_BUG(!parent);
-
- if (base) {
- name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
- gfp);
- if (name) {
- sprintf(name, "%s//null-%s", parent->base.hname, base);
- goto name;
- }
- /* fall through to try shorter uniq */
- }
-
- name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
- if (!name)
- return NULL;
- sprintf(name, "%s//null-%x", parent->base.hname,
- atomic_inc_return(&parent->ns->uniq_null));
-
-name:
- /* lookup to see if this is a dup creation */
- profile = aa_find_child(parent, basename(name));
- if (profile)
- goto out;
-
- profile = aa_alloc_profile(name, NULL, gfp);
- if (!profile)
- goto fail;
-
- profile->mode = APPARMOR_COMPLAIN;
- profile->label.flags |= FLAG_NULL;
- if (hat)
- profile->label.flags |= FLAG_HAT;
- profile->path_flags = parent->path_flags;
-
- /* released on free_profile */
- rcu_assign_pointer(profile->parent, aa_get_profile(parent));
- profile->ns = aa_get_ns(parent->ns);
- profile->file.dfa = aa_get_dfa(nulldfa);
- profile->policy.dfa = aa_get_dfa(nulldfa);
-
- mutex_lock(&profile->ns->lock);
- __add_profile(&parent->base.profiles, profile);
- mutex_unlock(&profile->ns->lock);
-
- /* refcount released by caller */
-out:
- kfree(name);
-
- return profile;
-
-fail:
- aa_free_profile(profile);
- return NULL;
-}
-
/* TODO: profile accounting - setup in remove */
/**
return profile;
}
+/**
+ * aa_new_null_profile - create or find a null-X learning profile
+ * @parent: profile that caused this profile to be created (NOT NULL)
+ * @hat: true if the null- learning profile is a hat
+ * @base: name to base the null profile off of
+ * @gfp: type of allocation
+ *
+ * Find/Create a null- complain mode profile used in learning mode. The
+ * name of the profile is unique and follows the format of parent//null-XXX.
+ * where XXX is based on the @name or if that fails or is not supplied
+ * a unique number
+ *
+ * null profiles are added to the profile list but the list does not
+ * hold a count on them so that they are automatically released when
+ * not in use.
+ *
+ * Returns: new refcounted profile else NULL on failure
+ */
+struct aa_profile *aa_new_null_profile(struct aa_profile *parent, bool hat,
+ const char *base, gfp_t gfp)
+{
+ struct aa_profile *p, *profile;
+ const char *bname;
+ char *name;
+
+ AA_BUG(!parent);
+
+ if (base) {
+ name = kmalloc(strlen(parent->base.hname) + 8 + strlen(base),
+ gfp);
+ if (name) {
+ sprintf(name, "%s//null-%s", parent->base.hname, base);
+ goto name;
+ }
+ /* fall through to try shorter uniq */
+ }
+
+ name = kmalloc(strlen(parent->base.hname) + 2 + 7 + 8, gfp);
+ if (!name)
+ return NULL;
+ sprintf(name, "%s//null-%x", parent->base.hname,
+ atomic_inc_return(&parent->ns->uniq_null));
+
+name:
+ /* lookup to see if this is a dup creation */
+ bname = basename(name);
+ profile = aa_find_child(parent, bname);
+ if (profile)
+ goto out;
+
+ profile = aa_alloc_profile(name, NULL, gfp);
+ if (!profile)
+ goto fail;
+
+ profile->mode = APPARMOR_COMPLAIN;
+ profile->label.flags |= FLAG_NULL;
+ if (hat)
+ profile->label.flags |= FLAG_HAT;
+ profile->path_flags = parent->path_flags;
+
+ /* released on free_profile */
+ rcu_assign_pointer(profile->parent, aa_get_profile(parent));
+ profile->ns = aa_get_ns(parent->ns);
+ profile->file.dfa = aa_get_dfa(nulldfa);
+ profile->policy.dfa = aa_get_dfa(nulldfa);
+
+ mutex_lock(&profile->ns->lock);
+ p = __find_child(&parent->base.profiles, bname);
+ if (p) {
+ aa_free_profile(profile);
+ profile = aa_get_profile(p);
+ } else {
+ __add_profile(&parent->base.profiles, profile);
+ }
+ mutex_unlock(&profile->ns->lock);
+
+ /* refcount released by caller */
+out:
+ kfree(name);
+
+ return profile;
+
+fail:
+ aa_free_profile(profile);
+ return NULL;
+}
+
/**
* replacement_allowed - test to see if replacement is allowed
* @profile: profile to test if it can be replaced (MAYBE NULL)
ns->unconfined->label.flags |= FLAG_IX_ON_NAME_ERROR |
FLAG_IMMUTIBLE | FLAG_NS_COUNT | FLAG_UNCONFINED;
ns->unconfined->mode = APPARMOR_UNCONFINED;
+ ns->unconfined->file.dfa = aa_get_dfa(nulldfa);
+ ns->unconfined->policy.dfa = aa_get_dfa(nulldfa);
/* ns and ns->unconfined share ns->unconfined refcount */
ns->unconfined->ns = ns;
audit_log_format(ab, " ns=");
audit_log_untrustedstring(ab, aad(sa)->iface.ns);
}
- if (aad(sa)->iface.name) {
+ if (aad(sa)->name) {
audit_log_format(ab, " name=");
- audit_log_untrustedstring(ab, aad(sa)->iface.name);
+ audit_log_untrustedstring(ab, aad(sa)->name);
}
if (aad(sa)->iface.pos)
audit_log_format(ab, " offset=%ld", aad(sa)->iface.pos);
aad(&sa)->iface.pos = e->pos - e->start;
aad(&sa)->iface.ns = ns_name;
if (new)
- aad(&sa)->iface.name = new->base.hname;
+ aad(&sa)->name = new->base.hname;
else
- aad(&sa)->iface.name = name;
+ aad(&sa)->name = name;
aad(&sa)->info = info;
aad(&sa)->error = error;
return 0;
}
+static bool unpack_u16(struct aa_ext *e, u16 *data, const char *name)
+{
+ if (unpack_nameX(e, AA_U16, name)) {
+ if (!inbounds(e, sizeof(u16)))
+ return 0;
+ if (data)
+ *data = le16_to_cpu(get_unaligned((__le16 *) e->pos));
+ e->pos += sizeof(u16);
+ return 1;
+ }
+ return 0;
+}
+
static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name)
{
if (unpack_nameX(e, AA_U32, name)) {
*/
static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile)
{
- void *pos = e->pos;
+ void *saved_pos = e->pos;
/* exec table is optional */
if (unpack_nameX(e, AA_STRUCT, "xtable")) {
fail:
aa_free_domain_entries(&profile->file.trans);
- e->pos = pos;
+ e->pos = saved_pos;
return 0;
}
{
struct aa_profile *profile = NULL;
const char *tmpname, *tmpns = NULL, *name = NULL;
- size_t ns_len;
+ const char *info = "failed to unpack profile";
+ size_t size = 0, ns_len;
struct rhashtable_params params = { 0 };
char *key = NULL;
struct aa_data *data;
tmpname = aa_splitn_fqname(name, strlen(name), &tmpns, &ns_len);
if (tmpns) {
*ns_name = kstrndup(tmpns, ns_len, GFP_KERNEL);
- if (!*ns_name)
+ if (!*ns_name) {
+ info = "out of memory";
goto fail;
+ }
name = tmpname;
}
if (IS_ERR(profile->xmatch)) {
error = PTR_ERR(profile->xmatch);
profile->xmatch = NULL;
+ info = "bad xmatch";
goto fail;
}
/* xmatch_len is not optional if xmatch is set */
if (profile->xmatch) {
- if (!unpack_u32(e, &tmp, NULL))
+ if (!unpack_u32(e, &tmp, NULL)) {
+ info = "missing xmatch len";
goto fail;
+ }
profile->xmatch_len = tmp;
}
(void) unpack_str(e, &profile->disconnected, "disconnected");
/* per profile debug flags (complain, audit) */
- if (!unpack_nameX(e, AA_STRUCT, "flags"))
+ if (!unpack_nameX(e, AA_STRUCT, "flags")) {
+ info = "profile missing flags";
goto fail;
+ }
+ info = "failed to unpack profile flags";
if (!unpack_u32(e, &tmp, NULL))
goto fail;
if (tmp & PACKED_FLAG_HAT)
/* set a default value if path_flags field is not present */
profile->path_flags = PATH_MEDIATE_DELETED;
+ info = "failed to unpack profile capabilities";
if (!unpack_u32(e, &(profile->caps.allow.cap[0]), NULL))
goto fail;
if (!unpack_u32(e, &(profile->caps.audit.cap[0]), NULL))
if (!unpack_u32(e, &tmpcap.cap[0], NULL))
goto fail;
+ info = "failed to unpack upper profile capabilities";
if (unpack_nameX(e, AA_STRUCT, "caps64")) {
/* optional upper half of 64 bit caps */
if (!unpack_u32(e, &(profile->caps.allow.cap[1]), NULL))
goto fail;
}
+ info = "failed to unpack extended profile capabilities";
if (unpack_nameX(e, AA_STRUCT, "capsx")) {
/* optional extended caps mediation mask */
if (!unpack_u32(e, &(profile->caps.extended.cap[0]), NULL))
goto fail;
}
- if (!unpack_rlimits(e, profile))
+ if (!unpack_rlimits(e, profile)) {
+ info = "failed to unpack profile rlimits";
goto fail;
+ }
+
+ size = unpack_array(e, "net_allowed_af");
+ if (size) {
+
+ for (i = 0; i < size; i++) {
+ /* discard extraneous rules that this kernel will
+ * never request
+ */
+ if (i >= AF_MAX) {
+ u16 tmp;
+
+ if (!unpack_u16(e, &tmp, NULL) ||
+ !unpack_u16(e, &tmp, NULL) ||
+ !unpack_u16(e, &tmp, NULL))
+ goto fail;
+ continue;
+ }
+ if (!unpack_u16(e, &profile->net.allow[i], NULL))
+ goto fail;
+ if (!unpack_u16(e, &profile->net.audit[i], NULL))
+ goto fail;
+ if (!unpack_u16(e, &profile->net.quiet[i], NULL))
+ goto fail;
+ }
+ if (!unpack_nameX(e, AA_ARRAYEND, NULL))
+ goto fail;
+ }
+ if (VERSION_LT(e->version, v7)) {
+ /* pre v7 policy always allowed these */
+ profile->net.allow[AF_UNIX] = 0xffff;
+ profile->net.allow[AF_NETLINK] = 0xffff;
+ }
if (unpack_nameX(e, AA_STRUCT, "policydb")) {
/* generic policy dfa - optional and may be NULL */
+ info = "failed to unpack policydb";
profile->policy.dfa = unpack_dfa(e);
if (IS_ERR(profile->policy.dfa)) {
error = PTR_ERR(profile->policy.dfa);
if (IS_ERR(profile->file.dfa)) {
error = PTR_ERR(profile->file.dfa);
profile->file.dfa = NULL;
+ info = "failed to unpack profile file rules";
goto fail;
} else if (profile->file.dfa) {
if (!unpack_u32(e, &profile->file.start, "dfa_start"))
} else
profile->file.dfa = aa_get_dfa(nulldfa);
- if (!unpack_trans_table(e, profile))
+ if (!unpack_trans_table(e, profile)) {
+ info = "failed to unpack profile transition table";
goto fail;
+ }
if (unpack_nameX(e, AA_STRUCT, "data")) {
+ info = "out of memory";
profile->data = kzalloc(sizeof(*profile->data), GFP_KERNEL);
if (!profile->data)
goto fail;
params.hashfn = strhash;
params.obj_cmpfn = datacmp;
- if (rhashtable_init(profile->data, ¶ms))
+ if (rhashtable_init(profile->data, ¶ms)) {
+ info = "failed to init key, value hash table";
goto fail;
+ }
while (unpack_strdup(e, &key, NULL)) {
data = kzalloc(sizeof(*data), GFP_KERNEL);
profile->data->p);
}
- if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+ if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+ info = "failed to unpack end of key, value data table";
goto fail;
+ }
}
- if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+ if (!unpack_nameX(e, AA_STRUCTEND, NULL)) {
+ info = "failed to unpack end of profile";
goto fail;
+ }
return profile;
name = NULL;
else if (!name)
name = "unknown";
- audit_iface(profile, NULL, name, "failed to unpack profile", e,
- error);
+ audit_iface(profile, NULL, name, info, e, error);
aa_free_profile(profile);
return ERR_PTR(error);
* if not specified use previous version
* Mask off everything that is not kernel abi version
*/
- if (VERSION_LT(e->version, v5) && VERSION_GT(e->version, v7)) {
+ if (VERSION_LT(e->version, v5) || VERSION_GT(e->version, v7)) {
audit_iface(NULL, NULL, NULL, "unsupported interface version",
e, error);
return error;
*
* Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
* affects the security markings on that inode, and if it is, should
- * inode_killpriv() be invoked or the change rejected?
+ * inode_killpriv() be invoked or the change rejected.
*
- * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and
- * -ve to deny the change.
+ * Returns 1 if security.capability has a value, meaning inode_killpriv()
+ * is required, 0 otherwise, meaning inode_killpriv() is not required.
*/
int cap_inode_need_killpriv(struct dentry *dentry)
{
bool "Large payload keys"
depends on KEYS
depends on TMPFS
- depends on (CRYPTO_ANSI_CPRNG = y || CRYPTO_DRBG = y)
select CRYPTO_AES
- select CRYPTO_ECB
- select CRYPTO_RNG
+ select CRYPTO_GCM
help
This option provides support for holding large keys within the kernel
(for example Kerberos ticket caches). The data may be stored out to
/* Large capacity key type
*
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
* Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
#include <linux/shmem_fs.h>
#include <linux/err.h>
#include <linux/scatterlist.h>
+#include <linux/random.h>
#include <keys/user-type.h>
#include <keys/big_key-type.h>
-#include <crypto/rng.h>
-#include <crypto/skcipher.h>
+#include <crypto/aead.h>
/*
* Layout of key payload words.
/*
* Key size for big_key data encryption
*/
-#define ENC_KEY_SIZE 16
+#define ENC_KEY_SIZE 32
+
+/*
+ * Authentication tag length
+ */
+#define ENC_AUTHTAG_SIZE 16
/*
* big_key defined keys take an arbitrary string as the description and an
.destroy = big_key_destroy,
.describe = big_key_describe,
.read = big_key_read,
+ /* no ->update(); don't add it without changing big_key_crypt() nonce */
};
/*
- * Crypto names for big_key data encryption
+ * Crypto names for big_key data authenticated encryption
*/
-static const char big_key_rng_name[] = "stdrng";
-static const char big_key_alg_name[] = "ecb(aes)";
+static const char big_key_alg_name[] = "gcm(aes)";
/*
- * Crypto algorithms for big_key data encryption
+ * Crypto algorithms for big_key data authenticated encryption
*/
-static struct crypto_rng *big_key_rng;
-static struct crypto_skcipher *big_key_skcipher;
+static struct crypto_aead *big_key_aead;
/*
- * Generate random key to encrypt big_key data
+ * Since changing the key affects the entire object, we need a mutex.
*/
-static inline int big_key_gen_enckey(u8 *key)
-{
- return crypto_rng_get_bytes(big_key_rng, key, ENC_KEY_SIZE);
-}
+static DEFINE_MUTEX(big_key_aead_lock);
/*
* Encrypt/decrypt big_key data
*/
static int big_key_crypt(enum big_key_op op, u8 *data, size_t datalen, u8 *key)
{
- int ret = -EINVAL;
+ int ret;
struct scatterlist sgio;
- SKCIPHER_REQUEST_ON_STACK(req, big_key_skcipher);
-
- if (crypto_skcipher_setkey(big_key_skcipher, key, ENC_KEY_SIZE)) {
+ struct aead_request *aead_req;
+ /* We always use a zero nonce. The reason we can get away with this is
+ * because we're using a different randomly generated key for every
+ * different encryption. Notably, too, key_type_big_key doesn't define
+ * an .update function, so there's no chance we'll wind up reusing the
+ * key to encrypt updated data. Simply put: one key, one encryption.
+ */
+ u8 zero_nonce[crypto_aead_ivsize(big_key_aead)];
+
+ aead_req = aead_request_alloc(big_key_aead, GFP_KERNEL);
+ if (!aead_req)
+ return -ENOMEM;
+
+ memset(zero_nonce, 0, sizeof(zero_nonce));
+ sg_init_one(&sgio, data, datalen + (op == BIG_KEY_ENC ? ENC_AUTHTAG_SIZE : 0));
+ aead_request_set_crypt(aead_req, &sgio, &sgio, datalen, zero_nonce);
+ aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
+ aead_request_set_ad(aead_req, 0);
+
+ mutex_lock(&big_key_aead_lock);
+ if (crypto_aead_setkey(big_key_aead, key, ENC_KEY_SIZE)) {
ret = -EAGAIN;
goto error;
}
-
- skcipher_request_set_tfm(req, big_key_skcipher);
- skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
- NULL, NULL);
-
- sg_init_one(&sgio, data, datalen);
- skcipher_request_set_crypt(req, &sgio, &sgio, datalen, NULL);
-
if (op == BIG_KEY_ENC)
- ret = crypto_skcipher_encrypt(req);
+ ret = crypto_aead_encrypt(aead_req);
else
- ret = crypto_skcipher_decrypt(req);
-
- skcipher_request_zero(req);
-
+ ret = crypto_aead_decrypt(aead_req);
error:
+ mutex_unlock(&big_key_aead_lock);
+ aead_request_free(aead_req);
return ret;
}
*
* File content is stored encrypted with randomly generated key.
*/
- size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+ size_t enclen = datalen + ENC_AUTHTAG_SIZE;
loff_t pos = 0;
- /* prepare aligned data to encrypt */
data = kmalloc(enclen, GFP_KERNEL);
if (!data)
return -ENOMEM;
-
memcpy(data, prep->data, datalen);
- memset(data + datalen, 0x00, enclen - datalen);
/* generate random key */
enckey = kmalloc(ENC_KEY_SIZE, GFP_KERNEL);
ret = -ENOMEM;
goto error;
}
-
- ret = big_key_gen_enckey(enckey);
- if (ret)
+ ret = get_random_bytes_wait(enckey, ENC_KEY_SIZE);
+ if (unlikely(ret))
goto err_enckey;
/* encrypt aligned data */
- ret = big_key_crypt(BIG_KEY_ENC, data, enclen, enckey);
+ ret = big_key_crypt(BIG_KEY_ENC, data, datalen, enckey);
if (ret)
goto err_enckey;
*path = file->f_path;
path_get(path);
fput(file);
- kfree(data);
+ kzfree(data);
} else {
/* Just store the data in a buffer */
void *data = kmalloc(datalen, GFP_KERNEL);
err_fput:
fput(file);
err_enckey:
- kfree(enckey);
+ kzfree(enckey);
error:
- kfree(data);
+ kzfree(data);
return ret;
}
path_put(path);
}
- kfree(prep->payload.data[big_key_data]);
+ kzfree(prep->payload.data[big_key_data]);
}
/*
path->mnt = NULL;
path->dentry = NULL;
}
- kfree(key->payload.data[big_key_data]);
+ kzfree(key->payload.data[big_key_data]);
key->payload.data[big_key_data] = NULL;
}
struct file *file;
u8 *data;
u8 *enckey = (u8 *)key->payload.data[big_key_data];
- size_t enclen = ALIGN(datalen, crypto_skcipher_blocksize(big_key_skcipher));
+ size_t enclen = datalen + ENC_AUTHTAG_SIZE;
loff_t pos = 0;
data = kmalloc(enclen, GFP_KERNEL);
err_fput:
fput(file);
error:
- kfree(data);
+ kzfree(data);
} else {
ret = datalen;
if (copy_to_user(buffer, key->payload.data[big_key_data],
*/
static int __init big_key_init(void)
{
- struct crypto_skcipher *cipher;
- struct crypto_rng *rng;
int ret;
- rng = crypto_alloc_rng(big_key_rng_name, 0, 0);
- if (IS_ERR(rng)) {
- pr_err("Can't alloc rng: %ld\n", PTR_ERR(rng));
- return PTR_ERR(rng);
- }
-
- big_key_rng = rng;
-
- /* seed RNG */
- ret = crypto_rng_reset(rng, NULL, crypto_rng_seedsize(rng));
- if (ret) {
- pr_err("Can't reset rng: %d\n", ret);
- goto error_rng;
- }
-
/* init block cipher */
- cipher = crypto_alloc_skcipher(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(cipher)) {
- ret = PTR_ERR(cipher);
+ big_key_aead = crypto_alloc_aead(big_key_alg_name, 0, CRYPTO_ALG_ASYNC);
+ if (IS_ERR(big_key_aead)) {
+ ret = PTR_ERR(big_key_aead);
pr_err("Can't alloc crypto: %d\n", ret);
- goto error_rng;
+ return ret;
+ }
+ ret = crypto_aead_setauthsize(big_key_aead, ENC_AUTHTAG_SIZE);
+ if (ret < 0) {
+ pr_err("Can't set crypto auth tag len: %d\n", ret);
+ goto free_aead;
}
-
- big_key_skcipher = cipher;
ret = register_key_type(&key_type_big_key);
if (ret < 0) {
pr_err("Can't register type: %d\n", ret);
- goto error_cipher;
+ goto free_aead;
}
return 0;
-error_cipher:
- crypto_free_skcipher(big_key_skcipher);
-error_rng:
- crypto_free_rng(big_key_rng);
+free_aead:
+ crypto_free_aead(big_key_aead);
return ret;
}
extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
-extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
+extern struct key *find_keyring_by_name(const char *name, bool uid_keyring);
extern int install_user_keyrings(void);
extern int install_thread_keyring_to_cred(struct cred *);
struct key_user *key_user_lookup(kuid_t uid)
{
struct key_user *candidate = NULL, *user;
- struct rb_node *parent = NULL;
- struct rb_node **p;
+ struct rb_node *parent, **p;
try_again:
+ parent = NULL;
p = &key_user_tree.rb_node;
spin_lock(&key_user_lock);
key->flags |= 1 << KEY_FLAG_IN_QUOTA;
if (flags & KEY_ALLOC_BUILT_IN)
key->flags |= 1 << KEY_FLAG_BUILTIN;
+ if (flags & KEY_ALLOC_UID_KEYRING)
+ key->flags |= 1 << KEY_FLAG_UID_KEYRING;
#ifdef KEY_DEBUGGING
key->magic = KEY_DEBUG_MAGIC;
key = key_ref_to_ptr(key_ref);
+ if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+ ret = -ENOKEY;
+ goto error2;
+ }
+
/* see if we can read it directly */
ret = key_permission(key_ref, KEY_NEED_READ);
if (ret == 0)
goto can_read_key;
if (ret != -EACCES)
- goto error;
+ goto error2;
/* we can't; see if it's searchable from this process's keyrings
* - we automatically take account of the fact that it may be
}
ret = keyctl_change_reqkey_auth(authkey);
- if (ret < 0)
- goto error;
+ if (ret == 0)
+ ret = authkey->serial;
key_put(authkey);
-
- ret = authkey->serial;
error:
return ret;
}
}
struct keyring_read_iterator_context {
- size_t qty;
+ size_t buflen;
size_t count;
key_serial_t __user *buffer;
};
int ret;
kenter("{%s,%d},,{%zu/%zu}",
- key->type->name, key->serial, ctx->count, ctx->qty);
+ key->type->name, key->serial, ctx->count, ctx->buflen);
- if (ctx->count >= ctx->qty)
+ if (ctx->count >= ctx->buflen)
return 1;
ret = put_user(key->serial, ctx->buffer);
return 0;
/* Calculate how much data we could return */
- ctx.qty = nr_keys * sizeof(key_serial_t);
-
if (!buffer || !buflen)
- return ctx.qty;
-
- if (buflen > ctx.qty)
- ctx.qty = buflen;
+ return nr_keys * sizeof(key_serial_t);
/* Copy the IDs of the subscribed keys into the buffer */
ctx.buffer = (key_serial_t __user *)buffer;
+ ctx.buflen = buflen;
ctx.count = 0;
ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx);
if (ret < 0) {
/*
* Find a keyring with the specified name.
*
- * All named keyrings in the current user namespace are searched, provided they
- * grant Search permission directly to the caller (unless this check is
- * skipped). Keyrings whose usage points have reached zero or who have been
- * revoked are skipped.
+ * Only keyrings that have nonzero refcount, are not revoked, and are owned by a
+ * user in the current user namespace are considered. If @uid_keyring is %true,
+ * the keyring additionally must have been allocated as a user or user session
+ * keyring; otherwise, it must grant Search permission directly to the caller.
*
* Returns a pointer to the keyring with the keyring's refcount having being
* incremented on success. -ENOKEY is returned if a key could not be found.
*/
-struct key *find_keyring_by_name(const char *name, bool skip_perm_check)
+struct key *find_keyring_by_name(const char *name, bool uid_keyring)
{
struct key *keyring;
int bucket;
if (strcmp(keyring->description, name) != 0)
continue;
- if (!skip_perm_check &&
- key_permission(make_key_ref(keyring, 0),
- KEY_NEED_SEARCH) < 0)
- continue;
+ if (uid_keyring) {
+ if (!test_bit(KEY_FLAG_UID_KEYRING,
+ &keyring->flags))
+ continue;
+ } else {
+ if (key_permission(make_key_ref(keyring, 0),
+ KEY_NEED_SEARCH) < 0)
+ continue;
+ }
/* we've got a match but we might end up racing with
* key_cleanup() if the keyring is currently 'dead'
struct keyring_search_context ctx = {
.index_key.type = key->type,
.index_key.description = key->description,
- .cred = current_cred(),
+ .cred = m->file->f_cred,
.match_data.cmp = lookup_user_key_possessed,
.match_data.raw_data = key,
.match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT,
}
}
- /* check whether the current task is allowed to view the key (assuming
- * non-possession)
- * - the caller holds a spinlock, and thus the RCU read lock, making our
- * access to __current_cred() safe
- */
+ /* check whether the current task is allowed to view the key */
rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW);
if (rc < 0)
return 0;
if (IS_ERR(uid_keyring)) {
uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID,
cred, user_keyring_perm,
- KEY_ALLOC_IN_QUOTA,
+ KEY_ALLOC_UID_KEYRING |
+ KEY_ALLOC_IN_QUOTA,
NULL, NULL);
if (IS_ERR(uid_keyring)) {
ret = PTR_ERR(uid_keyring);
session_keyring =
keyring_alloc(buf, user->uid, INVALID_GID,
cred, user_keyring_perm,
- KEY_ALLOC_IN_QUOTA,
+ KEY_ALLOC_UID_KEYRING |
+ KEY_ALLOC_IN_QUOTA,
NULL, NULL);
if (IS_ERR(session_keyring)) {
ret = PTR_ERR(session_keyring);
}
}
+static void free_request_key_auth(struct request_key_auth *rka)
+{
+ if (!rka)
+ return;
+ key_put(rka->target_key);
+ key_put(rka->dest_keyring);
+ if (rka->cred)
+ put_cred(rka->cred);
+ kfree(rka->callout_info);
+ kfree(rka);
+}
+
/*
* Destroy an instantiation authorisation token key.
*/
kenter("{%d}", key->serial);
- if (rka->cred) {
- put_cred(rka->cred);
- rka->cred = NULL;
- }
-
- key_put(rka->target_key);
- key_put(rka->dest_keyring);
- kfree(rka->callout_info);
- kfree(rka);
+ free_request_key_auth(rka);
}
/*
const struct cred *cred = current->cred;
struct key *authkey = NULL;
char desc[20];
- int ret;
+ int ret = -ENOMEM;
kenter("%d,", target->serial);
/* allocate a auth record */
- rka = kmalloc(sizeof(*rka), GFP_KERNEL);
- if (!rka) {
- kleave(" = -ENOMEM");
- return ERR_PTR(-ENOMEM);
- }
- rka->callout_info = kmalloc(callout_len, GFP_KERNEL);
- if (!rka->callout_info) {
- kleave(" = -ENOMEM");
- kfree(rka);
- return ERR_PTR(-ENOMEM);
- }
+ rka = kzalloc(sizeof(*rka), GFP_KERNEL);
+ if (!rka)
+ goto error;
+ rka->callout_info = kmemdup(callout_info, callout_len, GFP_KERNEL);
+ if (!rka->callout_info)
+ goto error_free_rka;
+ rka->callout_len = callout_len;
/* see if the calling process is already servicing the key request of
* another process */
/* if the auth key has been revoked, then the key we're
* servicing is already instantiated */
- if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags))
- goto auth_key_revoked;
+ if (test_bit(KEY_FLAG_REVOKED,
+ &cred->request_key_auth->flags)) {
+ up_read(&cred->request_key_auth->sem);
+ ret = -EKEYREVOKED;
+ goto error_free_rka;
+ }
irka = cred->request_key_auth->payload.data[0];
rka->cred = get_cred(irka->cred);
rka->target_key = key_get(target);
rka->dest_keyring = key_get(dest_keyring);
- memcpy(rka->callout_info, callout_info, callout_len);
- rka->callout_len = callout_len;
/* allocate the auth key */
sprintf(desc, "%x", target->serial);
KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA, NULL);
if (IS_ERR(authkey)) {
ret = PTR_ERR(authkey);
- goto error_alloc;
+ goto error_free_rka;
}
/* construct the auth key */
ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL);
if (ret < 0)
- goto error_inst;
+ goto error_put_authkey;
kleave(" = {%d,%d}", authkey->serial, refcount_read(&authkey->usage));
return authkey;
-auth_key_revoked:
- up_read(&cred->request_key_auth->sem);
- kfree(rka->callout_info);
- kfree(rka);
- kleave("= -EKEYREVOKED");
- return ERR_PTR(-EKEYREVOKED);
-
-error_inst:
- key_revoke(authkey);
+error_put_authkey:
key_put(authkey);
-error_alloc:
- key_put(rka->target_key);
- key_put(rka->dest_keyring);
- kfree(rka->callout_info);
- kfree(rka);
+error_free_rka:
+ free_request_key_auth(rka);
+error:
kleave("= %d", ret);
return ERR_PTR(ret);
}
/* kvm attributes for KVM_S390_VM_TOD */
#define KVM_S390_VM_TOD_LOW 0
#define KVM_S390_VM_TOD_HIGH 1
+#define KVM_S390_VM_TOD_EXT 2
+
+struct kvm_s390_vm_tod_clock {
+ __u8 epoch_idx;
+ __u64 tod;
+};
/* kvm attributes for KVM_S390_VM_CPU_MODEL */
/* processor related attributes are r/w */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31))
# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+# define DISABLE_PCID 0
#else
# define DISABLE_VME 0
# define DISABLE_K6_MTRR 0
# define DISABLE_CYRIX_ARR 0
# define DISABLE_CENTAUR_MCR 0
+# define DISABLE_PCID (1<<(X86_FEATURE_PCID & 31))
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
#define DISABLED_MASK1 0
#define DISABLED_MASK2 0
#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
-#define DISABLED_MASK4 0
+#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
#define DISABLED_MASK7 0
--- /dev/null
+#ifndef _ASM_GENERIC_HUGETLB_ENCODE_H_
+#define _ASM_GENERIC_HUGETLB_ENCODE_H_
+
+/*
+ * Several system calls take a flag to request "hugetlb" huge pages.
+ * Without further specification, these system calls will use the
+ * system's default huge page size. If a system supports multiple
+ * huge page sizes, the desired huge page size can be specified in
+ * bits [26:31] of the flag arguments. The value in these 6 bits
+ * will encode the log2 of the huge page size.
+ *
+ * The following definitions are associated with this huge page size
+ * encoding in flag arguments. System call specific header files
+ * that use this encoding should include this file. They can then
+ * provide definitions based on these with their own specific prefix.
+ * for example:
+ * #define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+ */
+
+#define HUGETLB_FLAG_ENCODE_SHIFT 26
+#define HUGETLB_FLAG_ENCODE_MASK 0x3f
+
+#define HUGETLB_FLAG_ENCODE_64KB (16 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_512KB (19 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1MB (20 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT)
+#define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT)
+
+#endif /* _ASM_GENERIC_HUGETLB_ENCODE_H_ */
overrides the coredump filter bits */
#define MADV_DODUMP 17 /* Clear the MADV_DONTDUMP flag */
+#define MADV_WIPEONFORK 18 /* Zero memory on fork, child only */
+#define MADV_KEEPONFORK 19 /* Undo MADV_WIPEONFORK */
+
/* compatibility flags */
#define MAP_FILE 0
-/*
- * When MAP_HUGETLB is set bits [26:31] encode the log2 of the huge page size.
- * This gives us 6 bits, which is enough until someone invents 128 bit address
- * spaces.
- *
- * Assume these are all power of twos.
- * When 0 use the default page size.
- */
-#define MAP_HUGE_SHIFT 26
-#define MAP_HUGE_MASK 0x3f
-
#define PKEY_DISABLE_ACCESS 0x1
#define PKEY_DISABLE_WRITE 0x2
#define PKEY_ACCESS_MASK (PKEY_DISABLE_ACCESS |\
struct drm_syncobj_create {
__u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
__u32 flags;
};
__u32 pad;
};
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+struct drm_syncobj_wait {
+ __u64 handles;
+ /* absolute timeout */
+ __s64 timeout_nsec;
+ __u32 count_handles;
+ __u32 flags;
+ __u32 first_signaled; /* only valid when not waiting all */
+ __u32 pad;
+};
+
+struct drm_syncobj_array {
+ __u64 handles;
+ __u32 count_handles;
+ __u32 pad;
+};
+
#if defined(__cplusplus)
}
#endif
#define DRM_IOCTL_SYNCOBJ_DESTROY DRM_IOWR(0xC0, struct drm_syncobj_destroy)
#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD DRM_IOWR(0xC1, struct drm_syncobj_handle)
#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL DRM_IOWR(0xC5, struct drm_syncobj_array)
/**
* Device specific ioctls should only be in their respective headers
#define DRM_I915_GEM_CONTEXT_GETPARAM 0x34
#define DRM_I915_GEM_CONTEXT_SETPARAM 0x35
#define DRM_I915_PERF_OPEN 0x36
+#define DRM_I915_PERF_ADD_CONFIG 0x37
+#define DRM_I915_PERF_REMOVE_CONFIG 0x38
#define DRM_IOCTL_I915_INIT DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
#define DRM_IOCTL_I915_FLUSH DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
#define DRM_IOCTL_I915_PERF_OPEN DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
/* Allow drivers to submit batchbuffers directly to hardware, relying
* on the security mechanisms provided by hardware.
*/
#define I915_PARAM_HAS_EXEC_BATCH_FIRST 48
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures. See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY 49
+
typedef struct drm_i915_getparam {
__s32 param;
/*
__u64 rsvd2;
};
+struct drm_i915_gem_exec_fence {
+ /**
+ * User's handle for a drm_syncobj to wait on or signal.
+ */
+ __u32 handle;
+
+#define I915_EXEC_FENCE_WAIT (1<<0)
+#define I915_EXEC_FENCE_SIGNAL (1<<1)
+ __u32 flags;
+};
+
struct drm_i915_gem_execbuffer2 {
/**
* List of gem_exec_object2 structs
__u32 DR1;
__u32 DR4;
__u32 num_cliprects;
- /** This is a struct drm_clip_rect *cliprects */
+ /**
+ * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
+ * is not set. If I915_EXEC_FENCE_ARRAY is set, then this is a
+ * struct drm_i915_gem_exec_fence *fences.
+ */
__u64 cliprects_ptr;
#define I915_EXEC_RING_MASK (7<<0)
#define I915_EXEC_DEFAULT (0<<0)
* element).
*/
#define I915_EXEC_BATCH_FIRST (1<<18)
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_BATCH_FIRST<<1))
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY (1<<19)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_ARRAY<<1))
#define I915_EXEC_CONTEXT_ID_MASK (0xffffffff)
#define i915_execbuffer2_set_context_id(eb2, context) \
DRM_I915_PERF_RECORD_MAX /* non-ABI */
};
+/**
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+ /** String formatted like "%08x-%04x-%04x-%04x-%012x" */
+ char uuid[36];
+
+ __u32 n_mux_regs;
+ __u32 n_boolean_regs;
+ __u32 n_flex_regs;
+
+ __u64 __user mux_regs_ptr;
+ __u64 __user boolean_regs_ptr;
+ __u64 __user flex_regs_ptr;
+};
+
#if defined(__cplusplus)
}
#endif
#define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
-enum bpf_sockmap_flags {
- BPF_SOCKMAP_UNSPEC,
- BPF_SOCKMAP_STRPARSER,
- __MAX_BPF_SOCKMAP_FLAG
-};
-
/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
* to the given target_fd cgroup the descendent cgroup will be able to
* override effective bpf program that was inherited from this cgroup
* int bpf_redirect(ifindex, flags)
* redirect to another netdev
* @ifindex: ifindex of the net device
- * @flags: bit 0 - if set, redirect to ingress instead of egress
- * other bits - reserved
- * Return: TC_ACT_REDIRECT
+ * @flags:
+ * cls_bpf:
+ * bit 0 - if set, redirect to ingress instead of egress
+ * other bits - reserved
+ * xdp_bpf:
+ * all bits - reserved
+ * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error
+ * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error
+ * int bpf_redirect_map(map, key, flags)
+ * redirect to endpoint in map
+ * @map: pointer to dev map
+ * @key: index in map to lookup
+ * @flags: --
+ * Return: XDP_REDIRECT on success or XDP_ABORT on error
*
* u32 bpf_get_route_realm(skb)
* retrieve a dst's tclassid
FN(skb_adjust_room), \
FN(redirect_map), \
FN(sk_redirect_map), \
- FN(sock_map_update),
+ FN(sock_map_update), \
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
__u32 family;
__u32 type;
__u32 protocol;
+ __u32 mark;
+ __u32 priority;
};
#define XDP_PACKET_HEADROOM 256
/* User return codes for XDP prog type.
* A valid XDP program must return one of these defined values. All other
- * return codes are reserved for future use. Unknown return codes will result
- * in packet drop.
+ * return codes are reserved for future use. Unknown return codes will
+ * result in packet drops and a warning via bpf_warn_invalid_xdp_action().
*/
enum xdp_action {
XDP_ABORTED = 0,
XDP_DROP,
XDP_PASS,
XDP_TX,
+ XDP_REDIRECT,
};
/* user accessible metadata for XDP packet hook
struct kvm_ppc_smmu_info {
__u64 flags;
__u32 slb_size;
- __u32 pad;
+ __u16 data_keys; /* # storage keys supported for data */
+ __u16 instr_keys; /* # storage keys supported for instructions */
struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
};
#ifndef _UAPI_LINUX_MMAN_H
#define _UAPI_LINUX_MMAN_H
-#include <uapi/asm/mman.h>
+#include <asm/mman.h>
+#include <asm-generic/hugetlb_encode.h>
#define MREMAP_MAYMOVE 1
#define MREMAP_FIXED 2
#define OVERCOMMIT_ALWAYS 1
#define OVERCOMMIT_NEVER 2
+/*
+ * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
+ * size other than the default is desired. See hugetlb_encode.h.
+ * All known huge page size encodings are provided here. It is the
+ * responsibility of the application to know which sizes are supported on
+ * the running system. See mmap(2) man page for details.
+ */
+#define MAP_HUGE_SHIFT HUGETLB_FLAG_ENCODE_SHIFT
+#define MAP_HUGE_MASK HUGETLB_FLAG_ENCODE_MASK
+
+#define MAP_HUGE_64KB HUGETLB_FLAG_ENCODE_64KB
+#define MAP_HUGE_512KB HUGETLB_FLAG_ENCODE_512KB
+#define MAP_HUGE_1MB HUGETLB_FLAG_ENCODE_1MB
+#define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB
+#define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB
+#define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB
+#define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB
+#define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB
+#define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB
+#define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB
+
#endif /* _UAPI_LINUX_MMAN_H */
If it's a GCC-compiled .c file, the error may be because the function
uses an inline asm() statement which has a "call" instruction. An
asm() statement with a call instruction must declare the use of the
- stack pointer in its output operand. For example, on x86_64:
+ stack pointer in its output operand. On x86_64, this means adding
+ the ASM_CALL_CONSTRAINT as an output constraint:
- register void *__sp asm("rsp");
- asm volatile("call func" : "+r" (__sp));
+ asm volatile("call func" : ASM_CALL_CONSTRAINT);
Otherwise the stack frame may not get created before the call.
break;
case 0x89:
- if (rex == 0x48 && modrm == 0xe5) {
+ if (rex_w && !rex_r && modrm_mod == 3 && modrm_reg == 4) {
- /* mov %rsp, %rbp */
+ /* mov %rsp, reg */
*type = INSN_STACK;
op->src.type = OP_SRC_REG;
op->src.reg = CFI_SP;
op->dest.type = OP_DEST_REG;
- op->dest.reg = CFI_BP;
+ op->dest.reg = op_to_cfi_reg[modrm_rm][rex_b];
break;
}
case 0x8d:
if (sib == 0x24 && rex_w && !rex_b && !rex_x) {
- /* lea disp(%rsp), reg */
*type = INSN_STACK;
- op->src.type = OP_SRC_ADD;
+ if (!insn.displacement.value) {
+ /* lea (%rsp), reg */
+ op->src.type = OP_SRC_REG;
+ } else {
+ /* lea disp(%rsp), reg */
+ op->src.type = OP_SRC_ADD;
+ op->src.offset = insn.displacement.value;
+ }
op->src.reg = CFI_SP;
- op->src.offset = insn.displacement.value;
op->dest.type = OP_DEST_REG;
op->dest.reg = op_to_cfi_reg[modrm_reg][rex_r];
switch (op->src.type) {
case OP_SRC_REG:
- if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP) {
+ if (op->src.reg == CFI_SP && op->dest.reg == CFI_BP &&
+ cfa->base == CFI_SP &&
+ regs[CFI_BP].base == CFI_CFA &&
+ regs[CFI_BP].offset == -cfa->offset) {
+
+ /* mov %rsp, %rbp */
+ cfa->base = op->dest.reg;
+ state->bp_scratch = false;
+ }
- if (cfa->base == CFI_SP &&
- regs[CFI_BP].base == CFI_CFA &&
- regs[CFI_BP].offset == -cfa->offset) {
+ else if (op->src.reg == CFI_SP &&
+ op->dest.reg == CFI_BP && state->drap) {
- /* mov %rsp, %rbp */
- cfa->base = op->dest.reg;
- state->bp_scratch = false;
- }
+ /* drap: mov %rsp, %rbp */
+ regs[CFI_BP].base = CFI_BP;
+ regs[CFI_BP].offset = -state->stack_size;
+ state->bp_scratch = false;
+ }
- else if (state->drap) {
+ else if (op->src.reg == CFI_SP && cfa->base == CFI_SP) {
- /* drap: mov %rsp, %rbp */
- regs[CFI_BP].base = CFI_BP;
- regs[CFI_BP].offset = -state->stack_size;
- state->bp_scratch = false;
- }
+ /*
+ * mov %rsp, %reg
+ *
+ * This is needed for the rare case where GCC
+ * does:
+ *
+ * mov %rsp, %rax
+ * ...
+ * mov %rax, %rsp
+ */
+ state->vals[op->dest.reg].base = CFI_CFA;
+ state->vals[op->dest.reg].offset = -state->stack_size;
}
else if (op->dest.reg == cfa->base) {
return -1;
}
- sec->data = elf_getdata(s, NULL);
- if (!sec->data) {
- WARN_ELF("elf_getdata");
- return -1;
- }
-
- if (sec->data->d_off != 0 ||
- sec->data->d_size != sec->sh.sh_size) {
- WARN("unexpected data attributes for %s", sec->name);
- return -1;
+ if (sec->sh.sh_size != 0) {
+ sec->data = elf_getdata(s, NULL);
+ if (!sec->data) {
+ WARN_ELF("elf_getdata");
+ return -1;
+ }
+ if (sec->data->d_off != 0 ||
+ sec->data->d_size != sec->sh.sh_size) {
+ WARN("unexpected data attributes for %s",
+ sec->name);
+ return -1;
+ }
}
-
- sec->len = sec->data->d_size;
+ sec->len = sec->sh.sh_size;
}
/* sanity check, one more call to elf_nextscn() should return NULL */
strcat(relaname, base->name);
sec = elf_create_section(elf, relaname, sizeof(GElf_Rela), 0);
+ free(relaname);
if (!sec)
return NULL;
struct section *sec;
Elf_Scn *s;
+ /* Update section headers for changed sections: */
list_for_each_entry(sec, &elf->sections, list) {
if (sec->changed) {
s = elf_getscn(elf->elf, sec->idx);
WARN_ELF("elf_getscn");
return -1;
}
- if (!gelf_update_shdr (s, &sec->sh)) {
+ if (!gelf_update_shdr(s, &sec->sh)) {
WARN_ELF("gelf_update_shdr");
return -1;
}
}
}
+ /* Make sure the new section header entries get updated properly. */
+ elf_flagelf(elf->elf, ELF_C_SET, ELF_F_DIRTY);
+
+ /* Write all changes to the file. */
if (elf_update(elf->elf, ELF_C_WRITE) < 0) {
WARN_ELF("elf_update");
return -1;
tools/perf
-tools/arch/alpha/include/asm/barrier.h
-tools/arch/arm/include/asm/barrier.h
-tools/arch/arm64/include/asm/barrier.h
-tools/arch/ia64/include/asm/barrier.h
-tools/arch/mips/include/asm/barrier.h
-tools/arch/powerpc/include/asm/barrier.h
-tools/arch/s390/include/asm/barrier.h
-tools/arch/sh/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier.h
-tools/arch/sparc/include/asm/barrier_32.h
-tools/arch/sparc/include/asm/barrier_64.h
-tools/arch/tile/include/asm/barrier.h
-tools/arch/x86/include/asm/barrier.h
-tools/arch/x86/include/asm/cmpxchg.h
-tools/arch/x86/include/asm/cpufeatures.h
-tools/arch/x86/include/asm/disabled-features.h
-tools/arch/x86/include/asm/required-features.h
-tools/arch/x86/include/uapi/asm/svm.h
-tools/arch/x86/include/uapi/asm/vmx.h
-tools/arch/x86/include/uapi/asm/kvm.h
-tools/arch/x86/include/uapi/asm/kvm_perf.h
-tools/arch/x86/lib/memcpy_64.S
-tools/arch/x86/lib/memset_64.S
-tools/arch/s390/include/uapi/asm/kvm_perf.h
-tools/arch/s390/include/uapi/asm/sie.h
-tools/arch/xtensa/include/asm/barrier.h
+tools/arch
tools/scripts
tools/build
-tools/arch/x86/include/asm/atomic.h
-tools/arch/x86/include/asm/rmwcc.h
+tools/include
tools/lib/traceevent
tools/lib/api
tools/lib/bpf
tools/lib/bitmap.c
tools/lib/str_error_r.c
tools/lib/vsprintf.c
-tools/include/asm/alternative-asm.h
-tools/include/asm/atomic.h
-tools/include/asm/barrier.h
-tools/include/asm/bug.h
-tools/include/asm-generic/atomic-gcc.h
-tools/include/asm-generic/barrier.h
-tools/include/asm-generic/bitops/arch_hweight.h
-tools/include/asm-generic/bitops/atomic.h
-tools/include/asm-generic/bitops/const_hweight.h
-tools/include/asm-generic/bitops/__ffs.h
-tools/include/asm-generic/bitops/__ffz.h
-tools/include/asm-generic/bitops/__fls.h
-tools/include/asm-generic/bitops/find.h
-tools/include/asm-generic/bitops/fls64.h
-tools/include/asm-generic/bitops/fls.h
-tools/include/asm-generic/bitops/hweight.h
-tools/include/asm-generic/bitops.h
-tools/include/linux/atomic.h
-tools/include/linux/bitops.h
-tools/include/linux/compiler.h
-tools/include/linux/compiler-gcc.h
-tools/include/linux/coresight-pmu.h
-tools/include/linux/bug.h
-tools/include/linux/filter.h
-tools/include/linux/hash.h
-tools/include/linux/kernel.h
-tools/include/linux/list.h
-tools/include/linux/log2.h
-tools/include/uapi/asm-generic/fcntl.h
-tools/include/uapi/asm-generic/ioctls.h
-tools/include/uapi/asm-generic/mman-common.h
-tools/include/uapi/asm-generic/mman.h
-tools/include/uapi/drm/drm.h
-tools/include/uapi/drm/i915_drm.h
-tools/include/uapi/linux/bpf.h
-tools/include/uapi/linux/bpf_common.h
-tools/include/uapi/linux/fcntl.h
-tools/include/uapi/linux/hw_breakpoint.h
-tools/include/uapi/linux/kvm.h
-tools/include/uapi/linux/mman.h
-tools/include/uapi/linux/perf_event.h
-tools/include/uapi/linux/sched.h
-tools/include/uapi/linux/stat.h
-tools/include/uapi/linux/vhost.h
-tools/include/uapi/sound/asound.h
-tools/include/linux/poison.h
-tools/include/linux/rbtree.h
-tools/include/linux/rbtree_augmented.h
-tools/include/linux/refcount.h
-tools/include/linux/string.h
-tools/include/linux/stringify.h
-tools/include/linux/types.h
-tools/include/linux/err.h
-tools/include/linux/bitmap.h
-tools/include/linux/time64.h
-tools/arch/*/include/uapi/asm/mman.h
-tools/arch/*/include/uapi/asm/perf_regs.h
libperf-y += header.o
-libperf-y += sym-handling.o
libperf-y += kvm-stat.o
libperf-$(CONFIG_DWARF) += dwarf-regs.o
+++ /dev/null
-/*
- * Architecture specific ELF symbol handling and relocation mapping.
- *
- * Copyright 2017 IBM Corp.
- * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.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 only)
- * as published by the Free Software Foundation.
- */
-
-#include "symbol.h"
-
-#ifdef HAVE_LIBELF_SUPPORT
-bool elf__needs_adjust_symbols(GElf_Ehdr ehdr)
-{
- if (ehdr.e_type == ET_EXEC)
- return false;
- return ehdr.e_type == ET_REL || ehdr.e_type == ET_DYN;
-}
-
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
- GElf_Shdr *shdr __maybe_unused,
- struct map *map)
-{
- if (map->type == MAP__FUNCTION)
- sym->st_value += map->start;
-}
-#endif
callchain_param.mode = CHAIN_FOLDED;
return 0;
}
-
- pr_err("Invalid callchain mode: %s\n", value);
return -1;
}
callchain_param.order_set = true;
return 0;
}
-
- pr_err("Invalid callchain order: %s\n", value);
return -1;
}
callchain_param.branch_callstack = 1;
return 0;
}
-
- pr_err("Invalid callchain sort key: %s\n", value);
return -1;
}
callchain_param.value = CCVAL_COUNT;
return 0;
}
-
- pr_err("Invalid callchain config key: %s\n", value);
return -1;
}
return ret;
}
- if (!strcmp(var, "print-type"))
- return parse_callchain_mode(value);
- if (!strcmp(var, "order"))
- return parse_callchain_order(value);
- if (!strcmp(var, "sort-key"))
- return parse_callchain_sort_key(value);
+ if (!strcmp(var, "print-type")){
+ int ret;
+ ret = parse_callchain_mode(value);
+ if (ret == -1)
+ pr_err("Invalid callchain mode: %s\n", value);
+ return ret;
+ }
+ if (!strcmp(var, "order")){
+ int ret;
+ ret = parse_callchain_order(value);
+ if (ret == -1)
+ pr_err("Invalid callchain order: %s\n", value);
+ return ret;
+ }
+ if (!strcmp(var, "sort-key")){
+ int ret;
+ ret = parse_callchain_sort_key(value);
+ if (ret == -1)
+ pr_err("Invalid callchain sort key: %s\n", value);
+ return ret;
+ }
if (!strcmp(var, "threshold")) {
callchain_param.min_percent = strtod(value, &endptr);
if (value == endptr) {
return evsel;
}
+static bool perf_event_can_profile_kernel(void)
+{
+ return geteuid() == 0 || perf_event_paranoid() == -1;
+}
+
struct perf_evsel *perf_evsel__new_cycles(bool precise)
{
struct perf_event_attr attr = {
.type = PERF_TYPE_HARDWARE,
.config = PERF_COUNT_HW_CPU_CYCLES,
- .exclude_kernel = geteuid() != 0,
+ .exclude_kernel = !perf_event_can_profile_kernel(),
};
struct perf_evsel *evsel;
void __weak arch__sym_update(struct symbol *s __maybe_unused,
GElf_Sym *sym __maybe_unused) { }
-void __weak arch__adjust_sym_map_offset(GElf_Sym *sym, GElf_Shdr *shdr,
- struct map *map __maybe_unused)
-{
- sym->st_value -= shdr->sh_addr - shdr->sh_offset;
-}
-
int dso__load_sym(struct dso *dso, struct map *map, struct symsrc *syms_ss,
struct symsrc *runtime_ss, int kmodule)
{
/* Adjust symbol to map to file offset */
if (adjust_kernel_syms)
- arch__adjust_sym_map_offset(&sym, &shdr, map);
+ sym.st_value -= shdr.sh_addr - shdr.sh_offset;
if (strcmp(section_name,
(curr_dso->short_name +
#ifdef HAVE_LIBELF_SUPPORT
bool elf__needs_adjust_symbols(GElf_Ehdr ehdr);
void arch__sym_update(struct symbol *s, GElf_Sym *sym);
-void arch__adjust_sym_map_offset(GElf_Sym *sym,
- GElf_Shdr *shdr __maybe_unused,
- struct map *map __maybe_unused);
#endif
#define SYMBOL_A 0
#include "syscalltbl.h"
#include <stdlib.h>
+#include <linux/compiler.h>
#ifdef HAVE_SYSCALL_TABLE
-#include <linux/compiler.h>
#include <string.h>
#include "string2.h"
#include "util.h"
set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
- set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
- set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
- set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
}
static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
override MAKEFLAGS =
endif
+ifneq ($(KBUILD_SRC),)
+override LDFLAGS =
+endif
+
BUILD := $(O)
ifndef BUILD
BUILD := $(KBUILD_OUTPUT)
export BUILD
all:
- for TARGET in $(TARGETS); do \
+ @for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
done;
run_tests: all
- for TARGET in $(TARGETS); do \
+ @for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET run_tests;\
done;
hotplug:
- for TARGET in $(TARGETS_HOTPLUG); do \
+ @for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET;\
done;
run_hotplug: hotplug
- for TARGET in $(TARGETS_HOTPLUG); do \
+ @for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET run_full_test;\
done;
clean_hotplug:
- for TARGET in $(TARGETS_HOTPLUG); do \
+ @for TARGET in $(TARGETS_HOTPLUG); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
ifdef INSTALL_PATH
@# Ask all targets to install their files
mkdir -p $(INSTALL_PATH)
- for TARGET in $(TARGETS); do \
+ @for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET INSTALL_PATH=$(INSTALL_PATH)/$$TARGET install; \
done;
endif
clean:
- for TARGET in $(TARGETS); do \
+ @for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
done;
unsigned int start, end, possible_cpus = 0;
char buff[128];
FILE *fp;
+ int n;
fp = fopen(fcpu, "r");
if (!fp) {
}
while (fgets(buff, sizeof(buff), fp)) {
- if (sscanf(buff, "%u-%u", &start, &end) == 2) {
- possible_cpus = start == 0 ? end + 1 : 0;
- break;
+ n = sscanf(buff, "%u-%u", &start, &end);
+ if (n == 0) {
+ printf("Failed to retrieve # possible CPUs!\n");
+ exit(1);
+ } else if (n == 1) {
+ end = start;
}
+ possible_cpus = start == 0 ? end + 1 : 0;
+ break;
}
-
fclose(fp);
- if (!possible_cpus) {
- printf("Failed to retrieve # possible CPUs!\n");
- exit(1);
- }
return possible_cpus;
}
uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+TEST_GEN_PROGS := step_after_suspend_test
+
ifeq ($(ARCH),x86)
-TEST_GEN_PROGS := breakpoint_test
+TEST_GEN_PROGS += breakpoint_test
endif
ifneq (,$(filter $(ARCH),aarch64 arm64))
-TEST_GEN_PROGS := breakpoint_test_arm64
+TEST_GEN_PROGS += breakpoint_test_arm64
endif
-TEST_GEN_PROGS += step_after_suspend_test
-
include ../lib.mk
#!/bin/sh
# description: Register/unregister many kprobe events
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
# ftrace fentry skip size depends on the machine architecture.
# Currently HAVE_KPROBES_ON_FTRACE defined on x86 and powerpc64le
case `uname -m` in
include ../lib.mk
all:
- for DIR in $(SUBDIRS); do \
+ @for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
+ if [ -e $$DIR/$(TEST_PROGS) ]; then
+ rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/;
+ fi
done
override define RUN_TESTS
- $(OUTPUT)/run.sh
+ @cd $(OUTPUT); ./run.sh
endef
override define INSTALL_RULE
endef
override define CLEAN
- for DIR in $(SUBDIRS); do \
+ @for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
mkdir $$BUILD_TARGET -p; \
make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
LDLIBS := $(LDLIBS) -lm
+ifeq (,$(filter $(ARCH),x86))
TEST_GEN_FILES := msr aperf
+endif
TEST_PROGS := run.sh
EVALUATE_ONLY=0
-max_cpus=$(($(nproc)-1))
+if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then
+ echo "$0 # Skipped: Test can only run on x86 architectures."
+ exit 0
+fi
-# compile programs
-gcc aperf.c -Wall -D_GNU_SOURCE -o aperf -lm
-[ $? -ne 0 ] && echo "Problem compiling aperf.c." && exit 1
-gcc -o msr msr.c -lm
-[ $? -ne 0 ] && echo "Problem compiling msr.c." && exit 1
+max_cpus=$(($(nproc)-1))
function run_test () {
OUTPUT := $(shell pwd)
endif
+# The following are built by lib.mk common compile rules.
+# TEST_CUSTOM_PROGS should be used by tests that require
+# custom build rule and prevent common build rule use.
+# TEST_PROGS are for test shell scripts.
+# TEST_CUSTOM_PROGS and TEST_PROGS will be run by common run_tests
+# and install targets. Common clean doesn't touch them.
TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS))
+TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED))
TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
test_num=`echo $$test_num+1 | bc`; \
echo "selftests: $$BASENAME_TEST"; \
echo "========================================"; \
- if [ ! -x $$BASENAME_TEST ]; then \
+ if [ ! -x $$TEST ]; then \
echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
else \
- cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
+ cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
fi; \
done;
endef
run_tests: all
- $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_PROGS))
+ifneq ($(KBUILD_SRC),)
+ @if [ "X$(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)" != "X" ]; then
+ @rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT)
+ fi
+ @if [ "X$(TEST_PROGS)" != "X" ]; then
+ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(OUTPUT)/$(TEST_PROGS))
+ else
+ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS))
+ fi
+else
+ $(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS))
+endif
define INSTALL_RULE
@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
echo "rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/"; \
rsync -a $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/; \
fi
- @if [ "X$(TEST_GEN_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \
+ @if [ "X$(TEST_GEN_PROGS)$(TEST_CUSTOM_PROGS)$(TEST_GEN_PROGS_EXTENDED)$(TEST_GEN_FILES)" != "X" ]; then \
mkdir -p ${INSTALL_PATH}; \
- echo "rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \
- rsync -a $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \
+ echo "rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/"; \
+ rsync -a $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(INSTALL_PATH)/; \
fi
endef
endif
define EMIT_TESTS
- @for TEST in $(TEST_GEN_PROGS) $(TEST_PROGS); do \
+ @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
BASENAME_TEST=`basename $$TEST`; \
- echo "(./$$BASENAME_TEST && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+ echo "(./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
done;
endef
emit_tests:
$(EMIT_TESTS)
+# define if isn't already. It is undefined in make O= case.
+ifeq ($(RM),)
+RM := rm -f
+endif
+
define CLEAN
$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
endef
clean:
$(CLEAN)
+# When make O= with kselftest target from main level
+# the following aren't defined.
+#
+ifneq ($(KBUILD_SRC),)
+LINK.c = $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+COMPILE.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c
+LINK.S = $(CC) $(ASFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH)
+endif
+
$(OUTPUT)/%:%.c
$(LINK.c) $^ $(LDLIBS) -o $@
include ../lib.mk
override define RUN_TESTS
- @./mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
- @./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
+ $(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
+ $(OUTPUT)//mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
endef
override define EMIT_TESTS
reuseport_bpf_cpu
reuseport_bpf_numa
reuseport_dualstack
+reuseaddr_conflict
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
TEST_GEN_FILES = socket
-TEST_GEN_FILES += psock_fanout psock_tpacket
-TEST_GEN_FILES += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_FILES += reuseport_dualstack msg_zerocopy
+TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
include ../lib.mk
#include <unistd.h>
#ifndef SO_EE_ORIGIN_ZEROCOPY
-#define SO_EE_ORIGIN_ZEROCOPY SO_EE_ORIGIN_UPAGE
+#define SO_EE_ORIGIN_ZEROCOPY 5
#endif
#ifndef SO_ZEROCOPY
exit 0
fi
-ip -Version 2>/dev/null >/dev/null
+ip link show 2>/dev/null >/dev/null
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without the ip tool"
exit 0
--- /dev/null
+/*
+ * Test for the regression introduced by
+ *
+ * b9470c27607b ("inet: kill smallest_size and smallest_port")
+ *
+ * If we open an ipv4 socket on a port with reuseaddr we shouldn't reset the tb
+ * when we open the ipv6 conterpart, which is what was happening previously.
+ */
+#include <errno.h>
+#include <error.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#define PORT 9999
+
+int open_port(int ipv6, int any)
+{
+ int fd = -1;
+ int reuseaddr = 1;
+ int v6only = 1;
+ int addrlen;
+ int ret = -1;
+ struct sockaddr *addr;
+ int family = ipv6 ? AF_INET6 : AF_INET;
+
+ struct sockaddr_in6 addr6 = {
+ .sin6_family = AF_INET6,
+ .sin6_port = htons(PORT),
+ .sin6_addr = in6addr_any
+ };
+ struct sockaddr_in addr4 = {
+ .sin_family = AF_INET,
+ .sin_port = htons(PORT),
+ .sin_addr.s_addr = any ? htonl(INADDR_ANY) : inet_addr("127.0.0.1"),
+ };
+
+
+ if (ipv6) {
+ addr = (struct sockaddr*)&addr6;
+ addrlen = sizeof(addr6);
+ } else {
+ addr = (struct sockaddr*)&addr4;
+ addrlen = sizeof(addr4);
+ }
+
+ if ((fd = socket(family, SOCK_STREAM, IPPROTO_TCP)) < 0) {
+ perror("socket");
+ goto out;
+ }
+
+ if (ipv6 && setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (void*)&v6only,
+ sizeof(v6only)) < 0) {
+ perror("setsockopt IPV6_V6ONLY");
+ goto out;
+ }
+
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &reuseaddr,
+ sizeof(reuseaddr)) < 0) {
+ perror("setsockopt SO_REUSEADDR");
+ goto out;
+ }
+
+ if (bind(fd, addr, addrlen) < 0) {
+ perror("bind");
+ goto out;
+ }
+
+ if (any)
+ return fd;
+
+ if (listen(fd, 1) < 0) {
+ perror("listen");
+ goto out;
+ }
+ return fd;
+out:
+ close(fd);
+ return ret;
+}
+
+int main(void)
+{
+ int listenfd;
+ int fd1, fd2;
+
+ fprintf(stderr, "Opening 127.0.0.1:%d\n", PORT);
+ listenfd = open_port(0, 0);
+ if (listenfd < 0)
+ error(1, errno, "Couldn't open listen socket");
+ fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+ fd1 = open_port(0, 1);
+ if (fd1 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+ fprintf(stderr, "Opening in6addr_any:%d\n", PORT);
+ fd1 = open_port(1, 1);
+ if (fd1 < 0)
+ error(1, errno, "Couldn't open ipv6 reuseport");
+ fprintf(stderr, "Opening INADDR_ANY:%d\n", PORT);
+ fd2 = open_port(0, 1);
+ if (fd2 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on a already bound non-reuseport socket");
+ close(fd1);
+ fprintf(stderr, "Opening INADDR_ANY:%d after closing ipv6 socket\n", PORT);
+ fd1 = open_port(0, 1);
+ if (fd1 >= 0)
+ error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
+ fprintf(stderr, "Success");
+ return 0;
+}
-TEST_GEN_PROGS := seccomp_bpf
-CFLAGS += -Wl,-no-as-needed -Wall
-LDFLAGS += -lpthread
+all:
include ../lib.mk
-$(TEST_GEN_PROGS): seccomp_bpf.c ../kselftest_harness.h
- $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+.PHONY: all clean
+
+BINARIES := seccomp_bpf seccomp_benchmark
+CFLAGS += -Wl,-no-as-needed -Wall
+
+seccomp_bpf: seccomp_bpf.c ../kselftest_harness.h
+ $(CC) $(CFLAGS) $(LDFLAGS) -lpthread $< -o $@
+
+TEST_PROGS += $(BINARIES)
+EXTRA_CLEAN := $(BINARIES)
+
+all: $(BINARIES)
--- /dev/null
+/*
+ * Strictly speaking, this is not a test. But it can report during test
+ * runs so relative performace can be measured.
+ */
+#define _GNU_SOURCE
+#include <assert.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/filter.h>
+#include <linux/seccomp.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+
+#define ARRAY_SIZE(a) (sizeof(a) / sizeof(a[0]))
+
+unsigned long long timing(clockid_t clk_id, unsigned long long samples)
+{
+ pid_t pid, ret;
+ unsigned long long i;
+ struct timespec start, finish;
+
+ pid = getpid();
+ assert(clock_gettime(clk_id, &start) == 0);
+ for (i = 0; i < samples; i++) {
+ ret = syscall(__NR_getpid);
+ assert(pid == ret);
+ }
+ assert(clock_gettime(clk_id, &finish) == 0);
+
+ i = finish.tv_sec - start.tv_sec;
+ i *= 1000000000;
+ i += finish.tv_nsec - start.tv_nsec;
+
+ printf("%lu.%09lu - %lu.%09lu = %llu\n",
+ finish.tv_sec, finish.tv_nsec,
+ start.tv_sec, start.tv_nsec,
+ i);
+
+ return i;
+}
+
+unsigned long long calibrate(void)
+{
+ unsigned long long i;
+
+ printf("Calibrating reasonable sample size...\n");
+
+ for (i = 5; ; i++) {
+ unsigned long long samples = 1 << i;
+
+ /* Find something that takes more than 5 seconds to run. */
+ if (timing(CLOCK_REALTIME, samples) / 1000000000ULL > 5)
+ return samples;
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ struct sock_filter filter[] = {
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)ARRAY_SIZE(filter),
+ .filter = filter,
+ };
+ long ret;
+ unsigned long long samples;
+ unsigned long long native, filtered;
+
+ if (argc > 1)
+ samples = strtoull(argv[1], NULL, 0);
+ else
+ samples = calibrate();
+
+ printf("Benchmarking %llu samples...\n", samples);
+
+ native = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid native: %llu ns\n", native);
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ assert(ret == 0);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ assert(ret == 0);
+
+ filtered = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid RET_ALLOW: %llu ns\n", filtered);
+
+ printf("Estimated seccomp overhead per syscall: %llu ns\n",
+ filtered - native);
+
+ if (filtered == native)
+ printf("Trying running again with more samples.\n");
+
+ return 0;
+}
*/
#include <sys/types.h>
-#include <asm/siginfo.h>
-#define __have_siginfo_t 1
-#define __have_sigval_t 1
-#define __have_sigevent_t 1
+
+/*
+ * glibc 2.26 and later have SIGSYS in siginfo_t. Before that,
+ * we need to use the kernel's siginfo.h file and trick glibc
+ * into accepting it.
+ */
+#if !__GLIBC_PREREQ(2, 26)
+# include <asm/siginfo.h>
+# define __have_siginfo_t 1
+# define __have_sigval_t 1
+# define __have_sigevent_t 1
+#endif
#include <errno.h>
#include <linux/filter.h>
#define SECCOMP_MODE_FILTER 2
#endif
-#ifndef SECCOMP_RET_KILL
-#define SECCOMP_RET_KILL 0x00000000U /* kill the task immediately */
-#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
-#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
-#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
-#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
-
-/* Masks for the return value sections. */
-#define SECCOMP_RET_ACTION 0x7fff0000U
-#define SECCOMP_RET_DATA 0x0000ffffU
-
+#ifndef SECCOMP_RET_ALLOW
struct seccomp_data {
int nr;
__u32 arch;
};
#endif
+#ifndef SECCOMP_RET_KILL_PROCESS
+#define SECCOMP_RET_KILL_PROCESS 0x80000000U /* kill the process */
+#define SECCOMP_RET_KILL_THREAD 0x00000000U /* kill the thread */
+#endif
+#ifndef SECCOMP_RET_KILL
+#define SECCOMP_RET_KILL SECCOMP_RET_KILL_THREAD
+#define SECCOMP_RET_TRAP 0x00030000U /* disallow and force a SIGSYS */
+#define SECCOMP_RET_ERRNO 0x00050000U /* returns an errno */
+#define SECCOMP_RET_TRACE 0x7ff00000U /* pass to a tracer or disallow */
+#define SECCOMP_RET_ALLOW 0x7fff0000U /* allow */
+#endif
+#ifndef SECCOMP_RET_LOG
+#define SECCOMP_RET_LOG 0x7ffc0000U /* allow after logging */
+#endif
+
+#ifndef __NR_seccomp
+# if defined(__i386__)
+# define __NR_seccomp 354
+# elif defined(__x86_64__)
+# define __NR_seccomp 317
+# elif defined(__arm__)
+# define __NR_seccomp 383
+# elif defined(__aarch64__)
+# define __NR_seccomp 277
+# elif defined(__hppa__)
+# define __NR_seccomp 338
+# elif defined(__powerpc__)
+# define __NR_seccomp 358
+# elif defined(__s390__)
+# define __NR_seccomp 348
+# else
+# warning "seccomp syscall number unknown for this architecture"
+# define __NR_seccomp 0xffff
+# endif
+#endif
+
+#ifndef SECCOMP_SET_MODE_STRICT
+#define SECCOMP_SET_MODE_STRICT 0
+#endif
+
+#ifndef SECCOMP_SET_MODE_FILTER
+#define SECCOMP_SET_MODE_FILTER 1
+#endif
+
+#ifndef SECCOMP_GET_ACTION_AVAIL
+#define SECCOMP_GET_ACTION_AVAIL 2
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_TSYNC
+#define SECCOMP_FILTER_FLAG_TSYNC 1
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_LOG
+#define SECCOMP_FILTER_FLAG_LOG 2
+#endif
+
+#ifndef seccomp
+int seccomp(unsigned int op, unsigned int flags, void *args)
+{
+ errno = 0;
+ return syscall(__NR_seccomp, op, flags, args);
+}
+#endif
+
#if __BYTE_ORDER == __LITTLE_ENDIAN
#define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
#elif __BYTE_ORDER == __BIG_ENDIAN
}
}
-/* Tests kernel support by checking for a copy_from_user() fault on * NULL. */
+/* Tests kernel support by checking for a copy_from_user() fault on NULL. */
TEST(mode_filter_support)
{
long ret;
EXPECT_EQ(EINVAL, errno);
}
+TEST(log_all)
+{
+ struct sock_filter filter[] = {
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+ };
+ struct sock_fprog prog = {
+ .len = (unsigned short)ARRAY_SIZE(filter),
+ .filter = filter,
+ };
+ long ret;
+ pid_t parent = getppid();
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ ASSERT_EQ(0, ret);
+
+ /* getppid() should succeed and be logged (no check for logging) */
+ EXPECT_EQ(parent, syscall(__NR_getppid));
+}
+
TEST_SIGNAL(unknown_ret_is_kill_inside, SIGSYS)
{
struct sock_filter filter[] = {
close(fd);
}
+/* This is a thread task to die via seccomp filter violation. */
+void *kill_thread(void *data)
+{
+ bool die = (bool)data;
+
+ if (die) {
+ prctl(PR_GET_SECCOMP, 0, 0, 0, 0);
+ return (void *)SIBLING_EXIT_FAILURE;
+ }
+
+ return (void *)SIBLING_EXIT_UNKILLED;
+}
+
+/* Prepare a thread that will kill itself or both of us. */
+void kill_thread_or_group(struct __test_metadata *_metadata, bool kill_process)
+{
+ pthread_t thread;
+ void *status;
+ /* Kill only when calling __NR_prctl. */
+ struct sock_filter filter_thread[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+ offsetof(struct seccomp_data, nr)),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_THREAD),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog prog_thread = {
+ .len = (unsigned short)ARRAY_SIZE(filter_thread),
+ .filter = filter_thread,
+ };
+ struct sock_filter filter_process[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+ offsetof(struct seccomp_data, nr)),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_prctl, 0, 1),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL_PROCESS),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog prog_process = {
+ .len = (unsigned short)ARRAY_SIZE(filter_process),
+ .filter = filter_process,
+ };
+
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0,
+ kill_process ? &prog_process : &prog_thread));
+
+ /*
+ * Add the KILL_THREAD rule again to make sure that the KILL_PROCESS
+ * flag cannot be downgraded by a new filter.
+ */
+ ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog_thread));
+
+ /* Start a thread that will exit immediately. */
+ ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)false));
+ ASSERT_EQ(0, pthread_join(thread, &status));
+ ASSERT_EQ(SIBLING_EXIT_UNKILLED, (unsigned long)status);
+
+ /* Start a thread that will die immediately. */
+ ASSERT_EQ(0, pthread_create(&thread, NULL, kill_thread, (void *)true));
+ ASSERT_EQ(0, pthread_join(thread, &status));
+ ASSERT_NE(SIBLING_EXIT_FAILURE, (unsigned long)status);
+
+ /*
+ * If we get here, only the spawned thread died. Let the parent know
+ * the whole process didn't die (i.e. this thread, the spawner,
+ * stayed running).
+ */
+ exit(42);
+}
+
+TEST(KILL_thread)
+{
+ int status;
+ pid_t child_pid;
+
+ child_pid = fork();
+ ASSERT_LE(0, child_pid);
+ if (child_pid == 0) {
+ kill_thread_or_group(_metadata, false);
+ _exit(38);
+ }
+
+ ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+ /* If only the thread was killed, we'll see exit 42. */
+ ASSERT_TRUE(WIFEXITED(status));
+ ASSERT_EQ(42, WEXITSTATUS(status));
+}
+
+TEST(KILL_process)
+{
+ int status;
+ pid_t child_pid;
+
+ child_pid = fork();
+ ASSERT_LE(0, child_pid);
+ if (child_pid == 0) {
+ kill_thread_or_group(_metadata, true);
+ _exit(38);
+ }
+
+ ASSERT_EQ(child_pid, waitpid(child_pid, &status, 0));
+
+ /* If the entire process was killed, we'll see SIGSYS. */
+ ASSERT_TRUE(WIFSIGNALED(status));
+ ASSERT_EQ(SIGSYS, WTERMSIG(status));
+}
+
/* TODO(wad) add 64-bit versus 32-bit arg tests. */
TEST(arg_out_of_range)
{
EXPECT_EQ(EINVAL, errno);
}
+#define ERRNO_FILTER(name, errno) \
+ struct sock_filter _read_filter_##name[] = { \
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS, \
+ offsetof(struct seccomp_data, nr)), \
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1), \
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | errno), \
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), \
+ }; \
+ struct sock_fprog prog_##name = { \
+ .len = (unsigned short)ARRAY_SIZE(_read_filter_##name), \
+ .filter = _read_filter_##name, \
+ }
+
+/* Make sure basic errno values are correctly passed through a filter. */
TEST(ERRNO_valid)
{
- struct sock_filter filter[] = {
- BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
- offsetof(struct seccomp_data, nr)),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | E2BIG),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
- };
- struct sock_fprog prog = {
- .len = (unsigned short)ARRAY_SIZE(filter),
- .filter = filter,
- };
+ ERRNO_FILTER(valid, E2BIG);
long ret;
pid_t parent = getppid();
ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
ASSERT_EQ(0, ret);
- ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_valid);
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
EXPECT_EQ(E2BIG, errno);
}
+/* Make sure an errno of zero is correctly handled by the arch code. */
TEST(ERRNO_zero)
{
- struct sock_filter filter[] = {
- BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
- offsetof(struct seccomp_data, nr)),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 0),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
- };
- struct sock_fprog prog = {
- .len = (unsigned short)ARRAY_SIZE(filter),
- .filter = filter,
- };
+ ERRNO_FILTER(zero, 0);
long ret;
pid_t parent = getppid();
ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
ASSERT_EQ(0, ret);
- ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_zero);
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
EXPECT_EQ(0, read(0, NULL, 0));
}
+/*
+ * The SECCOMP_RET_DATA mask is 16 bits wide, but errno is smaller.
+ * This tests that the errno value gets capped correctly, fixed by
+ * 580c57f10768 ("seccomp: cap SECCOMP_RET_ERRNO data to MAX_ERRNO").
+ */
TEST(ERRNO_capped)
{
- struct sock_filter filter[] = {
- BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
- offsetof(struct seccomp_data, nr)),
- BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_read, 0, 1),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ERRNO | 4096),
- BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
- };
- struct sock_fprog prog = {
- .len = (unsigned short)ARRAY_SIZE(filter),
- .filter = filter,
- };
+ ERRNO_FILTER(capped, 4096);
long ret;
pid_t parent = getppid();
ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
ASSERT_EQ(0, ret);
- ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_capped);
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
EXPECT_EQ(4095, errno);
}
+/*
+ * Filters are processed in reverse order: last applied is executed first.
+ * Since only the SECCOMP_RET_ACTION mask is tested for return values, the
+ * SECCOMP_RET_DATA mask results will follow the most recently applied
+ * matching filter return (and not the lowest or highest value).
+ */
+TEST(ERRNO_order)
+{
+ ERRNO_FILTER(first, 11);
+ ERRNO_FILTER(second, 13);
+ ERRNO_FILTER(third, 12);
+ long ret;
+ pid_t parent = getppid();
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_first);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_second);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_third);
+ ASSERT_EQ(0, ret);
+
+ EXPECT_EQ(parent, syscall(__NR_getppid));
+ EXPECT_EQ(-1, read(0, NULL, 0));
+ EXPECT_EQ(12, errno);
+}
+
FIXTURE_DATA(TRAP) {
struct sock_fprog prog;
};
syscall(__NR_getpid);
}
-static struct siginfo TRAP_info;
+static siginfo_t TRAP_info;
static volatile int TRAP_nr;
static void TRAP_action(int nr, siginfo_t *info, void *void_context)
{
FIXTURE_DATA(precedence) {
struct sock_fprog allow;
+ struct sock_fprog log;
struct sock_fprog trace;
struct sock_fprog error;
struct sock_fprog trap;
struct sock_filter allow_insns[] = {
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
};
+ struct sock_filter log_insns[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+ offsetof(struct seccomp_data, nr)),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 1, 0),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_LOG),
+ };
struct sock_filter trace_insns[] = {
BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
offsetof(struct seccomp_data, nr)),
memcpy(self->_x.filter, &_x##_insns, sizeof(_x##_insns)); \
self->_x.len = (unsigned short)ARRAY_SIZE(_x##_insns)
FILTER_ALLOC(allow);
+ FILTER_ALLOC(log);
FILTER_ALLOC(trace);
FILTER_ALLOC(error);
FILTER_ALLOC(trap);
{
#define FILTER_FREE(_x) if (self->_x.filter) free(self->_x.filter)
FILTER_FREE(allow);
+ FILTER_FREE(log);
FILTER_FREE(trace);
FILTER_FREE(error);
FILTER_FREE(trap);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trap);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->error);
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->trace);
ASSERT_EQ(0, ret);
/* Should work just fine. */
ASSERT_EQ(0, ret);
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
/* Should work just fine. */
EXPECT_EQ(parent, syscall(__NR_getppid));
/* No ptracer */
EXPECT_EQ(-1, syscall(__NR_getpid));
}
+TEST_F(precedence, log_is_fifth)
+{
+ pid_t mypid, parent;
+ long ret;
+
+ mypid = getpid();
+ parent = getppid();
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+ ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
+ /* Should work just fine. */
+ EXPECT_EQ(parent, syscall(__NR_getppid));
+ /* Should also work just fine */
+ EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
+TEST_F(precedence, log_is_fifth_in_any_order)
+{
+ pid_t mypid, parent;
+ long ret;
+
+ mypid = getpid();
+ parent = getppid();
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->log);
+ ASSERT_EQ(0, ret);
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->allow);
+ ASSERT_EQ(0, ret);
+ /* Should work just fine. */
+ EXPECT_EQ(parent, syscall(__NR_getppid));
+ /* Should also work just fine */
+ EXPECT_EQ(mypid, syscall(__NR_getpid));
+}
+
#ifndef PTRACE_O_TRACESECCOMP
#define PTRACE_O_TRACESECCOMP 0x00000080
#endif
# error "Do not know how to find your architecture's registers and syscalls"
#endif
+/* When the syscall return can't be changed, stub out the tests for it. */
+#ifdef SYSCALL_NUM_RET_SHARE_REG
+# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action)
+#else
+# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(val, action)
+#endif
+
/* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for
* architectures without HAVE_ARCH_TRACEHOOK (e.g. User-mode Linux).
*/
#ifdef SYSCALL_NUM_RET_SHARE_REG
TH_LOG("Can't modify syscall return on this architecture");
#else
- regs.SYSCALL_RET = 1;
+ regs.SYSCALL_RET = EPERM;
#endif
#ifdef HAVE_GETREGS
if (nr == __NR_getpid)
change_syscall(_metadata, tracee, __NR_getppid);
+ if (nr == __NR_open)
+ change_syscall(_metadata, tracee, -1);
}
FIXTURE_DATA(TRACE_syscall) {
free(self->prog.filter);
}
+TEST_F(TRACE_syscall, ptrace_syscall_redirected)
+{
+ /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+ teardown_trace_fixture(_metadata, self->tracer);
+ self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+ true);
+
+ /* Tracer will redirect getpid to getppid. */
+ EXPECT_NE(self->mypid, syscall(__NR_getpid));
+}
+
+TEST_F(TRACE_syscall, ptrace_syscall_dropped)
+{
+ /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */
+ teardown_trace_fixture(_metadata, self->tracer);
+ self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL,
+ true);
+
+ /* Tracer should skip the open syscall, resulting in EPERM. */
+ EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_open));
+}
+
TEST_F(TRACE_syscall, syscall_allowed)
{
long ret;
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0);
ASSERT_EQ(0, ret);
-#ifdef SYSCALL_NUM_RET_SHARE_REG
- /* gettid has been skipped */
- EXPECT_EQ(-1, syscall(__NR_gettid));
-#else
/* gettid has been skipped and an altered return value stored. */
- EXPECT_EQ(1, syscall(__NR_gettid));
-#endif
+ EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid));
EXPECT_NE(self->mytid, syscall(__NR_gettid));
}
ASSERT_EQ(0, ret);
/* Tracer will redirect getpid to getppid, and we should see EPERM. */
+ errno = 0;
EXPECT_EQ(-1, syscall(__NR_getpid));
EXPECT_EQ(EPERM, errno);
}
EXPECT_NE(self->mypid, syscall(__NR_getpid));
}
-#ifndef __NR_seccomp
-# if defined(__i386__)
-# define __NR_seccomp 354
-# elif defined(__x86_64__)
-# define __NR_seccomp 317
-# elif defined(__arm__)
-# define __NR_seccomp 383
-# elif defined(__aarch64__)
-# define __NR_seccomp 277
-# elif defined(__hppa__)
-# define __NR_seccomp 338
-# elif defined(__powerpc__)
-# define __NR_seccomp 358
-# elif defined(__s390__)
-# define __NR_seccomp 348
-# else
-# warning "seccomp syscall number unknown for this architecture"
-# define __NR_seccomp 0xffff
-# endif
-#endif
-
-#ifndef SECCOMP_SET_MODE_STRICT
-#define SECCOMP_SET_MODE_STRICT 0
-#endif
-
-#ifndef SECCOMP_SET_MODE_FILTER
-#define SECCOMP_SET_MODE_FILTER 1
-#endif
-
-#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
-#endif
-
-#ifndef seccomp
-int seccomp(unsigned int op, unsigned int flags, void *args)
-{
- errno = 0;
- return syscall(__NR_seccomp, op, flags, args);
-}
-#endif
-
TEST(seccomp_syscall)
{
struct sock_filter filter[] = {
}
}
+/*
+ * Test detection of known and unknown filter flags. Userspace needs to be able
+ * to check if a filter flag is supported by the current kernel and a good way
+ * of doing that is by attempting to enter filter mode, with the flag bit in
+ * question set, and a NULL pointer for the _args_ parameter. EFAULT indicates
+ * that the flag is valid and EINVAL indicates that the flag is invalid.
+ */
+TEST(detect_seccomp_filter_flags)
+{
+ unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
+ SECCOMP_FILTER_FLAG_LOG };
+ unsigned int flag, all_flags;
+ int i;
+ long ret;
+
+ /* Test detection of known-good filter flags */
+ for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+ flag = flags[i];
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+ ASSERT_NE(ENOSYS, errno) {
+ TH_LOG("Kernel does not support seccomp syscall!");
+ }
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EFAULT, errno) {
+ TH_LOG("Failed to detect that a known-good filter flag (0x%X) is supported!",
+ flag);
+ }
+
+ all_flags |= flag;
+ }
+
+ /* Test detection of all known-good filter flags */
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EFAULT, errno) {
+ TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+ all_flags);
+ }
+
+ /* Test detection of an unknown filter flag */
+ flag = -1;
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EINVAL, errno) {
+ TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported!",
+ flag);
+ }
+
+ /*
+ * Test detection of an unknown filter flag that may simply need to be
+ * added to this test
+ */
+ flag = flags[ARRAY_SIZE(flags) - 1] << 1;
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+ EXPECT_EQ(-1, ret);
+ EXPECT_EQ(EINVAL, errno) {
+ TH_LOG("Failed to detect that an unknown filter flag (0x%X) is unsupported! Does a new flag need to be added to this test?",
+ flag);
+ }
+}
+
TEST(TSYNC_first)
{
struct sock_filter filter[] = {
_metadata->passed = 0;
}
+TEST_SIGNAL(filter_flag_log, SIGSYS)
+{
+ struct sock_filter allow_filter[] = {
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_filter kill_filter[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS,
+ offsetof(struct seccomp_data, nr)),
+ BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getpid, 0, 1),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog allow_prog = {
+ .len = (unsigned short)ARRAY_SIZE(allow_filter),
+ .filter = allow_filter,
+ };
+ struct sock_fprog kill_prog = {
+ .len = (unsigned short)ARRAY_SIZE(kill_filter),
+ .filter = kill_filter,
+ };
+ long ret;
+ pid_t parent = getppid();
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret);
+
+ /* Verify that the FILTER_FLAG_LOG flag isn't accepted in strict mode */
+ ret = seccomp(SECCOMP_SET_MODE_STRICT, SECCOMP_FILTER_FLAG_LOG,
+ &allow_prog);
+ ASSERT_NE(ENOSYS, errno) {
+ TH_LOG("Kernel does not support seccomp syscall!");
+ }
+ EXPECT_NE(0, ret) {
+ TH_LOG("Kernel accepted FILTER_FLAG_LOG flag in strict mode!");
+ }
+ EXPECT_EQ(EINVAL, errno) {
+ TH_LOG("Kernel returned unexpected errno for FILTER_FLAG_LOG flag in strict mode!");
+ }
+
+ /* Verify that a simple, permissive filter can be added with no flags */
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &allow_prog);
+ EXPECT_EQ(0, ret);
+
+ /* See if the same filter can be added with the FILTER_FLAG_LOG flag */
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+ &allow_prog);
+ ASSERT_NE(EINVAL, errno) {
+ TH_LOG("Kernel does not support the FILTER_FLAG_LOG flag!");
+ }
+ EXPECT_EQ(0, ret);
+
+ /* Ensure that the kill filter works with the FILTER_FLAG_LOG flag */
+ ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_LOG,
+ &kill_prog);
+ EXPECT_EQ(0, ret);
+
+ EXPECT_EQ(parent, syscall(__NR_getppid));
+ /* getpid() should never return. */
+ EXPECT_EQ(0, syscall(__NR_getpid));
+}
+
+TEST(get_action_avail)
+{
+ __u32 actions[] = { SECCOMP_RET_KILL_THREAD, SECCOMP_RET_TRAP,
+ SECCOMP_RET_ERRNO, SECCOMP_RET_TRACE,
+ SECCOMP_RET_LOG, SECCOMP_RET_ALLOW };
+ __u32 unknown_action = 0x10000000U;
+ int i;
+ long ret;
+
+ ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[0]);
+ ASSERT_NE(ENOSYS, errno) {
+ TH_LOG("Kernel does not support seccomp syscall!");
+ }
+ ASSERT_NE(EINVAL, errno) {
+ TH_LOG("Kernel does not support SECCOMP_GET_ACTION_AVAIL operation!");
+ }
+ EXPECT_EQ(ret, 0);
+
+ for (i = 0; i < ARRAY_SIZE(actions); i++) {
+ ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &actions[i]);
+ EXPECT_EQ(ret, 0) {
+ TH_LOG("Expected action (0x%X) not available!",
+ actions[i]);
+ }
+ }
+
+ /* Check that an unknown action is handled properly (EOPNOTSUPP) */
+ ret = seccomp(SECCOMP_GET_ACTION_AVAIL, 0, &unknown_action);
+ EXPECT_EQ(ret, -1);
+ EXPECT_EQ(errno, EOPNOTSUPP);
+}
+
/*
* TODO:
* - add microbenchmarks
* - endianness checking when appropriate
* - 64-bit arg prodding
* - arch value testing (x86 modes especially)
+ * - verify that FILTER_FLAG_LOG filters generate log messages
+ * - verify that RET_LOG generates log messages
* - ...
*/
stack_t stk;
struct stk_data *p;
+#if __s390x__
+ register unsigned long sp asm("%15");
+#else
register unsigned long sp asm("sp");
+#endif
if (sp < (unsigned long)sstack ||
sp >= (unsigned long)sstack + SIGSTKSZ) {
CFLAGS += -I../../../../usr/include/
LDFLAGS += -pthread
-TEST_PROGS = sync_test
-
-all: $(TEST_PROGS)
+.PHONY: all clean
include ../lib.mk
+# lib.mk TEST_CUSTOM_PROGS var is for custom tests that need special
+# build rules. lib.mk will run and install them.
+
+TEST_CUSTOM_PROGS := $(OUTPUT)/sync_test
+all: $(TEST_CUSTOM_PROGS)
+
OBJS = sync_test.o sync.o
TESTS += sync_alloc.o
TESTS += sync_stress_consumer.o
TESTS += sync_stress_merge.o
-sync_test: $(OBJS) $(TESTS)
+OBJS := $(patsubst %,$(OUTPUT)/%,$(OBJS))
+TESTS := $(patsubst %,$(OUTPUT)/%,$(TESTS))
+
+$(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS)
+ $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS)
+
+$(OBJS): $(OUTPUT)/%.o: %.c
+ $(CC) -c $^ -o $@
+
+$(TESTS): $(OUTPUT)/%.o: %.c
+ $(CC) -c $^ -o $@
-EXTRA_CLEAN := sync_test $(OBJS) $(TESTS)
+EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS)
printf("%-22s %s missing CAP_WAKE_ALARM? : [UNSUPPORTED]\n",
clockstring(clock_id),
flags ? "ABSTIME":"RELTIME");
- return 0;
+ /* Indicate timer isn't set, so caller doesn't wait */
+ return 1;
}
printf("%s - timer_create() failed\n", clockstring(clock_id));
return -1;
int err;
err = setup_timer(clock_id, flags, interval, &tm1);
+ /* Unsupported case - return 0 to not fail the test */
if (err)
- return err;
+ return err == 1 ? 0 : err;
while (alarmcount < 5)
sleep(1);
timer_t tm1;
const int interval = 0;
struct timeval timeout;
- fd_set fds;
int err;
err = setup_timer(clock_id, flags, interval, &tm1);
+ /* Unsupported case - return 0 to not fail the test */
if (err)
- return err;
+ return err == 1 ? 0 : err;
memset(&timeout, 0, sizeof(timeout));
timeout.tv_sec = 5;
- FD_ZERO(&fds);
do {
- err = select(FD_SETSIZE, &fds, NULL, NULL, &timeout);
+ err = select(0, NULL, NULL, NULL, &timeout);
} while (err == -1 && errno == EINTR);
timer_delete(tm1);
-TEST_PROGS := watchdog-test
-
-all: $(TEST_PROGS)
+TEST_GEN_PROGS := watchdog-test
include ../lib.mk
-
-clean:
- rm -fr $(TEST_PROGS)
{
if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
return -EINVAL;
- if (args->gsi >= KVM_MAX_IRQ_ROUTES)
- return -EINVAL;
if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
return kvm_irqfd_deassign(kvm, args);
projects / mirror_ubuntu-bionic-kernel.git / commitdiff