diff options
350 files changed, 12718 insertions, 6024 deletions
diff --git a/Documentation/admin-guide/LSM/Smack.rst b/Documentation/admin-guide/LSM/Smack.rst index 6a5826a13aea..6d44f4fdbf59 100644 --- a/Documentation/admin-guide/LSM/Smack.rst +++ b/Documentation/admin-guide/LSM/Smack.rst @@ -818,6 +818,10 @@ Smack supports some mount options: specifies a label to which all labels set on the filesystem must have read access. Not yet enforced. + smackfstransmute=label: + behaves exactly like smackfsroot except that it also + sets the transmute flag on the root of the mount + These mount options apply to all file system types. Smack auditing diff --git a/Documentation/devicetree/bindings/input/touchscreen/raspberrypi,firmware-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/raspberrypi,firmware-ts.txt new file mode 100644 index 000000000000..2a1af240ccc3 --- /dev/null +++ b/Documentation/devicetree/bindings/input/touchscreen/raspberrypi,firmware-ts.txt @@ -0,0 +1,26 @@ +Raspberry Pi firmware based 7" touchscreen +===================================== + +Required properties: + - compatible: "raspberrypi,firmware-ts" + +Optional properties: + - firmware: Reference to RPi's firmware device node + - touchscreen-size-x: See touchscreen.txt + - touchscreen-size-y: See touchscreen.txt + - touchscreen-inverted-x: See touchscreen.txt + - touchscreen-inverted-y: See touchscreen.txt + - touchscreen-swapped-x-y: See touchscreen.txt + +Example: + +firmware: firmware-rpi { + compatible = "raspberrypi,bcm2835-firmware"; + mboxes = <&mailbox>; + + ts: touchscreen { + compatible = "raspberrypi,firmware-ts"; + touchscreen-size-x = <800>; + touchscreen-size-y = <480>; + }; +}; diff --git a/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt b/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt index b99d25fc2f26..ff3eafc5a882 100644 --- a/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt +++ b/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt @@ -15,12 +15,15 @@ Required properties: Array of strings. one of: - "nvidia,tegra186-hsp" + - "nvidia,tegra194-hsp", "nvidia,tegra186-hsp" - reg : Offset and length of the register set for the device. - interrupt-names Array of strings. Contains a list of names for the interrupts described by the interrupt property. May contain the following entries, in any order: - "doorbell" + - "sharedN", where 'N' is a number from zero up to the number of + external interrupts supported by the HSP instance minus one. Users of this binding MUST look up entries in the interrupt property by name, using this interrupt-names property to do so. - interrupts @@ -29,12 +32,29 @@ Required properties: in a matching order. - #mbox-cells : Should be 2. -The mbox specifier of the "mboxes" property in the client node should -contain two data. The first one should be the HSP type and the second -one should be the ID that the client is going to use. Those information -can be found in the following file. +The mbox specifier of the "mboxes" property in the client node should contain +two cells. The first cell determines the HSP type and the second cell is used +to identify the mailbox that the client is going to use. -- <dt-bindings/mailbox/tegra186-hsp.h>. +For doorbells, the second cell specifies the index of the doorbell to use. + +For shared mailboxes, the second cell is composed of two fields: +- bits 31..24: + A bit mask of flags that further specify how the shared mailbox will be + used. Valid flags are: + - bit 31: + Defines the direction of the mailbox. If set, the mailbox will be used + as a producer (i.e. used to send data). If cleared, the mailbox is the + consumer of data sent by a producer. + +- bits 23.. 0: + The index of the shared mailbox to use. The number of available mailboxes + may vary by instance of the HSP block and SoC generation. + +The following file contains definitions that can be used to construct mailbox +specifiers: + + <dt-bindings/mailbox/tegra186-hsp.h> Example: diff --git a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt index 0e72183f52bc..36603419d6f8 100644 --- a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt +++ b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt @@ -4,10 +4,14 @@ Required properties: - compatible : "olpc,ap-sp" - reg : base address and length of SoC's WTM registers - interrupts : SP-AP interrupt +- clocks : phandle + clock-specifier for the clock that drives the WTM +- clock-names: should be "sp" Example: ap-sp@d4290000 { compatible = "olpc,ap-sp"; reg = <0xd4290000 0x1000>; interrupts = <40>; + clocks = <&soc_clocks MMP2_CLK_SP>; + clock-names = "sp"; } diff --git a/Documentation/filesystems/cifs/TODO b/Documentation/filesystems/cifs/TODO index 852499aed64b..66b3f54aa6dc 100644 --- a/Documentation/filesystems/cifs/TODO +++ b/Documentation/filesystems/cifs/TODO @@ -1,4 +1,4 @@ -Version 2.11 September 13, 2017 +Version 2.14 December 21, 2018 A Partial List of Missing Features ================================== @@ -7,7 +7,7 @@ Contributions are welcome. There are plenty of opportunities for visible, important contributions to this module. Here is a partial list of the known problems and missing features: -a) SMB3 (and SMB3.02) missing optional features: +a) SMB3 (and SMB3.1.1) missing optional features: - multichannel (started), integration with RDMA - directory leases (improved metadata caching), started (root dir only) - T10 copy offload ie "ODX" (copy chunk, and "Duplicate Extents" ioctl @@ -21,8 +21,9 @@ using Directory Leases, currently only the root file handle is cached longer d) quota support (needs minor kernel change since quota calls to make it to network filesystems or deviceless filesystems) -e) Compounding (in progress) to reduce number of roundtrips, and also -better optimize open to reduce redundant opens (using reference counts more). +e) Additional use cases where we use "compoounding" (e.g. open/query/close +and open/setinfo/close) to reduce the number of roundtrips, and also +open to reduce redundant opens (using deferred close and reference counts more). f) Finish inotify support so kde and gnome file list windows will autorefresh (partially complete by Asser). Needs minor kernel @@ -43,11 +44,13 @@ exists. Also better integration with winbind for resolving SID owners k) Add tools to take advantage of more smb3 specific ioctls and features (passthrough ioctl/fsctl for sending various SMB3 fsctls to the server -is in progress) +is in progress, and a passthrough query_info call is already implemented +in cifs.ko to allow smb3 info levels queries to be sent from userspace) l) encrypted file support -m) improved stats gathering, tools (perhaps integration with nfsometer?) +m) improved stats gathering tools (perhaps integration with nfsometer?) +to extend and make easier to use what is currently in /proc/fs/cifs/Stats 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 @@ -76,6 +79,9 @@ and simplify the code. v) POSIX Extensions for SMB3.1.1 (started, create and mkdir support added so far). +w) Add support for additional strong encryption types, and additional spnego +authentication mechanisms (see MS-SMB2) + KNOWN BUGS ==================================== See http://bugzilla.samba.org - search on product "CifsVFS" for @@ -102,3 +108,11 @@ and when signing is disabled to request larger read sizes (larger than negotiated size) and send larger write sizes to modern servers. 4) More exhaustively test against less common servers + +5) Continue to extend the smb3 "buildbot" which does automated xfstesting +against Windows, Samba and Azure currently - to add additional tests and +to allow the buildbot to execute the tests faster. + +6) Address various coverity warnings (most are not bugs per-se, but +the more warnings are addressed, the easier it is to spot real +problems that static analyzers will point out in the future). diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index af6f6ba1fe80..c9558146ac58 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -79,6 +79,7 @@ Code Seq#(hex) Include File Comments 0x1b all InfiniBand Subsystem <http://infiniband.sourceforge.net/> 0x20 all drivers/cdrom/cm206.h 0x22 all scsi/sg.h +'!' 00-1F uapi/linux/seccomp.h '#' 00-3F IEEE 1394 Subsystem Block for the entire subsystem '$' 00-0F linux/perf_counter.h, linux/perf_event.h '%' 00-0F include/uapi/linux/stm.h diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst index f8eb77ddbd44..b0dfdaaca512 100644 --- a/Documentation/networking/snmp_counter.rst +++ b/Documentation/networking/snmp_counter.rst @@ -571,7 +571,97 @@ duplicate packet is received. * TcpExtTCPDSACKOfoRecv The TCP stack receives a DSACK, which indicate an out of order -duplciate packet is received. +duplicate packet is received. + +TCP out of order +=============== +* TcpExtTCPOFOQueue +The TCP layer receives an out of order packet and has enough memory +to queue it. + +* TcpExtTCPOFODrop +The TCP layer receives an out of order packet but doesn't have enough +memory, so drops it. Such packets won't be counted into +TcpExtTCPOFOQueue. + +* TcpExtTCPOFOMerge +The received out of order packet has an overlay with the previous +packet. the overlay part will be dropped. All of TcpExtTCPOFOMerge +packets will also be counted into TcpExtTCPOFOQueue. + +TCP PAWS +======= +PAWS (Protection Against Wrapped Sequence numbers) is an algorithm +which is used to drop old packets. It depends on the TCP +timestamps. For detail information, please refer the `timestamp wiki`_ +and the `RFC of PAWS`_. + +.. _RFC of PAWS: https://tools.ietf.org/html/rfc1323#page-17 +.. _timestamp wiki: https://en.wikipedia.org/wiki/Transmission_Control_Protocol#TCP_timestamps + +* TcpExtPAWSActive +Packets are dropped by PAWS in Syn-Sent status. + +* TcpExtPAWSEstab +Packets are dropped by PAWS in any status other than Syn-Sent. + +TCP ACK skip +=========== +In some scenarios, kernel would avoid sending duplicate ACKs too +frequently. Please find more details in the tcp_invalid_ratelimit +section of the `sysctl document`_. When kernel decides to skip an ACK +due to tcp_invalid_ratelimit, kernel would update one of below +counters to indicate the ACK is skipped in which scenario. The ACK +would only be skipped if the received packet is either a SYN packet or +it has no data. + +.. _sysctl document: https://www.kernel.org/doc/Documentation/networking/ip-sysctl.txt + +* TcpExtTCPACKSkippedSynRecv +The ACK is skipped in Syn-Recv status. The Syn-Recv status means the +TCP stack receives a SYN and replies SYN+ACK. Now the TCP stack is +waiting for an ACK. Generally, the TCP stack doesn't need to send ACK +in the Syn-Recv status. But in several scenarios, the TCP stack need +to send an ACK. E.g., the TCP stack receives the same SYN packet +repeately, the received packet does not pass the PAWS check, or the +received packet sequence number is out of window. In these scenarios, +the TCP stack needs to send ACK. If the ACk sending frequency is higher than +tcp_invalid_ratelimit allows, the TCP stack will skip sending ACK and +increase TcpExtTCPACKSkippedSynRecv. + + +* TcpExtTCPACKSkippedPAWS +The ACK is skipped due to PAWS (Protect Against Wrapped Sequence +numbers) check fails. If the PAWS check fails in Syn-Recv, Fin-Wait-2 +or Time-Wait statuses, the skipped ACK would be counted to +TcpExtTCPACKSkippedSynRecv, TcpExtTCPACKSkippedFinWait2 or +TcpExtTCPACKSkippedTimeWait. In all other statuses, the skipped ACK +would be counted to TcpExtTCPACKSkippedPAWS. + +* TcpExtTCPACKSkippedSeq +The sequence number is out of window and the timestamp passes the PAWS +check and the TCP status is not Syn-Recv, Fin-Wait-2, and Time-Wait. + +* TcpExtTCPACKSkippedFinWait2 +The ACK is skipped in Fin-Wait-2 status, the reason would be either +PAWS check fails or the received sequence number is out of window. + +* TcpExtTCPACKSkippedTimeWait +Tha ACK is skipped in Time-Wait status, the reason would be either +PAWS check failed or the received sequence number is out of window. + +* TcpExtTCPACKSkippedChallenge +The ACK is skipped if the ACK is a challenge ACK. The RFC 5961 defines +3 kind of challenge ACK, please refer `RFC 5961 section 3.2`_, +`RFC 5961 section 4.2`_ and `RFC 5961 section 5.2`_. Besides these +three scenarios, In some TCP status, the linux TCP stack would also +send challenge ACKs if the ACK number is before the first +unacknowledged number (more strict than `RFC 5961 section 5.2`_). + +.. _RFC 5961 section 3.2: https://tools.ietf.org/html/rfc5961#page-7 +.. _RFC 5961 section 4.2: https://tools.ietf.org/html/rfc5961#page-9 +.. _RFC 5961 section 5.2: https://tools.ietf.org/html/rfc5961#page-11 + examples ======= @@ -1188,3 +1278,151 @@ Run nstat on server B:: We have deleted the default route on server B. Server B couldn't find a route for the 8.8.8.8 IP address, so server B increased IpOutNoRoutes. + +TcpExtTCPACKSkippedSynRecv +------------------------ +In this test, we send 3 same SYN packets from client to server. The +first SYN will let server create a socket, set it to Syn-Recv status, +and reply a SYN/ACK. The second SYN will let server reply the SYN/ACK +again, and record the reply time (the duplicate ACK reply time). The +third SYN will let server check the previous duplicate ACK reply time, +and decide to skip the duplicate ACK, then increase the +TcpExtTCPACKSkippedSynRecv counter. + +Run tcpdump to capture a SYN packet:: + + nstatuser@nstat-a:~$ sudo tcpdump -c 1 -w /tmp/syn.pcap port 9000 + tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes + +Open another terminal, run nc command:: + + nstatuser@nstat-a:~$ nc nstat-b 9000 + +As the nstat-b didn't listen on port 9000, it should reply a RST, and +the nc command exited immediately. It was enough for the tcpdump +command to capture a SYN packet. A linux server might use hardware +offload for the TCP checksum, so the checksum in the /tmp/syn.pcap +might be not correct. We call tcprewrite to fix it:: + + nstatuser@nstat-a:~$ tcprewrite --infile=/tmp/syn.pcap --outfile=/tmp/syn_fixcsum.pcap --fixcsum + +On nstat-b, we run nc to listen on port 9000:: + + nstatuser@nstat-b:~$ nc -lkv 9000 + Listening on [0.0.0.0] (family 0, port 9000) + +On nstat-a, we blocked the packet from port 9000, or nstat-a would send +RST to nstat-b:: + + nstatuser@nstat-a:~$ sudo iptables -A INPUT -p tcp --sport 9000 -j DROP + +Send 3 SYN repeatly to nstat-b:: + + nstatuser@nstat-a:~$ for i in {1..3}; do sudo tcpreplay -i ens3 /tmp/syn_fixcsum.pcap; done + +Check snmp cunter on nstat-b:: + + nstatuser@nstat-b:~$ nstat | grep -i skip + TcpExtTCPACKSkippedSynRecv 1 0.0 + +As we expected, TcpExtTCPACKSkippedSynRecv is 1. + +TcpExtTCPACKSkippedPAWS +---------------------- +To trigger PAWS, we could send an old SYN. + +On nstat-b, let nc listen on port 9000:: + + nstatuser@nstat-b:~$ nc -lkv 9000 + Listening on [0.0.0.0] (family 0, port 9000) + +On nstat-a, run tcpdump to capture a SYN:: + + nstatuser@nstat-a:~$ sudo tcpdump -w /tmp/paws_pre.pcap -c 1 port 9000 + tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes + +On nstat-a, run nc as a client to connect nstat-b:: + + nstatuser@nstat-a:~$ nc -v nstat-b 9000 + Connection to nstat-b 9000 port [tcp/*] succeeded! + +Now the tcpdump has captured the SYN and exit. We should fix the +checksum:: + + nstatuser@nstat-a:~$ tcprewrite --infile /tmp/paws_pre.pcap --outfile /tmp/paws.pcap --fixcsum + +Send the SYN packet twice:: + + nstatuser@nstat-a:~$ for i in {1..2}; do sudo tcpreplay -i ens3 /tmp/paws.pcap; done + +On nstat-b, check the snmp counter:: + + nstatuser@nstat-b:~$ nstat | grep -i skip + TcpExtTCPACKSkippedPAWS 1 0.0 + +We sent two SYN via tcpreplay, both of them would let PAWS check +failed, the nstat-b replied an ACK for the first SYN, skipped the ACK +for the second SYN, and updated TcpExtTCPACKSkippedPAWS. + +TcpExtTCPACKSkippedSeq +-------------------- +To trigger TcpExtTCPACKSkippedSeq, we send packets which have valid +timestamp (to pass PAWS check) but the sequence number is out of +window. The linux TCP stack would avoid to skip if the packet has +data, so we need a pure ACK packet. To generate such a packet, we +could create two sockets: one on port 9000, another on port 9001. Then +we capture an ACK on port 9001, change the source/destination port +numbers to match the port 9000 socket. Then we could trigger +TcpExtTCPACKSkippedSeq via this packet. + +On nstat-b, open two terminals, run two nc commands to listen on both +port 9000 and port 9001:: + + nstatuser@nstat-b:~$ nc -lkv 9000 + Listening on [0.0.0.0] (family 0, port 9000) + + nstatuser@nstat-b:~$ nc -lkv 9001 + Listening on [0.0.0.0] (family 0, port 9001) + +On nstat-a, run two nc clients:: + + nstatuser@nstat-a:~$ nc -v nstat-b 9000 + Connection to nstat-b 9000 port [tcp/*] succeeded! + + nstatuser@nstat-a:~$ nc -v nstat-b 9001 + Connection to nstat-b 9001 port [tcp/*] succeeded! + +On nstat-a, run tcpdump to capture an ACK:: + + nstatuser@nstat-a:~$ sudo tcpdump -w /tmp/seq_pre.pcap -c 1 dst port 9001 + tcpdump: listening on ens3, link-type EN10MB (Ethernet), capture size 262144 bytes + +On nstat-b, send a packet via the port 9001 socket. E.g. we sent a +string 'foo' in our example:: + + nstatuser@nstat-b:~$ nc -lkv 9001 + Listening on [0.0.0.0] (family 0, port 9001) + Connection from nstat-a 42132 received! + foo + +On nstat-a, the tcpdump should have caputred the ACK. We should check +the source port numbers of the two nc clients:: + + nstatuser@nstat-a:~$ ss -ta '( dport = :9000 || dport = :9001 )' | tee + State Recv-Q Send-Q Local Address:Port Peer Address:Port + ESTAB 0 0 192.168.122.250:50208 192.168.122.251:9000 + ESTAB 0 0 192.168.122.250:42132 192.168.122.251:9001 + +Run tcprewrite, change port 9001 to port 9000, chagne port 42132 to +port 50208:: + + nstatuser@nstat-a:~$ tcprewrite --infile /tmp/seq_pre.pcap --outfile /tmp/seq.pcap -r 9001:9000 -r 42132:50208 --fixcsum + +Now the /tmp/seq.pcap is the packet we need. Send it to nstat-b:: + + nstatuser@nstat-a:~$ for i in {1..2}; do sudo tcpreplay -i ens3 /tmp/seq.pcap; done + +Check TcpExtTCPACKSkippedSeq on nstat-b:: + + nstatuser@nstat-b:~$ nstat | grep -i skip + TcpExtTCPACKSkippedSeq 1 0.0 diff --git a/Documentation/security/keys/trusted-encrypted.rst b/Documentation/security/keys/trusted-encrypted.rst index e8a1c35cd277..7b35fcb58933 100644 --- a/Documentation/security/keys/trusted-encrypted.rst +++ b/Documentation/security/keys/trusted-encrypted.rst @@ -18,10 +18,33 @@ integrity verifications match. A loaded Trusted Key can be updated with new when the kernel and initramfs are updated. The same key can have many saved blobs under different PCR values, so multiple boots are easily supported. +TPM 1.2 +------- + By default, trusted keys are sealed under the SRK, which has the default authorization value (20 zeros). This can be set at takeownership time with the trouser's utility: "tpm_takeownership -u -z". +TPM 2.0 +------- + +The user must first create a storage key and make it persistent, so the key is +available after reboot. This can be done using the following commands. + +With the IBM TSS 2 stack:: + + #> tsscreateprimary -hi o -st + Handle 80000000 + #> tssevictcontrol -hi o -ho 80000000 -hp 81000001 + +Or with the Intel TSS 2 stack:: + + #> tpm2_createprimary --hierarchy o -G rsa2048 -o key.ctxt + [...] + handle: 0x800000FF + #> tpm2_evictcontrol -c key.ctxt -p 0x81000001 + persistentHandle: 0x81000001 + Usage:: keyctl add trusted name "new keylen [options]" ring @@ -30,7 +53,9 @@ Usage:: keyctl print keyid options: - keyhandle= ascii hex value of sealing key default 0x40000000 (SRK) + keyhandle= ascii hex value of sealing key + TPM 1.2: default 0x40000000 (SRK) + TPM 2.0: no default; must be passed every time keyauth= ascii hex auth for sealing key default 0x00...i (40 ascii zeros) blobauth= ascii hex auth for sealed data default 0x00... @@ -84,6 +109,10 @@ Examples of trusted and encrypted key usage: Create and save a trusted key named "kmk" of length 32 bytes:: +Note: When using a TPM 2.0 with a persistent key with handle 0x81000001, +append 'keyhandle=0x81000001' to statements between quotes, such as +"new 32 keyhandle=0x81000001". + $ keyctl add trusted kmk "new 32" @u 440502848 diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 82a468bc7560..b1b846d8a094 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -122,6 +122,11 @@ In precedence order, they are: Results in the lower 16-bits of the return value being passed to userland as the errno without executing the system call. +``SECCOMP_RET_USER_NOTIF``: + Results in a ``struct seccomp_notif`` message sent on the userspace + notification fd, if it is attached, or ``-ENOSYS`` if it is not. See below + on discussion of how to handle user notifications. + ``SECCOMP_RET_TRACE``: When returned, this value will cause the kernel to attempt to notify a ``ptrace()``-based tracer prior to executing the system @@ -183,6 +188,85 @@ The ``samples/seccomp/`` directory contains both an x86-specific example and a more generic example of a higher level macro interface for BPF program generation. +Userspace Notification +====================== + +The ``SECCOMP_RET_USER_NOTIF`` return code lets seccomp filters pass a +particular syscall to userspace to be handled. This may be useful for +applications like container managers, which wish to intercept particular +syscalls (``mount()``, ``finit_module()``, etc.) and change their behavior. + +To acquire a notification FD, use the ``SECCOMP_FILTER_FLAG_NEW_LISTENER`` +argument to the ``seccomp()`` syscall: + +.. code-block:: c + + fd = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FILTER_FLAG_NEW_LISTENER, &prog); + +which (on success) will return a listener fd for the filter, which can then be +passed around via ``SCM_RIGHTS`` or similar. Note that filter fds correspond to +a particular filter, and not a particular task. So if this task then forks, +notifications from both tasks will appear on the same filter fd. Reads and +writes to/from a filter fd are also synchronized, so a filter fd can safely +have many readers. + +The interface for a seccomp notification fd consists of two structures: + +.. code-block:: c + + struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; + }; + + struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; + }; + + struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; + }; + +The ``struct seccomp_notif_sizes`` structure can be used to determine the size +of the various structures used in seccomp notifications. The size of ``struct +seccomp_data`` may change in the future, so code should use: + +.. code-block:: c + + struct seccomp_notif_sizes sizes; + seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes); + +to determine the size of the various structures to allocate. See +samples/seccomp/user-trap.c for an example. + +Users can read via ``ioctl(SECCOMP_IOCTL_NOTIF_RECV)`` (or ``poll()``) on a +seccomp notification fd to receive a ``struct seccomp_notif``, which contains +five members: the input length of the structure, a unique-per-filter ``id``, +the ``pid`` of the task which triggered this request (which may be 0 if the +task is in a pid ns not visible from the listener's pid namespace), a ``flags`` +member which for now only has ``SECCOMP_NOTIF_FLAG_SIGNALED``, representing +whether or not the notification is a result of a non-fatal signal, and the +``data`` passed to seccomp. Userspace can then make a decision based on this +information about what to do, and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a +response, indicating what should be returned to userspace. The ``id`` member of +``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct +seccomp_notif``. + +It is worth noting that ``struct seccomp_data`` contains the values of register +arguments to the syscall, but does not contain pointers to memory. The task's +memory is accessible to suitably privileged traces via ``ptrace()`` or +``/proc/pid/mem``. However, care should be taken to avoid the TOCTOU mentioned +above in this document: all arguments being read from the tracee's memory +should be read into the tracer's memory before any policy decisions are made. +This allows for an atomic decision on syscall arguments. + Sysctls ======= diff --git a/MAINTAINERS b/MAINTAINERS index 7ba42fbb2c4a..99113b9fcdd2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13162,7 +13162,9 @@ F: drivers/pci/hotplug/s390_pci_hpc.c S390 VFIO-CCW DRIVER M: Cornelia Huck <cohuck@redhat.com> -M: Halil Pasic <pasic@linux.ibm.com> +M: Farhan Ali <alifm@linux.ibm.com> +M: Eric Farman <farman@linux.ibm.com> +R: Halil Pasic <pasic@linux.ibm.com> L: linux-s390@vger.kernel.org L: kvm@vger.kernel.org S: Supported @@ -15949,15 +15951,16 @@ F: drivers/media/usb/zr364xx/ USER-MODE LINUX (UML) M: Jeff Dike <jdike@addtoit.com> M: Richard Weinberger <richard@nod.at> +M: Anton Ivanov <anton.ivanov@cambridgegreys.com> L: linux-um@lists.infradead.org W: http://user-mode-linux.sourceforge.net +Q: https://patchwork.ozlabs.org/project/linux-um/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rw/uml.git S: Maintained F: Documentation/virtual/uml/ F: arch/um/ F: arch/x86/um/ F: fs/hostfs/ -F: fs/hppfs/ USERSPACE COPYIN/COPYOUT (UIOVEC) M: Alexander Viro <viro@zeniv.linux.org.uk> diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index 8c00fd509c45..1a6a7092d942 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -221,16 +221,22 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid, void *ind) { register unsigned long reg0 asm ("0") = qid | (3UL << 24); - register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl; - register struct ap_queue_status reg1_out asm ("1"); + register union { + unsigned long value; + struct ap_qirq_ctrl qirqctrl; + struct ap_queue_status status; + } reg1 asm ("1"); register void *reg2 asm ("2") = ind; + reg1.qirqctrl = qirqctrl; + asm volatile( ".long 0xb2af0000" /* PQAP(AQIC) */ - : "=d" (reg1_out) - : "d" (reg0), "d" (reg1_in), "d" (reg2) + : "+d" (reg1) + : "d" (reg0), "d" (reg2) : "cc"); - return reg1_out; + + return reg1.status; } /* @@ -264,17 +270,21 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit, { register unsigned long reg0 asm ("0") = qid | (5UL << 24) | ((ifbit & 0x01) << 22); - register unsigned long reg1_in asm ("1") = apinfo->val; - register struct ap_queue_status reg1_out asm ("1"); + register union { + unsigned long value; + struct ap_queue_status status; + } reg1 asm ("1"); register unsigned long reg2 asm ("2"); + reg1.value = apinfo->val; + asm volatile( ".long 0xb2af0000" /* PQAP(QACT) */ - : "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2) + : "+d" (reg1), "=d" (reg2) : "d" (reg0) : "cc"); apinfo->val = reg2; - return reg1_out; + return reg1.status; } /** diff --git a/arch/s390/include/uapi/asm/zcrypt.h b/arch/s390/include/uapi/asm/zcrypt.h index 42c81a95e97b..494c34c50716 100644 --- a/arch/s390/include/uapi/asm/zcrypt.h +++ b/arch/s390/include/uapi/asm/zcrypt.h @@ -150,8 +150,8 @@ struct ica_xcRB { * @cprb_len: CPRB header length [0x0020] * @cprb_ver_id: CPRB version id. [0x04] * @pad_000: Alignment pad bytes - * @flags: Admin cmd [0x80] or functional cmd [0x00] - * @func_id: Function id / subtype [0x5434] + * @flags: Admin bit [0x80], Special bit [0x20] + * @func_id: Function id / subtype [0x5434] "T4" * @source_id: Source id [originator id] * @target_id: Target id [usage/ctrl domain id] * @ret_code: Return code diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c index 2ce28bf0c5ec..48c4ce668244 100644 --- a/arch/s390/kernel/compat_wrapper.c +++ b/arch/s390/kernel/compat_wrapper.c @@ -164,7 +164,7 @@ COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, fla COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags); COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags); COMPAT_SYSCALL_WRAP5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags); -COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, const char __user *, uargs) +COMPAT_SYSCALL_WRAP3(seccomp, unsigned int, op, unsigned int, flags, void __user *, uargs) COMPAT_SYSCALL_WRAP3(getrandom, char __user *, buf, size_t, count, unsigned int, flags) COMPAT_SYSCALL_WRAP2(memfd_create, const char __user *, uname, unsigned int, flags) COMPAT_SYSCALL_WRAP3(bpf, int, cmd, union bpf_attr *, attr, unsigned int, size); diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 2b8f32f56e0c..11613362c4e7 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -81,30 +81,6 @@ static inline int notify_page_fault(struct pt_regs *regs) return ret; } - -/* - * Unlock any spinlocks which will prevent us from getting the - * message out. - */ -void bust_spinlocks(int yes) -{ - if (yes) { - oops_in_progress = 1; - } else { - int loglevel_save = console_loglevel; - console_unblank(); - oops_in_progress = 0; - /* - * OK, the message is on the console. Now we call printk() - * without oops_in_progress set so that printk will give klogd - * a poke. Hold onto your hats... - */ - console_loglevel = 15; - printk(" "); - console_loglevel = loglevel_save; - } -} - /* * Find out which address space caused the exception. * Access register mode is impossible, ignore space == 3. diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 9f6f392a4461..6df622fb406d 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -382,9 +382,7 @@ static void zpci_irq_handler(struct airq_struct *airq) if (ai == -1UL) break; inc_irq_stat(IRQIO_MSI); - airq_iv_lock(aibv, ai); generic_handle_irq(airq_iv_get_data(aibv, ai)); - airq_iv_unlock(aibv, ai); } } } @@ -410,7 +408,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = aisb; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA); if (!zdev->aibv) return -ENOMEM; diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 19b2d2a9b43d..eeb7450db18c 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -436,7 +436,7 @@ int clp_get_state(u32 fid, enum zpci_state *state) struct clp_state_data sd = {fid, ZPCI_FN_STATE_RESERVED}; int rc; - rrb = clp_alloc_block(GFP_KERNEL); + rrb = clp_alloc_block(GFP_ATOMIC); if (!rrb) return -ENOMEM; diff --git a/arch/um/Kconfig b/arch/um/Kconfig index a238547671d6..ec9711d068b7 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -12,6 +12,7 @@ config UML select HAVE_UID16 select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK + select HAVE_DEBUG_BUGVERBOSE select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug index 2014597605ea..85726eeec345 100644 --- a/arch/um/Kconfig.debug +++ b/arch/um/Kconfig.debug @@ -16,6 +16,7 @@ config GPROF config GCOV bool "Enable gcov support" depends on DEBUG_INFO + depends on !KCOV help This option allows developers to retrieve coverage data from a UML session. diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index 05588f9466c7..a4e64edb8f38 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -211,12 +211,6 @@ void deactivate_chan(struct chan *chan, int irq) deactivate_fd(chan->fd, irq); } -void reactivate_chan(struct chan *chan, int irq) -{ - if (chan && chan->enabled) - reactivate_fd(chan->fd, irq); -} - int write_chan(struct chan *chan, const char *buf, int len, int write_irq) { @@ -228,8 +222,6 @@ int write_chan(struct chan *chan, const char *buf, int len, n = chan->ops->write(chan->fd, buf, len, chan->data); if (chan->primary) { ret = n; - if ((ret == -EAGAIN) || ((ret >= 0) && (ret < len))) - reactivate_fd(chan->fd, write_irq); } return ret; } @@ -527,8 +519,6 @@ void chan_interrupt(struct line *line, int irq) tty_insert_flip_char(port, c, TTY_NORMAL); } while (err > 0); - if (err == 0) - reactivate_fd(chan->fd, irq); if (err == -EIO) { if (chan->primary) { tty_port_tty_hangup(&line->port, false); diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 7e524efed584..e0e63931fb2b 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -235,14 +235,6 @@ void line_unthrottle(struct tty_struct *tty) line->throttled = 0; chan_interrupt(line, line->driver->read_irq); - - /* - * Maybe there is enough stuff pending that calling the interrupt - * throttles us again. In this case, line->throttled will be 1 - * again and we shouldn't turn the interrupt back on. - */ - if (!line->throttled) - reactivate_chan(line->chan_in, line->driver->read_irq); } static irqreturn_t line_write_interrupt(int irq, void *data) @@ -667,8 +659,6 @@ static irqreturn_t winch_interrupt(int irq, void *data) tty_kref_put(tty); } out: - if (winch->fd != -1) - reactivate_fd(winch->fd, WINCH_IRQ); return IRQ_HANDLED; } diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index d5f9a2d1da1b..ff3ab72fd90f 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -96,7 +96,6 @@ static irqreturn_t mconsole_interrupt(int irq, void *dev_id) } if (!list_empty(&mc_requests)) schedule_work(&mconsole_work); - reactivate_fd(fd, MCONSOLE_IRQ); return IRQ_HANDLED; } @@ -240,7 +239,6 @@ void mconsole_stop(struct mc_request *req) (*req->cmd->handler)(req); } os_set_fd_block(req->originating_fd, 0); - reactivate_fd(req->originating_fd, MCONSOLE_IRQ); mconsole_reply(req, "", 0, 0); } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 624cb47cc9cd..d80cfb1d9430 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -137,8 +137,6 @@ static irqreturn_t uml_net_interrupt(int irq, void *dev_id) schedule_work(&lp->work); goto out; } - reactivate_fd(lp->fd, UM_ETH_IRQ); - out: spin_unlock(&lp->lock); return IRQ_HANDLED; diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c index 40ca5cc275e9..b0e9ff35daee 100644 --- a/arch/um/drivers/port_kern.c +++ b/arch/um/drivers/port_kern.c @@ -137,7 +137,6 @@ static void port_work_proc(struct work_struct *unused) if (!port->has_connection) continue; - reactivate_fd(port->fd, ACCEPT_IRQ); while (port_accept(port)) ; port->has_connection = 0; diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index 778a0e52d5a5..1d5d3057e6f1 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -73,7 +73,6 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size, return ret ? : -EAGAIN; atomic_inc(&host_sleep_count); - reactivate_fd(random_fd, RANDOM_IRQ); add_sigio_fd(random_fd); add_wait_queue(&host_read_wait, &wait); diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 28c40624bcb6..a4a41421c5e2 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1,4 +1,5 @@ /* + * Copyright (C) 2018 Cambridge Greys Ltd * Copyright (C) 2015-2016 Anton Ivanov (aivanov@brocade.com) * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) * Licensed under the GPL @@ -43,11 +44,11 @@ #include <os.h> #include "cow.h" -enum ubd_req { UBD_READ, UBD_WRITE, UBD_FLUSH }; +/* Max request size is determined by sector mask - 32K */ +#define UBD_MAX_REQUEST (8 * sizeof(long)) struct io_thread_req { struct request *req; - enum ubd_req op; int fds[2]; unsigned long offsets[2]; unsigned long long offset; @@ -153,6 +154,7 @@ struct ubd { struct openflags openflags; unsigned shared:1; unsigned no_cow:1; + unsigned no_trim:1; struct cow cow; struct platform_device pdev; struct request_queue *queue; @@ -176,6 +178,7 @@ struct ubd { .boot_openflags = OPEN_FLAGS, \ .openflags = OPEN_FLAGS, \ .no_cow = 0, \ + .no_trim = 0, \ .shared = 0, \ .cow = DEFAULT_COW, \ .lock = __SPIN_LOCK_UNLOCKED(ubd_devs.lock), \ @@ -322,7 +325,7 @@ static int ubd_setup_common(char *str, int *index_out, char **error_out) *index_out = n; err = -EINVAL; - for (i = 0; i < sizeof("rscd="); i++) { + for (i = 0; i < sizeof("rscdt="); i++) { switch (*str) { case 'r': flags.w = 0; @@ -336,12 +339,15 @@ static int ubd_setup_common(char *str, int *index_out, char **error_out) case 'c': ubd_dev->shared = 1; break; + case 't': + ubd_dev->no_trim = 1; + break; case '=': str++; goto break_loop; default: *error_out = "Expected '=' or flag letter " - "(r, s, c, or d)"; + "(r, s, c, t or d)"; goto out; } str++; @@ -414,6 +420,7 @@ __uml_help(ubd_setup, " 'c' will cause the device to be treated as being shared between multiple\n" " UMLs and file locking will be turned off - this is appropriate for a\n" " cluster filesystem and inappropriate at almost all other times.\n\n" +" 't' will disable trim/discard support on the device (enabled by default).\n\n" ); static int udb_setup(char *str) @@ -511,16 +518,21 @@ static void ubd_handler(void) } for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { struct io_thread_req *io_req = (*irq_req_buffer)[count]; - int err = io_req->error ? BLK_STS_IOERR : BLK_STS_OK; - - if (!blk_update_request(io_req->req, err, io_req->length)) - __blk_mq_end_request(io_req->req, err); + if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { + blk_queue_max_discard_sectors(io_req->req->q, 0); + blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); + blk_queue_flag_clear(QUEUE_FLAG_DISCARD, io_req->req->q); + } + if ((io_req->error) || (io_req->buffer == NULL)) + blk_mq_end_request(io_req->req, io_req->error); + else { + if (!blk_update_request(io_req->req, io_req->error, io_req->length)) + __blk_mq_end_request(io_req->req, io_req->error); + } kfree(io_req); } } - - reactivate_fd(thread_fd, UBD_IRQ); } static irqreturn_t ubd_intr(int irq, void *dev) @@ -789,7 +801,7 @@ static int ubd_open_dev(struct ubd *ubd_dev) if((fd == -ENOENT) && create_cow){ fd = create_cow_file(ubd_dev->file, ubd_dev->cow.file, - ubd_dev->openflags, 1 << 9, PAGE_SIZE, + ubd_dev->openflags, SECTOR_SIZE, PAGE_SIZE, &ubd_dev->cow.bitmap_offset, &ubd_dev->cow.bitmap_len, &ubd_dev->cow.data_offset); @@ -830,6 +842,14 @@ static int ubd_open_dev(struct ubd *ubd_dev) if(err < 0) goto error; ubd_dev->cow.fd = err; } + if (ubd_dev->no_trim == 0) { + ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE; + ubd_dev->queue->limits.discard_alignment = SECTOR_SIZE; + blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST); + blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST); + blk_queue_flag_set(QUEUE_FLAG_DISCARD, ubd_dev->queue); + } + blk_queue_flag_set(QUEUE_FLAG_NONROT, ubd_dev->queue); return 0; error: os_close_file(ubd_dev->fd); @@ -882,7 +902,7 @@ static int ubd_disk_register(int major, u64 size, int unit, return 0; } -#define ROUND_BLOCK(n) ((n + ((1 << 9) - 1)) & (-1 << 9)) +#define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE)) static const struct blk_mq_ops ubd_mq_ops = { .queue_rq = ubd_queue_rq, @@ -1234,10 +1254,10 @@ static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask, __u64 bitmap_offset, unsigned long *bitmap_words, __u64 bitmap_len) { - __u64 sector = io_offset >> 9; + __u64 sector = io_offset >> SECTOR_SHIFT; int i, update_bitmap = 0; - for(i = 0; i < length >> 9; i++){ + for (i = 0; i < length >> SECTOR_SHIFT; i++) { if(cow_mask != NULL) ubd_set_bit(i, (unsigned char *) cow_mask); if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) @@ -1271,14 +1291,14 @@ static void cowify_bitmap(__u64 io_offset, int length, unsigned long *cow_mask, static void cowify_req(struct io_thread_req *req, unsigned long *bitmap, __u64 bitmap_offset, __u64 bitmap_len) { - __u64 sector = req->offset >> 9; + __u64 sector = req->offset >> SECTOR_SHIFT; int i; - if(req->length > (sizeof(req->sector_mask) * 8) << 9) + if (req->length > (sizeof(req->sector_mask) * 8) << SECTOR_SHIFT) panic("Operation too long"); - if(req->op == UBD_READ) { - for(i = 0; i < req->length >> 9; i++){ + if (req_op(req->req) == REQ_OP_READ) { + for (i = 0; i < req->length >> SECTOR_SHIFT; i++) { if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) ubd_set_bit(i, (unsigned char *) &req->sector_mask); @@ -1307,68 +1327,86 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->fds[0] = dev->fd; io_req->error = 0; - if (req_op(req) == REQ_OP_FLUSH) { - io_req->op = UBD_FLUSH; - } else { - io_req->fds[1] = dev->fd; - io_req->cow_offset = -1; - io_req->offset = off; - io_req->length = bvec->bv_len; - io_req->sector_mask = 0; - io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE; - io_req->offsets[0] = 0; - io_req->offsets[1] = dev->cow.data_offset; + if (bvec != NULL) { io_req->buffer = page_address(bvec->bv_page) + bvec->bv_offset; - io_req->sectorsize = 1 << 9; - - if (dev->cow.file) { - cowify_req(io_req, dev->cow.bitmap, - dev->cow.bitmap_offset, dev->cow.bitmap_len); - } + io_req->length = bvec->bv_len; + } else { + io_req->buffer = NULL; + io_req->length = blk_rq_bytes(req); } + io_req->sectorsize = SECTOR_SIZE; + io_req->fds[1] = dev->fd; + io_req->cow_offset = -1; + io_req->offset = off; + io_req->sector_mask = 0; + io_req->offsets[0] = 0; + io_req->offsets[1] = dev->cow.data_offset; + + if (dev->cow.file) + cowify_req(io_req, dev->cow.bitmap, + dev->cow.bitmap_offset, dev->cow.bitmap_len); + ret = os_write_file(thread_fd, &io_req, sizeof(io_req)); if (ret != sizeof(io_req)) { if (ret != -EAGAIN) pr_err("write to io thread failed: %d\n", -ret); kfree(io_req); } - return ret; } +static int queue_rw_req(struct blk_mq_hw_ctx *hctx, struct request *req) +{ + struct req_iterator iter; + struct bio_vec bvec; + int ret; + u64 off = (u64)blk_rq_pos(req) << SECTOR_SHIFT; + + rq_for_each_segment(bvec, req, iter) { + ret = ubd_queue_one_vec(hctx, req, off, &bvec); + if (ret < 0) + return ret; + off += bvec.bv_len; + } + return 0; +} + static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct ubd *ubd_dev = hctx->queue->queuedata; struct request *req = bd->rq; - int ret = 0; + int ret = 0, res = BLK_STS_OK; blk_mq_start_request(req); spin_lock_irq(&ubd_dev->lock); - if (req_op(req) == REQ_OP_FLUSH) { + switch (req_op(req)) { + /* operations with no lentgth/offset arguments */ + case REQ_OP_FLUSH: ret = ubd_queue_one_vec(hctx, req, 0, NULL); - } else { - struct req_iterator iter; - struct bio_vec bvec; - u64 off = (u64)blk_rq_pos(req) << 9; - - rq_for_each_segment(bvec, req, iter) { - ret = ubd_queue_one_vec(hctx, req, off, &bvec); - if (ret < 0) - goto out; - off += bvec.bv_len; - } + break; + case REQ_OP_READ: + case REQ_OP_WRITE: + ret = queue_rw_req(hctx, req); + break; + case REQ_OP_DISCARD: + case REQ_OP_WRITE_ZEROES: + ret = ubd_queue_one_vec(hctx, req, (u64)blk_rq_pos(req) << 9, NULL); + break; + default: + WARN_ON_ONCE(1); + res = BLK_STS_NOTSUPP; } -out: + spin_unlock_irq(&ubd_dev->lock); if (ret < 0) blk_mq_requeue_request(req, true); - return BLK_STS_OK; + return res; } static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo) @@ -1413,39 +1451,60 @@ static int ubd_ioctl(struct block_device *bdev, fmode_t mode, return -EINVAL; } +static int map_error(int error_code) +{ + switch (error_code) { + case 0: + return BLK_STS_OK; + case ENOSYS: + case EOPNOTSUPP: + return BLK_STS_NOTSUPP; + case ENOSPC: + return BLK_STS_NOSPC; + } + return BLK_STS_IOERR; +} + +/* + * Everything from here onwards *IS NOT PART OF THE KERNEL* + * + * The following functions are part of UML hypervisor code. + * All functions from here onwards are executed as a helper + * thread and are not allowed to execute any kernel functions. + * + * Any communication must occur strictly via shared memory and IPC. + * + * Do not add printks, locks, kernel memory operations, etc - it + * will result in unpredictable behaviour and/or crashes. + */ + static int update_bitmap(struct io_thread_req *req) { int n; if(req->cow_offset == -1) - return 0; + return map_error(0); n = os_pwrite_file(req->fds[1], &req->bitmap_words, sizeof(req->bitmap_words), req->cow_offset); - if(n != sizeof(req->bitmap_words)){ - printk("do_io - bitmap update failed, err = %d fd = %d\n", -n, - req->fds[1]); - return 1; - } + if (n != sizeof(req->bitmap_words)) + return map_error(-n); - return 0; + return map_error(0); } static void do_io(struct io_thread_req *req) { - char *buf; + char *buf = NULL; unsigned long len; int n, nsectors, start, end, bit; __u64 off; - if (req->op == UBD_FLUSH) { + /* FLUSH is really a special case, we cannot "case" it with others */ + + if (req_op(req->req) == REQ_OP_FLUSH) { /* fds[0] is always either the rw image or our cow file */ - n = os_sync_file(req->fds[0]); - if (n != 0) { - printk("do_io - sync failed err = %d " - "fd = %d\n", -n, req->fds[0]); - req->error = 1; - } + req->error = map_error(-os_sync_file(req->fds[0])); return; } @@ -1462,30 +1521,42 @@ static void do_io(struct io_thread_req *req) off = req->offset + req->offsets[bit] + start * req->sectorsize; len = (end - start) * req->sectorsize; - buf = &req->buffer[start * req->sectorsize]; + if (req->buffer != NULL) + buf = &req->buffer[start * req->sectorsize]; - if(req->op == UBD_READ){ + switch (req_op(req->req)) { + case REQ_OP_READ: n = 0; do { buf = &buf[n]; len -= n; n = os_pread_file(req->fds[bit], buf, len, off); if (n < 0) { - printk("do_io - read failed, err = %d " - "fd = %d\n", -n, req->fds[bit]); - req->error = 1; + req->error = map_error(-n); return; } } while((n < len) && (n != 0)); if (n < len) memset(&buf[n], 0, len - n); - } else { + break; + case REQ_OP_WRITE: n = os_pwrite_file(req->fds[bit], buf, len, off); if(n != len){ - printk("do_io - write failed err = %d " - "fd = %d\n", -n, req->fds[bit]); - req->error = 1; + req->error = map_error(-n); + return; + } + break; + case REQ_OP_DISCARD: + case REQ_OP_WRITE_ZEROES: + n = os_falloc_punch(req->fds[bit], off, len); + if (n) { + req->error = map_error(-n); return; } + break; + default: + WARN_ON_ONCE(1); + req->error = BLK_STS_NOTSUPP; + return; } start = end; @@ -1520,11 +1591,6 @@ int io_thread(void *arg) if (n == -EAGAIN) { ubd_read_poll(-1); continue; - } else { - printk("io_thread - read failed, fd = %d, " - "err = %d," - "reminder = %d\n", - kernel_fd, -n, io_remainder_size); } } @@ -1539,11 +1605,6 @@ int io_thread(void *arg) res = os_write_file(kernel_fd, ((char *) io_req_buffer) + written, n); if (res >= 0) { written += res; - } else { - if (res != -EAGAIN) { - printk("io_thread - write failed, fd = %d, " - "err = %d\n", kernel_fd, -n); - } } if (written < n) { ubd_write_poll(-1); diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c index 3d8cdbdb4e66..d2c17dd74620 100644 --- a/arch/um/drivers/vector_user.c +++ b/arch/um/drivers/vector_user.c @@ -25,11 +25,13 @@ #include <linux/if_packet.h> #include <sys/socket.h> #include <sys/wait.h> +#include <sys/uio.h> #include <linux/virtio_net.h> #include <netdb.h> #include <stdlib.h> #include <os.h> #include <um_malloc.h> +#include <sys/uio.h> #include "vector_user.h" #define ID_GRE 0 diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index b10dde6cb793..00bcbe2326d9 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -10,9 +10,7 @@ generic-y += exec.h generic-y += extable.h generic-y += ftrace.h generic-y += futex.h -generic-y += hardirq.h generic-y += hw_irq.h -generic-y += io.h generic-y += irq_regs.h generic-y += irq_work.h generic-y += kdebug.h diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 7485398d0737..9c04562310b3 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -197,12 +197,17 @@ static inline pte_t pte_mkold(pte_t pte) static inline pte_t pte_wrprotect(pte_t pte) { - pte_clear_bits(pte, _PAGE_RW); + if (likely(pte_get_bits(pte, _PAGE_RW))) + pte_clear_bits(pte, _PAGE_RW); + else + return pte; return(pte_mknewprot(pte)); } static inline pte_t pte_mkread(pte_t pte) { + if (unlikely(pte_get_bits(pte, _PAGE_USER))) + return pte; pte_set_bits(pte, _PAGE_USER); return(pte_mknewprot(pte)); } @@ -221,6 +226,8 @@ static inline pte_t pte_mkyoung(pte_t pte) static inline pte_t pte_mkwrite(pte_t pte) { + if (unlikely(pte_get_bits(pte, _PAGE_RW))) + return pte; pte_set_bits(pte, _PAGE_RW); return(pte_mknewprot(pte)); } diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h index a7a6120f19d5..e7242a0ae489 100644 --- a/arch/um/include/shared/irq_user.h +++ b/arch/um/include/shared/irq_user.h @@ -31,7 +31,6 @@ struct irq_fd { struct siginfo; extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); extern void free_irq_by_fd(int fd); -extern void reactivate_fd(int fd, int irqnum); extern void deactivate_fd(int fd, int irqnum); extern int deactivate_all_fds(void); extern int activate_ipi(int fd, int pid); diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 048ae37eb5aa..ebf23012a59b 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -175,6 +175,7 @@ extern int os_fchange_dir(int fd); extern unsigned os_major(unsigned long long dev); extern unsigned os_minor(unsigned long long dev); extern unsigned long long os_makedev(unsigned major, unsigned minor); +extern int os_falloc_punch(int fd, unsigned long long offset, int count); /* start_up.c */ extern void os_early_checks(void); diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 8360fa3f676d..f4874b7ec503 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -350,11 +350,6 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) } -void reactivate_fd(int fd, int irqnum) -{ - /** NOP - we do auto-EOI now **/ -} - void deactivate_fd(int fd, int irqnum) { struct irq_entry *to_free; @@ -449,7 +444,6 @@ int um_request_irq(unsigned int irq, int fd, int type, } EXPORT_SYMBOL(um_request_irq); -EXPORT_SYMBOL(reactivate_fd); /* * irq_chip must define at least enable/disable and ack when diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c index b5e0cbb34382..3fb6a4041ed6 100644 --- a/arch/um/kernel/sigio.c +++ b/arch/um/kernel/sigio.c @@ -16,7 +16,6 @@ static irqreturn_t sigio_interrupt(int irq, void *data) char c; os_read_file(sigio_irq_fd, &c, sizeof(c)); - reactivate_fd(sigio_irq_fd, SIGIO_WRITE_IRQ); return IRQ_HANDLED; } diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c index d450797a3a7c..7f06fdbc7ee1 100644 --- a/arch/um/kernel/skas/uaccess.c +++ b/arch/um/kernel/skas/uaccess.c @@ -62,27 +62,28 @@ static int do_op_one_page(unsigned long addr, int len, int is_write, jmp_buf buf; struct page *page; pte_t *pte; - int n, faulted; + int n; pte = maybe_map(addr, is_write); if (pte == NULL) return -1; page = pte_page(*pte); +#ifdef CONFIG_64BIT + pagefault_disable(); + addr = (unsigned long) page_address(page) + + (addr & ~PAGE_MASK); +#else addr = (unsigned long) kmap_atomic(page) + (addr & ~PAGE_MASK); +#endif + n = (*op)(addr, len, arg); - current->thread.fault_catcher = &buf; - - faulted = UML_SETJMP(&buf); - if (faulted == 0) - n = (*op)(addr, len, arg); - else - n = -1; - - current->thread.fault_catcher = NULL; - +#ifdef CONFIG_64BIT + pagefault_enable(); +#else kunmap_atomic((void *)addr); +#endif return n; } diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 37508b190106..8347161c2ae0 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -37,17 +37,19 @@ struct host_vm_change { } mprotect; } u; } ops[1]; + int userspace; int index; - struct mm_id *id; + struct mm_struct *mm; void *data; int force; }; -#define INIT_HVC(mm, force) \ +#define INIT_HVC(mm, force, userspace) \ ((struct host_vm_change) \ { .ops = { { .type = NONE } }, \ - .id = &mm->context.id, \ + .mm = mm, \ .data = NULL, \ + .userspace = userspace, \ .index = 0, \ .force = force }) @@ -68,18 +70,40 @@ static int do_ops(struct host_vm_change *hvc, int end, op = &hvc->ops[i]; switch (op->type) { case MMAP: - ret = map(hvc->id, op->u.mmap.addr, op->u.mmap.len, - op->u.mmap.prot, op->u.mmap.fd, - op->u.mmap.offset, finished, &hvc->data); + if (hvc->userspace) + ret = map(&hvc->mm->context.id, op->u.mmap.addr, + op->u.mmap.len, op->u.mmap.prot, + op->u.mmap.fd, + op->u.mmap.offset, finished, + &hvc->data); + else + map_memory(op->u.mmap.addr, op->u.mmap.offset, + op->u.mmap.len, 1, 1, 1); break; case MUNMAP: - ret = unmap(hvc->id, op->u.munmap.addr, - op->u.munmap.len, finished, &hvc->data); + if (hvc->userspace) + ret = unmap(&hvc->mm->context.id, + op->u.munmap.addr, + op->u.munmap.len, finished, + &hvc->data); + else + ret = os_unmap_memory( + (void *) op->u.munmap.addr, + op->u.munmap.len); + break; case MPROTECT: - ret = protect(hvc->id, op->u.mprotect.addr, - op->u.mprotect.len, op->u.mprotect.prot, - finished, &hvc->data); + if (hvc->userspace) + ret = protect(&hvc->mm->context.id, + op->u.mprotect.addr, + op->u.mprotect.len, + op->u.mprotect.prot, + finished, &hvc->data); + else + ret = os_protect_memory( + (void *) op->u.mprotect.addr, + op->u.mprotect.len, + 1, 1, 1); break; default: printk(KERN_ERR "Unknown op type %d in do_ops\n", @@ -100,9 +124,12 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, { __u64 offset; struct host_vm_op *last; - int fd, ret = 0; + int fd = -1, ret = 0; - fd = phys_mapping(phys, &offset); + if (hvc->userspace) + fd = phys_mapping(phys, &offset); + else + offset = phys; if (hvc->index != 0) { last = &hvc->ops[hvc->index - 1]; if ((last->type == MMAP) && @@ -215,10 +242,11 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) | (x ? UM_PROT_EXEC : 0)); if (hvc->force || pte_newpage(*pte)) { - if (pte_present(*pte)) - ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK, - PAGE_SIZE, prot, hvc); - else + if (pte_present(*pte)) { + if (pte_newpage(*pte)) + ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK, + PAGE_SIZE, prot, hvc); + } else ret = add_munmap(addr, PAGE_SIZE, hvc); } else if (pte_newprot(*pte)) ret = add_mprotect(addr, PAGE_SIZE, prot, hvc); @@ -277,9 +305,9 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr, pgd_t *pgd; struct host_vm_change hvc; unsigned long addr = start_addr, next; - int ret = 0; + int ret = 0, userspace = 1; - hvc = INIT_HVC(mm, force); + hvc = INIT_HVC(mm, force, userspace); pgd = pgd_offset(mm, addr); do { next = pgd_addr_end(addr, end_addr); @@ -314,9 +342,11 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) pmd_t *pmd; pte_t *pte; unsigned long addr, last; - int updated = 0, err; + int updated = 0, err = 0, force = 0, userspace = 0; + struct host_vm_change hvc; mm = &init_mm; + hvc = INIT_HVC(mm, force, userspace); for (addr = start; addr < end;) { pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) { @@ -325,8 +355,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) last = end; if (pgd_newpage(*pgd)) { updated = 1; - err = os_unmap_memory((void *) addr, - last - addr); + err = add_munmap(addr, last - addr, &hvc); if (err < 0) panic("munmap failed, errno = %d\n", -err); @@ -342,8 +371,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) last = end; if (pud_newpage(*pud)) { updated = 1; - err = os_unmap_memory((void *) addr, - last - addr); + err = add_munmap(addr, last - addr, &hvc); if (err < 0) panic("munmap failed, errno = %d\n", -err); @@ -359,8 +387,7 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) last = end; if (pmd_newpage(*pmd)) { updated = 1; - err = os_unmap_memory((void *) addr, - last - addr); + err = add_munmap(addr, last - addr, &hvc); if (err < 0) panic("munmap failed, errno = %d\n", -err); @@ -372,22 +399,25 @@ static int flush_tlb_kernel_range_common(unsigned long start, unsigned long end) pte = pte_offset_kernel(pmd, addr); if (!pte_present(*pte) || pte_newpage(*pte)) { updated = 1; - err = os_unmap_memory((void *) addr, - PAGE_SIZE); + err = add_munmap(addr, PAGE_SIZE, &hvc); if (err < 0) panic("munmap failed, errno = %d\n", -err); if (pte_present(*pte)) - map_memory(addr, - pte_val(*pte) & PAGE_MASK, - PAGE_SIZE, 1, 1, 1); + err = add_mmap(addr, pte_val(*pte) & PAGE_MASK, + PAGE_SIZE, 0, &hvc); } else if (pte_newprot(*pte)) { updated = 1; - os_protect_memory((void *) addr, PAGE_SIZE, 1, 1, 1); + err = add_mprotect(addr, PAGE_SIZE, 0, &hvc); } addr += PAGE_SIZE; } + if (!err) + err = do_ops(&hvc, hvc.index, 1); + + if (err < 0) + panic("flush_tlb_kernel failed, errno = %d\n", err); return updated; } @@ -491,6 +521,13 @@ pte_t *addr_pte(struct task_struct *task, unsigned long addr) void flush_tlb_all(void) { + /* + * Don't bother flushing if this address space is about to be + * destroyed. + */ + if (atomic_read(¤t->mm->mm_users) == 0) + return; + flush_tlb_mm(current->mm); } @@ -512,6 +549,13 @@ void __flush_tlb_one(unsigned long addr) static void fix_range(struct mm_struct *mm, unsigned long start_addr, unsigned long end_addr, int force) { + /* + * Don't bother flushing if this address space is about to be + * destroyed. + */ + if (atomic_read(&mm->mm_users) == 0) + return; + fix_range_common(mm, start_addr, end_addr, force); } @@ -527,13 +571,6 @@ EXPORT_SYMBOL(flush_tlb_range); void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, unsigned long end) { - /* - * Don't bother flushing if this address space is about to be - * destroyed. - */ - if (atomic_read(&mm->mm_users) == 0) - return; - fix_range(mm, start, end, 0); } diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index c0197097c86e..f25b110d4e70 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -610,3 +610,13 @@ unsigned long long os_makedev(unsigned major, unsigned minor) { return makedev(major, minor); } + +int os_falloc_punch(int fd, unsigned long long offset, int len) +{ + int n = fallocate(fd, FALLOC_FL_PUNCH_HOLE|FALLOC_FL_KEEP_SIZE, offset, len); + + if (n < 0) + return -errno; + return n; +} + diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8824d01c0c35..eb51b0e1189c 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -150,3 +150,7 @@ ifeq ($(CONFIG_X86_64),y) obj-$(CONFIG_MMCONF_FAM10H) += mmconf-fam10h_64.o obj-y += vsmp_64.o endif + +ifdef CONFIG_EFI +obj-$(CONFIG_IMA) += ima_arch.o +endif diff --git a/arch/x86/kernel/ima_arch.c b/arch/x86/kernel/ima_arch.c new file mode 100644 index 000000000000..e47cd9390ab4 --- /dev/null +++ b/arch/x86/kernel/ima_arch.c @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2018 IBM Corporation + */ +#include <linux/efi.h> +#include <linux/ima.h> + +extern struct boot_params boot_params; + +static enum efi_secureboot_mode get_sb_mode(void) +{ + efi_char16_t efi_SecureBoot_name[] = L"SecureBoot"; + efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID; + efi_status_t status; + unsigned long size; + u8 secboot; + + size = sizeof(secboot); + + /* Get variable contents into buffer */ + status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid, + NULL, &size, &secboot); + if (status == EFI_NOT_FOUND) { + pr_info("ima: secureboot mode disabled\n"); + return efi_secureboot_mode_disabled; + } + + if (status != EFI_SUCCESS) { + pr_info("ima: secureboot mode unknown\n"); + return efi_secureboot_mode_unknown; + } + + if (secboot == 0) { + pr_info("ima: secureboot mode disabled\n"); + return efi_secureboot_mode_disabled; + } + + pr_info("ima: secureboot mode enabled\n"); + return efi_secureboot_mode_enabled; +} + +bool arch_ima_get_secureboot(void) +{ + static enum efi_secureboot_mode sb_mode; + static bool initialized; + + if (!initialized && efi_enabled(EFI_BOOT)) { + sb_mode = boot_params.secure_boot; + + if (sb_mode == efi_secureboot_mode_unset) + sb_mode = get_sb_mode(); + initialized = true; + } + + if (sb_mode == efi_secureboot_mode_enabled) + return true; + else + return false; +} + +/* secureboot arch rules */ +static const char * const sb_arch_rules[] = { +#if !IS_ENABLED(CONFIG_KEXEC_VERIFY_SIG) + "appraise func=KEXEC_KERNEL_CHECK appraise_type=imasig", +#endif /* CONFIG_KEXEC_VERIFY_SIG */ + "measure func=KEXEC_KERNEL_CHECK", + NULL +}; + +const char * const *arch_get_ima_policy(void) +{ + if (IS_ENABLED(CONFIG_IMA_ARCH_POLICY) && arch_ima_get_secureboot()) + return sb_arch_rules; + return NULL; +} diff --git a/block/bio.c b/block/bio.c index 8281bfcbc265..4db1008309ed 100644 --- a/block/bio.c +++ b/block/bio.c @@ -2097,8 +2097,12 @@ EXPORT_SYMBOL_GPL(bio_associate_blkg); */ void bio_clone_blkg_association(struct bio *dst, struct bio *src) { + rcu_read_lock(); + if (src->bi_blkg) __bio_associate_blkg(dst, src->bi_blkg); + + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(bio_clone_blkg_association); #endif /* CONFIG_BLK_CGROUP */ diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c8cc1cbb6370..2bed5725aa03 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -438,29 +438,6 @@ static void blkg_destroy_all(struct request_queue *q) spin_unlock_irq(&q->queue_lock); } -/* - * A group is RCU protected, but having an rcu lock does not mean that one - * can access all the fields of blkg and assume these are valid. For - * example, don't try to follow throtl_data and request queue links. - * - * Having a reference to blkg under an rcu allows accesses to only values - * local to groups like group stats and group rate limits. - */ -void __blkg_release_rcu(struct rcu_head *rcu_head) -{ - struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head); - - /* release the blkcg and parent blkg refs this blkg has been holding */ - css_put(&blkg->blkcg->css); - if (blkg->parent) - blkg_put(blkg->parent); - - wb_congested_put(blkg->wb_congested); - - blkg_free(blkg); -} -EXPORT_SYMBOL_GPL(__blkg_release_rcu); - static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { diff --git a/block/bsg.c b/block/bsg.c index 44f6028b9567..50e5f8f666f2 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -177,6 +177,10 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode) goto out; } + pr_warn_once( + "BIDI support in bsg has been deprecated and might be removed. " + "Please report your use case to linux-scsi@vger.kernel.org\n"); + next_rq = blk_get_request(q, REQ_OP_SCSI_IN, 0); if (IS_ERR(next_rq)) { ret = PTR_ERR(next_rq); diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 9588e685d994..8cc9c429ad95 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -483,6 +483,8 @@ static int pata_macio_cable_detect(struct ata_port *ap) struct device_node *root = of_find_node_by_path("/"); const char *model = of_get_property(root, "model", NULL); + of_node_put(root); + if (cable && !strncmp(cable, "80-", 3)) { /* Some drives fail to detect 80c cable in PowerBook * These machine use proprietary short IDE cable diff --git a/drivers/base/swnode.c b/drivers/base/swnode.c index 306bb93287af..89ad8dee6ad5 100644 --- a/drivers/base/swnode.c +++ b/drivers/base/swnode.c @@ -477,7 +477,8 @@ software_node_get_parent(const struct fwnode_handle *fwnode) { struct software_node *swnode = to_software_node(fwnode); - return swnode->parent ? &swnode->parent->fwnode : NULL; + return swnode ? (swnode->parent ? &swnode->parent->fwnode : NULL) : + NULL; } struct fwnode_handle * @@ -487,7 +488,7 @@ software_node_get_next_child(const struct fwnode_handle *fwnode, struct software_node *p = to_software_node(fwnode); struct software_node *c = to_software_node(child); - if (list_empty(&p->children) || + if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) return NULL; diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index bf996bd44cfc..0903e0803ec8 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1601,8 +1601,6 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, return p->type->read_size; #endif default: - printk(KERN_DEBUG "fd_ioctl: unknown cmd %d for drive %d.", - cmd, drive); return -ENOSYS; } return 0; diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index 5d5e8d6a8a56..f13b48ff5f43 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -237,6 +237,8 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL"); seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C"); seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync"); + seq_print_rq_state_bit(m, f & EE_TRIM, &sep, "trim"); + seq_print_rq_state_bit(m, f & EE_ZEROOUT, &sep, "zero-out"); seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same"); seq_putc(m, '\n'); } diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 1e47db57b9d2..000a2f4c0e92 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -430,7 +430,11 @@ enum { __EE_MAY_SET_IN_SYNC, /* is this a TRIM aka REQ_OP_DISCARD? */ - __EE_IS_TRIM, + __EE_TRIM, + /* explicit zero-out requested, or + * our lower level cannot handle trim, + * and we want to fall back to zeroout instead */ + __EE_ZEROOUT, /* In case a barrier failed, * we need to resubmit without the barrier flag. */ @@ -472,7 +476,8 @@ enum { }; #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO) #define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC) -#define EE_IS_TRIM (1<<__EE_IS_TRIM) +#define EE_TRIM (1<<__EE_TRIM) +#define EE_ZEROOUT (1<<__EE_ZEROOUT) #define EE_RESUBMITTED (1<<__EE_RESUBMITTED) #define EE_WAS_ERROR (1<<__EE_WAS_ERROR) #define EE_HAS_DIGEST (1<<__EE_HAS_DIGEST) @@ -1556,6 +1561,8 @@ extern void start_resync_timer_fn(struct timer_list *t); extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req); /* drbd_receiver.c */ +extern int drbd_issue_discard_or_zero_out(struct drbd_device *device, + sector_t start, unsigned int nr_sectors, int flags); extern int drbd_receiver(struct drbd_thread *thi); extern int drbd_ack_receiver(struct drbd_thread *thi); extern void drbd_send_ping_wf(struct work_struct *ws); @@ -1609,13 +1616,7 @@ static inline void drbd_tcp_quickack(struct socket *sock) } /* sets the number of 512 byte sectors of our virtual device */ -static inline void drbd_set_my_capacity(struct drbd_device *device, - sector_t size) -{ - /* set_capacity(device->this_bdev->bd_disk, size); */ - set_capacity(device->vdisk, size); - device->this_bdev->bd_inode->i_size = (loff_t)size << 9; -} +void drbd_set_my_capacity(struct drbd_device *device, sector_t size); /* * used to submit our private bio diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index f973a2a845c8..714eb64fabfd 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1668,7 +1668,11 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection, (bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) | (bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) | (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) | - (bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0); + (bio_op(bio) == REQ_OP_WRITE_ZEROES ? + ((connection->agreed_features & DRBD_FF_WZEROES) ? + (DP_ZEROES |(!(bio->bi_opf & REQ_NOUNMAP) ? DP_DISCARD : 0)) + : DP_DISCARD) + : 0); else return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0; } @@ -1712,10 +1716,11 @@ int drbd_send_dblock(struct drbd_peer_device *peer_device, struct drbd_request * } p->dp_flags = cpu_to_be32(dp_flags); - if (dp_flags & DP_DISCARD) { + if (dp_flags & (DP_DISCARD|DP_ZEROES)) { + enum drbd_packet cmd = (dp_flags & DP_ZEROES) ? P_ZEROES : P_TRIM; struct p_trim *t = (struct p_trim*)p; t->size = cpu_to_be32(req->i.size); - err = __send_command(peer_device->connection, device->vnr, sock, P_TRIM, sizeof(*t), NULL, 0); + err = __send_command(peer_device->connection, device->vnr, sock, cmd, sizeof(*t), NULL, 0); goto out; } if (dp_flags & DP_WSAME) { @@ -2034,6 +2039,21 @@ void drbd_init_set_defaults(struct drbd_device *device) device->local_max_bio_size = DRBD_MAX_BIO_SIZE_SAFE; } +static void _drbd_set_my_capacity(struct drbd_device *device, sector_t size) +{ + /* set_capacity(device->this_bdev->bd_disk, size); */ + set_capacity(device->vdisk, size); + device->this_bdev->bd_inode->i_size = (loff_t)size << 9; +} + +void drbd_set_my_capacity(struct drbd_device *device, sector_t size) +{ + char ppb[10]; + _drbd_set_my_capacity(device, size); + drbd_info(device, "size = %s (%llu KB)\n", + ppsize(ppb, size>>1), (unsigned long long)size>>1); +} + void drbd_device_cleanup(struct drbd_device *device) { int i; @@ -2059,7 +2079,7 @@ void drbd_device_cleanup(struct drbd_device *device) } D_ASSERT(device, first_peer_device(device)->connection->net_conf == NULL); - drbd_set_my_capacity(device, 0); + _drbd_set_my_capacity(device, 0); if (device->bitmap) { /* maybe never allocated. */ drbd_bm_resize(device, 0, 1); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index d15703b1ffe8..f2471172a961 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -127,6 +127,35 @@ static int drbd_msg_put_info(struct sk_buff *skb, const char *info) return 0; } +__printf(2, 3) +static int drbd_msg_sprintf_info(struct sk_buff *skb, const char *fmt, ...) +{ + va_list args; + struct nlattr *nla, *txt; + int err = -EMSGSIZE; + int len; + + nla = nla_nest_start(skb, DRBD_NLA_CFG_REPLY); + if (!nla) + return err; + + txt = nla_reserve(skb, T_info_text, 256); + if (!txt) { + nla_nest_cancel(skb, nla); + return err; + } + va_start(args, fmt); + len = vscnprintf(nla_data(txt), 256, fmt, args); + va_end(args); + + /* maybe: retry with larger reserve, if truncated */ + txt->nla_len = nla_attr_size(len+1); + nlmsg_trim(skb, (char*)txt + NLA_ALIGN(txt->nla_len)); + nla_nest_end(skb, nla); + + return 0; +} + /* This would be a good candidate for a "pre_doit" hook, * and per-family private info->pointers. * But we need to stay compatible with older kernels. @@ -668,14 +697,15 @@ drbd_set_role(struct drbd_device *const device, enum drbd_role new_role, int for if (rv == SS_TWO_PRIMARIES) { /* Maybe the peer is detected as dead very soon... retry at most once more in this case. */ - int timeo; - rcu_read_lock(); - nc = rcu_dereference(connection->net_conf); - timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; - rcu_read_unlock(); - schedule_timeout_interruptible(timeo); - if (try < max_tries) + if (try < max_tries) { + int timeo; try = max_tries - 1; + rcu_read_lock(); + nc = rcu_dereference(connection->net_conf); + timeo = nc ? (nc->ping_timeo + 1) * HZ / 10 : 1; + rcu_read_unlock(); + schedule_timeout_interruptible(timeo); + } continue; } if (rv < SS_SUCCESS) { @@ -921,7 +951,6 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct } prev; sector_t u_size, size; struct drbd_md *md = &device->ldev->md; - char ppb[10]; void *buffer; int md_moved, la_size_changed; @@ -999,8 +1028,6 @@ drbd_determine_dev_size(struct drbd_device *device, enum dds_flags flags, struct /* racy, see comments above. */ drbd_set_my_capacity(device, size); md->la_size_sect = size; - drbd_info(device, "size = %s (%llu KB)\n", ppsize(ppb, size>>1), - (unsigned long long)size>>1); } if (rv <= DS_ERROR) goto err_out; @@ -1234,6 +1261,21 @@ static void fixup_discard_if_not_supported(struct request_queue *q) } } +static void fixup_write_zeroes(struct drbd_device *device, struct request_queue *q) +{ + /* Fixup max_write_zeroes_sectors after blk_queue_stack_limits(): + * if we can handle "zeroes" efficiently on the protocol, + * we want to do that, even if our backend does not announce + * max_write_zeroes_sectors itself. */ + struct drbd_connection *connection = first_peer_device(device)->connection; + /* If the peer announces WZEROES support, use it. Otherwise, rather + * send explicit zeroes than rely on some discard-zeroes-data magic. */ + if (connection->agreed_features & DRBD_FF_WZEROES) + q->limits.max_write_zeroes_sectors = DRBD_MAX_BBIO_SECTORS; + else + q->limits.max_write_zeroes_sectors = 0; +} + static void decide_on_write_same_support(struct drbd_device *device, struct request_queue *q, struct request_queue *b, struct o_qlim *o, @@ -1344,6 +1386,7 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi } } fixup_discard_if_not_supported(q); + fixup_write_zeroes(device, q); } void drbd_reconsider_queue_parameters(struct drbd_device *device, struct drbd_backing_dev *bdev, struct o_qlim *o) @@ -1514,6 +1557,30 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis } } +static int disk_opts_check_al_size(struct drbd_device *device, struct disk_conf *dc) +{ + int err = -EBUSY; + + if (device->act_log && + device->act_log->nr_elements == dc->al_extents) + return 0; + + drbd_suspend_io(device); + /* If IO completion is currently blocked, we would likely wait + * "forever" for the activity log to become unused. So we don't. */ + if (atomic_read(&device->ap_bio_cnt)) + goto out; + + wait_event(device->al_wait, lc_try_lock(device->act_log)); + drbd_al_shrink(device); + err = drbd_check_al_size(device, dc); + lc_unlock(device->act_log); + wake_up(&device->al_wait); +out: + drbd_resume_io(device); + return err; +} + int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) { struct drbd_config_context adm_ctx; @@ -1576,15 +1643,12 @@ int drbd_adm_disk_opts(struct sk_buff *skb, struct genl_info *info) } } - drbd_suspend_io(device); - wait_event(device->al_wait, lc_try_lock(device->act_log)); - drbd_al_shrink(device); - err = drbd_check_al_size(device, new_disk_conf); - lc_unlock(device->act_log); - wake_up(&device->al_wait); - drbd_resume_io(device); - + err = disk_opts_check_al_size(device, new_disk_conf); if (err) { + /* Could be just "busy". Ignore? + * Introduce dedicated error code? */ + drbd_msg_put_info(adm_ctx.reply_skb, + "Try again without changing current al-extents setting"); retcode = ERR_NOMEM; goto fail_unlock; } @@ -1934,9 +1998,9 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) } } - if (device->state.conn < C_CONNECTED && - device->state.role == R_PRIMARY && device->ed_uuid && - (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) { + if (device->state.pdsk != D_UP_TO_DATE && device->ed_uuid && + (device->state.role == R_PRIMARY || device->state.peer == R_PRIMARY) && + (device->ed_uuid & ~((u64)1)) != (nbc->md.uuid[UI_CURRENT] & ~((u64)1))) { drbd_err(device, "Can only attach to data with current UUID=%016llX\n", (unsigned long long)device->ed_uuid); retcode = ERR_DATA_NOT_CURRENT; @@ -1950,11 +2014,21 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) } /* Prevent shrinking of consistent devices ! */ - if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && - drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0) < nbc->md.la_size_sect) { - drbd_warn(device, "refusing to truncate a consistent device\n"); - retcode = ERR_DISK_TOO_SMALL; - goto force_diskless_dec; + { + unsigned long long nsz = drbd_new_dev_size(device, nbc, nbc->disk_conf->disk_size, 0); + unsigned long long eff = nbc->md.la_size_sect; + if (drbd_md_test_flag(nbc, MDF_CONSISTENT) && nsz < eff) { + if (nsz == nbc->disk_conf->disk_size) { + drbd_warn(device, "truncating a consistent device during attach (%llu < %llu)\n", nsz, eff); + } else { + drbd_warn(device, "refusing to truncate a consistent device (%llu < %llu)\n", nsz, eff); + drbd_msg_sprintf_info(adm_ctx.reply_skb, + "To-be-attached device has last effective > current size, and is consistent\n" + "(%llu > %llu sectors). Refusing to attach.", eff, nsz); + retcode = ERR_IMPLICIT_SHRINK; + goto force_diskless_dec; + } + } } lock_all_resources(); @@ -2654,8 +2728,10 @@ out: static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection, bool force) { + enum drbd_conns cstate; enum drbd_state_rv rv; +repeat: rv = conn_request_state(connection, NS(conn, C_DISCONNECTING), force ? CS_HARD : 0); @@ -2673,6 +2749,11 @@ static enum drbd_state_rv conn_try_disconnect(struct drbd_connection *connection break; case SS_CW_FAILED_BY_PEER: + spin_lock_irq(&connection->resource->req_lock); + cstate = connection->cstate; + spin_unlock_irq(&connection->resource->req_lock); + if (cstate <= C_WF_CONNECTION) + goto repeat; /* The peer probably wants to see us outdated. */ rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING, disk, D_OUTDATED), 0); diff --git a/drivers/block/drbd/drbd_protocol.h b/drivers/block/drbd/drbd_protocol.h index 48dabbb21e11..e6fc5ad72501 100644 --- a/drivers/block/drbd/drbd_protocol.h +++ b/drivers/block/drbd/drbd_protocol.h @@ -70,6 +70,11 @@ enum drbd_packet { * we may fall back to an opencoded loop instead. */ P_WSAME = 0x34, + /* 0x35 already claimed in DRBD 9 */ + P_ZEROES = 0x36, /* data sock: zero-out, WRITE_ZEROES */ + + /* 0x40 .. 0x48 already claimed in DRBD 9 */ + P_MAY_IGNORE = 0x100, /* Flag to test if (cmd > P_MAY_IGNORE) ... */ P_MAX_OPT_CMD = 0x101, @@ -130,6 +135,12 @@ struct p_header100 { #define DP_SEND_RECEIVE_ACK 128 /* This is a proto B write request */ #define DP_SEND_WRITE_ACK 256 /* This is a proto C write request */ #define DP_WSAME 512 /* equiv. REQ_WRITE_SAME */ +#define DP_ZEROES 1024 /* equiv. REQ_OP_WRITE_ZEROES */ + +/* possible combinations: + * REQ_OP_WRITE_ZEROES: DP_DISCARD | DP_ZEROES + * REQ_OP_WRITE_ZEROES + REQ_NOUNMAP: DP_ZEROES + */ struct p_data { u64 sector; /* 64 bits sector number */ @@ -197,6 +208,42 @@ struct p_block_req { */ #define DRBD_FF_WSAME 4 +/* supports REQ_OP_WRITE_ZEROES on the "wire" protocol. + * + * We used to map that to "discard" on the sending side, and if we cannot + * guarantee that discard zeroes data, the receiving side would map discard + * back to zero-out. + * + * With the introduction of REQ_OP_WRITE_ZEROES, + * we started to use that for both WRITE_ZEROES and DISCARDS, + * hoping that WRITE_ZEROES would "do what we want", + * UNMAP if possible, zero-out the rest. + * + * The example scenario is some LVM "thin" backend. + * + * While an un-allocated block on dm-thin reads as zeroes, on a dm-thin + * with "skip_block_zeroing=true", after a partial block write allocated + * that block, that same block may well map "undefined old garbage" from + * the backends on LBAs that have not yet been written to. + * + * If we cannot distinguish between zero-out and discard on the receiving + * side, to avoid "undefined old garbage" to pop up randomly at later times + * on supposedly zero-initialized blocks, we'd need to map all discards to + * zero-out on the receiving side. But that would potentially do a full + * alloc on thinly provisioned backends, even when the expectation was to + * unmap/trim/discard/de-allocate. + * + * We need to distinguish on the protocol level, whether we need to guarantee + * zeroes (and thus use zero-out, potentially doing the mentioned full-alloc), + * or if we want to put the emphasis on discard, and only do a "best effort + * zeroing" (by "discarding" blocks aligned to discard-granularity, and zeroing + * only potential unaligned head and tail clippings), to at least *try* to + * avoid "false positives" in an online-verify later, hoping that someone + * set skip_block_zeroing=false. + */ +#define DRBD_FF_WZEROES 8 + + struct p_connection_features { u32 protocol_min; u32 feature_flags; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index ccfcf00f2798..c7ad88d91a09 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -50,7 +50,7 @@ #include "drbd_req.h" #include "drbd_vli.h" -#define PRO_FEATURES (DRBD_FF_TRIM|DRBD_FF_THIN_RESYNC|DRBD_FF_WSAME) +#define PRO_FEATURES (DRBD_FF_TRIM|DRBD_FF_THIN_RESYNC|DRBD_FF_WSAME|DRBD_FF_WZEROES) struct packet_info { enum drbd_packet cmd; @@ -1490,14 +1490,129 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]); } -static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req) +/* + * Mapping "discard" to ZEROOUT with UNMAP does not work for us: + * Drivers have to "announce" q->limits.max_write_zeroes_sectors, or it + * will directly go to fallback mode, submitting normal writes, and + * never even try to UNMAP. + * + * And dm-thin does not do this (yet), mostly because in general it has + * to assume that "skip_block_zeroing" is set. See also: + * https://www.mail-archive.com/dm-devel%40redhat.com/msg07965.html + * https://www.redhat.com/archives/dm-devel/2018-January/msg00271.html + * + * We *may* ignore the discard-zeroes-data setting, if so configured. + * + * Assumption is that this "discard_zeroes_data=0" is only because the backend + * may ignore partial unaligned discards. + * + * LVM/DM thin as of at least + * LVM version: 2.02.115(2)-RHEL7 (2015-01-28) + * Library version: 1.02.93-RHEL7 (2015-01-28) + * Driver version: 4.29.0 + * still behaves this way. + * + * For unaligned (wrt. alignment and granularity) or too small discards, + * we zero-out the initial (and/or) trailing unaligned partial chunks, + * but discard all the aligned full chunks. + * + * At least for LVM/DM thin, with skip_block_zeroing=false, + * the result is effectively "discard_zeroes_data=1". + */ +/* flags: EE_TRIM|EE_ZEROOUT */ +int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, int flags) { struct block_device *bdev = device->ldev->backing_bdev; + struct request_queue *q = bdev_get_queue(bdev); + sector_t tmp, nr; + unsigned int max_discard_sectors, granularity; + int alignment; + int err = 0; - if (blkdev_issue_zeroout(bdev, peer_req->i.sector, peer_req->i.size >> 9, - GFP_NOIO, 0)) - peer_req->flags |= EE_WAS_ERROR; + if ((flags & EE_ZEROOUT) || !(flags & EE_TRIM)) + goto zero_out; + + /* Zero-sector (unknown) and one-sector granularities are the same. */ + granularity = max(q->limits.discard_granularity >> 9, 1U); + alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; + + max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22)); + max_discard_sectors -= max_discard_sectors % granularity; + if (unlikely(!max_discard_sectors)) + goto zero_out; + + if (nr_sectors < granularity) + goto zero_out; + + tmp = start; + if (sector_div(tmp, granularity) != alignment) { + if (nr_sectors < 2*granularity) + goto zero_out; + /* start + gran - (start + gran - align) % gran */ + tmp = start + granularity - alignment; + tmp = start + granularity - sector_div(tmp, granularity); + + nr = tmp - start; + /* don't flag BLKDEV_ZERO_NOUNMAP, we don't know how many + * layers are below us, some may have smaller granularity */ + err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0); + nr_sectors -= nr; + start = tmp; + } + while (nr_sectors >= max_discard_sectors) { + err |= blkdev_issue_discard(bdev, start, max_discard_sectors, GFP_NOIO, 0); + nr_sectors -= max_discard_sectors; + start += max_discard_sectors; + } + if (nr_sectors) { + /* max_discard_sectors is unsigned int (and a multiple of + * granularity, we made sure of that above already); + * nr is < max_discard_sectors; + * I don't need sector_div here, even though nr is sector_t */ + nr = nr_sectors; + nr -= (unsigned int)nr % granularity; + if (nr) { + err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0); + nr_sectors -= nr; + start += nr; + } + } + zero_out: + if (nr_sectors) { + err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, + (flags & EE_TRIM) ? 0 : BLKDEV_ZERO_NOUNMAP); + } + return err != 0; +} +static bool can_do_reliable_discards(struct drbd_device *device) +{ + struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev); + struct disk_conf *dc; + bool can_do; + + if (!blk_queue_discard(q)) + return false; + + rcu_read_lock(); + dc = rcu_dereference(device->ldev->disk_conf); + can_do = dc->discard_zeroes_if_aligned; + rcu_read_unlock(); + return can_do; +} + +static void drbd_issue_peer_discard_or_zero_out(struct drbd_device *device, struct drbd_peer_request *peer_req) +{ + /* If the backend cannot discard, or does not guarantee + * read-back zeroes in discarded ranges, we fall back to + * zero-out. Unless configuration specifically requested + * otherwise. */ + if (!can_do_reliable_discards(device)) + peer_req->flags |= EE_ZEROOUT; + + if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector, + peer_req->i.size >> 9, peer_req->flags & (EE_ZEROOUT|EE_TRIM))) + peer_req->flags |= EE_WAS_ERROR; drbd_endio_write_sec_final(peer_req); } @@ -1550,7 +1665,7 @@ int drbd_submit_peer_request(struct drbd_device *device, * Correctness first, performance later. Next step is to code an * asynchronous variant of the same. */ - if (peer_req->flags & (EE_IS_TRIM|EE_WRITE_SAME)) { + if (peer_req->flags & (EE_TRIM|EE_WRITE_SAME|EE_ZEROOUT)) { /* wait for all pending IO completions, before we start * zeroing things out. */ conn_wait_active_ee_empty(peer_req->peer_device->connection); @@ -1567,8 +1682,8 @@ int drbd_submit_peer_request(struct drbd_device *device, spin_unlock_irq(&device->resource->req_lock); } - if (peer_req->flags & EE_IS_TRIM) - drbd_issue_peer_discard(device, peer_req); + if (peer_req->flags & (EE_TRIM|EE_ZEROOUT)) + drbd_issue_peer_discard_or_zero_out(device, peer_req); else /* EE_WRITE_SAME */ drbd_issue_peer_wsame(device, peer_req); return 0; @@ -1765,6 +1880,7 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, void *dig_vv = peer_device->connection->int_dig_vv; unsigned long *data; struct p_trim *trim = (pi->cmd == P_TRIM) ? pi->data : NULL; + struct p_trim *zeroes = (pi->cmd == P_ZEROES) ? pi->data : NULL; struct p_trim *wsame = (pi->cmd == P_WSAME) ? pi->data : NULL; digest_size = 0; @@ -1786,6 +1902,10 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, if (!expect(data_size == 0)) return NULL; ds = be32_to_cpu(trim->size); + } else if (zeroes) { + if (!expect(data_size == 0)) + return NULL; + ds = be32_to_cpu(zeroes->size); } else if (wsame) { if (data_size != queue_logical_block_size(device->rq_queue)) { drbd_err(peer_device, "data size (%u) != drbd logical block size (%u)\n", @@ -1802,7 +1922,7 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, if (!expect(IS_ALIGNED(ds, 512))) return NULL; - if (trim || wsame) { + if (trim || wsame || zeroes) { if (!expect(ds <= (DRBD_MAX_BBIO_SECTORS << 9))) return NULL; } else if (!expect(ds <= DRBD_MAX_BIO_SIZE)) @@ -1827,7 +1947,11 @@ read_in_block(struct drbd_peer_device *peer_device, u64 id, sector_t sector, peer_req->flags |= EE_WRITE; if (trim) { - peer_req->flags |= EE_IS_TRIM; + peer_req->flags |= EE_TRIM; + return peer_req; + } + if (zeroes) { + peer_req->flags |= EE_ZEROOUT; return peer_req; } if (wsame) @@ -2326,8 +2450,12 @@ static unsigned long wire_flags_to_bio_flags(u32 dpf) static unsigned long wire_flags_to_bio_op(u32 dpf) { - if (dpf & DP_DISCARD) + if (dpf & DP_ZEROES) return REQ_OP_WRITE_ZEROES; + if (dpf & DP_DISCARD) + return REQ_OP_DISCARD; + if (dpf & DP_WSAME) + return REQ_OP_WRITE_SAME; else return REQ_OP_WRITE; } @@ -2518,8 +2646,19 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info * op_flags = wire_flags_to_bio_flags(dp_flags); if (pi->cmd == P_TRIM) { D_ASSERT(peer_device, peer_req->i.size > 0); + D_ASSERT(peer_device, op == REQ_OP_DISCARD); + D_ASSERT(peer_device, peer_req->pages == NULL); + /* need to play safe: an older DRBD sender + * may mean zero-out while sending P_TRIM. */ + if (0 == (connection->agreed_features & DRBD_FF_WZEROES)) + peer_req->flags |= EE_ZEROOUT; + } else if (pi->cmd == P_ZEROES) { + D_ASSERT(peer_device, peer_req->i.size > 0); D_ASSERT(peer_device, op == REQ_OP_WRITE_ZEROES); D_ASSERT(peer_device, peer_req->pages == NULL); + /* Do (not) pass down BLKDEV_ZERO_NOUNMAP? */ + if (dp_flags & DP_DISCARD) + peer_req->flags |= EE_TRIM; } else if (peer_req->pages == NULL) { D_ASSERT(device, peer_req->i.size == 0); D_ASSERT(device, dp_flags & DP_FLUSH); @@ -2587,7 +2726,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info * * we wait for all pending requests, respectively wait for * active_ee to become empty in drbd_submit_peer_request(); * better not add ourselves here. */ - if ((peer_req->flags & (EE_IS_TRIM|EE_WRITE_SAME)) == 0) + if ((peer_req->flags & (EE_TRIM|EE_WRITE_SAME|EE_ZEROOUT)) == 0) list_add_tail(&peer_req->w.list, &device->active_ee); spin_unlock_irq(&device->resource->req_lock); @@ -3364,7 +3503,7 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, enum drbd_conns rv = C_MASK; enum drbd_disk_state mydisk; struct net_conf *nc; - int hg, rule_nr, rr_conflict, tentative; + int hg, rule_nr, rr_conflict, tentative, always_asbp; mydisk = device->state.disk; if (mydisk == D_NEGOTIATING) @@ -3415,8 +3554,12 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, rcu_read_lock(); nc = rcu_dereference(peer_device->connection->net_conf); + always_asbp = nc->always_asbp; + rr_conflict = nc->rr_conflict; + tentative = nc->tentative; + rcu_read_unlock(); - if (hg == 100 || (hg == -100 && nc->always_asbp)) { + if (hg == 100 || (hg == -100 && always_asbp)) { int pcount = (device->state.role == R_PRIMARY) + (peer_role == R_PRIMARY); int forced = (hg == -100); @@ -3455,9 +3598,6 @@ static enum drbd_conns drbd_sync_handshake(struct drbd_peer_device *peer_device, "Sync from %s node\n", (hg < 0) ? "peer" : "this"); } - rr_conflict = nc->rr_conflict; - tentative = nc->tentative; - rcu_read_unlock(); if (hg == -100) { /* FIXME this log message is not correct if we end up here @@ -3980,6 +4120,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info struct o_qlim *o = (connection->agreed_features & DRBD_FF_WSAME) ? p->qlim : NULL; enum determine_dev_size dd = DS_UNCHANGED; sector_t p_size, p_usize, p_csize, my_usize; + sector_t new_size, cur_size; int ldsc = 0; /* local disk size changed */ enum dds_flags ddsf; @@ -3987,6 +4128,7 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info if (!peer_device) return config_unknown_volume(connection, pi); device = peer_device->device; + cur_size = drbd_get_capacity(device->this_bdev); p_size = be64_to_cpu(p->d_size); p_usize = be64_to_cpu(p->u_size); @@ -3997,7 +4139,6 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info device->p_size = p_size; if (get_ldev(device)) { - sector_t new_size, cur_size; rcu_read_lock(); my_usize = rcu_dereference(device->ldev->disk_conf)->disk_size; rcu_read_unlock(); @@ -4012,13 +4153,13 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info if (device->state.conn == C_WF_REPORT_PARAMS) p_usize = min_not_zero(my_usize, p_usize); - /* Never shrink a device with usable data during connect. - But allow online shrinking if we are connected. */ + /* Never shrink a device with usable data during connect, + * or "attach" on the peer. + * But allow online shrinking if we are connected. */ new_size = drbd_new_dev_size(device, device->ldev, p_usize, 0); - cur_size = drbd_get_capacity(device->this_bdev); if (new_size < cur_size && device->state.disk >= D_OUTDATED && - device->state.conn < C_CONNECTED) { + (device->state.conn < C_CONNECTED || device->state.pdsk == D_DISKLESS)) { drbd_err(device, "The peer's disk size is too small! (%llu < %llu sectors)\n", (unsigned long long)new_size, (unsigned long long)cur_size); conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD); @@ -4046,8 +4187,8 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info synchronize_rcu(); kfree(old_disk_conf); - drbd_info(device, "Peer sets u_size to %lu sectors\n", - (unsigned long)my_usize); + drbd_info(device, "Peer sets u_size to %lu sectors (old: %lu)\n", + (unsigned long)p_usize, (unsigned long)my_usize); } put_ldev(device); @@ -4080,9 +4221,36 @@ static int receive_sizes(struct drbd_connection *connection, struct packet_info * * However, if he sends a zero current size, * take his (user-capped or) backing disk size anyways. + * + * Unless of course he does not have a disk himself. + * In which case we ignore this completely. */ + sector_t new_size = p_csize ?: p_usize ?: p_size; drbd_reconsider_queue_parameters(device, NULL, o); - drbd_set_my_capacity(device, p_csize ?: p_usize ?: p_size); + if (new_size == 0) { + /* Ignore, peer does not know nothing. */ + } else if (new_size == cur_size) { + /* nothing to do */ + } else if (cur_size != 0 && p_size == 0) { + drbd_warn(device, "Ignored diskless peer device size (peer:%llu != me:%llu sectors)!\n", + (unsigned long long)new_size, (unsigned long long)cur_size); + } else if (new_size < cur_size && device->state.role == R_PRIMARY) { + drbd_err(device, "The peer's device size is too small! (%llu < %llu sectors); demote me first!\n", + (unsigned long long)new_size, (unsigned long long)cur_size); + conn_request_state(peer_device->connection, NS(conn, C_DISCONNECTING), CS_HARD); + return -EIO; + } else { + /* I believe the peer, if + * - I don't have a current size myself + * - we agree on the size anyways + * - I do have a current size, am Secondary, + * and he has the only disk + * - I do have a current size, am Primary, + * and he has the only disk, + * which is larger than my current size + */ + drbd_set_my_capacity(device, new_size); + } } if (get_ldev(device)) { @@ -4142,7 +4310,7 @@ static int receive_uuids(struct drbd_connection *connection, struct packet_info kfree(device->p_uuid); device->p_uuid = p_uuid; - if (device->state.conn < C_CONNECTED && + if ((device->state.conn < C_CONNECTED || device->state.pdsk == D_DISKLESS) && device->state.disk < D_INCONSISTENT && device->state.role == R_PRIMARY && (device->ed_uuid & ~((u64)1)) != (p_uuid[UI_CURRENT] & ~((u64)1))) { @@ -4368,6 +4536,25 @@ static int receive_state(struct drbd_connection *connection, struct packet_info if (peer_state.conn == C_AHEAD) ns.conn = C_BEHIND; + /* TODO: + * if (primary and diskless and peer uuid != effective uuid) + * abort attach on peer; + * + * If this node does not have good data, was already connected, but + * the peer did a late attach only now, trying to "negotiate" with me, + * AND I am currently Primary, possibly frozen, with some specific + * "effective" uuid, this should never be reached, really, because + * we first send the uuids, then the current state. + * + * In this scenario, we already dropped the connection hard + * when we received the unsuitable uuids (receive_uuids(). + * + * Should we want to change this, that is: not drop the connection in + * receive_uuids() already, then we would need to add a branch here + * that aborts the attach of "unsuitable uuids" on the peer in case + * this node is currently Diskless Primary. + */ + if (device->p_uuid && peer_state.disk >= D_NEGOTIATING && get_ldev_if_state(device, D_NEGOTIATING)) { int cr; /* consider resync */ @@ -4380,7 +4567,7 @@ static int receive_state(struct drbd_connection *connection, struct packet_info (peer_state.disk == D_NEGOTIATING || os.disk == D_NEGOTIATING)); /* if we have both been inconsistent, and the peer has been - * forced to be UpToDate with --overwrite-data */ + * forced to be UpToDate with --force */ cr |= test_bit(CONSIDER_RESYNC, &device->flags); /* if we had been plain connected, and the admin requested to * start a sync by "invalidate" or "invalidate-remote" */ @@ -4845,7 +5032,7 @@ static int receive_rs_deallocated(struct drbd_connection *connection, struct pac peer_req->w.cb = e_end_resync_block; peer_req->submit_jif = jiffies; - peer_req->flags |= EE_IS_TRIM; + peer_req->flags |= EE_TRIM; spin_lock_irq(&device->resource->req_lock); list_add_tail(&peer_req->w.list, &device->sync_ee); @@ -4913,6 +5100,7 @@ static struct data_cmd drbd_cmd_handler[] = { [P_CONN_ST_CHG_REQ] = { 0, sizeof(struct p_req_state), receive_req_conn_state }, [P_PROTOCOL_UPDATE] = { 1, sizeof(struct p_protocol), receive_protocol }, [P_TRIM] = { 0, sizeof(struct p_trim), receive_Data }, + [P_ZEROES] = { 0, sizeof(struct p_trim), receive_Data }, [P_RS_DEALLOCATED] = { 0, sizeof(struct p_block_desc), receive_rs_deallocated }, [P_WSAME] = { 1, sizeof(struct p_wsame), receive_Data }, }; @@ -5197,11 +5385,12 @@ static int drbd_do_features(struct drbd_connection *connection) drbd_info(connection, "Handshake successful: " "Agreed network protocol version %d\n", connection->agreed_pro_version); - drbd_info(connection, "Feature flags enabled on protocol level: 0x%x%s%s%s.\n", + drbd_info(connection, "Feature flags enabled on protocol level: 0x%x%s%s%s%s.\n", connection->agreed_features, connection->agreed_features & DRBD_FF_TRIM ? " TRIM" : "", connection->agreed_features & DRBD_FF_THIN_RESYNC ? " THIN_RESYNC" : "", - connection->agreed_features & DRBD_FF_WSAME ? " WRITE_SAME" : + connection->agreed_features & DRBD_FF_WSAME ? " WRITE_SAME" : "", + connection->agreed_features & DRBD_FF_WZEROES ? " WRITE_ZEROES" : connection->agreed_features ? "" : " none"); return 1; @@ -5284,7 +5473,7 @@ static int drbd_do_auth(struct drbd_connection *connection) if (pi.cmd != P_AUTH_CHALLENGE) { drbd_err(connection, "expected AuthChallenge packet, received: %s (0x%04x)\n", cmdname(pi.cmd), pi.cmd); - rv = 0; + rv = -1; goto fail; } diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 1c4da17e902e..643a04af213b 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -63,7 +63,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio drbd_req_make_private_bio(req, bio_src); req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0) | (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0) - | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0) + | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_ZEROES : 0) | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0); req->device = device; req->master_bio = bio_src; @@ -1155,12 +1155,11 @@ static int drbd_process_write_request(struct drbd_request *req) return remote; } -static void drbd_process_discard_req(struct drbd_request *req) +static void drbd_process_discard_or_zeroes_req(struct drbd_request *req, int flags) { - struct block_device *bdev = req->device->ldev->backing_bdev; - - if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9, - GFP_NOIO, 0)) + int err = drbd_issue_discard_or_zero_out(req->device, + req->i.sector, req->i.size >> 9, flags); + if (err) req->private_bio->bi_status = BLK_STS_IOERR; bio_endio(req->private_bio); } @@ -1189,9 +1188,11 @@ drbd_submit_req_private_bio(struct drbd_request *req) if (get_ldev(device)) { if (drbd_insert_fault(device, type)) bio_io_error(bio); - else if (bio_op(bio) == REQ_OP_WRITE_ZEROES || - bio_op(bio) == REQ_OP_DISCARD) - drbd_process_discard_req(req); + else if (bio_op(bio) == REQ_OP_WRITE_ZEROES) + drbd_process_discard_or_zeroes_req(req, EE_ZEROOUT | + ((bio->bi_opf & REQ_NOUNMAP) ? 0 : EE_TRIM)); + else if (bio_op(bio) == REQ_OP_DISCARD) + drbd_process_discard_or_zeroes_req(req, EE_TRIM); else generic_make_request(bio); put_ldev(device); diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index 94c654020f0f..c2f569d2661b 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -208,6 +208,7 @@ enum drbd_req_state_bits { __RQ_WRITE, __RQ_WSAME, __RQ_UNMAP, + __RQ_ZEROES, /* Should call drbd_al_complete_io() for this request... */ __RQ_IN_ACT_LOG, @@ -253,6 +254,7 @@ enum drbd_req_state_bits { #define RQ_WRITE (1UL << __RQ_WRITE) #define RQ_WSAME (1UL << __RQ_WSAME) #define RQ_UNMAP (1UL << __RQ_UNMAP) +#define RQ_ZEROES (1UL << __RQ_ZEROES) #define RQ_IN_ACT_LOG (1UL << __RQ_IN_ACT_LOG) #define RQ_UNPLUG (1UL << __RQ_UNPLUG) #define RQ_POSTPONED (1UL << __RQ_POSTPONED) diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 0813c654c893..2b4c0db5d867 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -688,11 +688,9 @@ request_detach(struct drbd_device *device) CS_VERBOSE | CS_ORDERED | CS_INHIBIT_MD_IO); } -enum drbd_state_rv -drbd_request_detach_interruptible(struct drbd_device *device) +int drbd_request_detach_interruptible(struct drbd_device *device) { - enum drbd_state_rv rv; - int ret; + int ret, rv; drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */ wait_event_interruptible(device->state_wait, @@ -1124,7 +1122,7 @@ static union drbd_state sanitize_state(struct drbd_device *device, union drbd_st ns.pdsk = D_UP_TO_DATE; } - /* Implications of the connection stat on the disk states */ + /* Implications of the connection state on the disk states */ disk_min = D_DISKLESS; disk_max = D_UP_TO_DATE; pdsk_min = D_INCONSISTENT; @@ -2109,9 +2107,8 @@ static int w_after_conn_state_ch(struct drbd_work *w, int unused) spin_unlock_irq(&connection->resource->req_lock); } } - kref_put(&connection->kref, drbd_destroy_connection); - conn_md_sync(connection); + kref_put(&connection->kref, drbd_destroy_connection); return 0; } diff --git a/drivers/block/drbd/drbd_state.h b/drivers/block/drbd/drbd_state.h index ea58301d0895..f87371e55e68 100644 --- a/drivers/block/drbd/drbd_state.h +++ b/drivers/block/drbd/drbd_state.h @@ -131,7 +131,7 @@ extern enum drbd_state_rv _drbd_set_state(struct drbd_device *, union drbd_state enum chg_state_flags, struct completion *done); extern void print_st_err(struct drbd_device *, union drbd_state, - union drbd_state, int); + union drbd_state, enum drbd_state_rv); enum drbd_state_rv _conn_request_state(struct drbd_connection *connection, union drbd_state mask, union drbd_state val, @@ -162,8 +162,7 @@ static inline int drbd_request_state(struct drbd_device *device, } /* for use in adm_detach() (drbd_adm_detach(), drbd_adm_down()) */ -enum drbd_state_rv -drbd_request_detach_interruptible(struct drbd_device *device); +int drbd_request_detach_interruptible(struct drbd_device *device); enum drbd_role conn_highest_role(struct drbd_connection *connection); enum drbd_role conn_highest_peer(struct drbd_connection *connection); diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 99255d0c9e2f..268ef0c5d4ab 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -153,7 +153,7 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l do_wake = list_empty(block_id == ID_SYNCER ? &device->sync_ee : &device->active_ee); /* FIXME do we want to detach for failed REQ_OP_DISCARD? - * ((peer_req->flags & (EE_WAS_ERROR|EE_IS_TRIM)) == EE_WAS_ERROR) */ + * ((peer_req->flags & (EE_WAS_ERROR|EE_TRIM)) == EE_WAS_ERROR) */ if (peer_req->flags & EE_WAS_ERROR) __drbd_chk_io_error(device, DRBD_WRITE_ERROR); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 0939f36548c9..b8a0720d3653 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -616,7 +616,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) default: WARN_ON_ONCE(1); return -EIO; - break; } } diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 9c0553dd13e7..0ff27e2d98c4 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -633,7 +633,6 @@ static int generic_request(struct vdc_port *port, u8 op, void *buf, int len) case VD_OP_GET_EFI: case VD_OP_SET_EFI: return -EOPNOTSUPP; - break; }; map_perm |= LDC_MAP_SHADOW | LDC_MAP_DIRECT | LDC_MAP_IO; diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index c1c676a33e4a..1e2ae90d7715 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -995,7 +995,11 @@ static void floppy_release(struct gendisk *disk, fmode_t mode) struct swim3 __iomem *sw = fs->swim3; mutex_lock(&swim3_mutex); - if (fs->ref_count > 0 && --fs->ref_count == 0) { + if (fs->ref_count > 0) + --fs->ref_count; + else if (fs->ref_count == -1) + fs->ref_count = 0; + if (fs->ref_count == 0) { swim3_action(fs, MOTOR_OFF); out_8(&sw->control_bic, 0xff); swim3_select(fs, RELAX); @@ -1087,8 +1091,6 @@ static int swim3_add_device(struct macio_dev *mdev, int index) struct floppy_state *fs = &floppy_states[index]; int rc = -EBUSY; - /* Do this first for message macros */ - memset(fs, 0, sizeof(*fs)); fs->mdev = mdev; fs->index = index; @@ -1151,7 +1153,6 @@ static int swim3_add_device(struct macio_dev *mdev, int index) swim3_err("%s", "Couldn't request interrupt\n"); pmac_call_feature(PMAC_FTR_SWIM3_ENABLE, swim, 0, 0); goto out_unmap; - return -EBUSY; } timer_setup(&fs->timeout, NULL, 0); @@ -1188,14 +1189,15 @@ static int swim3_attach(struct macio_dev *mdev, return rc; } - fs = &floppy_states[floppy_count]; - disk = alloc_disk(1); if (disk == NULL) { rc = -ENOMEM; goto out_unregister; } + fs = &floppy_states[floppy_count]; + memset(fs, 0, sizeof(*fs)); + disk->queue = blk_mq_init_sq_queue(&fs->tag_set, &swim3_mq_ops, 2, BLK_MQ_F_SHOULD_MERGE); if (IS_ERR(disk->queue)) { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 912c4265e592..b16a887bbd02 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -18,6 +18,7 @@ #define PART_BITS 4 #define VQ_NAME_LEN 16 +#define MAX_DISCARD_SEGMENTS 256u static int major; static DEFINE_IDA(vd_index_ida); @@ -172,10 +173,48 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr, return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); } +static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap) +{ + unsigned short segments = blk_rq_nr_discard_segments(req); + unsigned short n = 0; + struct virtio_blk_discard_write_zeroes *range; + struct bio *bio; + u32 flags = 0; + + if (unmap) + flags |= VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP; + + range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC); + if (!range) + return -ENOMEM; + + __rq_for_each_bio(bio, req) { + u64 sector = bio->bi_iter.bi_sector; + u32 num_sectors = bio->bi_iter.bi_size >> SECTOR_SHIFT; + + range[n].flags = cpu_to_le32(flags); + range[n].num_sectors = cpu_to_le32(num_sectors); + range[n].sector = cpu_to_le64(sector); + n++; + } + + req->special_vec.bv_page = virt_to_page(range); + req->special_vec.bv_offset = offset_in_page(range); + req->special_vec.bv_len = sizeof(*range) * segments; + req->rq_flags |= RQF_SPECIAL_PAYLOAD; + + return 0; +} + static inline void virtblk_request_done(struct request *req) { struct virtblk_req *vbr = blk_mq_rq_to_pdu(req); + if (req->rq_flags & RQF_SPECIAL_PAYLOAD) { + kfree(page_address(req->special_vec.bv_page) + + req->special_vec.bv_offset); + } + switch (req_op(req)) { case REQ_OP_SCSI_IN: case REQ_OP_SCSI_OUT: @@ -239,6 +278,7 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, int qid = hctx->queue_num; int err; bool notify = false; + bool unmap = false; u32 type; BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); @@ -251,6 +291,13 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, case REQ_OP_FLUSH: type = VIRTIO_BLK_T_FLUSH; break; + case REQ_OP_DISCARD: + type = VIRTIO_BLK_T_DISCARD; + break; + case REQ_OP_WRITE_ZEROES: + type = VIRTIO_BLK_T_WRITE_ZEROES; + unmap = !(req->cmd_flags & REQ_NOUNMAP); + break; case REQ_OP_SCSI_IN: case REQ_OP_SCSI_OUT: type = VIRTIO_BLK_T_SCSI_CMD; @@ -270,6 +317,12 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(req); + if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) { + err = virtblk_setup_discard_write_zeroes(req, unmap); + if (err) + return BLK_STS_RESOURCE; + } + num = blk_rq_map_sg(hctx->queue, req, vbr->sg); if (num) { if (rq_data_dir(req) == WRITE) @@ -817,6 +870,32 @@ static int virtblk_probe(struct virtio_device *vdev) if (!err && opt_io_size) blk_queue_io_opt(q, blk_size * opt_io_size); + if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { + q->limits.discard_granularity = blk_size; + + virtio_cread(vdev, struct virtio_blk_config, + discard_sector_alignment, &v); + q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0; + + virtio_cread(vdev, struct virtio_blk_config, + max_discard_sectors, &v); + blk_queue_max_discard_sectors(q, v ? v : UINT_MAX); + + virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, + &v); + blk_queue_max_discard_segments(q, + min_not_zero(v, + MAX_DISCARD_SEGMENTS)); + + blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + } + + if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { + virtio_cread(vdev, struct virtio_blk_config, + max_write_zeroes_sectors, &v); + blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX); + } + virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); @@ -910,14 +989,14 @@ static unsigned int features_legacy[] = { VIRTIO_BLK_F_SCSI, #endif VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, - VIRTIO_BLK_F_MQ, + VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, } ; static unsigned int features[] = { VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, - VIRTIO_BLK_F_MQ, + VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, }; static struct virtio_driver virtio_blk = { diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index a5b8afe3609c..f8b7345fe1cb 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -873,6 +873,7 @@ static void __exit exit_gdrom(void) platform_device_unregister(pd); platform_driver_unregister(&gdrom_driver); kfree(gd.toc); + kfree(gd.cd_info); } module_init(init_gdrom); diff --git a/drivers/char/tpm/Makefile b/drivers/char/tpm/Makefile index 4e9c33ca1f8f..a01c4cab902a 100644 --- a/drivers/char/tpm/Makefile +++ b/drivers/char/tpm/Makefile @@ -3,9 +3,19 @@ # Makefile for the kernel tpm device drivers. # obj-$(CONFIG_TCG_TPM) += tpm.o -tpm-y := tpm-interface.o tpm-dev.o tpm-sysfs.o tpm-chip.o tpm2-cmd.o \ - tpm-dev-common.o tpmrm-dev.o eventlog/common.o eventlog/tpm1.o \ - eventlog/tpm2.o tpm2-space.o +tpm-y := tpm-chip.o +tpm-y += tpm-dev-common.o +tpm-y += tpm-dev.o +tpm-y += tpm-interface.o +tpm-y += tpm1-cmd.o +tpm-y += tpm2-cmd.o +tpm-y += tpmrm-dev.o +tpm-y += tpm2-space.o +tpm-y += tpm-sysfs.o +tpm-y += eventlog/common.o +tpm-y += eventlog/tpm1.o +tpm-y += eventlog/tpm2.o + tpm-$(CONFIG_ACPI) += tpm_ppi.o eventlog/acpi.o tpm-$(CONFIG_EFI) += eventlog/efi.o tpm-$(CONFIG_OF) += eventlog/of.o diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c index abd675bec88c..64dc560859f2 100644 --- a/drivers/char/tpm/st33zp24/st33zp24.c +++ b/drivers/char/tpm/st33zp24/st33zp24.c @@ -649,7 +649,7 @@ int st33zp24_pm_resume(struct device *dev) } else { ret = tpm_pm_resume(dev); if (!ret) - tpm_do_selftest(chip); + tpm1_do_selftest(chip); } return ret; } /* st33zp24_pm_resume() */ diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index 46caadca916a..32db84683c40 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -451,14 +451,9 @@ int tpm_chip_register(struct tpm_chip *chip) { int rc; - if (chip->ops->flags & TPM_OPS_AUTO_STARTUP) { - if (chip->flags & TPM_CHIP_FLAG_TPM2) - rc = tpm2_auto_startup(chip); - else - rc = tpm1_auto_startup(chip); - if (rc) - return rc; - } + rc = tpm_auto_startup(chip); + if (rc) + return rc; tpm_sysfs_add_device(chip); diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 99b5133a9d05..5eecad233ea1 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -40,7 +40,7 @@ static void tpm_async_work(struct work_struct *work) tpm_put_ops(priv->chip); if (ret > 0) { - priv->data_pending = ret; + priv->response_length = ret; mod_timer(&priv->user_read_timer, jiffies + (120 * HZ)); } mutex_unlock(&priv->buffer_mutex); @@ -63,7 +63,8 @@ static void tpm_timeout_work(struct work_struct *work) timeout_work); mutex_lock(&priv->buffer_mutex); - priv->data_pending = 0; + priv->response_read = true; + priv->response_length = 0; memset(priv->data_buffer, 0, sizeof(priv->data_buffer)); mutex_unlock(&priv->buffer_mutex); wake_up_interruptible(&priv->async_wait); @@ -74,6 +75,7 @@ void tpm_common_open(struct file *file, struct tpm_chip *chip, { priv->chip = chip; priv->space = space; + priv->response_read = true; mutex_init(&priv->buffer_mutex); timer_setup(&priv->user_read_timer, user_reader_timeout, 0); @@ -90,22 +92,35 @@ ssize_t tpm_common_read(struct file *file, char __user *buf, ssize_t ret_size = 0; int rc; - del_singleshot_timer_sync(&priv->user_read_timer); - flush_work(&priv->timeout_work); mutex_lock(&priv->buffer_mutex); - if (priv->data_pending) { - ret_size = min_t(ssize_t, size, priv->data_pending); - if (ret_size > 0) { - rc = copy_to_user(buf, priv->data_buffer, ret_size); - memset(priv->data_buffer, 0, priv->data_pending); - if (rc) - ret_size = -EFAULT; + if (priv->response_length) { + priv->response_read = true; + + ret_size = min_t(ssize_t, size, priv->response_length); + if (!ret_size) { + priv->response_length = 0; + goto out; } - priv->data_pending = 0; + rc = copy_to_user(buf, priv->data_buffer + *off, ret_size); + if (rc) { + memset(priv->data_buffer, 0, TPM_BUFSIZE); + priv->response_length = 0; + ret_size = -EFAULT; + } else { + memset(priv->data_buffer + *off, 0, ret_size); + priv->response_length -= ret_size; + *off += ret_size; + } } +out: + if (!priv->response_length) { + *off = 0; + del_singleshot_timer_sync(&priv->user_read_timer); + flush_work(&priv->timeout_work); + } mutex_unlock(&priv->buffer_mutex); return ret_size; } @@ -125,7 +140,8 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, * tpm_read or a user_read_timer timeout. This also prevents split * buffered writes from blocking here. */ - if (priv->data_pending != 0 || priv->command_enqueued) { + if ((!priv->response_read && priv->response_length) || + priv->command_enqueued) { ret = -EBUSY; goto out; } @@ -150,6 +166,10 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, goto out; } + priv->response_length = 0; + priv->response_read = false; + *off = 0; + /* * If in nonblocking mode schedule an async job to send * the command return the size. @@ -168,7 +188,7 @@ ssize_t tpm_common_write(struct file *file, const char __user *buf, tpm_put_ops(priv->chip); if (ret > 0) { - priv->data_pending = ret; + priv->response_length = ret; mod_timer(&priv->user_read_timer, jiffies + (120 * HZ)); ret = size; } @@ -184,7 +204,7 @@ __poll_t tpm_common_poll(struct file *file, poll_table *wait) poll_wait(file, &priv->async_wait, wait); - if (priv->data_pending) + if (!priv->response_read || priv->response_length) mask = EPOLLIN | EPOLLRDNORM; else mask = EPOLLOUT | EPOLLWRNORM; @@ -201,7 +221,7 @@ void tpm_common_release(struct file *file, struct file_priv *priv) del_singleshot_timer_sync(&priv->user_read_timer); flush_work(&priv->timeout_work); file->private_data = NULL; - priv->data_pending = 0; + priv->response_length = 0; } int __init tpm_dev_common_init(void) diff --git a/drivers/char/tpm/tpm-dev.h b/drivers/char/tpm/tpm-dev.h index a126b575cb8c..1089fc0bb290 100644 --- a/drivers/char/tpm/tpm-dev.h +++ b/drivers/char/tpm/tpm-dev.h @@ -9,14 +9,13 @@ struct file_priv { struct tpm_chip *chip; struct tpm_space *space; - /* Holds the amount of data passed or an error code from async op */ - ssize_t data_pending; struct mutex buffer_mutex; - struct timer_list user_read_timer; /* user needs to claim result */ struct work_struct timeout_work; struct work_struct async_work; wait_queue_head_t async_wait; + size_t response_length; + bool response_read; bool command_enqueued; u8 data_buffer[TPM_BUFSIZE]; diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 129f640424b7..d9439f9abe78 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -33,297 +33,32 @@ #include "tpm.h" -#define TPM_MAX_ORDINAL 243 -#define TSC_MAX_ORDINAL 12 -#define TPM_PROTECTED_COMMAND 0x00 -#define TPM_CONNECTION_COMMAND 0x40 - /* * Bug workaround - some TPM's don't flush the most * recently changed pcr on suspend, so force the flush * with an extend to the selected _unused_ non-volatile pcr. */ -static int tpm_suspend_pcr; +static u32 tpm_suspend_pcr; module_param_named(suspend_pcr, tpm_suspend_pcr, uint, 0644); MODULE_PARM_DESC(suspend_pcr, "PCR to use for dummy writes to facilitate flush on suspend."); -/* - * Array with one entry per ordinal defining the maximum amount - * of time the chip could take to return the result. The ordinal - * designation of short, medium or long is defined in a table in - * TCG Specification TPM Main Part 2 TPM Structures Section 17. The - * values of the SHORT, MEDIUM, and LONG durations are retrieved - * from the chip during initialization with a call to tpm_get_timeouts. - */ -static const u8 tpm_ordinal_duration[TPM_MAX_ORDINAL] = { - TPM_UNDEFINED, /* 0 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 5 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 10 */ - TPM_SHORT, - TPM_MEDIUM, - TPM_LONG, - TPM_LONG, - TPM_MEDIUM, /* 15 */ - TPM_SHORT, - TPM_SHORT, - TPM_MEDIUM, - TPM_LONG, - TPM_SHORT, /* 20 */ - TPM_SHORT, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_SHORT, /* 25 */ - TPM_SHORT, - TPM_MEDIUM, - TPM_SHORT, - TPM_SHORT, - TPM_MEDIUM, /* 30 */ - TPM_LONG, - TPM_MEDIUM, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, /* 35 */ - TPM_MEDIUM, - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_MEDIUM, /* 40 */ - TPM_LONG, - TPM_MEDIUM, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, /* 45 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_LONG, - TPM_MEDIUM, /* 50 */ - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 55 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_MEDIUM, /* 60 */ - TPM_MEDIUM, - TPM_MEDIUM, - TPM_SHORT, - TPM_SHORT, - TPM_MEDIUM, /* 65 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 70 */ - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 75 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_LONG, /* 80 */ - TPM_UNDEFINED, - TPM_MEDIUM, - TPM_LONG, - TPM_SHORT, - TPM_UNDEFINED, /* 85 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 90 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, /* 95 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_MEDIUM, /* 100 */ - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 105 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 110 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, /* 115 */ - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_LONG, /* 120 */ - TPM_LONG, - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_SHORT, - TPM_SHORT, /* 125 */ - TPM_SHORT, - TPM_LONG, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, /* 130 */ - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_SHORT, - TPM_MEDIUM, - TPM_UNDEFINED, /* 135 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 140 */ - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 145 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 150 */ - TPM_MEDIUM, - TPM_MEDIUM, - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, /* 155 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 160 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 165 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_LONG, /* 170 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 175 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_MEDIUM, /* 180 */ - TPM_SHORT, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_MEDIUM, /* 185 */ - TPM_SHORT, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 190 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 195 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 200 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, - TPM_SHORT, /* 205 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_MEDIUM, /* 210 */ - TPM_UNDEFINED, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_MEDIUM, - TPM_UNDEFINED, /* 215 */ - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, - TPM_SHORT, /* 220 */ - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_SHORT, - TPM_UNDEFINED, /* 225 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 230 */ - TPM_LONG, - TPM_MEDIUM, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, /* 235 */ - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_UNDEFINED, - TPM_SHORT, /* 240 */ - TPM_UNDEFINED, - TPM_MEDIUM, -}; - -/* - * Returns max number of jiffies to wait +/** + * tpm_calc_ordinal_duration() - calculate the maximum command duration + * @chip: TPM chip to use. + * @ordinal: TPM command ordinal. + * + * The function returns the maximum amount of time the chip could take + * to return the result for a particular ordinal in jiffies. + * + * Return: A maximal duration time for an ordinal in jiffies. */ -unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, - u32 ordinal) +unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) { - int duration_idx = TPM_UNDEFINED; - int duration = 0; - - /* - * We only have a duration table for protected commands, where the upper - * 16 bits are 0. For the few other ordinals the fallback will be used. - */ - if (ordinal < TPM_MAX_ORDINAL) - duration_idx = tpm_ordinal_duration[ordinal]; - - if (duration_idx != TPM_UNDEFINED) - duration = chip->duration[duration_idx]; - if (duration <= 0) - return 2 * 60 * HZ; + if (chip->flags & TPM_CHIP_FLAG_TPM2) + return tpm2_calc_ordinal_duration(chip, ordinal); else - return duration; + return tpm1_calc_ordinal_duration(chip, ordinal); } EXPORT_SYMBOL_GPL(tpm_calc_ordinal_duration); @@ -477,13 +212,15 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip, if (need_locality) { rc = tpm_request_locality(chip, flags); - if (rc < 0) - goto out_no_locality; + if (rc < 0) { + need_locality = false; + goto out_locality; + } } rc = tpm_cmd_ready(chip, flags); if (rc) - goto out; + goto out_locality; rc = tpm2_prepare_space(chip, space, ordinal, buf); if (rc) @@ -500,10 +237,7 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip, if (chip->flags & TPM_CHIP_FLAG_IRQ) goto out_recv; - if (chip->flags & TPM_CHIP_FLAG_TPM2) - stop = jiffies + tpm2_calc_ordinal_duration(chip, ordinal); - else - stop = jiffies + tpm_calc_ordinal_duration(chip, ordinal); + stop = jiffies + tpm_calc_ordinal_duration(chip, ordinal); do { u8 status = chip->ops->status(chip); if ((status & chip->ops->req_complete_mask) == @@ -547,14 +281,13 @@ out_recv: dev_err(&chip->dev, "tpm2_commit_space: error %d\n", rc); out: - rc = tpm_go_idle(chip, flags); - if (rc) - goto out; + /* may fail but do not override previous error value in rc */ + tpm_go_idle(chip, flags); +out_locality: if (need_locality) tpm_relinquish_locality(chip, flags); -out_no_locality: if (chip->ops->clk_enable != NULL) chip->ops->clk_enable(chip, false); @@ -677,277 +410,18 @@ ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_space *space, } EXPORT_SYMBOL_GPL(tpm_transmit_cmd); -#define TPM_ORD_STARTUP 153 -#define TPM_ST_CLEAR 1 - -/** - * tpm_startup - turn on the TPM - * @chip: TPM chip to use - * - * Normally the firmware should start the TPM. This function is provided as a - * workaround if this does not happen. A legal case for this could be for - * example when a TPM emulator is used. - * - * Return: same as tpm_transmit_cmd() - */ -int tpm_startup(struct tpm_chip *chip) -{ - struct tpm_buf buf; - int rc; - - dev_info(&chip->dev, "starting up the TPM manually\n"); - - if (chip->flags & TPM_CHIP_FLAG_TPM2) { - rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_STARTUP); - if (rc < 0) - return rc; - - tpm_buf_append_u16(&buf, TPM2_SU_CLEAR); - } else { - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_STARTUP); - if (rc < 0) - return rc; - - tpm_buf_append_u16(&buf, TPM_ST_CLEAR); - } - - rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, - "attempting to start the TPM"); - - tpm_buf_destroy(&buf); - return rc; -} - -#define TPM_DIGEST_SIZE 20 -#define TPM_RET_CODE_IDX 6 -#define TPM_INTERNAL_RESULT_SIZE 200 -#define TPM_ORD_GET_CAP 101 -#define TPM_ORD_GET_RANDOM 70 - -static const struct tpm_input_header tpm_getcap_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(22), - .ordinal = cpu_to_be32(TPM_ORD_GET_CAP) -}; - -ssize_t tpm_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, - const char *desc, size_t min_cap_length) -{ - struct tpm_buf buf; - int rc; - - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_CAP); - if (rc) - return rc; - - if (subcap_id == TPM_CAP_VERSION_1_1 || - subcap_id == TPM_CAP_VERSION_1_2) { - tpm_buf_append_u32(&buf, subcap_id); - tpm_buf_append_u32(&buf, 0); - } else { - if (subcap_id == TPM_CAP_FLAG_PERM || - subcap_id == TPM_CAP_FLAG_VOL) - tpm_buf_append_u32(&buf, TPM_CAP_FLAG); - else - tpm_buf_append_u32(&buf, TPM_CAP_PROP); - - tpm_buf_append_u32(&buf, 4); - tpm_buf_append_u32(&buf, subcap_id); - } - rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, - min_cap_length, 0, desc); - if (!rc) - *cap = *(cap_t *)&buf.data[TPM_HEADER_SIZE + 4]; - - tpm_buf_destroy(&buf); - return rc; -} -EXPORT_SYMBOL_GPL(tpm_getcap); - int tpm_get_timeouts(struct tpm_chip *chip) { - cap_t cap; - unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4]; - ssize_t rc; - if (chip->flags & TPM_CHIP_FLAG_HAVE_TIMEOUTS) return 0; - if (chip->flags & TPM_CHIP_FLAG_TPM2) { - /* Fixed timeouts for TPM2 */ - chip->timeout_a = msecs_to_jiffies(TPM2_TIMEOUT_A); - chip->timeout_b = msecs_to_jiffies(TPM2_TIMEOUT_B); - chip->timeout_c = msecs_to_jiffies(TPM2_TIMEOUT_C); - chip->timeout_d = msecs_to_jiffies(TPM2_TIMEOUT_D); - chip->duration[TPM_SHORT] = - msecs_to_jiffies(TPM2_DURATION_SHORT); - chip->duration[TPM_MEDIUM] = - msecs_to_jiffies(TPM2_DURATION_MEDIUM); - chip->duration[TPM_LONG] = - msecs_to_jiffies(TPM2_DURATION_LONG); - chip->duration[TPM_LONG_LONG] = - msecs_to_jiffies(TPM2_DURATION_LONG_LONG); - - chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS; - return 0; - } - - rc = tpm_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL, - sizeof(cap.timeout)); - if (rc == TPM_ERR_INVALID_POSTINIT) { - if (tpm_startup(chip)) - return rc; - - rc = tpm_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, - "attempting to determine the timeouts", - sizeof(cap.timeout)); - } - - if (rc) { - dev_err(&chip->dev, - "A TPM error (%zd) occurred attempting to determine the timeouts\n", - rc); - return rc; - } - - timeout_old[0] = jiffies_to_usecs(chip->timeout_a); - timeout_old[1] = jiffies_to_usecs(chip->timeout_b); - timeout_old[2] = jiffies_to_usecs(chip->timeout_c); - timeout_old[3] = jiffies_to_usecs(chip->timeout_d); - timeout_chip[0] = be32_to_cpu(cap.timeout.a); - timeout_chip[1] = be32_to_cpu(cap.timeout.b); - timeout_chip[2] = be32_to_cpu(cap.timeout.c); - timeout_chip[3] = be32_to_cpu(cap.timeout.d); - memcpy(timeout_eff, timeout_chip, sizeof(timeout_eff)); - - /* - * Provide ability for vendor overrides of timeout values in case - * of misreporting. - */ - if (chip->ops->update_timeouts != NULL) - chip->timeout_adjusted = - chip->ops->update_timeouts(chip, timeout_eff); - - if (!chip->timeout_adjusted) { - /* Restore default if chip reported 0 */ - int i; - - for (i = 0; i < ARRAY_SIZE(timeout_eff); i++) { - if (timeout_eff[i]) - continue; - - timeout_eff[i] = timeout_old[i]; - chip->timeout_adjusted = true; - } - - if (timeout_eff[0] != 0 && timeout_eff[0] < 1000) { - /* timeouts in msec rather usec */ - for (i = 0; i != ARRAY_SIZE(timeout_eff); i++) - timeout_eff[i] *= 1000; - chip->timeout_adjusted = true; - } - } - - /* Report adjusted timeouts */ - if (chip->timeout_adjusted) { - dev_info(&chip->dev, - HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n", - timeout_chip[0], timeout_eff[0], - timeout_chip[1], timeout_eff[1], - timeout_chip[2], timeout_eff[2], - timeout_chip[3], timeout_eff[3]); - } - - chip->timeout_a = usecs_to_jiffies(timeout_eff[0]); - chip->timeout_b = usecs_to_jiffies(timeout_eff[1]); - chip->timeout_c = usecs_to_jiffies(timeout_eff[2]); - chip->timeout_d = usecs_to_jiffies(timeout_eff[3]); - - rc = tpm_getcap(chip, TPM_CAP_PROP_TIS_DURATION, &cap, - "attempting to determine the durations", - sizeof(cap.duration)); - if (rc) - return rc; - - chip->duration[TPM_SHORT] = - usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_short)); - chip->duration[TPM_MEDIUM] = - usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_medium)); - chip->duration[TPM_LONG] = - usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long)); - chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */ - - /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above - * value wrong and apparently reports msecs rather than usecs. So we - * fix up the resulting too-small TPM_SHORT value to make things work. - * We also scale the TPM_MEDIUM and -_LONG values by 1000. - */ - if (chip->duration[TPM_SHORT] < (HZ / 100)) { - chip->duration[TPM_SHORT] = HZ; - chip->duration[TPM_MEDIUM] *= 1000; - chip->duration[TPM_LONG] *= 1000; - chip->duration_adjusted = true; - dev_info(&chip->dev, "Adjusting TPM timeout parameters."); - } - - chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS; - return 0; + if (chip->flags & TPM_CHIP_FLAG_TPM2) + return tpm2_get_timeouts(chip); + else + return tpm1_get_timeouts(chip); } EXPORT_SYMBOL_GPL(tpm_get_timeouts); -#define TPM_ORD_CONTINUE_SELFTEST 83 -#define CONTINUE_SELFTEST_RESULT_SIZE 10 - -static const struct tpm_input_header continue_selftest_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(10), - .ordinal = cpu_to_be32(TPM_ORD_CONTINUE_SELFTEST), -}; - -/** - * tpm_continue_selftest -- run TPM's selftest - * @chip: TPM chip to use - * - * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing - * a TPM error code. - */ -static int tpm_continue_selftest(struct tpm_chip *chip) -{ - int rc; - struct tpm_cmd_t cmd; - - cmd.header.in = continue_selftest_header; - rc = tpm_transmit_cmd(chip, NULL, &cmd, CONTINUE_SELFTEST_RESULT_SIZE, - 0, 0, "continue selftest"); - return rc; -} - -#define TPM_ORDINAL_PCRREAD 21 -#define READ_PCR_RESULT_SIZE 30 -#define READ_PCR_RESULT_BODY_SIZE 20 -static const struct tpm_input_header pcrread_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(14), - .ordinal = cpu_to_be32(TPM_ORDINAL_PCRREAD) -}; - -int tpm_pcr_read_dev(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) -{ - int rc; - struct tpm_cmd_t cmd; - - cmd.header.in = pcrread_header; - cmd.params.pcrread_in.pcr_idx = cpu_to_be32(pcr_idx); - rc = tpm_transmit_cmd(chip, NULL, &cmd, READ_PCR_RESULT_SIZE, - READ_PCR_RESULT_BODY_SIZE, 0, - "attempting to read a pcr value"); - - if (rc == 0) - memcpy(res_buf, cmd.params.pcrread_out.pcr_result, - TPM_DIGEST_SIZE); - return rc; -} - /** * tpm_is_tpm2 - do we a have a TPM2 chip? * @chip: a &struct tpm_chip instance, %NULL for the default chip @@ -981,50 +455,24 @@ EXPORT_SYMBOL_GPL(tpm_is_tpm2); * * Return: same as with tpm_transmit_cmd() */ -int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) +int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) { int rc; chip = tpm_find_get_ops(chip); if (!chip) return -ENODEV; + if (chip->flags & TPM_CHIP_FLAG_TPM2) rc = tpm2_pcr_read(chip, pcr_idx, res_buf); else - rc = tpm_pcr_read_dev(chip, pcr_idx, res_buf); + rc = tpm1_pcr_read(chip, pcr_idx, res_buf); + tpm_put_ops(chip); return rc; } EXPORT_SYMBOL_GPL(tpm_pcr_read); -#define TPM_ORD_PCR_EXTEND 20 -#define EXTEND_PCR_RESULT_SIZE 34 -#define EXTEND_PCR_RESULT_BODY_SIZE 20 -static const struct tpm_input_header pcrextend_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(34), - .ordinal = cpu_to_be32(TPM_ORD_PCR_EXTEND) -}; - -static int tpm1_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash, - char *log_msg) -{ - struct tpm_buf buf; - int rc; - - rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_EXTEND); - if (rc) - return rc; - - tpm_buf_append_u32(&buf, pcr_idx); - tpm_buf_append(&buf, hash, TPM_DIGEST_SIZE); - - rc = tpm_transmit_cmd(chip, NULL, buf.data, EXTEND_PCR_RESULT_SIZE, - EXTEND_PCR_RESULT_BODY_SIZE, 0, log_msg); - tpm_buf_destroy(&buf); - return rc; -} - /** * tpm_pcr_extend - extend a PCR value in SHA1 bank. * @chip: a &struct tpm_chip instance, %NULL for the default chip @@ -1037,7 +485,7 @@ static int tpm1_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash, * * Return: same as with tpm_transmit_cmd() */ -int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash) +int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash) { int rc; struct tpm2_digest digest_list[ARRAY_SIZE(chip->active_banks)]; @@ -1071,97 +519,6 @@ int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash) EXPORT_SYMBOL_GPL(tpm_pcr_extend); /** - * tpm_do_selftest - have the TPM continue its selftest and wait until it - * can receive further commands - * @chip: TPM chip to use - * - * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing - * a TPM error code. - */ -int tpm_do_selftest(struct tpm_chip *chip) -{ - int rc; - unsigned int loops; - unsigned int delay_msec = 100; - unsigned long duration; - u8 dummy[TPM_DIGEST_SIZE]; - - duration = tpm_calc_ordinal_duration(chip, TPM_ORD_CONTINUE_SELFTEST); - - loops = jiffies_to_msecs(duration) / delay_msec; - - rc = tpm_continue_selftest(chip); - if (rc == TPM_ERR_INVALID_POSTINIT) { - chip->flags |= TPM_CHIP_FLAG_ALWAYS_POWERED; - dev_info(&chip->dev, "TPM not ready (%d)\n", rc); - } - /* This may fail if there was no TPM driver during a suspend/resume - * cycle; some may return 10 (BAD_ORDINAL), others 28 (FAILEDSELFTEST) - */ - if (rc) - return rc; - - do { - /* Attempt to read a PCR value */ - rc = tpm_pcr_read_dev(chip, 0, dummy); - - /* Some buggy TPMs will not respond to tpm_tis_ready() for - * around 300ms while the self test is ongoing, keep trying - * until the self test duration expires. */ - if (rc == -ETIME) { - dev_info( - &chip->dev, HW_ERR - "TPM command timed out during continue self test"); - tpm_msleep(delay_msec); - continue; - } - - if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) { - dev_info(&chip->dev, - "TPM is disabled/deactivated (0x%X)\n", rc); - /* TPM is disabled and/or deactivated; driver can - * proceed and TPM does handle commands for - * suspend/resume correctly - */ - return 0; - } - if (rc != TPM_WARN_DOING_SELFTEST) - return rc; - tpm_msleep(delay_msec); - } while (--loops > 0); - - return rc; -} -EXPORT_SYMBOL_GPL(tpm_do_selftest); - -/** - * tpm1_auto_startup - Perform the standard automatic TPM initialization - * sequence - * @chip: TPM chip to use - * - * Returns 0 on success, < 0 in case of fatal error. - */ -int tpm1_auto_startup(struct tpm_chip *chip) -{ - int rc; - - rc = tpm_get_timeouts(chip); - if (rc) - goto out; - rc = tpm_do_selftest(chip); - if (rc) { - dev_err(&chip->dev, "TPM self test failed\n"); - goto out; - } - - return rc; -out: - if (rc > 0) - rc = -ENODEV; - return rc; -} - -/** * tpm_send - send a TPM command * @chip: a &struct tpm_chip instance, %NULL for the default chip * @cmd: a TPM command buffer @@ -1184,14 +541,20 @@ int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) } EXPORT_SYMBOL_GPL(tpm_send); -#define TPM_ORD_SAVESTATE 152 -#define SAVESTATE_RESULT_SIZE 10 +int tpm_auto_startup(struct tpm_chip *chip) +{ + int rc; -static const struct tpm_input_header savestate_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(10), - .ordinal = cpu_to_be32(TPM_ORD_SAVESTATE) -}; + if (!(chip->ops->flags & TPM_OPS_AUTO_STARTUP)) + return 0; + + if (chip->flags & TPM_CHIP_FLAG_TPM2) + rc = tpm2_auto_startup(chip); + else + rc = tpm1_auto_startup(chip); + + return rc; +} /* * We are about to suspend. Save the TPM state @@ -1200,54 +563,18 @@ static const struct tpm_input_header savestate_header = { int tpm_pm_suspend(struct device *dev) { struct tpm_chip *chip = dev_get_drvdata(dev); - struct tpm_cmd_t cmd; - int rc, try; + int rc = 0; - u8 dummy_hash[TPM_DIGEST_SIZE] = { 0 }; - - if (chip == NULL) + if (!chip) return -ENODEV; if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED) return 0; - if (chip->flags & TPM_CHIP_FLAG_TPM2) { + if (chip->flags & TPM_CHIP_FLAG_TPM2) tpm2_shutdown(chip, TPM2_SU_STATE); - return 0; - } - - /* for buggy tpm, flush pcrs with extend to selected dummy */ - if (tpm_suspend_pcr) - rc = tpm1_pcr_extend(chip, tpm_suspend_pcr, dummy_hash, - "extending dummy pcr before suspend"); - - /* now do the actual savestate */ - for (try = 0; try < TPM_RETRY; try++) { - cmd.header.in = savestate_header; - rc = tpm_transmit_cmd(chip, NULL, &cmd, SAVESTATE_RESULT_SIZE, - 0, 0, NULL); - - /* - * If the TPM indicates that it is too busy to respond to - * this command then retry before giving up. It can take - * several seconds for this TPM to be ready. - * - * This can happen if the TPM has already been sent the - * SaveState command before the driver has loaded. TCG 1.2 - * specification states that any communication after SaveState - * may cause the TPM to invalidate previously saved state. - */ - if (rc != TPM_WARN_RETRY) - break; - tpm_msleep(TPM_TIMEOUT_RETRY); - } - - if (rc) - dev_err(&chip->dev, - "Error (%d) sending savestate before suspend\n", rc); - else if (try > 0) - dev_warn(&chip->dev, "TPM savestate took %dms\n", - try * TPM_TIMEOUT_RETRY); + else + rc = tpm1_pm_suspend(chip, tpm_suspend_pcr); return rc; } @@ -1268,75 +595,32 @@ int tpm_pm_resume(struct device *dev) } EXPORT_SYMBOL_GPL(tpm_pm_resume); -#define TPM_GETRANDOM_RESULT_SIZE 18 -static const struct tpm_input_header tpm_getrandom_header = { - .tag = cpu_to_be16(TPM_TAG_RQU_COMMAND), - .length = cpu_to_be32(14), - .ordinal = cpu_to_be32(TPM_ORD_GET_RANDOM) -}; - /** * tpm_get_random() - get random bytes from the TPM's RNG * @chip: a &struct tpm_chip instance, %NULL for the default chip * @out: destination buffer for the random bytes * @max: the max number of bytes to write to @out * - * Return: same as with tpm_transmit_cmd() + * Return: number of random bytes read or a negative error value. */ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max) { - struct tpm_cmd_t tpm_cmd; - u32 recd, num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA), rlength; - int err, total = 0, retries = 5; - u8 *dest = out; + int rc; - if (!out || !num_bytes || max > TPM_MAX_RNG_DATA) + if (!out || max > TPM_MAX_RNG_DATA) return -EINVAL; chip = tpm_find_get_ops(chip); if (!chip) return -ENODEV; - if (chip->flags & TPM_CHIP_FLAG_TPM2) { - err = tpm2_get_random(chip, out, max); - tpm_put_ops(chip); - return err; - } - - do { - tpm_cmd.header.in = tpm_getrandom_header; - tpm_cmd.params.getrandom_in.num_bytes = cpu_to_be32(num_bytes); - - err = tpm_transmit_cmd(chip, NULL, &tpm_cmd, - TPM_GETRANDOM_RESULT_SIZE + num_bytes, - offsetof(struct tpm_getrandom_out, - rng_data), - 0, "attempting get random"); - if (err) - break; - - recd = be32_to_cpu(tpm_cmd.params.getrandom_out.rng_data_len); - if (recd > num_bytes) { - total = -EFAULT; - break; - } - - rlength = be32_to_cpu(tpm_cmd.header.out.length); - if (rlength < TPM_HEADER_SIZE + - offsetof(struct tpm_getrandom_out, rng_data) + - recd) { - total = -EFAULT; - break; - } - memcpy(dest, tpm_cmd.params.getrandom_out.rng_data, recd); - - dest += recd; - total += recd; - num_bytes -= recd; - } while (retries-- && total < max); + if (chip->flags & TPM_CHIP_FLAG_TPM2) + rc = tpm2_get_random(chip, out, max); + else + rc = tpm1_get_random(chip, out, max); tpm_put_ops(chip); - return total ? total : -EIO; + return rc; } EXPORT_SYMBOL_GPL(tpm_get_random); diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index 83a77a445538..b88e08ec2c59 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -102,19 +102,19 @@ static ssize_t pcrs_show(struct device *dev, struct device_attribute *attr, cap_t cap; u8 digest[TPM_DIGEST_SIZE]; ssize_t rc; - int i, j, num_pcrs; + u32 i, j, num_pcrs; char *str = buf; struct tpm_chip *chip = to_tpm_chip(dev); - rc = tpm_getcap(chip, TPM_CAP_PROP_PCR, &cap, - "attempting to determine the number of PCRS", - sizeof(cap.num_pcrs)); + rc = tpm1_getcap(chip, TPM_CAP_PROP_PCR, &cap, + "attempting to determine the number of PCRS", + sizeof(cap.num_pcrs)); if (rc) return 0; num_pcrs = be32_to_cpu(cap.num_pcrs); for (i = 0; i < num_pcrs; i++) { - rc = tpm_pcr_read_dev(chip, i, digest); + rc = tpm1_pcr_read(chip, i, digest); if (rc) break; str += sprintf(str, "PCR-%02d: ", i); @@ -132,9 +132,9 @@ static ssize_t enabled_show(struct device *dev, struct device_attribute *attr, cap_t cap; ssize_t rc; - rc = tpm_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_PERM, &cap, - "attempting to determine the permanent enabled state", - sizeof(cap.perm_flags)); + rc = tpm1_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_PERM, &cap, + "attempting to determine the permanent enabled state", + sizeof(cap.perm_flags)); if (rc) return 0; @@ -149,9 +149,9 @@ static ssize_t active_show(struct device *dev, struct device_attribute *attr, cap_t cap; ssize_t rc; - rc = tpm_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_PERM, &cap, - "attempting to determine the permanent active state", - sizeof(cap.perm_flags)); + rc = tpm1_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_PERM, &cap, + "attempting to determine the permanent active state", + sizeof(cap.perm_flags)); if (rc) return 0; @@ -166,9 +166,9 @@ static ssize_t owned_show(struct device *dev, struct device_attribute *attr, cap_t cap; ssize_t rc; - rc = tpm_getcap(to_tpm_chip(dev), TPM_CAP_PROP_OWNER, &cap, - "attempting to determine the owner state", - sizeof(cap.owned)); + rc = tpm1_getcap(to_tpm_chip(dev), TPM_CAP_PROP_OWNER, &cap, + "attempting to determine the owner state", + sizeof(cap.owned)); if (rc) return 0; @@ -183,9 +183,9 @@ static ssize_t temp_deactivated_show(struct device *dev, cap_t cap; ssize_t rc; - rc = tpm_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_VOL, &cap, - "attempting to determine the temporary state", - sizeof(cap.stclear_flags)); + rc = tpm1_getcap(to_tpm_chip(dev), TPM_CAP_FLAG_VOL, &cap, + "attempting to determine the temporary state", + sizeof(cap.stclear_flags)); if (rc) return 0; @@ -202,18 +202,18 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, ssize_t rc; char *str = buf; - rc = tpm_getcap(chip, TPM_CAP_PROP_MANUFACTURER, &cap, - "attempting to determine the manufacturer", - sizeof(cap.manufacturer_id)); + rc = tpm1_getcap(chip, TPM_CAP_PROP_MANUFACTURER, &cap, + "attempting to determine the manufacturer", + sizeof(cap.manufacturer_id)); if (rc) return 0; str += sprintf(str, "Manufacturer: 0x%x\n", be32_to_cpu(cap.manufacturer_id)); /* Try to get a TPM version 1.2 TPM_CAP_VERSION_INFO */ - rc = tpm_getcap(chip, TPM_CAP_VERSION_1_2, &cap, - "attempting to determine the 1.2 version", - sizeof(cap.tpm_version_1_2)); + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_2, &cap, + "attempting to determine the 1.2 version", + sizeof(cap.tpm_version_1_2)); if (!rc) { str += sprintf(str, "TCG version: %d.%d\nFirmware version: %d.%d\n", @@ -223,9 +223,9 @@ static ssize_t caps_show(struct device *dev, struct device_attribute *attr, cap.tpm_version_1_2.revMinor); } else { /* Otherwise just use TPM_STRUCT_VER */ - rc = tpm_getcap(chip, TPM_CAP_VERSION_1_1, &cap, - "attempting to determine the 1.1 version", - sizeof(cap.tpm_version)); + rc = tpm1_getcap(chip, TPM_CAP_VERSION_1_1, &cap, + "attempting to determine the 1.1 version", + sizeof(cap.tpm_version)); if (rc) return 0; str += sprintf(str, diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index f20dc8ece348..f27d1f38a93d 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -134,22 +134,31 @@ enum tpm2_algorithms { }; enum tpm2_command_codes { - TPM2_CC_FIRST = 0x011F, - TPM2_CC_CREATE_PRIMARY = 0x0131, - TPM2_CC_SELF_TEST = 0x0143, - TPM2_CC_STARTUP = 0x0144, - TPM2_CC_SHUTDOWN = 0x0145, - TPM2_CC_CREATE = 0x0153, - TPM2_CC_LOAD = 0x0157, - TPM2_CC_UNSEAL = 0x015E, - TPM2_CC_CONTEXT_LOAD = 0x0161, - TPM2_CC_CONTEXT_SAVE = 0x0162, - TPM2_CC_FLUSH_CONTEXT = 0x0165, - TPM2_CC_GET_CAPABILITY = 0x017A, - TPM2_CC_GET_RANDOM = 0x017B, - TPM2_CC_PCR_READ = 0x017E, - TPM2_CC_PCR_EXTEND = 0x0182, - TPM2_CC_LAST = 0x018F, + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ }; enum tpm2_permanent_handles { @@ -368,18 +377,6 @@ enum tpm_sub_capabilities { TPM_CAP_PROP_TIS_DURATION = 0x120, }; -typedef union { - struct tpm_input_header in; - struct tpm_output_header out; -} tpm_cmd_header; - -struct tpm_pcrread_out { - u8 pcr_result[TPM_DIGEST_SIZE]; -} __packed; - -struct tpm_pcrread_in { - __be32 pcr_idx; -} __packed; /* 128 bytes is an arbitrary cap. This could be as large as TPM_BUFSIZE - 18 * bytes, but 128 is still a relatively large number of random bytes and @@ -387,28 +384,6 @@ struct tpm_pcrread_in { * compiler warnings about stack frame size. */ #define TPM_MAX_RNG_DATA 128 -struct tpm_getrandom_out { - __be32 rng_data_len; - u8 rng_data[TPM_MAX_RNG_DATA]; -} __packed; - -struct tpm_getrandom_in { - __be32 num_bytes; -} __packed; - -typedef union { - struct tpm_pcrread_in pcrread_in; - struct tpm_pcrread_out pcrread_out; - struct tpm_getrandom_in getrandom_in; - struct tpm_getrandom_out getrandom_out; -} tpm_cmd_params; - -struct tpm_cmd_t { - tpm_cmd_header header; - tpm_cmd_params params; -} __packed; - - /* A string buffer type for constructing TPM commands. This is based on the * ideas of string buffer code in security/keys/trusted.h but is heap based * in order to keep the stack usage minimal. @@ -531,12 +506,20 @@ ssize_t tpm_transmit_cmd(struct tpm_chip *chip, struct tpm_space *space, void *buf, size_t bufsiz, size_t min_rsp_body_length, unsigned int flags, const char *desc); -int tpm_startup(struct tpm_chip *chip); -ssize_t tpm_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, - const char *desc, size_t min_cap_length); int tpm_get_timeouts(struct tpm_chip *); +int tpm_auto_startup(struct tpm_chip *chip); + +int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr); int tpm1_auto_startup(struct tpm_chip *chip); -int tpm_do_selftest(struct tpm_chip *chip); +int tpm1_do_selftest(struct tpm_chip *chip); +int tpm1_get_timeouts(struct tpm_chip *chip); +unsigned long tpm1_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); +int tpm1_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash, + const char *log_msg); +int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); +ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, + const char *desc, size_t min_cap_length); +int tpm1_get_random(struct tpm_chip *chip, u8 *out, size_t max); unsigned long tpm_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal); int tpm_pm_suspend(struct device *dev); int tpm_pm_resume(struct device *dev); @@ -560,7 +543,6 @@ void tpm_chip_unregister(struct tpm_chip *chip); void tpm_sysfs_add_device(struct tpm_chip *chip); -int tpm_pcr_read_dev(struct tpm_chip *chip, int pcr_idx, u8 *res_buf); #ifdef CONFIG_ACPI extern void tpm_add_ppi(struct tpm_chip *chip); @@ -575,8 +557,9 @@ static inline u32 tpm2_rc_value(u32 rc) return (rc & BIT(7)) ? rc & 0xff : rc; } -int tpm2_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf); -int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count, +int tpm2_get_timeouts(struct tpm_chip *chip); +int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); +int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, u32 count, struct tpm2_digest *digests); int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max); void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle, diff --git a/drivers/char/tpm/tpm1-cmd.c b/drivers/char/tpm/tpm1-cmd.c new file mode 100644 index 000000000000..6f306338953b --- /dev/null +++ b/drivers/char/tpm/tpm1-cmd.c @@ -0,0 +1,781 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2004 IBM Corporation + * Copyright (C) 2014 Intel Corporation + * + * Authors: + * Leendert van Doorn <leendert@watson.ibm.com> + * Dave Safford <safford@watson.ibm.com> + * Reiner Sailer <sailer@watson.ibm.com> + * Kylene Hall <kjhall@us.ibm.com> + * + * Device driver for TCG/TCPA TPM (trusted platform module). + * Specifications at www.trustedcomputinggroup.org + */ + +#include <linux/poll.h> +#include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/spinlock.h> +#include <linux/freezer.h> +#include <linux/tpm_eventlog.h> + +#include "tpm.h" + +#define TPM_MAX_ORDINAL 243 + +/* + * Array with one entry per ordinal defining the maximum amount + * of time the chip could take to return the result. The ordinal + * designation of short, medium or long is defined in a table in + * TCG Specification TPM Main Part 2 TPM Structures Section 17. The + * values of the SHORT, MEDIUM, and LONG durations are retrieved + * from the chip during initialization with a call to tpm_get_timeouts. + */ +static const u8 tpm1_ordinal_duration[TPM_MAX_ORDINAL] = { + TPM_UNDEFINED, /* 0 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 5 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 10 */ + TPM_SHORT, + TPM_MEDIUM, + TPM_LONG, + TPM_LONG, + TPM_MEDIUM, /* 15 */ + TPM_SHORT, + TPM_SHORT, + TPM_MEDIUM, + TPM_LONG, + TPM_SHORT, /* 20 */ + TPM_SHORT, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_SHORT, /* 25 */ + TPM_SHORT, + TPM_MEDIUM, + TPM_SHORT, + TPM_SHORT, + TPM_MEDIUM, /* 30 */ + TPM_LONG, + TPM_MEDIUM, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, /* 35 */ + TPM_MEDIUM, + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_MEDIUM, /* 40 */ + TPM_LONG, + TPM_MEDIUM, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, /* 45 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_LONG, + TPM_MEDIUM, /* 50 */ + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 55 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_MEDIUM, /* 60 */ + TPM_MEDIUM, + TPM_MEDIUM, + TPM_SHORT, + TPM_SHORT, + TPM_MEDIUM, /* 65 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 70 */ + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 75 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_LONG, /* 80 */ + TPM_UNDEFINED, + TPM_MEDIUM, + TPM_LONG, + TPM_SHORT, + TPM_UNDEFINED, /* 85 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 90 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, /* 95 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_MEDIUM, /* 100 */ + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 105 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 110 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, /* 115 */ + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_LONG, /* 120 */ + TPM_LONG, + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_SHORT, + TPM_SHORT, /* 125 */ + TPM_SHORT, + TPM_LONG, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, /* 130 */ + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_SHORT, + TPM_MEDIUM, + TPM_UNDEFINED, /* 135 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 140 */ + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 145 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 150 */ + TPM_MEDIUM, + TPM_MEDIUM, + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, /* 155 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 160 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 165 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_LONG, /* 170 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 175 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_MEDIUM, /* 180 */ + TPM_SHORT, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_MEDIUM, /* 185 */ + TPM_SHORT, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 190 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 195 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 200 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, + TPM_SHORT, /* 205 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_MEDIUM, /* 210 */ + TPM_UNDEFINED, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_MEDIUM, + TPM_UNDEFINED, /* 215 */ + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, + TPM_SHORT, /* 220 */ + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_SHORT, + TPM_UNDEFINED, /* 225 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 230 */ + TPM_LONG, + TPM_MEDIUM, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, /* 235 */ + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_UNDEFINED, + TPM_SHORT, /* 240 */ + TPM_UNDEFINED, + TPM_MEDIUM, +}; + +/** + * tpm1_calc_ordinal_duration() - calculate the maximum command duration + * @chip: TPM chip to use. + * @ordinal: TPM command ordinal. + * + * The function returns the maximum amount of time the chip could take + * to return the result for a particular ordinal in jiffies. + * + * Return: A maximal duration time for an ordinal in jiffies. + */ +unsigned long tpm1_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) +{ + int duration_idx = TPM_UNDEFINED; + int duration = 0; + + /* + * We only have a duration table for protected commands, where the upper + * 16 bits are 0. For the few other ordinals the fallback will be used. + */ + if (ordinal < TPM_MAX_ORDINAL) + duration_idx = tpm1_ordinal_duration[ordinal]; + + if (duration_idx != TPM_UNDEFINED) + duration = chip->duration[duration_idx]; + if (duration <= 0) + return 2 * 60 * HZ; + else + return duration; +} + +#define TPM_ORD_STARTUP 153 +#define TPM_ST_CLEAR 1 + +/** + * tpm_startup() - turn on the TPM + * @chip: TPM chip to use + * + * Normally the firmware should start the TPM. This function is provided as a + * workaround if this does not happen. A legal case for this could be for + * example when a TPM emulator is used. + * + * Return: same as tpm_transmit_cmd() + */ +static int tpm1_startup(struct tpm_chip *chip) +{ + struct tpm_buf buf; + int rc; + + dev_info(&chip->dev, "starting up the TPM manually\n"); + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_STARTUP); + if (rc < 0) + return rc; + + tpm_buf_append_u16(&buf, TPM_ST_CLEAR); + + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, + "attempting to start the TPM"); + + tpm_buf_destroy(&buf); + + return rc; +} + +int tpm1_get_timeouts(struct tpm_chip *chip) +{ + cap_t cap; + unsigned long timeout_old[4], timeout_chip[4], timeout_eff[4]; + ssize_t rc; + + rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, NULL, + sizeof(cap.timeout)); + if (rc == TPM_ERR_INVALID_POSTINIT) { + if (tpm1_startup(chip)) + return rc; + + rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, + "attempting to determine the timeouts", + sizeof(cap.timeout)); + } + + if (rc) { + dev_err(&chip->dev, "A TPM error (%zd) occurred attempting to determine the timeouts\n", + rc); + return rc; + } + + timeout_old[0] = jiffies_to_usecs(chip->timeout_a); + timeout_old[1] = jiffies_to_usecs(chip->timeout_b); + timeout_old[2] = jiffies_to_usecs(chip->timeout_c); + timeout_old[3] = jiffies_to_usecs(chip->timeout_d); + timeout_chip[0] = be32_to_cpu(cap.timeout.a); + timeout_chip[1] = be32_to_cpu(cap.timeout.b); + timeout_chip[2] = be32_to_cpu(cap.timeout.c); + timeout_chip[3] = be32_to_cpu(cap.timeout.d); + memcpy(timeout_eff, timeout_chip, sizeof(timeout_eff)); + + /* + * Provide ability for vendor overrides of timeout values in case + * of misreporting. + */ + if (chip->ops->update_timeouts) + chip->timeout_adjusted = + chip->ops->update_timeouts(chip, timeout_eff); + + if (!chip->timeout_adjusted) { + /* Restore default if chip reported 0 */ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(timeout_eff); i++) { + if (timeout_eff[i]) + continue; + + timeout_eff[i] = timeout_old[i]; + chip->timeout_adjusted = true; + } + + if (timeout_eff[0] != 0 && timeout_eff[0] < 1000) { + /* timeouts in msec rather usec */ + for (i = 0; i != ARRAY_SIZE(timeout_eff); i++) + timeout_eff[i] *= 1000; + chip->timeout_adjusted = true; + } + } + + /* Report adjusted timeouts */ + if (chip->timeout_adjusted) { + dev_info(&chip->dev, HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n", + timeout_chip[0], timeout_eff[0], + timeout_chip[1], timeout_eff[1], + timeout_chip[2], timeout_eff[2], + timeout_chip[3], timeout_eff[3]); + } + + chip->timeout_a = usecs_to_jiffies(timeout_eff[0]); + chip->timeout_b = usecs_to_jiffies(timeout_eff[1]); + chip->timeout_c = usecs_to_jiffies(timeout_eff[2]); + chip->timeout_d = usecs_to_jiffies(timeout_eff[3]); + + rc = tpm1_getcap(chip, TPM_CAP_PROP_TIS_DURATION, &cap, + "attempting to determine the durations", + sizeof(cap.duration)); + if (rc) + return rc; + + chip->duration[TPM_SHORT] = + usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_short)); + chip->duration[TPM_MEDIUM] = + usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_medium)); + chip->duration[TPM_LONG] = + usecs_to_jiffies(be32_to_cpu(cap.duration.tpm_long)); + chip->duration[TPM_LONG_LONG] = 0; /* not used under 1.2 */ + + /* The Broadcom BCM0102 chipset in a Dell Latitude D820 gets the above + * value wrong and apparently reports msecs rather than usecs. So we + * fix up the resulting too-small TPM_SHORT value to make things work. + * We also scale the TPM_MEDIUM and -_LONG values by 1000. + */ + if (chip->duration[TPM_SHORT] < (HZ / 100)) { + chip->duration[TPM_SHORT] = HZ; + chip->duration[TPM_MEDIUM] *= 1000; + chip->duration[TPM_LONG] *= 1000; + chip->duration_adjusted = true; + dev_info(&chip->dev, "Adjusting TPM timeout parameters."); + } + + chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS; + return 0; +} + +#define TPM_ORD_PCR_EXTEND 20 +int tpm1_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash, + const char *log_msg) +{ + struct tpm_buf buf; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCR_EXTEND); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, pcr_idx); + tpm_buf_append(&buf, hash, TPM_DIGEST_SIZE); + + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + TPM_DIGEST_SIZE, 0, log_msg); + + tpm_buf_destroy(&buf); + return rc; +} + +#define TPM_ORD_GET_CAP 101 +ssize_t tpm1_getcap(struct tpm_chip *chip, u32 subcap_id, cap_t *cap, + const char *desc, size_t min_cap_length) +{ + struct tpm_buf buf; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_CAP); + if (rc) + return rc; + + if (subcap_id == TPM_CAP_VERSION_1_1 || + subcap_id == TPM_CAP_VERSION_1_2) { + tpm_buf_append_u32(&buf, subcap_id); + tpm_buf_append_u32(&buf, 0); + } else { + if (subcap_id == TPM_CAP_FLAG_PERM || + subcap_id == TPM_CAP_FLAG_VOL) + tpm_buf_append_u32(&buf, TPM_CAP_FLAG); + else + tpm_buf_append_u32(&buf, TPM_CAP_PROP); + + tpm_buf_append_u32(&buf, 4); + tpm_buf_append_u32(&buf, subcap_id); + } + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + min_cap_length, 0, desc); + if (!rc) + *cap = *(cap_t *)&buf.data[TPM_HEADER_SIZE + 4]; + + tpm_buf_destroy(&buf); + return rc; +} +EXPORT_SYMBOL_GPL(tpm1_getcap); + +#define TPM_ORD_GET_RANDOM 70 +struct tpm1_get_random_out { + __be32 rng_data_len; + u8 rng_data[TPM_MAX_RNG_DATA]; +} __packed; + +/** + * tpm1_get_random() - get random bytes from the TPM's RNG + * @chip: a &struct tpm_chip instance + * @dest: destination buffer for the random bytes + * @max: the maximum number of bytes to write to @dest + * + * Return: + * * number of bytes read + * * -errno or a TPM return code otherwise + */ +int tpm1_get_random(struct tpm_chip *chip, u8 *dest, size_t max) +{ + struct tpm1_get_random_out *out; + u32 num_bytes = min_t(u32, max, TPM_MAX_RNG_DATA); + struct tpm_buf buf; + u32 total = 0; + int retries = 5; + u32 recd; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); + if (rc) + return rc; + + do { + tpm_buf_append_u32(&buf, num_bytes); + + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + sizeof(out->rng_data_len), 0, + "attempting get random"); + if (rc) + goto out; + + out = (struct tpm1_get_random_out *)&buf.data[TPM_HEADER_SIZE]; + + recd = be32_to_cpu(out->rng_data_len); + if (recd > num_bytes) { + rc = -EFAULT; + goto out; + } + + if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + + sizeof(out->rng_data_len) + recd) { + rc = -EFAULT; + goto out; + } + memcpy(dest, out->rng_data, recd); + + dest += recd; + total += recd; + num_bytes -= recd; + + tpm_buf_reset(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_GET_RANDOM); + } while (retries-- && total < max); + + rc = total ? (int)total : -EIO; +out: + tpm_buf_destroy(&buf); + return rc; +} + +#define TPM_ORD_PCRREAD 21 +int tpm1_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) +{ + struct tpm_buf buf; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_PCRREAD); + if (rc) + return rc; + + tpm_buf_append_u32(&buf, pcr_idx); + + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + TPM_DIGEST_SIZE, 0, + "attempting to read a pcr value"); + if (rc) + goto out; + + if (tpm_buf_length(&buf) < TPM_DIGEST_SIZE) { + rc = -EFAULT; + goto out; + } + + memcpy(res_buf, &buf.data[TPM_HEADER_SIZE], TPM_DIGEST_SIZE); + +out: + tpm_buf_destroy(&buf); + return rc; +} + +#define TPM_ORD_CONTINUE_SELFTEST 83 +/** + * tpm_continue_selftest() - run TPM's selftest + * @chip: TPM chip to use + * + * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing + * a TPM error code. + */ +static int tpm1_continue_selftest(struct tpm_chip *chip) +{ + struct tpm_buf buf; + int rc; + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_CONTINUE_SELFTEST); + if (rc) + return rc; + + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + 0, 0, "continue selftest"); + + tpm_buf_destroy(&buf); + + return rc; +} + +/** + * tpm1_do_selftest - have the TPM continue its selftest and wait until it + * can receive further commands + * @chip: TPM chip to use + * + * Returns 0 on success, < 0 in case of fatal error or a value > 0 representing + * a TPM error code. + */ +int tpm1_do_selftest(struct tpm_chip *chip) +{ + int rc; + unsigned int loops; + unsigned int delay_msec = 100; + unsigned long duration; + u8 dummy[TPM_DIGEST_SIZE]; + + duration = tpm1_calc_ordinal_duration(chip, TPM_ORD_CONTINUE_SELFTEST); + + loops = jiffies_to_msecs(duration) / delay_msec; + + rc = tpm1_continue_selftest(chip); + if (rc == TPM_ERR_INVALID_POSTINIT) { + chip->flags |= TPM_CHIP_FLAG_ALWAYS_POWERED; + dev_info(&chip->dev, "TPM not ready (%d)\n", rc); + } + /* This may fail if there was no TPM driver during a suspend/resume + * cycle; some may return 10 (BAD_ORDINAL), others 28 (FAILEDSELFTEST) + */ + if (rc) + return rc; + + do { + /* Attempt to read a PCR value */ + rc = tpm1_pcr_read(chip, 0, dummy); + + /* Some buggy TPMs will not respond to tpm_tis_ready() for + * around 300ms while the self test is ongoing, keep trying + * until the self test duration expires. + */ + if (rc == -ETIME) { + dev_info(&chip->dev, HW_ERR "TPM command timed out during continue self test"); + tpm_msleep(delay_msec); + continue; + } + + if (rc == TPM_ERR_DISABLED || rc == TPM_ERR_DEACTIVATED) { + dev_info(&chip->dev, "TPM is disabled/deactivated (0x%X)\n", + rc); + /* TPM is disabled and/or deactivated; driver can + * proceed and TPM does handle commands for + * suspend/resume correctly + */ + return 0; + } + if (rc != TPM_WARN_DOING_SELFTEST) + return rc; + tpm_msleep(delay_msec); + } while (--loops > 0); + + return rc; +} +EXPORT_SYMBOL_GPL(tpm1_do_selftest); + +/** + * tpm1_auto_startup - Perform the standard automatic TPM initialization + * sequence + * @chip: TPM chip to use + * + * Returns 0 on success, < 0 in case of fatal error. + */ +int tpm1_auto_startup(struct tpm_chip *chip) +{ + int rc; + + rc = tpm1_get_timeouts(chip); + if (rc) + goto out; + rc = tpm1_do_selftest(chip); + if (rc) { + dev_err(&chip->dev, "TPM self test failed\n"); + goto out; + } + + return rc; +out: + if (rc > 0) + rc = -ENODEV; + return rc; +} + +#define TPM_ORD_SAVESTATE 152 + +/** + * tpm1_pm_suspend() - pm suspend handler + * @chip: TPM chip to use. + * @tpm_suspend_pcr: flush pcr for buggy TPM chips. + * + * The functions saves the TPM state to be restored on resume. + * + * Return: + * * 0 on success, + * * < 0 on error. + */ +int tpm1_pm_suspend(struct tpm_chip *chip, u32 tpm_suspend_pcr) +{ + u8 dummy_hash[TPM_DIGEST_SIZE] = { 0 }; + struct tpm_buf buf; + unsigned int try; + int rc; + + + /* for buggy tpm, flush pcrs with extend to selected dummy */ + if (tpm_suspend_pcr) + rc = tpm1_pcr_extend(chip, tpm_suspend_pcr, dummy_hash, + "extending dummy pcr before suspend"); + + rc = tpm_buf_init(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); + if (rc) + return rc; + /* now do the actual savestate */ + for (try = 0; try < TPM_RETRY; try++) { + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, + 0, 0, NULL); + + /* + * If the TPM indicates that it is too busy to respond to + * this command then retry before giving up. It can take + * several seconds for this TPM to be ready. + * + * This can happen if the TPM has already been sent the + * SaveState command before the driver has loaded. TCG 1.2 + * specification states that any communication after SaveState + * may cause the TPM to invalidate previously saved state. + */ + if (rc != TPM_WARN_RETRY) + break; + tpm_msleep(TPM_TIMEOUT_RETRY); + + tpm_buf_reset(&buf, TPM_TAG_RQU_COMMAND, TPM_ORD_SAVESTATE); + } + + if (rc) + dev_err(&chip->dev, "Error (%d) sending savestate before suspend\n", + rc); + else if (try > 0) + dev_warn(&chip->dev, "TPM savestate took %dms\n", + try * TPM_TIMEOUT_RETRY); + + tpm_buf_destroy(&buf); + + return rc; +} + diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 3acf4fd4e5a5..a6bec13afa69 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -40,129 +40,121 @@ static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SM3_256, TPM2_ALG_SM3_256}, }; -/* - * Array with one entry per ordinal defining the maximum amount - * of time the chip could take to return the result. The values - * of the SHORT, MEDIUM, and LONG durations are taken from the - * PC Client Profile (PTP) specification. - * LONG_LONG is for commands that generates keys which empirically - * takes longer time on some systems. +int tpm2_get_timeouts(struct tpm_chip *chip) +{ + /* Fixed timeouts for TPM2 */ + chip->timeout_a = msecs_to_jiffies(TPM2_TIMEOUT_A); + chip->timeout_b = msecs_to_jiffies(TPM2_TIMEOUT_B); + chip->timeout_c = msecs_to_jiffies(TPM2_TIMEOUT_C); + chip->timeout_d = msecs_to_jiffies(TPM2_TIMEOUT_D); + + /* PTP spec timeouts */ + chip->duration[TPM_SHORT] = msecs_to_jiffies(TPM2_DURATION_SHORT); + chip->duration[TPM_MEDIUM] = msecs_to_jiffies(TPM2_DURATION_MEDIUM); + chip->duration[TPM_LONG] = msecs_to_jiffies(TPM2_DURATION_LONG); + + /* Key creation commands long timeouts */ + chip->duration[TPM_LONG_LONG] = + msecs_to_jiffies(TPM2_DURATION_LONG_LONG); + + chip->flags |= TPM_CHIP_FLAG_HAVE_TIMEOUTS; + + return 0; +} + +/** + * tpm2_ordinal_duration_index() - returns an index to the chip duration table + * @ordinal: TPM command ordinal. + * + * The function returns an index to the chip duration table + * (enum tpm_duration), that describes the maximum amount of + * time the chip could take to return the result for a particular ordinal. + * + * The values of the MEDIUM, and LONG durations are taken + * from the PC Client Profile (PTP) specification (750, 2000 msec) + * + * LONG_LONG is for commands that generates keys which empirically takes + * a longer time on some systems. + * + * Return: + * * TPM_MEDIUM + * * TPM_LONG + * * TPM_LONG_LONG + * * TPM_UNDEFINED */ -static const u8 tpm2_ordinal_duration[TPM2_CC_LAST - TPM2_CC_FIRST + 1] = { - TPM_UNDEFINED, /* 11F */ - TPM_UNDEFINED, /* 120 */ - TPM_LONG, /* 121 */ - TPM_UNDEFINED, /* 122 */ - TPM_UNDEFINED, /* 123 */ - TPM_UNDEFINED, /* 124 */ - TPM_UNDEFINED, /* 125 */ - TPM_UNDEFINED, /* 126 */ - TPM_UNDEFINED, /* 127 */ - TPM_UNDEFINED, /* 128 */ - TPM_LONG, /* 129 */ - TPM_UNDEFINED, /* 12a */ - TPM_UNDEFINED, /* 12b */ - TPM_UNDEFINED, /* 12c */ - TPM_UNDEFINED, /* 12d */ - TPM_UNDEFINED, /* 12e */ - TPM_UNDEFINED, /* 12f */ - TPM_UNDEFINED, /* 130 */ - TPM_LONG_LONG, /* 131 */ - TPM_UNDEFINED, /* 132 */ - TPM_UNDEFINED, /* 133 */ - TPM_UNDEFINED, /* 134 */ - TPM_UNDEFINED, /* 135 */ - TPM_UNDEFINED, /* 136 */ - TPM_UNDEFINED, /* 137 */ - TPM_UNDEFINED, /* 138 */ - TPM_UNDEFINED, /* 139 */ - TPM_UNDEFINED, /* 13a */ - TPM_UNDEFINED, /* 13b */ - TPM_UNDEFINED, /* 13c */ - TPM_UNDEFINED, /* 13d */ - TPM_MEDIUM, /* 13e */ - TPM_UNDEFINED, /* 13f */ - TPM_UNDEFINED, /* 140 */ - TPM_UNDEFINED, /* 141 */ - TPM_UNDEFINED, /* 142 */ - TPM_LONG, /* 143 */ - TPM_MEDIUM, /* 144 */ - TPM_UNDEFINED, /* 145 */ - TPM_UNDEFINED, /* 146 */ - TPM_UNDEFINED, /* 147 */ - TPM_UNDEFINED, /* 148 */ - TPM_UNDEFINED, /* 149 */ - TPM_UNDEFINED, /* 14a */ - TPM_UNDEFINED, /* 14b */ - TPM_UNDEFINED, /* 14c */ - TPM_UNDEFINED, /* 14d */ - TPM_LONG, /* 14e */ - TPM_UNDEFINED, /* 14f */ - TPM_UNDEFINED, /* 150 */ - TPM_UNDEFINED, /* 151 */ - TPM_UNDEFINED, /* 152 */ - TPM_LONG_LONG, /* 153 */ - TPM_UNDEFINED, /* 154 */ - TPM_UNDEFINED, /* 155 */ - TPM_UNDEFINED, /* 156 */ - TPM_UNDEFINED, /* 157 */ - TPM_UNDEFINED, /* 158 */ - TPM_UNDEFINED, /* 159 */ - TPM_UNDEFINED, /* 15a */ - TPM_UNDEFINED, /* 15b */ - TPM_MEDIUM, /* 15c */ - TPM_UNDEFINED, /* 15d */ - TPM_UNDEFINED, /* 15e */ - TPM_UNDEFINED, /* 15f */ - TPM_UNDEFINED, /* 160 */ - TPM_UNDEFINED, /* 161 */ - TPM_UNDEFINED, /* 162 */ - TPM_UNDEFINED, /* 163 */ - TPM_UNDEFINED, /* 164 */ - TPM_UNDEFINED, /* 165 */ - TPM_UNDEFINED, /* 166 */ - TPM_UNDEFINED, /* 167 */ - TPM_UNDEFINED, /* 168 */ - TPM_UNDEFINED, /* 169 */ - TPM_UNDEFINED, /* 16a */ - TPM_UNDEFINED, /* 16b */ - TPM_UNDEFINED, /* 16c */ - TPM_UNDEFINED, /* 16d */ - TPM_UNDEFINED, /* 16e */ - TPM_UNDEFINED, /* 16f */ - TPM_UNDEFINED, /* 170 */ - TPM_UNDEFINED, /* 171 */ - TPM_UNDEFINED, /* 172 */ - TPM_UNDEFINED, /* 173 */ - TPM_UNDEFINED, /* 174 */ - TPM_UNDEFINED, /* 175 */ - TPM_UNDEFINED, /* 176 */ - TPM_LONG, /* 177 */ - TPM_UNDEFINED, /* 178 */ - TPM_UNDEFINED, /* 179 */ - TPM_MEDIUM, /* 17a */ - TPM_LONG, /* 17b */ - TPM_UNDEFINED, /* 17c */ - TPM_UNDEFINED, /* 17d */ - TPM_UNDEFINED, /* 17e */ - TPM_UNDEFINED, /* 17f */ - TPM_UNDEFINED, /* 180 */ - TPM_UNDEFINED, /* 181 */ - TPM_MEDIUM, /* 182 */ - TPM_UNDEFINED, /* 183 */ - TPM_UNDEFINED, /* 184 */ - TPM_MEDIUM, /* 185 */ - TPM_MEDIUM, /* 186 */ - TPM_UNDEFINED, /* 187 */ - TPM_UNDEFINED, /* 188 */ - TPM_UNDEFINED, /* 189 */ - TPM_UNDEFINED, /* 18a */ - TPM_UNDEFINED, /* 18b */ - TPM_UNDEFINED, /* 18c */ - TPM_UNDEFINED, /* 18d */ - TPM_UNDEFINED, /* 18e */ - TPM_UNDEFINED /* 18f */ -}; +static u8 tpm2_ordinal_duration_index(u32 ordinal) +{ + switch (ordinal) { + /* Startup */ + case TPM2_CC_STARTUP: /* 144 */ + return TPM_MEDIUM; + + case TPM2_CC_SELF_TEST: /* 143 */ + return TPM_LONG; + + case TPM2_CC_GET_RANDOM: /* 17B */ + return TPM_LONG; + + case TPM2_CC_SEQUENCE_UPDATE: /* 15C */ + return TPM_MEDIUM; + case TPM2_CC_SEQUENCE_COMPLETE: /* 13E */ + return TPM_MEDIUM; + case TPM2_CC_EVENT_SEQUENCE_COMPLETE: /* 185 */ + return TPM_MEDIUM; + case TPM2_CC_HASH_SEQUENCE_START: /* 186 */ + return TPM_MEDIUM; + + case TPM2_CC_VERIFY_SIGNATURE: /* 177 */ + return TPM_LONG; + + case TPM2_CC_PCR_EXTEND: /* 182 */ + return TPM_MEDIUM; + + case TPM2_CC_HIERARCHY_CONTROL: /* 121 */ + return TPM_LONG; + case TPM2_CC_HIERARCHY_CHANGE_AUTH: /* 129 */ + return TPM_LONG; + + case TPM2_CC_GET_CAPABILITY: /* 17A */ + return TPM_MEDIUM; + + case TPM2_CC_NV_READ: /* 14E */ + return TPM_LONG; + + case TPM2_CC_CREATE_PRIMARY: /* 131 */ + return TPM_LONG_LONG; + case TPM2_CC_CREATE: /* 153 */ + return TPM_LONG_LONG; + case TPM2_CC_CREATE_LOADED: /* 191 */ + return TPM_LONG_LONG; + + default: + return TPM_UNDEFINED; + } +} + +/** + * tpm2_calc_ordinal_duration() - calculate the maximum command duration + * @chip: TPM chip to use. + * @ordinal: TPM command ordinal. + * + * The function returns the maximum amount of time the chip could take + * to return the result for a particular ordinal in jiffies. + * + * Return: A maximal duration time for an ordinal in jiffies. + */ +unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) +{ + unsigned int index; + + index = tpm2_ordinal_duration_index(ordinal); + + if (index != TPM_UNDEFINED) + return chip->duration[index]; + else + return msecs_to_jiffies(TPM2_DURATION_DEFAULT); +} + struct tpm2_pcr_read_out { __be32 update_cnt; @@ -183,7 +175,7 @@ struct tpm2_pcr_read_out { * * Return: Same as with tpm_transmit_cmd. */ -int tpm2_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) +int tpm2_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) { int rc; struct tpm_buf buf; @@ -233,7 +225,7 @@ struct tpm2_null_auth_area { * * Return: Same as with tpm_transmit_cmd. */ -int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count, +int tpm2_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, u32 count, struct tpm2_digest *digests) { struct tpm_buf buf; @@ -280,7 +272,6 @@ int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count, return rc; } - struct tpm2_get_random_out { __be16 size; u8 buffer[TPM_MAX_RNG_DATA]; @@ -351,11 +342,10 @@ out: /** * tpm2_flush_context_cmd() - execute a TPM2_FlushContext command - * @chip: TPM chip to use - * @payload: the key data in clear and encrypted form - * @options: authentication values and other options + * @chip: TPM chip to use + * @handle: context handle + * @flags: tpm transmit flags - bitmap * - * Return: same as with tpm_transmit_cmd */ void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle, unsigned int flags) @@ -748,32 +738,6 @@ void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type) tpm_buf_destroy(&buf); } -/* - * tpm2_calc_ordinal_duration() - maximum duration for a command - * - * @chip: TPM chip to use. - * @ordinal: command code number. - * - * Return: maximum duration for a command - */ -unsigned long tpm2_calc_ordinal_duration(struct tpm_chip *chip, u32 ordinal) -{ - int index = TPM_UNDEFINED; - int duration = 0; - - if (ordinal >= TPM2_CC_FIRST && ordinal <= TPM2_CC_LAST) - index = tpm2_ordinal_duration[ordinal - TPM2_CC_FIRST]; - - if (index != TPM_UNDEFINED) - duration = chip->duration[index]; - - if (duration <= 0) - duration = msecs_to_jiffies(TPM2_DURATION_DEFAULT); - - return duration; -} -EXPORT_SYMBOL_GPL(tpm2_calc_ordinal_duration); - /** * tpm2_do_selftest() - ensure that all self tests have passed * @@ -983,6 +947,36 @@ out: } /** + * tpm2_startup - turn on the TPM + * @chip: TPM chip to use + * + * Normally the firmware should start the TPM. This function is provided as a + * workaround if this does not happen. A legal case for this could be for + * example when a TPM emulator is used. + * + * Return: same as tpm_transmit_cmd() + */ + +static int tpm2_startup(struct tpm_chip *chip) +{ + struct tpm_buf buf; + int rc; + + dev_info(&chip->dev, "starting up the TPM manually\n"); + + rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_STARTUP); + if (rc < 0) + return rc; + + tpm_buf_append_u16(&buf, TPM2_SU_CLEAR); + rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, + "attempting to start the TPM"); + tpm_buf_destroy(&buf); + + return rc; +} + +/** * tpm2_auto_startup - Perform the standard automatic TPM initialization * sequence * @chip: TPM chip to use @@ -993,7 +987,7 @@ int tpm2_auto_startup(struct tpm_chip *chip) { int rc; - rc = tpm_get_timeouts(chip); + rc = tpm2_get_timeouts(chip); if (rc) goto out; @@ -1002,7 +996,7 @@ int tpm2_auto_startup(struct tpm_chip *chip) goto out; if (rc == TPM2_RC_INITIALIZE) { - rc = tpm_startup(chip); + rc = tpm2_startup(chip); if (rc) goto out; diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index d2e101b32482..dcdfde3c253e 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -373,7 +373,7 @@ static int tpm2_map_response_header(struct tpm_chip *chip, u32 cc, u8 *rsp, dev_err(&chip->dev, "%s: unknown handle 0x%08X\n", __func__, phandle); break; - }; + } return 0; out_no_slots: diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c index caa86b19c76d..217f7f1cbde8 100644 --- a/drivers/char/tpm/tpm_i2c_nuvoton.c +++ b/drivers/char/tpm/tpm_i2c_nuvoton.c @@ -369,6 +369,7 @@ static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len) struct device *dev = chip->dev.parent; struct i2c_client *client = to_i2c_client(dev); u32 ordinal; + unsigned long duration; size_t count = 0; int burst_count, bytes2write, retries, rc = -EIO; @@ -455,12 +456,12 @@ static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len) return rc; } ordinal = be32_to_cpu(*((__be32 *) (buf + 6))); - rc = i2c_nuvoton_wait_for_data_avail(chip, - tpm_calc_ordinal_duration(chip, - ordinal), - &priv->read_queue); + duration = tpm_calc_ordinal_duration(chip, ordinal); + + rc = i2c_nuvoton_wait_for_data_avail(chip, duration, &priv->read_queue); if (rc) { - dev_err(dev, "%s() timeout command duration\n", __func__); + dev_err(dev, "%s() timeout command duration %ld\n", + __func__, duration); i2c_nuvoton_ready(chip); return rc; } diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index 25f6e2665385..07b5a487d0c8 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -39,8 +39,7 @@ static const struct vio_device_id tpm_ibmvtpm_device_table[] = { MODULE_DEVICE_TABLE(vio, tpm_ibmvtpm_device_table); /** - * - * ibmvtpm_send_crq_word - Send a CRQ request + * ibmvtpm_send_crq_word() - Send a CRQ request * @vdev: vio device struct * @w1: pre-constructed first word of tpm crq (second word is reserved) * @@ -54,8 +53,7 @@ static int ibmvtpm_send_crq_word(struct vio_dev *vdev, u64 w1) } /** - * - * ibmvtpm_send_crq - Send a CRQ request + * ibmvtpm_send_crq() - Send a CRQ request * * @vdev: vio device struct * @valid: Valid field diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index d2345d9fd7b5..bf7e49cfa643 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -473,11 +473,7 @@ static int tpm_tis_send_main(struct tpm_chip *chip, const u8 *buf, size_t len) if (chip->flags & TPM_CHIP_FLAG_IRQ) { ordinal = be32_to_cpu(*((__be32 *) (buf + 6))); - if (chip->flags & TPM_CHIP_FLAG_TPM2) - dur = tpm2_calc_ordinal_duration(chip, ordinal); - else - dur = tpm_calc_ordinal_duration(chip, ordinal); - + dur = tpm_calc_ordinal_duration(chip, ordinal); if (wait_for_tpm_stat (chip, TPM_STS_DATA_AVAIL | TPM_STS_VALID, dur, &priv->read_queue, false) < 0) { @@ -668,7 +664,7 @@ static int tpm_tis_gen_interrupt(struct tpm_chip *chip) if (chip->flags & TPM_CHIP_FLAG_TPM2) return tpm2_get_tpm_pt(chip, 0x100, &cap2, desc); else - return tpm_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, + return tpm1_getcap(chip, TPM_CAP_PROP_TIS_TIMEOUT, &cap, desc, 0); } @@ -1060,7 +1056,7 @@ int tpm_tis_resume(struct device *dev) * an error code but for unknown reason it isn't handled. */ if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) - tpm_do_selftest(chip); + tpm1_do_selftest(chip); return 0; } diff --git a/drivers/clk/imx/clk-imx8qxp-lpcg.c b/drivers/clk/imx/clk-imx8qxp-lpcg.c index dcae1dd85e43..99c2508de8e5 100644 --- a/drivers/clk/imx/clk-imx8qxp-lpcg.c +++ b/drivers/clk/imx/clk-imx8qxp-lpcg.c @@ -16,7 +16,7 @@ #include "clk-scu.h" #include "clk-imx8qxp-lpcg.h" -#include <dt-bindings/clock/imx8qxp-clock.h> +#include <dt-bindings/clock/imx8-clock.h> /* * struct imx8qxp_lpcg_data - Description of one LPCG clock @@ -56,100 +56,100 @@ struct imx8qxp_ss_lpcg { }; static const struct imx8qxp_lpcg_data imx8qxp_lpcg_adma[] = { - { IMX8QXP_ADMA_LPCG_UART0_IPG_CLK, "uart0_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_0_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_UART0_BAUD_CLK, "uart0_lpcg_baud_clk", "uart0_clk", 0, ADMA_LPUART_0_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_UART1_IPG_CLK, "uart1_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_1_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_UART1_BAUD_CLK, "uart1_lpcg_baud_clk", "uart1_clk", 0, ADMA_LPUART_1_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_UART2_IPG_CLK, "uart2_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_2_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_UART2_BAUD_CLK, "uart2_lpcg_baud_clk", "uart2_clk", 0, ADMA_LPUART_2_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_UART3_IPG_CLK, "uart3_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_3_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_UART3_BAUD_CLK, "uart3_lpcg_baud_clk", "uart3_clk", 0, ADMA_LPUART_3_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_I2C0_IPG_CLK, "i2c0_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_0_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_I2C0_CLK, "i2c0_lpcg_clk", "i2c0_clk", 0, ADMA_LPI2C_0_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_I2C1_IPG_CLK, "i2c1_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_1_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_I2C1_CLK, "i2c1_lpcg_clk", "i2c1_clk", 0, ADMA_LPI2C_1_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_I2C2_IPG_CLK, "i2c2_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_2_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_I2C2_CLK, "i2c2_lpcg_clk", "i2c2_clk", 0, ADMA_LPI2C_2_LPCG, 0, 0, }, - { IMX8QXP_ADMA_LPCG_I2C3_IPG_CLK, "i2c3_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_3_LPCG, 16, 0, }, - { IMX8QXP_ADMA_LPCG_I2C3_CLK, "i2c3_lpcg_clk", "i2c3_clk", 0, ADMA_LPI2C_3_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_UART0_IPG_CLK, "uart0_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_0_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_UART0_BAUD_CLK, "uart0_lpcg_baud_clk", "uart0_clk", 0, ADMA_LPUART_0_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_UART1_IPG_CLK, "uart1_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_1_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_UART1_BAUD_CLK, "uart1_lpcg_baud_clk", "uart1_clk", 0, ADMA_LPUART_1_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_UART2_IPG_CLK, "uart2_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_2_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_UART2_BAUD_CLK, "uart2_lpcg_baud_clk", "uart2_clk", 0, ADMA_LPUART_2_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_UART3_IPG_CLK, "uart3_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPUART_3_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_UART3_BAUD_CLK, "uart3_lpcg_baud_clk", "uart3_clk", 0, ADMA_LPUART_3_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_I2C0_IPG_CLK, "i2c0_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_0_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_I2C0_CLK, "i2c0_lpcg_clk", "i2c0_clk", 0, ADMA_LPI2C_0_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_I2C1_IPG_CLK, "i2c1_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_1_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_I2C1_CLK, "i2c1_lpcg_clk", "i2c1_clk", 0, ADMA_LPI2C_1_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_I2C2_IPG_CLK, "i2c2_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_2_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_I2C2_CLK, "i2c2_lpcg_clk", "i2c2_clk", 0, ADMA_LPI2C_2_LPCG, 0, 0, }, + { IMX_ADMA_LPCG_I2C3_IPG_CLK, "i2c3_lpcg_ipg_clk", "dma_ipg_clk_root", 0, ADMA_LPI2C_3_LPCG, 16, 0, }, + { IMX_ADMA_LPCG_I2C3_CLK, "i2c3_lpcg_clk", "i2c3_clk", 0, ADMA_LPI2C_3_LPCG, 0, 0, }, }; static const struct imx8qxp_ss_lpcg imx8qxp_ss_adma = { .lpcg = imx8qxp_lpcg_adma, .num_lpcg = ARRAY_SIZE(imx8qxp_lpcg_adma), - .num_max = IMX8QXP_ADMA_LPCG_CLK_END, + .num_max = IMX_ADMA_LPCG_CLK_END, }; static const struct imx8qxp_lpcg_data imx8qxp_lpcg_conn[] = { - { IMX8QXP_CONN_LPCG_SDHC0_PER_CLK, "sdhc0_lpcg_per_clk", "sdhc0_clk", 0, CONN_USDHC_0_LPCG, 0, 0, }, - { IMX8QXP_CONN_LPCG_SDHC0_IPG_CLK, "sdhc0_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_0_LPCG, 16, 0, }, - { IMX8QXP_CONN_LPCG_SDHC0_HCLK, "sdhc0_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_0_LPCG, 20, 0, }, - { IMX8QXP_CONN_LPCG_SDHC1_PER_CLK, "sdhc1_lpcg_per_clk", "sdhc1_clk", 0, CONN_USDHC_1_LPCG, 0, 0, }, - { IMX8QXP_CONN_LPCG_SDHC1_IPG_CLK, "sdhc1_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_1_LPCG, 16, 0, }, - { IMX8QXP_CONN_LPCG_SDHC1_HCLK, "sdhc1_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_1_LPCG, 20, 0, }, - { IMX8QXP_CONN_LPCG_SDHC2_PER_CLK, "sdhc2_lpcg_per_clk", "sdhc2_clk", 0, CONN_USDHC_2_LPCG, 0, 0, }, - { IMX8QXP_CONN_LPCG_SDHC2_IPG_CLK, "sdhc2_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_2_LPCG, 16, 0, }, - { IMX8QXP_CONN_LPCG_SDHC2_HCLK, "sdhc2_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_2_LPCG, 20, 0, }, - { IMX8QXP_CONN_LPCG_ENET0_ROOT_CLK, "enet0_ipg_root_clk", "enet0_clk", 0, CONN_ENET_0_LPCG, 0, 0, }, - { IMX8QXP_CONN_LPCG_ENET0_TX_CLK, "enet0_tx_clk", "enet0_clk", 0, CONN_ENET_0_LPCG, 4, 0, }, - { IMX8QXP_CONN_LPCG_ENET0_AHB_CLK, "enet0_ahb_clk", "conn_axi_clk_root", 0, CONN_ENET_0_LPCG, 8, 0, }, - { IMX8QXP_CONN_LPCG_ENET0_IPG_S_CLK, "enet0_ipg_s_clk", "conn_ipg_clk_root", 0, CONN_ENET_0_LPCG, 20, 0, }, - { IMX8QXP_CONN_LPCG_ENET0_IPG_CLK, "enet0_ipg_clk", "enet0_ipg_s_clk", 0, CONN_ENET_0_LPCG, 16, 0, }, - { IMX8QXP_CONN_LPCG_ENET1_ROOT_CLK, "enet1_ipg_root_clk", "enet1_clk", 0, CONN_ENET_1_LPCG, 0, 0, }, - { IMX8QXP_CONN_LPCG_ENET1_TX_CLK, "enet1_tx_clk", "enet1_clk", 0, CONN_ENET_1_LPCG, 4, 0, }, - { IMX8QXP_CONN_LPCG_ENET1_AHB_CLK, "enet1_ahb_clk", "conn_axi_clk_root", 0, CONN_ENET_1_LPCG, 8, 0, }, - { IMX8QXP_CONN_LPCG_ENET1_IPG_S_CLK, "enet1_ipg_s_clk", "conn_ipg_clk_root", 0, CONN_ENET_1_LPCG, 20, 0, }, - { IMX8QXP_CONN_LPCG_ENET1_IPG_CLK, "enet1_ipg_clk", "enet0_ipg_s_clk", 0, CONN_ENET_1_LPCG, 16, 0, }, + { IMX_CONN_LPCG_SDHC0_PER_CLK, "sdhc0_lpcg_per_clk", "sdhc0_clk", 0, CONN_USDHC_0_LPCG, 0, 0, }, + { IMX_CONN_LPCG_SDHC0_IPG_CLK, "sdhc0_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_0_LPCG, 16, 0, }, + { IMX_CONN_LPCG_SDHC0_HCLK, "sdhc0_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_0_LPCG, 20, 0, }, + { IMX_CONN_LPCG_SDHC1_PER_CLK, "sdhc1_lpcg_per_clk", "sdhc1_clk", 0, CONN_USDHC_1_LPCG, 0, 0, }, + { IMX_CONN_LPCG_SDHC1_IPG_CLK, "sdhc1_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_1_LPCG, 16, 0, }, + { IMX_CONN_LPCG_SDHC1_HCLK, "sdhc1_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_1_LPCG, 20, 0, }, + { IMX_CONN_LPCG_SDHC2_PER_CLK, "sdhc2_lpcg_per_clk", "sdhc2_clk", 0, CONN_USDHC_2_LPCG, 0, 0, }, + { IMX_CONN_LPCG_SDHC2_IPG_CLK, "sdhc2_lpcg_ipg_clk", "conn_ipg_clk_root", 0, CONN_USDHC_2_LPCG, 16, 0, }, + { IMX_CONN_LPCG_SDHC2_HCLK, "sdhc2_lpcg_ahb_clk", "conn_axi_clk_root", 0, CONN_USDHC_2_LPCG, 20, 0, }, + { IMX_CONN_LPCG_ENET0_ROOT_CLK, "enet0_ipg_root_clk", "enet0_clk", 0, CONN_ENET_0_LPCG, 0, 0, }, + { IMX_CONN_LPCG_ENET0_TX_CLK, "enet0_tx_clk", "enet0_clk", 0, CONN_ENET_0_LPCG, 4, 0, }, + { IMX_CONN_LPCG_ENET0_AHB_CLK, "enet0_ahb_clk", "conn_axi_clk_root", 0, CONN_ENET_0_LPCG, 8, 0, }, + { IMX_CONN_LPCG_ENET0_IPG_S_CLK, "enet0_ipg_s_clk", "conn_ipg_clk_root", 0, CONN_ENET_0_LPCG, 20, 0, }, + { IMX_CONN_LPCG_ENET0_IPG_CLK, "enet0_ipg_clk", "enet0_ipg_s_clk", 0, CONN_ENET_0_LPCG, 16, 0, }, + { IMX_CONN_LPCG_ENET1_ROOT_CLK, "enet1_ipg_root_clk", "enet1_clk", 0, CONN_ENET_1_LPCG, 0, 0, }, + { IMX_CONN_LPCG_ENET1_TX_CLK, "enet1_tx_clk", "enet1_clk", 0, CONN_ENET_1_LPCG, 4, 0, }, + { IMX_CONN_LPCG_ENET1_AHB_CLK, "enet1_ahb_clk", "conn_axi_clk_root", 0, CONN_ENET_1_LPCG, 8, 0, }, + { IMX_CONN_LPCG_ENET1_IPG_S_CLK, "enet1_ipg_s_clk", "conn_ipg_clk_root", 0, CONN_ENET_1_LPCG, 20, 0, }, + { IMX_CONN_LPCG_ENET1_IPG_CLK, "enet1_ipg_clk", "enet0_ipg_s_clk", 0, CONN_ENET_1_LPCG, 16, 0, }, }; static const struct imx8qxp_ss_lpcg imx8qxp_ss_conn = { .lpcg = imx8qxp_lpcg_conn, .num_lpcg = ARRAY_SIZE(imx8qxp_lpcg_conn), - .num_max = IMX8QXP_CONN_LPCG_CLK_END, + .num_max = IMX_CONN_LPCG_CLK_END, }; static const struct imx8qxp_lpcg_data imx8qxp_lpcg_lsio[] = { - { IMX8QXP_LSIO_LPCG_PWM0_IPG_CLK, "pwm0_lpcg_ipg_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM0_IPG_HF_CLK, "pwm0_lpcg_ipg_hf_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM0_IPG_S_CLK, "pwm0_lpcg_ipg_s_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM0_IPG_SLV_CLK, "pwm0_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_0_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM0_IPG_MSTR_CLK, "pwm0_lpcg_ipg_mstr_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM1_IPG_CLK, "pwm1_lpcg_ipg_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM1_IPG_HF_CLK, "pwm1_lpcg_ipg_hf_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM1_IPG_S_CLK, "pwm1_lpcg_ipg_s_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM1_IPG_SLV_CLK, "pwm1_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_1_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM1_IPG_MSTR_CLK, "pwm1_lpcg_ipg_mstr_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM2_IPG_CLK, "pwm2_lpcg_ipg_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM2_IPG_HF_CLK, "pwm2_lpcg_ipg_hf_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM2_IPG_S_CLK, "pwm2_lpcg_ipg_s_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM2_IPG_SLV_CLK, "pwm2_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_2_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM2_IPG_MSTR_CLK, "pwm2_lpcg_ipg_mstr_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM3_IPG_CLK, "pwm3_lpcg_ipg_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM3_IPG_HF_CLK, "pwm3_lpcg_ipg_hf_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM3_IPG_S_CLK, "pwm3_lpcg_ipg_s_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM3_IPG_SLV_CLK, "pwm3_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_3_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM3_IPG_MSTR_CLK, "pwm3_lpcg_ipg_mstr_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM4_IPG_CLK, "pwm4_lpcg_ipg_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM4_IPG_HF_CLK, "pwm4_lpcg_ipg_hf_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM4_IPG_S_CLK, "pwm4_lpcg_ipg_s_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM4_IPG_SLV_CLK, "pwm4_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_4_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM4_IPG_MSTR_CLK, "pwm4_lpcg_ipg_mstr_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM5_IPG_CLK, "pwm5_lpcg_ipg_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM5_IPG_HF_CLK, "pwm5_lpcg_ipg_hf_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM5_IPG_S_CLK, "pwm5_lpcg_ipg_s_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM5_IPG_SLV_CLK, "pwm5_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_5_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM5_IPG_MSTR_CLK, "pwm5_lpcg_ipg_mstr_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 24, 0, }, - { IMX8QXP_LSIO_LPCG_PWM6_IPG_CLK, "pwm6_lpcg_ipg_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 0, 0, }, - { IMX8QXP_LSIO_LPCG_PWM6_IPG_HF_CLK, "pwm6_lpcg_ipg_hf_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 4, 0, }, - { IMX8QXP_LSIO_LPCG_PWM6_IPG_S_CLK, "pwm6_lpcg_ipg_s_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 16, 0, }, - { IMX8QXP_LSIO_LPCG_PWM6_IPG_SLV_CLK, "pwm6_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_6_LPCG, 20, 0, }, - { IMX8QXP_LSIO_LPCG_PWM6_IPG_MSTR_CLK, "pwm6_lpcg_ipg_mstr_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM0_IPG_CLK, "pwm0_lpcg_ipg_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM0_IPG_HF_CLK, "pwm0_lpcg_ipg_hf_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM0_IPG_S_CLK, "pwm0_lpcg_ipg_s_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM0_IPG_SLV_CLK, "pwm0_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_0_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM0_IPG_MSTR_CLK, "pwm0_lpcg_ipg_mstr_clk", "pwm0_clk", 0, LSIO_PWM_0_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM1_IPG_CLK, "pwm1_lpcg_ipg_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM1_IPG_HF_CLK, "pwm1_lpcg_ipg_hf_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM1_IPG_S_CLK, "pwm1_lpcg_ipg_s_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM1_IPG_SLV_CLK, "pwm1_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_1_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM1_IPG_MSTR_CLK, "pwm1_lpcg_ipg_mstr_clk", "pwm1_clk", 0, LSIO_PWM_1_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM2_IPG_CLK, "pwm2_lpcg_ipg_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM2_IPG_HF_CLK, "pwm2_lpcg_ipg_hf_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM2_IPG_S_CLK, "pwm2_lpcg_ipg_s_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM2_IPG_SLV_CLK, "pwm2_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_2_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM2_IPG_MSTR_CLK, "pwm2_lpcg_ipg_mstr_clk", "pwm2_clk", 0, LSIO_PWM_2_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM3_IPG_CLK, "pwm3_lpcg_ipg_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM3_IPG_HF_CLK, "pwm3_lpcg_ipg_hf_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM3_IPG_S_CLK, "pwm3_lpcg_ipg_s_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM3_IPG_SLV_CLK, "pwm3_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_3_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM3_IPG_MSTR_CLK, "pwm3_lpcg_ipg_mstr_clk", "pwm3_clk", 0, LSIO_PWM_3_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM4_IPG_CLK, "pwm4_lpcg_ipg_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM4_IPG_HF_CLK, "pwm4_lpcg_ipg_hf_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM4_IPG_S_CLK, "pwm4_lpcg_ipg_s_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM4_IPG_SLV_CLK, "pwm4_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_4_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM4_IPG_MSTR_CLK, "pwm4_lpcg_ipg_mstr_clk", "pwm4_clk", 0, LSIO_PWM_4_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM5_IPG_CLK, "pwm5_lpcg_ipg_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM5_IPG_HF_CLK, "pwm5_lpcg_ipg_hf_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM5_IPG_S_CLK, "pwm5_lpcg_ipg_s_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM5_IPG_SLV_CLK, "pwm5_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_5_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM5_IPG_MSTR_CLK, "pwm5_lpcg_ipg_mstr_clk", "pwm5_clk", 0, LSIO_PWM_5_LPCG, 24, 0, }, + { IMX_LSIO_LPCG_PWM6_IPG_CLK, "pwm6_lpcg_ipg_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 0, 0, }, + { IMX_LSIO_LPCG_PWM6_IPG_HF_CLK, "pwm6_lpcg_ipg_hf_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 4, 0, }, + { IMX_LSIO_LPCG_PWM6_IPG_S_CLK, "pwm6_lpcg_ipg_s_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 16, 0, }, + { IMX_LSIO_LPCG_PWM6_IPG_SLV_CLK, "pwm6_lpcg_ipg_slv_clk", "lsio_bus_clk_root", 0, LSIO_PWM_6_LPCG, 20, 0, }, + { IMX_LSIO_LPCG_PWM6_IPG_MSTR_CLK, "pwm6_lpcg_ipg_mstr_clk", "pwm6_clk", 0, LSIO_PWM_6_LPCG, 24, 0, }, }; static const struct imx8qxp_ss_lpcg imx8qxp_ss_lsio = { .lpcg = imx8qxp_lpcg_lsio, .num_lpcg = ARRAY_SIZE(imx8qxp_lpcg_lsio), - .num_max = IMX8QXP_LSIO_LPCG_CLK_END, + .num_max = IMX_LSIO_LPCG_CLK_END, }; static int imx8qxp_lpcg_clk_probe(struct platform_device *pdev) diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index 33c9396b08f1..83e2ef96d81d 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -14,7 +14,7 @@ #include "clk-scu.h" -#include <dt-bindings/clock/imx8qxp-clock.h> +#include <dt-bindings/clock/imx8-clock.h> #include <dt-bindings/firmware/imx/rsrc.h> static int imx8qxp_clk_probe(struct platform_device *pdev) @@ -29,104 +29,104 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) return ret; clk_data = devm_kzalloc(&pdev->dev, struct_size(clk_data, hws, - IMX8QXP_SCU_CLK_END), GFP_KERNEL); + IMX_SCU_CLK_END), GFP_KERNEL); if (!clk_data) return -ENOMEM; - clk_data->num = IMX8QXP_SCU_CLK_END; + clk_data->num = IMX_SCU_CLK_END; clks = clk_data->hws; /* Fixed clocks */ - clks[IMX8QXP_CLK_DUMMY] = clk_hw_register_fixed_rate(NULL, "dummy", NULL, 0, 0); - clks[IMX8QXP_ADMA_IPG_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "dma_ipg_clk_root", NULL, 0, 120000000); - clks[IMX8QXP_CONN_AXI_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_axi_clk_root", NULL, 0, 333333333); - clks[IMX8QXP_CONN_AHB_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_ahb_clk_root", NULL, 0, 166666666); - clks[IMX8QXP_CONN_IPG_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_ipg_clk_root", NULL, 0, 83333333); - clks[IMX8QXP_DC_AXI_EXT_CLK] = clk_hw_register_fixed_rate(NULL, "dc_axi_ext_clk_root", NULL, 0, 800000000); - clks[IMX8QXP_DC_AXI_INT_CLK] = clk_hw_register_fixed_rate(NULL, "dc_axi_int_clk_root", NULL, 0, 400000000); - clks[IMX8QXP_DC_CFG_CLK] = clk_hw_register_fixed_rate(NULL, "dc_cfg_clk_root", NULL, 0, 100000000); - clks[IMX8QXP_MIPI_IPG_CLK] = clk_hw_register_fixed_rate(NULL, "mipi_ipg_clk_root", NULL, 0, 120000000); - clks[IMX8QXP_IMG_AXI_CLK] = clk_hw_register_fixed_rate(NULL, "img_axi_clk_root", NULL, 0, 400000000); - clks[IMX8QXP_IMG_IPG_CLK] = clk_hw_register_fixed_rate(NULL, "img_ipg_clk_root", NULL, 0, 200000000); - clks[IMX8QXP_IMG_PXL_CLK] = clk_hw_register_fixed_rate(NULL, "img_pxl_clk_root", NULL, 0, 600000000); - clks[IMX8QXP_HSIO_AXI_CLK] = clk_hw_register_fixed_rate(NULL, "hsio_axi_clk_root", NULL, 0, 400000000); - clks[IMX8QXP_HSIO_PER_CLK] = clk_hw_register_fixed_rate(NULL, "hsio_per_clk_root", NULL, 0, 133333333); - clks[IMX8QXP_LSIO_MEM_CLK] = clk_hw_register_fixed_rate(NULL, "lsio_mem_clk_root", NULL, 0, 200000000); - clks[IMX8QXP_LSIO_BUS_CLK] = clk_hw_register_fixed_rate(NULL, "lsio_bus_clk_root", NULL, 0, 100000000); + clks[IMX_CLK_DUMMY] = clk_hw_register_fixed_rate(NULL, "dummy", NULL, 0, 0); + clks[IMX_ADMA_IPG_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "dma_ipg_clk_root", NULL, 0, 120000000); + clks[IMX_CONN_AXI_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_axi_clk_root", NULL, 0, 333333333); + clks[IMX_CONN_AHB_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_ahb_clk_root", NULL, 0, 166666666); + clks[IMX_CONN_IPG_CLK_ROOT] = clk_hw_register_fixed_rate(NULL, "conn_ipg_clk_root", NULL, 0, 83333333); + clks[IMX_DC_AXI_EXT_CLK] = clk_hw_register_fixed_rate(NULL, "dc_axi_ext_clk_root", NULL, 0, 800000000); + clks[IMX_DC_AXI_INT_CLK] = clk_hw_register_fixed_rate(NULL, "dc_axi_int_clk_root", NULL, 0, 400000000); + clks[IMX_DC_CFG_CLK] = clk_hw_register_fixed_rate(NULL, "dc_cfg_clk_root", NULL, 0, 100000000); + clks[IMX_MIPI_IPG_CLK] = clk_hw_register_fixed_rate(NULL, "mipi_ipg_clk_root", NULL, 0, 120000000); + clks[IMX_IMG_AXI_CLK] = clk_hw_register_fixed_rate(NULL, "img_axi_clk_root", NULL, 0, 400000000); + clks[IMX_IMG_IPG_CLK] = clk_hw_register_fixed_rate(NULL, "img_ipg_clk_root", NULL, 0, 200000000); + clks[IMX_IMG_PXL_CLK] = clk_hw_register_fixed_rate(NULL, "img_pxl_clk_root", NULL, 0, 600000000); + clks[IMX_HSIO_AXI_CLK] = clk_hw_register_fixed_rate(NULL, "hsio_axi_clk_root", NULL, 0, 400000000); + clks[IMX_HSIO_PER_CLK] = clk_hw_register_fixed_rate(NULL, "hsio_per_clk_root", NULL, 0, 133333333); + clks[IMX_LSIO_MEM_CLK] = clk_hw_register_fixed_rate(NULL, "lsio_mem_clk_root", NULL, 0, 200000000); + clks[IMX_LSIO_BUS_CLK] = clk_hw_register_fixed_rate(NULL, "lsio_bus_clk_root", NULL, 0, 100000000); /* ARM core */ - clks[IMX8QXP_A35_CLK] = imx_clk_scu("a35_clk", IMX_SC_R_A35, IMX_SC_PM_CLK_CPU); + clks[IMX_A35_CLK] = imx_clk_scu("a35_clk", IMX_SC_R_A35, IMX_SC_PM_CLK_CPU); /* LSIO SS */ - clks[IMX8QXP_LSIO_PWM0_CLK] = imx_clk_scu("pwm0_clk", IMX_SC_R_PWM_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM1_CLK] = imx_clk_scu("pwm1_clk", IMX_SC_R_PWM_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM2_CLK] = imx_clk_scu("pwm2_clk", IMX_SC_R_PWM_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM3_CLK] = imx_clk_scu("pwm3_clk", IMX_SC_R_PWM_3, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM4_CLK] = imx_clk_scu("pwm4_clk", IMX_SC_R_PWM_4, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM5_CLK] = imx_clk_scu("pwm5_clk", IMX_SC_R_PWM_5, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM6_CLK] = imx_clk_scu("pwm6_clk", IMX_SC_R_PWM_6, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_PWM7_CLK] = imx_clk_scu("pwm7_clk", IMX_SC_R_PWM_7, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_GPT0_CLK] = imx_clk_scu("gpt0_clk", IMX_SC_R_GPT_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_GPT1_CLK] = imx_clk_scu("gpt1_clk", IMX_SC_R_GPT_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_GPT2_CLK] = imx_clk_scu("gpt2_clk", IMX_SC_R_GPT_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_GPT3_CLK] = imx_clk_scu("gpt3_clk", IMX_SC_R_GPT_3, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_GPT4_CLK] = imx_clk_scu("gpt4_clk", IMX_SC_R_GPT_4, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_FSPI0_CLK] = imx_clk_scu("fspi0_clk", IMX_SC_R_FSPI_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_LSIO_FSPI1_CLK] = imx_clk_scu("fspi1_clk", IMX_SC_R_FSPI_1, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM0_CLK] = imx_clk_scu("pwm0_clk", IMX_SC_R_PWM_0, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM1_CLK] = imx_clk_scu("pwm1_clk", IMX_SC_R_PWM_1, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM2_CLK] = imx_clk_scu("pwm2_clk", IMX_SC_R_PWM_2, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM3_CLK] = imx_clk_scu("pwm3_clk", IMX_SC_R_PWM_3, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM4_CLK] = imx_clk_scu("pwm4_clk", IMX_SC_R_PWM_4, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM5_CLK] = imx_clk_scu("pwm5_clk", IMX_SC_R_PWM_5, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM6_CLK] = imx_clk_scu("pwm6_clk", IMX_SC_R_PWM_6, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_PWM7_CLK] = imx_clk_scu("pwm7_clk", IMX_SC_R_PWM_7, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_GPT0_CLK] = imx_clk_scu("gpt0_clk", IMX_SC_R_GPT_0, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_GPT1_CLK] = imx_clk_scu("gpt1_clk", IMX_SC_R_GPT_1, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_GPT2_CLK] = imx_clk_scu("gpt2_clk", IMX_SC_R_GPT_2, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_GPT3_CLK] = imx_clk_scu("gpt3_clk", IMX_SC_R_GPT_3, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_GPT4_CLK] = imx_clk_scu("gpt4_clk", IMX_SC_R_GPT_4, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_FSPI0_CLK] = imx_clk_scu("fspi0_clk", IMX_SC_R_FSPI_0, IMX_SC_PM_CLK_PER); + clks[IMX_LSIO_FSPI1_CLK] = imx_clk_scu("fspi1_clk", IMX_SC_R_FSPI_1, IMX_SC_PM_CLK_PER); /* ADMA SS */ - clks[IMX8QXP_ADMA_UART0_CLK] = imx_clk_scu("uart0_clk", IMX_SC_R_UART_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_UART1_CLK] = imx_clk_scu("uart1_clk", IMX_SC_R_UART_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_UART2_CLK] = imx_clk_scu("uart2_clk", IMX_SC_R_UART_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_UART3_CLK] = imx_clk_scu("uart3_clk", IMX_SC_R_UART_3, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_SPI0_CLK] = imx_clk_scu("spi0_clk", IMX_SC_R_SPI_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_SPI1_CLK] = imx_clk_scu("spi1_clk", IMX_SC_R_SPI_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_SPI2_CLK] = imx_clk_scu("spi2_clk", IMX_SC_R_SPI_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_SPI3_CLK] = imx_clk_scu("spi3_clk", IMX_SC_R_SPI_3, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_CAN0_CLK] = imx_clk_scu("can0_clk", IMX_SC_R_CAN_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_I2C0_CLK] = imx_clk_scu("i2c0_clk", IMX_SC_R_I2C_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_I2C1_CLK] = imx_clk_scu("i2c1_clk", IMX_SC_R_I2C_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_I2C2_CLK] = imx_clk_scu("i2c2_clk", IMX_SC_R_I2C_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_I2C3_CLK] = imx_clk_scu("i2c3_clk", IMX_SC_R_I2C_3, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_FTM0_CLK] = imx_clk_scu("ftm0_clk", IMX_SC_R_FTM_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_FTM1_CLK] = imx_clk_scu("ftm1_clk", IMX_SC_R_FTM_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_ADC0_CLK] = imx_clk_scu("adc0_clk", IMX_SC_R_ADC_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_PWM_CLK] = imx_clk_scu("pwm_clk", IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_ADMA_LCD_CLK] = imx_clk_scu("lcd_clk", IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_UART0_CLK] = imx_clk_scu("uart0_clk", IMX_SC_R_UART_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_UART1_CLK] = imx_clk_scu("uart1_clk", IMX_SC_R_UART_1, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_UART2_CLK] = imx_clk_scu("uart2_clk", IMX_SC_R_UART_2, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_UART3_CLK] = imx_clk_scu("uart3_clk", IMX_SC_R_UART_3, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_SPI0_CLK] = imx_clk_scu("spi0_clk", IMX_SC_R_SPI_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_SPI1_CLK] = imx_clk_scu("spi1_clk", IMX_SC_R_SPI_1, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_SPI2_CLK] = imx_clk_scu("spi2_clk", IMX_SC_R_SPI_2, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_SPI3_CLK] = imx_clk_scu("spi3_clk", IMX_SC_R_SPI_3, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_CAN0_CLK] = imx_clk_scu("can0_clk", IMX_SC_R_CAN_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_I2C0_CLK] = imx_clk_scu("i2c0_clk", IMX_SC_R_I2C_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_I2C1_CLK] = imx_clk_scu("i2c1_clk", IMX_SC_R_I2C_1, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_I2C2_CLK] = imx_clk_scu("i2c2_clk", IMX_SC_R_I2C_2, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_I2C3_CLK] = imx_clk_scu("i2c3_clk", IMX_SC_R_I2C_3, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_FTM0_CLK] = imx_clk_scu("ftm0_clk", IMX_SC_R_FTM_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_FTM1_CLK] = imx_clk_scu("ftm1_clk", IMX_SC_R_FTM_1, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_ADC0_CLK] = imx_clk_scu("adc0_clk", IMX_SC_R_ADC_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_PWM_CLK] = imx_clk_scu("pwm_clk", IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER); + clks[IMX_ADMA_LCD_CLK] = imx_clk_scu("lcd_clk", IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER); /* Connectivity */ - clks[IMX8QXP_CONN_SDHC0_CLK] = imx_clk_scu("sdhc0_clk", IMX_SC_R_SDHC_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_SDHC1_CLK] = imx_clk_scu("sdhc1_clk", IMX_SC_R_SDHC_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_SDHC2_CLK] = imx_clk_scu("sdhc2_clk", IMX_SC_R_SDHC_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_ENET0_ROOT_CLK] = imx_clk_scu("enet0_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_ENET0_BYPASS_CLK] = imx_clk_scu("enet0_bypass_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_BYPASS); - clks[IMX8QXP_CONN_ENET0_RGMII_CLK] = imx_clk_scu("enet0_rgmii_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_MISC0); - clks[IMX8QXP_CONN_ENET1_ROOT_CLK] = imx_clk_scu("enet1_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_ENET1_BYPASS_CLK] = imx_clk_scu("enet1_bypass_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_BYPASS); - clks[IMX8QXP_CONN_ENET1_RGMII_CLK] = imx_clk_scu("enet1_rgmii_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_MISC0); - clks[IMX8QXP_CONN_GPMI_BCH_IO_CLK] = imx_clk_scu("gpmi_io_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_MST_BUS); - clks[IMX8QXP_CONN_GPMI_BCH_CLK] = imx_clk_scu("gpmi_bch_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_USB2_ACLK] = imx_clk_scu("usb3_aclk_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CONN_USB2_BUS_CLK] = imx_clk_scu("usb3_bus_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MST_BUS); - clks[IMX8QXP_CONN_USB2_LPM_CLK] = imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC); + clks[IMX_CONN_SDHC0_CLK] = imx_clk_scu("sdhc0_clk", IMX_SC_R_SDHC_0, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_SDHC1_CLK] = imx_clk_scu("sdhc1_clk", IMX_SC_R_SDHC_1, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_SDHC2_CLK] = imx_clk_scu("sdhc2_clk", IMX_SC_R_SDHC_2, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_ENET0_ROOT_CLK] = imx_clk_scu("enet0_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_ENET0_BYPASS_CLK] = imx_clk_scu("enet0_bypass_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_BYPASS); + clks[IMX_CONN_ENET0_RGMII_CLK] = imx_clk_scu("enet0_rgmii_clk", IMX_SC_R_ENET_0, IMX_SC_PM_CLK_MISC0); + clks[IMX_CONN_ENET1_ROOT_CLK] = imx_clk_scu("enet1_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_ENET1_BYPASS_CLK] = imx_clk_scu("enet1_bypass_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_BYPASS); + clks[IMX_CONN_ENET1_RGMII_CLK] = imx_clk_scu("enet1_rgmii_clk", IMX_SC_R_ENET_1, IMX_SC_PM_CLK_MISC0); + clks[IMX_CONN_GPMI_BCH_IO_CLK] = imx_clk_scu("gpmi_io_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_MST_BUS); + clks[IMX_CONN_GPMI_BCH_CLK] = imx_clk_scu("gpmi_bch_clk", IMX_SC_R_NAND, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_USB2_ACLK] = imx_clk_scu("usb3_aclk_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_PER); + clks[IMX_CONN_USB2_BUS_CLK] = imx_clk_scu("usb3_bus_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MST_BUS); + clks[IMX_CONN_USB2_LPM_CLK] = imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC); /* Display controller SS */ - clks[IMX8QXP_DC0_DISP0_CLK] = imx_clk_scu("dc0_disp0_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); - clks[IMX8QXP_DC0_DISP1_CLK] = imx_clk_scu("dc0_disp1_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); + clks[IMX_DC0_DISP0_CLK] = imx_clk_scu("dc0_disp0_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); + clks[IMX_DC0_DISP1_CLK] = imx_clk_scu("dc0_disp1_clk", IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); /* MIPI-LVDS SS */ - clks[IMX8QXP_MIPI0_I2C0_CLK] = imx_clk_scu("mipi0_i2c0_clk", IMX_SC_R_MIPI_0_I2C_0, IMX_SC_PM_CLK_MISC2); - clks[IMX8QXP_MIPI0_I2C1_CLK] = imx_clk_scu("mipi0_i2c1_clk", IMX_SC_R_MIPI_0_I2C_1, IMX_SC_PM_CLK_MISC2); + clks[IMX_MIPI0_I2C0_CLK] = imx_clk_scu("mipi0_i2c0_clk", IMX_SC_R_MIPI_0_I2C_0, IMX_SC_PM_CLK_MISC2); + clks[IMX_MIPI0_I2C1_CLK] = imx_clk_scu("mipi0_i2c1_clk", IMX_SC_R_MIPI_0_I2C_1, IMX_SC_PM_CLK_MISC2); /* MIPI CSI SS */ - clks[IMX8QXP_CSI0_CORE_CLK] = imx_clk_scu("mipi_csi0_core_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CSI0_ESC_CLK] = imx_clk_scu("mipi_csi0_esc_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_MISC); - clks[IMX8QXP_CSI0_I2C0_CLK] = imx_clk_scu("mipi_csi0_i2c0_clk", IMX_SC_R_CSI_0_I2C_0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_CSI0_PWM0_CLK] = imx_clk_scu("mipi_csi0_pwm0_clk", IMX_SC_R_CSI_0_PWM_0, IMX_SC_PM_CLK_PER); + clks[IMX_CSI0_CORE_CLK] = imx_clk_scu("mipi_csi0_core_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_PER); + clks[IMX_CSI0_ESC_CLK] = imx_clk_scu("mipi_csi0_esc_clk", IMX_SC_R_CSI_0, IMX_SC_PM_CLK_MISC); + clks[IMX_CSI0_I2C0_CLK] = imx_clk_scu("mipi_csi0_i2c0_clk", IMX_SC_R_CSI_0_I2C_0, IMX_SC_PM_CLK_PER); + clks[IMX_CSI0_PWM0_CLK] = imx_clk_scu("mipi_csi0_pwm0_clk", IMX_SC_R_CSI_0_PWM_0, IMX_SC_PM_CLK_PER); /* GPU SS */ - clks[IMX8QXP_GPU0_CORE_CLK] = imx_clk_scu("gpu_core0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_PER); - clks[IMX8QXP_GPU0_SHADER_CLK] = imx_clk_scu("gpu_shader0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_MISC); + clks[IMX_GPU0_CORE_CLK] = imx_clk_scu("gpu_core0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_PER); + clks[IMX_GPU0_SHADER_CLK] = imx_clk_scu("gpu_shader0_clk", IMX_SC_R_GPU_0_PID0, IMX_SC_PM_CLK_MISC); for (i = 0; i < clk_data->num; i++) { if (IS_ERR(clks[i])) diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c index d083b860f083..61fefc046ec5 100644 --- a/drivers/clk/mmp/clk-of-mmp2.c +++ b/drivers/clk/mmp/clk-of-mmp2.c @@ -53,6 +53,7 @@ #define APMU_DISP1 0x110 #define APMU_CCIC0 0x50 #define APMU_CCIC1 0xf4 +#define APMU_SP 0x68 #define MPMU_UART_PLL 0x14 struct mmp2_clk_unit { @@ -209,6 +210,8 @@ static struct mmp_clk_mix_config ccic1_mix_config = { .reg_info = DEFINE_MIX_REG_INFO(4, 16, 2, 6, 32), }; +static DEFINE_SPINLOCK(sp_lock); + static struct mmp_param_mux_clk apmu_mux_clks[] = { {MMP2_CLK_DISP0_MUX, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 2, 0, &disp0_lock}, {MMP2_CLK_DISP1_MUX, "disp1_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP1, 6, 2, 0, &disp1_lock}, @@ -239,6 +242,7 @@ static struct mmp_param_gate_clk apmu_gate_clks[] = { {MMP2_CLK_CCIC1, "ccic1_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x1b, 0x1b, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_PHY, "ccic1_phy_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x24, 0x24, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_SPHY, "ccic1_sphy_clk", "ccic1_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x300, 0x300, 0x0, 0, &ccic1_lock}, + {MMP2_CLK_SP, "sp_clk", NULL, CLK_SET_RATE_PARENT, APMU_SP, 0x1b, 0x1b, 0x0, 0, &sp_lock}, }; static void mmp2_axi_periph_clk_init(struct mmp2_clk_unit *pxa_unit) diff --git a/drivers/input/keyboard/nomadik-ske-keypad.c b/drivers/input/keyboard/nomadik-ske-keypad.c index 8567ee47761e..ae3b04557074 100644 --- a/drivers/input/keyboard/nomadik-ske-keypad.c +++ b/drivers/input/keyboard/nomadik-ske-keypad.c @@ -100,7 +100,7 @@ static int __init ske_keypad_chip_init(struct ske_keypad *keypad) while ((readl(keypad->reg_base + SKE_RIS) != 0x00000000) && timeout--) cpu_relax(); - if (!timeout) + if (timeout == -1) return -EINVAL; /* diff --git a/drivers/input/misc/drv2667.c b/drivers/input/misc/drv2667.c index 2849bb6906a8..6091f0490e8f 100644 --- a/drivers/input/misc/drv2667.c +++ b/drivers/input/misc/drv2667.c @@ -177,9 +177,9 @@ static int drv2667_set_waveform_freq(struct drv2667_data *haptics) error = regmap_write(haptics->regmap, DRV2667_PAGE, read_buf); if (error) { dev_err(&haptics->client->dev, - "Failed to set the page: %d\n", error); - return -EIO; - } + "Failed to set the page: %d\n", error); + return -EIO; + } } return error; diff --git a/drivers/input/misc/rotary_encoder.c b/drivers/input/misc/rotary_encoder.c index 30ec77ad32c6..d748897bf5e9 100644 --- a/drivers/input/misc/rotary_encoder.c +++ b/drivers/input/misc/rotary_encoder.c @@ -240,8 +240,10 @@ static int rotary_encoder_probe(struct platform_device *pdev) encoder->gpios = devm_gpiod_get_array(dev, NULL, GPIOD_IN); if (IS_ERR(encoder->gpios)) { - dev_err(dev, "unable to get gpios\n"); - return PTR_ERR(encoder->gpios); + err = PTR_ERR(encoder->gpios); + if (err != -EPROBE_DEFER) + dev_err(dev, "unable to get gpios: %d\n", err); + return err; } if (encoder->gpios->ndescs < 2) { dev_err(dev, "not enough gpios found\n"); diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index a94b6494e71a..f322a1768fbb 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1336,6 +1336,7 @@ MODULE_DEVICE_TABLE(i2c, elan_id); static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, + { "ELAN0501", 0 }, { "ELAN0600", 0 }, { "ELAN0602", 0 }, { "ELAN0605", 0 }, diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig index d90d9f1098ff..c9c7224d5ae0 100644 --- a/drivers/input/serio/Kconfig +++ b/drivers/input/serio/Kconfig @@ -254,7 +254,6 @@ config SERIO_APBPS2 config SERIO_OLPC_APSP tristate "OLPC AP-SP input support" - depends on OLPC || COMPILE_TEST help Say Y here if you want support for the keyboard and touchpad included in the OLPC XO-1.75 and XO-4 laptops. diff --git a/drivers/input/serio/olpc_apsp.c b/drivers/input/serio/olpc_apsp.c index 8e9a4209fcad..b36084710f69 100644 --- a/drivers/input/serio/olpc_apsp.c +++ b/drivers/input/serio/olpc_apsp.c @@ -23,6 +23,7 @@ #include <linux/of.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/clk.h> /* * The OLPC XO-1.75 and XO-4 laptops do not have a hardware PS/2 controller. @@ -74,6 +75,7 @@ struct olpc_apsp { struct serio *kbio; struct serio *padio; void __iomem *base; + struct clk *clk; int open_count; int irq; }; @@ -145,8 +147,21 @@ static int olpc_apsp_open(struct serio *port) { struct olpc_apsp *priv = port->port_data; unsigned int tmp; + unsigned long l; + int error; if (priv->open_count++ == 0) { + error = clk_prepare_enable(priv->clk); + if (error) + return error; + + l = readl(priv->base + COMMAND_FIFO_STATUS); + if (!(l & CMD_STS_MASK)) { + dev_err(priv->dev, "SP cannot accept commands.\n"); + clk_disable_unprepare(priv->clk); + return -EIO; + } + /* Enable interrupt 0 by clearing its bit */ tmp = readl(priv->base + PJ_INTERRUPT_MASK); writel(tmp & ~INT_0, priv->base + PJ_INTERRUPT_MASK); @@ -164,6 +179,8 @@ static void olpc_apsp_close(struct serio *port) /* Disable interrupt 0 */ tmp = readl(priv->base + PJ_INTERRUPT_MASK); writel(tmp | INT_0, priv->base + PJ_INTERRUPT_MASK); + + clk_disable_unprepare(priv->clk); } } @@ -172,15 +189,12 @@ static int olpc_apsp_probe(struct platform_device *pdev) struct serio *kb_serio, *pad_serio; struct olpc_apsp *priv; struct resource *res; - struct device_node *np; - unsigned long l; int error; priv = devm_kzalloc(&pdev->dev, sizeof(struct olpc_apsp), GFP_KERNEL); if (!priv) return -ENOMEM; - np = pdev->dev.of_node; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); priv->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(priv->base)) { @@ -192,11 +206,9 @@ static int olpc_apsp_probe(struct platform_device *pdev) if (priv->irq < 0) return priv->irq; - l = readl(priv->base + COMMAND_FIFO_STATUS); - if (!(l & CMD_STS_MASK)) { - dev_err(&pdev->dev, "SP cannot accept commands.\n"); - return -EIO; - } + priv->clk = devm_clk_get(&pdev->dev, "sp"); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); /* KEYBOARD */ kb_serio = kzalloc(sizeof(struct serio), GFP_KERNEL); diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 2a80675cfd94..af6027cc7bbf 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -696,6 +696,18 @@ config TOUCHSCREEN_EDT_FT5X06 To compile this driver as a module, choose M here: the module will be called edt-ft5x06. +config TOUCHSCREEN_RASPBERRYPI_FW + tristate "Raspberry Pi's firmware base touch screen support" + depends on RASPBERRYPI_FIRMWARE || COMPILE_TEST + help + Say Y here if you have the official Raspberry Pi 7 inch screen on + your system. + + If unsure, say N. + + To compile this driver as a module, choose M here: the + module will be called raspberrypi-ts. + config TOUCHSCREEN_MIGOR tristate "Renesas MIGO-R touchscreen" depends on (SH_MIGOR || COMPILE_TEST) && I2C diff --git a/drivers/input/touchscreen/Makefile b/drivers/input/touchscreen/Makefile index 5911a4190cd2..fcc7605fba8d 100644 --- a/drivers/input/touchscreen/Makefile +++ b/drivers/input/touchscreen/Makefile @@ -109,3 +109,4 @@ obj-$(CONFIG_TOUCHSCREEN_ZET6223) += zet6223.o obj-$(CONFIG_TOUCHSCREEN_ZFORCE) += zforce_ts.o obj-$(CONFIG_TOUCHSCREEN_COLIBRI_VF50) += colibri-vf50-ts.o obj-$(CONFIG_TOUCHSCREEN_ROHM_BU21023) += rohm_bu21023.o +obj-$(CONFIG_TOUCHSCREEN_RASPBERRYPI_FW) += raspberrypi-ts.o diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c index 6bad23ee47a1..6fa714c587b4 100644 --- a/drivers/input/touchscreen/ad7879.c +++ b/drivers/input/touchscreen/ad7879.c @@ -29,10 +29,9 @@ #include <linux/property.h> #include <linux/regmap.h> #include <linux/slab.h> -#include <linux/gpio.h> +#include <linux/gpio/driver.h> #include <linux/input/touchscreen.h> -#include <linux/platform_data/ad7879.h> #include <linux/module.h> #include "ad7879.h" @@ -290,7 +289,7 @@ static int ad7879_open(struct input_dev *input) return 0; } -static void ad7879_close(struct input_dev* input) +static void ad7879_close(struct input_dev *input) { struct ad7879 *ts = input_get_drvdata(input); @@ -452,47 +451,36 @@ static void ad7879_gpio_set_value(struct gpio_chip *chip, mutex_unlock(&ts->mutex); } -static int ad7879_gpio_add(struct ad7879 *ts, - const struct ad7879_platform_data *pdata) +static int ad7879_gpio_add(struct ad7879 *ts) { - bool gpio_export; - int gpio_base; int ret = 0; - if (pdata) { - gpio_export = pdata->gpio_export; - gpio_base = pdata->gpio_base; - } else { - gpio_export = device_property_read_bool(ts->dev, - "gpio-controller"); - gpio_base = -1; - } - mutex_init(&ts->mutex); - if (gpio_export) { - ts->gc.direction_input = ad7879_gpio_direction_input; - ts->gc.direction_output = ad7879_gpio_direction_output; - ts->gc.get = ad7879_gpio_get_value; - ts->gc.set = ad7879_gpio_set_value; - ts->gc.can_sleep = 1; - ts->gc.base = gpio_base; - ts->gc.ngpio = 1; - ts->gc.label = "AD7879-GPIO"; - ts->gc.owner = THIS_MODULE; - ts->gc.parent = ts->dev; - - ret = devm_gpiochip_add_data(ts->dev, &ts->gc, ts); - if (ret) - dev_err(ts->dev, "failed to register gpio %d\n", - ts->gc.base); - } + /* Do not create a chip unless flagged for it */ + if (!device_property_read_bool(ts->dev, "gpio-controller")) + return 0; + + ts->gc.direction_input = ad7879_gpio_direction_input; + ts->gc.direction_output = ad7879_gpio_direction_output; + ts->gc.get = ad7879_gpio_get_value; + ts->gc.set = ad7879_gpio_set_value; + ts->gc.can_sleep = 1; + ts->gc.base = -1; + ts->gc.ngpio = 1; + ts->gc.label = "AD7879-GPIO"; + ts->gc.owner = THIS_MODULE; + ts->gc.parent = ts->dev; + + ret = devm_gpiochip_add_data(ts->dev, &ts->gc, ts); + if (ret) + dev_err(ts->dev, "failed to register gpio %d\n", + ts->gc.base); return ret; } #else -static int ad7879_gpio_add(struct ad7879 *ts, - const struct ad7879_platform_data *pdata) +static int ad7879_gpio_add(struct ad7879 *ts) { return 0; } @@ -527,7 +515,6 @@ static int ad7879_parse_dt(struct device *dev, struct ad7879 *ts) int ad7879_probe(struct device *dev, struct regmap *regmap, int irq, u16 bustype, u8 devid) { - struct ad7879_platform_data *pdata = dev_get_platdata(dev); struct ad7879 *ts; struct input_dev *input_dev; int err; @@ -542,22 +529,9 @@ int ad7879_probe(struct device *dev, struct regmap *regmap, if (!ts) return -ENOMEM; - if (pdata) { - /* Platform data use swapped axis (backward compatibility) */ - ts->swap_xy = !pdata->swap_xy; - - ts->x_plate_ohms = pdata->x_plate_ohms ? : 400; - - ts->first_conversion_delay = pdata->first_conversion_delay; - ts->acquisition_time = pdata->acquisition_time; - ts->averaging = pdata->averaging; - ts->pen_down_acc_interval = pdata->pen_down_acc_interval; - ts->median = pdata->median; - } else { - err = ad7879_parse_dt(dev, ts); - if (err) - return err; - } + err = ad7879_parse_dt(dev, ts); + if (err) + return err; input_dev = devm_input_allocate_device(dev); if (!input_dev) { @@ -585,28 +559,13 @@ int ad7879_probe(struct device *dev, struct regmap *regmap, input_set_capability(input_dev, EV_KEY, BTN_TOUCH); - if (pdata) { - input_set_abs_params(input_dev, ABS_X, - pdata->x_min ? : 0, - pdata->x_max ? : MAX_12BIT, - 0, 0); - input_set_abs_params(input_dev, ABS_Y, - pdata->y_min ? : 0, - pdata->y_max ? : MAX_12BIT, - 0, 0); - input_set_abs_params(input_dev, ABS_PRESSURE, - pdata->pressure_min, - pdata->pressure_max ? : ~0, - 0, 0); - } else { - input_set_abs_params(input_dev, ABS_X, 0, MAX_12BIT, 0, 0); - input_set_abs_params(input_dev, ABS_Y, 0, MAX_12BIT, 0, 0); - input_set_capability(input_dev, EV_ABS, ABS_PRESSURE); - touchscreen_parse_properties(input_dev, false, NULL); - if (!input_abs_get_max(input_dev, ABS_PRESSURE)) { - dev_err(dev, "Touchscreen pressure is not specified\n"); - return -EINVAL; - } + input_set_abs_params(input_dev, ABS_X, 0, MAX_12BIT, 0, 0); + input_set_abs_params(input_dev, ABS_Y, 0, MAX_12BIT, 0, 0); + input_set_capability(input_dev, EV_ABS, ABS_PRESSURE); + touchscreen_parse_properties(input_dev, false, NULL); + if (!input_abs_get_max(input_dev, ABS_PRESSURE)) { + dev_err(dev, "Touchscreen pressure is not specified\n"); + return -EINVAL; } err = ad7879_write(ts, AD7879_REG_CTRL2, AD7879_RESET); @@ -655,7 +614,7 @@ int ad7879_probe(struct device *dev, struct regmap *regmap, if (err) return err; - err = ad7879_gpio_add(ts, pdata); + err = ad7879_gpio_add(ts); if (err) return err; diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index d3aacd534e9c..5c63d25ce84e 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -1585,10 +1585,10 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *fw) /* T7 config may have changed */ mxt_init_t7_power_cfg(data); -release_raw: - kfree(cfg.raw); release_mem: kfree(cfg.mem); +release_raw: + kfree(cfg.raw); return ret; } diff --git a/drivers/input/touchscreen/ektf2127.c b/drivers/input/touchscreen/ektf2127.c index 0ed34ff787ce..28fa1b36f7a5 100644 --- a/drivers/input/touchscreen/ektf2127.c +++ b/drivers/input/touchscreen/ektf2127.c @@ -51,7 +51,7 @@ struct ektf2127_ts { struct touchscreen_properties prop; }; -static void ektf2127_parse_coordinates(const u8* buf, unsigned int touch_count, +static void ektf2127_parse_coordinates(const u8 *buf, unsigned int touch_count, struct input_mt_pos *touches) { int index = 0; diff --git a/drivers/input/touchscreen/gunze.c b/drivers/input/touchscreen/gunze.c index 054c2537b392..56cf1a1ea3ea 100644 --- a/drivers/input/touchscreen/gunze.c +++ b/drivers/input/touchscreen/gunze.c @@ -53,7 +53,7 @@ struct gunze { char phys[32]; }; -static void gunze_process_packet(struct gunze* gunze) +static void gunze_process_packet(struct gunze *gunze) { struct input_dev *dev = gunze->dev; @@ -72,7 +72,7 @@ static void gunze_process_packet(struct gunze* gunze) static irqreturn_t gunze_interrupt(struct serio *serio, unsigned char data, unsigned int flags) { - struct gunze* gunze = serio_get_drvdata(serio); + struct gunze *gunze = serio_get_drvdata(serio); if (data == '\r') { gunze_process_packet(gunze); diff --git a/drivers/input/touchscreen/inexio.c b/drivers/input/touchscreen/inexio.c index b9bc56233ccc..13bd0bf580a7 100644 --- a/drivers/input/touchscreen/inexio.c +++ b/drivers/input/touchscreen/inexio.c @@ -79,7 +79,7 @@ static void inexio_process_data(struct inexio *pinexio) static irqreturn_t inexio_interrupt(struct serio *serio, unsigned char data, unsigned int flags) { - struct inexio* pinexio = serio_get_drvdata(serio); + struct inexio *pinexio = serio_get_drvdata(serio); pinexio->data[pinexio->idx] = data; @@ -97,7 +97,7 @@ static irqreturn_t inexio_interrupt(struct serio *serio, static void inexio_disconnect(struct serio *serio) { - struct inexio* pinexio = serio_get_drvdata(serio); + struct inexio *pinexio = serio_get_drvdata(serio); input_get_device(pinexio->dev); input_unregister_device(pinexio->dev); diff --git a/drivers/input/touchscreen/mtouch.c b/drivers/input/touchscreen/mtouch.c index a3707fad4d1c..8278a9058640 100644 --- a/drivers/input/touchscreen/mtouch.c +++ b/drivers/input/touchscreen/mtouch.c @@ -90,7 +90,7 @@ static void mtouch_process_response(struct mtouch *mtouch) static irqreturn_t mtouch_interrupt(struct serio *serio, unsigned char data, unsigned int flags) { - struct mtouch* mtouch = serio_get_drvdata(serio); + struct mtouch *mtouch = serio_get_drvdata(serio); mtouch->data[mtouch->idx] = data; @@ -110,7 +110,7 @@ static irqreturn_t mtouch_interrupt(struct serio *serio, static void mtouch_disconnect(struct serio *serio) { - struct mtouch* mtouch = serio_get_drvdata(serio); + struct mtouch *mtouch = serio_get_drvdata(serio); input_get_device(mtouch->dev); input_unregister_device(mtouch->dev); diff --git a/drivers/input/touchscreen/raspberrypi-ts.c b/drivers/input/touchscreen/raspberrypi-ts.c new file mode 100644 index 000000000000..f456c1125bd6 --- /dev/null +++ b/drivers/input/touchscreen/raspberrypi-ts.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Raspberry Pi firmware based touchscreen driver + * + * Copyright (C) 2015, 2017 Raspberry Pi + * Copyright (C) 2018 Nicolas Saenz Julienne <nsaenzjulienne@suse.de> + */ + +#include <linux/io.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/bitops.h> +#include <linux/dma-mapping.h> +#include <linux/platform_device.h> +#include <linux/input.h> +#include <linux/input/mt.h> +#include <linux/input-polldev.h> +#include <linux/input/touchscreen.h> +#include <soc/bcm2835/raspberrypi-firmware.h> + +#define RPI_TS_DEFAULT_WIDTH 800 +#define RPI_TS_DEFAULT_HEIGHT 480 + +#define RPI_TS_MAX_SUPPORTED_POINTS 10 + +#define RPI_TS_FTS_TOUCH_DOWN 0 +#define RPI_TS_FTS_TOUCH_CONTACT 2 + +#define RPI_TS_POLL_INTERVAL 17 /* 60fps */ + +#define RPI_TS_NPOINTS_REG_INVALIDATE 99 + +struct rpi_ts { + struct platform_device *pdev; + struct input_polled_dev *poll_dev; + struct touchscreen_properties prop; + + void __iomem *fw_regs_va; + dma_addr_t fw_regs_phys; + + int known_ids; +}; + +struct rpi_ts_regs { + u8 device_mode; + u8 gesture_id; + u8 num_points; + struct rpi_ts_touch { + u8 xh; + u8 xl; + u8 yh; + u8 yl; + u8 pressure; /* Not supported */ + u8 area; /* Not supported */ + } point[RPI_TS_MAX_SUPPORTED_POINTS]; +}; + +static void rpi_ts_poll(struct input_polled_dev *dev) +{ + struct input_dev *input = dev->input; + struct rpi_ts *ts = dev->private; + struct rpi_ts_regs regs; + int modified_ids = 0; + long released_ids; + int event_type; + int touchid; + int x, y; + int i; + + memcpy_fromio(®s, ts->fw_regs_va, sizeof(regs)); + /* + * We poll the memory based register copy of the touchscreen chip using + * the number of points register to know whether the copy has been + * updated (we write 99 to the memory copy, the GPU will write between + * 0 - 10 points) + */ + iowrite8(RPI_TS_NPOINTS_REG_INVALIDATE, + ts->fw_regs_va + offsetof(struct rpi_ts_regs, num_points)); + + if (regs.num_points == RPI_TS_NPOINTS_REG_INVALIDATE || + (regs.num_points == 0 && ts->known_ids == 0)) + return; + + for (i = 0; i < regs.num_points; i++) { + x = (((int)regs.point[i].xh & 0xf) << 8) + regs.point[i].xl; + y = (((int)regs.point[i].yh & 0xf) << 8) + regs.point[i].yl; + touchid = (regs.point[i].yh >> 4) & 0xf; + event_type = (regs.point[i].xh >> 6) & 0x03; + + modified_ids |= BIT(touchid); + + if (event_type == RPI_TS_FTS_TOUCH_DOWN || + event_type == RPI_TS_FTS_TOUCH_CONTACT) { + input_mt_slot(input, touchid); + input_mt_report_slot_state(input, MT_TOOL_FINGER, 1); + touchscreen_report_pos(input, &ts->prop, x, y, true); + } + } + + released_ids = ts->known_ids & ~modified_ids; + for_each_set_bit(i, &released_ids, RPI_TS_MAX_SUPPORTED_POINTS) { + input_mt_slot(input, i); + input_mt_report_slot_state(input, MT_TOOL_FINGER, 0); + modified_ids &= ~(BIT(i)); + } + ts->known_ids = modified_ids; + + input_mt_sync_frame(input); + input_sync(input); +} + +static void rpi_ts_dma_cleanup(void *data) +{ + struct rpi_ts *ts = data; + struct device *dev = &ts->pdev->dev; + + dma_free_coherent(dev, PAGE_SIZE, ts->fw_regs_va, ts->fw_regs_phys); +} + +static int rpi_ts_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct input_polled_dev *poll_dev; + struct device_node *fw_node; + struct rpi_firmware *fw; + struct input_dev *input; + struct rpi_ts *ts; + u32 touchbuf; + int error; + + fw_node = of_get_parent(np); + if (!fw_node) { + dev_err(dev, "Missing firmware node\n"); + return -ENOENT; + } + + fw = rpi_firmware_get(fw_node); + of_node_put(fw_node); + if (!fw) + return -EPROBE_DEFER; + + ts = devm_kzalloc(dev, sizeof(*ts), GFP_KERNEL); + if (!ts) + return -ENOMEM; + ts->pdev = pdev; + + ts->fw_regs_va = dma_zalloc_coherent(dev, PAGE_SIZE, &ts->fw_regs_phys, + GFP_KERNEL); + if (!ts->fw_regs_va) { + dev_err(dev, "failed to dma_alloc_coherent\n"); + return -ENOMEM; + } + + error = devm_add_action_or_reset(dev, rpi_ts_dma_cleanup, ts); + if (error) { + dev_err(dev, "failed to devm_add_action_or_reset, %d\n", error); + return error; + } + + + touchbuf = (u32)ts->fw_regs_phys; + error = rpi_firmware_property(fw, RPI_FIRMWARE_FRAMEBUFFER_SET_TOUCHBUF, + &touchbuf, sizeof(touchbuf)); + + if (error || touchbuf != 0) { + dev_warn(dev, "Failed to set touchbuf, %d\n", error); + return error; + } + + poll_dev = devm_input_allocate_polled_device(dev); + if (!poll_dev) { + dev_err(dev, "Failed to allocate input device\n"); + return -ENOMEM; + } + ts->poll_dev = poll_dev; + input = poll_dev->input; + + input->name = "raspberrypi-ts"; + input->id.bustype = BUS_HOST; + poll_dev->poll_interval = RPI_TS_POLL_INTERVAL; + poll_dev->poll = rpi_ts_poll; + poll_dev->private = ts; + + input_set_abs_params(input, ABS_MT_POSITION_X, 0, + RPI_TS_DEFAULT_WIDTH, 0, 0); + input_set_abs_params(input, ABS_MT_POSITION_Y, 0, + RPI_TS_DEFAULT_HEIGHT, 0, 0); + touchscreen_parse_properties(input, true, &ts->prop); + + error = input_mt_init_slots(input, RPI_TS_MAX_SUPPORTED_POINTS, + INPUT_MT_DIRECT); + if (error) { + dev_err(dev, "could not init mt slots, %d\n", error); + return error; + } + + error = input_register_polled_device(poll_dev); + if (error) { + dev_err(dev, "could not register input device, %d\n", error); + return error; + } + + return 0; +} + +static const struct of_device_id rpi_ts_match[] = { + { .compatible = "raspberrypi,firmware-ts", }, + {}, +}; +MODULE_DEVICE_TABLE(of, rpi_ts_match); + +static struct platform_driver rpi_ts_driver = { + .driver = { + .name = "raspberrypi-ts", + .of_match_table = rpi_ts_match, + }, + .probe = rpi_ts_probe, +}; +module_platform_driver(rpi_ts_driver); + +MODULE_AUTHOR("Gordon Hollingworth"); +MODULE_AUTHOR("Nicolas Saenz Julienne <nsaenzjulienne@suse.de>"); +MODULE_DESCRIPTION("Raspberry Pi firmware based touchscreen driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 0ff517d3c98f..a4ceb61c5b60 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -852,7 +852,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf) u16 ret; if (contr == 0) { - strlcpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN); + strncpy(buf, capi_manufakturer, CAPI_MANUFACTURER_LEN); return CAPI_NOERROR; } @@ -860,7 +860,7 @@ u16 capi20_get_manufacturer(u32 contr, u8 *buf) ctr = get_capi_ctr_by_nr(contr); if (ctr && ctr->state == CAPI_CTR_RUNNING) { - strlcpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN); + strncpy(buf, ctr->manu, CAPI_MANUFACTURER_LEN); ret = CAPI_NOERROR; } else ret = CAPI_REGNOTINSTALLED; diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c index 5b719b561860..81dd465afcf4 100644 --- a/drivers/isdn/hisax/hfc_pci.c +++ b/drivers/isdn/hisax/hfc_pci.c @@ -1169,11 +1169,13 @@ HFCPCI_l1hw(struct PStack *st, int pr, void *arg) if (cs->debug & L1_DEB_LAPD) debugl1(cs, "-> PH_REQUEST_PULL"); #endif + spin_lock_irqsave(&cs->lock, flags); if (!cs->tx_skb) { test_and_clear_bit(FLG_L1_PULL_REQ, &st->l1.Flags); st->l1.l1l2(st, PH_PULL | CONFIRM, NULL); } else test_and_set_bit(FLG_L1_PULL_REQ, &st->l1.Flags); + spin_unlock_irqrestore(&cs->lock, flags); break; case (HW_RESET | REQUEST): spin_lock_irqsave(&cs->lock, flags); diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c index 3fcf062d752c..5ee20da7bdb3 100644 --- a/drivers/lightnvm/pblk-recovery.c +++ b/drivers/lightnvm/pblk-recovery.c @@ -418,7 +418,6 @@ retry_rq: if (ret) { pblk_err(pblk, "I/O submission failed: %d\n", ret); bio_put(bio); - bio_put(bio); return ret; } diff --git a/drivers/mailbox/arm_mhu.c b/drivers/mailbox/arm_mhu.c index 99befa76e37c..64d85c6a2bdf 100644 --- a/drivers/mailbox/arm_mhu.c +++ b/drivers/mailbox/arm_mhu.c @@ -152,7 +152,7 @@ static int mhu_probe(struct amba_device *adev, const struct amba_id *id) amba_set_drvdata(adev, mhu); - err = mbox_controller_register(&mhu->mbox); + err = devm_mbox_controller_register(dev, &mhu->mbox); if (err) { dev_err(dev, "Failed to register mailboxes %d\n", err); return err; @@ -162,15 +162,6 @@ static int mhu_probe(struct amba_device *adev, const struct amba_id *id) return 0; } -static int mhu_remove(struct amba_device *adev) -{ - struct arm_mhu *mhu = amba_get_drvdata(adev); - - mbox_controller_unregister(&mhu->mbox); - - return 0; -} - static struct amba_id mhu_ids[] = { { .id = 0x1bb098, @@ -186,7 +177,6 @@ static struct amba_driver arm_mhu_driver = { }, .id_table = mhu_ids, .probe = mhu_probe, - .remove = mhu_remove, }; module_amba_driver(arm_mhu_driver); diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index d7a8ed7d8097..d713271ebf7c 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1665,7 +1665,7 @@ skip_debugfs: mbox->controller.chans[index].con_priv = &mbox->rings[index]; /* Register mailbox controller */ - ret = mbox_controller_register(&mbox->controller); + ret = devm_mbox_controller_register(dev, &mbox->controller); if (ret) goto fail_free_debugfs_root; @@ -1691,8 +1691,6 @@ static int flexrm_mbox_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; struct flexrm_mbox *mbox = platform_get_drvdata(pdev); - mbox_controller_unregister(&mbox->controller); - debugfs_remove_recursive(mbox->root); platform_msi_domain_free_irqs(dev); diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c index 4fe7be0bdd11..ccf3d62af7e7 100644 --- a/drivers/mailbox/bcm-pdc-mailbox.c +++ b/drivers/mailbox/bcm-pdc-mailbox.c @@ -1471,7 +1471,7 @@ static int pdc_mb_init(struct pdc_state *pdcs) mbc->chans[chan_index].con_priv = pdcs; /* Register mailbox controller */ - err = mbox_controller_register(mbc); + err = devm_mbox_controller_register(dev, mbc); if (err) { dev_crit(dev, "Failed to register PDC mailbox controller. Error %d.", @@ -1641,8 +1641,6 @@ static int pdc_remove(struct platform_device *pdev) pdc_hw_disable(pdcs); - mbox_controller_unregister(&pdcs->mbc); - dma_pool_destroy(pdcs->rx_buf_pool); dma_pool_destroy(pdcs->ring_pool); return 0; diff --git a/drivers/mailbox/bcm2835-mailbox.c b/drivers/mailbox/bcm2835-mailbox.c index e92bbc533821..39761d190545 100644 --- a/drivers/mailbox/bcm2835-mailbox.c +++ b/drivers/mailbox/bcm2835-mailbox.c @@ -1,15 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010,2015 Broadcom * Copyright (C) 2013-2014 Lubomir Rintel * Copyright (C) 2013 Craig McGeachie * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This device provides a mechanism for writing to the mailboxes, - * that are shared between the ARM and the VideoCore processor - * * Parts of the driver are based on: * - arch/arm/mach-bcm2708/vcio.c file written by Gray Girling that was * obtained from branch "rpi-3.6.y" of git://github.com/raspberrypi/ @@ -178,7 +172,7 @@ static int bcm2835_mbox_probe(struct platform_device *pdev) if (!mbox->controller.chans) return -ENOMEM; - ret = mbox_controller_register(&mbox->controller); + ret = devm_mbox_controller_register(dev, &mbox->controller); if (ret) return ret; @@ -188,13 +182,6 @@ static int bcm2835_mbox_probe(struct platform_device *pdev) return ret; } -static int bcm2835_mbox_remove(struct platform_device *pdev) -{ - struct bcm2835_mbox *mbox = platform_get_drvdata(pdev); - mbox_controller_unregister(&mbox->controller); - return 0; -} - static const struct of_device_id bcm2835_mbox_of_match[] = { { .compatible = "brcm,bcm2835-mbox", }, {}, @@ -207,7 +194,6 @@ static struct platform_driver bcm2835_mbox_driver = { .of_match_table = bcm2835_mbox_of_match, }, .probe = bcm2835_mbox_probe, - .remove = bcm2835_mbox_remove, }; module_platform_driver(bcm2835_mbox_driver); diff --git a/drivers/mailbox/hi3660-mailbox.c b/drivers/mailbox/hi3660-mailbox.c index 3eea6b642484..53f4bc2488c5 100644 --- a/drivers/mailbox/hi3660-mailbox.c +++ b/drivers/mailbox/hi3660-mailbox.c @@ -38,6 +38,7 @@ #define MBOX_AUTOMATIC_ACK 1 #define MBOX_STATE_IDLE BIT(4) +#define MBOX_STATE_READY BIT(5) #define MBOX_STATE_ACK BIT(7) #define MBOX_MSG_LEN 8 @@ -91,8 +92,8 @@ static int hi3660_mbox_check_state(struct mbox_chan *chan) unsigned long val; unsigned int ret; - /* Mailbox is idle so directly bail out */ - if (readl(base + MBOX_MODE_REG) & MBOX_STATE_IDLE) + /* Mailbox is ready to use */ + if (readl(base + MBOX_MODE_REG) & MBOX_STATE_READY) return 0; /* Wait for acknowledge from remote */ @@ -103,9 +104,9 @@ static int hi3660_mbox_check_state(struct mbox_chan *chan) return ret; } - /* Ensure channel is released */ - writel(0xffffffff, base + MBOX_IMASK_REG); - writel(BIT(mchan->ack_irq), base + MBOX_SRC_REG); + /* clear ack state, mailbox will get back to ready state */ + writel(BIT(mchan->ack_irq), base + MBOX_ICLR_REG); + return 0; } @@ -160,10 +161,6 @@ static int hi3660_mbox_startup(struct mbox_chan *chan) { int ret; - ret = hi3660_mbox_check_state(chan); - if (ret) - return ret; - ret = hi3660_mbox_unlock(chan); if (ret) return ret; @@ -183,10 +180,11 @@ static int hi3660_mbox_send_data(struct mbox_chan *chan, void *msg) void __iomem *base = MBOX_BASE(mbox, ch); u32 *buf = msg; unsigned int i; + int ret; - /* Ensure channel is released */ - writel_relaxed(0xffffffff, base + MBOX_IMASK_REG); - writel_relaxed(BIT(mchan->ack_irq), base + MBOX_SRC_REG); + ret = hi3660_mbox_check_state(chan); + if (ret) + return ret; /* Clear mask for destination interrupt */ writel_relaxed(~BIT(mchan->dst_irq), base + MBOX_IMASK_REG); @@ -206,7 +204,7 @@ static int hi3660_mbox_send_data(struct mbox_chan *chan, void *msg) return 0; } -static struct mbox_chan_ops hi3660_mbox_ops = { +static const struct mbox_chan_ops hi3660_mbox_ops = { .startup = hi3660_mbox_startup, .send_data = hi3660_mbox_send_data, }; @@ -267,7 +265,7 @@ static int hi3660_mbox_probe(struct platform_device *pdev) for (ch = 0; ch < MBOX_CHAN_MAX; ch++) chan[ch].con_priv = (void *)ch; - err = mbox_controller_register(&mbox->controller); + err = devm_mbox_controller_register(dev, &mbox->controller); if (err) { dev_err(dev, "Failed to register mailbox %d\n", err); return err; @@ -278,17 +276,8 @@ static int hi3660_mbox_probe(struct platform_device *pdev) return 0; } -static int hi3660_mbox_remove(struct platform_device *pdev) -{ - struct hi3660_mbox *mbox = platform_get_drvdata(pdev); - - mbox_controller_unregister(&mbox->controller); - return 0; -} - static struct platform_driver hi3660_mbox_driver = { .probe = hi3660_mbox_probe, - .remove = hi3660_mbox_remove, .driver = { .name = "hi3660-mbox", .of_match_table = hi3660_mbox_of_match, diff --git a/drivers/mailbox/hi6220-mailbox.c b/drivers/mailbox/hi6220-mailbox.c index 4fa9803cd204..c32cbfaf223a 100644 --- a/drivers/mailbox/hi6220-mailbox.c +++ b/drivers/mailbox/hi6220-mailbox.c @@ -349,7 +349,7 @@ static int hi6220_mbox_probe(struct platform_device *pdev) mbox->controller.txpoll_period = 5; } - err = mbox_controller_register(&mbox->controller); + err = devm_mbox_controller_register(dev, &mbox->controller); if (err) { dev_err(dev, "Failed to register mailbox %d\n", err); return err; @@ -360,14 +360,6 @@ static int hi6220_mbox_probe(struct platform_device *pdev) return 0; } -static int hi6220_mbox_remove(struct platform_device *pdev) -{ - struct hi6220_mbox *mbox = platform_get_drvdata(pdev); - - mbox_controller_unregister(&mbox->controller); - return 0; -} - static struct platform_driver hi6220_mbox_driver = { .driver = { .name = "hi6220-mbox", @@ -375,7 +367,6 @@ static struct platform_driver hi6220_mbox_driver = { .of_match_table = hi6220_mbox_of_match, }, .probe = hi6220_mbox_probe, - .remove = hi6220_mbox_remove, }; static int __init hi6220_mbox_init(void) diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 363d35d5e49d..774362a05159 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -324,14 +324,13 @@ static int imx_mu_probe(struct platform_device *pdev) imx_mu_init_generic(priv); - return mbox_controller_register(&priv->mbox); + return devm_mbox_controller_register(dev, &priv->mbox); } static int imx_mu_remove(struct platform_device *pdev) { struct imx_mu_priv *priv = platform_get_drvdata(pdev); - mbox_controller_unregister(&priv->mbox); clk_disable_unprepare(priv->clk); return 0; diff --git a/drivers/mailbox/mailbox-altera.c b/drivers/mailbox/mailbox-altera.c index bcb29df9549e..397e25ddae29 100644 --- a/drivers/mailbox/mailbox-altera.c +++ b/drivers/mailbox/mailbox-altera.c @@ -341,7 +341,7 @@ static int altera_mbox_probe(struct platform_device *pdev) } } - ret = mbox_controller_register(&mbox->controller); + ret = devm_mbox_controller_register(&pdev->dev, &mbox->controller); if (ret) { dev_err(&pdev->dev, "Register mailbox failed\n"); goto err; @@ -352,18 +352,6 @@ err: return ret; } -static int altera_mbox_remove(struct platform_device *pdev) -{ - struct altera_mbox *mbox = platform_get_drvdata(pdev); - - if (!mbox) - return -EINVAL; - - mbox_controller_unregister(&mbox->controller); - - return 0; -} - static const struct of_device_id altera_mbox_match[] = { { .compatible = "altr,mailbox-1.0" }, { /* Sentinel */ } @@ -373,7 +361,6 @@ MODULE_DEVICE_TABLE(of, altera_mbox_match); static struct platform_driver altera_mbox_driver = { .probe = altera_mbox_probe, - .remove = altera_mbox_remove, .driver = { .name = DRIVER_NAME, .of_match_table = altera_mbox_match, diff --git a/drivers/mailbox/mailbox-sti.c b/drivers/mailbox/mailbox-sti.c index 779d41262ef0..adf82b85dbb2 100644 --- a/drivers/mailbox/mailbox-sti.c +++ b/drivers/mailbox/mailbox-sti.c @@ -462,7 +462,7 @@ static int sti_mbox_probe(struct platform_device *pdev) mbox->chans = chans; mbox->num_chans = STI_MBOX_CHAN_MAX; - ret = mbox_controller_register(mbox); + ret = devm_mbox_controller_register(&pdev->dev, mbox); if (ret) return ret; @@ -480,7 +480,6 @@ static int sti_mbox_probe(struct platform_device *pdev) IRQF_ONESHOT, mdev->name, mdev); if (ret) { dev_err(&pdev->dev, "Can't claim IRQ %d\n", irq); - mbox_controller_unregister(mbox); return -EINVAL; } @@ -489,18 +488,8 @@ static int sti_mbox_probe(struct platform_device *pdev) return 0; } -static int sti_mbox_remove(struct platform_device *pdev) -{ - struct sti_mbox_device *mdev = platform_get_drvdata(pdev); - - mbox_controller_unregister(mdev->mbox); - - return 0; -} - static struct platform_driver sti_mbox_driver = { .probe = sti_mbox_probe, - .remove = sti_mbox_remove, .driver = { .name = "sti-mailbox", .of_match_table = sti_mailbox_match, diff --git a/drivers/mailbox/mailbox-xgene-slimpro.c b/drivers/mailbox/mailbox-xgene-slimpro.c index b8b2b3533f46..8f397da1150b 100644 --- a/drivers/mailbox/mailbox-xgene-slimpro.c +++ b/drivers/mailbox/mailbox-xgene-slimpro.c @@ -224,7 +224,7 @@ static int slimpro_mbox_probe(struct platform_device *pdev) ctx->mb_ctrl.ops = &slimpro_mbox_ops; ctx->mb_ctrl.num_chans = i; - rc = mbox_controller_register(&ctx->mb_ctrl); + rc = devm_mbox_controller_register(&pdev->dev, &ctx->mb_ctrl); if (rc) { dev_err(&pdev->dev, "APM X-Gene SLIMpro MailBox register failed:%d\n", rc); @@ -235,14 +235,6 @@ static int slimpro_mbox_probe(struct platform_device *pdev) return 0; } -static int slimpro_mbox_remove(struct platform_device *pdev) -{ - struct slimpro_mbox *smb = platform_get_drvdata(pdev); - - mbox_controller_unregister(&smb->mb_ctrl); - return 0; -} - static const struct of_device_id slimpro_of_match[] = { {.compatible = "apm,xgene-slimpro-mbox" }, { }, @@ -259,7 +251,6 @@ MODULE_DEVICE_TABLE(acpi, slimpro_acpi_ids); static struct platform_driver slimpro_mbox_driver = { .probe = slimpro_mbox_probe, - .remove = slimpro_mbox_remove, .driver = { .name = "xgene-slimpro-mbox", .of_match_table = of_match_ptr(slimpro_of_match), diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 674b35f402f5..c6a7d4582dc6 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -284,6 +284,34 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg) EXPORT_SYMBOL_GPL(mbox_send_message); /** + * mbox_flush - flush a mailbox channel + * @chan: mailbox channel to flush + * @timeout: time, in milliseconds, to allow the flush operation to succeed + * + * Mailbox controllers that need to work in atomic context can implement the + * ->flush() callback to busy loop until a transmission has been completed. + * The implementation must call mbox_chan_txdone() upon success. Clients can + * call the mbox_flush() function at any time after mbox_send_message() to + * flush the transmission. After the function returns success, the mailbox + * transmission is guaranteed to have completed. + * + * Returns: 0 on success or a negative error code on failure. + */ +int mbox_flush(struct mbox_chan *chan, unsigned long timeout) +{ + int ret; + + if (!chan->mbox->ops->flush) + return -ENOTSUPP; + + ret = chan->mbox->ops->flush(chan, timeout); + if (ret < 0) + tx_tick(chan, ret); + + return ret; +} + +/** * mbox_request_channel - Request a mailbox channel. * @cl: Identity of the client requesting the channel. * @index: Index of mailbox specifier in 'mboxes' property. @@ -327,7 +355,8 @@ struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index) list_for_each_entry(mbox, &mbox_cons, node) if (mbox->dev->of_node == spec.np) { chan = mbox->of_xlate(mbox, &spec); - break; + if (!IS_ERR(chan)) + break; } of_node_put(spec.np); @@ -515,3 +544,73 @@ void mbox_controller_unregister(struct mbox_controller *mbox) mutex_unlock(&con_mutex); } EXPORT_SYMBOL_GPL(mbox_controller_unregister); + +static void __devm_mbox_controller_unregister(struct device *dev, void *res) +{ + struct mbox_controller **mbox = res; + + mbox_controller_unregister(*mbox); +} + +static int devm_mbox_controller_match(struct device *dev, void *res, void *data) +{ + struct mbox_controller **mbox = res; + + if (WARN_ON(!mbox || !*mbox)) + return 0; + + return *mbox == data; +} + +/** + * devm_mbox_controller_register() - managed mbox_controller_register() + * @dev: device owning the mailbox controller being registered + * @mbox: mailbox controller being registered + * + * This function adds a device-managed resource that will make sure that the + * mailbox controller, which is registered using mbox_controller_register() + * as part of this function, will be unregistered along with the rest of + * device-managed resources upon driver probe failure or driver removal. + * + * Returns 0 on success or a negative error code on failure. + */ +int devm_mbox_controller_register(struct device *dev, + struct mbox_controller *mbox) +{ + struct mbox_controller **ptr; + int err; + + ptr = devres_alloc(__devm_mbox_controller_unregister, sizeof(*ptr), + GFP_KERNEL); + if (!ptr) + return -ENOMEM; + + err = mbox_controller_register(mbox); + if (err < 0) { + devres_free(ptr); + return err; + } + + devres_add(dev, ptr); + *ptr = mbox; + + return 0; +} +EXPORT_SYMBOL_GPL(devm_mbox_controller_register); + +/** + * devm_mbox_controller_unregister() - managed mbox_controller_unregister() + * @dev: device owning the mailbox controller being unregistered + * @mbox: mailbox controller being unregistered + * + * This function unregisters the mailbox controller and removes the device- + * managed resource that was set up to automatically unregister the mailbox + * controller on driver probe failure or driver removal. It's typically not + * necessary to call this function. + */ +void devm_mbox_controller_unregister(struct device *dev, struct mbox_controller *mbox) +{ + WARN_ON(devres_release(dev, __devm_mbox_controller_unregister, + devm_mbox_controller_match, mbox)); +} +EXPORT_SYMBOL_GPL(devm_mbox_controller_unregister); diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c index f7cc29c00302..22811784dc7d 100644 --- a/drivers/mailbox/mtk-cmdq-mailbox.c +++ b/drivers/mailbox/mtk-cmdq-mailbox.c @@ -337,17 +337,8 @@ static int cmdq_remove(struct platform_device *pdev) { struct cmdq *cmdq = platform_get_drvdata(pdev); - mbox_controller_unregister(&cmdq->mbox); clk_unprepare(cmdq->clock); - if (cmdq->mbox.chans) - devm_kfree(&pdev->dev, cmdq->mbox.chans); - - if (cmdq->thread) - devm_kfree(&pdev->dev, cmdq->thread); - - devm_kfree(&pdev->dev, cmdq); - return 0; } @@ -524,7 +515,7 @@ static int cmdq_probe(struct platform_device *pdev) cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i]; } - err = mbox_controller_register(&cmdq->mbox); + err = devm_mbox_controller_register(dev, &cmdq->mbox); if (err < 0) { dev_err(dev, "failed to register mailbox: %d\n", err); return err; diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c index db66e952a871..ca50177a33f2 100644 --- a/drivers/mailbox/omap-mailbox.c +++ b/drivers/mailbox/omap-mailbox.c @@ -486,7 +486,7 @@ static int omap_mbox_register(struct omap_mbox_device *mdev) list_add(&mdev->elem, &omap_mbox_devices); mutex_unlock(&omap_mbox_devices_lock); - ret = mbox_controller_register(&mdev->controller); + ret = devm_mbox_controller_register(mdev->dev, &mdev->controller); err_out: if (ret) { @@ -508,8 +508,6 @@ static int omap_mbox_unregister(struct omap_mbox_device *mdev) list_del(&mdev->elem); mutex_unlock(&omap_mbox_devices_lock); - mbox_controller_unregister(&mdev->controller); - mboxes = mdev->mboxes; for (i = 0; mboxes[i]; i++) device_unregister(mboxes[i]->dev); diff --git a/drivers/mailbox/platform_mhu.c b/drivers/mailbox/platform_mhu.c index e13201a5cec6..d2502c5be130 100644 --- a/drivers/mailbox/platform_mhu.c +++ b/drivers/mailbox/platform_mhu.c @@ -163,7 +163,7 @@ static int platform_mhu_probe(struct platform_device *pdev) platform_set_drvdata(pdev, mhu); - err = mbox_controller_register(&mhu->mbox); + err = devm_mbox_controller_register(dev, &mhu->mbox); if (err) { dev_err(dev, "Failed to register mailboxes %d\n", err); return err; @@ -173,15 +173,6 @@ static int platform_mhu_probe(struct platform_device *pdev) return 0; } -static int platform_mhu_remove(struct platform_device *pdev) -{ - struct platform_mhu *mhu = platform_get_drvdata(pdev); - - mbox_controller_unregister(&mhu->mbox); - - return 0; -} - static const struct of_device_id platform_mhu_dt_ids[] = { { .compatible = "amlogic,meson-gxbb-mhu", }, { /* sentinel */ }, @@ -190,7 +181,6 @@ MODULE_DEVICE_TABLE(of, platform_mhu_dt_ids); static struct platform_driver platform_mhu_driver = { .probe = platform_mhu_probe, - .remove = platform_mhu_remove, .driver = { .name = "platform-mhu", .of_match_table = platform_mhu_dt_ids, diff --git a/drivers/mailbox/qcom-apcs-ipc-mailbox.c b/drivers/mailbox/qcom-apcs-ipc-mailbox.c index aed23ac9550d..3cf2937be149 100644 --- a/drivers/mailbox/qcom-apcs-ipc-mailbox.c +++ b/drivers/mailbox/qcom-apcs-ipc-mailbox.c @@ -91,7 +91,7 @@ static int qcom_apcs_ipc_probe(struct platform_device *pdev) apcs->mbox.chans = apcs->mbox_chans; apcs->mbox.num_chans = ARRAY_SIZE(apcs->mbox_chans); - ret = mbox_controller_register(&apcs->mbox); + ret = devm_mbox_controller_register(&pdev->dev, &apcs->mbox); if (ret) { dev_err(&pdev->dev, "failed to register APCS IPC controller\n"); return ret; @@ -115,7 +115,6 @@ static int qcom_apcs_ipc_remove(struct platform_device *pdev) struct qcom_apcs_ipc *apcs = platform_get_drvdata(pdev); struct platform_device *clk = apcs->clk; - mbox_controller_unregister(&apcs->mbox); platform_device_unregister(clk); return 0; diff --git a/drivers/mailbox/rockchip-mailbox.c b/drivers/mailbox/rockchip-mailbox.c index d702a204f5c1..f24a77b1a0ff 100644 --- a/drivers/mailbox/rockchip-mailbox.c +++ b/drivers/mailbox/rockchip-mailbox.c @@ -247,28 +247,15 @@ static int rockchip_mbox_probe(struct platform_device *pdev) mb->chans[i].msg = NULL; } - ret = mbox_controller_register(&mb->mbox); + ret = devm_mbox_controller_register(&pdev->dev, &mb->mbox); if (ret < 0) dev_err(&pdev->dev, "Failed to register mailbox: %d\n", ret); return ret; } -static int rockchip_mbox_remove(struct platform_device *pdev) -{ - struct rockchip_mbox *mb = platform_get_drvdata(pdev); - - if (!mb) - return -EINVAL; - - mbox_controller_unregister(&mb->mbox); - - return 0; -} - static struct platform_driver rockchip_mbox_driver = { .probe = rockchip_mbox_probe, - .remove = rockchip_mbox_remove, .driver = { .name = "rockchip-mailbox", .of_match_table = of_match_ptr(rockchip_mbox_of_match), diff --git a/drivers/mailbox/stm32-ipcc.c b/drivers/mailbox/stm32-ipcc.c index 533b0da5235d..a338bd4cd7db 100644 --- a/drivers/mailbox/stm32-ipcc.c +++ b/drivers/mailbox/stm32-ipcc.c @@ -299,7 +299,7 @@ static int stm32_ipcc_probe(struct platform_device *pdev) for (i = 0; i < ipcc->controller.num_chans; i++) ipcc->controller.chans[i].con_priv = (void *)i; - ret = mbox_controller_register(&ipcc->controller); + ret = devm_mbox_controller_register(dev, &ipcc->controller); if (ret) goto err_irq_wkp; @@ -329,8 +329,6 @@ static int stm32_ipcc_remove(struct platform_device *pdev) { struct stm32_ipcc *ipcc = platform_get_drvdata(pdev); - mbox_controller_unregister(&ipcc->controller); - if (ipcc->wkp) dev_pm_clear_wake_irq(&pdev->dev); diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c index 0cde356c11ab..e443f6a2ec4b 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2016-2018, NVIDIA CORPORATION. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -11,16 +11,29 @@ * more details. */ +#include <linux/delay.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/mailbox_controller.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/pm.h> #include <linux/slab.h> #include <dt-bindings/mailbox/tegra186-hsp.h> +#include "mailbox.h" + +#define HSP_INT_IE(x) (0x100 + ((x) * 4)) +#define HSP_INT_IV 0x300 +#define HSP_INT_IR 0x304 + +#define HSP_INT_EMPTY_SHIFT 0 +#define HSP_INT_EMPTY_MASK 0xff +#define HSP_INT_FULL_SHIFT 8 +#define HSP_INT_FULL_MASK 0xff + #define HSP_INT_DIMENSIONING 0x380 #define HSP_nSM_SHIFT 0 #define HSP_nSS_SHIFT 4 @@ -34,6 +47,11 @@ #define HSP_DB_RAW 0x8 #define HSP_DB_PENDING 0xc +#define HSP_SM_SHRD_MBOX 0x0 +#define HSP_SM_SHRD_MBOX_FULL BIT(31) +#define HSP_SM_SHRD_MBOX_FULL_INT_IE 0x04 +#define HSP_SM_SHRD_MBOX_EMPTY_INT_IE 0x08 + #define HSP_DB_CCPLEX 1 #define HSP_DB_BPMP 3 #define HSP_DB_MAX 7 @@ -55,6 +73,12 @@ struct tegra_hsp_doorbell { unsigned int index; }; +struct tegra_hsp_mailbox { + struct tegra_hsp_channel channel; + unsigned int index; + bool producer; +}; + struct tegra_hsp_db_map { const char *name; unsigned int master; @@ -63,13 +87,18 @@ struct tegra_hsp_db_map { struct tegra_hsp_soc { const struct tegra_hsp_db_map *map; + bool has_per_mb_ie; }; struct tegra_hsp { + struct device *dev; const struct tegra_hsp_soc *soc; - struct mbox_controller mbox; + struct mbox_controller mbox_db; + struct mbox_controller mbox_sm; void __iomem *regs; - unsigned int irq; + unsigned int doorbell_irq; + unsigned int *shared_irqs; + unsigned int shared_irq; unsigned int num_sm; unsigned int num_as; unsigned int num_ss; @@ -78,13 +107,10 @@ struct tegra_hsp { spinlock_t lock; struct list_head doorbells; -}; + struct tegra_hsp_mailbox *mailboxes; -static inline struct tegra_hsp * -to_tegra_hsp(struct mbox_controller *mbox) -{ - return container_of(mbox, struct tegra_hsp, mbox); -} + unsigned long mask; +}; static inline u32 tegra_hsp_readl(struct tegra_hsp *hsp, unsigned int offset) { @@ -158,7 +184,7 @@ static irqreturn_t tegra_hsp_doorbell_irq(int irq, void *data) spin_lock(&hsp->lock); - for_each_set_bit(master, &value, hsp->mbox.num_chans) { + for_each_set_bit(master, &value, hsp->mbox_db.num_chans) { struct tegra_hsp_doorbell *db; db = __tegra_hsp_doorbell_get(hsp, master); @@ -182,6 +208,71 @@ static irqreturn_t tegra_hsp_doorbell_irq(int irq, void *data) return IRQ_HANDLED; } +static irqreturn_t tegra_hsp_shared_irq(int irq, void *data) +{ + struct tegra_hsp *hsp = data; + unsigned long bit, mask; + u32 status, value; + void *msg; + + status = tegra_hsp_readl(hsp, HSP_INT_IR) & hsp->mask; + + /* process EMPTY interrupts first */ + mask = (status >> HSP_INT_EMPTY_SHIFT) & HSP_INT_EMPTY_MASK; + + for_each_set_bit(bit, &mask, hsp->num_sm) { + struct tegra_hsp_mailbox *mb = &hsp->mailboxes[bit]; + + if (mb->producer) { + /* + * Disable EMPTY interrupts until data is sent with + * the next message. These interrupts are level- + * triggered, so if we kept them enabled they would + * constantly trigger until we next write data into + * the message. + */ + spin_lock(&hsp->lock); + + hsp->mask &= ~BIT(HSP_INT_EMPTY_SHIFT + mb->index); + tegra_hsp_writel(hsp, hsp->mask, + HSP_INT_IE(hsp->shared_irq)); + + spin_unlock(&hsp->lock); + + mbox_chan_txdone(mb->channel.chan, 0); + } + } + + /* process FULL interrupts */ + mask = (status >> HSP_INT_FULL_SHIFT) & HSP_INT_FULL_MASK; + + for_each_set_bit(bit, &mask, hsp->num_sm) { + struct tegra_hsp_mailbox *mb = &hsp->mailboxes[bit]; + + if (!mb->producer) { + value = tegra_hsp_channel_readl(&mb->channel, + HSP_SM_SHRD_MBOX); + value &= ~HSP_SM_SHRD_MBOX_FULL; + msg = (void *)(unsigned long)value; + mbox_chan_received_data(mb->channel.chan, msg); + + /* + * Need to clear all bits here since some producers, + * such as TCU, depend on fields in the register + * getting cleared by the consumer. + * + * The mailbox API doesn't give the consumers a way + * of doing that explicitly, so we have to make sure + * we cover all possible cases. + */ + tegra_hsp_channel_writel(&mb->channel, 0x0, + HSP_SM_SHRD_MBOX); + } + } + + return IRQ_HANDLED; +} + static struct tegra_hsp_channel * tegra_hsp_doorbell_create(struct tegra_hsp *hsp, const char *name, unsigned int master, unsigned int index) @@ -190,17 +281,17 @@ tegra_hsp_doorbell_create(struct tegra_hsp *hsp, const char *name, unsigned int offset; unsigned long flags; - db = kzalloc(sizeof(*db), GFP_KERNEL); + db = devm_kzalloc(hsp->dev, sizeof(*db), GFP_KERNEL); if (!db) return ERR_PTR(-ENOMEM); - offset = (1 + (hsp->num_sm / 2) + hsp->num_ss + hsp->num_as) << 16; + offset = (1 + (hsp->num_sm / 2) + hsp->num_ss + hsp->num_as) * SZ_64K; offset += index * 0x100; db->channel.regs = hsp->regs + offset; db->channel.hsp = hsp; - db->name = kstrdup_const(name, GFP_KERNEL); + db->name = devm_kstrdup_const(hsp->dev, name, GFP_KERNEL); db->master = master; db->index = index; @@ -211,13 +302,6 @@ tegra_hsp_doorbell_create(struct tegra_hsp *hsp, const char *name, return &db->channel; } -static void __tegra_hsp_doorbell_destroy(struct tegra_hsp_doorbell *db) -{ - list_del(&db->list); - kfree_const(db->name); - kfree(db); -} - static int tegra_hsp_doorbell_send_data(struct mbox_chan *chan, void *data) { struct tegra_hsp_doorbell *db = chan->con_priv; @@ -235,8 +319,8 @@ static int tegra_hsp_doorbell_startup(struct mbox_chan *chan) unsigned long flags; u32 value; - if (db->master >= hsp->mbox.num_chans) { - dev_err(hsp->mbox.dev, + if (db->master >= chan->mbox->num_chans) { + dev_err(chan->mbox->dev, "invalid master ID %u for HSP channel\n", db->master); return -EINVAL; @@ -281,46 +365,167 @@ static void tegra_hsp_doorbell_shutdown(struct mbox_chan *chan) spin_unlock_irqrestore(&hsp->lock, flags); } -static const struct mbox_chan_ops tegra_hsp_doorbell_ops = { +static const struct mbox_chan_ops tegra_hsp_db_ops = { .send_data = tegra_hsp_doorbell_send_data, .startup = tegra_hsp_doorbell_startup, .shutdown = tegra_hsp_doorbell_shutdown, }; -static struct mbox_chan *of_tegra_hsp_xlate(struct mbox_controller *mbox, +static int tegra_hsp_mailbox_send_data(struct mbox_chan *chan, void *data) +{ + struct tegra_hsp_mailbox *mb = chan->con_priv; + struct tegra_hsp *hsp = mb->channel.hsp; + unsigned long flags; + u32 value; + + if (WARN_ON(!mb->producer)) + return -EPERM; + + /* copy data and mark mailbox full */ + value = (u32)(unsigned long)data; + value |= HSP_SM_SHRD_MBOX_FULL; + + tegra_hsp_channel_writel(&mb->channel, value, HSP_SM_SHRD_MBOX); + + /* enable EMPTY interrupt for the shared mailbox */ + spin_lock_irqsave(&hsp->lock, flags); + + hsp->mask |= BIT(HSP_INT_EMPTY_SHIFT + mb->index); + tegra_hsp_writel(hsp, hsp->mask, HSP_INT_IE(hsp->shared_irq)); + + spin_unlock_irqrestore(&hsp->lock, flags); + + return 0; +} + +static int tegra_hsp_mailbox_flush(struct mbox_chan *chan, + unsigned long timeout) +{ + struct tegra_hsp_mailbox *mb = chan->con_priv; + struct tegra_hsp_channel *ch = &mb->channel; + u32 value; + + timeout = jiffies + msecs_to_jiffies(timeout); + + while (time_before(jiffies, timeout)) { + value = tegra_hsp_channel_readl(ch, HSP_SM_SHRD_MBOX); + if ((value & HSP_SM_SHRD_MBOX_FULL) == 0) { + mbox_chan_txdone(chan, 0); + return 0; + } + + udelay(1); + } + + return -ETIME; +} + +static int tegra_hsp_mailbox_startup(struct mbox_chan *chan) +{ + struct tegra_hsp_mailbox *mb = chan->con_priv; + struct tegra_hsp_channel *ch = &mb->channel; + struct tegra_hsp *hsp = mb->channel.hsp; + unsigned long flags; + + chan->txdone_method = TXDONE_BY_IRQ; + + /* + * Shared mailboxes start out as consumers by default. FULL and EMPTY + * interrupts are coalesced at the same shared interrupt. + * + * Keep EMPTY interrupts disabled at startup and only enable them when + * the mailbox is actually full. This is required because the FULL and + * EMPTY interrupts are level-triggered, so keeping EMPTY interrupts + * enabled all the time would cause an interrupt storm while mailboxes + * are idle. + */ + + spin_lock_irqsave(&hsp->lock, flags); + + if (mb->producer) + hsp->mask &= ~BIT(HSP_INT_EMPTY_SHIFT + mb->index); + else + hsp->mask |= BIT(HSP_INT_FULL_SHIFT + mb->index); + + tegra_hsp_writel(hsp, hsp->mask, HSP_INT_IE(hsp->shared_irq)); + + spin_unlock_irqrestore(&hsp->lock, flags); + + if (hsp->soc->has_per_mb_ie) { + if (mb->producer) + tegra_hsp_channel_writel(ch, 0x0, + HSP_SM_SHRD_MBOX_EMPTY_INT_IE); + else + tegra_hsp_channel_writel(ch, 0x1, + HSP_SM_SHRD_MBOX_FULL_INT_IE); + } + + return 0; +} + +static void tegra_hsp_mailbox_shutdown(struct mbox_chan *chan) +{ + struct tegra_hsp_mailbox *mb = chan->con_priv; + struct tegra_hsp_channel *ch = &mb->channel; + struct tegra_hsp *hsp = mb->channel.hsp; + unsigned long flags; + + if (hsp->soc->has_per_mb_ie) { + if (mb->producer) + tegra_hsp_channel_writel(ch, 0x0, + HSP_SM_SHRD_MBOX_EMPTY_INT_IE); + else + tegra_hsp_channel_writel(ch, 0x0, + HSP_SM_SHRD_MBOX_FULL_INT_IE); + } + + spin_lock_irqsave(&hsp->lock, flags); + + if (mb->producer) + hsp->mask &= ~BIT(HSP_INT_EMPTY_SHIFT + mb->index); + else + hsp->mask &= ~BIT(HSP_INT_FULL_SHIFT + mb->index); + + tegra_hsp_writel(hsp, hsp->mask, HSP_INT_IE(hsp->shared_irq)); + + spin_unlock_irqrestore(&hsp->lock, flags); +} + +static const struct mbox_chan_ops tegra_hsp_sm_ops = { + .send_data = tegra_hsp_mailbox_send_data, + .flush = tegra_hsp_mailbox_flush, + .startup = tegra_hsp_mailbox_startup, + .shutdown = tegra_hsp_mailbox_shutdown, +}; + +static struct mbox_chan *tegra_hsp_db_xlate(struct mbox_controller *mbox, const struct of_phandle_args *args) { + struct tegra_hsp *hsp = container_of(mbox, struct tegra_hsp, mbox_db); + unsigned int type = args->args[0], master = args->args[1]; struct tegra_hsp_channel *channel = ERR_PTR(-ENODEV); - struct tegra_hsp *hsp = to_tegra_hsp(mbox); - unsigned int type = args->args[0]; - unsigned int master = args->args[1]; struct tegra_hsp_doorbell *db; struct mbox_chan *chan; unsigned long flags; unsigned int i; - switch (type) { - case TEGRA_HSP_MBOX_TYPE_DB: - db = tegra_hsp_doorbell_get(hsp, master); - if (db) - channel = &db->channel; - - break; + if (type != TEGRA_HSP_MBOX_TYPE_DB || !hsp->doorbell_irq) + return ERR_PTR(-ENODEV); - default: - break; - } + db = tegra_hsp_doorbell_get(hsp, master); + if (db) + channel = &db->channel; if (IS_ERR(channel)) return ERR_CAST(channel); spin_lock_irqsave(&hsp->lock, flags); - for (i = 0; i < hsp->mbox.num_chans; i++) { - chan = &hsp->mbox.chans[i]; + for (i = 0; i < mbox->num_chans; i++) { + chan = &mbox->chans[i]; if (!chan->con_priv) { - chan->con_priv = channel; channel->chan = chan; + chan->con_priv = db; break; } @@ -332,17 +537,27 @@ static struct mbox_chan *of_tegra_hsp_xlate(struct mbox_controller *mbox, return chan ?: ERR_PTR(-EBUSY); } -static void tegra_hsp_remove_doorbells(struct tegra_hsp *hsp) +static struct mbox_chan *tegra_hsp_sm_xlate(struct mbox_controller *mbox, + const struct of_phandle_args *args) { - struct tegra_hsp_doorbell *db, *tmp; - unsigned long flags; + struct tegra_hsp *hsp = container_of(mbox, struct tegra_hsp, mbox_sm); + unsigned int type = args->args[0], index; + struct tegra_hsp_mailbox *mb; - spin_lock_irqsave(&hsp->lock, flags); + index = args->args[1] & TEGRA_HSP_SM_MASK; - list_for_each_entry_safe(db, tmp, &hsp->doorbells, list) - __tegra_hsp_doorbell_destroy(db); + if (type != TEGRA_HSP_MBOX_TYPE_SM || !hsp->shared_irqs || + index >= hsp->num_sm) + return ERR_PTR(-ENODEV); - spin_unlock_irqrestore(&hsp->lock, flags); + mb = &hsp->mailboxes[index]; + + if ((args->args[1] & TEGRA_HSP_SM_FLAG_TX) == 0) + mb->producer = false; + else + mb->producer = true; + + return mb->channel.chan; } static int tegra_hsp_add_doorbells(struct tegra_hsp *hsp) @@ -353,10 +568,8 @@ static int tegra_hsp_add_doorbells(struct tegra_hsp *hsp) while (map->name) { channel = tegra_hsp_doorbell_create(hsp, map->name, map->master, map->index); - if (IS_ERR(channel)) { - tegra_hsp_remove_doorbells(hsp); + if (IS_ERR(channel)) return PTR_ERR(channel); - } map++; } @@ -364,10 +577,70 @@ static int tegra_hsp_add_doorbells(struct tegra_hsp *hsp) return 0; } +static int tegra_hsp_add_mailboxes(struct tegra_hsp *hsp, struct device *dev) +{ + int i; + + hsp->mailboxes = devm_kcalloc(dev, hsp->num_sm, sizeof(*hsp->mailboxes), + GFP_KERNEL); + if (!hsp->mailboxes) + return -ENOMEM; + + for (i = 0; i < hsp->num_sm; i++) { + struct tegra_hsp_mailbox *mb = &hsp->mailboxes[i]; + + mb->index = i; + + mb->channel.hsp = hsp; + mb->channel.regs = hsp->regs + SZ_64K + i * SZ_32K; + mb->channel.chan = &hsp->mbox_sm.chans[i]; + mb->channel.chan->con_priv = mb; + } + + return 0; +} + +static int tegra_hsp_request_shared_irq(struct tegra_hsp *hsp) +{ + unsigned int i, irq = 0; + int err; + + for (i = 0; i < hsp->num_si; i++) { + irq = hsp->shared_irqs[i]; + if (irq <= 0) + continue; + + err = devm_request_irq(hsp->dev, irq, tegra_hsp_shared_irq, 0, + dev_name(hsp->dev), hsp); + if (err < 0) { + dev_err(hsp->dev, "failed to request interrupt: %d\n", + err); + continue; + } + + hsp->shared_irq = i; + + /* disable all interrupts */ + tegra_hsp_writel(hsp, 0, HSP_INT_IE(hsp->shared_irq)); + + dev_dbg(hsp->dev, "interrupt requested: %u\n", irq); + + break; + } + + if (i == hsp->num_si) { + dev_err(hsp->dev, "failed to find available interrupt\n"); + return -ENOENT; + } + + return 0; +} + static int tegra_hsp_probe(struct platform_device *pdev) { struct tegra_hsp *hsp; struct resource *res; + unsigned int i; u32 value; int err; @@ -375,6 +648,7 @@ static int tegra_hsp_probe(struct platform_device *pdev) if (!hsp) return -ENOMEM; + hsp->dev = &pdev->dev; hsp->soc = of_device_get_match_data(&pdev->dev); INIT_LIST_HEAD(&hsp->doorbells); spin_lock_init(&hsp->lock); @@ -392,62 +666,136 @@ static int tegra_hsp_probe(struct platform_device *pdev) hsp->num_si = (value >> HSP_nSI_SHIFT) & HSP_nINT_MASK; err = platform_get_irq_byname(pdev, "doorbell"); + if (err >= 0) + hsp->doorbell_irq = err; + + if (hsp->num_si > 0) { + unsigned int count = 0; + + hsp->shared_irqs = devm_kcalloc(&pdev->dev, hsp->num_si, + sizeof(*hsp->shared_irqs), + GFP_KERNEL); + if (!hsp->shared_irqs) + return -ENOMEM; + + for (i = 0; i < hsp->num_si; i++) { + char *name; + + name = kasprintf(GFP_KERNEL, "shared%u", i); + if (!name) + return -ENOMEM; + + err = platform_get_irq_byname(pdev, name); + if (err >= 0) { + hsp->shared_irqs[i] = err; + count++; + } + + kfree(name); + } + + if (count == 0) { + devm_kfree(&pdev->dev, hsp->shared_irqs); + hsp->shared_irqs = NULL; + } + } + + /* setup the doorbell controller */ + hsp->mbox_db.of_xlate = tegra_hsp_db_xlate; + hsp->mbox_db.num_chans = 32; + hsp->mbox_db.dev = &pdev->dev; + hsp->mbox_db.ops = &tegra_hsp_db_ops; + + hsp->mbox_db.chans = devm_kcalloc(&pdev->dev, hsp->mbox_db.num_chans, + sizeof(*hsp->mbox_db.chans), + GFP_KERNEL); + if (!hsp->mbox_db.chans) + return -ENOMEM; + + if (hsp->doorbell_irq) { + err = tegra_hsp_add_doorbells(hsp); + if (err < 0) { + dev_err(&pdev->dev, "failed to add doorbells: %d\n", + err); + return err; + } + } + + err = devm_mbox_controller_register(&pdev->dev, &hsp->mbox_db); if (err < 0) { - dev_err(&pdev->dev, "failed to get doorbell IRQ: %d\n", err); + dev_err(&pdev->dev, "failed to register doorbell mailbox: %d\n", + err); return err; } - hsp->irq = err; - - hsp->mbox.of_xlate = of_tegra_hsp_xlate; - hsp->mbox.num_chans = 32; - hsp->mbox.dev = &pdev->dev; - hsp->mbox.txdone_irq = false; - hsp->mbox.txdone_poll = false; - hsp->mbox.ops = &tegra_hsp_doorbell_ops; + /* setup the shared mailbox controller */ + hsp->mbox_sm.of_xlate = tegra_hsp_sm_xlate; + hsp->mbox_sm.num_chans = hsp->num_sm; + hsp->mbox_sm.dev = &pdev->dev; + hsp->mbox_sm.ops = &tegra_hsp_sm_ops; - hsp->mbox.chans = devm_kcalloc(&pdev->dev, hsp->mbox.num_chans, - sizeof(*hsp->mbox.chans), - GFP_KERNEL); - if (!hsp->mbox.chans) + hsp->mbox_sm.chans = devm_kcalloc(&pdev->dev, hsp->mbox_sm.num_chans, + sizeof(*hsp->mbox_sm.chans), + GFP_KERNEL); + if (!hsp->mbox_sm.chans) return -ENOMEM; - err = tegra_hsp_add_doorbells(hsp); + if (hsp->shared_irqs) { + err = tegra_hsp_add_mailboxes(hsp, &pdev->dev); + if (err < 0) { + dev_err(&pdev->dev, "failed to add mailboxes: %d\n", + err); + return err; + } + } + + err = devm_mbox_controller_register(&pdev->dev, &hsp->mbox_sm); if (err < 0) { - dev_err(&pdev->dev, "failed to add doorbells: %d\n", err); + dev_err(&pdev->dev, "failed to register shared mailbox: %d\n", + err); return err; } platform_set_drvdata(pdev, hsp); - err = mbox_controller_register(&hsp->mbox); - if (err) { - dev_err(&pdev->dev, "failed to register mailbox: %d\n", err); - tegra_hsp_remove_doorbells(hsp); - return err; + if (hsp->doorbell_irq) { + err = devm_request_irq(&pdev->dev, hsp->doorbell_irq, + tegra_hsp_doorbell_irq, IRQF_NO_SUSPEND, + dev_name(&pdev->dev), hsp); + if (err < 0) { + dev_err(&pdev->dev, + "failed to request doorbell IRQ#%u: %d\n", + hsp->doorbell_irq, err); + return err; + } } - err = devm_request_irq(&pdev->dev, hsp->irq, tegra_hsp_doorbell_irq, - IRQF_NO_SUSPEND, dev_name(&pdev->dev), hsp); - if (err < 0) { - dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", - hsp->irq, err); - return err; + if (hsp->shared_irqs) { + err = tegra_hsp_request_shared_irq(hsp); + if (err < 0) + return err; } return 0; } -static int tegra_hsp_remove(struct platform_device *pdev) +static int tegra_hsp_resume(struct device *dev) { - struct tegra_hsp *hsp = platform_get_drvdata(pdev); + struct tegra_hsp *hsp = dev_get_drvdata(dev); + unsigned int i; - mbox_controller_unregister(&hsp->mbox); - tegra_hsp_remove_doorbells(hsp); + for (i = 0; i < hsp->num_sm; i++) { + struct tegra_hsp_mailbox *mb = &hsp->mailboxes[i]; + + if (mb->channel.chan->cl) + tegra_hsp_mailbox_startup(mb->channel.chan); + } return 0; } +static SIMPLE_DEV_PM_OPS(tegra_hsp_pm_ops, NULL, tegra_hsp_resume); + static const struct tegra_hsp_db_map tegra186_hsp_db_map[] = { { "ccplex", TEGRA_HSP_DB_MASTER_CCPLEX, HSP_DB_CCPLEX, }, { "bpmp", TEGRA_HSP_DB_MASTER_BPMP, HSP_DB_BPMP, }, @@ -456,10 +804,17 @@ static const struct tegra_hsp_db_map tegra186_hsp_db_map[] = { static const struct tegra_hsp_soc tegra186_hsp_soc = { .map = tegra186_hsp_db_map, + .has_per_mb_ie = false, +}; + +static const struct tegra_hsp_soc tegra194_hsp_soc = { + .map = tegra186_hsp_db_map, + .has_per_mb_ie = true, }; static const struct of_device_id tegra_hsp_match[] = { { .compatible = "nvidia,tegra186-hsp", .data = &tegra186_hsp_soc }, + { .compatible = "nvidia,tegra194-hsp", .data = &tegra194_hsp_soc }, { } }; @@ -467,9 +822,9 @@ static struct platform_driver tegra_hsp_driver = { .driver = { .name = "tegra-hsp", .of_match_table = tegra_hsp_match, + .pm = &tegra_hsp_pm_ops, }, .probe = tegra_hsp_probe, - .remove = tegra_hsp_remove, }; static int __init tegra_hsp_init(void) diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c index 713d701b6568..88047d835211 100644 --- a/drivers/mailbox/ti-msgmgr.c +++ b/drivers/mailbox/ti-msgmgr.c @@ -547,7 +547,7 @@ static struct mbox_chan *ti_msgmgr_of_xlate(struct mbox_controller *mbox, } if (d->is_sproxy) { - if (req_pid > d->num_valid_queues) + if (req_pid >= d->num_valid_queues) goto err; qinst = &inst->qinsts[req_pid]; return qinst->chan; @@ -817,26 +817,15 @@ static int ti_msgmgr_probe(struct platform_device *pdev) mbox->of_xlate = ti_msgmgr_of_xlate; platform_set_drvdata(pdev, inst); - ret = mbox_controller_register(mbox); + ret = devm_mbox_controller_register(dev, mbox); if (ret) dev_err(dev, "Failed to register mbox_controller(%d)\n", ret); return ret; } -static int ti_msgmgr_remove(struct platform_device *pdev) -{ - struct ti_msgmgr_inst *inst; - - inst = platform_get_drvdata(pdev); - mbox_controller_unregister(&inst->mbox); - - return 0; -} - static struct platform_driver ti_msgmgr_driver = { .probe = ti_msgmgr_probe, - .remove = ti_msgmgr_remove, .driver = { .name = "ti-msgmgr", .of_match_table = of_match_ptr(ti_msgmgr_of_match), diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index aa4a1f5206f1..361fbde76654 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -303,11 +303,10 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum, * send them to our master MDIO bus controller */ if (addr == BRCM_PSEUDO_PHY_ADDR && priv->indir_phy_mask & BIT(addr)) - bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val); + return bcm_sf2_sw_indir_rw(priv, 0, addr, regnum, val); else - mdiobus_write_nested(priv->master_mii_bus, addr, regnum, val); - - return 0; + return mdiobus_write_nested(priv->master_mii_bus, addr, + regnum, val); } static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id) diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 9dc6da039a6d..3164aad29bcf 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -473,7 +473,9 @@ static void atl1e_mdio_write(struct net_device *netdev, int phy_id, { struct atl1e_adapter *adapter = netdev_priv(netdev); - atl1e_write_phy_reg(&adapter->hw, reg_num & MDIO_REG_ADDR_MASK, val); + if (atl1e_write_phy_reg(&adapter->hw, + reg_num & MDIO_REG_ADDR_MASK, val)) + netdev_err(netdev, "write phy register failed\n"); } static int atl1e_mii_ioctl(struct net_device *netdev, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 7c49681407ad..127b1f624413 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1229,6 +1229,10 @@ int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init, rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_hw_sched), &temp_buff); + + if (rc) + return rc; + hw_sched_buff = (struct cudbg_hw_sched *)temp_buff.data; hw_sched_buff->map = t4_read_reg(padap, TP_TX_MOD_QUEUE_REQ_MAP_A); hw_sched_buff->mode = TIMERMODE_G(t4_read_reg(padap, TP_MOD_CONFIG_A)); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index bc6eb30aa20f..41c6fa200e74 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -928,7 +928,7 @@ int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr) hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK; /* Create element to be added to the driver hash table */ - hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC); if (!hash_entry) return -ENOMEM; hash_entry->addr = addr; diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 40705938eecc..f75b9c11b2d2 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -553,7 +553,7 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr) hash = (crc >> TGEC_HASH_MCAST_SHIFT) & TGEC_HASH_ADR_MSK; /* Create element to be added to the driver hash table */ - hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL); + hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC); if (!hash_entry) return -ENOMEM; hash_entry->addr = addr; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index d3b9aaf96c1c..07cd58798083 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3995,17 +3995,18 @@ static int hns3_reset_notify_up_enet(struct hnae3_handle *handle) struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev); int ret = 0; + clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state); + if (netif_running(kinfo->netdev)) { - ret = hns3_nic_net_up(kinfo->netdev); + ret = hns3_nic_net_open(kinfo->netdev); if (ret) { + set_bit(HNS3_NIC_STATE_RESETTING, &priv->state); netdev_err(kinfo->netdev, "hns net up fail, ret=%d!\n", ret); return ret; } } - clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state); - return ret; } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 6d48dc62a44b..da323b9e1f62 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -1106,6 +1106,11 @@ static void hinic_remove(struct pci_dev *pdev) dev_info(&pdev->dev, "HiNIC driver - removed\n"); } +static void hinic_shutdown(struct pci_dev *pdev) +{ + pci_disable_device(pdev); +} + static const struct pci_device_id hinic_pci_table[] = { { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0}, { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0}, @@ -1119,6 +1124,7 @@ static struct pci_driver hinic_driver = { .id_table = hinic_pci_table, .probe = hinic_probe, .remove = hinic_remove, + .shutdown = hinic_shutdown, }; module_pci_driver(hinic_driver); diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index a4681780a55d..098d8764c0ea 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1171,11 +1171,15 @@ out: map_failed_frags: last = i+1; - for (i = 0; i < last; i++) + for (i = 1; i < last; i++) dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address, descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK, DMA_TO_DEVICE); + dma_unmap_single(&adapter->vdev->dev, + descs[0].fields.address, + descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK, + DMA_TO_DEVICE); map_failed: if (!firmware_has_feature(FW_FEATURE_CMO)) netdev_err(netdev, "tx: unable to map xmit buffer\n"); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 6a059d6ee03f..e0875476a780 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5240,6 +5240,8 @@ static int mvpp2_probe(struct platform_device *pdev) if (has_acpi_companion(&pdev->dev)) { acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev); + if (!acpi_id) + return -EINVAL; priv->hw_version = (unsigned long)acpi_id->driver_data; } else { priv->hw_version = diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 99bc3de906e2..298930d39b79 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1477,6 +1477,8 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) } RTL_W8(tp, Cfg9346, Cfg9346_Lock); + + device_set_wakeup_enable(tp_to_dev(tp), wolopts); } static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) @@ -1498,8 +1500,6 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) rtl_unlock_work(tp); - device_set_wakeup_enable(d, tp->saved_wolopts); - pm_runtime_put_noidle(d); return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index d07520fb969e..62ccbd47c1db 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -59,7 +59,9 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv) gmac->clk_enabled = 1; } else { clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE); - clk_prepare(gmac->tx_clk); + ret = clk_prepare(gmac->tx_clk); + if (ret) + return ret; } return 0; diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 9319d84bf49f..d84501441edd 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -8100,6 +8100,8 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end) start += 3; prop_len = niu_pci_eeprom_read(np, start + 4); + if (prop_len < 0) + return prop_len; err = niu_pci_vpd_get_propname(np, start + 5, namebuf, 64); if (err < 0) return err; @@ -8144,8 +8146,12 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end) netif_printk(np, probe, KERN_DEBUG, np->dev, "VPD_SCAN: Reading in property [%s] len[%d]\n", namebuf, prop_len); - for (i = 0; i < prop_len; i++) - *prop_buf++ = niu_pci_eeprom_read(np, off + i); + for (i = 0; i < prop_len; i++) { + err = niu_pci_eeprom_read(np, off + i); + if (err >= 0) + *prop_buf = err; + ++prop_buf; + } } start += len; diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index 054f78295d1d..2a9ba4acd7fa 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -590,7 +590,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs, return ERR_CAST(cpts->refclk); } - clk_prepare(cpts->refclk); + ret = clk_prepare(cpts->refclk); + if (ret) + return ERR_PTR(ret); cpts->cc.read = cpts_systim_read; cpts->cc.mask = CLOCKSOURCE_MASK(32); diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 28c749980359..a19868cba48c 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -523,10 +523,7 @@ static void resync_tnc(struct timer_list *t) /* Start resync timer again -- the TNC might be still absent */ - - del_timer(&sp->resync_t); - sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; - add_timer(&sp->resync_t); + mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); } static inline int tnc_init(struct sixpack *sp) @@ -537,9 +534,7 @@ static inline int tnc_init(struct sixpack *sp) sp->tty->ops->write(sp->tty, &inbyte, 1); - del_timer(&sp->resync_t); - sp->resync_t.expires = jiffies + SIXP_RESYNC_TIMEOUT; - add_timer(&sp->resync_t); + mod_timer(&sp->resync_t, jiffies + SIXP_RESYNC_TIMEOUT); return 0; } @@ -897,11 +892,8 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd) /* if the state byte has been received, the TNC is present, so the resync timer can be reset. */ - if (sp->tnc_state == TNC_IN_SYNC) { - del_timer(&sp->resync_t); - sp->resync_t.expires = jiffies + SIXP_INIT_RESYNC_TIMEOUT; - add_timer(&sp->resync_t); - } + if (sp->tnc_state == TNC_IN_SYNC) + mod_timer(&sp->resync_t, jiffies + SIXP_INIT_RESYNC_TIMEOUT); sp->status1 = cmd & SIXP_PRIO_DATA_MASK; } diff --git a/drivers/net/tap.c b/drivers/net/tap.c index 443b2694130c..c0b52e48f0e6 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1177,8 +1177,6 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) goto err_kfree; } - skb_probe_transport_header(skb, ETH_HLEN); - /* Move network header to the right position for VLAN tagged packets */ if ((skb->protocol == htons(ETH_P_8021Q) || skb->protocol == htons(ETH_P_8021AD)) && @@ -1189,6 +1187,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) tap = rcu_dereference(q->tap); if (tap) { skb->dev = tap->dev; + skb_probe_transport_header(skb, ETH_HLEN); dev_queue_xmit(skb); } else { kfree_skb(skb); diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 7a42336c8af8..839fa7715709 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1180,7 +1180,6 @@ static int ucc_hdlc_probe(struct platform_device *pdev) if (register_hdlc_device(dev)) { ret = -ENOBUFS; pr_err("ucc_hdlc: unable to register hdlc device\n"); - free_netdev(dev); goto free_dev; } diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 1098263ab862..46c3d983b7b7 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -485,8 +485,10 @@ static int x25_asy_open(struct net_device *dev) /* Cleanup */ kfree(sl->xbuff); + sl->xbuff = NULL; noxbuff: kfree(sl->rbuff); + sl->rbuff = NULL; norbuff: return -ENOMEM; } diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 5e9ebdb0594c..397af07e4d88 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1192,20 +1192,7 @@ static int dasd_hosts_show(struct seq_file *m, void *v) return rc; } -static int dasd_hosts_open(struct inode *inode, struct file *file) -{ - struct dasd_device *device = inode->i_private; - - return single_open(file, dasd_hosts_show, device); -} - -static const struct file_operations dasd_hosts_fops = { - .owner = THIS_MODULE, - .open = dasd_hosts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(dasd_hosts); static void dasd_hosts_exit(struct dasd_device *device) { diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c index 5cb80c645489..1770b99f607e 100644 --- a/drivers/s390/block/dasd_proc.c +++ b/drivers/s390/block/dasd_proc.c @@ -339,8 +339,7 @@ dasd_proc_init(void) dasd_proc_root_entry = proc_mkdir("dasd", NULL); if (!dasd_proc_root_entry) goto out_nodasd; - dasd_devices_entry = proc_create_seq("devices", - S_IFREG | S_IRUGO | S_IWUSR, + dasd_devices_entry = proc_create_seq("devices", 0444, dasd_proc_root_entry, &dasd_devices_seq_ops); if (!dasd_devices_entry) diff --git a/drivers/s390/char/tape_proc.c b/drivers/s390/char/tape_proc.c index 32a14ee31c6b..2238d9df6c47 100644 --- a/drivers/s390/char/tape_proc.c +++ b/drivers/s390/char/tape_proc.c @@ -111,11 +111,8 @@ static const struct seq_operations tape_proc_seq = { void tape_proc_init(void) { - tape_proc_devices = proc_create_seq("tapedevices", - S_IFREG | S_IRUGO | S_IWUSR, NULL, &tape_proc_seq); - if (tape_proc_devices == NULL) { - return; - } + tape_proc_devices = proc_create_seq("tapedevices", 0444, NULL, + &tape_proc_seq); } /* diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c index 68a82f3e2e92..d2f98e5829d4 100644 --- a/drivers/s390/cio/qdio_debug.c +++ b/drivers/s390/cio/qdio_debug.c @@ -190,19 +190,7 @@ static int qstat_show(struct seq_file *m, void *v) return 0; } -static int qstat_seq_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, qstat_show, - file_inode(filp)->i_private); -} - -static const struct file_operations debugfs_fops = { - .owner = THIS_MODULE, - .open = qstat_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(qstat); static char *qperf_names[] = { "Assumed adapter interrupts", @@ -305,8 +293,8 @@ static void setup_debugfs_entry(struct qdio_q *q) snprintf(name, QDIO_DEBUGFS_NAME_LEN, "%s_%d", q->is_input_q ? "input" : "output", q->nr); - q->debugfs_q = debugfs_create_file(name, S_IFREG | S_IRUGO | S_IWUSR, - q->irq_ptr->debugfs_dev, q, &debugfs_fops); + q->debugfs_q = debugfs_create_file(name, 0444, + q->irq_ptr->debugfs_dev, q, &qstat_fops); if (IS_ERR(q->debugfs_q)) q->debugfs_q = NULL; } diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c index f94aa01f9c36..cab17865aafe 100644 --- a/drivers/s390/cio/vfio_ccw_fsm.c +++ b/drivers/s390/cio/vfio_ccw_fsm.c @@ -130,7 +130,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, struct mdev_device *mdev = private->mdev; char *errstr = "request"; - private->state = VFIO_CCW_STATE_BOXED; + private->state = VFIO_CCW_STATE_BUSY; memcpy(scsw, io_region->scsw_area, sizeof(*scsw)); @@ -216,11 +216,6 @@ fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = { [VFIO_CCW_EVENT_IO_REQ] = fsm_io_request, [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, }, - [VFIO_CCW_STATE_BOXED] = { - [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, - [VFIO_CCW_EVENT_IO_REQ] = fsm_io_busy, - [VFIO_CCW_EVENT_INTERRUPT] = fsm_irq, - }, [VFIO_CCW_STATE_BUSY] = { [VFIO_CCW_EVENT_NOT_OPER] = fsm_notoper, [VFIO_CCW_EVENT_IO_REQ] = fsm_io_busy, diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h index 078e46f9623d..08e9a7dc9176 100644 --- a/drivers/s390/cio/vfio_ccw_private.h +++ b/drivers/s390/cio/vfio_ccw_private.h @@ -63,7 +63,6 @@ enum vfio_ccw_state { VFIO_CCW_STATE_NOT_OPER, VFIO_CCW_STATE_STANDBY, VFIO_CCW_STATE_IDLE, - VFIO_CCW_STATE_BOXED, VFIO_CCW_STATE_BUSY, /* last element! */ NR_VFIO_CCW_STATES diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 9f5a201c4c87..48ea0004a56d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -299,7 +299,7 @@ static int ap_query_queue(ap_qid_t qid, int *queue_depth, int *device_type, ap_max_domain_id = 15; switch (*device_type) { /* For CEX2 and CEX3 the available functions - * are not refrected by the facilities bits. + * are not reflected by the facilities bits. * Instead it is coded into the type. So here * modify the function bits based on the type. */ @@ -1317,7 +1317,7 @@ static int ap_get_compatible_type(ap_qid_t qid, int rawtype, unsigned int func) } /* - * helper function to be used with bus_find_dev + * Helper function to be used with bus_find_dev * matches for the card device with the given id */ static int __match_card_device_with_id(struct device *dev, void *data) @@ -1325,7 +1325,8 @@ static int __match_card_device_with_id(struct device *dev, void *data) return is_card_dev(dev) && to_ap_card(dev)->id == (int)(long) data; } -/* helper function to be used with bus_find_dev +/* + * Helper function to be used with bus_find_dev * matches for the queue device with a given qid */ static int __match_queue_device_with_qid(struct device *dev, void *data) @@ -1333,143 +1334,185 @@ static int __match_queue_device_with_qid(struct device *dev, void *data) return is_queue_dev(dev) && to_ap_queue(dev)->qid == (int)(long) data; } -/** - * ap_scan_bus(): Scan the AP bus for new devices - * Runs periodically, workqueue timer (ap_config_time) +/* + * Helper function for ap_scan_bus(). + * Does the scan bus job for the given adapter id. */ -static void ap_scan_bus(struct work_struct *unused) +static void _ap_scan_bus_adapter(int id) { - struct ap_queue *aq; + ap_qid_t qid; + unsigned int func; struct ap_card *ac; struct device *dev; - ap_qid_t qid; - int comp_type, depth = 0, type = 0; - unsigned int func = 0; - int rc, id, dom, borked, domains, defdomdevs = 0; - - AP_DBF(DBF_DEBUG, "%s running\n", __func__); + struct ap_queue *aq; + int rc, dom, depth, type, comp_type, borked; + + /* check if there is a card device registered with this id */ + dev = bus_find_device(&ap_bus_type, NULL, + (void *)(long) id, + __match_card_device_with_id); + ac = dev ? to_ap_card(dev) : NULL; + if (!ap_test_config_card_id(id)) { + if (dev) { + /* Card device has been removed from configuration */ + bus_for_each_dev(&ap_bus_type, NULL, + (void *)(long) id, + __ap_queue_devices_with_id_unregister); + device_unregister(dev); + put_device(dev); + } + return; + } - ap_query_configuration(ap_configuration); - ap_select_domain(); + /* + * This card id is enabled in the configuration. If we already have + * a card device with this id, check if type and functions are still + * the very same. Also verify that at least one queue is available. + */ + if (ac) { + /* find the first valid queue */ + for (dom = 0; dom < AP_DOMAINS; dom++) { + qid = AP_MKQID(id, dom); + if (ap_query_queue(qid, &depth, &type, &func) == 0) + break; + } + borked = 0; + if (dom >= AP_DOMAINS) { + /* no accessible queue on this card */ + borked = 1; + } else if (ac->raw_hwtype != type) { + /* card type has changed */ + AP_DBF(DBF_INFO, "card=%02x type changed.\n", id); + borked = 1; + } else if (ac->functions != func) { + /* card functions have changed */ + AP_DBF(DBF_INFO, "card=%02x functions changed.\n", id); + borked = 1; + } + if (borked) { + /* unregister card device and associated queues */ + bus_for_each_dev(&ap_bus_type, NULL, + (void *)(long) id, + __ap_queue_devices_with_id_unregister); + device_unregister(dev); + put_device(dev); + /* go back if there is no valid queue on this card */ + if (dom >= AP_DOMAINS) + return; + ac = NULL; + } + } - for (id = 0; id < AP_DEVICES; id++) { - /* check if device is registered */ + /* + * Go through all possible queue ids. Check and maybe create or release + * queue devices for this card. If there exists no card device yet, + * create a card device also. + */ + for (dom = 0; dom < AP_DOMAINS; dom++) { + qid = AP_MKQID(id, dom); dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) id, - __match_card_device_with_id); - ac = dev ? to_ap_card(dev) : NULL; - if (!ap_test_config_card_id(id)) { + (void *)(long) qid, + __match_queue_device_with_qid); + aq = dev ? to_ap_queue(dev) : NULL; + if (!ap_test_config_domain(dom)) { if (dev) { - /* Card device has been removed from - * configuration, remove the belonging - * queue devices. + /* Queue device exists but has been + * removed from configuration. */ - bus_for_each_dev(&ap_bus_type, NULL, - (void *)(long) id, - __ap_queue_devices_with_id_unregister); - /* now remove the card device */ device_unregister(dev); put_device(dev); } continue; } - /* According to the configuration there should be a card - * device, so check if there is at least one valid queue - * and maybe create queue devices and the card device. - */ - domains = 0; - for (dom = 0; dom < AP_DOMAINS; dom++) { - qid = AP_MKQID(id, dom); - dev = bus_find_device(&ap_bus_type, NULL, - (void *)(long) qid, - __match_queue_device_with_qid); - aq = dev ? to_ap_queue(dev) : NULL; - if (!ap_test_config_domain(dom)) { - if (dev) { - /* Queue device exists but has been - * removed from configuration. - */ - device_unregister(dev); - put_device(dev); - } - continue; - } - rc = ap_query_queue(qid, &depth, &type, &func); - if (dev) { + /* try to fetch infos about this queue */ + rc = ap_query_queue(qid, &depth, &type, &func); + if (dev) { + if (rc == -ENODEV) + borked = 1; + else { spin_lock_bh(&aq->lock); - if (rc == -ENODEV || - /* adapter reconfiguration */ - (ac && ac->functions != func)) - aq->state = AP_STATE_BORKED; borked = aq->state == AP_STATE_BORKED; spin_unlock_bh(&aq->lock); - if (borked) /* Remove broken device */ - device_unregister(dev); - put_device(dev); - if (!borked) { - domains++; - if (dom == ap_domain_index) - defdomdevs++; - continue; - } - } - if (rc) - continue; - /* a new queue device is needed, check out comp type */ - comp_type = ap_get_compatible_type(qid, type, func); - if (!comp_type) - continue; - /* maybe a card device needs to be created first */ - if (!ac) { - ac = ap_card_create(id, depth, type, - comp_type, func); - if (!ac) - continue; - ac->ap_dev.device.bus = &ap_bus_type; - ac->ap_dev.device.parent = ap_root_device; - dev_set_name(&ac->ap_dev.device, - "card%02x", id); - /* Register card with AP bus */ - rc = device_register(&ac->ap_dev.device); - if (rc) { - put_device(&ac->ap_dev.device); - ac = NULL; - break; - } - /* get it and thus adjust reference counter */ - get_device(&ac->ap_dev.device); } - /* now create the new queue device */ - aq = ap_queue_create(qid, comp_type); - if (!aq) + if (borked) /* Remove broken device */ + device_unregister(dev); + put_device(dev); + continue; + } + if (rc) + continue; + /* a new queue device is needed, check out comp type */ + comp_type = ap_get_compatible_type(qid, type, func); + if (!comp_type) + continue; + /* maybe a card device needs to be created first */ + if (!ac) { + ac = ap_card_create(id, depth, type, comp_type, func); + if (!ac) continue; - aq->card = ac; - aq->ap_dev.device.bus = &ap_bus_type; - aq->ap_dev.device.parent = &ac->ap_dev.device; - dev_set_name(&aq->ap_dev.device, - "%02x.%04x", id, dom); - /* Register device */ - rc = device_register(&aq->ap_dev.device); + ac->ap_dev.device.bus = &ap_bus_type; + ac->ap_dev.device.parent = ap_root_device; + dev_set_name(&ac->ap_dev.device, "card%02x", id); + /* Register card device with AP bus */ + rc = device_register(&ac->ap_dev.device); if (rc) { - put_device(&aq->ap_dev.device); - continue; + put_device(&ac->ap_dev.device); + ac = NULL; + break; } - domains++; - if (dom == ap_domain_index) - defdomdevs++; - } /* end domain loop */ - if (ac) { - /* remove card dev if there are no queue devices */ - if (!domains) - device_unregister(&ac->ap_dev.device); - put_device(&ac->ap_dev.device); + /* get it and thus adjust reference counter */ + get_device(&ac->ap_dev.device); + } + /* now create the new queue device */ + aq = ap_queue_create(qid, comp_type); + if (!aq) + continue; + aq->card = ac; + aq->ap_dev.device.bus = &ap_bus_type; + aq->ap_dev.device.parent = &ac->ap_dev.device; + dev_set_name(&aq->ap_dev.device, "%02x.%04x", id, dom); + /* Register queue device */ + rc = device_register(&aq->ap_dev.device); + if (rc) { + put_device(&aq->ap_dev.device); + continue; } - } /* end device loop */ + } /* end domain loop */ + + if (ac) + put_device(&ac->ap_dev.device); +} - if (ap_domain_index >= 0 && defdomdevs < 1) - AP_DBF(DBF_INFO, - "no queue device with default domain %d available\n", - ap_domain_index); +/** + * ap_scan_bus(): Scan the AP bus for new devices + * Runs periodically, workqueue timer (ap_config_time) + */ +static void ap_scan_bus(struct work_struct *unused) +{ + int id; + + AP_DBF(DBF_DEBUG, "%s running\n", __func__); + + ap_query_configuration(ap_configuration); + ap_select_domain(); + + /* loop over all possible adapters */ + for (id = 0; id < AP_DEVICES; id++) + _ap_scan_bus_adapter(id); + + /* check if there is at least one queue available with default domain */ + if (ap_domain_index >= 0) { + struct device *dev = + bus_find_device(&ap_bus_type, NULL, + (void *)(long) ap_domain_index, + __match_queue_device_with_qid); + if (dev) + put_device(dev); + else + AP_DBF(DBF_INFO, + "no queue device with default domain %d available\n", + ap_domain_index); + } mod_timer(&ap_config_timer, jiffies + ap_config_time * HZ); } diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 0aa4b3ccc948..576ac08777c5 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -14,6 +14,9 @@ #include <asm/facility.h> #include "ap_bus.h" +#include "ap_debug.h" + +static void __ap_flush_queue(struct ap_queue *aq); /** * ap_queue_enable_interruption(): Enable interruption on an AP queue. @@ -541,7 +544,25 @@ static ssize_t reset_show(struct device *dev, return rc; } -static DEVICE_ATTR_RO(reset); +static ssize_t reset_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct ap_queue *aq = to_ap_queue(dev); + + spin_lock_bh(&aq->lock); + __ap_flush_queue(aq); + aq->state = AP_STATE_RESET_START; + ap_wait(ap_sm_event(aq, AP_EVENT_POLL)); + spin_unlock_bh(&aq->lock); + + AP_DBF(DBF_INFO, "reset queue=%02x.%04x triggered by user\n", + AP_QID_CARD(aq->qid), AP_QID_QUEUE(aq->qid)); + + return count; +} + +static DEVICE_ATTR_RW(reset); static ssize_t interrupt_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c index 7667b38728f0..31c6c847eaca 100644 --- a/drivers/s390/crypto/vfio_ap_drv.c +++ b/drivers/s390/crypto/vfio_ap_drv.c @@ -11,6 +11,7 @@ #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/string.h> +#include <asm/facility.h> #include "vfio_ap_private.h" #define VFIO_AP_ROOT_NAME "vfio_ap" diff --git a/drivers/s390/crypto/zcrypt_error.h b/drivers/s390/crypto/zcrypt_error.h index 240b27f3f5f6..f34ee41cbed8 100644 --- a/drivers/s390/crypto/zcrypt_error.h +++ b/drivers/s390/crypto/zcrypt_error.h @@ -51,6 +51,7 @@ struct error_hdr { #define REP82_ERROR_FORMAT_FIELD 0x29 #define REP82_ERROR_INVALID_COMMAND 0x30 #define REP82_ERROR_MALFORMED_MSG 0x40 +#define REP82_ERROR_INVALID_SPECIAL_CMD 0x41 #define REP82_ERROR_INVALID_DOMAIN_PRECHECK 0x42 #define REP82_ERROR_RESERVED_FIELDO 0x50 /* old value */ #define REP82_ERROR_WORD_ALIGNMENT 0x60 @@ -89,6 +90,7 @@ static inline int convert_error(struct zcrypt_queue *zq, case REP88_ERROR_MESSAGE_MALFORMD: case REP82_ERROR_INVALID_DOMAIN_PRECHECK: case REP82_ERROR_INVALID_DOMAIN_PENDING: + case REP82_ERROR_INVALID_SPECIAL_CMD: // REP88_ERROR_INVALID_KEY // '82' CEX2A // REP88_ERROR_OPERAND // '84' CEX2A // REP88_ERROR_OPERAND_EVEN_MOD // '85' CEX2A diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index a08472ae5b1b..8e10ab436d1f 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -884,7 +884,7 @@ vhost_scsi_get_req(struct vhost_virtqueue *vq, struct vhost_scsi_ctx *vc, if (unlikely(!copy_from_iter_full(vc->req, vc->req_size, &vc->out_iter))) { - vq_err(vq, "Faulted on copy_from_iter\n"); + vq_err(vq, "Faulted on copy_from_iter_full\n"); } else if (unlikely(*vc->lunp != 1)) { /* virtio-scsi spec requires byte 0 of the lun to be 1 */ vq_err(vq, "Illegal virtio-scsi lun: %u\n", *vc->lunp); @@ -1436,7 +1436,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs, se_tpg = &tpg->se_tpg; ret = target_depend_item(&se_tpg->tpg_group.cg_item); if (ret) { - pr_warn("configfs_depend_item() failed: %d\n", ret); + pr_warn("target_depend_item() failed: %d\n", ret); kfree(vs_tpg); mutex_unlock(&tpg->tv_tpg_mutex); goto out; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 98ed5be132c6..bc42d38ae031 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -27,14 +27,14 @@ enum { }; /* Used to track all the vhost_vsock instances on the system. */ -static DEFINE_SPINLOCK(vhost_vsock_lock); +static DEFINE_MUTEX(vhost_vsock_mutex); static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8); struct vhost_vsock { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; - /* Link to global vhost_vsock_hash, writes use vhost_vsock_lock */ + /* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */ struct hlist_node hash; struct vhost_work send_pkt_work; @@ -51,7 +51,7 @@ static u32 vhost_transport_get_local_cid(void) return VHOST_VSOCK_DEFAULT_HOST_CID; } -/* Callers that dereference the return value must hold vhost_vsock_lock or the +/* Callers that dereference the return value must hold vhost_vsock_mutex or the * RCU read lock. */ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) @@ -584,10 +584,10 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) { struct vhost_vsock *vsock = file->private_data; - spin_lock_bh(&vhost_vsock_lock); + mutex_lock(&vhost_vsock_mutex); if (vsock->guest_cid) hash_del_rcu(&vsock->hash); - spin_unlock_bh(&vhost_vsock_lock); + mutex_unlock(&vhost_vsock_mutex); /* Wait for other CPUs to finish using vsock */ synchronize_rcu(); @@ -631,10 +631,10 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) return -EINVAL; /* Refuse if CID is already in use */ - spin_lock_bh(&vhost_vsock_lock); + mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); if (other && other != vsock) { - spin_unlock_bh(&vhost_vsock_lock); + mutex_unlock(&vhost_vsock_mutex); return -EADDRINUSE; } @@ -643,7 +643,7 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) vsock->guest_cid = guest_cid; hash_add_rcu(vhost_vsock_hash, &vsock->hash, guest_cid); - spin_unlock_bh(&vhost_vsock_lock); + mutex_unlock(&vhost_vsock_mutex); return 0; } diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index de062fb201bc..eff9ddc7c4ab 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -52,7 +52,8 @@ static void vp_get(struct virtio_device *vdev, unsigned offset, { struct virtio_pci_device *vp_dev = to_vp_device(vdev); void __iomem *ioaddr = vp_dev->ioaddr + - VIRTIO_PCI_CONFIG(vp_dev) + offset; + VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) + + offset; u8 *ptr = buf; int i; @@ -67,7 +68,8 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, { struct virtio_pci_device *vp_dev = to_vp_device(vdev); void __iomem *ioaddr = vp_dev->ioaddr + - VIRTIO_PCI_CONFIG(vp_dev) + offset; + VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) + + offset; const u8 *ptr = buf; int i; diff --git a/fs/block_dev.c b/fs/block_dev.c index 450be88cffef..c546cdce77e6 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -237,11 +237,9 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, qc = submit_bio(&bio); for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); - + set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio.bi_private)) break; - if (!(iocb->ki_flags & IOCB_HIPRI) || !blk_poll(bdev_get_queue(bdev), qc, true)) io_schedule(); @@ -426,8 +424,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) return -EIOCBQUEUED; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); - + set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->waiter)) break; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 85dadb93c992..f1ddc9d03c10 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -190,8 +190,9 @@ config CIFS_DFS_UPCALL moves to a different server. This feature also enables an upcall mechanism for CIFS which contacts userspace helper utilities to provide server name resolution (host names to - IP addresses) which is needed for implicit mounts of DFS junction - points. If unsure, say Y. + IP addresses) which is needed in order to reconnect to + servers if their addresses change or for implicit mounts of + DFS junction points. If unsure, say Y. config CIFS_NFSD_EXPORT bool "Allow nfsd to export CIFS file system" diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 85817991ee68..51af69a1a328 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -17,7 +17,7 @@ cifs-$(CONFIG_CIFS_ACL) += cifsacl.o cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o -cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o +cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index ba178b09de0b..593fb422d0f3 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -30,6 +30,9 @@ #include "cifsproto.h" #include "cifs_debug.h" #include "cifsfs.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif #ifdef CONFIG_CIFS_SMB_DIRECT #include "smbdirect.h" #endif @@ -629,6 +632,11 @@ cifs_proc_init(void) &cifs_security_flags_proc_fops); proc_create("LookupCacheEnabled", 0644, proc_fs_cifs, &cifs_lookup_cache_proc_fops); + +#ifdef CONFIG_CIFS_DFS_UPCALL + proc_create("dfscache", 0644, proc_fs_cifs, &dfscache_proc_fops); +#endif + #ifdef CONFIG_CIFS_SMB_DIRECT proc_create("rdma_readwrite_threshold", 0644, proc_fs_cifs, &cifs_rdma_readwrite_threshold_proc_fops); @@ -663,6 +671,10 @@ cifs_proc_clean(void) remove_proc_entry("SecurityFlags", proc_fs_cifs); remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs); remove_proc_entry("LookupCacheEnabled", proc_fs_cifs); + +#ifdef CONFIG_CIFS_DFS_UPCALL + remove_proc_entry("dfscache", proc_fs_cifs); +#endif #ifdef CONFIG_CIFS_SMB_DIRECT remove_proc_entry("rdma_readwrite_threshold", proc_fs_cifs); remove_proc_entry("smbd_max_frmr_depth", proc_fs_cifs); diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index b97c74efd04a..d9b99abe1243 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -25,6 +25,7 @@ #include "dns_resolve.h" #include "cifs_debug.h" #include "cifs_unicode.h" +#include "dfs_cache.h" static LIST_HEAD(cifs_dfs_automount_list); @@ -126,7 +127,7 @@ cifs_build_devname(char *nodename, const char *prepath) * @sb_mountdata: parent/root DFS mount options (template) * @fullpath: full path in UNC format * @ref: server's referral - * @devname: pointer for saving device name + * @devname: optional pointer for saving device name * * creates mount options for submount based on template options sb_mountdata * and replacing unc,ip,prefixpath options with ones we've got form ref_unc. @@ -140,6 +141,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, char **devname) { int rc; + char *name; char *mountdata = NULL; const char *prepath = NULL; int md_len; @@ -158,17 +160,17 @@ char *cifs_compose_mount_options(const char *sb_mountdata, prepath++; } - *devname = cifs_build_devname(ref->node_name, prepath); - if (IS_ERR(*devname)) { - rc = PTR_ERR(*devname); - *devname = NULL; + name = cifs_build_devname(ref->node_name, prepath); + if (IS_ERR(name)) { + rc = PTR_ERR(name); + name = NULL; goto compose_mount_options_err; } - rc = dns_resolve_server_name_to_ip(*devname, &srvIP); + rc = dns_resolve_server_name_to_ip(name, &srvIP); if (rc < 0) { cifs_dbg(FYI, "%s: Failed to resolve server part of %s to IP: %d\n", - __func__, *devname, rc); + __func__, name, rc); goto compose_mount_options_err; } @@ -224,6 +226,9 @@ char *cifs_compose_mount_options(const char *sb_mountdata, strcat(mountdata, "ip="); strcat(mountdata, srvIP); + if (devname) + *devname = name; + /*cifs_dbg(FYI, "%s: parent mountdata: %s\n", __func__, sb_mountdata);*/ /*cifs_dbg(FYI, "%s: submount mountdata: %s\n", __func__, mountdata );*/ @@ -234,8 +239,7 @@ compose_mount_options_out: compose_mount_options_err: kfree(mountdata); mountdata = ERR_PTR(rc); - kfree(*devname); - *devname = NULL; + kfree(name); goto compose_mount_options_out; } @@ -251,20 +255,30 @@ static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt, { struct vfsmount *mnt; char *mountdata; - char *devname = NULL; + char *devname; + + /* + * Always pass down the DFS full path to smb3_do_mount() so we + * can use it later for failover. + */ + devname = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL); + if (!devname) + return ERR_PTR(-ENOMEM); + + convert_delimiter(devname, '/'); /* strip first '\' from fullpath */ mountdata = cifs_compose_mount_options(cifs_sb->mountdata, - fullpath + 1, ref, &devname); - - if (IS_ERR(mountdata)) + fullpath + 1, ref, NULL); + if (IS_ERR(mountdata)) { + kfree(devname); return (struct vfsmount *)mountdata; + } mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata); kfree(mountdata); kfree(devname); return mnt; - } static void dump_referral(const struct dfs_info3_param *ref) @@ -282,16 +296,15 @@ static void dump_referral(const struct dfs_info3_param *ref) */ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) { - struct dfs_info3_param *referrals = NULL; - unsigned int num_referrals = 0; + struct dfs_info3_param referral = {0}; struct cifs_sb_info *cifs_sb; struct cifs_ses *ses; - char *full_path; + struct cifs_tcon *tcon; + char *full_path, *root_path; unsigned int xid; - int i; + int len; int rc; struct vfsmount *mnt; - struct tcon_link *tlink; cifs_dbg(FYI, "in %s\n", __func__); BUG_ON(IS_ROOT(mntpt)); @@ -315,48 +328,69 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt) if (full_path == NULL) goto cdda_exit; - tlink = cifs_sb_tlink(cifs_sb); - if (IS_ERR(tlink)) { - mnt = ERR_CAST(tlink); + cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); + + if (!cifs_sb_master_tlink(cifs_sb)) { + cifs_dbg(FYI, "%s: master tlink is NULL\n", __func__); goto free_full_path; } - ses = tlink_tcon(tlink)->ses; + tcon = cifs_sb_master_tcon(cifs_sb); + if (!tcon) { + cifs_dbg(FYI, "%s: master tcon is NULL\n", __func__); + goto free_full_path; + } + + root_path = kstrdup(tcon->treeName, GFP_KERNEL); + if (!root_path) { + mnt = ERR_PTR(-ENOMEM); + goto free_full_path; + } + cifs_dbg(FYI, "%s: root path: %s\n", __func__, root_path); + + ses = tcon->ses; xid = get_xid(); - rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls, - &num_referrals, &referrals, - cifs_remap(cifs_sb)); - free_xid(xid); - cifs_put_tlink(tlink); - - mnt = ERR_PTR(-ENOENT); - for (i = 0; i < num_referrals; i++) { - int len; - dump_referral(referrals + i); - /* connect to a node */ - len = strlen(referrals[i].node_name); - if (len < 2) { - cifs_dbg(VFS, "%s: Net Address path too short: %s\n", - __func__, referrals[i].node_name); - mnt = ERR_PTR(-EINVAL); - break; - } - mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, - full_path, referrals + i); - cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", - __func__, referrals[i].node_name, mnt); - if (!IS_ERR(mnt)) - goto success; + /* + * If DFS root has been expired, then unconditionally fetch it again to + * refresh DFS referral cache. + */ + rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), + root_path + 1, NULL, NULL); + if (!rc) { + rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), full_path + 1, + &referral, NULL); } - /* no valid submounts were found; return error from get_dfs_path() by - * preference */ - if (rc != 0) + free_xid(xid); + + if (rc) { mnt = ERR_PTR(rc); + goto free_root_path; + } + + dump_referral(&referral); -success: - free_dfs_info_array(referrals, num_referrals); + len = strlen(referral.node_name); + if (len < 2) { + cifs_dbg(VFS, "%s: Net Address path too short: %s\n", + __func__, referral.node_name); + mnt = ERR_PTR(-EINVAL); + goto free_dfs_ref; + } + /* + * cifs_mount() will retry every available node server in case + * of failures. + */ + mnt = cifs_dfs_do_refmount(mntpt, cifs_sb, full_path, &referral); + cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n", __func__, + referral.node_name, mnt); + +free_dfs_ref: + free_dfs_info_param(&referral); +free_root_path: + kfree(root_path); free_full_path: kfree(full_path); cdda_exit: diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 63d7530f2e1d..42f0d67f1054 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -72,6 +72,15 @@ struct cifs_sb_info { char *mountdata; /* options received at mount time or via DFS refs */ struct delayed_work prune_tlinks; struct rcu_head rcu; + + /* only used when CIFS_MOUNT_USE_PREFIX_PATH is set */ char *prepath; + + /* + * Path initially provided by the mount call. We might connect + * to something different via DFS but we want to keep it to do + * failover properly. + */ + char *origin_fullpath; /* \\HOST\SHARE\[OPTIONAL PATH] */ }; #endif /* _CIFS_FS_SB_H */ diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 85b31cfa2f3c..d2a05e46d6f5 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -224,7 +224,7 @@ int cifs_verify_signature(struct smb_rqst *rqst, if (cifs_pdu->Command == SMB_COM_LOCKING_ANDX) { struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)cifs_pdu; - if (pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE) + if (pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE) return 0; } @@ -304,12 +304,17 @@ int setup_ntlm_response(struct cifs_ses *ses, const struct nls_table *nls_cp) int calc_lanman_hash(const char *password, const char *cryptkey, bool encrypt, char *lnm_session_key) { - int i; + int i, len; int rc; char password_with_pad[CIFS_ENCPWD_SIZE] = {0}; - if (password) - strncpy(password_with_pad, password, CIFS_ENCPWD_SIZE); + if (password) { + for (len = 0; len < CIFS_ENCPWD_SIZE; len++) + if (!password[len]) + break; + + memcpy(password_with_pad, password, len); + } if (!encrypt && global_secflags & CIFSSEC_MAY_PLNTXT) { memcpy(lnm_session_key, password_with_pad, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 865706edb307..62d48d486d8f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -52,6 +52,9 @@ #include "cifs_spnego.h" #include "fscache.h" #include "smb2pdu.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif int cifsFYI = 0; bool traceSMB; @@ -1494,10 +1497,15 @@ init_cifs(void) if (rc) goto out_destroy_mids; +#ifdef CONFIG_CIFS_DFS_UPCALL + rc = dfs_cache_init(); + if (rc) + goto out_destroy_request_bufs; +#endif /* CONFIG_CIFS_DFS_UPCALL */ #ifdef CONFIG_CIFS_UPCALL rc = init_cifs_spnego(); if (rc) - goto out_destroy_request_bufs; + goto out_destroy_dfs_cache; #endif /* CONFIG_CIFS_UPCALL */ #ifdef CONFIG_CIFS_ACL @@ -1525,6 +1533,10 @@ out_register_key_type: #endif #ifdef CONFIG_CIFS_UPCALL exit_cifs_spnego(); +out_destroy_dfs_cache: +#endif +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_cache_destroy(); out_destroy_request_bufs: #endif cifs_destroy_request_bufs(); @@ -1556,6 +1568,9 @@ exit_cifs(void) #ifdef CONFIG_CIFS_UPCALL exit_cifs_spnego(); #endif +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_cache_destroy(); +#endif cifs_destroy_request_bufs(); cifs_destroy_mids(); cifs_destroy_inodecache(); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 4c3b5cfccc49..26776eddd85d 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.14" +#define CIFS_VERSION "2.15" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 38ab0fca49e1..01ded7038b19 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -701,6 +701,13 @@ struct TCP_Server_Info { struct delayed_work reconnect; /* reconnect workqueue job */ struct mutex reconnect_mutex; /* prevent simultaneous reconnects */ unsigned long echo_interval; + + /* + * Number of targets available for reconnect. The more targets + * the more tasks have to wait to let the demultiplex thread + * reconnect. + */ + int nr_targets; }; static inline unsigned int @@ -1014,6 +1021,11 @@ struct cifs_tcon { struct list_head pending_opens; /* list of incomplete opens */ struct cached_fid crfid; /* Cached root fid */ /* BB add field for back pointer to sb struct(s)? */ +#ifdef CONFIG_CIFS_DFS_UPCALL + char *dfs_path; + int remap:2; + struct list_head ulist; /* cache update list */ +#endif }; /* @@ -1508,6 +1520,7 @@ struct dfs_info3_param { int ref_flag; char *path_name; char *node_name; + int ttl; }; /* @@ -1545,7 +1558,6 @@ static inline void free_dfs_info_param(struct dfs_info3_param *param) if (param) { kfree(param->path_name); kfree(param->node_name); - kfree(param); } } @@ -1790,6 +1802,7 @@ extern struct smb_version_values smb3any_values; extern struct smb_version_operations smb30_operations; extern struct smb_version_values smb30_values; #define SMB302_VERSION_STRING "3.02" +#define ALT_SMB302_VERSION_STRING "3.0.2" /*extern struct smb_version_operations smb302_operations;*/ /* not needed yet */ extern struct smb_version_values smb302_values; #define SMB311_VERSION_STRING "3.1.1" diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index fa361bc00602..336c116995d7 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -22,6 +22,9 @@ #define _CIFSPROTO_H #include <linux/nls.h> #include "trace.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif struct statfs; struct smb_vol; @@ -213,7 +216,7 @@ extern int cifs_match_super(struct super_block *, void *); extern void cifs_cleanup_volume_info(struct smb_vol *pvolume_info); extern struct smb_vol *cifs_get_volume_info(char *mount_data, const char *devname, bool is_smb3); -extern int cifs_mount(struct cifs_sb_info *, struct smb_vol *); +extern int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol); extern void cifs_umount(struct cifs_sb_info *); extern void cifs_mark_open_files_invalid(struct cifs_tcon *tcon); extern void cifs_reopen_persistent_handles(struct cifs_tcon *tcon); @@ -294,11 +297,6 @@ extern int CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, unsigned int *num_of_nodes, const struct nls_table *nls_codepage, int remap); -extern int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, - const char *old_path, - const struct nls_table *nls_codepage, - unsigned int *num_referrals, - struct dfs_info3_param **referrals, int remap); extern int parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, unsigned int *num_of_nodes, struct dfs_info3_param **target_nodes, @@ -524,6 +522,11 @@ extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, const struct nls_table *codepage); extern int SMBencrypt(unsigned char *passwd, const unsigned char *c8, unsigned char *p24); +extern void +cifs_cleanup_volume_info_contents(struct smb_vol *volume_info); + +extern struct TCP_Server_Info * +cifs_find_tcp_session(struct smb_vol *vol); void cifs_readdata_release(struct kref *refcount); int cifs_async_readv(struct cifs_readdata *rdata); @@ -562,4 +565,17 @@ void cifs_free_hash(struct crypto_shash **shash, struct sdesc **sdesc); extern void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, unsigned int *len, unsigned int *offset); +void extract_unc_hostname(const char *unc, const char **h, size_t *len); + +#ifdef CONFIG_CIFS_DFS_UPCALL +static inline int get_dfs_path(const unsigned int xid, struct cifs_ses *ses, + const char *old_path, + const struct nls_table *nls_codepage, + struct dfs_info3_param *referral, int remap) +{ + return dfs_cache_find(xid, ses, nls_codepage, remap, old_path, + referral, NULL); +} +#endif + #endif /* _CIFSPROTO_H */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index f82fd342bca5..b1f49c1c543a 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -44,6 +44,9 @@ #include "cifs_debug.h" #include "fscache.h" #include "smbdirect.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif #ifdef CONFIG_CIFS_POSIX static struct { @@ -118,6 +121,77 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon) */ } +#ifdef CONFIG_CIFS_DFS_UPCALL +static int __cifs_reconnect_tcon(const struct nls_table *nlsc, + struct cifs_tcon *tcon) +{ + int rc; + struct dfs_cache_tgt_list tl; + struct dfs_cache_tgt_iterator *it = NULL; + char tree[MAX_TREE_SIZE + 1]; + const char *tcp_host; + size_t tcp_host_len; + const char *dfs_host; + size_t dfs_host_len; + + if (tcon->ipc) { + snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + tcon->ses->server->hostname); + return CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + } + + if (!tcon->dfs_path) + return CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); + + rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); + if (rc) + return rc; + + extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, + &tcp_host_len); + + for (it = dfs_cache_get_tgt_iterator(&tl); it; + it = dfs_cache_get_next_tgt(&tl, it)) { + const char *tgt = dfs_cache_get_tgt_name(it); + + extract_unc_hostname(tgt, &dfs_host, &dfs_host_len); + + if (dfs_host_len != tcp_host_len + || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { + cifs_dbg(FYI, "%s: skipping %.*s, doesn't match %.*s", + __func__, + (int)dfs_host_len, dfs_host, + (int)tcp_host_len, tcp_host); + continue; + } + + snprintf(tree, sizeof(tree), "\\%s", tgt); + + rc = CIFSTCon(0, tcon->ses, tree, tcon, nlsc); + if (!rc) + break; + if (rc == -EREMOTE) + break; + } + + if (!rc) { + if (it) + rc = dfs_cache_noreq_update_tgthint(tcon->dfs_path + 1, + it); + else + rc = -ENOENT; + } + dfs_cache_free_tgts(&tl); + return rc; +} +#else +static inline int __cifs_reconnect_tcon(const struct nls_table *nlsc, + struct cifs_tcon *tcon) +{ + return CIFSTCon(0, tcon->ses, tcon->treeName, tcon, nlsc); +} +#endif + /* reconnect the socket, tcon, and smb session if needed */ static int cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) @@ -126,6 +200,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) struct cifs_ses *ses; struct TCP_Server_Info *server; struct nls_table *nls_codepage; + int retries; /* * SMBs NegProt, SessSetup, uLogoff do not have tcon yet so check for @@ -152,9 +227,12 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } } + retries = server->nr_targets; + /* - * Give demultiplex thread up to 10 seconds to reconnect, should be - * greater than cifs socket timeout which is 7 seconds + * Give demultiplex thread up to 10 seconds to each target available for + * reconnect -- should be greater than cifs socket timeout which is 7 + * seconds. */ while (server->tcpStatus == CifsNeedReconnect) { rc = wait_event_interruptible_timeout(server->response_q, @@ -170,6 +248,9 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) if (server->tcpStatus != CifsNeedReconnect) break; + if (--retries) + continue; + /* * on "soft" mounts we wait once. Hard mounts keep * retrying until process is killed or server comes @@ -179,6 +260,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) cifs_dbg(FYI, "gave up waiting on reconnect in smb_init\n"); return -EHOSTDOWN; } + retries = server->nr_targets; } if (!ses->need_reconnect && !tcon->need_reconnect) @@ -214,7 +296,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } cifs_mark_open_files_invalid(tcon); - rc = CIFSTCon(0, ses, tcon->treeName, tcon, nls_codepage); + rc = __cifs_reconnect_tcon(nls_codepage, tcon); mutex_unlock(&ses->session_mutex); cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 6f24f129a751..69b9d5606eba 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -56,6 +56,11 @@ #include "fscache.h" #include "smb2proto.h" #include "smbdirect.h" +#include "dns_resolve.h" +#include "cifsfs.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif extern mempool_t *cifs_req_poolp; extern bool disable_legacy_dialects; @@ -304,6 +309,7 @@ static const match_table_t cifs_smb_version_tokens = { { Smb_21, SMB21_VERSION_STRING }, { Smb_30, SMB30_VERSION_STRING }, { Smb_302, SMB302_VERSION_STRING }, + { Smb_302, ALT_SMB302_VERSION_STRING }, { Smb_311, SMB311_VERSION_STRING }, { Smb_311, ALT_SMB311_VERSION_STRING }, { Smb_3any, SMB3ANY_VERSION_STRING }, @@ -317,6 +323,131 @@ static void tlink_rb_insert(struct rb_root *root, struct tcon_link *new_tlink); static void cifs_prune_tlinks(struct work_struct *work); static int cifs_setup_volume_info(struct smb_vol *volume_info, char *mount_data, const char *devname, bool is_smb3); +static char *extract_hostname(const char *unc); + +/* + * Resolve hostname and set ip addr in tcp ses. Useful for hostnames that may + * get their ip addresses changed at some point. + * + * This should be called with server->srv_mutex held. + */ +#ifdef CONFIG_CIFS_DFS_UPCALL +static int reconn_set_ipaddr(struct TCP_Server_Info *server) +{ + int rc; + int len; + char *unc, *ipaddr = NULL; + + if (!server->hostname) + return -EINVAL; + + len = strlen(server->hostname) + 3; + + unc = kmalloc(len, GFP_KERNEL); + if (!unc) { + cifs_dbg(FYI, "%s: failed to create UNC path\n", __func__); + return -ENOMEM; + } + snprintf(unc, len, "\\\\%s", server->hostname); + + rc = dns_resolve_server_name_to_ip(unc, &ipaddr); + kfree(unc); + + if (rc < 0) { + cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n", + __func__, server->hostname, rc); + return rc; + } + + rc = cifs_convert_address((struct sockaddr *)&server->dstaddr, ipaddr, + strlen(ipaddr)); + kfree(ipaddr); + + return !rc ? -1 : 0; +} +#else +static inline int reconn_set_ipaddr(struct TCP_Server_Info *server) +{ + return 0; +} +#endif + +#ifdef CONFIG_CIFS_DFS_UPCALL +struct super_cb_data { + struct TCP_Server_Info *server; + struct cifs_sb_info *cifs_sb; +}; + +/* These functions must be called with server->srv_mutex held */ + +static void super_cb(struct super_block *sb, void *arg) +{ + struct super_cb_data *d = arg; + struct cifs_sb_info *cifs_sb; + struct cifs_tcon *tcon; + + if (d->cifs_sb) + return; + + cifs_sb = CIFS_SB(sb); + tcon = cifs_sb_master_tcon(cifs_sb); + if (tcon->ses->server == d->server) + d->cifs_sb = cifs_sb; +} + +static inline struct cifs_sb_info * +find_super_by_tcp(struct TCP_Server_Info *server) +{ + struct super_cb_data d = { + .server = server, + .cifs_sb = NULL, + }; + + iterate_supers_type(&cifs_fs_type, super_cb, &d); + return d.cifs_sb ? d.cifs_sb : ERR_PTR(-ENOENT); +} + +static void reconn_inval_dfs_target(struct TCP_Server_Info *server, + struct cifs_sb_info *cifs_sb, + struct dfs_cache_tgt_list *tgt_list, + struct dfs_cache_tgt_iterator **tgt_it) +{ + const char *name; + + if (!cifs_sb || !cifs_sb->origin_fullpath || !tgt_list || + !server->nr_targets) + return; + + if (!*tgt_it) { + *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); + } else { + *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); + if (!*tgt_it) + *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); + } + + cifs_dbg(FYI, "%s: UNC: %s\n", __func__, cifs_sb->origin_fullpath); + + name = dfs_cache_get_tgt_name(*tgt_it); + + kfree(server->hostname); + + server->hostname = extract_hostname(name); + if (!server->hostname) { + cifs_dbg(FYI, "%s: failed to extract hostname from target: %d\n", + __func__, -ENOMEM); + } +} + +static inline int reconn_setup_dfs_targets(struct cifs_sb_info *cifs_sb, + struct dfs_cache_tgt_list *tl, + struct dfs_cache_tgt_iterator **it) +{ + if (!cifs_sb->origin_fullpath) + return -EOPNOTSUPP; + return dfs_cache_noreq_find(cifs_sb->origin_fullpath + 1, NULL, tl); +} +#endif /* * cifs tcp session reconnection @@ -335,8 +466,33 @@ cifs_reconnect(struct TCP_Server_Info *server) struct cifs_tcon *tcon; struct mid_q_entry *mid_entry; struct list_head retry_list; +#ifdef CONFIG_CIFS_DFS_UPCALL + struct cifs_sb_info *cifs_sb = NULL; + struct dfs_cache_tgt_list tgt_list = {0}; + struct dfs_cache_tgt_iterator *tgt_it = NULL; +#endif spin_lock(&GlobalMid_Lock); + server->nr_targets = 1; +#ifdef CONFIG_CIFS_DFS_UPCALL + cifs_sb = find_super_by_tcp(server); + if (IS_ERR(cifs_sb)) { + rc = PTR_ERR(cifs_sb); + cifs_dbg(FYI, "%s: will not do DFS failover: rc = %d\n", + __func__, rc); + cifs_sb = NULL; + } else { + rc = reconn_setup_dfs_targets(cifs_sb, &tgt_list, &tgt_it); + if (rc) { + cifs_dbg(VFS, "%s: no target servers for DFS failover\n", + __func__); + } else { + server->nr_targets = dfs_cache_get_nr_tgts(&tgt_list); + } + } + cifs_dbg(FYI, "%s: will retry %d target(s)\n", __func__, + server->nr_targets); +#endif if (server->tcpStatus == CifsExiting) { /* the demux thread will exit normally next time through the loop */ @@ -410,14 +566,27 @@ cifs_reconnect(struct TCP_Server_Info *server) do { try_to_freeze(); - /* we should try only the port we connected to before */ mutex_lock(&server->srv_mutex); + /* + * Set up next DFS target server (if any) for reconnect. If DFS + * feature is disabled, then we will retry last server we + * connected to before. + */ if (cifs_rdma_enabled(server)) rc = smbd_reconnect(server); else rc = generic_ip_connect(server); if (rc) { cifs_dbg(FYI, "reconnect error %d\n", rc); +#ifdef CONFIG_CIFS_DFS_UPCALL + reconn_inval_dfs_target(server, cifs_sb, &tgt_list, + &tgt_it); +#endif + rc = reconn_set_ipaddr(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } mutex_unlock(&server->srv_mutex); msleep(3000); } else { @@ -430,6 +599,22 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); +#ifdef CONFIG_CIFS_DFS_UPCALL + if (tgt_it) { + rc = dfs_cache_noreq_update_tgthint(cifs_sb->origin_fullpath + 1, + tgt_it); + if (rc) { + cifs_dbg(VFS, "%s: failed to update DFS target hint: rc = %d\n", + __func__, rc); + } + rc = dfs_cache_update_vol(cifs_sb->origin_fullpath, server); + if (rc) { + cifs_dbg(VFS, "%s: failed to update vol info in DFS cache: rc = %d\n", + __func__, rc); + } + dfs_cache_free_tgts(&tgt_list); + } +#endif if (server->tcpStatus == CifsNeedNegotiate) mod_delayed_work(cifsiod_wq, &server->echo, 0); @@ -1043,7 +1228,12 @@ extract_hostname(const char *unc) /* skip double chars at beginning of string */ /* BB: check validity of these bytes? */ - src = unc + 2; + if (strlen(unc) < 3) + return ERR_PTR(-EINVAL); + for (src = unc; *src && *src == '\\'; src++) + ; + if (!*src) + return ERR_PTR(-EINVAL); /* delimiter between hostname and sharename is always '\\' now */ delim = strchr(src, '\\'); @@ -1827,7 +2017,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, vol->password = NULL; break; } - /* Yes it is. Drop down to Opt_pass below.*/ + /* Fallthrough - to Opt_pass below.*/ case Opt_pass: /* Obtain the value string */ value = strchr(data, '='); @@ -2289,7 +2479,7 @@ static int match_server(struct TCP_Server_Info *server, struct smb_vol *vol) return 1; } -static struct TCP_Server_Info * +struct TCP_Server_Info * cifs_find_tcp_session(struct smb_vol *vol) { struct TCP_Server_Info *server; @@ -2461,6 +2651,8 @@ smbd_connected: } tcp_ses->tcpStatus = CifsNeedNegotiate; + tcp_ses->nr_targets = 1; + /* thread spawned, put it on the list */ spin_lock(&cifs_tcp_ses_lock); list_add(&tcp_ses->tcp_ses_list, &cifs_tcp_ses_list); @@ -3256,25 +3448,6 @@ out: return rc; } -int -get_dfs_path(const unsigned int xid, struct cifs_ses *ses, const char *old_path, - const struct nls_table *nls_codepage, unsigned int *num_referrals, - struct dfs_info3_param **referrals, int remap) -{ - int rc = 0; - - if (!ses->server->ops->get_dfs_refer) - return -ENOSYS; - - *num_referrals = 0; - *referrals = NULL; - - rc = ses->server->ops->get_dfs_refer(xid, ses, old_path, - referrals, num_referrals, - nls_codepage, remap); - return rc; -} - #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key cifs_key[2]; static struct lock_class_key cifs_slock_key[2]; @@ -3746,8 +3919,8 @@ int cifs_setup_cifs_sb(struct smb_vol *pvolume_info, return 0; } -static void -cleanup_volume_info_contents(struct smb_vol *volume_info) +void +cifs_cleanup_volume_info_contents(struct smb_vol *volume_info) { kfree(volume_info->username); kzfree(volume_info->password); @@ -3762,10 +3935,136 @@ cifs_cleanup_volume_info(struct smb_vol *volume_info) { if (!volume_info) return; - cleanup_volume_info_contents(volume_info); + cifs_cleanup_volume_info_contents(volume_info); kfree(volume_info); } +/* Release all succeed connections */ +static inline void mount_put_conns(struct cifs_sb_info *cifs_sb, + unsigned int xid, + struct TCP_Server_Info *server, + struct cifs_ses *ses, struct cifs_tcon *tcon) +{ + int rc = 0; + + if (tcon) + cifs_put_tcon(tcon); + else if (ses) + cifs_put_smb_ses(ses); + else if (server) + cifs_put_tcp_session(server, 0); + cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; + free_xid(xid); +} + +/* Get connections for tcp, ses and tcon */ +static int mount_get_conns(struct smb_vol *vol, struct cifs_sb_info *cifs_sb, + unsigned int *xid, + struct TCP_Server_Info **nserver, + struct cifs_ses **nses, struct cifs_tcon **ntcon) +{ + int rc = 0; + struct TCP_Server_Info *server; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + *nserver = NULL; + *nses = NULL; + *ntcon = NULL; + + *xid = get_xid(); + + /* get a reference to a tcp session */ + server = cifs_get_tcp_session(vol); + if (IS_ERR(server)) { + rc = PTR_ERR(server); + return rc; + } + + *nserver = server; + + if ((vol->max_credits < 20) || (vol->max_credits > 60000)) + server->max_credits = SMB2_MAX_CREDITS_AVAILABLE; + else + server->max_credits = vol->max_credits; + + /* get a reference to a SMB session */ + ses = cifs_get_smb_ses(server, vol); + if (IS_ERR(ses)) { + rc = PTR_ERR(ses); + return rc; + } + + *nses = ses; + + if ((vol->persistent == true) && (!(ses->server->capabilities & + SMB2_GLOBAL_CAP_PERSISTENT_HANDLES))) { + cifs_dbg(VFS, "persistent handles not supported by server\n"); + return -EOPNOTSUPP; + } + + /* search for existing tcon to this server share */ + tcon = cifs_get_tcon(ses, vol); + if (IS_ERR(tcon)) { + rc = PTR_ERR(tcon); + return rc; + } + + *ntcon = tcon; + + /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ + if (tcon->posix_extensions) + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; + + /* tell server which Unix caps we support */ + if (cap_unix(tcon->ses)) { + /* + * reset of caps checks mount to see if unix extensions disabled + * for just this mount. + */ + reset_cifs_unix_caps(*xid, tcon, cifs_sb, vol); + if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && + (le64_to_cpu(tcon->fsUnixInfo.Capability) & + CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) + return -EACCES; + } else + tcon->unix_ext = 0; /* server does not support them */ + + /* do not care if a following call succeed - informational */ + if (!tcon->pipe && server->ops->qfs_tcon) + server->ops->qfs_tcon(*xid, tcon); + + cifs_sb->wsize = server->ops->negotiate_wsize(tcon, vol); + cifs_sb->rsize = server->ops->negotiate_rsize(tcon, vol); + + return 0; +} + +static int mount_setup_tlink(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, + struct cifs_tcon *tcon) +{ + struct tcon_link *tlink; + + /* hang the tcon off of the superblock */ + tlink = kzalloc(sizeof(*tlink), GFP_KERNEL); + if (tlink == NULL) + return -ENOMEM; + + tlink->tl_uid = ses->linux_uid; + tlink->tl_tcon = tcon; + tlink->tl_time = jiffies; + set_bit(TCON_LINK_MASTER, &tlink->tl_flags); + set_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); + + cifs_sb->master_tlink = tlink; + spin_lock(&cifs_sb->tlink_tree_lock); + tlink_rb_insert(&cifs_sb->tlink_tree, tlink); + spin_unlock(&cifs_sb->tlink_tree_lock); + + queue_delayed_work(cifsiod_wq, &cifs_sb->prune_tlinks, + TLINK_IDLE_EXPIRE); + return 0; +} #ifdef CONFIG_CIFS_DFS_UPCALL /* @@ -3774,10 +4073,11 @@ cifs_cleanup_volume_info(struct smb_vol *volume_info) */ static char * build_unc_path_to_root(const struct smb_vol *vol, - const struct cifs_sb_info *cifs_sb) + const struct cifs_sb_info *cifs_sb, bool useppath) { char *full_path, *pos; - unsigned int pplen = vol->prepath ? strlen(vol->prepath) + 1 : 0; + unsigned int pplen = useppath && vol->prepath ? + strlen(vol->prepath) + 1 : 0; unsigned int unc_len = strnlen(vol->UNC, MAX_TREE_SIZE + 1); full_path = kmalloc(unc_len + pplen + 1, GFP_KERNEL); @@ -3799,8 +4099,9 @@ build_unc_path_to_root(const struct smb_vol *vol, return full_path; } -/* - * Perform a dfs referral query for a share and (optionally) prefix +/** + * expand_dfs_referral - Perform a dfs referral query and update the cifs_sb + * * * If a referral is found, cifs_sb->mountdata will be (re-)allocated * to a string containing updated options for the submount. Otherwise it @@ -3815,39 +4116,36 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, int check_prefix) { int rc; - unsigned int num_referrals = 0; - struct dfs_info3_param *referrals = NULL; + struct dfs_info3_param referral = {0}; char *full_path = NULL, *ref_path = NULL, *mdata = NULL; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) return -EREMOTE; - full_path = build_unc_path_to_root(volume_info, cifs_sb); + full_path = build_unc_path_to_root(volume_info, cifs_sb, true); if (IS_ERR(full_path)) return PTR_ERR(full_path); /* For DFS paths, skip the first '\' of the UNC */ ref_path = check_prefix ? full_path + 1 : volume_info->UNC + 1; - rc = get_dfs_path(xid, ses, ref_path, cifs_sb->local_nls, - &num_referrals, &referrals, cifs_remap(cifs_sb)); - - if (!rc && num_referrals > 0) { + rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), + ref_path, &referral, NULL); + if (!rc) { char *fake_devname = NULL; mdata = cifs_compose_mount_options(cifs_sb->mountdata, - full_path + 1, referrals, + full_path + 1, &referral, &fake_devname); - - free_dfs_info_array(referrals, num_referrals); + free_dfs_info_param(&referral); if (IS_ERR(mdata)) { rc = PTR_ERR(mdata); mdata = NULL; } else { - cleanup_volume_info_contents(volume_info); + cifs_cleanup_volume_info_contents(volume_info); rc = cifs_setup_volume_info(volume_info, mdata, - fake_devname, false); + fake_devname, false); } kfree(fake_devname); kfree(cifs_sb->mountdata); @@ -3856,6 +4154,143 @@ expand_dfs_referral(const unsigned int xid, struct cifs_ses *ses, kfree(full_path); return rc; } + +static inline int get_next_dfs_tgt(const char *path, + struct dfs_cache_tgt_list *tgt_list, + struct dfs_cache_tgt_iterator **tgt_it) +{ + if (!*tgt_it) + *tgt_it = dfs_cache_get_tgt_iterator(tgt_list); + else + *tgt_it = dfs_cache_get_next_tgt(tgt_list, *tgt_it); + return !*tgt_it ? -EHOSTDOWN : 0; +} + +static int update_vol_info(const struct dfs_cache_tgt_iterator *tgt_it, + struct smb_vol *fake_vol, struct smb_vol *vol) +{ + const char *tgt = dfs_cache_get_tgt_name(tgt_it); + int len = strlen(tgt) + 2; + char *new_unc; + + new_unc = kmalloc(len, GFP_KERNEL); + if (!new_unc) + return -ENOMEM; + snprintf(new_unc, len, "\\%s", tgt); + + kfree(vol->UNC); + vol->UNC = new_unc; + + if (fake_vol->prepath) { + kfree(vol->prepath); + vol->prepath = fake_vol->prepath; + fake_vol->prepath = NULL; + } + memcpy(&vol->dstaddr, &fake_vol->dstaddr, sizeof(vol->dstaddr)); + + return 0; +} + +static int setup_dfs_tgt_conn(const char *path, + const struct dfs_cache_tgt_iterator *tgt_it, + struct cifs_sb_info *cifs_sb, + struct smb_vol *vol, + unsigned int *xid, + struct TCP_Server_Info **server, + struct cifs_ses **ses, + struct cifs_tcon **tcon) +{ + int rc; + struct dfs_info3_param ref = {0}; + char *mdata = NULL, *fake_devname = NULL; + struct smb_vol fake_vol = {0}; + + cifs_dbg(FYI, "%s: dfs path: %s\n", __func__, path); + + rc = dfs_cache_get_tgt_referral(path, tgt_it, &ref); + if (rc) + return rc; + + mdata = cifs_compose_mount_options(cifs_sb->mountdata, path, &ref, + &fake_devname); + free_dfs_info_param(&ref); + + if (IS_ERR(mdata)) { + rc = PTR_ERR(mdata); + mdata = NULL; + } else { + cifs_dbg(FYI, "%s: fake_devname: %s\n", __func__, fake_devname); + rc = cifs_setup_volume_info(&fake_vol, mdata, fake_devname, + false); + } + kfree(mdata); + kfree(fake_devname); + + if (!rc) { + /* + * We use a 'fake_vol' here because we need pass it down to the + * mount_{get,put} functions to test connection against new DFS + * targets. + */ + mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon); + rc = mount_get_conns(&fake_vol, cifs_sb, xid, server, ses, + tcon); + if (!rc) { + /* + * We were able to connect to new target server. + * Update current volume info with new target server. + */ + rc = update_vol_info(tgt_it, &fake_vol, vol); + } + } + cifs_cleanup_volume_info_contents(&fake_vol); + return rc; +} + +static int mount_do_dfs_failover(const char *path, + struct cifs_sb_info *cifs_sb, + struct smb_vol *vol, + struct cifs_ses *root_ses, + unsigned int *xid, + struct TCP_Server_Info **server, + struct cifs_ses **ses, + struct cifs_tcon **tcon) +{ + int rc; + struct dfs_cache_tgt_list tgt_list; + struct dfs_cache_tgt_iterator *tgt_it = NULL; + + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) + return -EOPNOTSUPP; + + rc = dfs_cache_noreq_find(path, NULL, &tgt_list); + if (rc) + return rc; + + for (;;) { + /* Get next DFS target server - if any */ + rc = get_next_dfs_tgt(path, &tgt_list, &tgt_it); + if (rc) + break; + /* Connect to next DFS target */ + rc = setup_dfs_tgt_conn(path, tgt_it, cifs_sb, vol, xid, server, + ses, tcon); + if (!rc || rc == -EACCES || rc == -EOPNOTSUPP) + break; + } + if (!rc) { + /* + * Update DFS target hint in DFS referral cache with the target + * server we successfully reconnected to. + */ + rc = dfs_cache_update_tgthint(*xid, root_ses ? root_ses : *ses, + cifs_sb->local_nls, + cifs_remap(cifs_sb), path, + tgt_it); + } + dfs_cache_free_tgts(&tgt_list); + return rc; +} #endif static int @@ -3954,107 +4389,108 @@ cifs_are_all_path_components_accessible(struct TCP_Server_Info *server, return rc; } -int -cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info) +/* + * Check if path is remote (e.g. a DFS share). Return -EREMOTE if it is, + * otherwise 0. + */ +static int is_path_remote(struct cifs_sb_info *cifs_sb, struct smb_vol *vol, + const unsigned int xid, + struct TCP_Server_Info *server, + struct cifs_tcon *tcon) { int rc; - unsigned int xid; - struct cifs_ses *ses; - struct cifs_tcon *tcon; - struct TCP_Server_Info *server; - char *full_path; - struct tcon_link *tlink; -#ifdef CONFIG_CIFS_DFS_UPCALL - int referral_walks_count = 0; -#endif + char *full_path; -#ifdef CONFIG_CIFS_DFS_UPCALL -try_mount_again: - /* cleanup activities if we're chasing a referral */ - if (referral_walks_count) { - if (tcon) - cifs_put_tcon(tcon); - else if (ses) - cifs_put_smb_ses(ses); + if (!server->ops->is_path_accessible) + return -EOPNOTSUPP; - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; - - free_xid(xid); - } -#endif - rc = 0; - tcon = NULL; - ses = NULL; - server = NULL; - full_path = NULL; - tlink = NULL; + /* + * cifs_build_path_to_root works only when we have a valid tcon + */ + full_path = cifs_build_path_to_root(vol, cifs_sb, tcon, + tcon->Flags & SMB_SHARE_IS_IN_DFS); + if (full_path == NULL) + return -ENOMEM; - xid = get_xid(); + cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); - /* get a reference to a tcp session */ - server = cifs_get_tcp_session(volume_info); - if (IS_ERR(server)) { - rc = PTR_ERR(server); - goto out; - } - if ((volume_info->max_credits < 20) || - (volume_info->max_credits > 60000)) - server->max_credits = SMB2_MAX_CREDITS_AVAILABLE; - else - server->max_credits = volume_info->max_credits; - /* get a reference to a SMB session */ - ses = cifs_get_smb_ses(server, volume_info); - if (IS_ERR(ses)) { - rc = PTR_ERR(ses); - ses = NULL; - goto mount_fail_check; + rc = server->ops->is_path_accessible(xid, tcon, cifs_sb, + full_path); + if (rc != 0 && rc != -EREMOTE) { + kfree(full_path); + return rc; } - if ((volume_info->persistent == true) && ((ses->server->capabilities & - SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) { - cifs_dbg(VFS, "persistent handles not supported by server\n"); - rc = -EOPNOTSUPP; - goto mount_fail_check; + if (rc != -EREMOTE) { + rc = cifs_are_all_path_components_accessible(server, xid, tcon, + cifs_sb, + full_path); + if (rc != 0) { + cifs_dbg(VFS, "cannot query dirs between root and final path, " + "enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); + cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + rc = 0; + } } - /* search for existing tcon to this server share */ - tcon = cifs_get_tcon(ses, volume_info); - if (IS_ERR(tcon)) { - rc = PTR_ERR(tcon); - tcon = NULL; - if (rc == -EACCES) - goto mount_fail_check; - - goto remote_path_check; - } + kfree(full_path); + return rc; +} - /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */ - if (tcon->posix_extensions) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; +#ifdef CONFIG_CIFS_DFS_UPCALL +int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) +{ + int rc = 0; + unsigned int xid; + struct cifs_ses *ses; + struct cifs_tcon *root_tcon = NULL; + struct cifs_tcon *tcon = NULL; + struct TCP_Server_Info *server; + char *root_path = NULL, *full_path = NULL; + char *old_mountdata; + int count; - /* tell server which Unix caps we support */ - if (cap_unix(tcon->ses)) { - /* reset of caps checks mount to see if unix extensions - disabled for just this mount */ - reset_cifs_unix_caps(xid, tcon, cifs_sb, volume_info); - if ((tcon->ses->server->tcpStatus == CifsNeedReconnect) && - (le64_to_cpu(tcon->fsUnixInfo.Capability) & - CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP)) { - rc = -EACCES; - goto mount_fail_check; + rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, &tcon); + if (!rc && tcon) { + /* If not a standalone DFS root, then check if path is remote */ + rc = dfs_cache_find(xid, ses, cifs_sb->local_nls, + cifs_remap(cifs_sb), vol->UNC + 1, NULL, + NULL); + if (rc) { + rc = is_path_remote(cifs_sb, vol, xid, server, tcon); + if (!rc) + goto out; + if (rc != -EREMOTE) + goto error; } - } else - tcon->unix_ext = 0; /* server does not support them */ - - /* do not care if a following call succeed - informational */ - if (!tcon->pipe && server->ops->qfs_tcon) - server->ops->qfs_tcon(xid, tcon); - - cifs_sb->wsize = server->ops->negotiate_wsize(tcon, volume_info); - cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info); + } + /* + * If first DFS target server went offline and we failed to connect it, + * server and ses pointers are NULL at this point, though we still have + * chance to get a cached DFS referral in expand_dfs_referral() and + * retry next target available in it. + * + * If a NULL ses ptr is passed to dfs_cache_find(), a lookup will be + * performed against DFS path and *no* requests will be sent to server + * for any new DFS referrals. Hence it's safe to skip checking whether + * server or ses ptr is NULL. + */ + if (rc == -EACCES || rc == -EOPNOTSUPP) + goto error; + + root_path = build_unc_path_to_root(vol, cifs_sb, false); + if (IS_ERR(root_path)) { + rc = PTR_ERR(root_path); + root_path = NULL; + goto error; + } -remote_path_check: -#ifdef CONFIG_CIFS_DFS_UPCALL + full_path = build_unc_path_to_root(vol, cifs_sb, true); + if (IS_ERR(full_path)) { + rc = PTR_ERR(full_path); + full_path = NULL; + goto error; + } /* * Perform an unconditional check for whether there are DFS * referrals for this path without prefix, to provide support @@ -4062,119 +4498,173 @@ remote_path_check: * with PATH_NOT_COVERED to requests that include the prefix. * Chase the referral if found, otherwise continue normally. */ - if (referral_walks_count == 0) { - int refrc = expand_dfs_referral(xid, ses, volume_info, cifs_sb, - false); - if (!refrc) { - referral_walks_count++; - goto try_mount_again; - } + old_mountdata = cifs_sb->mountdata; + (void)expand_dfs_referral(xid, ses, vol, cifs_sb, false); + + if (cifs_sb->mountdata == NULL) { + rc = -ENOENT; + goto error; } -#endif - /* check if a whole path is not remote */ - if (!rc && tcon) { - if (!server->ops->is_path_accessible) { - rc = -ENOSYS; - goto mount_fail_check; + if (cifs_sb->mountdata != old_mountdata) { + /* If we were redirected, reconnect to new target server */ + mount_put_conns(cifs_sb, xid, server, ses, tcon); + rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, &tcon); + } + if (rc) { + if (rc == -EACCES || rc == -EOPNOTSUPP) + goto error; + /* Perform DFS failover to any other DFS targets */ + rc = mount_do_dfs_failover(root_path + 1, cifs_sb, vol, NULL, + &xid, &server, &ses, &tcon); + if (rc) + goto error; + } + + kfree(root_path); + root_path = build_unc_path_to_root(vol, cifs_sb, false); + if (IS_ERR(root_path)) { + rc = PTR_ERR(root_path); + root_path = NULL; + goto error; + } + /* Cache out resolved root server */ + (void)dfs_cache_find(xid, ses, cifs_sb->local_nls, cifs_remap(cifs_sb), + root_path + 1, NULL, NULL); + /* + * Save root tcon for additional DFS requests to update or create a new + * DFS cache entry, or even perform DFS failover. + */ + spin_lock(&cifs_tcp_ses_lock); + tcon->tc_count++; + tcon->dfs_path = root_path; + root_path = NULL; + tcon->remap = cifs_remap(cifs_sb); + spin_unlock(&cifs_tcp_ses_lock); + + root_tcon = tcon; + + for (count = 1; ;) { + if (!rc && tcon) { + rc = is_path_remote(cifs_sb, vol, xid, server, tcon); + if (!rc || rc != -EREMOTE) + break; } /* - * cifs_build_path_to_root works only when we have a valid tcon + * BB: when we implement proper loop detection, + * we will remove this check. But now we need it + * to prevent an indefinite loop if 'DFS tree' is + * misconfigured (i.e. has loops). */ - full_path = cifs_build_path_to_root(volume_info, cifs_sb, tcon, - tcon->Flags & SMB_SHARE_IS_IN_DFS); - if (full_path == NULL) { - rc = -ENOMEM; - goto mount_fail_check; - } - rc = server->ops->is_path_accessible(xid, tcon, cifs_sb, - full_path); - if (rc != 0 && rc != -EREMOTE) { - kfree(full_path); - goto mount_fail_check; + if (count++ > MAX_NESTED_LINKS) { + rc = -ELOOP; + break; } - if (rc != -EREMOTE) { - rc = cifs_are_all_path_components_accessible(server, - xid, tcon, cifs_sb, - full_path); - if (rc != 0) { - cifs_dbg(VFS, "cannot query dirs between root and final path, " - "enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; - rc = 0; - } - } kfree(full_path); - } - - /* get referral if needed */ - if (rc == -EREMOTE) { -#ifdef CONFIG_CIFS_DFS_UPCALL - if (referral_walks_count > MAX_NESTED_LINKS) { - /* - * BB: when we implement proper loop detection, - * we will remove this check. But now we need it - * to prevent an indefinite loop if 'DFS tree' is - * misconfigured (i.e. has loops). - */ - rc = -ELOOP; - goto mount_fail_check; + full_path = build_unc_path_to_root(vol, cifs_sb, true); + if (IS_ERR(full_path)) { + rc = PTR_ERR(full_path); + full_path = NULL; + break; } - rc = expand_dfs_referral(xid, ses, volume_info, cifs_sb, true); + old_mountdata = cifs_sb->mountdata; + rc = expand_dfs_referral(xid, root_tcon->ses, vol, cifs_sb, + true); + if (rc) + break; - if (!rc) { - referral_walks_count++; - goto try_mount_again; + if (cifs_sb->mountdata != old_mountdata) { + mount_put_conns(cifs_sb, xid, server, ses, tcon); + rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, + &tcon); + } + if (rc) { + if (rc == -EACCES || rc == -EOPNOTSUPP) + break; + /* Perform DFS failover to any other DFS targets */ + rc = mount_do_dfs_failover(full_path + 1, cifs_sb, vol, + root_tcon->ses, &xid, + &server, &ses, &tcon); + if (rc == -EACCES || rc == -EOPNOTSUPP || !server || + !ses) + goto error; } - goto mount_fail_check; -#else /* No DFS support, return error on mount */ - rc = -EOPNOTSUPP; -#endif } + cifs_put_tcon(root_tcon); if (rc) - goto mount_fail_check; + goto error; - /* now, hang the tcon off of the superblock */ - tlink = kzalloc(sizeof *tlink, GFP_KERNEL); - if (tlink == NULL) { + spin_lock(&cifs_tcp_ses_lock); + if (!tcon->dfs_path) { + /* Save full path in new tcon to do failover when reconnecting tcons */ + tcon->dfs_path = full_path; + full_path = NULL; + tcon->remap = cifs_remap(cifs_sb); + } + cifs_sb->origin_fullpath = kstrndup(tcon->dfs_path, + strlen(tcon->dfs_path), + GFP_ATOMIC); + if (!cifs_sb->origin_fullpath) { + spin_unlock(&cifs_tcp_ses_lock); rc = -ENOMEM; - goto mount_fail_check; + goto error; } + spin_unlock(&cifs_tcp_ses_lock); - tlink->tl_uid = ses->linux_uid; - tlink->tl_tcon = tcon; - tlink->tl_time = jiffies; - set_bit(TCON_LINK_MASTER, &tlink->tl_flags); - set_bit(TCON_LINK_IN_TREE, &tlink->tl_flags); + rc = dfs_cache_add_vol(vol, cifs_sb->origin_fullpath); + if (rc) { + kfree(cifs_sb->origin_fullpath); + goto error; + } + /* + * After reconnecting to a different server, unique ids won't + * match anymore, so we disable serverino. This prevents + * dentry revalidation to think the dentry are stale (ESTALE). + */ + cifs_autodisable_serverino(cifs_sb); +out: + free_xid(xid); + return mount_setup_tlink(cifs_sb, ses, tcon); - cifs_sb->master_tlink = tlink; - spin_lock(&cifs_sb->tlink_tree_lock); - tlink_rb_insert(&cifs_sb->tlink_tree, tlink); - spin_unlock(&cifs_sb->tlink_tree_lock); +error: + kfree(full_path); + kfree(root_path); + mount_put_conns(cifs_sb, xid, server, ses, tcon); + return rc; +} +#else +int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *vol) +{ + int rc = 0; + unsigned int xid; + struct cifs_ses *ses; + struct cifs_tcon *tcon; + struct TCP_Server_Info *server; - queue_delayed_work(cifsiod_wq, &cifs_sb->prune_tlinks, - TLINK_IDLE_EXPIRE); + rc = mount_get_conns(vol, cifs_sb, &xid, &server, &ses, &tcon); + if (rc) + goto error; -mount_fail_check: - /* on error free sesinfo and tcon struct if needed */ - if (rc) { - /* If find_unc succeeded then rc == 0 so we can not end */ - /* up accidentally freeing someone elses tcon struct */ - if (tcon) - cifs_put_tcon(tcon); - else if (ses) - cifs_put_smb_ses(ses); - else - cifs_put_tcp_session(server, 0); + if (tcon) { + rc = is_path_remote(cifs_sb, vol, xid, server, tcon); + if (rc == -EREMOTE) + rc = -EOPNOTSUPP; + if (rc) + goto error; } -out: free_xid(xid); + + return mount_setup_tlink(cifs_sb, ses, tcon); + +error: + mount_put_conns(cifs_sb, xid, server, ses, tcon); return rc; } +#endif /* * Issue a TREE_CONNECT request. @@ -4370,6 +4860,10 @@ cifs_umount(struct cifs_sb_info *cifs_sb) kfree(cifs_sb->mountdata); kfree(cifs_sb->prepath); +#ifdef CONFIG_CIFS_DFS_UPCALL + dfs_cache_del_vol(cifs_sb->origin_fullpath); + kfree(cifs_sb->origin_fullpath); +#endif call_rcu(&cifs_sb->rcu, delayed_free); } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c new file mode 100644 index 000000000000..cd63c4a70875 --- /dev/null +++ b/fs/cifs/dfs_cache.c @@ -0,0 +1,1367 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DFS referral cache routines + * + * Copyright (c) 2018 Paulo Alcantara <palcantara@suse.de> + */ + +#include <linux/rcupdate.h> +#include <linux/rculist.h> +#include <linux/jhash.h> +#include <linux/ktime.h> +#include <linux/slab.h> +#include <linux/nls.h> +#include <linux/workqueue.h> +#include "cifsglob.h" +#include "smb2pdu.h" +#include "smb2proto.h" +#include "cifsproto.h" +#include "cifs_debug.h" +#include "cifs_unicode.h" +#include "smb2glob.h" + +#include "dfs_cache.h" + +#define DFS_CACHE_HTABLE_SIZE 32 +#define DFS_CACHE_MAX_ENTRIES 64 + +#define IS_INTERLINK_SET(v) ((v) & (DFSREF_REFERRAL_SERVER | \ + DFSREF_STORAGE_SERVER)) + +struct dfs_cache_tgt { + char *t_name; + struct list_head t_list; +}; + +struct dfs_cache_entry { + struct hlist_node ce_hlist; + const char *ce_path; + int ce_ttl; + int ce_srvtype; + int ce_flags; + struct timespec64 ce_etime; + int ce_path_consumed; + int ce_numtgts; + struct list_head ce_tlist; + struct dfs_cache_tgt *ce_tgthint; + struct rcu_head ce_rcu; +}; + +static struct kmem_cache *dfs_cache_slab __read_mostly; + +struct dfs_cache_vol_info { + char *vi_fullpath; + struct smb_vol vi_vol; + struct list_head vi_list; +}; + +struct dfs_cache { + struct mutex dc_lock; + struct nls_table *dc_nlsc; + struct list_head dc_vol_list; + int dc_ttl; + struct delayed_work dc_refresh; +}; + +static struct dfs_cache dfs_cache; + +/* + * Number of entries in the cache + */ +static size_t dfs_cache_count; + +static DEFINE_MUTEX(dfs_cache_list_lock); +static struct hlist_head dfs_cache_htable[DFS_CACHE_HTABLE_SIZE]; + +static void refresh_cache_worker(struct work_struct *work); + +static inline bool is_path_valid(const char *path) +{ + return path && (strchr(path + 1, '\\') || strchr(path + 1, '/')); +} + +static inline int get_normalized_path(const char *path, char **npath) +{ + if (*path == '\\') { + *npath = (char *)path; + } else { + *npath = kstrndup(path, strlen(path), GFP_KERNEL); + if (!*npath) + return -ENOMEM; + convert_delimiter(*npath, '\\'); + } + return 0; +} + +static inline void free_normalized_path(const char *path, char *npath) +{ + if (path != npath) + kfree(npath); +} + +static inline bool cache_entry_expired(const struct dfs_cache_entry *ce) +{ + struct timespec64 ts; + + ktime_get_coarse_real_ts64(&ts); + return timespec64_compare(&ts, &ce->ce_etime) >= 0; +} + +static inline void free_tgts(struct dfs_cache_entry *ce) +{ + struct dfs_cache_tgt *t, *n; + + list_for_each_entry_safe(t, n, &ce->ce_tlist, t_list) { + list_del(&t->t_list); + kfree(t->t_name); + kfree(t); + } +} + +static void free_cache_entry(struct rcu_head *rcu) +{ + struct dfs_cache_entry *ce = container_of(rcu, struct dfs_cache_entry, + ce_rcu); + kmem_cache_free(dfs_cache_slab, ce); +} + +static inline void flush_cache_ent(struct dfs_cache_entry *ce) +{ + if (hlist_unhashed(&ce->ce_hlist)) + return; + + hlist_del_init_rcu(&ce->ce_hlist); + kfree(ce->ce_path); + free_tgts(ce); + dfs_cache_count--; + call_rcu(&ce->ce_rcu, free_cache_entry); +} + +static void flush_cache_ents(void) +{ + int i; + + rcu_read_lock(); + for (i = 0; i < DFS_CACHE_HTABLE_SIZE; i++) { + struct hlist_head *l = &dfs_cache_htable[i]; + struct dfs_cache_entry *ce; + + hlist_for_each_entry_rcu(ce, l, ce_hlist) + flush_cache_ent(ce); + } + rcu_read_unlock(); +} + +/* + * dfs cache /proc file + */ +static int dfscache_proc_show(struct seq_file *m, void *v) +{ + int bucket; + struct dfs_cache_entry *ce; + struct dfs_cache_tgt *t; + + seq_puts(m, "DFS cache\n---------\n"); + + mutex_lock(&dfs_cache_list_lock); + + rcu_read_lock(); + hash_for_each_rcu(dfs_cache_htable, bucket, ce, ce_hlist) { + seq_printf(m, + "cache entry: path=%s,type=%s,ttl=%d,etime=%ld," + "interlink=%s,path_consumed=%d,expired=%s\n", + ce->ce_path, + ce->ce_srvtype == DFS_TYPE_ROOT ? "root" : "link", + ce->ce_ttl, ce->ce_etime.tv_nsec, + IS_INTERLINK_SET(ce->ce_flags) ? "yes" : "no", + ce->ce_path_consumed, + cache_entry_expired(ce) ? "yes" : "no"); + + list_for_each_entry(t, &ce->ce_tlist, t_list) { + seq_printf(m, " %s%s\n", + t->t_name, + ce->ce_tgthint == t ? " (target hint)" : ""); + } + + } + rcu_read_unlock(); + + mutex_unlock(&dfs_cache_list_lock); + return 0; +} + +static ssize_t dfscache_proc_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + char c; + int rc; + + rc = get_user(c, buffer); + if (rc) + return rc; + + if (c != '0') + return -EINVAL; + + cifs_dbg(FYI, "clearing dfs cache"); + mutex_lock(&dfs_cache_list_lock); + flush_cache_ents(); + mutex_unlock(&dfs_cache_list_lock); + + return count; +} + +static int dfscache_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, dfscache_proc_show, NULL); +} + +const struct file_operations dfscache_proc_fops = { + .open = dfscache_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = dfscache_proc_write, +}; + +#ifdef CONFIG_CIFS_DEBUG2 +static inline void dump_tgts(const struct dfs_cache_entry *ce) +{ + struct dfs_cache_tgt *t; + + cifs_dbg(FYI, "target list:\n"); + list_for_each_entry(t, &ce->ce_tlist, t_list) { + cifs_dbg(FYI, " %s%s\n", t->t_name, + ce->ce_tgthint == t ? " (target hint)" : ""); + } +} + +static inline void dump_ce(const struct dfs_cache_entry *ce) +{ + cifs_dbg(FYI, "cache entry: path=%s,type=%s,ttl=%d,etime=%ld," + "interlink=%s,path_consumed=%d,expired=%s\n", ce->ce_path, + ce->ce_srvtype == DFS_TYPE_ROOT ? "root" : "link", ce->ce_ttl, + ce->ce_etime.tv_nsec, + IS_INTERLINK_SET(ce->ce_flags) ? "yes" : "no", + ce->ce_path_consumed, + cache_entry_expired(ce) ? "yes" : "no"); + dump_tgts(ce); +} + +static inline void dump_refs(const struct dfs_info3_param *refs, int numrefs) +{ + int i; + + cifs_dbg(FYI, "DFS referrals returned by the server:\n"); + for (i = 0; i < numrefs; i++) { + const struct dfs_info3_param *ref = &refs[i]; + + cifs_dbg(FYI, + "\n" + "flags: 0x%x\n" + "path_consumed: %d\n" + "server_type: 0x%x\n" + "ref_flag: 0x%x\n" + "path_name: %s\n" + "node_name: %s\n" + "ttl: %d (%dm)\n", + ref->flags, ref->path_consumed, ref->server_type, + ref->ref_flag, ref->path_name, ref->node_name, + ref->ttl, ref->ttl / 60); + } +} +#else +#define dump_tgts(e) +#define dump_ce(e) +#define dump_refs(r, n) +#endif + +/** + * dfs_cache_init - Initialize DFS referral cache. + * + * Return zero if initialized successfully, otherwise non-zero. + */ +int dfs_cache_init(void) +{ + int i; + + dfs_cache_slab = kmem_cache_create("cifs_dfs_cache", + sizeof(struct dfs_cache_entry), 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!dfs_cache_slab) + return -ENOMEM; + + for (i = 0; i < DFS_CACHE_HTABLE_SIZE; i++) + INIT_HLIST_HEAD(&dfs_cache_htable[i]); + + INIT_LIST_HEAD(&dfs_cache.dc_vol_list); + mutex_init(&dfs_cache.dc_lock); + INIT_DELAYED_WORK(&dfs_cache.dc_refresh, refresh_cache_worker); + dfs_cache.dc_ttl = -1; + dfs_cache.dc_nlsc = load_nls_default(); + + cifs_dbg(FYI, "%s: initialized DFS referral cache\n", __func__); + return 0; +} + +static inline unsigned int cache_entry_hash(const void *data, int size) +{ + unsigned int h; + + h = jhash(data, size, 0); + return h & (DFS_CACHE_HTABLE_SIZE - 1); +} + +/* Check whether second path component of @path is SYSVOL or NETLOGON */ +static inline bool is_sysvol_or_netlogon(const char *path) +{ + const char *s; + char sep = path[0]; + + s = strchr(path + 1, sep) + 1; + return !strncasecmp(s, "sysvol", strlen("sysvol")) || + !strncasecmp(s, "netlogon", strlen("netlogon")); +} + +/* Return target hint of a DFS cache entry */ +static inline char *get_tgt_name(const struct dfs_cache_entry *ce) +{ + struct dfs_cache_tgt *t = ce->ce_tgthint; + + return t ? t->t_name : ERR_PTR(-ENOENT); +} + +/* Return expire time out of a new entry's TTL */ +static inline struct timespec64 get_expire_time(int ttl) +{ + struct timespec64 ts = { + .tv_sec = ttl, + .tv_nsec = 0, + }; + struct timespec64 now; + + ktime_get_coarse_real_ts64(&now); + return timespec64_add(now, ts); +} + +/* Allocate a new DFS target */ +static inline struct dfs_cache_tgt *alloc_tgt(const char *name) +{ + struct dfs_cache_tgt *t; + + t = kmalloc(sizeof(*t), GFP_KERNEL); + if (!t) + return ERR_PTR(-ENOMEM); + t->t_name = kstrndup(name, strlen(name), GFP_KERNEL); + if (!t->t_name) { + kfree(t); + return ERR_PTR(-ENOMEM); + } + INIT_LIST_HEAD(&t->t_list); + return t; +} + +/* + * Copy DFS referral information to a cache entry and conditionally update + * target hint. + */ +static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, + struct dfs_cache_entry *ce, const char *tgthint) +{ + int i; + + ce->ce_ttl = refs[0].ttl; + ce->ce_etime = get_expire_time(ce->ce_ttl); + ce->ce_srvtype = refs[0].server_type; + ce->ce_flags = refs[0].ref_flag; + ce->ce_path_consumed = refs[0].path_consumed; + + for (i = 0; i < numrefs; i++) { + struct dfs_cache_tgt *t; + + t = alloc_tgt(refs[i].node_name); + if (IS_ERR(t)) { + free_tgts(ce); + return PTR_ERR(t); + } + if (tgthint && !strcasecmp(t->t_name, tgthint)) { + list_add(&t->t_list, &ce->ce_tlist); + tgthint = NULL; + } else { + list_add_tail(&t->t_list, &ce->ce_tlist); + } + ce->ce_numtgts++; + } + + ce->ce_tgthint = list_first_entry_or_null(&ce->ce_tlist, + struct dfs_cache_tgt, t_list); + + return 0; +} + +/* Allocate a new cache entry */ +static struct dfs_cache_entry * +alloc_cache_entry(const char *path, const struct dfs_info3_param *refs, + int numrefs) +{ + struct dfs_cache_entry *ce; + int rc; + + ce = kmem_cache_zalloc(dfs_cache_slab, GFP_KERNEL); + if (!ce) + return ERR_PTR(-ENOMEM); + + ce->ce_path = kstrdup_const(path, GFP_KERNEL); + if (!ce->ce_path) { + kmem_cache_free(dfs_cache_slab, ce); + return ERR_PTR(-ENOMEM); + } + INIT_HLIST_NODE(&ce->ce_hlist); + INIT_LIST_HEAD(&ce->ce_tlist); + + rc = copy_ref_data(refs, numrefs, ce, NULL); + if (rc) { + kfree(ce->ce_path); + kmem_cache_free(dfs_cache_slab, ce); + ce = ERR_PTR(rc); + } + return ce; +} + +static void remove_oldest_entry(void) +{ + int bucket; + struct dfs_cache_entry *ce; + struct dfs_cache_entry *to_del = NULL; + + rcu_read_lock(); + hash_for_each_rcu(dfs_cache_htable, bucket, ce, ce_hlist) { + if (!to_del || timespec64_compare(&ce->ce_etime, + &to_del->ce_etime) < 0) + to_del = ce; + } + if (!to_del) { + cifs_dbg(FYI, "%s: no entry to remove", __func__); + goto out; + } + cifs_dbg(FYI, "%s: removing entry", __func__); + dump_ce(to_del); + flush_cache_ent(to_del); +out: + rcu_read_unlock(); +} + +/* Add a new DFS cache entry */ +static inline struct dfs_cache_entry * +add_cache_entry(unsigned int hash, const char *path, + const struct dfs_info3_param *refs, int numrefs) +{ + struct dfs_cache_entry *ce; + + ce = alloc_cache_entry(path, refs, numrefs); + if (IS_ERR(ce)) + return ce; + + hlist_add_head_rcu(&ce->ce_hlist, &dfs_cache_htable[hash]); + + mutex_lock(&dfs_cache.dc_lock); + if (dfs_cache.dc_ttl < 0) { + dfs_cache.dc_ttl = ce->ce_ttl; + queue_delayed_work(cifsiod_wq, &dfs_cache.dc_refresh, + dfs_cache.dc_ttl * HZ); + } else { + dfs_cache.dc_ttl = min_t(int, dfs_cache.dc_ttl, ce->ce_ttl); + mod_delayed_work(cifsiod_wq, &dfs_cache.dc_refresh, + dfs_cache.dc_ttl * HZ); + } + mutex_unlock(&dfs_cache.dc_lock); + + return ce; +} + +static struct dfs_cache_entry *__find_cache_entry(unsigned int hash, + const char *path) +{ + struct dfs_cache_entry *ce; + bool found = false; + + rcu_read_lock(); + hlist_for_each_entry_rcu(ce, &dfs_cache_htable[hash], ce_hlist) { + if (!strcasecmp(path, ce->ce_path)) { +#ifdef CONFIG_CIFS_DEBUG2 + char *name = get_tgt_name(ce); + + if (unlikely(IS_ERR(name))) { + rcu_read_unlock(); + return ERR_CAST(name); + } + cifs_dbg(FYI, "%s: cache hit\n", __func__); + cifs_dbg(FYI, "%s: target hint: %s\n", __func__, name); +#endif + found = true; + break; + } + } + rcu_read_unlock(); + return found ? ce : ERR_PTR(-ENOENT); +} + +/* + * Find a DFS cache entry in hash table and optionally check prefix path against + * @path. + * Use whole path components in the match. + * Return ERR_PTR(-ENOENT) if the entry is not found. + */ +static inline struct dfs_cache_entry *find_cache_entry(const char *path, + unsigned int *hash) +{ + *hash = cache_entry_hash(path, strlen(path)); + return __find_cache_entry(*hash, path); +} + +static inline void destroy_slab_cache(void) +{ + rcu_barrier(); + kmem_cache_destroy(dfs_cache_slab); +} + +static inline void free_vol(struct dfs_cache_vol_info *vi) +{ + list_del(&vi->vi_list); + kfree(vi->vi_fullpath); + cifs_cleanup_volume_info_contents(&vi->vi_vol); + kfree(vi); +} + +static inline void free_vol_list(void) +{ + struct dfs_cache_vol_info *vi, *nvi; + + list_for_each_entry_safe(vi, nvi, &dfs_cache.dc_vol_list, vi_list) + free_vol(vi); +} + +/** + * dfs_cache_destroy - destroy DFS referral cache + */ +void dfs_cache_destroy(void) +{ + cancel_delayed_work_sync(&dfs_cache.dc_refresh); + unload_nls(dfs_cache.dc_nlsc); + free_vol_list(); + mutex_destroy(&dfs_cache.dc_lock); + + flush_cache_ents(); + destroy_slab_cache(); + mutex_destroy(&dfs_cache_list_lock); + + cifs_dbg(FYI, "%s: destroyed DFS referral cache\n", __func__); +} + +static inline struct dfs_cache_entry * +__update_cache_entry(const char *path, const struct dfs_info3_param *refs, + int numrefs) +{ + int rc; + unsigned int h; + struct dfs_cache_entry *ce; + char *s, *th = NULL; + + ce = find_cache_entry(path, &h); + if (IS_ERR(ce)) + return ce; + + if (ce->ce_tgthint) { + s = ce->ce_tgthint->t_name; + th = kstrndup(s, strlen(s), GFP_KERNEL); + if (!th) + return ERR_PTR(-ENOMEM); + } + + free_tgts(ce); + ce->ce_numtgts = 0; + + rc = copy_ref_data(refs, numrefs, ce, th); + kfree(th); + + if (rc) + ce = ERR_PTR(rc); + + return ce; +} + +/* Update an expired cache entry by getting a new DFS referral from server */ +static struct dfs_cache_entry * +update_cache_entry(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *nls_codepage, int remap, + const char *path, struct dfs_cache_entry *ce) +{ + int rc; + struct dfs_info3_param *refs = NULL; + int numrefs = 0; + + cifs_dbg(FYI, "%s: update expired cache entry\n", __func__); + /* + * Check if caller provided enough parameters to update an expired + * entry. + */ + if (!ses || !ses->server || !ses->server->ops->get_dfs_refer) + return ERR_PTR(-ETIME); + if (unlikely(!nls_codepage)) + return ERR_PTR(-ETIME); + + cifs_dbg(FYI, "%s: DFS referral request for %s\n", __func__, path); + + rc = ses->server->ops->get_dfs_refer(xid, ses, path, &refs, &numrefs, + nls_codepage, remap); + if (rc) + ce = ERR_PTR(rc); + else + ce = __update_cache_entry(path, refs, numrefs); + + dump_refs(refs, numrefs); + free_dfs_info_array(refs, numrefs); + + return ce; +} + +/* + * Find, create or update a DFS cache entry. + * + * If the entry wasn't found, it will create a new one. Or if it was found but + * expired, then it will update the entry accordingly. + * + * For interlinks, __cifs_dfs_mount() and expand_dfs_referral() are supposed to + * handle them properly. + */ +static struct dfs_cache_entry * +do_dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *nls_codepage, int remap, + const char *path, bool noreq) +{ + int rc; + unsigned int h; + struct dfs_cache_entry *ce; + struct dfs_info3_param *nrefs; + int numnrefs; + + cifs_dbg(FYI, "%s: search path: %s\n", __func__, path); + + ce = find_cache_entry(path, &h); + if (IS_ERR(ce)) { + cifs_dbg(FYI, "%s: cache miss\n", __func__); + /* + * If @noreq is set, no requests will be sent to the server for + * either updating or getting a new DFS referral. + */ + if (noreq) + return ce; + /* + * No cache entry was found, so check for valid parameters that + * will be required to get a new DFS referral and then create a + * new cache entry. + */ + if (!ses || !ses->server || !ses->server->ops->get_dfs_refer) { + ce = ERR_PTR(-EOPNOTSUPP); + return ce; + } + if (unlikely(!nls_codepage)) { + ce = ERR_PTR(-EINVAL); + return ce; + } + + nrefs = NULL; + numnrefs = 0; + + cifs_dbg(FYI, "%s: DFS referral request for %s\n", __func__, + path); + + rc = ses->server->ops->get_dfs_refer(xid, ses, path, &nrefs, + &numnrefs, nls_codepage, + remap); + if (rc) { + ce = ERR_PTR(rc); + return ce; + } + + dump_refs(nrefs, numnrefs); + + cifs_dbg(FYI, "%s: new cache entry\n", __func__); + + if (dfs_cache_count >= DFS_CACHE_MAX_ENTRIES) { + cifs_dbg(FYI, "%s: reached max cache size (%d)", + __func__, DFS_CACHE_MAX_ENTRIES); + remove_oldest_entry(); + } + ce = add_cache_entry(h, path, nrefs, numnrefs); + free_dfs_info_array(nrefs, numnrefs); + + if (IS_ERR(ce)) + return ce; + + dfs_cache_count++; + } + + dump_ce(ce); + + /* Just return the found cache entry in case @noreq is set */ + if (noreq) + return ce; + + if (cache_entry_expired(ce)) { + cifs_dbg(FYI, "%s: expired cache entry\n", __func__); + ce = update_cache_entry(xid, ses, nls_codepage, remap, path, + ce); + if (IS_ERR(ce)) { + cifs_dbg(FYI, "%s: failed to update expired entry\n", + __func__); + } + } + return ce; +} + +/* Set up a new DFS referral from a given cache entry */ +static int setup_ref(const char *path, const struct dfs_cache_entry *ce, + struct dfs_info3_param *ref, const char *tgt) +{ + int rc; + + cifs_dbg(FYI, "%s: set up new ref\n", __func__); + + memset(ref, 0, sizeof(*ref)); + + ref->path_name = kstrndup(path, strlen(path), GFP_KERNEL); + if (!ref->path_name) + return -ENOMEM; + + ref->path_consumed = ce->ce_path_consumed; + + ref->node_name = kstrndup(tgt, strlen(tgt), GFP_KERNEL); + if (!ref->node_name) { + rc = -ENOMEM; + goto err_free_path; + } + + ref->ttl = ce->ce_ttl; + ref->server_type = ce->ce_srvtype; + ref->ref_flag = ce->ce_flags; + + return 0; + +err_free_path: + kfree(ref->path_name); + ref->path_name = NULL; + return rc; +} + +/* Return target list of a DFS cache entry */ +static int get_tgt_list(const struct dfs_cache_entry *ce, + struct dfs_cache_tgt_list *tl) +{ + int rc; + struct list_head *head = &tl->tl_list; + struct dfs_cache_tgt *t; + struct dfs_cache_tgt_iterator *it, *nit; + + memset(tl, 0, sizeof(*tl)); + INIT_LIST_HEAD(head); + + list_for_each_entry(t, &ce->ce_tlist, t_list) { + it = kzalloc(sizeof(*it), GFP_KERNEL); + if (!it) { + rc = -ENOMEM; + goto err_free_it; + } + + it->it_name = kstrndup(t->t_name, strlen(t->t_name), + GFP_KERNEL); + if (!it->it_name) { + rc = -ENOMEM; + goto err_free_it; + } + + if (ce->ce_tgthint == t) + list_add(&it->it_list, head); + else + list_add_tail(&it->it_list, head); + } + tl->tl_numtgts = ce->ce_numtgts; + + return 0; + +err_free_it: + list_for_each_entry_safe(it, nit, head, it_list) { + kfree(it->it_name); + kfree(it); + } + return rc; +} + +/** + * dfs_cache_find - find a DFS cache entry + * + * If it doesn't find the cache entry, then it will get a DFS referral + * for @path and create a new entry. + * + * In case the cache entry exists but expired, it will get a DFS referral + * for @path and then update the respective cache entry. + * + * These parameters are passed down to the get_dfs_refer() call if it + * needs to be issued: + * @xid: syscall xid + * @ses: smb session to issue the request on + * @nls_codepage: charset conversion + * @remap: path character remapping type + * @path: path to lookup in DFS referral cache. + * + * @ref: when non-NULL, store single DFS referral result in it. + * @tgt_list: when non-NULL, store complete DFS target list in it. + * + * Return zero if the target was found, otherwise non-zero. + */ +int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *nls_codepage, int remap, + const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list) +{ + int rc; + char *npath; + struct dfs_cache_entry *ce; + + if (unlikely(!is_path_valid(path))) + return -EINVAL; + + rc = get_normalized_path(path, &npath); + if (rc) + return rc; + + mutex_lock(&dfs_cache_list_lock); + ce = do_dfs_cache_find(xid, ses, nls_codepage, remap, npath, false); + if (!IS_ERR(ce)) { + if (ref) + rc = setup_ref(path, ce, ref, get_tgt_name(ce)); + else + rc = 0; + if (!rc && tgt_list) + rc = get_tgt_list(ce, tgt_list); + } else { + rc = PTR_ERR(ce); + } + mutex_unlock(&dfs_cache_list_lock); + free_normalized_path(path, npath); + return rc; +} + +/** + * dfs_cache_noreq_find - find a DFS cache entry without sending any requests to + * the currently connected server. + * + * NOTE: This function will neither update a cache entry in case it was + * expired, nor create a new cache entry if @path hasn't been found. It heavily + * relies on an existing cache entry. + * + * @path: path to lookup in the DFS referral cache. + * @ref: when non-NULL, store single DFS referral result in it. + * @tgt_list: when non-NULL, store complete DFS target list in it. + * + * Return 0 if successful. + * Return -ENOENT if the entry was not found. + * Return non-zero for other errors. + */ +int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list) +{ + int rc; + char *npath; + struct dfs_cache_entry *ce; + + if (unlikely(!is_path_valid(path))) + return -EINVAL; + + rc = get_normalized_path(path, &npath); + if (rc) + return rc; + + mutex_lock(&dfs_cache_list_lock); + ce = do_dfs_cache_find(0, NULL, NULL, 0, npath, true); + if (IS_ERR(ce)) { + rc = PTR_ERR(ce); + goto out; + } + + if (ref) + rc = setup_ref(path, ce, ref, get_tgt_name(ce)); + else + rc = 0; + if (!rc && tgt_list) + rc = get_tgt_list(ce, tgt_list); +out: + mutex_unlock(&dfs_cache_list_lock); + free_normalized_path(path, npath); + return rc; +} + +/** + * dfs_cache_update_tgthint - update target hint of a DFS cache entry + * + * If it doesn't find the cache entry, then it will get a DFS referral for @path + * and create a new entry. + * + * In case the cache entry exists but expired, it will get a DFS referral + * for @path and then update the respective cache entry. + * + * @xid: syscall id + * @ses: smb session + * @nls_codepage: charset conversion + * @remap: type of character remapping for paths + * @path: path to lookup in DFS referral cache. + * @it: DFS target iterator + * + * Return zero if the target hint was updated successfully, otherwise non-zero. + */ +int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *nls_codepage, int remap, + const char *path, + const struct dfs_cache_tgt_iterator *it) +{ + int rc; + char *npath; + struct dfs_cache_entry *ce; + struct dfs_cache_tgt *t; + + if (unlikely(!is_path_valid(path))) + return -EINVAL; + + rc = get_normalized_path(path, &npath); + if (rc) + return rc; + + cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + + mutex_lock(&dfs_cache_list_lock); + ce = do_dfs_cache_find(xid, ses, nls_codepage, remap, npath, false); + if (IS_ERR(ce)) { + rc = PTR_ERR(ce); + goto out; + } + + rc = 0; + + t = ce->ce_tgthint; + + if (likely(!strcasecmp(it->it_name, t->t_name))) + goto out; + + list_for_each_entry(t, &ce->ce_tlist, t_list) { + if (!strcasecmp(t->t_name, it->it_name)) { + ce->ce_tgthint = t; + cifs_dbg(FYI, "%s: new target hint: %s\n", __func__, + it->it_name); + break; + } + } + +out: + mutex_unlock(&dfs_cache_list_lock); + free_normalized_path(path, npath); + return rc; +} + +/** + * dfs_cache_noreq_update_tgthint - update target hint of a DFS cache entry + * without sending any requests to the currently connected server. + * + * NOTE: This function will neither update a cache entry in case it was + * expired, nor create a new cache entry if @path hasn't been found. It heavily + * relies on an existing cache entry. + * + * @path: path to lookup in DFS referral cache. + * @it: target iterator which contains the target hint to update the cache + * entry with. + * + * Return zero if the target hint was updated successfully, otherwise non-zero. + */ +int dfs_cache_noreq_update_tgthint(const char *path, + const struct dfs_cache_tgt_iterator *it) +{ + int rc; + char *npath; + struct dfs_cache_entry *ce; + struct dfs_cache_tgt *t; + + if (unlikely(!is_path_valid(path)) || !it) + return -EINVAL; + + rc = get_normalized_path(path, &npath); + if (rc) + return rc; + + cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + + mutex_lock(&dfs_cache_list_lock); + + ce = do_dfs_cache_find(0, NULL, NULL, 0, npath, true); + if (IS_ERR(ce)) { + rc = PTR_ERR(ce); + goto out; + } + + rc = 0; + + t = ce->ce_tgthint; + + if (unlikely(!strcasecmp(it->it_name, t->t_name))) + goto out; + + list_for_each_entry(t, &ce->ce_tlist, t_list) { + if (!strcasecmp(t->t_name, it->it_name)) { + ce->ce_tgthint = t; + cifs_dbg(FYI, "%s: new target hint: %s\n", __func__, + it->it_name); + break; + } + } + +out: + mutex_unlock(&dfs_cache_list_lock); + free_normalized_path(path, npath); + return rc; +} + +/** + * dfs_cache_get_tgt_referral - returns a DFS referral (@ref) from a given + * target iterator (@it). + * + * @path: path to lookup in DFS referral cache. + * @it: DFS target iterator. + * @ref: DFS referral pointer to set up the gathered information. + * + * Return zero if the DFS referral was set up correctly, otherwise non-zero. + */ +int dfs_cache_get_tgt_referral(const char *path, + const struct dfs_cache_tgt_iterator *it, + struct dfs_info3_param *ref) +{ + int rc; + char *npath; + struct dfs_cache_entry *ce; + unsigned int h; + + if (!it || !ref) + return -EINVAL; + if (unlikely(!is_path_valid(path))) + return -EINVAL; + + rc = get_normalized_path(path, &npath); + if (rc) + return rc; + + cifs_dbg(FYI, "%s: path: %s\n", __func__, npath); + + mutex_lock(&dfs_cache_list_lock); + + ce = find_cache_entry(npath, &h); + if (IS_ERR(ce)) { + rc = PTR_ERR(ce); + goto out; + } + + cifs_dbg(FYI, "%s: target name: %s\n", __func__, it->it_name); + + rc = setup_ref(path, ce, ref, it->it_name); + +out: + mutex_unlock(&dfs_cache_list_lock); + free_normalized_path(path, npath); + return rc; +} + +static int dup_vol(struct smb_vol *vol, struct smb_vol *new) +{ + memcpy(new, vol, sizeof(*new)); + + if (vol->username) { + new->username = kstrndup(vol->username, strlen(vol->username), + GFP_KERNEL); + if (!new->username) + return -ENOMEM; + } + if (vol->password) { + new->password = kstrndup(vol->password, strlen(vol->password), + GFP_KERNEL); + if (!new->password) + goto err_free_username; + } + if (vol->UNC) { + cifs_dbg(FYI, "%s: vol->UNC: %s\n", __func__, vol->UNC); + new->UNC = kstrndup(vol->UNC, strlen(vol->UNC), GFP_KERNEL); + if (!new->UNC) + goto err_free_password; + } + if (vol->domainname) { + new->domainname = kstrndup(vol->domainname, + strlen(vol->domainname), GFP_KERNEL); + if (!new->domainname) + goto err_free_unc; + } + if (vol->iocharset) { + new->iocharset = kstrndup(vol->iocharset, + strlen(vol->iocharset), GFP_KERNEL); + if (!new->iocharset) + goto err_free_domainname; + } + if (vol->prepath) { + cifs_dbg(FYI, "%s: vol->prepath: %s\n", __func__, vol->prepath); + new->prepath = kstrndup(vol->prepath, strlen(vol->prepath), + GFP_KERNEL); + if (!new->prepath) + goto err_free_iocharset; + } + + return 0; + +err_free_iocharset: + kfree(new->iocharset); +err_free_domainname: + kfree(new->domainname); +err_free_unc: + kfree(new->UNC); +err_free_password: + kzfree(new->password); +err_free_username: + kfree(new->username); + kfree(new); + return -ENOMEM; +} + +/** + * dfs_cache_add_vol - add a cifs volume during mount() that will be handled by + * DFS cache refresh worker. + * + * @vol: cifs volume. + * @fullpath: origin full path. + * + * Return zero if volume was set up correctly, otherwise non-zero. + */ +int dfs_cache_add_vol(struct smb_vol *vol, const char *fullpath) +{ + int rc; + struct dfs_cache_vol_info *vi; + + if (!vol || !fullpath) + return -EINVAL; + + cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); + + vi = kzalloc(sizeof(*vi), GFP_KERNEL); + if (!vi) + return -ENOMEM; + + vi->vi_fullpath = kstrndup(fullpath, strlen(fullpath), GFP_KERNEL); + if (!vi->vi_fullpath) { + rc = -ENOMEM; + goto err_free_vi; + } + + rc = dup_vol(vol, &vi->vi_vol); + if (rc) + goto err_free_fullpath; + + mutex_lock(&dfs_cache.dc_lock); + list_add_tail(&vi->vi_list, &dfs_cache.dc_vol_list); + mutex_unlock(&dfs_cache.dc_lock); + return 0; + +err_free_fullpath: + kfree(vi->vi_fullpath); +err_free_vi: + kfree(vi); + return rc; +} + +static inline struct dfs_cache_vol_info *find_vol(const char *fullpath) +{ + struct dfs_cache_vol_info *vi; + + list_for_each_entry(vi, &dfs_cache.dc_vol_list, vi_list) { + cifs_dbg(FYI, "%s: vi->vi_fullpath: %s\n", __func__, + vi->vi_fullpath); + if (!strcasecmp(vi->vi_fullpath, fullpath)) + return vi; + } + return ERR_PTR(-ENOENT); +} + +/** + * dfs_cache_update_vol - update vol info in DFS cache after failover + * + * @fullpath: fullpath to look up in volume list. + * @server: TCP ses pointer. + * + * Return zero if volume was updated, otherwise non-zero. + */ +int dfs_cache_update_vol(const char *fullpath, struct TCP_Server_Info *server) +{ + int rc; + struct dfs_cache_vol_info *vi; + + if (!fullpath || !server) + return -EINVAL; + + cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); + + mutex_lock(&dfs_cache.dc_lock); + + vi = find_vol(fullpath); + if (IS_ERR(vi)) { + rc = PTR_ERR(vi); + goto out; + } + + cifs_dbg(FYI, "%s: updating volume info\n", __func__); + memcpy(&vi->vi_vol.dstaddr, &server->dstaddr, + sizeof(vi->vi_vol.dstaddr)); + rc = 0; + +out: + mutex_unlock(&dfs_cache.dc_lock); + return rc; +} + +/** + * dfs_cache_del_vol - remove volume info in DFS cache during umount() + * + * @fullpath: fullpath to look up in volume list. + */ +void dfs_cache_del_vol(const char *fullpath) +{ + struct dfs_cache_vol_info *vi; + + if (!fullpath || !*fullpath) + return; + + cifs_dbg(FYI, "%s: fullpath: %s\n", __func__, fullpath); + + mutex_lock(&dfs_cache.dc_lock); + vi = find_vol(fullpath); + if (!IS_ERR(vi)) + free_vol(vi); + mutex_unlock(&dfs_cache.dc_lock); +} + +/* Get all tcons that are within a DFS namespace and can be refreshed */ +static void get_tcons(struct TCP_Server_Info *server, struct list_head *head) +{ + struct cifs_ses *ses; + struct cifs_tcon *tcon; + + INIT_LIST_HEAD(head); + + spin_lock(&cifs_tcp_ses_lock); + list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + if (!tcon->need_reconnect && !tcon->need_reopen_files && + tcon->dfs_path) { + tcon->tc_count++; + list_add_tail(&tcon->ulist, head); + } + } + if (ses->tcon_ipc && !ses->tcon_ipc->need_reconnect && + ses->tcon_ipc->dfs_path) { + list_add_tail(&ses->tcon_ipc->ulist, head); + } + } + spin_unlock(&cifs_tcp_ses_lock); +} + +/* Refresh DFS cache entry from a given tcon */ +static void do_refresh_tcon(struct dfs_cache *dc, struct cifs_tcon *tcon) +{ + int rc = 0; + unsigned int xid; + char *path, *npath; + unsigned int h; + struct dfs_cache_entry *ce; + struct dfs_info3_param *refs = NULL; + int numrefs = 0; + + xid = get_xid(); + + path = tcon->dfs_path + 1; + + rc = get_normalized_path(path, &npath); + if (rc) + goto out; + + mutex_lock(&dfs_cache_list_lock); + ce = find_cache_entry(npath, &h); + mutex_unlock(&dfs_cache_list_lock); + + if (IS_ERR(ce)) { + rc = PTR_ERR(ce); + goto out; + } + + if (!cache_entry_expired(ce)) + goto out; + + if (unlikely(!tcon->ses->server->ops->get_dfs_refer)) { + rc = -EOPNOTSUPP; + } else { + rc = tcon->ses->server->ops->get_dfs_refer(xid, tcon->ses, path, + &refs, &numrefs, + dc->dc_nlsc, + tcon->remap); + if (!rc) { + mutex_lock(&dfs_cache_list_lock); + ce = __update_cache_entry(npath, refs, numrefs); + mutex_unlock(&dfs_cache_list_lock); + dump_refs(refs, numrefs); + free_dfs_info_array(refs, numrefs); + if (IS_ERR(ce)) + rc = PTR_ERR(ce); + } + } + if (rc) + cifs_dbg(FYI, "%s: failed to update expired entry\n", __func__); +out: + free_xid(xid); + free_normalized_path(path, npath); +} + +/* + * Worker that will refresh DFS cache based on lowest TTL value from a DFS + * referral. + * + * FIXME: ensure that all requests are sent to DFS root for refreshing the + * cache. + */ +static void refresh_cache_worker(struct work_struct *work) +{ + struct dfs_cache *dc = container_of(work, struct dfs_cache, + dc_refresh.work); + struct dfs_cache_vol_info *vi; + struct TCP_Server_Info *server; + LIST_HEAD(list); + struct cifs_tcon *tcon, *ntcon; + + mutex_lock(&dc->dc_lock); + + list_for_each_entry(vi, &dc->dc_vol_list, vi_list) { + server = cifs_find_tcp_session(&vi->vi_vol); + if (IS_ERR_OR_NULL(server)) + continue; + if (server->tcpStatus != CifsGood) + goto next; + get_tcons(server, &list); + list_for_each_entry_safe(tcon, ntcon, &list, ulist) { + do_refresh_tcon(dc, tcon); + list_del_init(&tcon->ulist); + cifs_put_tcon(tcon); + } +next: + cifs_put_tcp_session(server, 0); + } + queue_delayed_work(cifsiod_wq, &dc->dc_refresh, dc->dc_ttl * HZ); + mutex_unlock(&dc->dc_lock); +} diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h new file mode 100644 index 000000000000..22f366514f3a --- /dev/null +++ b/fs/cifs/dfs_cache.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * DFS referral cache routines + * + * Copyright (c) 2018 Paulo Alcantara <palcantara@suse.de> + */ + +#ifndef _CIFS_DFS_CACHE_H +#define _CIFS_DFS_CACHE_H + +#include <linux/nls.h> +#include <linux/list.h> +#include "cifsglob.h" + +struct dfs_cache_tgt_list { + int tl_numtgts; + struct list_head tl_list; +}; + +struct dfs_cache_tgt_iterator { + char *it_name; + struct list_head it_list; +}; + +extern int dfs_cache_init(void); +extern void dfs_cache_destroy(void); +extern const struct file_operations dfscache_proc_fops; + +extern int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, + const struct nls_table *nls_codepage, int remap, + const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list); +extern int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, + struct dfs_cache_tgt_list *tgt_list); +extern int dfs_cache_update_tgthint(const unsigned int xid, + struct cifs_ses *ses, + const struct nls_table *nls_codepage, + int remap, const char *path, + const struct dfs_cache_tgt_iterator *it); +extern int +dfs_cache_noreq_update_tgthint(const char *path, + const struct dfs_cache_tgt_iterator *it); +extern int dfs_cache_get_tgt_referral(const char *path, + const struct dfs_cache_tgt_iterator *it, + struct dfs_info3_param *ref); +extern int dfs_cache_add_vol(struct smb_vol *vol, const char *fullpath); +extern int dfs_cache_update_vol(const char *fullpath, + struct TCP_Server_Info *server); +extern void dfs_cache_del_vol(const char *fullpath); + +static inline struct dfs_cache_tgt_iterator * +dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl, + struct dfs_cache_tgt_iterator *it) +{ + if (!tl || list_empty(&tl->tl_list) || !it || + list_is_last(&it->it_list, &tl->tl_list)) + return NULL; + return list_next_entry(it, it_list); +} + +static inline struct dfs_cache_tgt_iterator * +dfs_cache_get_tgt_iterator(struct dfs_cache_tgt_list *tl) +{ + if (!tl) + return NULL; + return list_first_entry_or_null(&tl->tl_list, + struct dfs_cache_tgt_iterator, + it_list); +} + +static inline void dfs_cache_free_tgts(struct dfs_cache_tgt_list *tl) +{ + struct dfs_cache_tgt_iterator *it, *nit; + + if (!tl || list_empty(&tl->tl_list)) + return; + list_for_each_entry_safe(it, nit, &tl->tl_list, it_list) { + list_del(&it->it_list); + kfree(it->it_name); + kfree(it); + } + tl->tl_numtgts = 0; +} + +static inline const char * +dfs_cache_get_tgt_name(const struct dfs_cache_tgt_iterator *it) +{ + return it ? it->it_name : NULL; +} + +static inline int +dfs_cache_get_nr_tgts(const struct dfs_cache_tgt_list *tl) +{ + return tl ? tl->tl_numtgts : 0; +} + +#endif /* _CIFS_DFS_CACHE_H */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6706328ce03f..5e405164394a 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2617,11 +2617,13 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (rc) break; + cur_len = min_t(const size_t, len, wsize); + if (ctx->direct_io) { ssize_t result; result = iov_iter_get_pages_alloc( - from, &pagevec, wsize, &start); + from, &pagevec, cur_len, &start); if (result < 0) { cifs_dbg(VFS, "direct_writev couldn't get user pages " @@ -2630,6 +2632,9 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, result, from->type, from->iov_offset, from->count); dump_stack(); + + rc = result; + add_credits_and_wake_if(server, credits, 0); break; } cur_len = (size_t)result; @@ -3313,13 +3318,16 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, cur_len, &start); if (result < 0) { cifs_dbg(VFS, - "couldn't get user pages (cur_len=%zd)" + "couldn't get user pages (rc=%zd)" " iter type %d" " iov_offset %zd count %zd\n", result, direct_iov.type, direct_iov.iov_offset, direct_iov.count); dump_stack(); + + rc = result; + add_credits_and_wake_if(server, credits, 0); break; } cur_len = (size_t)result; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index a81a9df997c1..13fb59aadebc 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -333,7 +333,7 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb) fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran); fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime; fattr->cf_nlink = 2; - fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL; + fattr->cf_flags = CIFS_FATTR_DFS_REFERRAL; } static int @@ -730,7 +730,6 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, FILE_ALL_INFO *data, struct super_block *sb, int xid, const struct cifs_fid *fid) { - bool validinum = false; __u16 srchflgs; int rc = 0, tmprc = ENOSYS; struct cifs_tcon *tcon; @@ -821,7 +820,6 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, (FILE_DIRECTORY_INFO *)data, cifs_sb); fattr.cf_uniqueid = le64_to_cpu( ((SEARCH_ID_FULL_DIR_INFO *)data)->UniqueId); - validinum = true; cifs_buf_release(srchinf->ntwrk_buf_start); } @@ -840,31 +838,29 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, */ if (*inode == NULL) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { - if (validinum == false) { - if (server->ops->get_srv_inum) - tmprc = server->ops->get_srv_inum(xid, - tcon, cifs_sb, full_path, - &fattr.cf_uniqueid, data); - if (tmprc) { - cifs_dbg(FYI, "GetSrvInodeNum rc %d\n", - tmprc); - fattr.cf_uniqueid = iunique(sb, ROOT_I); - cifs_autodisable_serverino(cifs_sb); - } else if ((fattr.cf_uniqueid == 0) && - strlen(full_path) == 0) { - /* some servers ret bad root ino ie 0 */ - cifs_dbg(FYI, "Invalid (0) inodenum\n"); - fattr.cf_flags |= - CIFS_FATTR_FAKE_ROOT_INO; - fattr.cf_uniqueid = - simple_hashstr(tcon->treeName); - } + if (server->ops->get_srv_inum) + tmprc = server->ops->get_srv_inum(xid, + tcon, cifs_sb, full_path, + &fattr.cf_uniqueid, data); + if (tmprc) { + cifs_dbg(FYI, "GetSrvInodeNum rc %d\n", + tmprc); + fattr.cf_uniqueid = iunique(sb, ROOT_I); + cifs_autodisable_serverino(cifs_sb); + } else if ((fattr.cf_uniqueid == 0) && + strlen(full_path) == 0) { + /* some servers ret bad root ino ie 0 */ + cifs_dbg(FYI, "Invalid (0) inodenum\n"); + fattr.cf_flags |= + CIFS_FATTR_FAKE_ROOT_INO; + fattr.cf_uniqueid = + simple_hashstr(tcon->treeName); } } else fattr.cf_uniqueid = iunique(sb, ROOT_I); } else { - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) && - validinum == false && server->ops->get_srv_inum) { + if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) + && server->ops->get_srv_inum) { /* * Pass a NULL tcon to ensure we don't make a round * trip to the server. This only works for SMB2+. diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 8a41f4eba726..bee203055b30 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -111,21 +111,27 @@ struct cifs_tcon * tconInfoAlloc(void) { struct cifs_tcon *ret_buf; - ret_buf = kzalloc(sizeof(struct cifs_tcon), GFP_KERNEL); - if (ret_buf) { - atomic_inc(&tconInfoAllocCount); - ret_buf->tidStatus = CifsNew; - ++ret_buf->tc_count; - INIT_LIST_HEAD(&ret_buf->openFileList); - INIT_LIST_HEAD(&ret_buf->tcon_list); - spin_lock_init(&ret_buf->open_file_lock); - mutex_init(&ret_buf->crfid.fid_mutex); - ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid), - GFP_KERNEL); - spin_lock_init(&ret_buf->stat_lock); - atomic_set(&ret_buf->num_local_opens, 0); - atomic_set(&ret_buf->num_remote_opens, 0); + + ret_buf = kzalloc(sizeof(*ret_buf), GFP_KERNEL); + if (!ret_buf) + return NULL; + ret_buf->crfid.fid = kzalloc(sizeof(*ret_buf->crfid.fid), GFP_KERNEL); + if (!ret_buf->crfid.fid) { + kfree(ret_buf); + return NULL; } + + atomic_inc(&tconInfoAllocCount); + ret_buf->tidStatus = CifsNew; + ++ret_buf->tc_count; + INIT_LIST_HEAD(&ret_buf->openFileList); + INIT_LIST_HEAD(&ret_buf->tcon_list); + spin_lock_init(&ret_buf->open_file_lock); + mutex_init(&ret_buf->crfid.fid_mutex); + spin_lock_init(&ret_buf->stat_lock); + atomic_set(&ret_buf->num_local_opens, 0); + atomic_set(&ret_buf->num_remote_opens, 0); + return ret_buf; } @@ -140,6 +146,9 @@ tconInfoFree(struct cifs_tcon *buf_to_free) kfree(buf_to_free->nativeFileSystem); kzfree(buf_to_free->password); kfree(buf_to_free->crfid.fid); +#ifdef CONFIG_CIFS_DFS_UPCALL + kfree(buf_to_free->dfs_path); +#endif kfree(buf_to_free); } @@ -525,9 +534,17 @@ void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) { if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { + struct cifs_tcon *tcon = NULL; + + if (cifs_sb->master_tlink) + tcon = cifs_sb_master_tcon(cifs_sb); + cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; - cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s. This server doesn't seem to support them properly. Hardlinks will not be recognized on this mount. Consider mounting with the \"noserverino\" option to silence this message.\n", - cifs_sb_master_tcon(cifs_sb)->treeName); + cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s.\n", + tcon ? tcon->treeName : "new server"); + cifs_dbg(VFS, "The server doesn't seem to support them properly or the files might be on different servers (DFS).\n"); + cifs_dbg(VFS, "Hardlinks will not be recognized on this mount. Consider mounting with the \"noserverino\" option to silence this message.\n"); + } } @@ -732,6 +749,8 @@ parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size, goto parse_DFS_referrals_exit; } + node->ttl = le32_to_cpu(ref->TimeToLive); + ref++; } @@ -933,3 +952,20 @@ void rqst_page_get_length(struct smb_rqst *rqst, unsigned int page, else if (page == 0) *len = rqst->rq_pagesz - rqst->rq_offset; } + +void extract_unc_hostname(const char *unc, const char **h, size_t *len) +{ + const char *end; + + /* skip initial slashes */ + while (*unc && (*unc == '\\' || *unc == '/')) + unc++; + + end = unc; + + while (*end && !(*end == '\\' || *end == '/')) + end++; + + *h = unc; + *len = end - unc; +} diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index e169e1a5fd35..3925a7bfc74d 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -655,7 +655,14 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, /* scan and find it */ int i; char *cur_ent; - char *end_of_smb = cfile->srch_inf.ntwrk_buf_start + + char *end_of_smb; + + if (cfile->srch_inf.ntwrk_buf_start == NULL) { + cifs_dbg(VFS, "ntwrk_buf_start is NULL during readdir\n"); + return -EIO; + } + + end_of_smb = cfile->srch_inf.ntwrk_buf_start + server->ops->calc_smb_size( cfile->srch_inf.ntwrk_buf_start, server); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index aa23c00367ec..dcd49ad60c83 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -534,9 +534,9 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if (global_secflags & CIFSSEC_MAY_NTLM) return NTLM; default: - /* Fallthrough to attempt LANMAN authentication next */ break; } + /* Fallthrough - to attempt LANMAN authentication next */ case CIFS_NEGFLAVOR_LANMAN: switch (requested) { case LANMAN: @@ -1154,14 +1154,12 @@ out: static int _sess_auth_rawntlmssp_assemble_req(struct sess_data *sess_data) { - struct smb_hdr *smb_buf; SESSION_SETUP_ANDX *pSMB; struct cifs_ses *ses = sess_data->ses; __u32 capabilities; char *bcc_ptr; pSMB = (SESSION_SETUP_ANDX *)sess_data->iov[0].iov_base; - smb_buf = (struct smb_hdr *)pSMB; capabilities = cifs_ssetup_hdr(ses, pSMB); if ((pSMB->req.hdr.Flags2 & SMBFLG2_UNICODE) == 0) { diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 378151e09e91..32a6c020478f 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -929,19 +929,18 @@ cifs_unix_dfs_readlink(const unsigned int xid, struct cifs_tcon *tcon, { #ifdef CONFIG_CIFS_DFS_UPCALL int rc; - unsigned int num_referrals = 0; - struct dfs_info3_param *referrals = NULL; + struct dfs_info3_param referral = {0}; - rc = get_dfs_path(xid, tcon->ses, searchName, nls_codepage, - &num_referrals, &referrals, 0); + rc = get_dfs_path(xid, tcon->ses, searchName, nls_codepage, &referral, + 0); - if (!rc && num_referrals > 0) { - *symlinkinfo = kstrndup(referrals->node_name, - strlen(referrals->node_name), + if (!rc) { + *symlinkinfo = kstrndup(referral.node_name, + strlen(referral.node_name), GFP_KERNEL); + free_dfs_info_param(&referral); if (!*symlinkinfo) rc = -ENOMEM; - free_dfs_info_array(referrals, num_referrals); } return rc; #else /* No DFS support */ diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index a8999f930b22..f14533da3a93 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -49,7 +49,6 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_open_parms oparms; struct cifs_fid fid; struct cifs_ses *ses = tcon->ses; - struct TCP_Server_Info *server = ses->server; int num_rqst = 0; struct smb_rqst rqst[3]; int resp_buftype[3]; @@ -97,7 +96,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, if (rc) goto finished; - smb2_set_next_command(server, &rqst[num_rqst++], 0); + smb2_set_next_command(tcon, &rqst[num_rqst++]); /* Operation */ switch (command) { @@ -111,7 +110,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, SMB2_O_INFO_FILE, 0, sizeof(struct smb2_file_all_info) + PATH_MAX * 2, 0, NULL); - smb2_set_next_command(server, &rqst[num_rqst], 0); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; case SMB2_OP_DELETE: @@ -134,7 +133,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_DISPOSITION_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - smb2_set_next_command(server, &rqst[num_rqst], 1); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: @@ -149,7 +148,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - smb2_set_next_command(server, &rqst[num_rqst], 0); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; case SMB2_OP_SET_INFO: @@ -165,7 +164,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_BASIC_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - smb2_set_next_command(server, &rqst[num_rqst], 0); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; case SMB2_OP_RENAME: @@ -189,7 +188,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - smb2_set_next_command(server, &rqst[num_rqst], 0); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; case SMB2_OP_HARDLINK: @@ -213,7 +212,7 @@ smb2_compound_op(const unsigned int xid, struct cifs_tcon *tcon, COMPOUND_FID, current->tgid, FILE_LINK_INFORMATION, SMB2_O_INFO_FILE, 0, data, size); - smb2_set_next_command(server, &rqst[num_rqst], 0); + smb2_set_next_command(tcon, &rqst[num_rqst]); smb2_set_related(&rqst[num_rqst++]); break; default: @@ -388,7 +387,6 @@ smb2_set_path_attr(const unsigned int xid, struct cifs_tcon *tcon, rc = -ENOMEM; goto smb2_rename_path; } - rc = smb2_compound_op(xid, tcon, cifs_sb, from_name, access, FILE_OPEN, 0, smb2_to_name, command); smb2_rename_path: diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c index d47b7f5dfa6c..924269cec135 100644 --- a/fs/cifs/smb2maperror.c +++ b/fs/cifs/smb2maperror.c @@ -379,8 +379,8 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_NONEXISTENT_EA_ENTRY, -EIO, "STATUS_NONEXISTENT_EA_ENTRY"}, {STATUS_NO_EAS_ON_FILE, -ENODATA, "STATUS_NO_EAS_ON_FILE"}, {STATUS_EA_CORRUPT_ERROR, -EIO, "STATUS_EA_CORRUPT_ERROR"}, - {STATUS_FILE_LOCK_CONFLICT, -EIO, "STATUS_FILE_LOCK_CONFLICT"}, - {STATUS_LOCK_NOT_GRANTED, -EIO, "STATUS_LOCK_NOT_GRANTED"}, + {STATUS_FILE_LOCK_CONFLICT, -EACCES, "STATUS_FILE_LOCK_CONFLICT"}, + {STATUS_LOCK_NOT_GRANTED, -EACCES, "STATUS_LOCK_NOT_GRANTED"}, {STATUS_DELETE_PENDING, -ENOENT, "STATUS_DELETE_PENDING"}, {STATUS_CTL_FILE_NOT_SUPPORTED, -ENOSYS, "STATUS_CTL_FILE_NOT_SUPPORTED"}, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e25c7aade98a..33100ef74d7f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -831,72 +831,48 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, { int rc; __le16 *utf16_path; - __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct cifs_open_parms oparms; - struct cifs_fid fid; - struct smb2_file_full_ea_info *smb2_data; - int ea_buf_size = SMB2_MIN_EA_BUF; + struct kvec rsp_iov = {NULL, 0}; + int buftype = CIFS_NO_BUFFER; + struct smb2_query_info_rsp *rsp; + struct smb2_file_full_ea_info *info = NULL; utf16_path = cifs_convert_path_to_utf16(path, cifs_sb); if (!utf16_path) return -ENOMEM; - oparms.tcon = tcon; - oparms.desired_access = FILE_READ_EA; - oparms.disposition = FILE_OPEN; - if (backup_cred(cifs_sb)) - oparms.create_options = CREATE_OPEN_BACKUP_INTENT; - else - oparms.create_options = 0; - oparms.fid = &fid; - oparms.reconnect = false; - - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); - kfree(utf16_path); + rc = smb2_query_info_compound(xid, tcon, utf16_path, + FILE_READ_EA, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, + SMB2_MAX_EA_BUF, + &rsp_iov, &buftype, cifs_sb); if (rc) { - cifs_dbg(FYI, "open failed rc=%d\n", rc); - return rc; - } - - while (1) { - smb2_data = kzalloc(ea_buf_size, GFP_KERNEL); - if (smb2_data == NULL) { - SMB2_close(xid, tcon, fid.persistent_fid, - fid.volatile_fid); - return -ENOMEM; - } - - rc = SMB2_query_eas(xid, tcon, fid.persistent_fid, - fid.volatile_fid, - ea_buf_size, smb2_data); - - if (rc != -E2BIG) - break; - - kfree(smb2_data); - ea_buf_size <<= 1; - - if (ea_buf_size > SMB2_MAX_EA_BUF) { - cifs_dbg(VFS, "EA size is too large\n"); - SMB2_close(xid, tcon, fid.persistent_fid, - fid.volatile_fid); - return -ENOMEM; - } + /* + * If ea_name is NULL (listxattr) and there are no EAs, + * return 0 as it's not an error. Otherwise, the specified + * ea_name was not found. + */ + if (!ea_name && rc == -ENODATA) + rc = 0; + goto qeas_exit; } - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; + rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset), + le32_to_cpu(rsp->OutputBufferLength), + &rsp_iov, + sizeof(struct smb2_file_full_ea_info)); + if (rc) + goto qeas_exit; - /* - * If ea_name is NULL (listxattr) and there are no EAs, return 0 as it's - * not an error. Otherwise, the specified ea_name was not found. - */ - if (!rc) - rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data, - SMB2_MAX_EA_BUF, ea_name); - else if (!ea_name && rc == -ENODATA) - rc = 0; + info = (struct smb2_file_full_ea_info *)( + le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp); + rc = move_smb2_ea_to_cifs(ea_data, buf_size, info, + le32_to_cpu(rsp->OutputBufferLength), ea_name); - kfree(smb2_data); + qeas_exit: + kfree(utf16_path); + free_rsp_buf(buftype, rsp_iov.iov_base); return rc; } @@ -907,14 +883,27 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, const __u16 ea_value_len, const struct nls_table *nls_codepage, struct cifs_sb_info *cifs_sb) { - int rc; - __le16 *utf16_path; - __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; - struct cifs_open_parms oparms; - struct cifs_fid fid; - struct smb2_file_full_ea_info *ea; + struct cifs_ses *ses = tcon->ses; + __le16 *utf16_path = NULL; int ea_name_len = strlen(ea_name); + int flags = 0; int len; + struct smb_rqst rqst[3]; + int resp_buftype[3]; + struct kvec rsp_iov[3]; + struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; + struct cifs_open_parms oparms; + __u8 oplock = SMB2_OPLOCK_LEVEL_NONE; + struct cifs_fid fid; + struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + unsigned int size[1]; + void *data[1]; + struct smb2_file_full_ea_info *ea = NULL; + struct kvec close_iov[1]; + int rc; + + if (smb3_encryption_required(tcon)) + flags |= CIFS_TRANSFORM_REQ; if (ea_name_len > 255) return -EINVAL; @@ -923,6 +912,16 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, if (!utf16_path) return -ENOMEM; + memset(rqst, 0, sizeof(rqst)); + resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER; + memset(rsp_iov, 0, sizeof(rsp_iov)); + + /* Open */ + memset(&open_iov, 0, sizeof(open_iov)); + rqst[0].rq_iov = open_iov; + rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; + + memset(&oparms, 0, sizeof(oparms)); oparms.tcon = tcon; oparms.desired_access = FILE_WRITE_EA; oparms.disposition = FILE_OPEN; @@ -933,18 +932,22 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL); - kfree(utf16_path); - if (rc) { - cifs_dbg(FYI, "open failed rc=%d\n", rc); - return rc; - } + rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); + if (rc) + goto sea_exit; + smb2_set_next_command(tcon, &rqst[0]); + + + /* Set Info */ + memset(&si_iov, 0, sizeof(si_iov)); + rqst[1].rq_iov = si_iov; + rqst[1].rq_nvec = 1; len = sizeof(ea) + ea_name_len + ea_value_len + 1; ea = kzalloc(len, GFP_KERNEL); if (ea == NULL) { - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); - return -ENOMEM; + rc = -ENOMEM; + goto sea_exit; } ea->ea_name_length = ea_name_len; @@ -952,12 +955,36 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, memcpy(ea->ea_data, ea_name, ea_name_len + 1); memcpy(ea->ea_data + ea_name_len + 1, ea_value, ea_value_len); - rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea, - len); - kfree(ea); + size[0] = len; + data[0] = ea; + + rc = SMB2_set_info_init(tcon, &rqst[1], COMPOUND_FID, + COMPOUND_FID, current->tgid, + FILE_FULL_EA_INFORMATION, + SMB2_O_INFO_FILE, 0, data, size); + smb2_set_next_command(tcon, &rqst[1]); + smb2_set_related(&rqst[1]); - SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + /* Close */ + memset(&close_iov, 0, sizeof(close_iov)); + rqst[2].rq_iov = close_iov; + rqst[2].rq_nvec = 1; + rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID); + smb2_set_related(&rqst[2]); + + rc = compound_send_recv(xid, ses, flags, 3, rqst, + resp_buftype, rsp_iov); + + sea_exit: + kfree(ea); + kfree(utf16_path); + SMB2_open_free(&rqst[0]); + SMB2_set_info_free(&rqst[1]); + SMB2_close_free(&rqst[2]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); return rc; } #endif @@ -1194,7 +1221,7 @@ smb2_ioctl_query_info(const unsigned int xid, rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, path); if (rc) goto iqinf_exit; - smb2_set_next_command(ses->server, &rqst[0], 0); + smb2_set_next_command(tcon, &rqst[0]); /* Query */ memset(&qi_iov, 0, sizeof(qi_iov)); @@ -1208,7 +1235,7 @@ smb2_ioctl_query_info(const unsigned int xid, qi.output_buffer_length, buffer); if (rc) goto iqinf_exit; - smb2_set_next_command(ses->server, &rqst[1], 0); + smb2_set_next_command(tcon, &rqst[1]); smb2_set_related(&rqst[1]); /* Close */ @@ -1761,49 +1788,79 @@ smb2_set_related(struct smb_rqst *rqst) char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0}; void -smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst, - bool has_space_for_padding) +smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst) { struct smb2_sync_hdr *shdr; + struct cifs_ses *ses = tcon->ses; + struct TCP_Server_Info *server = ses->server; unsigned long len = smb_rqst_len(server, rqst); + int i, num_padding; /* SMB headers in a compound are 8 byte aligned. */ - if (len & 7) { - if (has_space_for_padding) { - len = rqst->rq_iov[rqst->rq_nvec - 1].iov_len; - rqst->rq_iov[rqst->rq_nvec - 1].iov_len = - (len + 7) & ~7; - } else { - rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding; - rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7); - rqst->rq_nvec++; + + /* No padding needed */ + if (!(len & 7)) + goto finished; + + num_padding = 8 - (len & 7); + if (!smb3_encryption_required(tcon)) { + /* + * If we do not have encryption then we can just add an extra + * iov for the padding. + */ + rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding; + rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding; + rqst->rq_nvec++; + len += num_padding; + } else { + /* + * We can not add a small padding iov for the encryption case + * because the encryption framework can not handle the padding + * iovs. + * We have to flatten this into a single buffer and add + * the padding to it. + */ + for (i = 1; i < rqst->rq_nvec; i++) { + memcpy(rqst->rq_iov[0].iov_base + + rqst->rq_iov[0].iov_len, + rqst->rq_iov[i].iov_base, + rqst->rq_iov[i].iov_len); + rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len; } - len = smb_rqst_len(server, rqst); + memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len, + 0, num_padding); + rqst->rq_iov[0].iov_len += num_padding; + len += num_padding; + rqst->rq_nvec = 1; } + finished: shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base); shdr->NextCommand = cpu_to_le32(len); } -static int -smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, - struct kstatfs *buf) +/* + * Passes the query info response back to the caller on success. + * Caller need to free this with free_rsp_buf(). + */ +int +smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, + __le16 *utf16_path, u32 desired_access, + u32 class, u32 type, u32 output_len, + struct kvec *rsp, int *buftype, + struct cifs_sb_info *cifs_sb) { - struct smb2_query_info_rsp *rsp; - struct smb2_fs_full_size_info *info = NULL; + struct cifs_ses *ses = tcon->ses; + int flags = 0; struct smb_rqst rqst[3]; int resp_buftype[3]; struct kvec rsp_iov[3]; struct kvec open_iov[SMB2_CREATE_IOV_SIZE]; struct kvec qi_iov[1]; struct kvec close_iov[1]; - struct cifs_ses *ses = tcon->ses; - struct TCP_Server_Info *server = ses->server; - __le16 srch_path = 0; /* Null - open root of share */ u8 oplock = SMB2_OPLOCK_LEVEL_NONE; struct cifs_open_parms oparms; struct cifs_fid fid; - int flags = 0; int rc; if (smb3_encryption_required(tcon)) @@ -1818,29 +1875,31 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, rqst[0].rq_nvec = SMB2_CREATE_IOV_SIZE; oparms.tcon = tcon; - oparms.desired_access = FILE_READ_ATTRIBUTES; + oparms.desired_access = desired_access; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (cifs_sb && backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; - rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &srch_path); + rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, utf16_path); if (rc) - goto qfs_exit; - smb2_set_next_command(server, &rqst[0], 0); + goto qic_exit; + smb2_set_next_command(tcon, &rqst[0]); memset(&qi_iov, 0, sizeof(qi_iov)); rqst[1].rq_iov = qi_iov; rqst[1].rq_nvec = 1; rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID, - FS_FULL_SIZE_INFORMATION, - SMB2_O_INFO_FILESYSTEM, 0, - sizeof(struct smb2_fs_full_size_info), 0, + class, type, 0, + output_len, 0, NULL); if (rc) - goto qfs_exit; - smb2_set_next_command(server, &rqst[1], 0); + goto qic_exit; + smb2_set_next_command(tcon, &rqst[1]); smb2_set_related(&rqst[1]); memset(&close_iov, 0, sizeof(close_iov)); @@ -1849,32 +1908,61 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID); if (rc) - goto qfs_exit; + goto qic_exit; smb2_set_related(&rqst[2]); rc = compound_send_recv(xid, ses, flags, 3, rqst, resp_buftype, rsp_iov); + if (rc) { + free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); + goto qic_exit; + } + *rsp = rsp_iov[1]; + *buftype = resp_buftype[1]; + + qic_exit: + SMB2_open_free(&rqst[0]); + SMB2_query_info_free(&rqst[1]); + SMB2_close_free(&rqst[2]); + free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); + free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + return rc; +} + +static int +smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon, + struct kstatfs *buf) +{ + struct smb2_query_info_rsp *rsp; + struct smb2_fs_full_size_info *info = NULL; + __le16 utf16_path = 0; /* Null - open root of share */ + struct kvec rsp_iov = {NULL, 0}; + int buftype = CIFS_NO_BUFFER; + int rc; + + + rc = smb2_query_info_compound(xid, tcon, &utf16_path, + FILE_READ_ATTRIBUTES, + FS_FULL_SIZE_INFORMATION, + SMB2_O_INFO_FILESYSTEM, + sizeof(struct smb2_fs_full_size_info), + &rsp_iov, &buftype, NULL); if (rc) goto qfs_exit; - rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; + rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base; buf->f_type = SMB2_MAGIC_NUMBER; info = (struct smb2_fs_full_size_info *)( le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp); rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset), le32_to_cpu(rsp->OutputBufferLength), - &rsp_iov[1], + &rsp_iov, sizeof(struct smb2_fs_full_size_info)); if (!rc) smb2_copy_fs_info_to_kstatfs(info, buf); qfs_exit: - SMB2_open_free(&rqst[0]); - SMB2_query_info_free(&rqst[1]); - SMB2_close_free(&rqst[2]); - free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); - free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); - free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base); + free_rsp_buf(buftype, rsp_iov.iov_base); return rc; } @@ -2743,7 +2831,7 @@ init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign) smb2_sg_set_buf(&sg[idx++], rqst[i].rq_iov[j].iov_base + skip, rqst[i].rq_iov[j].iov_len - skip); - } + } for (j = 0; j < rqst[i].rq_npages; j++) { unsigned int len, offset; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 27f86537a5d1..e283590955cd 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -50,6 +50,9 @@ #include "cifs_spnego.h" #include "smbdirect.h" #include "trace.h" +#ifdef CONFIG_CIFS_DFS_UPCALL +#include "dfs_cache.h" +#endif /* * The following table defines the expected "StructureSize" of SMB2 requests @@ -152,6 +155,77 @@ out: return; } +#ifdef CONFIG_CIFS_DFS_UPCALL +static int __smb2_reconnect(const struct nls_table *nlsc, + struct cifs_tcon *tcon) +{ + int rc; + struct dfs_cache_tgt_list tl; + struct dfs_cache_tgt_iterator *it = NULL; + char tree[MAX_TREE_SIZE + 1]; + const char *tcp_host; + size_t tcp_host_len; + const char *dfs_host; + size_t dfs_host_len; + + if (tcon->ipc) { + snprintf(tree, sizeof(tree), "\\\\%s\\IPC$", + tcon->ses->server->hostname); + return SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + } + + if (!tcon->dfs_path) + return SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); + + rc = dfs_cache_noreq_find(tcon->dfs_path + 1, NULL, &tl); + if (rc) + return rc; + + extract_unc_hostname(tcon->ses->server->hostname, &tcp_host, + &tcp_host_len); + + for (it = dfs_cache_get_tgt_iterator(&tl); it; + it = dfs_cache_get_next_tgt(&tl, it)) { + const char *tgt = dfs_cache_get_tgt_name(it); + + extract_unc_hostname(tgt, &dfs_host, &dfs_host_len); + + if (dfs_host_len != tcp_host_len + || strncasecmp(dfs_host, tcp_host, dfs_host_len) != 0) { + cifs_dbg(FYI, "%s: skipping %.*s, doesn't match %.*s", + __func__, + (int)dfs_host_len, dfs_host, + (int)tcp_host_len, tcp_host); + continue; + } + + snprintf(tree, sizeof(tree), "\\%s", tgt); + + rc = SMB2_tcon(0, tcon->ses, tree, tcon, nlsc); + if (!rc) + break; + if (rc == -EREMOTE) + break; + } + + if (!rc) { + if (it) + rc = dfs_cache_noreq_update_tgthint(tcon->dfs_path + 1, + it); + else + rc = -ENOENT; + } + dfs_cache_free_tgts(&tl); + return rc; +} +#else +static inline int __smb2_reconnect(const struct nls_table *nlsc, + struct cifs_tcon *tcon) +{ + return SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nlsc); +} +#endif + static int smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) { @@ -159,6 +233,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) struct nls_table *nls_codepage; struct cifs_ses *ses; struct TCP_Server_Info *server; + int retries; /* * SMB2s NegProt, SessSetup, Logoff do not have tcon yet so @@ -192,9 +267,12 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) ses = tcon->ses; server = ses->server; + retries = server->nr_targets; + /* - * Give demultiplex thread up to 10 seconds to reconnect, should be - * greater than cifs socket timeout which is 7 seconds + * Give demultiplex thread up to 10 seconds to each target available for + * reconnect -- should be greater than cifs socket timeout which is 7 + * seconds. */ while (server->tcpStatus == CifsNeedReconnect) { /* @@ -225,6 +303,9 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) if (server->tcpStatus != CifsNeedReconnect) break; + if (--retries) + continue; + /* * on "soft" mounts we wait once. Hard mounts keep * retrying until process is killed or server comes @@ -234,6 +315,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) cifs_dbg(FYI, "gave up waiting on reconnect in smb_init\n"); return -EHOSTDOWN; } + retries = server->nr_targets; } if (!tcon->ses->need_reconnect && !tcon->need_reconnect) @@ -271,7 +353,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon) if (tcon->use_persistent) tcon->need_reopen_files = true; - rc = SMB2_tcon(0, tcon->ses, tcon->treeName, tcon, nls_codepage); + rc = __smb2_reconnect(nls_codepage, tcon); mutex_unlock(&tcon->ses->session_mutex); cifs_dbg(FYI, "reconnect tcon rc = %d\n", rc); @@ -1955,7 +2037,6 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, struct smb_rqst rqst; struct smb2_create_req *req; struct smb2_create_rsp *rsp = NULL; - struct TCP_Server_Info *server; struct cifs_ses *ses = tcon->ses; struct kvec iov[3]; /* make sure at least one for each open context */ struct kvec rsp_iov = {NULL, 0}; @@ -1978,9 +2059,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode, if (!utf16_path) return -ENOMEM; - if (ses && (ses->server)) - server = ses->server; - else { + if (!ses || !(ses->server)) { rc = -EIO; goto err_free_path; } @@ -2768,18 +2847,6 @@ qinf_exit: return rc; } -int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_fid, u64 volatile_fid, - int ea_buf_size, struct smb2_file_full_ea_info *data) -{ - return query_info(xid, tcon, persistent_fid, volatile_fid, - FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, 0, - ea_buf_size, - sizeof(struct smb2_file_full_ea_info), - (void **)&data, - NULL); -} - int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, u64 volatile_fid, struct smb2_file_all_info *data) { @@ -3994,7 +4061,6 @@ static int build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level, int outbuf_len, u64 persistent_fid, u64 volatile_fid) { - struct TCP_Server_Info *server; int rc; struct smb2_query_info_req *req; unsigned int total_len; @@ -4004,8 +4070,6 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level, if ((tcon->ses == NULL) || (tcon->ses->server == NULL)) return -EIO; - server = tcon->ses->server; - rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req, &total_len); if (rc) diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 5671d5ee7f58..05dea6750c33 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1398,7 +1398,6 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ -#define SMB2_MIN_EA_BUF 2048 #define SMB2_MAX_EA_BUF 65536 struct smb2_file_full_ea_info { /* encoding of response for level 15 */ diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 2fe78acd7d0c..87733b27a65f 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -116,9 +116,8 @@ extern void smb2_reconnect_server(struct work_struct *work); extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server); extern unsigned long smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst); -extern void smb2_set_next_command(struct TCP_Server_Info *server, - struct smb_rqst *rqst, - bool has_space_for_padding); +extern void smb2_set_next_command(struct cifs_tcon *tcon, + struct smb_rqst *rqst); extern void smb2_set_related(struct smb_rqst *rqst); /* @@ -154,10 +153,6 @@ extern int SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, extern void SMB2_close_free(struct smb_rqst *rqst); extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id); -extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, - u64 persistent_file_id, u64 volatile_file_id, - int ea_buf_size, - struct smb2_file_full_ea_info *data); extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_file_id, u64 volatile_file_id, struct smb2_file_all_info *data); @@ -241,4 +236,10 @@ extern void smb2_copy_fs_info_to_kstatfs( extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server); extern int smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec); +extern int smb2_query_info_compound(const unsigned int xid, + struct cifs_tcon *tcon, + __le16 *utf16_path, u32 desired_access, + u32 class, u32 type, u32 output_len, + struct kvec *rsp, int *buftype, + struct cifs_sb_info *cifs_sb); #endif /* _SMB2PROTO_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 83ff0c25710d..5be7302853b6 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -126,9 +126,11 @@ DeleteMidQEntry(struct mid_q_entry *midEntry) if ((slow_rsp_threshold != 0) && time_after(now, midEntry->when_alloc + (slow_rsp_threshold * HZ)) && (midEntry->command != command)) { - /* smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command */ - if ((le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) && - (le16_to_cpu(midEntry->command) >= 0)) + /* + * smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command + * NB: le16_to_cpu returns unsigned so can not be negative below + */ + if (le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) cifs_stats_inc(&midEntry->server->smb2slowcmd[le16_to_cpu(midEntry->command)]); trace_smb3_slow_rsp(le16_to_cpu(midEntry->command), diff --git a/fs/iomap.c b/fs/iomap.c index 3a0cd557b4cf..a3088fae567b 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1921,8 +1921,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, return -EIOCBQUEUED; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); - + set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(dio->submit.waiter)) break; diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 00d5ef5f99f7..214a2fa1f1e3 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -128,24 +128,14 @@ static void encode_netobj(struct xdr_stream *xdr, static int decode_netobj(struct xdr_stream *xdr, struct xdr_netobj *obj) { - u32 length; - __be32 *p; + ssize_t ret; - p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - goto out_overflow; - length = be32_to_cpup(p++); - if (unlikely(length > XDR_MAX_NETOBJ)) - goto out_size; - obj->len = length; - obj->data = (u8 *)p; + ret = xdr_stream_decode_opaque_inline(xdr, (void *)&obj->data, + XDR_MAX_NETOBJ); + if (unlikely(ret < 0)) + return -EIO; + obj->len = ret; return 0; -out_size: - dprintk("NFS: returned netobj was too long: %u\n", length); - return -EIO; -out_overflow: - print_overflow_msg(__func__, xdr); - return -EIO; } /* diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index d20b92f271c2..e8a004097d18 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -256,7 +256,7 @@ static int nlm_wait_on_grace(wait_queue_head_t *queue) * Generic NLM call */ static int -nlmclnt_call(struct rpc_cred *cred, struct nlm_rqst *req, u32 proc) +nlmclnt_call(const struct cred *cred, struct nlm_rqst *req, u32 proc) { struct nlm_host *host = req->a_host; struct rpc_clnt *clnt; @@ -401,7 +401,7 @@ int nlm_async_reply(struct nlm_rqst *req, u32 proc, const struct rpc_call_ops *t * completion in order to be able to correctly track the lock * state. */ -static int nlmclnt_async_call(struct rpc_cred *cred, struct nlm_rqst *req, u32 proc, const struct rpc_call_ops *tk_ops) +static int nlmclnt_async_call(const struct cred *cred, struct nlm_rqst *req, u32 proc, const struct rpc_call_ops *tk_ops) { struct rpc_message msg = { .rpc_argp = &req->a_args, @@ -442,7 +442,7 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl) fl->fl_start = req->a_res.lock.fl.fl_start; fl->fl_end = req->a_res.lock.fl.fl_end; fl->fl_type = req->a_res.lock.fl.fl_type; - fl->fl_pid = 0; + fl->fl_pid = -req->a_res.lock.fl.fl_pid; break; default: status = nlm_stat_to_errno(req->a_res.status); @@ -510,7 +510,7 @@ static int do_vfs_lock(struct file_lock *fl) static int nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) { - struct rpc_cred *cred = nfs_file_cred(fl->fl_file); + const struct cred *cred = nfs_file_cred(fl->fl_file); struct nlm_host *host = req->a_host; struct nlm_res *resp = &req->a_res; struct nlm_wait *block = NULL; diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c index 2c6176387143..747b9c8c940a 100644 --- a/fs/lockd/clntxdr.c +++ b/fs/lockd/clntxdr.c @@ -125,24 +125,14 @@ static void encode_netobj(struct xdr_stream *xdr, static int decode_netobj(struct xdr_stream *xdr, struct xdr_netobj *obj) { - u32 length; - __be32 *p; + ssize_t ret; - p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - goto out_overflow; - length = be32_to_cpup(p++); - if (unlikely(length > XDR_MAX_NETOBJ)) - goto out_size; - obj->len = length; - obj->data = (u8 *)p; + ret = xdr_stream_decode_opaque_inline(xdr, (void *)&obj->data, + XDR_MAX_NETOBJ); + if (unlikely(ret < 0)) + return -EIO; + obj->len = ret; return 0; -out_size: - dprintk("NFS: returned netobj was too long: %u\n", length); - return -EIO; -out_overflow: - print_overflow_msg(__func__, xdr); - return -EIO; } /* diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 7147e4aebecc..9846f7e95282 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -127,7 +127,7 @@ nlm_decode_lock(__be32 *p, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_owner = current->files; - fl->fl_pid = (pid_t)lock->svid; + fl->fl_pid = current->tgid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ start = ntohl(*p++); @@ -269,7 +269,7 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = (pid_t)lock->svid; + lock->fl.fl_pid = current->tgid; if (!(p = nlm_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 7ed9edf9aed4..70154f376695 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -119,7 +119,7 @@ nlm4_decode_lock(__be32 *p, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_owner = current->files; - fl->fl_pid = (pid_t)lock->svid; + fl->fl_pid = current->tgid; fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; /* as good as anything else */ p = xdr_decode_hyper(p, &start); @@ -266,7 +266,7 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) memset(lock, 0, sizeof(*lock)); locks_init_lock(&lock->fl); lock->svid = ~(u32) 0; - lock->fl.fl_pid = (pid_t)lock->svid; + lock->fl.fl_pid = current->tgid; if (!(p = nlm4_decode_cookie(p, &argp->cookie)) || !(p = xdr_decode_string_inplace(p, &lock->caller, diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index d3781cd983f6..690221747b47 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -584,7 +584,7 @@ static int decode_sector_number(__be32 **rp, sector_t *sp) static struct nfs4_deviceid_node * bl_find_get_deviceid(struct nfs_server *server, - const struct nfs4_deviceid *id, struct rpc_cred *cred, + const struct nfs4_deviceid *id, const struct cred *cred, gfp_t gfp_mask) { struct nfs4_deviceid_node *node; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 509dc5adeb8f..0b602a39dd71 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -56,7 +56,7 @@ static int nfs4_callback_up_net(struct svc_serv *serv, struct net *net) nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret > 0) { nn->nfs_callback_tcpport6 = ret; - dprintk("NFS: Callback listener port = %u (af %u, net %x\n", + dprintk("NFS: Callback listener port = %u (af %u, net %x)\n", nn->nfs_callback_tcpport6, PF_INET6, net->ns.inum); } else if (ret != -EAFNOSUPPORT) goto out_err; @@ -206,11 +206,13 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, goto err_bind; } - ret = -EPROTONOSUPPORT; + ret = 0; if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0) ret = nfs4_callback_up_net(serv, net); - else if (xprt->ops->bc_up) - ret = xprt->ops->bc_up(serv, net); + else if (xprt->ops->bc_setup) + set_bc_enabled(serv); + else + ret = -EPROTONOSUPPORT; if (ret < 0) { printk(KERN_ERR "NFS: callback service start failed\n"); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 96d5f8135eb9..fb1cf1a4bda2 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -151,7 +151,6 @@ EXPORT_SYMBOL_GPL(unregister_nfs_version); struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) { struct nfs_client *clp; - struct rpc_cred *cred; int err = -ENOMEM; if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) @@ -182,9 +181,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_proto = cl_init->proto; clp->cl_net = get_net(cl_init->net); - cred = rpc_lookup_machine_cred("*"); - if (!IS_ERR(cred)) - clp->cl_machine_cred = cred; + clp->cl_principal = "*"; nfs_fscache_get_client_cookie(clp); return clp; @@ -246,9 +243,6 @@ void nfs_free_client(struct nfs_client *clp) if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); - if (clp->cl_machine_cred != NULL) - put_rpccred(clp->cl_machine_cred); - put_net(clp->cl_net); put_nfs_version(clp->cl_nfs_mod); kfree(clp->cl_hostname); @@ -527,6 +521,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, return PTR_ERR(clnt); } + clnt->cl_principal = clp->cl_principal; clp->cl_rpcclient = clnt; return 0; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 6ec2f78c1e19..885363ca8569 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -26,10 +26,8 @@ static void nfs_free_delegation(struct nfs_delegation *delegation) { - if (delegation->cred) { - put_rpccred(delegation->cred); - delegation->cred = NULL; - } + put_cred(delegation->cred); + delegation->cred = NULL; kfree_rcu(delegation, rcu); } @@ -178,13 +176,13 @@ again: * @pagemod_limit: write delegation "space_limit" * */ -void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, +void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; - struct rpc_cred *oldcred = NULL; + const struct cred *oldcred = NULL; rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); @@ -195,12 +193,12 @@ void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, delegation->type = type; delegation->pagemod_limit = pagemod_limit; oldcred = delegation->cred; - delegation->cred = get_rpccred(cred); + delegation->cred = get_cred(cred); clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); spin_unlock(&delegation->lock); rcu_read_unlock(); - put_rpccred(oldcred); + put_cred(oldcred); trace_nfs4_reclaim_delegation(inode, type); return; } @@ -341,7 +339,7 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation, * * Returns zero on success, or a negative errno value. */ -int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, +int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) @@ -360,7 +358,7 @@ int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, delegation->type = type; delegation->pagemod_limit = pagemod_limit; delegation->change_attr = inode_peek_iversion_raw(inode); - delegation->cred = get_rpccred(cred); + delegation->cred = get_cred(cred); delegation->inode = inode; delegation->flags = 1<<NFS_DELEGATION_REFERENCED; spin_lock_init(&delegation->lock); @@ -1047,7 +1045,7 @@ void nfs_reap_expired_delegations(struct nfs_client *clp) struct nfs_delegation *delegation; struct nfs_server *server; struct inode *inode; - struct rpc_cred *cred; + const struct cred *cred; nfs4_stateid stateid; restart: @@ -1069,7 +1067,7 @@ restart: nfs_sb_deactive(server->super); goto restart; } - cred = get_rpccred_rcu(delegation->cred); + cred = get_cred_rcu(delegation->cred); nfs4_stateid_copy(&stateid, &delegation->stateid); clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags); rcu_read_unlock(); @@ -1078,7 +1076,7 @@ restart: nfs_revoke_delegation(inode, &stateid); nfs_inode_find_state_and_recover(inode, &stateid); } - put_rpccred(cred); + put_cred(cred); if (nfs4_server_rebooted(clp)) { nfs_inode_mark_test_expired_delegation(server,inode); iput(inode); @@ -1173,7 +1171,7 @@ out: * otherwise "false" is returned. */ bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, - nfs4_stateid *dst, struct rpc_cred **cred) + nfs4_stateid *dst, const struct cred **cred) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_delegation *delegation; @@ -1187,7 +1185,7 @@ bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid_copy(dst, &delegation->stateid); nfs_mark_delegation_referenced(delegation); if (cred) - *cred = get_rpccred(delegation->cred); + *cred = get_cred(delegation->cred); } rcu_read_unlock(); return ret; diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index bb1ef8c37af4..dcbf3394ba0e 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -15,7 +15,7 @@ */ struct nfs_delegation { struct list_head super_list; - struct rpc_cred *cred; + const struct cred *cred; struct inode *inode; nfs4_stateid stateid; fmode_t type; @@ -36,9 +36,9 @@ enum { NFS_DELEGATION_TEST_EXPIRED, }; -int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, +int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit); -void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, +void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit); int nfs4_inode_return_delegation(struct inode *inode); int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); @@ -60,10 +60,10 @@ void nfs_mark_test_expired_all_delegations(struct nfs_client *clp); void nfs_reap_expired_delegations(struct nfs_client *clp); /* NFSv4 delegation-related procedures */ -int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync); +int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync); int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type); int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid); -bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred); +bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred); bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 71b2e390becf..6bf4471850c8 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -67,7 +67,7 @@ const struct address_space_operations nfs_dir_aops = { .freepage = nfs_readdir_clear_array, }; -static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) +static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(dir); struct nfs_open_dir_context *ctx; @@ -77,7 +77,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->attr_gencount = nfsi->attr_gencount; ctx->dir_cookie = 0; ctx->dup_cookie = 0; - ctx->cred = get_rpccred(cred); + ctx->cred = get_cred(cred); spin_lock(&dir->i_lock); list_add(&ctx->list, &nfsi->open_files); spin_unlock(&dir->i_lock); @@ -91,7 +91,7 @@ static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_cont spin_lock(&dir->i_lock); list_del(&ctx->list); spin_unlock(&dir->i_lock); - put_rpccred(ctx->cred); + put_cred(ctx->cred); kfree(ctx); } @@ -103,23 +103,18 @@ nfs_opendir(struct inode *inode, struct file *filp) { int res = 0; struct nfs_open_dir_context *ctx; - struct rpc_cred *cred; dfprintk(FILE, "NFS: open dir(%pD2)\n", filp); nfs_inc_stats(inode, NFSIOS_VFSOPEN); - cred = rpc_lookup_cred(); - if (IS_ERR(cred)) - return PTR_ERR(cred); - ctx = alloc_nfs_open_dir_context(inode, cred); + ctx = alloc_nfs_open_dir_context(inode, current_cred()); if (IS_ERR(ctx)) { res = PTR_ERR(ctx); goto out; } filp->private_data = ctx; out: - put_rpccred(cred); return res; } @@ -334,7 +329,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct file *file, struct inode *inode) { struct nfs_open_dir_context *ctx = file->private_data; - struct rpc_cred *cred = ctx->cred; + const struct cred *cred = ctx->cred; unsigned long timestamp, gencount; int error; @@ -2139,7 +2134,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt static void nfs_access_free_entry(struct nfs_access_entry *entry) { - put_rpccred(entry->cred); + put_cred(entry->cred); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); @@ -2265,17 +2260,18 @@ void nfs_access_zap_cache(struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); -static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred) +static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; - struct nfs_access_entry *entry; while (n != NULL) { - entry = rb_entry(n, struct nfs_access_entry, rb_node); + struct nfs_access_entry *entry = + rb_entry(n, struct nfs_access_entry, rb_node); + int cmp = cred_fscmp(cred, entry->cred); - if (cred < entry->cred) + if (cmp < 0) n = n->rb_left; - else if (cred > entry->cred) + else if (cmp > 0) n = n->rb_right; else return entry; @@ -2283,7 +2279,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, st return NULL; } -static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2326,7 +2322,7 @@ out_zap: return -ENOENT; } -static int nfs_access_get_cached_rcu(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res) +static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res) { /* Only check the most recently returned cache entry, * but do it without locking. @@ -2363,15 +2359,17 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry * struct rb_node **p = &root_node->rb_node; struct rb_node *parent = NULL; struct nfs_access_entry *entry; + int cmp; spin_lock(&inode->i_lock); while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); + cmp = cred_fscmp(set->cred, entry->cred); - if (set->cred < entry->cred) + if (cmp < 0) p = &parent->rb_left; - else if (set->cred > entry->cred) + else if (cmp > 0) p = &parent->rb_right; else goto found; @@ -2395,7 +2393,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_rpccred(set->cred); + cache->cred = get_cred(set->cred); cache->mask = set->mask; /* The above field assignments must be visible @@ -2459,7 +2457,7 @@ void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result) } EXPORT_SYMBOL_GPL(nfs_access_set_mask); -static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) +static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) { struct nfs_access_entry cache; bool may_block = (mask & MAY_NOT_BLOCK) == 0; @@ -2523,7 +2521,7 @@ static int nfs_open_permission_mask(int openflags) return mask; } -int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) +int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags) { return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); } @@ -2548,7 +2546,7 @@ static int nfs_execute_ok(struct inode *inode, int mask) int nfs_permission(struct inode *inode, int mask) { - struct rpc_cred *cred; + const struct cred *cred = current_cred(); int res = 0; nfs_inc_stats(inode, NFSIOS_VFSACCESS); @@ -2582,20 +2580,11 @@ force_lookup: /* Always try fast lookups first */ rcu_read_lock(); - cred = rpc_lookup_cred_nonblock(); - if (!IS_ERR(cred)) - res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK); - else - res = PTR_ERR(cred); + res = nfs_do_access(inode, cred, mask|MAY_NOT_BLOCK); rcu_read_unlock(); if (res == -ECHILD && !(mask & MAY_NOT_BLOCK)) { /* Fast lookup failed, try the slow way */ - cred = rpc_lookup_cred(); - if (!IS_ERR(cred)) { - res = nfs_do_access(inode, cred, mask); - put_rpccred(cred); - } else - res = PTR_ERR(cred); + res = nfs_do_access(inode, cred, mask); } out: if (!res && (mask & MAY_EXEC)) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 310d7500f665..63abe705f4ca 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -9,6 +9,7 @@ #include <linux/nfs_fs.h> #include <linux/nfs_page.h> #include <linux/module.h> +#include <linux/sched/mm.h> #include <linux/sunrpc/metrics.h> @@ -27,9 +28,6 @@ #define FF_LAYOUT_POLL_RETRY_MAX (15*HZ) #define FF_LAYOUTRETURN_MAXERR 20 - -static struct group_info *ff_zero_group; - static void ff_layout_read_record_layoutstats_done(struct rpc_task *task, struct nfs_pgio_header *hdr); static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, @@ -226,16 +224,14 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags) static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror) { - struct rpc_cred *cred; + const struct cred *cred; ff_layout_remove_mirror(mirror); kfree(mirror->fh_versions); cred = rcu_access_pointer(mirror->ro_cred); - if (cred) - put_rpccred(cred); + put_cred(cred); cred = rcu_access_pointer(mirror->rw_cred); - if (cred) - put_rpccred(cred); + put_cred(cred); nfs4_ff_layout_put_deviceid(mirror->mirror_ds); kfree(mirror); } @@ -413,8 +409,10 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, for (i = 0; i < fls->mirror_array_cnt; i++) { struct nfs4_ff_layout_mirror *mirror; - struct auth_cred acred = { .group_info = ff_zero_group }; - struct rpc_cred __rcu *cred; + struct cred *kcred; + const struct cred *cred; + kuid_t uid; + kgid_t gid; u32 ds_count, fh_count, id; int j; @@ -482,21 +480,28 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, if (rc) goto out_err_free; - acred.uid = make_kuid(&init_user_ns, id); + uid = make_kuid(&init_user_ns, id); /* group */ rc = decode_name(&stream, &id); if (rc) goto out_err_free; - acred.gid = make_kgid(&init_user_ns, id); + gid = make_kgid(&init_user_ns, id); - /* find the cred for it */ - rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags)); - if (IS_ERR(cred)) { - rc = PTR_ERR(cred); - goto out_err_free; + if (gfp_flags & __GFP_FS) + kcred = prepare_kernel_cred(NULL); + else { + unsigned int nofs_flags = memalloc_nofs_save(); + kcred = prepare_kernel_cred(NULL); + memalloc_nofs_restore(nofs_flags); } + rc = -ENOMEM; + if (!kcred) + goto out_err_free; + kcred->fsuid = uid; + kcred->fsgid = gid; + cred = kcred; if (lgr->range.iomode == IOMODE_READ) rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred); @@ -519,8 +524,8 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, dprintk("%s: iomode %s uid %u gid %u\n", __func__, lgr->range.iomode == IOMODE_READ ? "READ" : "RW", - from_kuid(&init_user_ns, acred.uid), - from_kgid(&init_user_ns, acred.gid)); + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid)); } p = xdr_inline_decode(&stream, 4); @@ -1698,7 +1703,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; - struct rpc_cred *ds_cred; + const struct cred *ds_cred; loff_t offset = hdr->args.offset; u32 idx = hdr->pgio_mirror_idx; int vers; @@ -1749,7 +1754,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) vers == 3 ? &ff_layout_read_call_ops_v3 : &ff_layout_read_call_ops_v4, 0, RPC_TASK_SOFTCONN); - put_rpccred(ds_cred); + put_cred(ds_cred); return PNFS_ATTEMPTED; out_failed: @@ -1765,7 +1770,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) struct pnfs_layout_segment *lseg = hdr->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; - struct rpc_cred *ds_cred; + const struct cred *ds_cred; loff_t offset = hdr->args.offset; int vers; struct nfs_fh *fh; @@ -1814,7 +1819,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) vers == 3 ? &ff_layout_write_call_ops_v3 : &ff_layout_write_call_ops_v4, sync, RPC_TASK_SOFTCONN); - put_rpccred(ds_cred); + put_cred(ds_cred); return PNFS_ATTEMPTED; out_failed: @@ -1844,7 +1849,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) struct pnfs_layout_segment *lseg = data->lseg; struct nfs4_pnfs_ds *ds; struct rpc_clnt *ds_clnt; - struct rpc_cred *ds_cred; + const struct cred *ds_cred; u32 idx; int vers, ret; struct nfs_fh *fh; @@ -1884,7 +1889,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how) vers == 3 ? &ff_layout_commit_call_ops_v3 : &ff_layout_commit_call_ops_v4, how, RPC_TASK_SOFTCONN); - put_rpccred(ds_cred); + put_cred(ds_cred); return ret; out_err: pnfs_generic_prepare_to_resend_writes(data); @@ -2383,11 +2388,6 @@ static int __init nfs4flexfilelayout_init(void) { printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n", __func__); - if (!ff_zero_group) { - ff_zero_group = groups_alloc(0); - if (!ff_zero_group) - return -ENOMEM; - } return pnfs_register_layoutdriver(&flexfilelayout_type); } @@ -2396,10 +2396,6 @@ static void __exit nfs4flexfilelayout_exit(void) printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n", __func__); pnfs_unregister_layoutdriver(&flexfilelayout_type); - if (ff_zero_group) { - put_group_info(ff_zero_group); - ff_zero_group = NULL; - } } MODULE_ALIAS("nfs-layouttype4-4"); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index de50a342d5a5..c2626bad466b 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -81,8 +81,8 @@ struct nfs4_ff_layout_mirror { u32 fh_versions_cnt; struct nfs_fh *fh_versions; nfs4_stateid stateid; - struct rpc_cred __rcu *ro_cred; - struct rpc_cred __rcu *rw_cred; + const struct cred __rcu *ro_cred; + const struct cred __rcu *rw_cred; refcount_t ref; spinlock_t lock; unsigned long flags; @@ -229,8 +229,8 @@ nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx, struct nfs_client *ds_clp, struct inode *inode); -struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, - u32 ds_idx, struct rpc_cred *mdscred); +const struct cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, + u32 ds_idx, const struct cred *mdscred); bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg); bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index d23347389626..11766a74216d 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -330,10 +330,10 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo, return 0; } -static struct rpc_cred * +static const struct cred * ff_layout_get_mirror_cred(struct nfs4_ff_layout_mirror *mirror, u32 iomode) { - struct rpc_cred *cred, __rcu **pcred; + const struct cred *cred, __rcu **pcred; if (iomode == IOMODE_READ) pcred = &mirror->ro_cred; @@ -346,7 +346,7 @@ ff_layout_get_mirror_cred(struct nfs4_ff_layout_mirror *mirror, u32 iomode) if (!cred) break; - cred = get_rpccred_rcu(cred); + cred = get_cred_rcu(cred); } while(!cred); rcu_read_unlock(); return cred; @@ -465,19 +465,19 @@ out: return ds; } -struct rpc_cred * +const struct cred * ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx, - struct rpc_cred *mdscred) + const struct cred *mdscred) { struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx); - struct rpc_cred *cred; + const struct cred *cred; if (mirror && !mirror->mirror_ds->ds_versions[0].tightly_coupled) { cred = ff_layout_get_mirror_cred(mirror, lseg->pls_range.iomode); if (!cred) - cred = get_rpccred(mdscred); + cred = get_cred(mdscred); } else { - cred = get_rpccred(mdscred); + cred = get_cred(mdscred); } return cred; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 5b1eee4952b7..094775ea0781 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -950,18 +950,17 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, struct file *filp) { struct nfs_open_context *ctx; - struct rpc_cred *cred = rpc_lookup_cred(); - if (IS_ERR(cred)) - return ERR_CAST(cred); + const struct cred *cred = get_current_cred(); ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { - put_rpccred(cred); + put_cred(cred); return ERR_PTR(-ENOMEM); } nfs_sb_active(dentry->d_sb); ctx->dentry = dget(dentry); ctx->cred = cred; + ctx->ll_cred = NULL; ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; @@ -997,10 +996,10 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) } if (inode != NULL) NFS_PROTO(inode)->close_context(ctx, is_sync); - if (ctx->cred != NULL) - put_rpccred(ctx->cred); + put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); + put_rpccred(ctx->ll_cred); kfree(ctx->mdsthreshold); kfree_rcu(ctx, rcu_head); } @@ -1042,7 +1041,7 @@ EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics */ -struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode) +struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *pos, *ctx = NULL; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 8357ff69962f..7f80f036ebd9 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -254,7 +254,7 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, - struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, + const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags); void nfs_free_request(struct nfs_page *req); struct nfs_pgio_mirror * @@ -269,7 +269,7 @@ static inline bool nfs_pgio_has_mirroring(struct nfs_pageio_descriptor *desc) static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1, const struct nfs_open_context *ctx2) { - return ctx1->cred == ctx2->cred && ctx1->state == ctx2->state; + return cred_fscmp(ctx1->cred, ctx2->cred) == 0 && ctx1->state == ctx2->state; } /* nfs2xdr.c */ @@ -395,7 +395,6 @@ extern const struct super_operations nfs_sops; extern struct file_system_type nfs_fs_type; extern struct file_system_type nfs_xdev_fs_type; #if IS_ENABLED(CONFIG_NFS_V4) -extern struct file_system_type nfs4_xdev_fs_type; extern struct file_system_type nfs4_referral_fs_type; #endif bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); @@ -565,13 +564,13 @@ extern struct nfs_client *nfs4_init_client(struct nfs_client *clp, const struct nfs_client_initdata *); extern int nfs40_walk_client_list(struct nfs_client *clp, struct nfs_client **result, - struct rpc_cred *cred); + const struct cred *cred); extern int nfs41_walk_client_list(struct nfs_client *clp, struct nfs_client **result, - struct rpc_cred *cred); -extern int nfs4_test_session_trunk(struct rpc_clnt *, - struct rpc_xprt *, - void *); + const struct cred *cred); +extern void nfs4_test_session_trunk(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data); static inline struct inode *nfs_igrab_and_active(struct inode *inode) { diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 71bc16225b98..a3ad2d46fd42 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -607,7 +607,7 @@ out: * readdirplus. */ static int -nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, +nfs3_proc_readdir(struct dentry *dentry, const struct cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); @@ -628,7 +628,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, .rpc_proc = &nfs3_procedures[NFS3PROC_READDIR], .rpc_argp = &arg, .rpc_resp = &res, - .rpc_cred = cred + .rpc_cred = cred, }; int status = -ENOMEM; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 1b994b527518..06ac3d9ac7c6 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -62,10 +62,11 @@ struct nfs4_minor_version_ops { void (*free_lock_state)(struct nfs_server *, struct nfs4_lock_state *); int (*test_and_free_expired)(struct nfs_server *, - nfs4_stateid *, struct rpc_cred *); + nfs4_stateid *, const struct cred *); struct nfs_seqid * (*alloc_seqid)(struct nfs_seqid_counter *, gfp_t); - int (*session_trunk)(struct rpc_clnt *, struct rpc_xprt *, void *); + void (*session_trunk)(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, void *data); const struct rpc_call_ops *call_sync_ops; const struct nfs4_state_recovery_ops *reboot_recovery_ops; const struct nfs4_state_recovery_ops *nograce_recovery_ops; @@ -107,7 +108,7 @@ struct nfs4_state_owner { unsigned long so_expires; struct rb_node so_server_node; - struct rpc_cred *so_cred; /* Associated cred */ + const struct cred *so_cred; /* Associated cred */ spinlock_t so_lock; atomic_t so_count; @@ -212,10 +213,10 @@ struct nfs4_state_recovery_ops { int state_flag_bit; int (*recover_open)(struct nfs4_state_owner *, struct nfs4_state *); int (*recover_lock)(struct nfs4_state *, struct file_lock *); - int (*establish_clid)(struct nfs_client *, struct rpc_cred *); - int (*reclaim_complete)(struct nfs_client *, struct rpc_cred *); + int (*establish_clid)(struct nfs_client *, const struct cred *); + int (*reclaim_complete)(struct nfs_client *, const struct cred *); int (*detect_trunking)(struct nfs_client *, struct nfs_client **, - struct rpc_cred *); + const struct cred *); }; struct nfs4_opendata { @@ -245,19 +246,19 @@ struct nfs4_opendata { struct nfs4_add_xprt_data { struct nfs_client *clp; - struct rpc_cred *cred; + const struct cred *cred; }; struct nfs4_state_maintenance_ops { - int (*sched_state_renewal)(struct nfs_client *, struct rpc_cred *, unsigned); - struct rpc_cred * (*get_state_renewal_cred_locked)(struct nfs_client *); - int (*renew_lease)(struct nfs_client *, struct rpc_cred *); + int (*sched_state_renewal)(struct nfs_client *, const struct cred *, unsigned); + const struct cred * (*get_state_renewal_cred)(struct nfs_client *); + int (*renew_lease)(struct nfs_client *, const struct cred *); }; struct nfs4_mig_recovery_ops { int (*get_locations)(struct inode *, struct nfs4_fs_locations *, - struct page *, struct rpc_cred *); - int (*fsid_present)(struct inode *, struct rpc_cred *); + struct page *, const struct cred *); + int (*fsid_present)(struct inode *, const struct cred *); }; extern const struct dentry_operations nfs4_dentry_operations; @@ -286,21 +287,21 @@ extern int nfs4_call_sync(struct rpc_clnt *, struct nfs_server *, struct rpc_message *, struct nfs4_sequence_args *, struct nfs4_sequence_res *, int); extern void nfs4_init_sequence(struct nfs4_sequence_args *, struct nfs4_sequence_res *, int, int); -extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *); -extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *); +extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, const struct cred *, struct nfs4_setclientid_res *); +extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, const struct cred *); extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *, bool); -extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred); -extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred); +extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, const struct cred *cred); +extern int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred); extern int nfs4_destroy_clientid(struct nfs_client *clp); -extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); -extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); +extern int nfs4_init_clientid(struct nfs_client *, const struct cred *); +extern int nfs41_init_clientid(struct nfs_client *, const struct cred *); extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, - struct page *page, struct rpc_cred *); -extern int nfs4_proc_fsid_present(struct inode *, struct rpc_cred *); + struct page *page, const struct cred *); +extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *); extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *); @@ -312,8 +313,8 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, #if defined(CONFIG_NFS_V4_1) extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *); -extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *); -extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *); +extern int nfs4_proc_create_session(struct nfs_client *, const struct cred *); +extern int nfs4_proc_destroy_session(struct nfs4_session *, const struct cred *); extern int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo); extern int nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, @@ -338,7 +339,6 @@ static inline bool _nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, struct rpc_clnt **clntp, struct rpc_message *msg) { - struct rpc_cred *newcred = NULL; rpc_authflavor_t flavor; if (sp4_mode == NFS_SP4_MACH_CRED_CLEANUP || @@ -353,13 +353,7 @@ _nfs4_state_protect(struct nfs_client *clp, unsigned long sp4_mode, return false; } if (test_bit(sp4_mode, &clp->cl_sp4_flags)) { - spin_lock(&clp->cl_lock); - if (clp->cl_machine_cred != NULL) - /* don't call get_rpccred on the machine cred - - * a reference will be held for life of clp */ - newcred = clp->cl_machine_cred; - spin_unlock(&clp->cl_lock); - msg->rpc_cred = newcred; + msg->rpc_cred = rpc_machine_cred(); flavor = clp->cl_rpcclient->cl_auth->au_flavor; WARN_ON_ONCE(flavor != RPC_AUTH_GSS_KRB5I && @@ -450,16 +444,16 @@ extern void nfs4_set_lease_period(struct nfs_client *clp, /* nfs4state.c */ -struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); -struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp); -struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp); +const struct cred *nfs4_get_clid_cred(struct nfs_client *clp); +const struct cred *nfs4_get_machine_cred(struct nfs_client *clp); +const struct cred *nfs4_get_renew_cred(struct nfs_client *clp); int nfs4_discover_server_trunking(struct nfs_client *clp, struct nfs_client **); int nfs40_discover_server_trunking(struct nfs_client *clp, - struct nfs_client **, struct rpc_cred *); + struct nfs_client **, const struct cred *); #if defined(CONFIG_NFS_V4_1) int nfs41_discover_server_trunking(struct nfs_client *clp, - struct nfs_client **, struct rpc_cred *); + struct nfs_client **, const struct cred *); extern void nfs4_schedule_session_recovery(struct nfs4_session *, int); extern void nfs41_notify_server(struct nfs_client *); #else @@ -468,7 +462,7 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, } #endif /* CONFIG_NFS_V4_1 */ -extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t); +extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, const struct cred *, gfp_t); extern void nfs4_put_state_owner(struct nfs4_state_owner *); extern void nfs4_purge_state_owners(struct nfs_server *); extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *); @@ -494,7 +488,7 @@ extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp); extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl); extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t, const struct nfs_lock_context *, nfs4_stateid *, - struct rpc_cred **); + const struct cred **); extern bool nfs4_refresh_open_stateid(nfs4_stateid *dst, struct nfs4_state *state); extern bool nfs4_copy_open_stateid(nfs4_stateid *dst, diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 8f53455c4765..2548405da1f7 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -545,7 +545,7 @@ static int nfs4_match_client(struct nfs_client *pos, struct nfs_client *new, */ int nfs40_walk_client_list(struct nfs_client *new, struct nfs_client **result, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); struct nfs_client *pos, *prev = NULL; @@ -711,7 +711,7 @@ out_err: */ int nfs41_walk_client_list(struct nfs_client *new, struct nfs_client **result, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id); struct nfs_client *pos, *prev = NULL; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 0ba2b0fb8ff3..557a5d636183 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -93,19 +93,19 @@ static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinf static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *label, struct inode *inode); static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode); -static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, +static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, struct nfs_open_context *ctx, struct nfs4_label *ilabel, struct nfs4_label *olabel); #ifdef CONFIG_NFS_V4_1 static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, - struct rpc_cred *cred, + const struct cred *cred, struct nfs4_slot *slot, bool is_privileged); static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *, - struct rpc_cred *); + const struct cred *); static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *, - struct rpc_cred *, bool); + const struct cred *, bool); #endif #ifdef CONFIG_NFS_V4_SECURITY_LABEL @@ -361,7 +361,7 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent static void nfs4_test_and_free_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops; @@ -370,7 +370,7 @@ static void nfs4_test_and_free_stateid(struct nfs_server *server, static void __nfs4_free_revoked_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { stateid->type = NFS4_REVOKED_STATEID_TYPE; nfs4_test_and_free_stateid(server, stateid, cred); @@ -378,7 +378,7 @@ static void __nfs4_free_revoked_stateid(struct nfs_server *server, static void nfs4_free_revoked_stateid(struct nfs_server *server, const nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { nfs4_stateid tmp; @@ -908,7 +908,7 @@ static const struct rpc_call_ops nfs41_call_sync_ops = { static void nfs4_sequence_process_interrupted(struct nfs_client *client, - struct nfs4_slot *slot, struct rpc_cred *cred) + struct nfs4_slot *slot, const struct cred *cred) { struct rpc_task *task; @@ -939,7 +939,7 @@ EXPORT_SYMBOL_GPL(nfs4_sequence_done); static void nfs4_sequence_process_interrupted(struct nfs_client *client, - struct nfs4_slot *slot, struct rpc_cred *cred) + struct nfs4_slot *slot, const struct cred *cred) { WARN_ON_ONCE(1); slot->interrupted = 0; @@ -2484,7 +2484,7 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data) * Note that in the non-execute case, we want to turn off permission * checking if we just created a new file (POSIX open() semantics). */ -static int nfs4_opendata_access(struct rpc_cred *cred, +static int nfs4_opendata_access(const struct cred *cred, struct nfs4_opendata *opendata, struct nfs4_state *state, fmode_t fmode, int openflags) @@ -2651,7 +2651,7 @@ static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st static int nfs40_test_and_free_expired_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { return -NFS4ERR_BAD_STATEID; } @@ -2659,7 +2659,7 @@ static int nfs40_test_and_free_expired_stateid(struct nfs_server *server, #if defined(CONFIG_NFS_V4_1) static int nfs41_test_and_free_expired_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { int status; @@ -2693,7 +2693,7 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) struct nfs_server *server = NFS_SERVER(state->inode); nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred; + const struct cred *cred = NULL; int status; /* Get the delegation credential for use by test/free_stateid */ @@ -2718,14 +2718,16 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) return; } - cred = get_rpccred(delegation->cred); + if (delegation->cred) + cred = get_cred(delegation->cred); rcu_read_unlock(); status = nfs41_test_and_free_expired_stateid(server, &stateid, cred); trace_nfs4_test_delegation_stateid(state, NULL, status); if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) nfs_finish_clear_delegation_stateid(state, &stateid); - put_rpccred(cred); + if (delegation->cred) + put_cred(cred); } /** @@ -2748,7 +2750,7 @@ static int nfs41_check_expired_locks(struct nfs4_state *state) spin_lock(&state->state_lock); list_for_each_entry(lsp, &state->lock_states, ls_locks) { if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) { - struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + const struct cred *cred = lsp->ls_state->owner->so_cred; refcount_inc(&lsp->ls_count); spin_unlock(&state->state_lock); @@ -2792,7 +2794,7 @@ static int nfs41_check_open_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); nfs4_stateid *stateid = &state->open_stateid; - struct rpc_cred *cred = state->owner->so_cred; + const struct cred *cred = state->owner->so_cred; int status; if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) { @@ -2950,7 +2952,7 @@ static int _nfs4_do_open(struct inode *dir, struct nfs_server *server = NFS_SERVER(dir); struct nfs4_opendata *opendata; struct dentry *dentry = ctx->dentry; - struct rpc_cred *cred = ctx->cred; + const struct cred *cred = ctx->cred; struct nfs4_threshold **ctx_th = &ctx->mdsthreshold; fmode_t fmode = ctx->mode & (FMODE_READ|FMODE_WRITE|FMODE_EXEC); enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; @@ -3120,7 +3122,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, static int _nfs4_do_setattr(struct inode *inode, struct nfs_setattrargs *arg, struct nfs_setattrres *res, - struct rpc_cred *cred, + const struct cred *cred, struct nfs_open_context *ctx) { struct nfs_server *server = NFS_SERVER(inode); @@ -3130,7 +3132,7 @@ static int _nfs4_do_setattr(struct inode *inode, .rpc_resp = res, .rpc_cred = cred, }; - struct rpc_cred *delegation_cred = NULL; + const struct cred *delegation_cred = NULL; unsigned long timestamp = jiffies; bool truncate; int status; @@ -3165,14 +3167,14 @@ zero_stateid: status = nfs4_call_sync(server->client, server, &msg, &arg->seq_args, &res->seq_res, 1); - put_rpccred(delegation_cred); + put_cred(delegation_cred); if (status == 0 && ctx != NULL) renew_lease(server, timestamp); trace_nfs4_setattr(inode, &arg->stateid, status); return status; } -static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred, +static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, struct nfs_open_context *ctx, struct nfs4_label *ilabel, struct nfs4_label *olabel) @@ -3973,7 +3975,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, struct iattr *sattr) { struct inode *inode = d_inode(dentry); - struct rpc_cred *cred = NULL; + const struct cred *cred = NULL; struct nfs_open_context *ctx = NULL; struct nfs4_label *label = NULL; int status; @@ -4202,7 +4204,6 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry return -ENOMEM; args.bitmask = server->cache_consistency_bitmask; } - status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 0); if (!status) { nfs_access_set_mask(entry, res.access); @@ -4691,7 +4692,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, return err; } -static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, +static int _nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); @@ -4729,7 +4730,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, return status; } -static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, +static int nfs4_proc_readdir(struct dentry *dentry, const struct cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { struct nfs4_exception exception = { }; @@ -5257,7 +5258,7 @@ static const struct rpc_call_ops nfs4_renew_ops = { .rpc_release = nfs4_renew_release, }; -static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) +static int nfs4_proc_async_renew(struct nfs_client *clp, const struct cred *cred, unsigned renew_flags) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], @@ -5281,7 +5282,7 @@ static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred, &nfs4_renew_ops, data); } -static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred) +static int nfs4_proc_renew(struct nfs_client *clp, const struct cred *cred) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENEW], @@ -5696,7 +5697,6 @@ nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) { struct nfs4_label ilabel, *olabel = NULL; struct nfs_fattr fattr; - struct rpc_cred *cred; int status; if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) @@ -5709,10 +5709,6 @@ nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) ilabel.label = (char *)buf; ilabel.len = buflen; - cred = rpc_lookup_cred(); - if (IS_ERR(cred)) - return PTR_ERR(cred); - olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); if (IS_ERR(olabel)) { status = -PTR_ERR(olabel); @@ -5725,7 +5721,6 @@ nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) nfs4_label_free(olabel); out: - put_rpccred(cred); return status; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ @@ -5894,13 +5889,13 @@ static const struct rpc_call_ops nfs4_setclientid_ops = { * @clp: state data structure * @program: RPC program for NFSv4 callback service * @port: IP port number for NFS4 callback service - * @cred: RPC credential to use for this call + * @cred: credential to use for this call * @res: where to place the result * * Returns zero, a negative errno, or a negative NFS4ERR status code. */ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, - unsigned short port, struct rpc_cred *cred, + unsigned short port, const struct cred *cred, struct nfs4_setclientid_res *res) { nfs4_verifier sc_verifier; @@ -5969,13 +5964,13 @@ out: * nfs4_proc_setclientid_confirm - Confirm client ID * @clp: state data structure * @res: result of a previous SETCLIENTID - * @cred: RPC credential to use for this call + * @cred: credential to use for this call * * Returns zero, a negative errno, or a negative NFS4ERR status code. */ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct nfs4_setclientid_res *arg, - struct rpc_cred *cred) + const struct cred *cred) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM], @@ -6138,7 +6133,7 @@ static const struct rpc_call_ops nfs4_delegreturn_ops = { .rpc_release = nfs4_delegreturn_release, }; -static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync) +static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync) { struct nfs4_delegreturndata *data; struct nfs_server *server = NFS_SERVER(inode); @@ -6205,7 +6200,7 @@ out: return status; } -int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync) +int nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, const nfs4_stateid *stateid, int issync) { struct nfs_server *server = NFS_SERVER(inode); struct nfs4_exception exception = { }; @@ -7268,7 +7263,7 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, */ static int _nfs40_proc_get_locations(struct inode *inode, struct nfs4_fs_locations *locations, - struct page *page, struct rpc_cred *cred) + struct page *page, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; @@ -7325,7 +7320,7 @@ static int _nfs40_proc_get_locations(struct inode *inode, */ static int _nfs41_proc_get_locations(struct inode *inode, struct nfs4_fs_locations *locations, - struct page *page, struct rpc_cred *cred) + struct page *page, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; @@ -7384,7 +7379,7 @@ static int _nfs41_proc_get_locations(struct inode *inode, */ int nfs4_proc_get_locations(struct inode *inode, struct nfs4_fs_locations *locations, - struct page *page, struct rpc_cred *cred) + struct page *page, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; @@ -7415,7 +7410,7 @@ int nfs4_proc_get_locations(struct inode *inode, * is appended to this compound to identify the client ID which is * performing recovery. */ -static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +static int _nfs40_proc_fsid_present(struct inode *inode, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; @@ -7461,7 +7456,7 @@ static int _nfs40_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) * this operation is identified in the SEQUENCE operation in this * compound. */ -static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +static int _nfs41_proc_fsid_present(struct inode *inode, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; @@ -7508,7 +7503,7 @@ static int _nfs41_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) * NFS4ERR code if some error occurred on the server, or a * negative errno if a local failure occurred. */ -int nfs4_proc_fsid_present(struct inode *inode, struct rpc_cred *cred) +int nfs4_proc_fsid_present(struct inode *inode, const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; @@ -7555,7 +7550,7 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct .rpc_resp = &res, }; struct rpc_clnt *clnt = NFS_SERVER(dir)->client; - struct rpc_cred *cred = NULL; + const struct cred *cred = NULL; if (use_integrity) { clnt = NFS_SERVER(dir)->nfs_client->cl_rpcclient; @@ -7572,8 +7567,7 @@ static int _nfs4_proc_secinfo(struct inode *dir, const struct qstr *name, struct &res.seq_res, 0); dprintk("NFS reply secinfo: %d\n", status); - if (cred) - put_rpccred(cred); + put_cred(cred); return status; } @@ -7654,7 +7648,7 @@ static int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct nfs_client *clp, - struct rpc_cred *cred) + const struct cred *cred) { int status; struct nfs41_bind_conn_to_session_args args = { @@ -7716,7 +7710,7 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt, struct rpc_bind_conn_calldata { struct nfs_client *clp; - struct rpc_cred *cred; + const struct cred *cred; }; static int @@ -7729,7 +7723,7 @@ nfs4_proc_bind_conn_to_session_callback(struct rpc_clnt *clnt, return nfs4_proc_bind_one_conn_to_session(clnt, xprt, p->clp, p->cred); } -int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred) +int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, const struct cred *cred) { struct rpc_bind_conn_calldata data = { .clp = clp, @@ -7895,7 +7889,7 @@ static const struct rpc_call_ops nfs4_exchange_id_call_ops = { * Wrapper for EXCHANGE_ID operation. */ static struct rpc_task * -nfs4_run_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, +nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred, u32 sp4_how, struct rpc_xprt *xprt) { struct rpc_message msg = { @@ -7991,7 +7985,7 @@ out: * * Wrapper for EXCHANGE_ID operation. */ -static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, +static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred, u32 sp4_how) { struct rpc_task *task; @@ -8058,7 +8052,7 @@ out: * * Will attempt to negotiate SP4_MACH_CRED if krb5i / krb5p auth is used. */ -int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) +int nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cred) { rpc_authflavor_t authflavor = clp->cl_rpcclient->cl_auth->au_flavor; int status; @@ -8090,7 +8084,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) * @xprt: the rpc_xprt to test * @data: call data for _nfs4_proc_exchange_id. */ -int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, +void nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data; @@ -8107,20 +8101,22 @@ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt, /* Test connection for session trunking. Async exchange_id call */ task = nfs4_run_exchange_id(adata->clp, adata->cred, sp4_how, xprt); if (IS_ERR(task)) - return PTR_ERR(task); + return; status = task->tk_status; if (status == 0) status = nfs4_detect_session_trunking(adata->clp, task->tk_msg.rpc_resp, xprt); + if (status == 0) + rpc_clnt_xprt_switch_add_xprt(clnt, xprt); + rpc_put_task(task); - return status; } EXPORT_SYMBOL_GPL(nfs4_test_session_trunk); static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, - struct rpc_cred *cred) + const struct cred *cred) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID], @@ -8138,7 +8134,7 @@ static int _nfs4_proc_destroy_clientid(struct nfs_client *clp, } static int nfs4_proc_destroy_clientid(struct nfs_client *clp, - struct rpc_cred *cred) + const struct cred *cred) { unsigned int loop; int ret; @@ -8159,7 +8155,7 @@ static int nfs4_proc_destroy_clientid(struct nfs_client *clp, int nfs4_destroy_clientid(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; int ret = 0; if (clp->cl_mvops->minor_version < 1) @@ -8170,8 +8166,7 @@ int nfs4_destroy_clientid(struct nfs_client *clp) goto out; cred = nfs4_get_clid_cred(clp); ret = nfs4_proc_destroy_clientid(clp, cred); - if (cred) - put_rpccred(cred); + put_cred(cred); switch (ret) { case 0: case -NFS4ERR_STALE_CLIENTID: @@ -8387,7 +8382,7 @@ static void nfs4_update_session(struct nfs4_session *session, } static int _nfs4_proc_create_session(struct nfs_client *clp, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_session *session = clp->cl_session; struct nfs41_create_session_args args = { @@ -8439,7 +8434,7 @@ out: * It is the responsibility of the caller to verify the session is * expired before calling this routine. */ -int nfs4_proc_create_session(struct nfs_client *clp, struct rpc_cred *cred) +int nfs4_proc_create_session(struct nfs_client *clp, const struct cred *cred) { int status; unsigned *ptr; @@ -8470,7 +8465,7 @@ out: * The caller must serialize access to this routine. */ int nfs4_proc_destroy_session(struct nfs4_session *session, - struct rpc_cred *cred) + const struct cred *cred) { struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION], @@ -8572,7 +8567,7 @@ static const struct rpc_call_ops nfs41_sequence_ops = { }; static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, - struct rpc_cred *cred, + const struct cred *cred, struct nfs4_slot *slot, bool is_privileged) { @@ -8615,7 +8610,7 @@ out_err: return ret; } -static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cred, unsigned renew_flags) +static int nfs41_proc_async_sequence(struct nfs_client *clp, const struct cred *cred, unsigned renew_flags) { struct rpc_task *task; int ret = 0; @@ -8631,7 +8626,7 @@ static int nfs41_proc_async_sequence(struct nfs_client *clp, struct rpc_cred *cr return ret; } -static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred) +static int nfs4_proc_sequence(struct nfs_client *clp, const struct cred *cred) { struct rpc_task *task; int ret; @@ -8727,7 +8722,7 @@ static const struct rpc_call_ops nfs4_reclaim_complete_call_ops = { * Issue a global reclaim complete. */ static int nfs41_proc_reclaim_complete(struct nfs_client *clp, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_reclaim_complete_data *calldata; struct rpc_task *task; @@ -9080,7 +9075,7 @@ int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync) static int _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_getdeviceinfo_args args = { .pdev = pdev, @@ -9112,7 +9107,7 @@ _nfs4_proc_getdeviceinfo(struct nfs_server *server, int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_exception exception = { }; int err; @@ -9169,7 +9164,7 @@ static void nfs4_layoutcommit_release(void *calldata) pnfs_cleanup_layoutcommit(data); nfs_post_op_update_inode_force_wcc(data->args.inode, data->res.fattr); - put_rpccred(data->cred); + put_cred(data->cred); nfs_iput_and_deactive(data->inode); kfree(data); } @@ -9245,7 +9240,7 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_resp = &res, }; struct rpc_clnt *clnt = server->client; - struct rpc_cred *cred = NULL; + const struct cred *cred = NULL; int status; if (use_integrity) { @@ -9259,8 +9254,7 @@ _nfs41_proc_secinfo_no_name(struct nfs_server *server, struct nfs_fh *fhandle, &res.seq_res, 0); dprintk("<-- %s status=%d\n", __func__, status); - if (cred) - put_rpccred(cred); + put_cred(cred); return status; } @@ -9373,7 +9367,7 @@ out: static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { int status; struct nfs41_test_stateid_args args = { @@ -9434,7 +9428,7 @@ static void nfs4_handle_delay_or_session_error(struct nfs_server *server, */ static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_exception exception = { }; int err; @@ -9496,7 +9490,7 @@ static const struct rpc_call_ops nfs41_free_stateid_ops = { */ static int nfs41_free_stateid(struct nfs_server *server, const nfs4_stateid *stateid, - struct rpc_cred *cred, + const struct cred *cred, bool privileged) { struct rpc_message msg = { @@ -9537,7 +9531,7 @@ static int nfs41_free_stateid(struct nfs_server *server, static void nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp) { - struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + const struct cred *cred = lsp->ls_state->owner->so_cred; nfs41_free_stateid(server, &lsp->ls_stateid, cred, false); nfs4_free_lock_state(server, lsp); @@ -9608,14 +9602,14 @@ static const struct nfs4_state_recovery_ops nfs41_nograce_recovery_ops = { static const struct nfs4_state_maintenance_ops nfs40_state_renewal_ops = { .sched_state_renewal = nfs4_proc_async_renew, - .get_state_renewal_cred_locked = nfs4_get_renew_cred_locked, + .get_state_renewal_cred = nfs4_get_renew_cred, .renew_lease = nfs4_proc_renew, }; #if defined(CONFIG_NFS_V4_1) static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = { .sched_state_renewal = nfs41_proc_async_sequence, - .get_state_renewal_cred_locked = nfs4_get_machine_cred_locked, + .get_state_renewal_cred = nfs4_get_machine_cred, .renew_lease = nfs4_proc_sequence, }; #endif diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index 1f8c2ae43a8d..6ea431b067dd 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -57,7 +57,7 @@ nfs4_renew_state(struct work_struct *work) const struct nfs4_state_maintenance_ops *ops; struct nfs_client *clp = container_of(work, struct nfs_client, cl_renewd.work); - struct rpc_cred *cred; + const struct cred *cred; long lease; unsigned long last, now; unsigned renew_flags = 0; @@ -68,7 +68,6 @@ nfs4_renew_state(struct work_struct *work) if (test_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state)) goto out; - spin_lock(&clp->cl_lock); lease = clp->cl_lease_time; last = clp->cl_last_renewal; now = jiffies; @@ -79,8 +78,7 @@ nfs4_renew_state(struct work_struct *work) renew_flags |= NFS4_RENEW_DELEGATION_CB; if (renew_flags != 0) { - cred = ops->get_state_renewal_cred_locked(clp); - spin_unlock(&clp->cl_lock); + cred = ops->get_state_renewal_cred(clp); if (cred == NULL) { if (!(renew_flags & NFS4_RENEW_DELEGATION_CB)) { set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); @@ -92,7 +90,7 @@ nfs4_renew_state(struct work_struct *work) /* Queue an asynchronous RENEW. */ ret = ops->sched_state_renewal(clp, cred, renew_flags); - put_rpccred(cred); + put_cred(cred); switch (ret) { default: goto out_exp; @@ -104,7 +102,6 @@ nfs4_renew_state(struct work_struct *work) } else { dprintk("%s: failed to call renewd. Reason: lease not expired \n", __func__); - spin_unlock(&clp->cl_lock); } nfs4_schedule_state_renewal(clp); out_exp: diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index 769b85655c4b..a5489d70a724 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -573,12 +573,11 @@ static void nfs4_destroy_session_slot_tables(struct nfs4_session *session) void nfs4_destroy_session(struct nfs4_session *session) { struct rpc_xprt *xprt; - struct rpc_cred *cred; + const struct cred *cred; cred = nfs4_get_clid_cred(session->clp); nfs4_proc_destroy_session(session, cred); - if (cred) - put_rpccred(cred); + put_cred(cred); rcu_read_lock(); xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index d8decf2ec48f..02488b50534a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -87,7 +87,7 @@ const nfs4_stateid current_stateid = { static DEFINE_MUTEX(nfs_clid_init_mutex); -int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) +int nfs4_init_clientid(struct nfs_client *clp, const struct cred *cred) { struct nfs4_setclientid_res clid = { .clientid = clp->cl_clientid, @@ -134,7 +134,7 @@ out: */ int nfs40_discover_server_trunking(struct nfs_client *clp, struct nfs_client **result, - struct rpc_cred *cred) + const struct cred *cred) { struct nfs4_setclientid_res clid = { .clientid = clp->cl_clientid, @@ -164,32 +164,23 @@ out: return status; } -struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp) +const struct cred *nfs4_get_machine_cred(struct nfs_client *clp) { - struct rpc_cred *cred = NULL; - - if (clp->cl_machine_cred != NULL) - cred = get_rpccred(clp->cl_machine_cred); - return cred; + return get_cred(rpc_machine_cred()); } static void nfs4_root_machine_cred(struct nfs_client *clp) { - struct rpc_cred *cred, *new; - new = rpc_lookup_machine_cred(NULL); - spin_lock(&clp->cl_lock); - cred = clp->cl_machine_cred; - clp->cl_machine_cred = new; - spin_unlock(&clp->cl_lock); - if (cred != NULL) - put_rpccred(cred); + /* Force root creds instead of machine */ + clp->cl_principal = NULL; + clp->cl_rpcclient->cl_principal = NULL; } -static struct rpc_cred * +static const struct cred * nfs4_get_renew_cred_server_locked(struct nfs_server *server) { - struct rpc_cred *cred = NULL; + const struct cred *cred = NULL; struct nfs4_state_owner *sp; struct rb_node *pos; @@ -199,29 +190,30 @@ nfs4_get_renew_cred_server_locked(struct nfs_server *server) sp = rb_entry(pos, struct nfs4_state_owner, so_server_node); if (list_empty(&sp->so_states)) continue; - cred = get_rpccred(sp->so_cred); + cred = get_cred(sp->so_cred); break; } return cred; } /** - * nfs4_get_renew_cred_locked - Acquire credential for a renew operation + * nfs4_get_renew_cred - Acquire credential for a renew operation * @clp: client state handle * * Returns an rpc_cred with reference count bumped, or NULL. * Caller must hold clp->cl_lock. */ -struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp) +const struct cred *nfs4_get_renew_cred(struct nfs_client *clp) { - struct rpc_cred *cred = NULL; + const struct cred *cred = NULL; struct nfs_server *server; /* Use machine credentials if available */ - cred = nfs4_get_machine_cred_locked(clp); + cred = nfs4_get_machine_cred(clp); if (cred != NULL) goto out; + spin_lock(&clp->cl_lock); rcu_read_lock(); list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { cred = nfs4_get_renew_cred_server_locked(server); @@ -229,6 +221,7 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp) break; } rcu_read_unlock(); + spin_unlock(&clp->cl_lock); out: return cred; @@ -319,7 +312,7 @@ static void nfs41_finish_session_reset(struct nfs_client *clp) nfs41_setup_state_renewal(clp); } -int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred) +int nfs41_init_clientid(struct nfs_client *clp, const struct cred *cred) { int status; @@ -354,7 +347,7 @@ out: */ int nfs41_discover_server_trunking(struct nfs_client *clp, struct nfs_client **result, - struct rpc_cred *cred) + const struct cred *cred) { int status; @@ -392,32 +385,32 @@ int nfs41_discover_server_trunking(struct nfs_client *clp, * nfs4_get_clid_cred - Acquire credential for a setclientid operation * @clp: client state handle * - * Returns an rpc_cred with reference count bumped, or NULL. + * Returns a cred with reference count bumped, or NULL. */ -struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp) +const struct cred *nfs4_get_clid_cred(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; - spin_lock(&clp->cl_lock); - cred = nfs4_get_machine_cred_locked(clp); - spin_unlock(&clp->cl_lock); + cred = nfs4_get_machine_cred(clp); return cred; } static struct nfs4_state_owner * -nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred) +nfs4_find_state_owner_locked(struct nfs_server *server, const struct cred *cred) { struct rb_node **p = &server->state_owners.rb_node, *parent = NULL; struct nfs4_state_owner *sp; + int cmp; while (*p != NULL) { parent = *p; sp = rb_entry(parent, struct nfs4_state_owner, so_server_node); + cmp = cred_fscmp(cred, sp->so_cred); - if (cred < sp->so_cred) + if (cmp < 0) p = &parent->rb_left; - else if (cred > sp->so_cred) + else if (cmp > 0) p = &parent->rb_right; else { if (!list_empty(&sp->so_lru)) @@ -436,14 +429,16 @@ nfs4_insert_state_owner_locked(struct nfs4_state_owner *new) struct rb_node **p = &server->state_owners.rb_node, *parent = NULL; struct nfs4_state_owner *sp; + int cmp; while (*p != NULL) { parent = *p; sp = rb_entry(parent, struct nfs4_state_owner, so_server_node); + cmp = cred_fscmp(new->so_cred, sp->so_cred); - if (new->so_cred < sp->so_cred) + if (cmp < 0) p = &parent->rb_left; - else if (new->so_cred > sp->so_cred) + else if (cmp > 0) p = &parent->rb_right; else { if (!list_empty(&sp->so_lru)) @@ -490,7 +485,7 @@ nfs4_destroy_seqid_counter(struct nfs_seqid_counter *sc) */ static struct nfs4_state_owner * nfs4_alloc_state_owner(struct nfs_server *server, - struct rpc_cred *cred, + const struct cred *cred, gfp_t gfp_flags) { struct nfs4_state_owner *sp; @@ -505,7 +500,7 @@ nfs4_alloc_state_owner(struct nfs_server *server, return NULL; } sp->so_server = server; - sp->so_cred = get_rpccred(cred); + sp->so_cred = get_cred(cred); spin_lock_init(&sp->so_lock); INIT_LIST_HEAD(&sp->so_states); nfs4_init_seqid_counter(&sp->so_seqid); @@ -534,7 +529,7 @@ nfs4_reset_state_owner(struct nfs4_state_owner *sp) static void nfs4_free_state_owner(struct nfs4_state_owner *sp) { nfs4_destroy_seqid_counter(&sp->so_seqid); - put_rpccred(sp->so_cred); + put_cred(sp->so_cred); ida_simple_remove(&sp->so_server->openowner_id, sp->so_seqid.owner_id); kfree(sp); } @@ -572,7 +567,7 @@ static void nfs4_gc_state_owners(struct nfs_server *server) * Returns a pointer to an instantiated nfs4_state_owner struct, or NULL. */ struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server, - struct rpc_cred *cred, + const struct cred *cred, gfp_t gfp_flags) { struct nfs_client *clp = server->nfs_client; @@ -1041,7 +1036,7 @@ bool nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state) */ int nfs4_select_rw_stateid(struct nfs4_state *state, fmode_t fmode, const struct nfs_lock_context *l_ctx, - nfs4_stateid *dst, struct rpc_cred **cred) + nfs4_stateid *dst, const struct cred **cred) { int ret; @@ -1560,7 +1555,7 @@ static void nfs42_complete_copies(struct nfs4_state_owner *sp, struct nfs4_state spin_lock(&sp->so_server->nfs_client->cl_lock); list_for_each_entry(copy, &sp->so_server->ss_copies, copies) { - if (nfs4_stateid_match_other(&state->stateid, ©->parent_state->stateid)) + if (!nfs4_stateid_match_other(&state->stateid, ©->parent_state->stateid)) continue; copy->flags = 1; complete(©->completion); @@ -1741,7 +1736,7 @@ static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) static int nfs4_reclaim_complete(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops, - struct rpc_cred *cred) + const struct cred *cred) { /* Notify the server we're done reclaiming our state */ if (ops->reclaim_complete) @@ -1792,7 +1787,7 @@ static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp) static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) { const struct nfs4_state_recovery_ops *ops; - struct rpc_cred *cred; + const struct cred *cred; int err; if (!nfs4_state_clear_reclaim_reboot(clp)) @@ -1800,7 +1795,7 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) ops = clp->cl_mvops->reboot_recovery_ops; cred = nfs4_get_clid_cred(clp); err = nfs4_reclaim_complete(clp, ops, cred); - put_rpccred(cred); + put_cred(cred); if (err == -NFS4ERR_CONN_NOT_BOUND_TO_SESSION) set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); } @@ -1896,7 +1891,7 @@ restart: static int nfs4_check_lease(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; const struct nfs4_state_maintenance_ops *ops = clp->cl_mvops->state_renewal_ops; int status; @@ -1904,9 +1899,7 @@ static int nfs4_check_lease(struct nfs_client *clp) /* Is the client already known to have an expired lease? */ if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) return 0; - spin_lock(&clp->cl_lock); - cred = ops->get_state_renewal_cred_locked(clp); - spin_unlock(&clp->cl_lock); + cred = ops->get_state_renewal_cred(clp); if (cred == NULL) { cred = nfs4_get_clid_cred(clp); status = -ENOKEY; @@ -1914,7 +1907,7 @@ static int nfs4_check_lease(struct nfs_client *clp) goto out; } status = ops->renew_lease(clp, cred); - put_rpccred(cred); + put_cred(cred); if (status == -ETIMEDOUT) { set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); return 0; @@ -1974,7 +1967,7 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) static int nfs4_establish_lease(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; const struct nfs4_state_recovery_ops *ops = clp->cl_mvops->reboot_recovery_ops; int status; @@ -1986,7 +1979,7 @@ static int nfs4_establish_lease(struct nfs_client *clp) if (cred == NULL) return -ENOENT; status = ops->establish_clid(clp, cred); - put_rpccred(cred); + put_cred(cred); if (status != 0) return status; pnfs_destroy_all_layouts(clp); @@ -2033,7 +2026,7 @@ static int nfs4_purge_lease(struct nfs_client *clp) * * Returns zero or a negative NFS4ERR status code. */ -static int nfs4_try_migration(struct nfs_server *server, struct rpc_cred *cred) +static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred) { struct nfs_client *clp = server->nfs_client; struct nfs4_fs_locations *locations = NULL; @@ -2103,14 +2096,12 @@ static int nfs4_handle_migration(struct nfs_client *clp) const struct nfs4_state_maintenance_ops *ops = clp->cl_mvops->state_renewal_ops; struct nfs_server *server; - struct rpc_cred *cred; + const struct cred *cred; dprintk("%s: migration reported on \"%s\"\n", __func__, clp->cl_hostname); - spin_lock(&clp->cl_lock); - cred = ops->get_state_renewal_cred_locked(clp); - spin_unlock(&clp->cl_lock); + cred = ops->get_state_renewal_cred(clp); if (cred == NULL) return -NFS4ERR_NOENT; @@ -2131,13 +2122,13 @@ restart: rcu_read_unlock(); status = nfs4_try_migration(server, cred); if (status < 0) { - put_rpccred(cred); + put_cred(cred); return status; } goto restart; } rcu_read_unlock(); - put_rpccred(cred); + put_cred(cred); return 0; } @@ -2151,14 +2142,12 @@ static int nfs4_handle_lease_moved(struct nfs_client *clp) const struct nfs4_state_maintenance_ops *ops = clp->cl_mvops->state_renewal_ops; struct nfs_server *server; - struct rpc_cred *cred; + const struct cred *cred; dprintk("%s: lease moved reported on \"%s\"\n", __func__, clp->cl_hostname); - spin_lock(&clp->cl_lock); - cred = ops->get_state_renewal_cred_locked(clp); - spin_unlock(&clp->cl_lock); + cred = ops->get_state_renewal_cred(clp); if (cred == NULL) return -NFS4ERR_NOENT; @@ -2186,7 +2175,7 @@ restart: rcu_read_unlock(); out: - put_rpccred(cred); + put_cred(cred); return 0; } @@ -2209,7 +2198,7 @@ int nfs4_discover_server_trunking(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops = clp->cl_mvops->reboot_recovery_ops; struct rpc_clnt *clnt; - struct rpc_cred *cred; + const struct cred *cred; int i, status; dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname); @@ -2225,7 +2214,7 @@ again: goto out_unlock; status = ops->detect_trunking(clp, result, cred); - put_rpccred(cred); + put_cred(cred); switch (status) { case 0: case -EINTR: @@ -2416,7 +2405,7 @@ out_recovery: static int nfs4_reset_session(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; int status; if (!nfs4_has_session(clp)) @@ -2454,14 +2443,13 @@ static int nfs4_reset_session(struct nfs_client *clp) dprintk("%s: session reset was successful for server %s!\n", __func__, clp->cl_hostname); out: - if (cred) - put_rpccred(cred); + put_cred(cred); return status; } static int nfs4_bind_conn_to_session(struct nfs_client *clp) { - struct rpc_cred *cred; + const struct cred *cred; int ret; if (!nfs4_has_session(clp)) @@ -2471,8 +2459,7 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) return ret; cred = nfs4_get_clid_cred(clp); ret = nfs4_proc_bind_conn_to_session(clp, cred); - if (cred) - put_rpccred(cred); + put_cred(cred); clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state); switch (ret) { case 0: diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index b1483b303e0b..b4557cf685fb 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -10,157 +10,302 @@ #include <linux/tracepoint.h> +TRACE_DEFINE_ENUM(EPERM); +TRACE_DEFINE_ENUM(ENOENT); +TRACE_DEFINE_ENUM(EIO); +TRACE_DEFINE_ENUM(ENXIO); +TRACE_DEFINE_ENUM(EACCES); +TRACE_DEFINE_ENUM(EEXIST); +TRACE_DEFINE_ENUM(EXDEV); +TRACE_DEFINE_ENUM(ENOTDIR); +TRACE_DEFINE_ENUM(EISDIR); +TRACE_DEFINE_ENUM(EFBIG); +TRACE_DEFINE_ENUM(ENOSPC); +TRACE_DEFINE_ENUM(EROFS); +TRACE_DEFINE_ENUM(EMLINK); +TRACE_DEFINE_ENUM(ENAMETOOLONG); +TRACE_DEFINE_ENUM(ENOTEMPTY); +TRACE_DEFINE_ENUM(EDQUOT); +TRACE_DEFINE_ENUM(ESTALE); +TRACE_DEFINE_ENUM(EBADHANDLE); +TRACE_DEFINE_ENUM(EBADCOOKIE); +TRACE_DEFINE_ENUM(ENOTSUPP); +TRACE_DEFINE_ENUM(ETOOSMALL); +TRACE_DEFINE_ENUM(EREMOTEIO); +TRACE_DEFINE_ENUM(EBADTYPE); +TRACE_DEFINE_ENUM(EAGAIN); +TRACE_DEFINE_ENUM(ELOOP); +TRACE_DEFINE_ENUM(EOPNOTSUPP); +TRACE_DEFINE_ENUM(EDEADLK); +TRACE_DEFINE_ENUM(ENOMEM); +TRACE_DEFINE_ENUM(EKEYEXPIRED); +TRACE_DEFINE_ENUM(ETIMEDOUT); +TRACE_DEFINE_ENUM(ERESTARTSYS); +TRACE_DEFINE_ENUM(ECONNREFUSED); +TRACE_DEFINE_ENUM(ECONNRESET); +TRACE_DEFINE_ENUM(ENETUNREACH); +TRACE_DEFINE_ENUM(EHOSTUNREACH); +TRACE_DEFINE_ENUM(EHOSTDOWN); +TRACE_DEFINE_ENUM(EPIPE); +TRACE_DEFINE_ENUM(EPFNOSUPPORT); +TRACE_DEFINE_ENUM(EPROTONOSUPPORT); + +TRACE_DEFINE_ENUM(NFS4_OK); +TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); +TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); +TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); +TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); +TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); +TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); +TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); +TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); +TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); +TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); +TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DELAY); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); +TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); +TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_EXIST); +TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FBIG); +TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); +TRACE_DEFINE_ENUM(NFS4ERR_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_INVAL); +TRACE_DEFINE_ENUM(NFS4ERR_IO); +TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); +TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); +TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); +TRACE_DEFINE_ENUM(NFS4ERR_MLINK); +TRACE_DEFINE_ENUM(NFS4ERR_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFS4ERR_NOENT); +TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); +TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); +TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_NXIO); +TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); +TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); +TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_PERM); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); +TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); +TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); +TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); +TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_ROFS); +TRACE_DEFINE_ENUM(NFS4ERR_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); +TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFS4ERR_STALE); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); +TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); +TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); +TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); +TRACE_DEFINE_ENUM(NFS4ERR_XDEV); + #define show_nfsv4_errors(error) \ - __print_symbolic(error, \ + __print_symbolic(-(error), \ { NFS4_OK, "OK" }, \ /* Mapped by nfs4_stat_to_errno() */ \ - { -EPERM, "EPERM" }, \ - { -ENOENT, "ENOENT" }, \ - { -EIO, "EIO" }, \ - { -ENXIO, "ENXIO" }, \ - { -EACCES, "EACCES" }, \ - { -EEXIST, "EEXIST" }, \ - { -EXDEV, "EXDEV" }, \ - { -ENOTDIR, "ENOTDIR" }, \ - { -EISDIR, "EISDIR" }, \ - { -EFBIG, "EFBIG" }, \ - { -ENOSPC, "ENOSPC" }, \ - { -EROFS, "EROFS" }, \ - { -EMLINK, "EMLINK" }, \ - { -ENAMETOOLONG, "ENAMETOOLONG" }, \ - { -ENOTEMPTY, "ENOTEMPTY" }, \ - { -EDQUOT, "EDQUOT" }, \ - { -ESTALE, "ESTALE" }, \ - { -EBADHANDLE, "EBADHANDLE" }, \ - { -EBADCOOKIE, "EBADCOOKIE" }, \ - { -ENOTSUPP, "ENOTSUPP" }, \ - { -ETOOSMALL, "ETOOSMALL" }, \ - { -EREMOTEIO, "EREMOTEIO" }, \ - { -EBADTYPE, "EBADTYPE" }, \ - { -EAGAIN, "EAGAIN" }, \ - { -ELOOP, "ELOOP" }, \ - { -EOPNOTSUPP, "EOPNOTSUPP" }, \ - { -EDEADLK, "EDEADLK" }, \ + { EPERM, "EPERM" }, \ + { ENOENT, "ENOENT" }, \ + { EIO, "EIO" }, \ + { ENXIO, "ENXIO" }, \ + { EACCES, "EACCES" }, \ + { EEXIST, "EEXIST" }, \ + { EXDEV, "EXDEV" }, \ + { ENOTDIR, "ENOTDIR" }, \ + { EISDIR, "EISDIR" }, \ + { EFBIG, "EFBIG" }, \ + { ENOSPC, "ENOSPC" }, \ + { EROFS, "EROFS" }, \ + { EMLINK, "EMLINK" }, \ + { ENAMETOOLONG, "ENAMETOOLONG" }, \ + { ENOTEMPTY, "ENOTEMPTY" }, \ + { EDQUOT, "EDQUOT" }, \ + { ESTALE, "ESTALE" }, \ + { EBADHANDLE, "EBADHANDLE" }, \ + { EBADCOOKIE, "EBADCOOKIE" }, \ + { ENOTSUPP, "ENOTSUPP" }, \ + { ETOOSMALL, "ETOOSMALL" }, \ + { EREMOTEIO, "EREMOTEIO" }, \ + { EBADTYPE, "EBADTYPE" }, \ + { EAGAIN, "EAGAIN" }, \ + { ELOOP, "ELOOP" }, \ + { EOPNOTSUPP, "EOPNOTSUPP" }, \ + { EDEADLK, "EDEADLK" }, \ /* RPC errors */ \ - { -ENOMEM, "ENOMEM" }, \ - { -EKEYEXPIRED, "EKEYEXPIRED" }, \ - { -ETIMEDOUT, "ETIMEDOUT" }, \ - { -ERESTARTSYS, "ERESTARTSYS" }, \ - { -ECONNREFUSED, "ECONNREFUSED" }, \ - { -ECONNRESET, "ECONNRESET" }, \ - { -ENETUNREACH, "ENETUNREACH" }, \ - { -EHOSTUNREACH, "EHOSTUNREACH" }, \ - { -EHOSTDOWN, "EHOSTDOWN" }, \ - { -EPIPE, "EPIPE" }, \ - { -EPFNOSUPPORT, "EPFNOSUPPORT" }, \ - { -EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + { ENOMEM, "ENOMEM" }, \ + { EKEYEXPIRED, "EKEYEXPIRED" }, \ + { ETIMEDOUT, "ETIMEDOUT" }, \ + { ERESTARTSYS, "ERESTARTSYS" }, \ + { ECONNREFUSED, "ECONNREFUSED" }, \ + { ECONNRESET, "ECONNRESET" }, \ + { ENETUNREACH, "ENETUNREACH" }, \ + { EHOSTUNREACH, "EHOSTUNREACH" }, \ + { EHOSTDOWN, "EHOSTDOWN" }, \ + { EPIPE, "EPIPE" }, \ + { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ /* NFSv4 native errors */ \ - { -NFS4ERR_ACCESS, "ACCESS" }, \ - { -NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ - { -NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ - { -NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ - { -NFS4ERR_BADCHAR, "BADCHAR" }, \ - { -NFS4ERR_BADHANDLE, "BADHANDLE" }, \ - { -NFS4ERR_BADIOMODE, "BADIOMODE" }, \ - { -NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ - { -NFS4ERR_BADLABEL, "BADLABEL" }, \ - { -NFS4ERR_BADNAME, "BADNAME" }, \ - { -NFS4ERR_BADOWNER, "BADOWNER" }, \ - { -NFS4ERR_BADSESSION, "BADSESSION" }, \ - { -NFS4ERR_BADSLOT, "BADSLOT" }, \ - { -NFS4ERR_BADTYPE, "BADTYPE" }, \ - { -NFS4ERR_BADXDR, "BADXDR" }, \ - { -NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ - { -NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ - { -NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ - { -NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ - { -NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ - { -NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ - { -NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { -NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ - { -NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ - { -NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ - { -NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ + { NFS4ERR_ACCESS, "ACCESS" }, \ + { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { NFS4ERR_BADCHAR, "BADCHAR" }, \ + { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { NFS4ERR_BADLABEL, "BADLABEL" }, \ + { NFS4ERR_BADNAME, "BADNAME" }, \ + { NFS4ERR_BADOWNER, "BADOWNER" }, \ + { NFS4ERR_BADSESSION, "BADSESSION" }, \ + { NFS4ERR_BADSLOT, "BADSLOT" }, \ + { NFS4ERR_BADTYPE, "BADTYPE" }, \ + { NFS4ERR_BADXDR, "BADXDR" }, \ + { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ "CONN_NOT_BOUND_TO_SESSION" }, \ - { -NFS4ERR_DEADLOCK, "DEADLOCK" }, \ - { -NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ - { -NFS4ERR_DELAY, "DELAY" }, \ - { -NFS4ERR_DELEG_ALREADY_WANTED, \ + { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { NFS4ERR_DELAY, "DELAY" }, \ + { NFS4ERR_DELEG_ALREADY_WANTED, \ "DELEG_ALREADY_WANTED" }, \ - { -NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ - { -NFS4ERR_DENIED, "DENIED" }, \ - { -NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ - { -NFS4ERR_DQUOT, "DQUOT" }, \ - { -NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ - { -NFS4ERR_EXIST, "EXIST" }, \ - { -NFS4ERR_EXPIRED, "EXPIRED" }, \ - { -NFS4ERR_FBIG, "FBIG" }, \ - { -NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ - { -NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ - { -NFS4ERR_GRACE, "GRACE" }, \ - { -NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ - { -NFS4ERR_INVAL, "INVAL" }, \ - { -NFS4ERR_IO, "IO" }, \ - { -NFS4ERR_ISDIR, "ISDIR" }, \ - { -NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ - { -NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ - { -NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ - { -NFS4ERR_LOCKED, "LOCKED" }, \ - { -NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ - { -NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ - { -NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ - { -NFS4ERR_MLINK, "MLINK" }, \ - { -NFS4ERR_MOVED, "MOVED" }, \ - { -NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { -NFS4ERR_NOENT, "NOENT" }, \ - { -NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ - { -NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ - { -NFS4ERR_NOSPC, "NOSPC" }, \ - { -NFS4ERR_NOTDIR, "NOTDIR" }, \ - { -NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ - { -NFS4ERR_NOTSUPP, "NOTSUPP" }, \ - { -NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ - { -NFS4ERR_NOT_SAME, "NOT_SAME" }, \ - { -NFS4ERR_NO_GRACE, "NO_GRACE" }, \ - { -NFS4ERR_NXIO, "NXIO" }, \ - { -NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ - { -NFS4ERR_OPENMODE, "OPENMODE" }, \ - { -NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ - { -NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ - { -NFS4ERR_PERM, "PERM" }, \ - { -NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ - { -NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ - { -NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ - { -NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ - { -NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ - { -NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ - { -NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ - { -NFS4ERR_REP_TOO_BIG_TO_CACHE, \ + { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { NFS4ERR_DENIED, "DENIED" }, \ + { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { NFS4ERR_DQUOT, "DQUOT" }, \ + { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { NFS4ERR_EXIST, "EXIST" }, \ + { NFS4ERR_EXPIRED, "EXPIRED" }, \ + { NFS4ERR_FBIG, "FBIG" }, \ + { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { NFS4ERR_GRACE, "GRACE" }, \ + { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { NFS4ERR_INVAL, "INVAL" }, \ + { NFS4ERR_IO, "IO" }, \ + { NFS4ERR_ISDIR, "ISDIR" }, \ + { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { NFS4ERR_LOCKED, "LOCKED" }, \ + { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { NFS4ERR_MLINK, "MLINK" }, \ + { NFS4ERR_MOVED, "MOVED" }, \ + { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFS4ERR_NOENT, "NOENT" }, \ + { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { NFS4ERR_NOSPC, "NOSPC" }, \ + { NFS4ERR_NOTDIR, "NOTDIR" }, \ + { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { NFS4ERR_NXIO, "NXIO" }, \ + { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { NFS4ERR_OPENMODE, "OPENMODE" }, \ + { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { NFS4ERR_PERM, "PERM" }, \ + { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { NFS4ERR_REP_TOO_BIG_TO_CACHE, \ "REP_TOO_BIG_TO_CACHE" }, \ - { -NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ - { -NFS4ERR_RESOURCE, "RESOURCE" }, \ - { -NFS4ERR_RESTOREFH, "RESTOREFH" }, \ - { -NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ - { -NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ - { -NFS4ERR_ROFS, "ROFS" }, \ - { -NFS4ERR_SAME, "SAME" }, \ - { -NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ - { -NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ - { -NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ - { -NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ - { -NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ - { -NFS4ERR_STALE, "STALE" }, \ - { -NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ - { -NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ - { -NFS4ERR_SYMLINK, "SYMLINK" }, \ - { -NFS4ERR_TOOSMALL, "TOOSMALL" }, \ - { -NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ - { -NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ - { -NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ - { -NFS4ERR_WRONGSEC, "WRONGSEC" }, \ - { -NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ - { -NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { -NFS4ERR_XDEV, "XDEV" }) + { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { NFS4ERR_RESOURCE, "RESOURCE" }, \ + { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { NFS4ERR_ROFS, "ROFS" }, \ + { NFS4ERR_SAME, "SAME" }, \ + { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { NFS4ERR_STALE, "STALE" }, \ + { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { NFS4ERR_SYMLINK, "SYMLINK" }, \ + { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { NFS4ERR_XDEV, "XDEV" }) #define show_open_flags(flags) \ __print_flags(flags, "|", \ @@ -558,6 +703,13 @@ TRACE_EVENT(nfs4_close, ) ); +TRACE_DEFINE_ENUM(F_GETLK); +TRACE_DEFINE_ENUM(F_SETLK); +TRACE_DEFINE_ENUM(F_SETLKW); +TRACE_DEFINE_ENUM(F_RDLCK); +TRACE_DEFINE_ENUM(F_WRLCK); +TRACE_DEFINE_ENUM(F_UNLCK); + #define show_lock_cmd(type) \ __print_symbolic((int)type, \ { F_GETLK, "GETLK" }, \ @@ -1451,6 +1603,10 @@ DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); #ifdef CONFIG_NFS_V4_1 DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); +TRACE_DEFINE_ENUM(IOMODE_READ); +TRACE_DEFINE_ENUM(IOMODE_RW); +TRACE_DEFINE_ENUM(IOMODE_ANY); + #define show_pnfs_iomode(iomode) \ __print_symbolic(iomode, \ { IOMODE_READ, "READ" }, \ @@ -1528,6 +1684,20 @@ DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutcommit); DEFINE_NFS4_INODE_STATEID_EVENT(nfs4_layoutreturn); DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_UNKNOWN); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NO_PNFS); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RD_ZEROLEN); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_MDSTHRESH); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_NOMEM); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_BULK_RECALL); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_IO_TEST_FAIL); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_FOUND_CACHED); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RETURN); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_BLOCKED); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_INVALID_OPEN); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_RETRY); +TRACE_DEFINE_ENUM(PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET); + #define show_pnfs_update_layout_reason(reason) \ __print_symbolic(reason, \ { PNFS_UPDATE_LAYOUT_UNKNOWN, "unknown" }, \ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 5c4568a0804b..e54d899c1848 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -461,7 +461,7 @@ EXPORT_SYMBOL_GPL(nfs_wait_on_request); * @prev: previous request in desc, or NULL * @req: this request * - * Returns zero if @req can be coalesced into @desc, otherwise it returns + * Returns zero if @req cannot be coalesced into @desc, otherwise it returns * the size of the request. */ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc, @@ -587,7 +587,7 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata) } int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, - struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, + const struct cred *cred, const struct nfs_rpc_ops *rpc_ops, const struct rpc_call_ops *call_ops, int how, int flags) { struct rpc_task *task; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 06cb90e9bc6e..53726da5c010 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -275,7 +275,7 @@ pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo) list_del_init(&lo->plh_layouts); spin_unlock(&clp->cl_lock); } - put_rpccred(lo->plh_lc_cred); + put_cred(lo->plh_lc_cred); return ld->free_layout_hdr(lo); } @@ -1038,7 +1038,7 @@ pnfs_alloc_init_layoutget_args(struct inode *ino, lgp->args.ctx = get_nfs_open_context(ctx); nfs4_stateid_copy(&lgp->args.stateid, stateid); lgp->gfp_flags = gfp_flags; - lgp->cred = get_rpccred(ctx->cred); + lgp->cred = get_cred(ctx->cred); return lgp; } @@ -1049,7 +1049,7 @@ void pnfs_layoutget_free(struct nfs4_layoutget *lgp) nfs4_free_pages(lgp->args.layout.pages, max_pages); if (lgp->args.inode) pnfs_put_layout_hdr(NFS_I(lgp->args.inode)->layout); - put_rpccred(lgp->cred); + put_cred(lgp->cred); put_nfs_open_context(lgp->args.ctx); kfree(lgp); } @@ -1324,7 +1324,7 @@ pnfs_commit_and_return_layout(struct inode *inode) bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, - const struct rpc_cred *cred) + const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1583,7 +1583,7 @@ alloc_init_layout_hdr(struct inode *ino, INIT_LIST_HEAD(&lo->plh_return_segs); INIT_LIST_HEAD(&lo->plh_bulk_destroy); lo->plh_inode = ino; - lo->plh_lc_cred = get_rpccred(ctx->cred); + lo->plh_lc_cred = get_cred(ctx->cred); lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID; return lo; } @@ -2928,7 +2928,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) spin_unlock(&inode->i_lock); data->args.inode = inode; - data->cred = get_rpccred(nfsi->layout->plh_lc_cred); + data->cred = get_cred(nfsi->layout->plh_lc_cred); nfs_fattr_init(&data->fattr); data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask; data->res.fattr = &data->fattr; @@ -2941,7 +2941,7 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) if (ld->prepare_layoutcommit) { status = ld->prepare_layoutcommit(&data->args); if (status) { - put_rpccred(data->cred); + put_cred(data->cred); spin_lock(&inode->i_lock); set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags); if (end_pos > nfsi->layout->plh_lwb) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index e2e9fcd5341d..5e80a07b7bea 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -200,7 +200,7 @@ struct pnfs_layout_hdr { u32 plh_return_seq; enum pnfs_iomode plh_return_iomode; loff_t plh_lwb; /* last write byte for layoutcommit */ - struct rpc_cred *plh_lc_cred; /* layoutcommit cred */ + const struct cred *plh_lc_cred; /* layoutcommit cred */ struct inode *plh_inode; }; @@ -230,7 +230,7 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); extern size_t max_response_pages(struct nfs_server *server); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev, - struct rpc_cred *cred); + const struct cred *cred); extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync); @@ -280,7 +280,7 @@ int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, - const struct rpc_cred *cred); + const struct cred *cred); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, int ret); @@ -343,7 +343,7 @@ struct nfs4_deviceid_node { struct nfs4_deviceid_node * nfs4_find_get_deviceid(struct nfs_server *server, - const struct nfs4_deviceid *id, struct rpc_cred *cred, + const struct nfs4_deviceid *id, const struct cred *cred, gfp_t gfp_mask); void nfs4_delete_deviceid(const struct pnfs_layoutdriver_type *, const struct nfs_client *, const struct nfs4_deviceid *); void nfs4_init_deviceid_node(struct nfs4_deviceid_node *, struct nfs_server *, @@ -694,7 +694,7 @@ static inline bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, struct nfs4_layoutreturn_res *res, - const struct rpc_cred *cred) + const struct cred *cred) { return false; } diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c index e8a07b3f9aaa..7fb59487ee90 100644 --- a/fs/nfs/pnfs_dev.c +++ b/fs/nfs/pnfs_dev.c @@ -94,7 +94,7 @@ _lookup_deviceid(const struct pnfs_layoutdriver_type *ld, static struct nfs4_deviceid_node * nfs4_get_device_info(struct nfs_server *server, const struct nfs4_deviceid *dev_id, - struct rpc_cred *cred, gfp_t gfp_flags) + const struct cred *cred, gfp_t gfp_flags) { struct nfs4_deviceid_node *d = NULL; struct pnfs_device *pdev = NULL; @@ -184,7 +184,7 @@ __nfs4_find_get_deviceid(struct nfs_server *server, struct nfs4_deviceid_node * nfs4_find_get_deviceid(struct nfs_server *server, - const struct nfs4_deviceid *id, struct rpc_cred *cred, + const struct nfs4_deviceid *id, const struct cred *cred, gfp_t gfp_mask) { long hash = nfs4_deviceid_hash(id); diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index d5e4d3cd8c7f..f5ad75fafc3c 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -686,7 +686,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, rpc_clnt_setup_test_and_add_xprt, &rpcdata); if (xprtdata.cred) - put_rpccred(xprtdata.cred); + put_cred(xprtdata.cred); } else { clp = nfs4_set_ds_client(mds_srv, (struct sockaddr *)&da->da_addr, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index e0c257bd62b9..5552fa8b6e12 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -490,7 +490,7 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name) * from nfs_readdir by calling the decode_entry function directly. */ static int -nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, +nfs_proc_readdir(struct dentry *dentry, const struct cred *cred, u64 cookie, struct page **pages, unsigned int count, bool plus) { struct inode *dir = d_inode(dentry); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ac4b2f005778..7c942462d8c6 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2168,7 +2168,10 @@ static int nfs_validate_text_mount_data(void *options, if (args->version == 4) { #if IS_ENABLED(CONFIG_NFS_V4) - port = NFS_PORT; + if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA) + port = NFS_RDMA_PORT; + else + port = NFS_PORT; max_namelen = NFS4_MAXNAMLEN; max_pathlen = NFS4_MAXPATHLEN; nfs_validate_transport_protocol(args); @@ -2178,8 +2181,11 @@ static int nfs_validate_text_mount_data(void *options, #else goto out_v4_not_compiled; #endif /* CONFIG_NFS_V4 */ - } else + } else { nfs_set_mount_transport_protocol(args); + if (args->nfs_server.protocol == XPRT_TRANSPORT_RDMA) + port = NFS_RDMA_PORT; + } nfs_set_port(sap, &args->nfs_server.port, port); @@ -2409,8 +2415,7 @@ static int nfs_compare_mount_options(const struct super_block *s, const struct n goto Ebusy; if (a->acdirmax != b->acdirmax) goto Ebusy; - if (b->auth_info.flavor_len > 0 && - clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) + if (clnt_a->cl_auth->au_flavor != clnt_b->cl_auth->au_flavor) goto Ebusy; return 1; Ebusy: diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index fd61bf0fce63..79b97b3c4427 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -31,7 +31,7 @@ static void nfs_free_unlinkdata(struct nfs_unlinkdata *data) { - put_rpccred(data->cred); + put_cred(data->cred); kfree(data->args.name.name); kfree(data); } @@ -177,11 +177,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name) goto out_free; data->args.name.len = name->len; - data->cred = rpc_lookup_cred(); - if (IS_ERR(data->cred)) { - status = PTR_ERR(data->cred); - goto out_free_name; - } + data->cred = get_current_cred(); data->res.dir_attr = &data->dir_attr; init_waitqueue_head(&data->wq); @@ -202,8 +198,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name) return 0; out_unlock: spin_unlock(&dentry->d_lock); - put_rpccred(data->cred); -out_free_name: + put_cred(data->cred); kfree(data->args.name.name); out_free: kfree(data); @@ -307,7 +302,7 @@ static void nfs_async_rename_release(void *calldata) iput(data->old_dir); iput(data->new_dir); nfs_sb_deactive(sb); - put_rpccred(data->cred); + put_cred(data->cred); kfree(data); } @@ -352,12 +347,7 @@ nfs_async_rename(struct inode *old_dir, struct inode *new_dir, return ERR_PTR(-ENOMEM); task_setup_data.callback_data = data; - data->cred = rpc_lookup_cred(); - if (IS_ERR(data->cred)) { - struct rpc_task *task = ERR_CAST(data->cred); - kfree(data); - return task; - } + data->cred = get_current_cred(); msg.rpc_argp = &data->args; msg.rpc_resp = &data->res; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 4f15665f0ad1..5a0bbf917a32 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1233,9 +1233,12 @@ int nfs_key_timeout_notify(struct file *filp, struct inode *inode) { struct nfs_open_context *ctx = nfs_file_open_context(filp); - struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; - return rpcauth_key_timeout_notify(auth, ctx->cred); + if (nfs_ctx_key_to_expire(ctx, inode) && + !ctx->ll_cred) + /* Already expired! */ + return -EACCES; + return 0; } /* @@ -1244,8 +1247,23 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode) bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) { struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; + struct rpc_cred *cred = ctx->ll_cred; + struct auth_cred acred = { + .cred = ctx->cred, + }; - return rpcauth_cred_key_to_expire(auth, ctx->cred); + if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) { + put_rpccred(cred); + ctx->ll_cred = NULL; + cred = NULL; + } + if (!cred) + cred = auth->au_ops->lookup_cred(auth, &acred, 0); + if (!cred || IS_ERR(cred)) + return true; + ctx->ll_cred = cred; + return !!(cred->cr_ops->crkey_timeout && + cred->cr_ops->crkey_timeout(cred)); } /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 25987bcdf96f..c74e4538d0eb 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -844,24 +844,23 @@ static int max_cb_time(struct net *net) return max(nn->nfsd4_lease/10, (time_t)1) * HZ; } -static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) +static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) { if (clp->cl_minorversion == 0) { - char *principal = clp->cl_cred.cr_targ_princ ? - clp->cl_cred.cr_targ_princ : "nfs"; - struct rpc_cred *cred; - - cred = rpc_lookup_machine_cred(principal); - if (!IS_ERR(cred)) - get_rpccred(cred); - return cred; + client->cl_principal = clp->cl_cred.cr_targ_princ ? + clp->cl_cred.cr_targ_princ : "nfs"; + + return get_cred(rpc_machine_cred()); } else { - struct rpc_auth *auth = client->cl_auth; - struct auth_cred acred = {}; + struct cred *kcred; + + kcred = prepare_kernel_cred(NULL); + if (!kcred) + return NULL; - acred.uid = ses->se_cb_sec.uid; - acred.gid = ses->se_cb_sec.gid; - return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0); + kcred->uid = ses->se_cb_sec.uid; + kcred->gid = ses->se_cb_sec.gid; + return kcred; } } @@ -884,7 +883,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c .flags = (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET), }; struct rpc_clnt *client; - struct rpc_cred *cred; + const struct cred *cred; if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && @@ -1214,7 +1213,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) if (clp->cl_cb_client) { rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; - put_rpccred(clp->cl_cb_cred); + put_cred(clp->cl_cb_cred); clp->cl_cb_cred = NULL; } if (clp->cl_cb_conn.cb_xprt) { diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 2b36aa037ce0..44517fb5c0de 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -656,7 +656,6 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task) struct nfsd_net *nn; ktime_t now, cutoff; const struct nfsd4_layout_ops *ops; - LIST_HEAD(reaplist); switch (task->tk_status) { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index d505990dac7c..0cfd257ffdaf 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -863,8 +863,7 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_rename *rename = &u->rename; __be32 status; - if (opens_in_grace(SVC_NET(rqstp)) && - !(cstate->save_fh.fh_export->ex_flags & NFSEXP_NOSUBTREECHECK)) + if (opens_in_grace(SVC_NET(rqstp))) return nfserr_grace; status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname, rename->rn_snamelen, &cstate->current_fh, @@ -1016,8 +1015,6 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nvecs = svc_fill_write_vector(rqstp, write->wr_pagelist, &write->wr_head, write->wr_buflen); - if (!nvecs) - return nfserr_io; WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp, @@ -1348,7 +1345,7 @@ static __be32 nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_fallocate *fallocate, int flags) { - __be32 status = nfserr_notsupp; + __be32 status; struct file *file; status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -2682,25 +2679,25 @@ static const struct nfsd4_operation nfsd4_ops[] = { /* NFSv4.2 operations */ [OP_ALLOCATE] = { .op_func = nfsd4_allocate, - .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_ALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_DEALLOCATE] = { .op_func = nfsd4_deallocate, - .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_DEALLOCATE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_CLONE] = { .op_func = nfsd4_clone, - .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_CLONE", .op_rsize_bop = nfsd4_only_status_rsize, }, [OP_COPY] = { .op_func = nfsd4_copy, - .op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME, + .op_flags = OP_MODIFIES_SOMETHING, .op_name = "OP_COPY", .op_rsize_bop = nfsd4_copy_rsize, }, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 9c247fa1e959..5188f9f70c78 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -662,7 +662,7 @@ struct cld_net { struct cld_upcall { struct list_head cu_list; struct cld_net *cu_net; - struct task_struct *cu_task; + struct completion cu_done; struct cld_msg cu_msg; }; @@ -671,23 +671,18 @@ __cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg) { int ret; struct rpc_pipe_msg msg; + struct cld_upcall *cup = container_of(cmsg, struct cld_upcall, cu_msg); memset(&msg, 0, sizeof(msg)); msg.data = cmsg; msg.len = sizeof(*cmsg); - /* - * Set task state before we queue the upcall. That prevents - * wake_up_process in the downcall from racing with schedule. - */ - set_current_state(TASK_UNINTERRUPTIBLE); ret = rpc_queue_upcall(pipe, &msg); if (ret < 0) { - set_current_state(TASK_RUNNING); goto out; } - schedule(); + wait_for_completion(&cup->cu_done); if (msg.errno < 0) ret = msg.errno; @@ -754,7 +749,7 @@ cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (copy_from_user(&cup->cu_msg, src, mlen) != 0) return -EFAULT; - wake_up_process(cup->cu_task); + complete(&cup->cu_done); return mlen; } @@ -769,7 +764,7 @@ cld_pipe_destroy_msg(struct rpc_pipe_msg *msg) if (msg->errno >= 0) return; - wake_up_process(cup->cu_task); + complete(&cup->cu_done); } static const struct rpc_pipe_ops cld_upcall_ops = { @@ -900,7 +895,7 @@ restart_search: goto restart_search; } } - new->cu_task = current; + init_completion(&new->cu_done); new->cu_msg.cm_vers = CLD_UPCALL_VERSION; put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid); new->cu_net = cn; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a334828723fa..fb3c9844c82a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5112,7 +5112,7 @@ nfs4_find_file(struct nfs4_stid *s, int flags) } static __be32 -nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) +nfs4_check_olstateid(struct nfs4_ol_stateid *ols, int flags) { __be32 status; @@ -5195,7 +5195,7 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, break; case NFS4_OPEN_STID: case NFS4_LOCK_STID: - status = nfs4_check_olstateid(fhp, openlockstateid(s), flags); + status = nfs4_check_olstateid(openlockstateid(s), flags); break; default: status = nfserr_bad_stateid; @@ -6230,15 +6230,15 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, case NFS4_READ_LT: case NFS4_READW_LT: file_lock->fl_type = F_RDLCK; - break; + break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: file_lock->fl_type = F_WRLCK; - break; + break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); status = nfserr_inval; - goto out; + goto out; } lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 6384c9b94898..b33f9785b756 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1126,6 +1126,8 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': + if (nn->nfsd_serv) + return -EBUSY; nfsd4_end_grace(nn); break; default: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 6aacb325b6a0..396c76755b03 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -327,7 +327,7 @@ struct nfs4_client { #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) unsigned long cl_flags; - struct rpc_cred *cl_cb_cred; + const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; u32 cl_cb_ident; #define NFSD4_CB_UP 0 diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eb67098117b4..9824e32b2f23 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -396,10 +396,23 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap, bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); - if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE)) + if (iap->ia_valid & ATTR_SIZE) { accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE; - if (iap->ia_valid & ATTR_SIZE) ftype = S_IFREG; + } + + /* + * If utimes(2) and friends are called with times not NULL, we should + * not set NFSD_MAY_WRITE bit. Otherwise fh_verify->nfsd_permission + * will return EACCESS, when the caller's effective UID does not match + * the owner of the file, and the caller is not privileged. In this + * situation, we should return EPERM(notify_change will return this). + */ + if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME)) { + accmode |= NFSD_MAY_OWNER_OVERRIDE; + if (!(iap->ia_valid & (ATTR_ATIME_SET | ATTR_MTIME_SET))) + accmode |= NFSD_MAY_WRITE; + } /* Callers that do fh_verify should do the fh_want_write: */ get_write_count = !fhp->fh_dentry; diff --git a/include/dt-bindings/clock/imx8-clock.h b/include/dt-bindings/clock/imx8-clock.h new file mode 100644 index 000000000000..4236818e3be5 --- /dev/null +++ b/include/dt-bindings/clock/imx8-clock.h @@ -0,0 +1,289 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2018 NXP + * Dong Aisheng <aisheng.dong@nxp.com> + */ + +#ifndef __DT_BINDINGS_CLOCK_IMX_H +#define __DT_BINDINGS_CLOCK_IMX_H + +/* SCU Clocks */ + +#define IMX_CLK_DUMMY 0 + +/* CPU */ +#define IMX_A35_CLK 1 + +/* LSIO SS */ +#define IMX_LSIO_MEM_CLK 2 +#define IMX_LSIO_BUS_CLK 3 +#define IMX_LSIO_PWM0_CLK 10 +#define IMX_LSIO_PWM1_CLK 11 +#define IMX_LSIO_PWM2_CLK 12 +#define IMX_LSIO_PWM3_CLK 13 +#define IMX_LSIO_PWM4_CLK 14 +#define IMX_LSIO_PWM5_CLK 15 +#define IMX_LSIO_PWM6_CLK 16 +#define IMX_LSIO_PWM7_CLK 17 +#define IMX_LSIO_GPT0_CLK 18 +#define IMX_LSIO_GPT1_CLK 19 +#define IMX_LSIO_GPT2_CLK 20 +#define IMX_LSIO_GPT3_CLK 21 +#define IMX_LSIO_GPT4_CLK 22 +#define IMX_LSIO_FSPI0_CLK 23 +#define IMX_LSIO_FSPI1_CLK 24 + +/* Connectivity SS */ +#define IMX_CONN_AXI_CLK_ROOT 30 +#define IMX_CONN_AHB_CLK_ROOT 31 +#define IMX_CONN_IPG_CLK_ROOT 32 +#define IMX_CONN_SDHC0_CLK 40 +#define IMX_CONN_SDHC1_CLK 41 +#define IMX_CONN_SDHC2_CLK 42 +#define IMX_CONN_ENET0_ROOT_CLK 43 +#define IMX_CONN_ENET0_BYPASS_CLK 44 +#define IMX_CONN_ENET0_RGMII_CLK 45 +#define IMX_CONN_ENET1_ROOT_CLK 46 +#define IMX_CONN_ENET1_BYPASS_CLK 47 +#define IMX_CONN_ENET1_RGMII_CLK 48 +#define IMX_CONN_GPMI_BCH_IO_CLK 49 +#define IMX_CONN_GPMI_BCH_CLK 50 +#define IMX_CONN_USB2_ACLK 51 +#define IMX_CONN_USB2_BUS_CLK 52 +#define IMX_CONN_USB2_LPM_CLK 53 + +/* HSIO SS */ +#define IMX_HSIO_AXI_CLK 60 +#define IMX_HSIO_PER_CLK 61 + +/* Display controller SS */ +#define IMX_DC_AXI_EXT_CLK 70 +#define IMX_DC_AXI_INT_CLK 71 +#define IMX_DC_CFG_CLK 72 +#define IMX_DC0_PLL0_CLK 80 +#define IMX_DC0_PLL1_CLK 81 +#define IMX_DC0_DISP0_CLK 82 +#define IMX_DC0_DISP1_CLK 83 + +/* MIPI-LVDS SS */ +#define IMX_MIPI_IPG_CLK 90 +#define IMX_MIPI0_PIXEL_CLK 100 +#define IMX_MIPI0_BYPASS_CLK 101 +#define IMX_MIPI0_LVDS_PIXEL_CLK 102 +#define IMX_MIPI0_LVDS_BYPASS_CLK 103 +#define IMX_MIPI0_LVDS_PHY_CLK 104 +#define IMX_MIPI0_I2C0_CLK 105 +#define IMX_MIPI0_I2C1_CLK 106 +#define IMX_MIPI0_PWM0_CLK 107 +#define IMX_MIPI1_PIXEL_CLK 108 +#define IMX_MIPI1_BYPASS_CLK 109 +#define IMX_MIPI1_LVDS_PIXEL_CLK 110 +#define IMX_MIPI1_LVDS_BYPASS_CLK 111 +#define IMX_MIPI1_LVDS_PHY_CLK 112 +#define IMX_MIPI1_I2C0_CLK 113 +#define IMX_MIPI1_I2C1_CLK 114 +#define IMX_MIPI1_PWM0_CLK 115 + +/* IMG SS */ +#define IMX_IMG_AXI_CLK 120 +#define IMX_IMG_IPG_CLK 121 +#define IMX_IMG_PXL_CLK 122 + +/* MIPI-CSI SS */ +#define IMX_CSI0_CORE_CLK 130 +#define IMX_CSI0_ESC_CLK 131 +#define IMX_CSI0_PWM0_CLK 132 +#define IMX_CSI0_I2C0_CLK 133 + +/* PARALLER CSI SS */ +#define IMX_PARALLEL_CSI_DPLL_CLK 140 +#define IMX_PARALLEL_CSI_PIXEL_CLK 141 +#define IMX_PARALLEL_CSI_MCLK_CLK 142 + +/* VPU SS */ +#define IMX_VPU_ENC_CLK 150 +#define IMX_VPU_DEC_CLK 151 + +/* GPU SS */ +#define IMX_GPU0_CORE_CLK 160 +#define IMX_GPU0_SHADER_CLK 161 + +/* ADMA SS */ +#define IMX_ADMA_IPG_CLK_ROOT 165 +#define IMX_ADMA_UART0_CLK 170 +#define IMX_ADMA_UART1_CLK 171 +#define IMX_ADMA_UART2_CLK 172 +#define IMX_ADMA_UART3_CLK 173 +#define IMX_ADMA_SPI0_CLK 174 +#define IMX_ADMA_SPI1_CLK 175 +#define IMX_ADMA_SPI2_CLK 176 +#define IMX_ADMA_SPI3_CLK 177 +#define IMX_ADMA_CAN0_CLK 178 +#define IMX_ADMA_CAN1_CLK 179 +#define IMX_ADMA_CAN2_CLK 180 +#define IMX_ADMA_I2C0_CLK 181 +#define IMX_ADMA_I2C1_CLK 182 +#define IMX_ADMA_I2C2_CLK 183 +#define IMX_ADMA_I2C3_CLK 184 +#define IMX_ADMA_FTM0_CLK 185 +#define IMX_ADMA_FTM1_CLK 186 +#define IMX_ADMA_ADC0_CLK 187 +#define IMX_ADMA_PWM_CLK 188 +#define IMX_ADMA_LCD_CLK 189 + +#define IMX_SCU_CLK_END 190 + +/* LPCG clocks */ + +/* LSIO SS LPCG */ +#define IMX_LSIO_LPCG_PWM0_IPG_CLK 0 +#define IMX_LSIO_LPCG_PWM0_IPG_S_CLK 1 +#define IMX_LSIO_LPCG_PWM0_IPG_HF_CLK 2 +#define IMX_LSIO_LPCG_PWM0_IPG_SLV_CLK 3 +#define IMX_LSIO_LPCG_PWM0_IPG_MSTR_CLK 4 +#define IMX_LSIO_LPCG_PWM1_IPG_CLK 5 +#define IMX_LSIO_LPCG_PWM1_IPG_S_CLK 6 +#define IMX_LSIO_LPCG_PWM1_IPG_HF_CLK 7 +#define IMX_LSIO_LPCG_PWM1_IPG_SLV_CLK 8 +#define IMX_LSIO_LPCG_PWM1_IPG_MSTR_CLK 9 +#define IMX_LSIO_LPCG_PWM2_IPG_CLK 10 +#define IMX_LSIO_LPCG_PWM2_IPG_S_CLK 11 +#define IMX_LSIO_LPCG_PWM2_IPG_HF_CLK 12 +#define IMX_LSIO_LPCG_PWM2_IPG_SLV_CLK 13 +#define IMX_LSIO_LPCG_PWM2_IPG_MSTR_CLK 14 +#define IMX_LSIO_LPCG_PWM3_IPG_CLK 15 +#define IMX_LSIO_LPCG_PWM3_IPG_S_CLK 16 +#define IMX_LSIO_LPCG_PWM3_IPG_HF_CLK 17 +#define IMX_LSIO_LPCG_PWM3_IPG_SLV_CLK 18 +#define IMX_LSIO_LPCG_PWM3_IPG_MSTR_CLK 19 +#define IMX_LSIO_LPCG_PWM4_IPG_CLK 20 +#define IMX_LSIO_LPCG_PWM4_IPG_S_CLK 21 +#define IMX_LSIO_LPCG_PWM4_IPG_HF_CLK 22 +#define IMX_LSIO_LPCG_PWM4_IPG_SLV_CLK 23 +#define IMX_LSIO_LPCG_PWM4_IPG_MSTR_CLK 24 +#define IMX_LSIO_LPCG_PWM5_IPG_CLK 25 +#define IMX_LSIO_LPCG_PWM5_IPG_S_CLK 26 +#define IMX_LSIO_LPCG_PWM5_IPG_HF_CLK 27 +#define IMX_LSIO_LPCG_PWM5_IPG_SLV_CLK 28 +#define IMX_LSIO_LPCG_PWM5_IPG_MSTR_CLK 29 +#define IMX_LSIO_LPCG_PWM6_IPG_CLK 30 +#define IMX_LSIO_LPCG_PWM6_IPG_S_CLK 31 +#define IMX_LSIO_LPCG_PWM6_IPG_HF_CLK 32 +#define IMX_LSIO_LPCG_PWM6_IPG_SLV_CLK 33 +#define IMX_LSIO_LPCG_PWM6_IPG_MSTR_CLK 34 +#define IMX_LSIO_LPCG_PWM7_IPG_CLK 35 +#define IMX_LSIO_LPCG_PWM7_IPG_S_CLK 36 +#define IMX_LSIO_LPCG_PWM7_IPG_HF_CLK 37 +#define IMX_LSIO_LPCG_PWM7_IPG_SLV_CLK 38 +#define IMX_LSIO_LPCG_PWM7_IPG_MSTR_CLK 39 +#define IMX_LSIO_LPCG_GPT0_IPG_CLK 40 +#define IMX_LSIO_LPCG_GPT0_IPG_S_CLK 41 +#define IMX_LSIO_LPCG_GPT0_IPG_HF_CLK 42 +#define IMX_LSIO_LPCG_GPT0_IPG_SLV_CLK 43 +#define IMX_LSIO_LPCG_GPT0_IPG_MSTR_CLK 44 +#define IMX_LSIO_LPCG_GPT1_IPG_CLK 45 +#define IMX_LSIO_LPCG_GPT1_IPG_S_CLK 46 +#define IMX_LSIO_LPCG_GPT1_IPG_HF_CLK 47 +#define IMX_LSIO_LPCG_GPT1_IPG_SLV_CLK 48 +#define IMX_LSIO_LPCG_GPT1_IPG_MSTR_CLK 49 +#define IMX_LSIO_LPCG_GPT2_IPG_CLK 50 +#define IMX_LSIO_LPCG_GPT2_IPG_S_CLK 51 +#define IMX_LSIO_LPCG_GPT2_IPG_HF_CLK 52 +#define IMX_LSIO_LPCG_GPT2_IPG_SLV_CLK 53 +#define IMX_LSIO_LPCG_GPT2_IPG_MSTR_CLK 54 +#define IMX_LSIO_LPCG_GPT3_IPG_CLK 55 +#define IMX_LSIO_LPCG_GPT3_IPG_S_CLK 56 +#define IMX_LSIO_LPCG_GPT3_IPG_HF_CLK 57 +#define IMX_LSIO_LPCG_GPT3_IPG_SLV_CLK 58 +#define IMX_LSIO_LPCG_GPT3_IPG_MSTR_CLK 59 +#define IMX_LSIO_LPCG_GPT4_IPG_CLK 60 +#define IMX_LSIO_LPCG_GPT4_IPG_S_CLK 61 +#define IMX_LSIO_LPCG_GPT4_IPG_HF_CLK 62 +#define IMX_LSIO_LPCG_GPT4_IPG_SLV_CLK 63 +#define IMX_LSIO_LPCG_GPT4_IPG_MSTR_CLK 64 +#define IMX_LSIO_LPCG_FSPI0_HCLK 65 +#define IMX_LSIO_LPCG_FSPI0_IPG_CLK 66 +#define IMX_LSIO_LPCG_FSPI0_IPG_S_CLK 67 +#define IMX_LSIO_LPCG_FSPI0_IPG_SFCK 68 +#define IMX_LSIO_LPCG_FSPI1_HCLK 69 +#define IMX_LSIO_LPCG_FSPI1_IPG_CLK 70 +#define IMX_LSIO_LPCG_FSPI1_IPG_S_CLK 71 +#define IMX_LSIO_LPCG_FSPI1_IPG_SFCK 72 + +#define IMX_LSIO_LPCG_CLK_END 73 + +/* Connectivity SS LPCG */ +#define IMX_CONN_LPCG_SDHC0_IPG_CLK 0 +#define IMX_CONN_LPCG_SDHC0_PER_CLK 1 +#define IMX_CONN_LPCG_SDHC0_HCLK 2 +#define IMX_CONN_LPCG_SDHC1_IPG_CLK 3 +#define IMX_CONN_LPCG_SDHC1_PER_CLK 4 +#define IMX_CONN_LPCG_SDHC1_HCLK 5 +#define IMX_CONN_LPCG_SDHC2_IPG_CLK 6 +#define IMX_CONN_LPCG_SDHC2_PER_CLK 7 +#define IMX_CONN_LPCG_SDHC2_HCLK 8 +#define IMX_CONN_LPCG_GPMI_APB_CLK 9 +#define IMX_CONN_LPCG_GPMI_BCH_APB_CLK 10 +#define IMX_CONN_LPCG_GPMI_BCH_IO_CLK 11 +#define IMX_CONN_LPCG_GPMI_BCH_CLK 12 +#define IMX_CONN_LPCG_APBHDMA_CLK 13 +#define IMX_CONN_LPCG_ENET0_ROOT_CLK 14 +#define IMX_CONN_LPCG_ENET0_TX_CLK 15 +#define IMX_CONN_LPCG_ENET0_AHB_CLK 16 +#define IMX_CONN_LPCG_ENET0_IPG_S_CLK 17 +#define IMX_CONN_LPCG_ENET0_IPG_CLK 18 + +#define IMX_CONN_LPCG_ENET1_ROOT_CLK 19 +#define IMX_CONN_LPCG_ENET1_TX_CLK 20 +#define IMX_CONN_LPCG_ENET1_AHB_CLK 21 +#define IMX_CONN_LPCG_ENET1_IPG_S_CLK 22 +#define IMX_CONN_LPCG_ENET1_IPG_CLK 23 + +#define IMX_CONN_LPCG_CLK_END 24 + +/* ADMA SS LPCG */ +#define IMX_ADMA_LPCG_UART0_IPG_CLK 0 +#define IMX_ADMA_LPCG_UART0_BAUD_CLK 1 +#define IMX_ADMA_LPCG_UART1_IPG_CLK 2 +#define IMX_ADMA_LPCG_UART1_BAUD_CLK 3 +#define IMX_ADMA_LPCG_UART2_IPG_CLK 4 +#define IMX_ADMA_LPCG_UART2_BAUD_CLK 5 +#define IMX_ADMA_LPCG_UART3_IPG_CLK 6 +#define IMX_ADMA_LPCG_UART3_BAUD_CLK 7 +#define IMX_ADMA_LPCG_SPI0_IPG_CLK 8 +#define IMX_ADMA_LPCG_SPI1_IPG_CLK 9 +#define IMX_ADMA_LPCG_SPI2_IPG_CLK 10 +#define IMX_ADMA_LPCG_SPI3_IPG_CLK 11 +#define IMX_ADMA_LPCG_SPI0_CLK 12 +#define IMX_ADMA_LPCG_SPI1_CLK 13 +#define IMX_ADMA_LPCG_SPI2_CLK 14 +#define IMX_ADMA_LPCG_SPI3_CLK 15 +#define IMX_ADMA_LPCG_CAN0_IPG_CLK 16 +#define IMX_ADMA_LPCG_CAN0_IPG_PE_CLK 17 +#define IMX_ADMA_LPCG_CAN0_IPG_CHI_CLK 18 +#define IMX_ADMA_LPCG_CAN1_IPG_CLK 19 +#define IMX_ADMA_LPCG_CAN1_IPG_PE_CLK 20 +#define IMX_ADMA_LPCG_CAN1_IPG_CHI_CLK 21 +#define IMX_ADMA_LPCG_CAN2_IPG_CLK 22 +#define IMX_ADMA_LPCG_CAN2_IPG_PE_CLK 23 +#define IMX_ADMA_LPCG_CAN2_IPG_CHI_CLK 24 +#define IMX_ADMA_LPCG_I2C0_CLK 25 +#define IMX_ADMA_LPCG_I2C1_CLK 26 +#define IMX_ADMA_LPCG_I2C2_CLK 27 +#define IMX_ADMA_LPCG_I2C3_CLK 28 +#define IMX_ADMA_LPCG_I2C0_IPG_CLK 29 +#define IMX_ADMA_LPCG_I2C1_IPG_CLK 30 +#define IMX_ADMA_LPCG_I2C2_IPG_CLK 31 +#define IMX_ADMA_LPCG_I2C3_IPG_CLK 32 +#define IMX_ADMA_LPCG_FTM0_CLK 33 +#define IMX_ADMA_LPCG_FTM1_CLK 34 +#define IMX_ADMA_LPCG_FTM0_IPG_CLK 35 +#define IMX_ADMA_LPCG_FTM1_IPG_CLK 36 +#define IMX_ADMA_LPCG_PWM_HI_CLK 37 +#define IMX_ADMA_LPCG_PWM_IPG_CLK 38 +#define IMX_ADMA_LPCG_LCD_PIX_CLK 39 +#define IMX_ADMA_LPCG_LCD_APB_CLK 40 + +#define IMX_ADMA_LPCG_CLK_END 41 + +#endif /* __DT_BINDINGS_CLOCK_IMX_H */ diff --git a/include/dt-bindings/clock/imx8qxp-clock.h b/include/dt-bindings/clock/imx8qxp-clock.h deleted file mode 100644 index 6fec3687f3c7..000000000000 --- a/include/dt-bindings/clock/imx8qxp-clock.h +++ /dev/null @@ -1,289 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * Copyright 2018 NXP - * Dong Aisheng <aisheng.dong@nxp.com> - */ - -#ifndef __DT_BINDINGS_CLOCK_IMX8QXP_H -#define __DT_BINDINGS_CLOCK_IMX8QXP_H - -/* SCU Clocks */ - -#define IMX8QXP_CLK_DUMMY 0 - -/* CPU */ -#define IMX8QXP_A35_CLK 1 - -/* LSIO SS */ -#define IMX8QXP_LSIO_MEM_CLK 2 -#define IMX8QXP_LSIO_BUS_CLK 3 -#define IMX8QXP_LSIO_PWM0_CLK 10 -#define IMX8QXP_LSIO_PWM1_CLK 11 -#define IMX8QXP_LSIO_PWM2_CLK 12 -#define IMX8QXP_LSIO_PWM3_CLK 13 -#define IMX8QXP_LSIO_PWM4_CLK 14 -#define IMX8QXP_LSIO_PWM5_CLK 15 -#define IMX8QXP_LSIO_PWM6_CLK 16 -#define IMX8QXP_LSIO_PWM7_CLK 17 -#define IMX8QXP_LSIO_GPT0_CLK 18 -#define IMX8QXP_LSIO_GPT1_CLK 19 -#define IMX8QXP_LSIO_GPT2_CLK 20 -#define IMX8QXP_LSIO_GPT3_CLK 21 -#define IMX8QXP_LSIO_GPT4_CLK 22 -#define IMX8QXP_LSIO_FSPI0_CLK 23 -#define IMX8QXP_LSIO_FSPI1_CLK 24 - -/* Connectivity SS */ -#define IMX8QXP_CONN_AXI_CLK_ROOT 30 -#define IMX8QXP_CONN_AHB_CLK_ROOT 31 -#define IMX8QXP_CONN_IPG_CLK_ROOT 32 -#define IMX8QXP_CONN_SDHC0_CLK 40 -#define IMX8QXP_CONN_SDHC1_CLK 41 -#define IMX8QXP_CONN_SDHC2_CLK 42 -#define IMX8QXP_CONN_ENET0_ROOT_CLK 43 -#define IMX8QXP_CONN_ENET0_BYPASS_CLK 44 -#define IMX8QXP_CONN_ENET0_RGMII_CLK 45 -#define IMX8QXP_CONN_ENET1_ROOT_CLK 46 -#define IMX8QXP_CONN_ENET1_BYPASS_CLK 47 -#define IMX8QXP_CONN_ENET1_RGMII_CLK 48 -#define IMX8QXP_CONN_GPMI_BCH_IO_CLK 49 -#define IMX8QXP_CONN_GPMI_BCH_CLK 50 -#define IMX8QXP_CONN_USB2_ACLK 51 -#define IMX8QXP_CONN_USB2_BUS_CLK 52 -#define IMX8QXP_CONN_USB2_LPM_CLK 53 - -/* HSIO SS */ -#define IMX8QXP_HSIO_AXI_CLK 60 -#define IMX8QXP_HSIO_PER_CLK 61 - -/* Display controller SS */ -#define IMX8QXP_DC_AXI_EXT_CLK 70 -#define IMX8QXP_DC_AXI_INT_CLK 71 -#define IMX8QXP_DC_CFG_CLK 72 -#define IMX8QXP_DC0_PLL0_CLK 80 -#define IMX8QXP_DC0_PLL1_CLK 81 -#define IMX8QXP_DC0_DISP0_CLK 82 -#define IMX8QXP_DC0_DISP1_CLK 83 - -/* MIPI-LVDS SS */ -#define IMX8QXP_MIPI_IPG_CLK 90 -#define IMX8QXP_MIPI0_PIXEL_CLK 100 -#define IMX8QXP_MIPI0_BYPASS_CLK 101 -#define IMX8QXP_MIPI0_LVDS_PIXEL_CLK 102 -#define IMX8QXP_MIPI0_LVDS_BYPASS_CLK 103 -#define IMX8QXP_MIPI0_LVDS_PHY_CLK 104 -#define IMX8QXP_MIPI0_I2C0_CLK 105 -#define IMX8QXP_MIPI0_I2C1_CLK 106 -#define IMX8QXP_MIPI0_PWM0_CLK 107 -#define IMX8QXP_MIPI1_PIXEL_CLK 108 -#define IMX8QXP_MIPI1_BYPASS_CLK 109 -#define IMX8QXP_MIPI1_LVDS_PIXEL_CLK 110 -#define IMX8QXP_MIPI1_LVDS_BYPASS_CLK 111 -#define IMX8QXP_MIPI1_LVDS_PHY_CLK 112 -#define IMX8QXP_MIPI1_I2C0_CLK 113 -#define IMX8QXP_MIPI1_I2C1_CLK 114 -#define IMX8QXP_MIPI1_PWM0_CLK 115 - -/* IMG SS */ -#define IMX8QXP_IMG_AXI_CLK 120 -#define IMX8QXP_IMG_IPG_CLK 121 -#define IMX8QXP_IMG_PXL_CLK 122 - -/* MIPI-CSI SS */ -#define IMX8QXP_CSI0_CORE_CLK 130 -#define IMX8QXP_CSI0_ESC_CLK 131 -#define IMX8QXP_CSI0_PWM0_CLK 132 -#define IMX8QXP_CSI0_I2C0_CLK 133 - -/* PARALLER CSI SS */ -#define IMX8QXP_PARALLEL_CSI_DPLL_CLK 140 -#define IMX8QXP_PARALLEL_CSI_PIXEL_CLK 141 -#define IMX8QXP_PARALLEL_CSI_MCLK_CLK 142 - -/* VPU SS */ -#define IMX8QXP_VPU_ENC_CLK 150 -#define IMX8QXP_VPU_DEC_CLK 151 - -/* GPU SS */ -#define IMX8QXP_GPU0_CORE_CLK 160 -#define IMX8QXP_GPU0_SHADER_CLK 161 - -/* ADMA SS */ -#define IMX8QXP_ADMA_IPG_CLK_ROOT 165 -#define IMX8QXP_ADMA_UART0_CLK 170 -#define IMX8QXP_ADMA_UART1_CLK 171 -#define IMX8QXP_ADMA_UART2_CLK 172 -#define IMX8QXP_ADMA_UART3_CLK 173 -#define IMX8QXP_ADMA_SPI0_CLK 174 -#define IMX8QXP_ADMA_SPI1_CLK 175 -#define IMX8QXP_ADMA_SPI2_CLK 176 -#define IMX8QXP_ADMA_SPI3_CLK 177 -#define IMX8QXP_ADMA_CAN0_CLK 178 -#define IMX8QXP_ADMA_CAN1_CLK 179 -#define IMX8QXP_ADMA_CAN2_CLK 180 -#define IMX8QXP_ADMA_I2C0_CLK 181 -#define IMX8QXP_ADMA_I2C1_CLK 182 -#define IMX8QXP_ADMA_I2C2_CLK 183 -#define IMX8QXP_ADMA_I2C3_CLK 184 -#define IMX8QXP_ADMA_FTM0_CLK 185 -#define IMX8QXP_ADMA_FTM1_CLK 186 -#define IMX8QXP_ADMA_ADC0_CLK 187 -#define IMX8QXP_ADMA_PWM_CLK 188 -#define IMX8QXP_ADMA_LCD_CLK 189 - -#define IMX8QXP_SCU_CLK_END 190 - -/* LPCG clocks */ - -/* LSIO SS LPCG */ -#define IMX8QXP_LSIO_LPCG_PWM0_IPG_CLK 0 -#define IMX8QXP_LSIO_LPCG_PWM0_IPG_S_CLK 1 -#define IMX8QXP_LSIO_LPCG_PWM0_IPG_HF_CLK 2 -#define IMX8QXP_LSIO_LPCG_PWM0_IPG_SLV_CLK 3 -#define IMX8QXP_LSIO_LPCG_PWM0_IPG_MSTR_CLK 4 -#define IMX8QXP_LSIO_LPCG_PWM1_IPG_CLK 5 -#define IMX8QXP_LSIO_LPCG_PWM1_IPG_S_CLK 6 -#define IMX8QXP_LSIO_LPCG_PWM1_IPG_HF_CLK 7 -#define IMX8QXP_LSIO_LPCG_PWM1_IPG_SLV_CLK 8 -#define IMX8QXP_LSIO_LPCG_PWM1_IPG_MSTR_CLK 9 -#define IMX8QXP_LSIO_LPCG_PWM2_IPG_CLK 10 -#define IMX8QXP_LSIO_LPCG_PWM2_IPG_S_CLK 11 -#define IMX8QXP_LSIO_LPCG_PWM2_IPG_HF_CLK 12 -#define IMX8QXP_LSIO_LPCG_PWM2_IPG_SLV_CLK 13 -#define IMX8QXP_LSIO_LPCG_PWM2_IPG_MSTR_CLK 14 -#define IMX8QXP_LSIO_LPCG_PWM3_IPG_CLK 15 -#define IMX8QXP_LSIO_LPCG_PWM3_IPG_S_CLK 16 -#define IMX8QXP_LSIO_LPCG_PWM3_IPG_HF_CLK 17 -#define IMX8QXP_LSIO_LPCG_PWM3_IPG_SLV_CLK 18 -#define IMX8QXP_LSIO_LPCG_PWM3_IPG_MSTR_CLK 19 -#define IMX8QXP_LSIO_LPCG_PWM4_IPG_CLK 20 -#define IMX8QXP_LSIO_LPCG_PWM4_IPG_S_CLK 21 -#define IMX8QXP_LSIO_LPCG_PWM4_IPG_HF_CLK 22 -#define IMX8QXP_LSIO_LPCG_PWM4_IPG_SLV_CLK 23 -#define IMX8QXP_LSIO_LPCG_PWM4_IPG_MSTR_CLK 24 -#define IMX8QXP_LSIO_LPCG_PWM5_IPG_CLK 25 -#define IMX8QXP_LSIO_LPCG_PWM5_IPG_S_CLK 26 -#define IMX8QXP_LSIO_LPCG_PWM5_IPG_HF_CLK 27 -#define IMX8QXP_LSIO_LPCG_PWM5_IPG_SLV_CLK 28 -#define IMX8QXP_LSIO_LPCG_PWM5_IPG_MSTR_CLK 29 -#define IMX8QXP_LSIO_LPCG_PWM6_IPG_CLK 30 -#define IMX8QXP_LSIO_LPCG_PWM6_IPG_S_CLK 31 -#define IMX8QXP_LSIO_LPCG_PWM6_IPG_HF_CLK 32 -#define IMX8QXP_LSIO_LPCG_PWM6_IPG_SLV_CLK 33 -#define IMX8QXP_LSIO_LPCG_PWM6_IPG_MSTR_CLK 34 -#define IMX8QXP_LSIO_LPCG_PWM7_IPG_CLK 35 -#define IMX8QXP_LSIO_LPCG_PWM7_IPG_S_CLK 36 -#define IMX8QXP_LSIO_LPCG_PWM7_IPG_HF_CLK 37 -#define IMX8QXP_LSIO_LPCG_PWM7_IPG_SLV_CLK 38 -#define IMX8QXP_LSIO_LPCG_PWM7_IPG_MSTR_CLK 39 -#define IMX8QXP_LSIO_LPCG_GPT0_IPG_CLK 40 -#define IMX8QXP_LSIO_LPCG_GPT0_IPG_S_CLK 41 -#define IMX8QXP_LSIO_LPCG_GPT0_IPG_HF_CLK 42 -#define IMX8QXP_LSIO_LPCG_GPT0_IPG_SLV_CLK 43 -#define IMX8QXP_LSIO_LPCG_GPT0_IPG_MSTR_CLK 44 -#define IMX8QXP_LSIO_LPCG_GPT1_IPG_CLK 45 -#define IMX8QXP_LSIO_LPCG_GPT1_IPG_S_CLK 46 -#define IMX8QXP_LSIO_LPCG_GPT1_IPG_HF_CLK 47 -#define IMX8QXP_LSIO_LPCG_GPT1_IPG_SLV_CLK 48 -#define IMX8QXP_LSIO_LPCG_GPT1_IPG_MSTR_CLK 49 -#define IMX8QXP_LSIO_LPCG_GPT2_IPG_CLK 50 -#define IMX8QXP_LSIO_LPCG_GPT2_IPG_S_CLK 51 -#define IMX8QXP_LSIO_LPCG_GPT2_IPG_HF_CLK 52 -#define IMX8QXP_LSIO_LPCG_GPT2_IPG_SLV_CLK 53 -#define IMX8QXP_LSIO_LPCG_GPT2_IPG_MSTR_CLK 54 -#define IMX8QXP_LSIO_LPCG_GPT3_IPG_CLK 55 -#define IMX8QXP_LSIO_LPCG_GPT3_IPG_S_CLK 56 -#define IMX8QXP_LSIO_LPCG_GPT3_IPG_HF_CLK 57 -#define IMX8QXP_LSIO_LPCG_GPT3_IPG_SLV_CLK 58 -#define IMX8QXP_LSIO_LPCG_GPT3_IPG_MSTR_CLK 59 -#define IMX8QXP_LSIO_LPCG_GPT4_IPG_CLK 60 -#define IMX8QXP_LSIO_LPCG_GPT4_IPG_S_CLK 61 -#define IMX8QXP_LSIO_LPCG_GPT4_IPG_HF_CLK 62 -#define IMX8QXP_LSIO_LPCG_GPT4_IPG_SLV_CLK 63 -#define IMX8QXP_LSIO_LPCG_GPT4_IPG_MSTR_CLK 64 -#define IMX8QXP_LSIO_LPCG_FSPI0_HCLK 65 -#define IMX8QXP_LSIO_LPCG_FSPI0_IPG_CLK 66 -#define IMX8QXP_LSIO_LPCG_FSPI0_IPG_S_CLK 67 -#define IMX8QXP_LSIO_LPCG_FSPI0_IPG_SFCK 68 -#define IMX8QXP_LSIO_LPCG_FSPI1_HCLK 69 -#define IMX8QXP_LSIO_LPCG_FSPI1_IPG_CLK 70 -#define IMX8QXP_LSIO_LPCG_FSPI1_IPG_S_CLK 71 -#define IMX8QXP_LSIO_LPCG_FSPI1_IPG_SFCK 72 - -#define IMX8QXP_LSIO_LPCG_CLK_END 73 - -/* Connectivity SS LPCG */ -#define IMX8QXP_CONN_LPCG_SDHC0_IPG_CLK 0 -#define IMX8QXP_CONN_LPCG_SDHC0_PER_CLK 1 -#define IMX8QXP_CONN_LPCG_SDHC0_HCLK 2 -#define IMX8QXP_CONN_LPCG_SDHC1_IPG_CLK 3 -#define IMX8QXP_CONN_LPCG_SDHC1_PER_CLK 4 -#define IMX8QXP_CONN_LPCG_SDHC1_HCLK 5 -#define IMX8QXP_CONN_LPCG_SDHC2_IPG_CLK 6 -#define IMX8QXP_CONN_LPCG_SDHC2_PER_CLK 7 -#define IMX8QXP_CONN_LPCG_SDHC2_HCLK 8 -#define IMX8QXP_CONN_LPCG_GPMI_APB_CLK 9 -#define IMX8QXP_CONN_LPCG_GPMI_BCH_APB_CLK 10 -#define IMX8QXP_CONN_LPCG_GPMI_BCH_IO_CLK 11 -#define IMX8QXP_CONN_LPCG_GPMI_BCH_CLK 12 -#define IMX8QXP_CONN_LPCG_APBHDMA_CLK 13 -#define IMX8QXP_CONN_LPCG_ENET0_ROOT_CLK 14 -#define IMX8QXP_CONN_LPCG_ENET0_TX_CLK 15 -#define IMX8QXP_CONN_LPCG_ENET0_AHB_CLK 16 -#define IMX8QXP_CONN_LPCG_ENET0_IPG_S_CLK 17 -#define IMX8QXP_CONN_LPCG_ENET0_IPG_CLK 18 - -#define IMX8QXP_CONN_LPCG_ENET1_ROOT_CLK 19 -#define IMX8QXP_CONN_LPCG_ENET1_TX_CLK 20 -#define IMX8QXP_CONN_LPCG_ENET1_AHB_CLK 21 -#define IMX8QXP_CONN_LPCG_ENET1_IPG_S_CLK 22 -#define IMX8QXP_CONN_LPCG_ENET1_IPG_CLK 23 - -#define IMX8QXP_CONN_LPCG_CLK_END 24 - -/* ADMA SS LPCG */ -#define IMX8QXP_ADMA_LPCG_UART0_IPG_CLK 0 -#define IMX8QXP_ADMA_LPCG_UART0_BAUD_CLK 1 -#define IMX8QXP_ADMA_LPCG_UART1_IPG_CLK 2 -#define IMX8QXP_ADMA_LPCG_UART1_BAUD_CLK 3 -#define IMX8QXP_ADMA_LPCG_UART2_IPG_CLK 4 -#define IMX8QXP_ADMA_LPCG_UART2_BAUD_CLK 5 -#define IMX8QXP_ADMA_LPCG_UART3_IPG_CLK 6 -#define IMX8QXP_ADMA_LPCG_UART3_BAUD_CLK 7 -#define IMX8QXP_ADMA_LPCG_SPI0_IPG_CLK 8 -#define IMX8QXP_ADMA_LPCG_SPI1_IPG_CLK 9 -#define IMX8QXP_ADMA_LPCG_SPI2_IPG_CLK 10 -#define IMX8QXP_ADMA_LPCG_SPI3_IPG_CLK 11 -#define IMX8QXP_ADMA_LPCG_SPI0_CLK 12 -#define IMX8QXP_ADMA_LPCG_SPI1_CLK 13 -#define IMX8QXP_ADMA_LPCG_SPI2_CLK 14 -#define IMX8QXP_ADMA_LPCG_SPI3_CLK 15 -#define IMX8QXP_ADMA_LPCG_CAN0_IPG_CLK 16 -#define IMX8QXP_ADMA_LPCG_CAN0_IPG_PE_CLK 17 -#define IMX8QXP_ADMA_LPCG_CAN0_IPG_CHI_CLK 18 -#define IMX8QXP_ADMA_LPCG_CAN1_IPG_CLK 19 -#define IMX8QXP_ADMA_LPCG_CAN1_IPG_PE_CLK 20 -#define IMX8QXP_ADMA_LPCG_CAN1_IPG_CHI_CLK 21 -#define IMX8QXP_ADMA_LPCG_CAN2_IPG_CLK 22 -#define IMX8QXP_ADMA_LPCG_CAN2_IPG_PE_CLK 23 -#define IMX8QXP_ADMA_LPCG_CAN2_IPG_CHI_CLK 24 -#define IMX8QXP_ADMA_LPCG_I2C0_CLK 25 -#define IMX8QXP_ADMA_LPCG_I2C1_CLK 26 -#define IMX8QXP_ADMA_LPCG_I2C2_CLK 27 -#define IMX8QXP_ADMA_LPCG_I2C3_CLK 28 -#define IMX8QXP_ADMA_LPCG_I2C0_IPG_CLK 29 -#define IMX8QXP_ADMA_LPCG_I2C1_IPG_CLK 30 -#define IMX8QXP_ADMA_LPCG_I2C2_IPG_CLK 31 -#define IMX8QXP_ADMA_LPCG_I2C3_IPG_CLK 32 -#define IMX8QXP_ADMA_LPCG_FTM0_CLK 33 -#define IMX8QXP_ADMA_LPCG_FTM1_CLK 34 -#define IMX8QXP_ADMA_LPCG_FTM0_IPG_CLK 35 -#define IMX8QXP_ADMA_LPCG_FTM1_IPG_CLK 36 -#define IMX8QXP_ADMA_LPCG_PWM_HI_CLK 37 -#define IMX8QXP_ADMA_LPCG_PWM_IPG_CLK 38 -#define IMX8QXP_ADMA_LPCG_LCD_PIX_CLK 39 -#define IMX8QXP_ADMA_LPCG_LCD_APB_CLK 40 - -#define IMX8QXP_ADMA_LPCG_CLK_END 41 - -#endif /* __DT_BINDINGS_CLOCK_IMX8QXP_H */ diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h index 228a5e234af0..7b24fc791146 100644 --- a/include/dt-bindings/clock/marvell,mmp2.h +++ b/include/dt-bindings/clock/marvell,mmp2.h @@ -71,6 +71,7 @@ #define MMP2_CLK_CCIC1_MIX 117 #define MMP2_CLK_CCIC1_PHY 118 #define MMP2_CLK_CCIC1_SPHY 119 +#define MMP2_CLK_SP 120 #define MMP2_NR_CLKS 200 #endif diff --git a/include/dt-bindings/mailbox/tegra186-hsp.h b/include/dt-bindings/mailbox/tegra186-hsp.h index bcab5b7ca785..3bdec7a84d35 100644 --- a/include/dt-bindings/mailbox/tegra186-hsp.h +++ b/include/dt-bindings/mailbox/tegra186-hsp.h @@ -22,4 +22,15 @@ #define TEGRA_HSP_DB_MASTER_CCPLEX 17 #define TEGRA_HSP_DB_MASTER_BPMP 19 +/* + * Shared mailboxes are unidirectional, so the direction needs to be specified + * in the device tree. + */ +#define TEGRA_HSP_SM_MASK 0x00ffffff +#define TEGRA_HSP_SM_FLAG_RX (0 << 31) +#define TEGRA_HSP_SM_FLAG_TX (1 << 31) + +#define TEGRA_HSP_SM_RX(x) (TEGRA_HSP_SM_FLAG_RX | ((x) & TEGRA_HSP_SM_MASK)) +#define TEGRA_HSP_SM_TX(x) (TEGRA_HSP_SM_FLAG_TX | ((x) & TEGRA_HSP_SM_MASK)) + #endif diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index f025fd1e22e6..76c61318fda5 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -499,22 +499,33 @@ static inline void blkg_get(struct blkcg_gq *blkg) */ static inline bool blkg_tryget(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + return blkg && percpu_ref_tryget(&blkg->refcnt); } /** * blkg_tryget_closest - try and get a blkg ref on the closet blkg * @blkg: blkg to get * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. + * This needs to be called rcu protected. As the failure mode here is to walk + * up the blkg tree, this ensure that the blkg->parent pointers are always + * valid. This returns the blkg that it ended up taking a reference on or %NULL + * if no reference was taken. */ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) { - while (blkg && !percpu_ref_tryget(&blkg->refcnt)) + struct blkcg_gq *ret_blkg = NULL; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + while (blkg) { + if (blkg_tryget(blkg)) { + ret_blkg = blkg; + break; + } blkg = blkg->parent; + } - return blkg; + return ret_blkg; } /** diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c233efc106c6..27b74947cd2b 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -148,6 +148,7 @@ struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; u32 curframe; + bool speculative; }; #define bpf_get_spilled_reg(slot, frame) \ @@ -167,15 +168,24 @@ struct bpf_verifier_state_list { struct bpf_verifier_state_list *next; }; +/* Possible states for alu_state member. */ +#define BPF_ALU_SANITIZE_SRC 1U +#define BPF_ALU_SANITIZE_DST 2U +#define BPF_ALU_NEG_VALUE (1U << 2) +#define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \ + BPF_ALU_SANITIZE_DST) + struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ unsigned long map_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ + u32 alu_limit; /* limit for add/sub register with pointer */ }; int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ + u8 alu_state; /* used in combination with alu_limit */ }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ @@ -212,6 +222,8 @@ struct bpf_subprog_info { * one verifier_env per bpf_check() call */ struct bpf_verifier_env { + u32 insn_idx; + u32 prev_insn_idx; struct bpf_prog *prog; /* eBPF program being verified */ const struct bpf_verifier_ops *ops; struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */ diff --git a/include/linux/cred.h b/include/linux/cred.h index 7eed6101c791..4907c9df86b3 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -169,6 +169,7 @@ extern int change_create_files_as(struct cred *, struct inode *); extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); +extern int cred_fscmp(const struct cred *, const struct cred *); extern void __init cred_init(void); /* @@ -236,7 +237,7 @@ static inline struct cred *get_new_cred(struct cred *cred) * @cred: The credentials to reference * * Get a reference on the specified set of credentials. The caller must - * release the reference. + * release the reference. If %NULL is passed, it is returned with no action. * * This is used to deal with a committed set of credentials. Although the * pointer is const, this will temporarily discard the const and increment the @@ -247,16 +248,29 @@ static inline struct cred *get_new_cred(struct cred *cred) static inline const struct cred *get_cred(const struct cred *cred) { struct cred *nonconst_cred = (struct cred *) cred; + if (!cred) + return cred; validate_creds(cred); return get_new_cred(nonconst_cred); } +static inline const struct cred *get_cred_rcu(const struct cred *cred) +{ + struct cred *nonconst_cred = (struct cred *) cred; + if (!cred) + return NULL; + if (!atomic_inc_not_zero(&nonconst_cred->usage)) + return NULL; + validate_creds(cred); + return cred; +} + /** * put_cred - Release a reference to a set of credentials * @cred: The credentials to release * * Release a reference to a set of credentials, deleting them when the last ref - * is released. + * is released. If %NULL is passed, nothing is done. * * This takes a const pointer to a set of credentials because the credentials * on task_struct are attached by const pointers to prevent accidental @@ -266,9 +280,11 @@ static inline void put_cred(const struct cred *_cred) { struct cred *cred = (struct cred *) _cred; - validate_creds(cred); - if (atomic_dec_and_test(&(cred)->usage)) - __put_cred(cred); + if (cred) { + validate_creds(cred); + if (atomic_dec_and_test(&(cred)->usage)) + __put_cred(cred); + } } /** diff --git a/include/linux/drbd.h b/include/linux/drbd.h index 2d0259327721..a19d98367f08 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,7 +51,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.10" +#define REL_VERSION "8.4.11" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 diff --git a/include/linux/efi.h b/include/linux/efi.h index becd5d76a207..45ff763fba76 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -663,6 +663,10 @@ void efi_native_runtime_setup(void); #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) +#define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) +#define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) +#define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) + /* * This GUID is used to pass to the kernel proper the struct screen_info * structure that was populated by the stub based on the GOP protocol instance @@ -934,6 +938,27 @@ typedef struct { efi_memory_desc_t entry[0]; } efi_memory_attributes_table_t; +typedef struct { + efi_guid_t signature_owner; + u8 signature_data[]; +} efi_signature_data_t; + +typedef struct { + efi_guid_t signature_type; + u32 signature_list_size; + u32 signature_header_size; + u32 signature_size; + u8 signature_header[]; + /* efi_signature_data_t signatures[][] */ +} efi_signature_list_t; + +typedef u8 efi_sha256_hash_t[32]; + +typedef struct { + efi_sha256_hash_t to_be_signed_hash; + efi_time_t time_of_revocation; +} efi_cert_x509_sha256_t; + /* * All runtime access to EFI goes through this structure: */ @@ -1113,6 +1138,15 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm, char * __init efi_md_typeattr_format(char *buf, size_t size, const efi_memory_desc_t *md); + +typedef void (*efi_element_handler_t)(const char *source, + const void *element_data, + size_t element_size); +extern int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)); + /** * efi_range_is_wc - check the WC bit on an address range * @start: starting kvirt address diff --git a/include/linux/filter.h b/include/linux/filter.h index 8c8544b375eb..ad106d845b22 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -53,14 +53,10 @@ struct sock_reuseport; #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ -/* Kernel hidden auxiliary/helper register for hardening step. - * Only used by eBPF JITs. It's nothing more than a temporary - * register that JITs use internally, only that here it's part - * of eBPF instructions that have been rewritten for blinding - * constants. See JIT pre-step in bpf_jit_blind_constants(). - */ +/* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG -#define MAX_BPF_JIT_REG (MAX_BPF_REG + 1) +#define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) +#define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h index 5972e4969197..eeae59d3ceb7 100644 --- a/include/linux/genl_magic_struct.h +++ b/include/linux/genl_magic_struct.h @@ -191,6 +191,7 @@ static inline void ct_assert_unique_operations(void) { switch (0) { #include GENL_MAGIC_INCLUDE_FILE + case 0: ; } } @@ -209,6 +210,7 @@ static inline void ct_assert_unique_top_level_attributes(void) { switch (0) { #include GENL_MAGIC_INCLUDE_FILE + case 0: ; } } @@ -218,7 +220,8 @@ static inline void ct_assert_unique_top_level_attributes(void) static inline void ct_assert_unique_ ## s_name ## _attributes(void) \ { \ switch (0) { \ - s_fields \ + s_fields \ + case 0: \ ; \ } \ } diff --git a/include/linux/ima.h b/include/linux/ima.h index 97914a2833d1..b5e16b8c50b7 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -30,6 +30,21 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif +#if defined(CONFIG_X86) && defined(CONFIG_EFI) +extern bool arch_ima_get_secureboot(void); +extern const char * const *arch_get_ima_policy(void); +#else +static inline bool arch_ima_get_secureboot(void) +{ + return false; +} + +static inline const char * const *arch_get_ima_policy(void) +{ + return NULL; +} +#endif + #else static inline int ima_bprm_check(struct linux_binprm *bprm) { diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h index 44348710953f..faa7da3c9c8b 100644 --- a/include/linux/mailbox_client.h +++ b/include/linux/mailbox_client.h @@ -44,6 +44,7 @@ struct mbox_chan *mbox_request_channel_byname(struct mbox_client *cl, const char *name); struct mbox_chan *mbox_request_channel(struct mbox_client *cl, int index); int mbox_send_message(struct mbox_chan *chan, void *mssg); +int mbox_flush(struct mbox_chan *chan, unsigned long timeout); void mbox_client_txdone(struct mbox_chan *chan, int r); /* atomic */ bool mbox_client_peek_data(struct mbox_chan *chan); /* atomic */ void mbox_free_channel(struct mbox_chan *chan); /* may sleep */ diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h index 74deadb42d76..4994a438444c 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -24,6 +24,9 @@ struct mbox_chan; * transmission of data is reported by the controller via * mbox_chan_txdone (if it has some TX ACK irq). It must not * sleep. + * @flush: Called when a client requests transmissions to be blocking but + * the context doesn't allow sleeping. Typically the controller + * will implement a busy loop waiting for the data to flush out. * @startup: Called when a client requests the chan. The controller * could ask clients for additional parameters of communication * to be provided via client's chan_data. This call may @@ -46,6 +49,7 @@ struct mbox_chan; */ struct mbox_chan_ops { int (*send_data)(struct mbox_chan *chan, void *data); + int (*flush)(struct mbox_chan *chan, unsigned long timeout); int (*startup)(struct mbox_chan *chan); void (*shutdown)(struct mbox_chan *chan); bool (*last_tx_done)(struct mbox_chan *chan); @@ -131,4 +135,9 @@ void mbox_controller_unregister(struct mbox_controller *mbox); /* can sleep */ void mbox_chan_received_data(struct mbox_chan *chan, void *data); /* atomic */ void mbox_chan_txdone(struct mbox_chan *chan, int r); /* atomic */ +int devm_mbox_controller_register(struct device *dev, + struct mbox_controller *mbox); +void devm_mbox_controller_unregister(struct device *dev, + struct mbox_controller *mbox); + #endif /* __MAILBOX_CONTROLLER_H */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6e0417c02279..40e30376130b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -51,7 +51,7 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - struct rpc_cred * cred; + const struct cred * cred; __u32 mask; struct rcu_head rcu_head; }; @@ -70,7 +70,8 @@ struct nfs_open_context { struct nfs_lock_context lock_context; fl_owner_t flock_owner; struct dentry *dentry; - struct rpc_cred *cred; + const struct cred *cred; + struct rpc_cred *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; @@ -88,7 +89,7 @@ struct nfs_open_context { struct nfs_open_dir_context { struct list_head list; - struct rpc_cred *cred; + const struct cred *cred; unsigned long attr_gencount; __u64 dir_cookie; __u64 dup_cookie; @@ -390,7 +391,7 @@ extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, struct nfs4_label *label); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); -extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, fmode_t mode); +extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); extern struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode, struct file *filp); extern void nfs_inode_attach_open_context(struct nfs_open_context *ctx); extern void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx); @@ -461,7 +462,7 @@ static inline struct nfs_open_context *nfs_file_open_context(struct file *filp) return filp->private_data; } -static inline struct rpc_cred *nfs_file_cred(struct file *file) +static inline const struct cred *nfs_file_cred(struct file *file) { if (file != NULL) { struct nfs_open_context *ctx = @@ -490,7 +491,7 @@ extern const struct dentry_operations nfs_dentry_operations; extern void nfs_force_lookup_revalidate(struct inode *dir); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); -extern int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags); +extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); /* diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 0fc0b9135d46..6aa8cc83c3b6 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -58,7 +58,7 @@ struct nfs_client { struct nfs_subversion * cl_nfs_mod; /* pointer to nfs version module */ u32 cl_minorversion;/* NFSv4 minorversion */ - struct rpc_cred *cl_machine_cred; + const char * cl_principal; /* used for machine cred */ #if IS_ENABLED(CONFIG_NFS_V4) struct list_head cl_ds_clients; /* auth flavor data servers */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 0e016252cfc6..441a93ebcac0 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -270,7 +270,7 @@ struct nfs4_layoutget_res { struct nfs4_layoutget { struct nfs4_layoutget_args args; struct nfs4_layoutget_res res; - struct rpc_cred *cred; + const struct cred *cred; gfp_t gfp_flags; }; @@ -309,7 +309,7 @@ struct nfs4_layoutcommit_data { struct rpc_task task; struct nfs_fattr fattr; struct list_head lseg_list; - struct rpc_cred *cred; + const struct cred *cred; struct inode *inode; struct nfs4_layoutcommit_args args; struct nfs4_layoutcommit_res res; @@ -334,7 +334,7 @@ struct nfs4_layoutreturn_res { struct nfs4_layoutreturn { struct nfs4_layoutreturn_args args; struct nfs4_layoutreturn_res res; - struct rpc_cred *cred; + const struct cred *cred; struct nfs_client *clp; struct inode *inode; int rpc_status; @@ -1469,7 +1469,7 @@ enum { struct nfs_io_completion; struct nfs_pgio_header { struct inode *inode; - struct rpc_cred *cred; + const struct cred *cred; struct list_head pages; struct nfs_page *req; struct nfs_writeverf verf; /* Used for writes */ @@ -1529,7 +1529,7 @@ struct nfs_commit_info { struct nfs_commit_data { struct rpc_task task; struct inode *inode; - struct rpc_cred *cred; + const struct cred *cred; struct nfs_fattr fattr; struct nfs_writeverf verf; struct list_head pages; /* Coalesced requests we wish to flush */ @@ -1560,7 +1560,7 @@ struct nfs_unlinkdata { struct nfs_removeres res; struct dentry *dentry; wait_queue_head_t wq; - struct rpc_cred *cred; + const struct cred *cred; struct nfs_fattr dir_attr; long timeout; }; @@ -1568,7 +1568,7 @@ struct nfs_unlinkdata { struct nfs_renamedata { struct nfs_renameargs args; struct nfs_renameres res; - struct rpc_cred *cred; + const struct cred *cred; struct inode *old_dir; struct dentry *old_dentry; struct nfs_fattr old_fattr; @@ -1634,7 +1634,7 @@ struct nfs_rpc_ops { unsigned int, struct iattr *); int (*mkdir) (struct inode *, struct dentry *, struct iattr *); int (*rmdir) (struct inode *, const struct qstr *); - int (*readdir) (struct dentry *, struct rpc_cred *, + int (*readdir) (struct dentry *, const struct cred *, u64, struct page **, unsigned int, bool); int (*mknod) (struct inode *, struct dentry *, struct iattr *, dev_t); diff --git a/include/linux/phy.h b/include/linux/phy.h index da039f211c22..3b051f761450 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1,6 +1,6 @@ /* * Framework and drivers for configuring and reading different PHYs - * Based on code in sungem_phy.c and gianfar_phy.c + * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * @@ -110,9 +110,9 @@ typedef enum { * @speeds: buffer to store supported speeds in. * @size: size of speeds buffer. * - * Description: Returns the number of supported speeds, and - * fills the speeds * buffer with the supported speeds. If speeds buffer is - * too small to contain * all currently supported speeds, will return as + * Description: Returns the number of supported speeds, and fills + * the speeds buffer with the supported speeds. If speeds buffer is + * too small to contain all currently supported speeds, will return as * many speeds as can fit. */ unsigned int phy_supported_speeds(struct phy_device *phy, @@ -120,7 +120,10 @@ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int size); /** - * It maps 'enum phy_interface_t' found in include/linux/phy.h + * phy_modes - map phy_interface_t enum to device tree binding of phy-mode + * @interface: enum phy_interface_t value + * + * Description: maps 'enum phy_interface_t' defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get phy interface from device tree. */ diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 1fdefadf150a..e8e118d70fd7 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -110,6 +110,7 @@ struct phy_ops { /** * struct phy_attrs - represents phy attributes * @bus_width: Data path width implemented by PHY + * @mode: PHY mode */ struct phy_attrs { u32 bus_width; @@ -121,7 +122,6 @@ struct phy_attrs { * @dev: phy device * @id: id of the phy device * @ops: function pointers for performing phy operations - * @init_data: list of PHY consumers (non-dt only) * @mutex: mutex to protect phy_ops * @init_count: used to protect when the PHY is used by multiple consumers * @power_count: used to protect when the PHY is used by multiple consumers diff --git a/include/linux/platform_data/ad7879.h b/include/linux/platform_data/ad7879.h deleted file mode 100644 index 6655cc8453ac..000000000000 --- a/include/linux/platform_data/ad7879.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* linux/platform_data/ad7879.h */ - -/* Touchscreen characteristics vary between boards and models. The - * platform_data for the device's "struct device" holds this information. - * - * It's OK if the min/max values are zero. - */ -struct ad7879_platform_data { - u16 model; /* 7879 */ - u16 x_plate_ohms; - u16 x_min, x_max; - u16 y_min, y_max; - u16 pressure_min, pressure_max; - - bool swap_xy; /* swap x and y axes */ - - /* [0..255] 0=OFF Starts at 1=550us and goes - * all the way to 9.440ms in steps of 35us. - */ - u8 pen_down_acc_interval; - /* [0..15] Starts at 0=128us and goes all the - * way to 4.096ms in steps of 128us. - */ - u8 first_conversion_delay; - /* [0..3] 0 = 2us, 1 = 4us, 2 = 8us, 3 = 16us */ - u8 acquisition_time; - /* [0..3] Average X middle samples 0 = 2, 1 = 4, 2 = 8, 3 = 16 */ - u8 averaging; - /* [0..3] Perform X measurements 0 = OFF, - * 1 = 4, 2 = 8, 3 = 16 (median > averaging) - */ - u8 median; - /* 1 = AUX/VBAT/GPIO export GPIO to gpiolib - * requires CONFIG_GPIOLIB - */ - bool gpio_export; - /* identifies the first GPIO number handled by this chip; - * or, if negative, requests dynamic ID allocation. - */ - s32 gpio_base; -}; diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 6894976b54e3..186cd8e970c7 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -573,6 +573,8 @@ static inline void **__ptr_ring_swap_queue(struct ptr_ring *r, void **queue, else if (destroy) destroy(ptr); + if (producer >= size) + producer = 0; __ptr_ring_set_size(r, size); r->producer = producer; r->consumer_head = 0; diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index e5320f6c8654..84868d37b35d 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -4,9 +4,10 @@ #include <uapi/linux/seccomp.h> -#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ - SECCOMP_FILTER_FLAG_LOG | \ - SECCOMP_FILTER_FLAG_SPEC_ALLOW) +#define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ + SECCOMP_FILTER_FLAG_LOG | \ + SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ + SECCOMP_FILTER_FLAG_NEW_LISTENER) #ifdef CONFIG_SECCOMP @@ -43,7 +44,7 @@ extern void secure_computing_strict(int this_syscall); #endif extern long prctl_get_seccomp(void); -extern long prctl_set_seccomp(unsigned long, char __user *); +extern long prctl_set_seccomp(unsigned long, void __user *); static inline int seccomp_mode(struct seccomp *s) { diff --git a/include/linux/sunrpc/auth.h b/include/linux/sunrpc/auth.h index c4db9424b63b..eed3cb16ccf1 100644 --- a/include/linux/sunrpc/auth.h +++ b/include/linux/sunrpc/auth.h @@ -37,21 +37,9 @@ struct rpcsec_gss_info; -/* auth_cred ac_flags bits */ -enum { - RPC_CRED_KEY_EXPIRE_SOON = 1, /* underlying cred key will expire soon */ - RPC_CRED_NOTIFY_TIMEOUT = 2, /* nofity generic cred when underlying - key will expire soon */ -}; - -/* Work around the lack of a VFS credential */ struct auth_cred { - kuid_t uid; - kgid_t gid; - struct group_info *group_info; - const char *principal; - unsigned long ac_flags; - unsigned char machine_cred : 1; + const struct cred *cred; + const char *principal; /* If present, this is a machine credential */ }; /* @@ -68,8 +56,7 @@ struct rpc_cred { unsigned long cr_expire; /* when to gc */ unsigned long cr_flags; /* various flags */ refcount_t cr_count; /* ref count */ - - kuid_t cr_uid; + const struct cred *cr_cred; /* per-flavor data */ }; @@ -78,8 +65,7 @@ struct rpc_cred { #define RPCAUTH_CRED_HASHED 2 #define RPCAUTH_CRED_NEGATIVE 3 -/* rpc_auth au_flags */ -#define RPCAUTH_AUTH_NO_CRKEY_TIMEOUT 0x0001 /* underlying cred has no key timeout */ +const struct cred *rpc_machine_cred(void); /* * Client authentication handle @@ -116,7 +102,6 @@ struct rpc_auth_create_args { /* Flags for rpcauth_lookupcred() */ #define RPCAUTH_LOOKUP_NEW 0x01 /* Accept an uninitialised cred */ -#define RPCAUTH_LOOKUP_RCU 0x02 /* lock-less lookup */ /* * Client authentication ops @@ -146,7 +131,6 @@ struct rpc_credops { void (*crdestroy)(struct rpc_cred *); int (*crmatch)(struct auth_cred *, struct rpc_cred *, int); - struct rpc_cred * (*crbind)(struct rpc_task *, struct rpc_cred *, int); __be32 * (*crmarshal)(struct rpc_task *, __be32 *); int (*crrefresh)(struct rpc_task *); __be32 * (*crvalidate)(struct rpc_task *, __be32 *); @@ -155,7 +139,6 @@ struct rpc_credops { int (*crunwrap_resp)(struct rpc_task *, kxdrdproc_t, void *, __be32 *, void *); int (*crkey_timeout)(struct rpc_cred *); - bool (*crkey_to_expire)(struct rpc_cred *); char * (*crstringify_acceptor)(struct rpc_cred *); bool (*crneed_reencode)(struct rpc_task *); }; @@ -164,16 +147,10 @@ extern const struct rpc_authops authunix_ops; extern const struct rpc_authops authnull_ops; int __init rpc_init_authunix(void); -int __init rpc_init_generic_auth(void); int __init rpcauth_init_module(void); void rpcauth_remove_module(void); -void rpc_destroy_generic_auth(void); void rpc_destroy_authunix(void); -struct rpc_cred * rpc_lookup_cred(void); -struct rpc_cred * rpc_lookup_cred_nonblock(void); -struct rpc_cred * rpc_lookup_generic_cred(struct auth_cred *, int, gfp_t); -struct rpc_cred * rpc_lookup_machine_cred(const char *service_name); int rpcauth_register(const struct rpc_authops *); int rpcauth_unregister(const struct rpc_authops *); struct rpc_auth * rpcauth_create(const struct rpc_auth_create_args *, @@ -187,7 +164,6 @@ int rpcauth_list_flavors(rpc_authflavor_t *, int); struct rpc_cred * rpcauth_lookup_credcache(struct rpc_auth *, struct auth_cred *, int, gfp_t); void rpcauth_init_cred(struct rpc_cred *, const struct auth_cred *, struct rpc_auth *, const struct rpc_credops *); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *, int); -struct rpc_cred * rpcauth_generic_bind_cred(struct rpc_task *, struct rpc_cred *, int); void put_rpccred(struct rpc_cred *); __be32 * rpcauth_marshcred(struct rpc_task *, __be32 *); __be32 * rpcauth_checkverf(struct rpc_task *, __be32 *); @@ -200,9 +176,6 @@ int rpcauth_uptodatecred(struct rpc_task *); int rpcauth_init_credcache(struct rpc_auth *); void rpcauth_destroy_credcache(struct rpc_auth *); void rpcauth_clear_credcache(struct rpc_cred_cache *); -int rpcauth_key_timeout_notify(struct rpc_auth *, - struct rpc_cred *); -bool rpcauth_cred_key_to_expire(struct rpc_auth *, struct rpc_cred *); char * rpcauth_stringify_acceptor(struct rpc_cred *); static inline @@ -213,21 +186,5 @@ struct rpc_cred *get_rpccred(struct rpc_cred *cred) return NULL; } -/** - * get_rpccred_rcu - get a reference to a cred using rcu-protected pointer - * @cred: cred of which to take a reference - * - * In some cases, we may have a pointer to a credential to which we - * want to take a reference, but don't already have one. Because these - * objects are freed using RCU, we can access the cr_count while its - * on its way to destruction and only take a reference if it's not already - * zero. - */ -static inline struct rpc_cred * -get_rpccred_rcu(struct rpc_cred *cred) -{ - return get_rpccred(cred); -} - #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_AUTH_H */ diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 28721cf73ec3..d4229a78524a 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -47,11 +47,14 @@ void xprt_free_bc_rqst(struct rpc_rqst *req); /* * Determine if a shared backchannel is in use */ -static inline int svc_is_backchannel(const struct svc_rqst *rqstp) +static inline bool svc_is_backchannel(const struct svc_rqst *rqstp) { - if (rqstp->rq_server->sv_bc_xprt) - return 1; - return 0; + return rqstp->rq_server->sv_bc_enabled; +} + +static inline void set_bc_enabled(struct svc_serv *serv) +{ + serv->sv_bc_enabled = true; } #else /* CONFIG_SUNRPC_BACKCHANNEL */ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, @@ -60,9 +63,13 @@ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, return 0; } -static inline int svc_is_backchannel(const struct svc_rqst *rqstp) +static inline bool svc_is_backchannel(const struct svc_rqst *rqstp) +{ + return false; +} + +static inline void set_bc_enabled(struct svc_serv *serv) { - return 0; } static inline void xprt_free_bc_request(struct rpc_rqst *req) diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 73d5c4a870fa..1c441714d569 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -66,6 +66,7 @@ struct rpc_clnt { struct rpc_rtt cl_rtt_default; struct rpc_timeout cl_timeout_default; const struct rpc_program *cl_program; + const char * cl_principal; /* use for machine cred */ #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct dentry *cl_debugfs; /* debugfs directory */ #endif @@ -127,8 +128,8 @@ struct rpc_create_args { }; struct rpc_add_xprt_test { - int (*add_xprt_test)(struct rpc_clnt *, - struct rpc_xprt *, + void (*add_xprt_test)(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, void *calldata); void *data; }; diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index 7b540c066594..219aa3910a0c 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -26,7 +26,7 @@ struct rpc_message { const struct rpc_procinfo *rpc_proc; /* Procedure information */ void * rpc_argp; /* Arguments */ void * rpc_resp; /* Result */ - struct rpc_cred * rpc_cred; /* Credentials */ + const struct cred * rpc_cred; /* Credentials */ }; struct rpc_call_ops; @@ -71,6 +71,7 @@ struct rpc_task { struct rpc_clnt * tk_client; /* RPC client */ struct rpc_xprt * tk_xprt; /* Transport */ + struct rpc_cred * tk_op_cred; /* cred being operated on */ struct rpc_rqst * tk_rqstp; /* RPC request */ @@ -105,6 +106,7 @@ struct rpc_task_setup { struct rpc_task *task; struct rpc_clnt *rpc_client; struct rpc_xprt *rpc_xprt; + struct rpc_cred *rpc_op_cred; /* credential being operated on */ const struct rpc_message *rpc_message; const struct rpc_call_ops *callback_ops; void *callback_data; @@ -118,6 +120,7 @@ struct rpc_task_setup { */ #define RPC_TASK_ASYNC 0x0001 /* is an async task */ #define RPC_TASK_SWAPPER 0x0002 /* is swapping in/out */ +#define RPC_TASK_NULLCREDS 0x0010 /* Use AUTH_NULL credential */ #define RPC_CALL_MAJORSEEN 0x0020 /* major timeout seen */ #define RPC_TASK_ROOTCREDS 0x0040 /* force root creds */ #define RPC_TASK_DYNAMIC 0x0080 /* task was kmalloc'ed */ @@ -131,7 +134,6 @@ struct rpc_task_setup { #define RPC_IS_ASYNC(t) ((t)->tk_flags & RPC_TASK_ASYNC) #define RPC_IS_SWAPPER(t) ((t)->tk_flags & RPC_TASK_SWAPPER) -#define RPC_DO_ROOTOVERRIDE(t) ((t)->tk_flags & RPC_TASK_ROOTCREDS) #define RPC_ASSASSINATED(t) ((t)->tk_flags & RPC_TASK_KILLED) #define RPC_IS_SOFT(t) ((t)->tk_flags & (RPC_TASK_SOFT|RPC_TASK_TIMEOUT)) #define RPC_IS_SOFTCONN(t) ((t)->tk_flags & RPC_TASK_SOFTCONN) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 73e130a840ce..e52385340b3b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -109,7 +109,7 @@ struct svc_serv { spinlock_t sv_cb_lock; /* protects the svc_cb_list */ wait_queue_head_t sv_cb_waitq; /* sleep here if there are no * entries in the svc_cb_list */ - struct svc_xprt *sv_bc_xprt; /* callback on fore channel */ + bool sv_bc_enabled; /* service uses backchannel */ #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; @@ -295,9 +295,12 @@ struct svc_rqst { struct svc_cacherep * rq_cacherep; /* cache info */ struct task_struct *rq_task; /* service thread */ spinlock_t rq_lock; /* per-request lock */ + struct net *rq_bc_net; /* pointer to backchannel's + * net namespace + */ }; -#define SVC_NET(svc_rqst) (svc_rqst->rq_xprt->xpt_net) +#define SVC_NET(rqst) (rqst->rq_xprt ? rqst->rq_xprt->xpt_net : rqst->rq_bc_net) /* * Rigorous type checking on sockaddr type conversions diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index e6e26918504c..981f0d726ad4 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -135,6 +135,7 @@ struct svc_rdma_recv_ctxt { u32 rc_byte_len; unsigned int rc_page_count; unsigned int rc_hdr_count; + u32 rc_inv_rkey; struct page *rc_pages[RPCSVC_MAXPAGES]; }; @@ -192,7 +193,6 @@ extern int svc_rdma_sendto(struct svc_rqst *); extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *); extern void svc_sq_reap(struct svcxprt_rdma *); extern void svc_rq_reap(struct svcxprt_rdma *); -extern void svc_rdma_prep_reply_hdr(struct svc_rqst *); extern struct svc_xprt_class svc_rdma_class; #ifdef CONFIG_SUNRPC_BACKCHANNEL diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 6b7a86c4d6e6..b3f9577e17d6 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -20,7 +20,6 @@ struct svc_xprt_ops { struct svc_xprt *(*xpo_accept)(struct svc_xprt *); int (*xpo_has_wspace)(struct svc_xprt *); int (*xpo_recvfrom)(struct svc_rqst *); - void (*xpo_prep_reply_hdr)(struct svc_rqst *); int (*xpo_sendto)(struct svc_rqst *); void (*xpo_release_rqst)(struct svc_rqst *); void (*xpo_detach)(struct svc_xprt *); diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index a4ab4f8d9140..ad7e910b119d 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -157,7 +157,6 @@ struct rpc_xprt_ops { void (*inject_disconnect)(struct rpc_xprt *xprt); int (*bc_setup)(struct rpc_xprt *xprt, unsigned int min_reqs); - int (*bc_up)(struct svc_serv *serv, struct net *net); size_t (*bc_maxpayload)(struct rpc_xprt *xprt); void (*bc_free_rqst)(struct rpc_rqst *rqst); void (*bc_destroy)(struct rpc_xprt *xprt, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 251979d2e709..257cccba3062 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -898,7 +898,7 @@ asmlinkage long sys_renameat2(int olddfd, const char __user *oldname, int newdfd, const char __user *newname, unsigned int flags); asmlinkage long sys_seccomp(unsigned int op, unsigned int flags, - const char __user *uargs); + void __user *uargs); asmlinkage long sys_getrandom(char __user *buf, size_t count, unsigned int flags); asmlinkage long sys_memfd_create(const char __user *uname_ptr, unsigned int flags); diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4609b94142d4..b49a55cf775f 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -53,8 +53,8 @@ struct tpm_class_ops { #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); -extern int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf); -extern int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash); +extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf); +extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); extern int tpm_seal_trusted(struct tpm_chip *chip, @@ -69,15 +69,18 @@ static inline int tpm_is_tpm2(struct tpm_chip *chip) { return -ENODEV; } -static inline int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf) + +static inline int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, u8 *res_buf) { return -ENODEV; } -static inline int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, + +static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, const u8 *hash) { return -ENODEV; } + static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) { return -ENODEV; diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index cbcf35ce1b14..34f019650941 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -308,6 +308,26 @@ int ip_tunnel_encap_del_ops(const struct ip_tunnel_encap_ops *op, int ip_tunnel_encap_setup(struct ip_tunnel *t, struct ip_tunnel_encap *ipencap); +static inline bool pskb_inet_may_pull(struct sk_buff *skb) +{ + int nhlen; + + switch (skb->protocol) { +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + nhlen = sizeof(struct ipv6hdr); + break; +#endif + case htons(ETH_P_IP): + nhlen = sizeof(struct iphdr); + break; + default: + nhlen = 0; + } + + return pskb_network_may_pull(skb, nhlen); +} + static inline int ip_encap_hlen(struct ip_tunnel_encap *e) { const struct ip_tunnel_encap_ops *ops; diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h index 4b2b2baf8ab4..f32fc8289473 100644 --- a/include/net/netfilter/nf_conntrack_count.h +++ b/include/net/netfilter/nf_conntrack_count.h @@ -5,17 +5,10 @@ struct nf_conncount_data; -enum nf_conncount_list_add { - NF_CONNCOUNT_ADDED, /* list add was ok */ - NF_CONNCOUNT_ERR, /* -ENOMEM, must drop skb */ - NF_CONNCOUNT_SKIP, /* list is already reclaimed by gc */ -}; - struct nf_conncount_list { spinlock_t list_lock; struct list_head head; /* connections with the same filtering key */ unsigned int count; /* length of list */ - bool dead; }; struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family, @@ -29,18 +22,12 @@ unsigned int nf_conncount_count(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone); -void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit); +int nf_conncount_add(struct net *net, struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone); void nf_conncount_list_init(struct nf_conncount_list *list); -enum nf_conncount_list_add -nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone); - bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list); diff --git a/include/net/sock.h b/include/net/sock.h index a6235c286ef9..2b229f7be8eb 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -298,6 +298,7 @@ struct sock_common { * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer * @sk_stamp: time stamp of last packet received + * @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only * @sk_tsflags: SO_TIMESTAMPING socket options * @sk_tskey: counter to disambiguate concurrent tstamp requests * @sk_zckey: counter to order MSG_ZEROCOPY notifications @@ -474,6 +475,9 @@ struct sock { const struct cred *sk_peer_cred; long sk_rcvtimeo; ktime_t sk_stamp; +#if BITS_PER_LONG==32 + seqlock_t sk_stamp_seq; +#endif u16 sk_tsflags; u8 sk_shutdown; u32 sk_tskey; @@ -2297,6 +2301,34 @@ static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb) atomic_add(segs, &sk->sk_drops); } +static inline ktime_t sock_read_timestamp(struct sock *sk) +{ +#if BITS_PER_LONG==32 + unsigned int seq; + ktime_t kt; + + do { + seq = read_seqbegin(&sk->sk_stamp_seq); + kt = sk->sk_stamp; + } while (read_seqretry(&sk->sk_stamp_seq, seq)); + + return kt; +#else + return sk->sk_stamp; +#endif +} + +static inline void sock_write_timestamp(struct sock *sk, ktime_t kt) +{ +#if BITS_PER_LONG==32 + write_seqlock(&sk->sk_stamp_seq); + sk->sk_stamp = kt; + write_sequnlock(&sk->sk_stamp_seq); +#else + sk->sk_stamp = kt; +#endif +} + void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, @@ -2321,7 +2353,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE))) __sock_recv_timestamp(msg, sk, skb); else - sk->sk_stamp = kt; + sock_write_timestamp(sk, kt); if (sock_flag(sk, SOCK_WIFI_STATUS) && skb->wifi_acked_valid) __sock_recv_wifi_status(msg, sk, skb); @@ -2342,9 +2374,9 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY) __sock_recv_ts_and_drops(msg, sk, skb); else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP))) - sk->sk_stamp = skb->tstamp; + sock_write_timestamp(sk, skb->tstamp); else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP)) - sk->sk_stamp = 0; + sock_write_timestamp(sk, 0); } void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index b093058f78aa..399b1aedc927 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -10,6 +10,7 @@ #if !defined(_TRACE_RPCRDMA_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_RPCRDMA_H +#include <linux/scatterlist.h> #include <linux/tracepoint.h> #include <trace/events/rdma.h> @@ -97,7 +98,6 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) - __field(const void *, mr) __field(unsigned int, pos) __field(int, nents) __field(u32, handle) @@ -109,7 +109,6 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, TP_fast_assign( __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; - __entry->mr = mr; __entry->pos = pos; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; @@ -118,8 +117,8 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u mr=%p pos=%u %u@0x%016llx:0x%08x (%s)", - __entry->task_id, __entry->client_id, __entry->mr, + TP_printk("task:%u@%u pos=%u %u@0x%016llx:0x%08x (%s)", + __entry->task_id, __entry->client_id, __entry->pos, __entry->length, (unsigned long long)__entry->offset, __entry->handle, __entry->nents < __entry->nsegs ? "more" : "last" @@ -127,7 +126,7 @@ DECLARE_EVENT_CLASS(xprtrdma_rdch_event, ); #define DEFINE_RDCH_EVENT(name) \ - DEFINE_EVENT(xprtrdma_rdch_event, name, \ + DEFINE_EVENT(xprtrdma_rdch_event, xprtrdma_chunk_##name,\ TP_PROTO( \ const struct rpc_task *task, \ unsigned int pos, \ @@ -148,7 +147,6 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) - __field(const void *, mr) __field(int, nents) __field(u32, handle) __field(u32, length) @@ -159,7 +157,6 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, TP_fast_assign( __entry->task_id = task->tk_pid; __entry->client_id = task->tk_client->cl_clid; - __entry->mr = mr; __entry->nents = mr->mr_nents; __entry->handle = mr->mr_handle; __entry->length = mr->mr_length; @@ -167,8 +164,8 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, __entry->nsegs = nsegs; ), - TP_printk("task:%u@%u mr=%p %u@0x%016llx:0x%08x (%s)", - __entry->task_id, __entry->client_id, __entry->mr, + TP_printk("task:%u@%u %u@0x%016llx:0x%08x (%s)", + __entry->task_id, __entry->client_id, __entry->length, (unsigned long long)__entry->offset, __entry->handle, __entry->nents < __entry->nsegs ? "more" : "last" @@ -176,7 +173,7 @@ DECLARE_EVENT_CLASS(xprtrdma_wrch_event, ); #define DEFINE_WRCH_EVENT(name) \ - DEFINE_EVENT(xprtrdma_wrch_event, name, \ + DEFINE_EVENT(xprtrdma_wrch_event, xprtrdma_chunk_##name,\ TP_PROTO( \ const struct rpc_task *task, \ struct rpcrdma_mr *mr, \ @@ -234,6 +231,18 @@ DECLARE_EVENT_CLASS(xprtrdma_frwr_done, ), \ TP_ARGS(wc, frwr)) +TRACE_DEFINE_ENUM(DMA_BIDIRECTIONAL); +TRACE_DEFINE_ENUM(DMA_TO_DEVICE); +TRACE_DEFINE_ENUM(DMA_FROM_DEVICE); +TRACE_DEFINE_ENUM(DMA_NONE); + +#define xprtrdma_show_direction(x) \ + __print_symbolic(x, \ + { DMA_BIDIRECTIONAL, "BIDIR" }, \ + { DMA_TO_DEVICE, "TO_DEVICE" }, \ + { DMA_FROM_DEVICE, "FROM_DEVICE" }, \ + { DMA_NONE, "NONE" }) + DECLARE_EVENT_CLASS(xprtrdma_mr, TP_PROTO( const struct rpcrdma_mr *mr @@ -246,6 +255,7 @@ DECLARE_EVENT_CLASS(xprtrdma_mr, __field(u32, handle) __field(u32, length) __field(u64, offset) + __field(u32, dir) ), TP_fast_assign( @@ -253,12 +263,13 @@ DECLARE_EVENT_CLASS(xprtrdma_mr, __entry->handle = mr->mr_handle; __entry->length = mr->mr_length; __entry->offset = mr->mr_offset; + __entry->dir = mr->mr_dir; ), - TP_printk("mr=%p %u@0x%016llx:0x%08x", + TP_printk("mr=%p %u@0x%016llx:0x%08x (%s)", __entry->mr, __entry->length, - (unsigned long long)__entry->offset, - __entry->handle + (unsigned long long)__entry->offset, __entry->handle, + xprtrdma_show_direction(__entry->dir) ) ); @@ -371,11 +382,13 @@ TRACE_EVENT(xprtrdma_disconnect, DEFINE_RXPRT_EVENT(xprtrdma_conn_start); DEFINE_RXPRT_EVENT(xprtrdma_conn_tout); DEFINE_RXPRT_EVENT(xprtrdma_create); -DEFINE_RXPRT_EVENT(xprtrdma_destroy); +DEFINE_RXPRT_EVENT(xprtrdma_op_destroy); DEFINE_RXPRT_EVENT(xprtrdma_remove); DEFINE_RXPRT_EVENT(xprtrdma_reinsert); DEFINE_RXPRT_EVENT(xprtrdma_reconnect); -DEFINE_RXPRT_EVENT(xprtrdma_inject_dsc); +DEFINE_RXPRT_EVENT(xprtrdma_op_inject_dsc); +DEFINE_RXPRT_EVENT(xprtrdma_op_close); +DEFINE_RXPRT_EVENT(xprtrdma_op_connect); TRACE_EVENT(xprtrdma_qp_event, TP_PROTO( @@ -437,9 +450,9 @@ TRACE_EVENT(xprtrdma_createmrs, DEFINE_RXPRT_EVENT(xprtrdma_nomrs); -DEFINE_RDCH_EVENT(xprtrdma_read_chunk); -DEFINE_WRCH_EVENT(xprtrdma_write_chunk); -DEFINE_WRCH_EVENT(xprtrdma_reply_chunk); +DEFINE_RDCH_EVENT(read); +DEFINE_WRCH_EVENT(write); +DEFINE_WRCH_EVENT(reply); TRACE_DEFINE_ENUM(rpcrdma_noch); TRACE_DEFINE_ENUM(rpcrdma_readch); @@ -570,7 +583,7 @@ TRACE_EVENT(xprtrdma_post_recvs, __entry->r_xprt = r_xprt; __entry->count = count; __entry->status = status; - __entry->posted = r_xprt->rx_buf.rb_posted_receives; + __entry->posted = r_xprt->rx_ep.rep_receive_count; __assign_str(addr, rpcrdma_addrstr(r_xprt)); __assign_str(port, rpcrdma_portstr(r_xprt)); ), @@ -651,12 +664,147 @@ DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_fastreg); DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li); DEFINE_FRWR_DONE_EVENT(xprtrdma_wc_li_wake); +TRACE_EVENT(xprtrdma_frwr_alloc, + TP_PROTO( + const struct rpcrdma_mr *mr, + int rc + ), + + TP_ARGS(mr, rc), + + TP_STRUCT__entry( + __field(const void *, mr) + __field(int, rc) + ), + + TP_fast_assign( + __entry->mr = mr; + __entry->rc = rc; + ), + + TP_printk("mr=%p: rc=%d", + __entry->mr, __entry->rc + ) +); + +TRACE_EVENT(xprtrdma_frwr_dereg, + TP_PROTO( + const struct rpcrdma_mr *mr, + int rc + ), + + TP_ARGS(mr, rc), + + TP_STRUCT__entry( + __field(const void *, mr) + __field(u32, handle) + __field(u32, length) + __field(u64, offset) + __field(u32, dir) + __field(int, rc) + ), + + TP_fast_assign( + __entry->mr = mr; + __entry->handle = mr->mr_handle; + __entry->length = mr->mr_length; + __entry->offset = mr->mr_offset; + __entry->dir = mr->mr_dir; + __entry->rc = rc; + ), + + TP_printk("mr=%p %u@0x%016llx:0x%08x (%s): rc=%d", + __entry->mr, __entry->length, + (unsigned long long)__entry->offset, __entry->handle, + xprtrdma_show_direction(__entry->dir), + __entry->rc + ) +); + +TRACE_EVENT(xprtrdma_frwr_sgerr, + TP_PROTO( + const struct rpcrdma_mr *mr, + int sg_nents + ), + + TP_ARGS(mr, sg_nents), + + TP_STRUCT__entry( + __field(const void *, mr) + __field(u64, addr) + __field(u32, dir) + __field(int, nents) + ), + + TP_fast_assign( + __entry->mr = mr; + __entry->addr = mr->mr_sg->dma_address; + __entry->dir = mr->mr_dir; + __entry->nents = sg_nents; + ), + + TP_printk("mr=%p dma addr=0x%llx (%s) sg_nents=%d", + __entry->mr, __entry->addr, + xprtrdma_show_direction(__entry->dir), + __entry->nents + ) +); + +TRACE_EVENT(xprtrdma_frwr_maperr, + TP_PROTO( + const struct rpcrdma_mr *mr, + int num_mapped + ), + + TP_ARGS(mr, num_mapped), + + TP_STRUCT__entry( + __field(const void *, mr) + __field(u64, addr) + __field(u32, dir) + __field(int, num_mapped) + __field(int, nents) + ), + + TP_fast_assign( + __entry->mr = mr; + __entry->addr = mr->mr_sg->dma_address; + __entry->dir = mr->mr_dir; + __entry->num_mapped = num_mapped; + __entry->nents = mr->mr_nents; + ), + + TP_printk("mr=%p dma addr=0x%llx (%s) nents=%d of %d", + __entry->mr, __entry->addr, + xprtrdma_show_direction(__entry->dir), + __entry->num_mapped, __entry->nents + ) +); + DEFINE_MR_EVENT(localinv); DEFINE_MR_EVENT(map); DEFINE_MR_EVENT(unmap); DEFINE_MR_EVENT(remoteinv); DEFINE_MR_EVENT(recycle); +TRACE_EVENT(xprtrdma_dma_maperr, + TP_PROTO( + u64 addr + ), + + TP_ARGS(addr), + + TP_STRUCT__entry( + __field(u64, addr) + ), + + TP_fast_assign( + __entry->addr = addr; + ), + + TP_printk("dma addr=0x%llx\n", __entry->addr) +); + /** ** Reply events **/ @@ -824,7 +972,7 @@ TRACE_EVENT(xprtrdma_decode_seg, ** Allocation/release of rpcrdma_reqs and rpcrdma_reps **/ -TRACE_EVENT(xprtrdma_allocate, +TRACE_EVENT(xprtrdma_op_allocate, TP_PROTO( const struct rpc_task *task, const struct rpcrdma_req *req @@ -854,7 +1002,7 @@ TRACE_EVENT(xprtrdma_allocate, ) ); -TRACE_EVENT(xprtrdma_rpc_done, +TRACE_EVENT(xprtrdma_op_free, TP_PROTO( const struct rpc_task *task, const struct rpcrdma_req *req @@ -917,6 +1065,34 @@ TRACE_EVENT(xprtrdma_cb_setup, DEFINE_CB_EVENT(xprtrdma_cb_call); DEFINE_CB_EVENT(xprtrdma_cb_reply); +TRACE_EVENT(xprtrdma_leaked_rep, + TP_PROTO( + const struct rpc_rqst *rqst, + const struct rpcrdma_rep *rep + ), + + TP_ARGS(rqst, rep), + + TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) + __field(u32, xid) + __field(const void *, rep) + ), + + TP_fast_assign( + __entry->task_id = rqst->rq_task->tk_pid; + __entry->client_id = rqst->rq_task->tk_client->cl_clid; + __entry->xid = be32_to_cpu(rqst->rq_xid); + __entry->rep = rep; + ), + + TP_printk("task:%u@%u xid=0x%08x rep=%p", + __entry->task_id, __entry->client_id, __entry->xid, + __entry->rep + ) +); + /** ** Server-side RPC/RDMA events **/ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 28e384186c35..0d5d0d91f861 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -16,40 +16,6 @@ DECLARE_EVENT_CLASS(rpc_task_status, - TP_PROTO(struct rpc_task *task), - - TP_ARGS(task), - - TP_STRUCT__entry( - __field(unsigned int, task_id) - __field(unsigned int, client_id) - __field(int, status) - ), - - TP_fast_assign( - __entry->task_id = task->tk_pid; - __entry->client_id = task->tk_client->cl_clid; - __entry->status = task->tk_status; - ), - - TP_printk("task:%u@%u status=%d", - __entry->task_id, __entry->client_id, - __entry->status) -); - -DEFINE_EVENT(rpc_task_status, rpc_call_status, - TP_PROTO(struct rpc_task *task), - - TP_ARGS(task) -); - -DEFINE_EVENT(rpc_task_status, rpc_bind_status, - TP_PROTO(struct rpc_task *task), - - TP_ARGS(task) -); - -TRACE_EVENT(rpc_connect_status, TP_PROTO(const struct rpc_task *task), TP_ARGS(task), @@ -70,6 +36,16 @@ TRACE_EVENT(rpc_connect_status, __entry->task_id, __entry->client_id, __entry->status) ); +#define DEFINE_RPC_STATUS_EVENT(name) \ + DEFINE_EVENT(rpc_task_status, rpc_##name##_status, \ + TP_PROTO( \ + const struct rpc_task *task \ + ), \ + TP_ARGS(task)) + +DEFINE_RPC_STATUS_EVENT(call); +DEFINE_RPC_STATUS_EVENT(bind); +DEFINE_RPC_STATUS_EVENT(connect); TRACE_EVENT(rpc_request, TP_PROTO(const struct rpc_task *task), @@ -134,30 +110,17 @@ DECLARE_EVENT_CLASS(rpc_task_running, __entry->action ) ); +#define DEFINE_RPC_RUNNING_EVENT(name) \ + DEFINE_EVENT(rpc_task_running, rpc_task_##name, \ + TP_PROTO( \ + const struct rpc_task *task, \ + const void *action \ + ), \ + TP_ARGS(task, action)) -DEFINE_EVENT(rpc_task_running, rpc_task_begin, - - TP_PROTO(const struct rpc_task *task, const void *action), - - TP_ARGS(task, action) - -); - -DEFINE_EVENT(rpc_task_running, rpc_task_run_action, - - TP_PROTO(const struct rpc_task *task, const void *action), - - TP_ARGS(task, action) - -); - -DEFINE_EVENT(rpc_task_running, rpc_task_complete, - - TP_PROTO(const struct rpc_task *task, const void *action), - - TP_ARGS(task, action) - -); +DEFINE_RPC_RUNNING_EVENT(begin); +DEFINE_RPC_RUNNING_EVENT(run_action); +DEFINE_RPC_RUNNING_EVENT(complete); DECLARE_EVENT_CLASS(rpc_task_queued, @@ -195,22 +158,16 @@ DECLARE_EVENT_CLASS(rpc_task_queued, __get_str(q_name) ) ); +#define DEFINE_RPC_QUEUED_EVENT(name) \ + DEFINE_EVENT(rpc_task_queued, rpc_task_##name, \ + TP_PROTO( \ + const struct rpc_task *task, \ + const struct rpc_wait_queue *q \ + ), \ + TP_ARGS(task, q)) -DEFINE_EVENT(rpc_task_queued, rpc_task_sleep, - - TP_PROTO(const struct rpc_task *task, const struct rpc_wait_queue *q), - - TP_ARGS(task, q) - -); - -DEFINE_EVENT(rpc_task_queued, rpc_task_wakeup, - - TP_PROTO(const struct rpc_task *task, const struct rpc_wait_queue *q), - - TP_ARGS(task, q) - -); +DEFINE_RPC_QUEUED_EVENT(sleep); +DEFINE_RPC_QUEUED_EVENT(wakeup); TRACE_EVENT(rpc_stats_latency, @@ -410,7 +367,11 @@ DEFINE_RPC_SOCKET_EVENT(rpc_socket_close); DEFINE_RPC_SOCKET_EVENT(rpc_socket_shutdown); DECLARE_EVENT_CLASS(rpc_xprt_event, - TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), + TP_PROTO( + const struct rpc_xprt *xprt, + __be32 xid, + int status + ), TP_ARGS(xprt, xid, status), @@ -432,22 +393,19 @@ DECLARE_EVENT_CLASS(rpc_xprt_event, __get_str(port), __entry->xid, __entry->status) ); +#define DEFINE_RPC_XPRT_EVENT(name) \ + DEFINE_EVENT(rpc_xprt_event, xprt_##name, \ + TP_PROTO( \ + const struct rpc_xprt *xprt, \ + __be32 xid, \ + int status \ + ), \ + TP_ARGS(xprt, xid, status)) -DEFINE_EVENT(rpc_xprt_event, xprt_timer, - TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), - TP_ARGS(xprt, xid, status)); - -DEFINE_EVENT(rpc_xprt_event, xprt_lookup_rqst, - TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), - TP_ARGS(xprt, xid, status)); - -DEFINE_EVENT(rpc_xprt_event, xprt_transmit, - TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), - TP_ARGS(xprt, xid, status)); - -DEFINE_EVENT(rpc_xprt_event, xprt_complete_rqst, - TP_PROTO(struct rpc_xprt *xprt, __be32 xid, int status), - TP_ARGS(xprt, xid, status)); +DEFINE_RPC_XPRT_EVENT(timer); +DEFINE_RPC_XPRT_EVENT(lookup_rqst); +DEFINE_RPC_XPRT_EVENT(transmit); +DEFINE_RPC_XPRT_EVENT(complete_rqst); TRACE_EVENT(xprt_ping, TP_PROTO(const struct rpc_xprt *xprt, int status), @@ -569,7 +527,8 @@ TRACE_EVENT(svc_process, __field(u32, vers) __field(u32, proc) __string(service, name) - __string(addr, rqst->rq_xprt->xpt_remotebuf) + __string(addr, rqst->rq_xprt ? + rqst->rq_xprt->xpt_remotebuf : "(null)") ), TP_fast_assign( @@ -577,7 +536,8 @@ TRACE_EVENT(svc_process, __entry->vers = rqst->rq_vers; __entry->proc = rqst->rq_proc; __assign_str(service, name); - __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); + __assign_str(addr, rqst->rq_xprt ? + rqst->rq_xprt->xpt_remotebuf : "(null)"); ), TP_printk("addr=%s xid=0x%08x service=%s vers=%u proc=%u", @@ -587,7 +547,9 @@ TRACE_EVENT(svc_process, DECLARE_EVENT_CLASS(svc_rqst_event, - TP_PROTO(struct svc_rqst *rqst), + TP_PROTO( + const struct svc_rqst *rqst + ), TP_ARGS(rqst), @@ -607,14 +569,15 @@ DECLARE_EVENT_CLASS(svc_rqst_event, __get_str(addr), __entry->xid, show_rqstp_flags(__entry->flags)) ); +#define DEFINE_SVC_RQST_EVENT(name) \ + DEFINE_EVENT(svc_rqst_event, svc_##name, \ + TP_PROTO( \ + const struct svc_rqst *rqst \ + ), \ + TP_ARGS(rqst)) -DEFINE_EVENT(svc_rqst_event, svc_defer, - TP_PROTO(struct svc_rqst *rqst), - TP_ARGS(rqst)); - -DEFINE_EVENT(svc_rqst_event, svc_drop, - TP_PROTO(struct svc_rqst *rqst), - TP_ARGS(rqst)); +DEFINE_SVC_RQST_EVENT(defer); +DEFINE_SVC_RQST_EVENT(drop); DECLARE_EVENT_CLASS(svc_rqst_status, @@ -801,7 +764,9 @@ TRACE_EVENT(svc_stats_latency, ); DECLARE_EVENT_CLASS(svc_deferred_event, - TP_PROTO(struct svc_deferred_req *dr), + TP_PROTO( + const struct svc_deferred_req *dr + ), TP_ARGS(dr), @@ -818,13 +783,16 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_printk("addr=%s xid=0x%08x", __get_str(addr), __entry->xid) ); +#define DEFINE_SVC_DEFERRED_EVENT(name) \ + DEFINE_EVENT(svc_deferred_event, svc_##name##_deferred, \ + TP_PROTO( \ + const struct svc_deferred_req *dr \ + ), \ + TP_ARGS(dr)) + +DEFINE_SVC_DEFERRED_EVENT(drop); +DEFINE_SVC_DEFERRED_EVENT(revisit); -DEFINE_EVENT(svc_deferred_event, svc_drop_deferred, - TP_PROTO(struct svc_deferred_req *dr), - TP_ARGS(dr)); -DEFINE_EVENT(svc_deferred_event, svc_revisit_deferred, - TP_PROTO(struct svc_deferred_req *dr), - TP_ARGS(dr)); #endif /* _TRACE_SUNRPC_H */ #include <trace/define_trace.h> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 9efc0e73d50b..90734aa5aa36 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -15,11 +15,13 @@ #define SECCOMP_SET_MODE_STRICT 0 #define SECCOMP_SET_MODE_FILTER 1 #define SECCOMP_GET_ACTION_AVAIL 2 +#define SECCOMP_GET_NOTIF_SIZES 3 /* Valid flags for SECCOMP_SET_MODE_FILTER */ -#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) -#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) -#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) +#define SECCOMP_FILTER_FLAG_LOG (1UL << 1) +#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) /* * All BPF programs must return a 32-bit value. @@ -35,6 +37,7 @@ #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_USER_NOTIF 0x7fc00000U /* notifies userspace */ #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 */ @@ -60,4 +63,35 @@ struct seccomp_data { __u64 args[6]; }; +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) #endif /* _UAPI_LINUX_SECCOMP_H */ diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 84c3de89696a..40d028eed645 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -11,94 +11,9 @@ * device configuration. */ +#include <linux/vhost_types.h> #include <linux/types.h> -#include <linux/compiler.h> #include <linux/ioctl.h> -#include <linux/virtio_config.h> -#include <linux/virtio_ring.h> - -struct vhost_vring_state { - unsigned int index; - unsigned int num; -}; - -struct vhost_vring_file { - unsigned int index; - int fd; /* Pass -1 to unbind from file. */ - -}; - -struct vhost_vring_addr { - unsigned int index; - /* Option flags. */ - unsigned int flags; - /* Flag values: */ - /* Whether log address is valid. If set enables logging. */ -#define VHOST_VRING_F_LOG 0 - - /* Start of array of descriptors (virtually contiguous) */ - __u64 desc_user_addr; - /* Used structure address. Must be 32 bit aligned */ - __u64 used_user_addr; - /* Available structure address. Must be 16 bit aligned */ - __u64 avail_user_addr; - /* Logging support. */ - /* Log writes to used structure, at offset calculated from specified - * address. Address must be 32 bit aligned. */ - __u64 log_guest_addr; -}; - -/* no alignment requirement */ -struct vhost_iotlb_msg { - __u64 iova; - __u64 size; - __u64 uaddr; -#define VHOST_ACCESS_RO 0x1 -#define VHOST_ACCESS_WO 0x2 -#define VHOST_ACCESS_RW 0x3 - __u8 perm; -#define VHOST_IOTLB_MISS 1 -#define VHOST_IOTLB_UPDATE 2 -#define VHOST_IOTLB_INVALIDATE 3 -#define VHOST_IOTLB_ACCESS_FAIL 4 - __u8 type; -}; - -#define VHOST_IOTLB_MSG 0x1 -#define VHOST_IOTLB_MSG_V2 0x2 - -struct vhost_msg { - int type; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_msg_v2 { - __u32 type; - __u32 reserved; - union { - struct vhost_iotlb_msg iotlb; - __u8 padding[64]; - }; -}; - -struct vhost_memory_region { - __u64 guest_phys_addr; - __u64 memory_size; /* bytes */ - __u64 userspace_addr; - __u64 flags_padding; /* No flags are currently specified. */ -}; - -/* All region addresses and sizes must be 4K aligned. */ -#define VHOST_PAGE_SIZE 0x1000 - -struct vhost_memory { - __u32 nregions; - __u32 padding; - struct vhost_memory_region regions[0]; -}; /* ioctls */ @@ -186,31 +101,7 @@ struct vhost_memory { * device. This can be used to stop the ring (e.g. for migration). */ #define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file) -/* Feature bits */ -/* Log all write descriptors. Can be changed while device is active. */ -#define VHOST_F_LOG_ALL 26 -/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ -#define VHOST_NET_F_VIRTIO_NET_HDR 27 - -/* VHOST_SCSI specific definitions */ - -/* - * Used by QEMU userspace to ensure a consistent vhost-scsi ABI. - * - * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate + - * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage - * ABI Rev 1: January 2013. Ignore vhost_tpgt filed in struct vhost_scsi_target. - * All the targets under vhost_wwpn can be seen and used by guset. - */ - -#define VHOST_SCSI_ABI_VERSION 1 - -struct vhost_scsi_target { - int abi_version; - char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */ - unsigned short vhost_tpgt; - unsigned short reserved; -}; +/* VHOST_SCSI specific defines */ #define VHOST_SCSI_SET_ENDPOINT _IOW(VHOST_VIRTIO, 0x40, struct vhost_scsi_target) #define VHOST_SCSI_CLEAR_ENDPOINT _IOW(VHOST_VIRTIO, 0x41, struct vhost_scsi_target) diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h new file mode 100644 index 000000000000..c907290ff065 --- /dev/null +++ b/include/uapi/linux/vhost_types.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_VHOST_TYPES_H +#define _LINUX_VHOST_TYPES_H +/* Userspace interface for in-kernel virtio accelerators. */ + +/* vhost is used to reduce the number of system calls involved in virtio. + * + * Existing virtio net code is used in the guest without modification. + * + * This header includes interface used by userspace hypervisor for + * device configuration. + */ + +#include <linux/types.h> +#include <linux/compiler.h> +#include <linux/virtio_config.h> +#include <linux/virtio_ring.h> + +struct vhost_vring_state { + unsigned int index; + unsigned int num; +}; + +struct vhost_vring_file { + unsigned int index; + int fd; /* Pass -1 to unbind from file. */ + +}; + +struct vhost_vring_addr { + unsigned int index; + /* Option flags. */ + unsigned int flags; + /* Flag values: */ + /* Whether log address is valid. If set enables logging. */ +#define VHOST_VRING_F_LOG 0 + + /* Start of array of descriptors (virtually contiguous) */ + __u64 desc_user_addr; + /* Used structure address. Must be 32 bit aligned */ + __u64 used_user_addr; + /* Available structure address. Must be 16 bit aligned */ + __u64 avail_user_addr; + /* Logging support. */ + /* Log writes to used structure, at offset calculated from specified + * address. Address must be 32 bit aligned. */ + __u64 log_guest_addr; +}; + +/* no alignment requirement */ +struct vhost_iotlb_msg { + __u64 iova; + __u64 size; + __u64 uaddr; +#define VHOST_ACCESS_RO 0x1 +#define VHOST_ACCESS_WO 0x2 +#define VHOST_ACCESS_RW 0x3 + __u8 perm; +#define VHOST_IOTLB_MISS 1 +#define VHOST_IOTLB_UPDATE 2 +#define VHOST_IOTLB_INVALIDATE 3 +#define VHOST_IOTLB_ACCESS_FAIL 4 + __u8 type; +}; + +#define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 + +struct vhost_msg { + int type; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + +struct vhost_memory_region { + __u64 guest_phys_addr; + __u64 memory_size; /* bytes */ + __u64 userspace_addr; + __u64 flags_padding; /* No flags are currently specified. */ +}; + +/* All region addresses and sizes must be 4K aligned. */ +#define VHOST_PAGE_SIZE 0x1000 + +struct vhost_memory { + __u32 nregions; + __u32 padding; + struct vhost_memory_region regions[0]; +}; + +/* VHOST_SCSI specific definitions */ + +/* + * Used by QEMU userspace to ensure a consistent vhost-scsi ABI. + * + * ABI Rev 0: July 2012 version starting point for v3.6-rc merge candidate + + * RFC-v2 vhost-scsi userspace. Add GET_ABI_VERSION ioctl usage + * ABI Rev 1: January 2013. Ignore vhost_tpgt field in struct vhost_scsi_target. + * All the targets under vhost_wwpn can be seen and used by guset. + */ + +#define VHOST_SCSI_ABI_VERSION 1 + +struct vhost_scsi_target { + int abi_version; + char vhost_wwpn[224]; /* TRANSPORT_IQN_LEN */ + unsigned short vhost_tpgt; + unsigned short reserved; +}; + +/* Feature bits */ +/* Log all write descriptors. Can be changed while device is active. */ +#define VHOST_F_LOG_ALL 26 +/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ +#define VHOST_NET_F_VIRTIO_NET_HDR 27 + +#endif diff --git a/include/uapi/linux/virtio_blk.h b/include/uapi/linux/virtio_blk.h index 9ebe4d968dd5..0f99d7b49ede 100644 --- a/include/uapi/linux/virtio_blk.h +++ b/include/uapi/linux/virtio_blk.h @@ -38,6 +38,8 @@ #define VIRTIO_BLK_F_BLK_SIZE 6 /* Block size of disk is available*/ #define VIRTIO_BLK_F_TOPOLOGY 10 /* Topology information is available */ #define VIRTIO_BLK_F_MQ 12 /* support more than one vq */ +#define VIRTIO_BLK_F_DISCARD 13 /* DISCARD is supported */ +#define VIRTIO_BLK_F_WRITE_ZEROES 14 /* WRITE ZEROES is supported */ /* Legacy feature bits */ #ifndef VIRTIO_BLK_NO_LEGACY @@ -86,6 +88,39 @@ struct virtio_blk_config { /* number of vqs, only available when VIRTIO_BLK_F_MQ is set */ __u16 num_queues; + + /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */ + /* + * The maximum discard sectors (in 512-byte sectors) for + * one segment. + */ + __u32 max_discard_sectors; + /* + * The maximum number of discard segments in a + * discard command. + */ + __u32 max_discard_seg; + /* Discard commands must be aligned to this number of sectors. */ + __u32 discard_sector_alignment; + + /* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */ + /* + * The maximum number of write zeroes sectors (in 512-byte sectors) in + * one segment. + */ + __u32 max_write_zeroes_sectors; + /* + * The maximum number of segments in a write zeroes + * command. + */ + __u32 max_write_zeroes_seg; + /* + * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the + * deallocation of one or more of the sectors. + */ + __u8 write_zeroes_may_unmap; + + __u8 unused1[3]; } __attribute__((packed)); /* @@ -114,6 +149,12 @@ struct virtio_blk_config { /* Get device ID command */ #define VIRTIO_BLK_T_GET_ID 8 +/* Discard command */ +#define VIRTIO_BLK_T_DISCARD 11 + +/* Write zeroes command */ +#define VIRTIO_BLK_T_WRITE_ZEROES 13 + #ifndef VIRTIO_BLK_NO_LEGACY /* Barrier before this op. */ #define VIRTIO_BLK_T_BARRIER 0x80000000 @@ -133,6 +174,19 @@ struct virtio_blk_outhdr { __virtio64 sector; }; +/* Unmap this range (only valid for write zeroes command) */ +#define VIRTIO_BLK_WRITE_ZEROES_FLAG_UNMAP 0x00000001 + +/* Discard/write zeroes range for each request. */ +struct virtio_blk_discard_write_zeroes { + /* discard/write zeroes start sector */ + __le64 sector; + /* number of discard/write zeroes sectors */ + __le32 num_sectors; + /* flags for this range */ + __le32 flags; +}; + #ifndef VIRTIO_BLK_NO_LEGACY struct virtio_scsi_inhdr { __virtio32 errors; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 38de580abcc2..f908b9356025 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -54,6 +54,7 @@ #define DST regs[insn->dst_reg] #define SRC regs[insn->src_reg] #define FP regs[BPF_REG_FP] +#define AX regs[BPF_REG_AX] #define ARG1 regs[BPF_REG_ARG1] #define CTX regs[BPF_REG_CTX] #define IMM insn->imm @@ -857,6 +858,26 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, BUILD_BUG_ON(BPF_REG_AX + 1 != MAX_BPF_JIT_REG); BUILD_BUG_ON(MAX_BPF_REG + 1 != MAX_BPF_JIT_REG); + /* Constraints on AX register: + * + * AX register is inaccessible from user space. It is mapped in + * all JITs, and used here for constant blinding rewrites. It is + * typically "stateless" meaning its contents are only valid within + * the executed instruction, but not across several instructions. + * There are a few exceptions however which are further detailed + * below. + * + * Constant blinding is only used by JITs, not in the interpreter. + * The interpreter uses AX in some occasions as a local temporary + * register e.g. in DIV or MOD instructions. + * + * In restricted circumstances, the verifier can also use the AX + * register for rewrites as long as they do not interfere with + * the above cases! + */ + if (from->dst_reg == BPF_REG_AX || from->src_reg == BPF_REG_AX) + goto out; + if (from->imm == 0 && (from->code == (BPF_ALU | BPF_MOV | BPF_K) || from->code == (BPF_ALU64 | BPF_MOV | BPF_K))) { @@ -1188,7 +1209,6 @@ bool bpf_opcode_in_insntable(u8 code) */ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) { - u64 tmp; #define BPF_INSN_2_LBL(x, y) [BPF_##x | BPF_##y] = &&x##_##y #define BPF_INSN_3_LBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = &&x##_##y##_##z static const void *jumptable[256] = { @@ -1268,36 +1288,36 @@ select_insn: (*(s64 *) &DST) >>= IMM; CONT; ALU64_MOD_X: - div64_u64_rem(DST, SRC, &tmp); - DST = tmp; + div64_u64_rem(DST, SRC, &AX); + DST = AX; CONT; ALU_MOD_X: - tmp = (u32) DST; - DST = do_div(tmp, (u32) SRC); + AX = (u32) DST; + DST = do_div(AX, (u32) SRC); CONT; ALU64_MOD_K: - div64_u64_rem(DST, IMM, &tmp); - DST = tmp; + div64_u64_rem(DST, IMM, &AX); + DST = AX; CONT; ALU_MOD_K: - tmp = (u32) DST; - DST = do_div(tmp, (u32) IMM); + AX = (u32) DST; + DST = do_div(AX, (u32) IMM); CONT; ALU64_DIV_X: DST = div64_u64(DST, SRC); CONT; ALU_DIV_X: - tmp = (u32) DST; - do_div(tmp, (u32) SRC); - DST = (u32) tmp; + AX = (u32) DST; + do_div(AX, (u32) SRC); + DST = (u32) AX; CONT; ALU64_DIV_K: DST = div64_u64(DST, IMM); CONT; ALU_DIV_K: - tmp = (u32) DST; - do_div(tmp, (u32) IMM); - DST = (u32) tmp; + AX = (u32) DST; + do_div(AX, (u32) IMM); + DST = (u32) AX; CONT; ALU_END_TO_BE: switch (IMM) { @@ -1553,7 +1573,7 @@ STACK_FRAME_NON_STANDARD(___bpf_prog_run); /* jump table */ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ - u64 regs[MAX_BPF_REG]; \ + u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ ARG1 = (u64) (unsigned long) ctx; \ @@ -1566,7 +1586,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \ const struct bpf_insn *insn) \ { \ u64 stack[stack_size / sizeof(u64)]; \ - u64 regs[MAX_BPF_REG]; \ + u64 regs[MAX_BPF_EXT_REG]; \ \ FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \ BPF_R1 = r1; \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 71d86e3024ae..f6bc62a9ee8e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -710,6 +710,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, free_func_state(dst_state->frame[i]); dst_state->frame[i] = NULL; } + dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; @@ -754,7 +755,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx, } static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, - int insn_idx, int prev_insn_idx) + int insn_idx, int prev_insn_idx, + bool speculative) { struct bpf_verifier_state *cur = env->cur_state; struct bpf_verifier_stack_elem *elem; @@ -772,6 +774,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env, err = copy_verifier_state(&elem->st, cur); if (err) goto err; + elem->st.speculative |= speculative; if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) { verbose(env, "BPF program is too complex\n"); goto err; @@ -1387,6 +1390,31 @@ static int check_stack_read(struct bpf_verifier_env *env, } } +static int check_stack_access(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + int off, int size) +{ + /* Stack accesses must be at a fixed offset, so that we + * can determine what type of data were returned. See + * check_stack_read(). + */ + if (!tnum_is_const(reg->var_off)) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); + verbose(env, "variable stack access var_off=%s off=%d size=%d", + tn_buf, off, size); + return -EACCES; + } + + if (off >= 0 || off < -MAX_BPF_STACK) { + verbose(env, "invalid stack off=%d size=%d\n", off, size); + return -EACCES; + } + + return 0; +} + /* check read/write into map element returned by bpf_map_lookup_elem() */ static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off, int size, bool zero_size_allowed) @@ -1418,13 +1446,17 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, */ if (env->log.level) print_verifier_state(env, state); + /* The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if (reg->smin_value < 0) { + if (reg->smin_value < 0 && + (reg->smin_value == S64_MIN || + (off + reg->smin_value != (s64)(s32)(off + reg->smin_value)) || + reg->smin_value + off < 0)) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1954,24 +1986,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } } else if (reg->type == PTR_TO_STACK) { - /* stack accesses must be at a fixed offset, so that we can - * determine what type of data were returned. - * See check_stack_read(). - */ - if (!tnum_is_const(reg->var_off)) { - char tn_buf[48]; - - tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable stack access var_off=%s off=%d size=%d", - tn_buf, off, size); - return -EACCES; - } off += reg->var_off.value; - if (off >= 0 || off < -MAX_BPF_STACK) { - verbose(env, "invalid stack off=%d size=%d\n", off, - size); - return -EACCES; - } + err = check_stack_access(env, reg, off, size); + if (err) + return err; state = func(env, reg); err = update_stack_depth(env, state, off); @@ -3052,6 +3070,102 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env, return true; } +static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) +{ + return &env->insn_aux_data[env->insn_idx]; +} + +static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, + u32 *ptr_limit, u8 opcode, bool off_is_neg) +{ + bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || + (opcode == BPF_SUB && !off_is_neg); + u32 off; + + switch (ptr_reg->type) { + case PTR_TO_STACK: + off = ptr_reg->off + ptr_reg->var_off.value; + if (mask_to_left) + *ptr_limit = MAX_BPF_STACK + off; + else + *ptr_limit = -off; + return 0; + case PTR_TO_MAP_VALUE: + if (mask_to_left) { + *ptr_limit = ptr_reg->umax_value + ptr_reg->off; + } else { + off = ptr_reg->smin_value + ptr_reg->off; + *ptr_limit = ptr_reg->map_ptr->value_size - off; + } + return 0; + default: + return -EINVAL; + } +} + +static int sanitize_ptr_alu(struct bpf_verifier_env *env, + struct bpf_insn *insn, + const struct bpf_reg_state *ptr_reg, + struct bpf_reg_state *dst_reg, + bool off_is_neg) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_insn_aux_data *aux = cur_aux(env); + bool ptr_is_dst_reg = ptr_reg == dst_reg; + u8 opcode = BPF_OP(insn->code); + u32 alu_state, alu_limit; + struct bpf_reg_state tmp; + bool ret; + + if (env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K) + return 0; + + /* We already marked aux for masking from non-speculative + * paths, thus we got here in the first place. We only care + * to explore bad access from here. + */ + if (vstate->speculative) + goto do_sim; + + alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; + alu_state |= ptr_is_dst_reg ? + BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + + if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) + return 0; + + /* If we arrived here from different branches with different + * limits to sanitize, then this won't work. + */ + if (aux->alu_state && + (aux->alu_state != alu_state || + aux->alu_limit != alu_limit)) + return -EACCES; + + /* Corresponding fixup done in fixup_bpf_calls(). */ + aux->alu_state = alu_state; + aux->alu_limit = alu_limit; + +do_sim: + /* Simulate and find potential out-of-bounds access under + * speculative execution from truncation as a result of + * masking when off was not within expected range. If off + * sits in dst, then we temporarily need to move ptr there + * to simulate dst (== 0) +/-= ptr. Needed, for example, + * for cases where we use K-based arithmetic in one direction + * and truncated reg-based in the other in order to explore + * bad access. + */ + if (!ptr_is_dst_reg) { + tmp = *dst_reg; + *dst_reg = *ptr_reg; + } + ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); + if (!ptr_is_dst_reg) + *dst_reg = tmp; + return !ret ? -EFAULT : 0; +} + /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a @@ -3070,8 +3184,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; + u32 dst = insn->dst_reg, src = insn->src_reg; u8 opcode = BPF_OP(insn->code); - u32 dst = insn->dst_reg; + int ret; dst_reg = ®s[dst]; @@ -3104,6 +3219,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; + case PTR_TO_MAP_VALUE: + if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { + verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", + off_reg == dst_reg ? dst : src); + return -EACCES; + } + /* fall-through */ default: break; } @@ -3120,6 +3242,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, switch (opcode) { case BPF_ADD: + ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); + if (ret < 0) { + verbose(env, "R%d tried to add from different maps or paths\n", dst); + return ret; + } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ @@ -3170,6 +3297,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } break; case BPF_SUB: + ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); + if (ret < 0) { + verbose(env, "R%d tried to sub from different maps or paths\n", dst); + return ret; + } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", @@ -3249,6 +3381,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); + + /* For unprivileged we require that resulting offset must be in bounds + * in order to be able to sanitize access later on. + */ + if (!env->allow_ptr_leaks) { + if (dst_reg->type == PTR_TO_MAP_VALUE && + check_map_access(env, dst, dst_reg->off, 1, false)) { + verbose(env, "R%d pointer arithmetic of map value goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } else if (dst_reg->type == PTR_TO_STACK && + check_stack_access(env, dst_reg, dst_reg->off + + dst_reg->var_off.value, 1)) { + verbose(env, "R%d stack pointer arithmetic goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + } + return 0; } @@ -4348,7 +4499,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, } } - other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx); + other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, + false); if (!other_branch) return -EFAULT; other_branch_regs = other_branch->frame[other_branch->curframe]->regs; @@ -5458,6 +5610,12 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->curframe != cur->curframe) return false; + /* Verification state from speculative execution simulation + * must never prune a non-speculative execution one. + */ + if (old->speculative && !cur->speculative) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -5650,7 +5808,6 @@ static int do_check(struct bpf_verifier_env *env) struct bpf_insn *insns = env->prog->insnsi; struct bpf_reg_state *regs; int insn_cnt = env->prog->len, i; - int insn_idx, prev_insn_idx = 0; int insn_processed = 0; bool do_print_state = false; @@ -5660,6 +5817,7 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; + state->speculative = false; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); @@ -5670,19 +5828,19 @@ static int do_check(struct bpf_verifier_env *env) BPF_MAIN_FUNC /* callsite */, 0 /* frameno */, 0 /* subprogno, zero == main subprog */); - insn_idx = 0; + for (;;) { struct bpf_insn *insn; u8 class; int err; - if (insn_idx >= insn_cnt) { + if (env->insn_idx >= insn_cnt) { verbose(env, "invalid insn idx %d insn_cnt %d\n", - insn_idx, insn_cnt); + env->insn_idx, insn_cnt); return -EFAULT; } - insn = &insns[insn_idx]; + insn = &insns[env->insn_idx]; class = BPF_CLASS(insn->code); if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) { @@ -5692,17 +5850,19 @@ static int do_check(struct bpf_verifier_env *env) return -E2BIG; } - err = is_state_visited(env, insn_idx); + err = is_state_visited(env, env->insn_idx); if (err < 0) return err; if (err == 1) { /* found equivalent state, can prune the search */ if (env->log.level) { if (do_print_state) - verbose(env, "\nfrom %d to %d: safe\n", - prev_insn_idx, insn_idx); + verbose(env, "\nfrom %d to %d%s: safe\n", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); else - verbose(env, "%d: safe\n", insn_idx); + verbose(env, "%d: safe\n", env->insn_idx); } goto process_bpf_exit; } @@ -5715,10 +5875,12 @@ static int do_check(struct bpf_verifier_env *env) if (env->log.level > 1 || (env->log.level && do_print_state)) { if (env->log.level > 1) - verbose(env, "%d:", insn_idx); + verbose(env, "%d:", env->insn_idx); else - verbose(env, "\nfrom %d to %d:", - prev_insn_idx, insn_idx); + verbose(env, "\nfrom %d to %d%s:", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); print_verifier_state(env, state->frame[state->curframe]); do_print_state = false; } @@ -5729,20 +5891,20 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; - verbose_linfo(env, insn_idx, "; "); - verbose(env, "%d: ", insn_idx); + verbose_linfo(env, env->insn_idx, "; "); + verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); } if (bpf_prog_is_dev_bound(env->prog->aux)) { - err = bpf_prog_offload_verify_insn(env, insn_idx, - prev_insn_idx); + err = bpf_prog_offload_verify_insn(env, env->insn_idx, + env->prev_insn_idx); if (err) return err; } regs = cur_regs(env); - env->insn_aux_data[insn_idx].seen = true; + env->insn_aux_data[env->insn_idx].seen = true; if (class == BPF_ALU || class == BPF_ALU64) { err = check_alu_op(env, insn); @@ -5768,13 +5930,13 @@ static int do_check(struct bpf_verifier_env *env) /* check that memory (src_reg + off) is readable, * the state of dst_reg will be updated by this func */ - err = check_mem_access(env, insn_idx, insn->src_reg, insn->off, - BPF_SIZE(insn->code), BPF_READ, - insn->dst_reg, false); + err = check_mem_access(env, env->insn_idx, insn->src_reg, + insn->off, BPF_SIZE(insn->code), + BPF_READ, insn->dst_reg, false); if (err) return err; - prev_src_type = &env->insn_aux_data[insn_idx].ptr_type; + prev_src_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_src_type == NOT_INIT) { /* saw a valid insn @@ -5799,10 +5961,10 @@ static int do_check(struct bpf_verifier_env *env) enum bpf_reg_type *prev_dst_type, dst_reg_type; if (BPF_MODE(insn->code) == BPF_XADD) { - err = check_xadd(env, insn_idx, insn); + err = check_xadd(env, env->insn_idx, insn); if (err) return err; - insn_idx++; + env->insn_idx++; continue; } @@ -5818,13 +5980,13 @@ static int do_check(struct bpf_verifier_env *env) dst_reg_type = regs[insn->dst_reg].type; /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, - insn->src_reg, false); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_WRITE, insn->src_reg, false); if (err) return err; - prev_dst_type = &env->insn_aux_data[insn_idx].ptr_type; + prev_dst_type = &env->insn_aux_data[env->insn_idx].ptr_type; if (*prev_dst_type == NOT_INIT) { *prev_dst_type = dst_reg_type; @@ -5852,9 +6014,9 @@ static int do_check(struct bpf_verifier_env *env) } /* check that memory (dst_reg + off) is writeable */ - err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off, - BPF_SIZE(insn->code), BPF_WRITE, - -1, false); + err = check_mem_access(env, env->insn_idx, insn->dst_reg, + insn->off, BPF_SIZE(insn->code), + BPF_WRITE, -1, false); if (err) return err; @@ -5872,9 +6034,9 @@ static int do_check(struct bpf_verifier_env *env) } if (insn->src_reg == BPF_PSEUDO_CALL) - err = check_func_call(env, insn, &insn_idx); + err = check_func_call(env, insn, &env->insn_idx); else - err = check_helper_call(env, insn->imm, insn_idx); + err = check_helper_call(env, insn->imm, env->insn_idx); if (err) return err; @@ -5887,7 +6049,7 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } - insn_idx += insn->off + 1; + env->insn_idx += insn->off + 1; continue; } else if (opcode == BPF_EXIT) { @@ -5901,8 +6063,8 @@ static int do_check(struct bpf_verifier_env *env) if (state->curframe) { /* exit from nested function */ - prev_insn_idx = insn_idx; - err = prepare_func_exit(env, &insn_idx); + env->prev_insn_idx = env->insn_idx; + err = prepare_func_exit(env, &env->insn_idx); if (err) return err; do_print_state = true; @@ -5932,7 +6094,8 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; process_bpf_exit: - err = pop_stack(env, &prev_insn_idx, &insn_idx); + err = pop_stack(env, &env->prev_insn_idx, + &env->insn_idx); if (err < 0) { if (err != -ENOENT) return err; @@ -5942,7 +6105,7 @@ process_bpf_exit: continue; } } else { - err = check_cond_jmp_op(env, insn, &insn_idx); + err = check_cond_jmp_op(env, insn, &env->insn_idx); if (err) return err; } @@ -5959,8 +6122,8 @@ process_bpf_exit: if (err) return err; - insn_idx++; - env->insn_aux_data[insn_idx].seen = true; + env->insn_idx++; + env->insn_aux_data[env->insn_idx].seen = true; } else { verbose(env, "invalid BPF_LD mode\n"); return -EINVAL; @@ -5970,7 +6133,7 @@ process_bpf_exit: return -EINVAL; } - insn_idx++; + env->insn_idx++; } verbose(env, "processed %d insns (limit %d), stack depth ", @@ -6709,6 +6872,57 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) || + insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) { + const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X; + const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X; + struct bpf_insn insn_buf[16]; + struct bpf_insn *patch = &insn_buf[0]; + bool issrc, isneg; + u32 off_reg; + + aux = &env->insn_aux_data[i + delta]; + if (!aux->alu_state) + continue; + + isneg = aux->alu_state & BPF_ALU_NEG_VALUE; + issrc = (aux->alu_state & BPF_ALU_SANITIZE) == + BPF_ALU_SANITIZE_SRC; + + off_reg = issrc ? insn->src_reg : insn->dst_reg; + if (isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); + *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); + *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); + *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63); + if (issrc) { + *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX, + off_reg); + insn->src_reg = BPF_REG_AX; + } else { + *patch++ = BPF_ALU64_REG(BPF_AND, off_reg, + BPF_REG_AX); + } + if (isneg) + insn->code = insn->code == code_add ? + code_sub : code_add; + *patch++ = *insn; + if (issrc && isneg) + *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); + cnt = patch - insn_buf; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) diff --git a/kernel/cred.c b/kernel/cred.c index ecf03657e71c..21f4a97085b4 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/binfmts.h> #include <linux/cn_proc.h> +#include <linux/uidgid.h> #if 0 #define kdebug(FMT, ...) \ @@ -194,11 +195,12 @@ const struct cred *get_task_cred(struct task_struct *task) do { cred = __task_cred((task)); BUG_ON(!cred); - } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage)); + } while (!get_cred_rcu(cred)); rcu_read_unlock(); return cred; } +EXPORT_SYMBOL(get_task_cred); /* * Allocate blank credentials, such that the credentials can be filled in at a @@ -564,6 +566,60 @@ void revert_creds(const struct cred *old) } EXPORT_SYMBOL(revert_creds); +/** + * cred_fscmp - Compare two credentials with respect to filesystem access. + * @a: The first credential + * @b: The second credential + * + * cred_cmp() will return zero if both credentials have the same + * fsuid, fsgid, and supplementary groups. That is, if they will both + * provide the same access to files based on mode/uid/gid. + * If the credentials are different, then either -1 or 1 will + * be returned depending on whether @a comes before or after @b + * respectively in an arbitrary, but stable, ordering of credentials. + * + * Return: -1, 0, or 1 depending on comparison + */ +int cred_fscmp(const struct cred *a, const struct cred *b) +{ + struct group_info *ga, *gb; + int g; + + if (a == b) + return 0; + if (uid_lt(a->fsuid, b->fsuid)) + return -1; + if (uid_gt(a->fsuid, b->fsuid)) + return 1; + + if (gid_lt(a->fsgid, b->fsgid)) + return -1; + if (gid_gt(a->fsgid, b->fsgid)) + return 1; + + ga = a->group_info; + gb = b->group_info; + if (ga == gb) + return 0; + if (ga == NULL) + return -1; + if (gb == NULL) + return 1; + if (ga->ngroups < gb->ngroups) + return -1; + if (ga->ngroups > gb->ngroups) + return 1; + + for (g = 0; g < ga->ngroups; g++) { + if (gid_lt(ga->gid[g], gb->gid[g])) + return -1; + if (gid_gt(ga->gid[g], gb->gid[g])) + return 1; + } + return 0; +} +EXPORT_SYMBOL(cred_fscmp); + /* * initialise the credentials stuff */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index f2ae2324c232..d7f538847b84 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -33,12 +33,74 @@ #endif #ifdef CONFIG_SECCOMP_FILTER +#include <linux/file.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/tracehook.h> #include <linux/uaccess.h> +#include <linux/anon_inodes.h> + +enum notify_state { + SECCOMP_NOTIFY_INIT, + SECCOMP_NOTIFY_SENT, + SECCOMP_NOTIFY_REPLIED, +}; + +struct seccomp_knotif { + /* The struct pid of the task whose filter triggered the notification */ + struct task_struct *task; + + /* The "cookie" for this request; this is unique for this filter. */ + u64 id; + + /* + * The seccomp data. This pointer is valid the entire time this + * notification is active, since it comes from __seccomp_filter which + * eclipses the entire lifecycle here. + */ + const struct seccomp_data *data; + + /* + * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a + * struct seccomp_knotif is created and starts out in INIT. Once the + * handler reads the notification off of an FD, it transitions to SENT. + * If a signal is received the state transitions back to INIT and + * another message is sent. When the userspace handler replies, state + * transitions to REPLIED. + */ + enum notify_state state; + + /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ + int error; + long val; + + /* Signals when this has entered SECCOMP_NOTIFY_REPLIED */ + struct completion ready; + + struct list_head list; +}; + +/** + * struct notification - container for seccomp userspace notifications. Since + * most seccomp filters will not have notification listeners attached and this + * structure is fairly large, we store the notification-specific stuff in a + * separate structure. + * + * @request: A semaphore that users of this notification can wait on for + * changes. Actual reads and writes are still controlled with + * filter->notify_lock. + * @next_id: The id of the next request. + * @notifications: A list of struct seccomp_knotif elements. + * @wqh: A wait queue for poll. + */ +struct notification { + struct semaphore request; + u64 next_id; + struct list_head notifications; + wait_queue_head_t wqh; +}; /** * struct seccomp_filter - container for seccomp BPF programs @@ -50,6 +112,8 @@ * @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 + * @notif: the struct that holds all notification related information + * @notify_lock: A lock for all notification-related accesses. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting @@ -66,6 +130,8 @@ struct seccomp_filter { bool log; struct seccomp_filter *prev; struct bpf_prog *prog; + struct notification *notif; + struct mutex notify_lock; }; /* Limit any path through the tree to 256KB worth of instructions. */ @@ -188,7 +254,6 @@ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { - struct seccomp_data sd_local; u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = @@ -198,11 +263,6 @@ static u32 seccomp_run_filters(const struct seccomp_data *sd, if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; - if (!sd) { - populate_seccomp_data(&sd_local); - sd = &sd_local; - } - /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). @@ -392,6 +452,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) if (!sfilter) return ERR_PTR(-ENOMEM); + mutex_init(&sfilter->notify_lock); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, seccomp_check_filter, save_orig); if (ret < 0) { @@ -485,7 +546,6 @@ static long seccomp_attach_filter(unsigned int flags, static void __get_seccomp_filter(struct seccomp_filter *filter) { - /* Reference count is bounded by the number of total processes. */ refcount_inc(&filter->usage); } @@ -556,11 +616,13 @@ static void seccomp_send_sigsys(int syscall, int reason) #define SECCOMP_LOG_TRACE (1 << 4) #define SECCOMP_LOG_LOG (1 << 5) #define SECCOMP_LOG_ALLOW (1 << 6) +#define SECCOMP_LOG_USER_NOTIF (1 << 7) static u32 seccomp_actions_logged = SECCOMP_LOG_KILL_PROCESS | SECCOMP_LOG_KILL_THREAD | SECCOMP_LOG_TRAP | SECCOMP_LOG_ERRNO | + SECCOMP_LOG_USER_NOTIF | SECCOMP_LOG_TRACE | SECCOMP_LOG_LOG; @@ -581,6 +643,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, case SECCOMP_RET_TRACE: log = requested && seccomp_actions_logged & SECCOMP_LOG_TRACE; break; + case SECCOMP_RET_USER_NOTIF: + log = requested && seccomp_actions_logged & SECCOMP_LOG_USER_NOTIF; + break; case SECCOMP_RET_LOG: log = seccomp_actions_logged & SECCOMP_LOG_LOG; break; @@ -652,12 +717,75 @@ void secure_computing_strict(int this_syscall) #else #ifdef CONFIG_SECCOMP_FILTER +static u64 seccomp_next_notify_id(struct seccomp_filter *filter) +{ + /* + * Note: overflow is ok here, the id just needs to be unique per + * filter. + */ + lockdep_assert_held(&filter->notify_lock); + return filter->notif->next_id++; +} + +static void seccomp_do_user_notification(int this_syscall, + struct seccomp_filter *match, + const struct seccomp_data *sd) +{ + int err; + long ret = 0; + struct seccomp_knotif n = {}; + + mutex_lock(&match->notify_lock); + err = -ENOSYS; + if (!match->notif) + goto out; + + n.task = current; + n.state = SECCOMP_NOTIFY_INIT; + n.data = sd; + n.id = seccomp_next_notify_id(match); + init_completion(&n.ready); + list_add(&n.list, &match->notif->notifications); + + up(&match->notif->request); + wake_up_poll(&match->notif->wqh, EPOLLIN | EPOLLRDNORM); + mutex_unlock(&match->notify_lock); + + /* + * This is where we wait for a reply from userspace. + */ + err = wait_for_completion_interruptible(&n.ready); + mutex_lock(&match->notify_lock); + if (err == 0) { + ret = n.val; + err = n.error; + } + + /* + * Note that it's possible the listener died in between the time when + * we were notified of a respons (or a signal) and when we were able to + * re-acquire the lock, so only delete from the list if the + * notification actually exists. + * + * Also note that this test is only valid because there's no way to + * *reattach* to a notifier right now. If one is added, we'll need to + * keep track of the notif itself and make sure they match here. + */ + if (match->notif) + list_del(&n.list); +out: + mutex_unlock(&match->notify_lock); + syscall_set_return_value(current, task_pt_regs(current), + err, ret); +} + static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, const bool recheck_after_trace) { u32 filter_ret, action; struct seccomp_filter *match = NULL; int data; + struct seccomp_data sd_local; /* * Make sure that any changes to mode from another thread have @@ -665,6 +793,11 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, */ rmb(); + if (!sd) { + populate_seccomp_data(&sd_local); + sd = &sd_local; + } + filter_ret = seccomp_run_filters(sd, &match); data = filter_ret & SECCOMP_RET_DATA; action = filter_ret & SECCOMP_RET_ACTION_FULL; @@ -728,6 +861,10 @@ static int __seccomp_filter(int this_syscall, const struct seccomp_data *sd, return 0; + case SECCOMP_RET_USER_NOTIF: + seccomp_do_user_notification(this_syscall, match, sd); + goto skip; + case SECCOMP_RET_LOG: seccomp_log(this_syscall, 0, action, true); return 0; @@ -834,6 +971,262 @@ out: } #ifdef CONFIG_SECCOMP_FILTER +static int seccomp_notify_release(struct inode *inode, struct file *file) +{ + struct seccomp_filter *filter = file->private_data; + struct seccomp_knotif *knotif; + + mutex_lock(&filter->notify_lock); + + /* + * If this file is being closed because e.g. the task who owned it + * died, let's wake everyone up who was waiting on us. + */ + list_for_each_entry(knotif, &filter->notif->notifications, list) { + if (knotif->state == SECCOMP_NOTIFY_REPLIED) + continue; + + knotif->state = SECCOMP_NOTIFY_REPLIED; + knotif->error = -ENOSYS; + knotif->val = 0; + + complete(&knotif->ready); + } + + kfree(filter->notif); + filter->notif = NULL; + mutex_unlock(&filter->notify_lock); + __put_seccomp_filter(filter); + return 0; +} + +static long seccomp_notify_recv(struct seccomp_filter *filter, + void __user *buf) +{ + struct seccomp_knotif *knotif = NULL, *cur; + struct seccomp_notif unotif; + ssize_t ret; + + memset(&unotif, 0, sizeof(unotif)); + + ret = down_interruptible(&filter->notif->request); + if (ret < 0) + return ret; + + mutex_lock(&filter->notify_lock); + list_for_each_entry(cur, &filter->notif->notifications, list) { + if (cur->state == SECCOMP_NOTIFY_INIT) { + knotif = cur; + break; + } + } + + /* + * If we didn't find a notification, it could be that the task was + * interrupted by a fatal signal between the time we were woken and + * when we were able to acquire the rw lock. + */ + if (!knotif) { + ret = -ENOENT; + goto out; + } + + unotif.id = knotif->id; + unotif.pid = task_pid_vnr(knotif->task); + unotif.data = *(knotif->data); + + knotif->state = SECCOMP_NOTIFY_SENT; + wake_up_poll(&filter->notif->wqh, EPOLLOUT | EPOLLWRNORM); + ret = 0; +out: + mutex_unlock(&filter->notify_lock); + + if (ret == 0 && copy_to_user(buf, &unotif, sizeof(unotif))) { + ret = -EFAULT; + + /* + * Userspace screwed up. To make sure that we keep this + * notification alive, let's reset it back to INIT. It + * may have died when we released the lock, so we need to make + * sure it's still around. + */ + knotif = NULL; + mutex_lock(&filter->notify_lock); + list_for_each_entry(cur, &filter->notif->notifications, list) { + if (cur->id == unotif.id) { + knotif = cur; + break; + } + } + + if (knotif) { + knotif->state = SECCOMP_NOTIFY_INIT; + up(&filter->notif->request); + } + mutex_unlock(&filter->notify_lock); + } + + return ret; +} + +static long seccomp_notify_send(struct seccomp_filter *filter, + void __user *buf) +{ + struct seccomp_notif_resp resp = {}; + struct seccomp_knotif *knotif = NULL, *cur; + long ret; + + if (copy_from_user(&resp, buf, sizeof(resp))) + return -EFAULT; + + if (resp.flags) + return -EINVAL; + + ret = mutex_lock_interruptible(&filter->notify_lock); + if (ret < 0) + return ret; + + list_for_each_entry(cur, &filter->notif->notifications, list) { + if (cur->id == resp.id) { + knotif = cur; + break; + } + } + + if (!knotif) { + ret = -ENOENT; + goto out; + } + + /* Allow exactly one reply. */ + if (knotif->state != SECCOMP_NOTIFY_SENT) { + ret = -EINPROGRESS; + goto out; + } + + ret = 0; + knotif->state = SECCOMP_NOTIFY_REPLIED; + knotif->error = resp.error; + knotif->val = resp.val; + complete(&knotif->ready); +out: + mutex_unlock(&filter->notify_lock); + return ret; +} + +static long seccomp_notify_id_valid(struct seccomp_filter *filter, + void __user *buf) +{ + struct seccomp_knotif *knotif = NULL; + u64 id; + long ret; + + if (copy_from_user(&id, buf, sizeof(id))) + return -EFAULT; + + ret = mutex_lock_interruptible(&filter->notify_lock); + if (ret < 0) + return ret; + + ret = -ENOENT; + list_for_each_entry(knotif, &filter->notif->notifications, list) { + if (knotif->id == id) { + if (knotif->state == SECCOMP_NOTIFY_SENT) + ret = 0; + goto out; + } + } + +out: + mutex_unlock(&filter->notify_lock); + return ret; +} + +static long seccomp_notify_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + struct seccomp_filter *filter = file->private_data; + void __user *buf = (void __user *)arg; + + switch (cmd) { + case SECCOMP_IOCTL_NOTIF_RECV: + return seccomp_notify_recv(filter, buf); + case SECCOMP_IOCTL_NOTIF_SEND: + return seccomp_notify_send(filter, buf); + case SECCOMP_IOCTL_NOTIF_ID_VALID: + return seccomp_notify_id_valid(filter, buf); + default: + return -EINVAL; + } +} + +static __poll_t seccomp_notify_poll(struct file *file, + struct poll_table_struct *poll_tab) +{ + struct seccomp_filter *filter = file->private_data; + __poll_t ret = 0; + struct seccomp_knotif *cur; + + poll_wait(file, &filter->notif->wqh, poll_tab); + + if (mutex_lock_interruptible(&filter->notify_lock) < 0) + return EPOLLERR; + + list_for_each_entry(cur, &filter->notif->notifications, list) { + if (cur->state == SECCOMP_NOTIFY_INIT) + ret |= EPOLLIN | EPOLLRDNORM; + if (cur->state == SECCOMP_NOTIFY_SENT) + ret |= EPOLLOUT | EPOLLWRNORM; + if ((ret & EPOLLIN) && (ret & EPOLLOUT)) + break; + } + + mutex_unlock(&filter->notify_lock); + + return ret; +} + +static const struct file_operations seccomp_notify_ops = { + .poll = seccomp_notify_poll, + .release = seccomp_notify_release, + .unlocked_ioctl = seccomp_notify_ioctl, +}; + +static struct file *init_listener(struct seccomp_filter *filter) +{ + struct file *ret = ERR_PTR(-EBUSY); + struct seccomp_filter *cur; + + for (cur = current->seccomp.filter; cur; cur = cur->prev) { + if (cur->notif) + goto out; + } + + ret = ERR_PTR(-ENOMEM); + filter->notif = kzalloc(sizeof(*(filter->notif)), GFP_KERNEL); + if (!filter->notif) + goto out; + + sema_init(&filter->notif->request, 0); + filter->notif->next_id = get_random_u64(); + INIT_LIST_HEAD(&filter->notif->notifications); + init_waitqueue_head(&filter->notif->wqh); + + ret = anon_inode_getfile("seccomp notify", &seccomp_notify_ops, + filter, O_RDWR); + if (IS_ERR(ret)) + goto out_notif; + + /* The file has a reference to it now */ + __get_seccomp_filter(filter); + +out_notif: + if (IS_ERR(ret)) + kfree(filter->notif); +out: + return ret; +} + /** * seccomp_set_mode_filter: internal function for setting seccomp filter * @flags: flags to change filter behavior @@ -853,6 +1246,8 @@ static long seccomp_set_mode_filter(unsigned int flags, const unsigned long seccomp_mode = SECCOMP_MODE_FILTER; struct seccomp_filter *prepared = NULL; long ret = -EINVAL; + int listener = -1; + struct file *listener_f = NULL; /* Validate flags. */ if (flags & ~SECCOMP_FILTER_FLAG_MASK) @@ -863,13 +1258,28 @@ static long seccomp_set_mode_filter(unsigned int flags, if (IS_ERR(prepared)) return PTR_ERR(prepared); + if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { + listener = get_unused_fd_flags(O_CLOEXEC); + if (listener < 0) { + ret = listener; + goto out_free; + } + + listener_f = init_listener(prepared); + if (IS_ERR(listener_f)) { + put_unused_fd(listener); + ret = PTR_ERR(listener_f); + goto out_free; + } + } + /* * Make sure we cannot change seccomp or nnp state via TSYNC * while another thread is in the middle of calling exec. */ if (flags & SECCOMP_FILTER_FLAG_TSYNC && mutex_lock_killable(¤t->signal->cred_guard_mutex)) - goto out_free; + goto out_put_fd; spin_lock_irq(¤t->sighand->siglock); @@ -887,6 +1297,16 @@ out: spin_unlock_irq(¤t->sighand->siglock); if (flags & SECCOMP_FILTER_FLAG_TSYNC) mutex_unlock(¤t->signal->cred_guard_mutex); +out_put_fd: + if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) { + if (ret < 0) { + fput(listener_f); + put_unused_fd(listener); + } else { + fd_install(listener, listener_f); + ret = listener; + } + } out_free: seccomp_filter_free(prepared); return ret; @@ -911,6 +1331,7 @@ static long seccomp_get_action_avail(const char __user *uaction) case SECCOMP_RET_KILL_THREAD: case SECCOMP_RET_TRAP: case SECCOMP_RET_ERRNO: + case SECCOMP_RET_USER_NOTIF: case SECCOMP_RET_TRACE: case SECCOMP_RET_LOG: case SECCOMP_RET_ALLOW: @@ -922,9 +1343,23 @@ static long seccomp_get_action_avail(const char __user *uaction) return 0; } +static long seccomp_get_notif_sizes(void __user *usizes) +{ + struct seccomp_notif_sizes sizes = { + .seccomp_notif = sizeof(struct seccomp_notif), + .seccomp_notif_resp = sizeof(struct seccomp_notif_resp), + .seccomp_data = sizeof(struct seccomp_data), + }; + + if (copy_to_user(usizes, &sizes, sizeof(sizes))) + return -EFAULT; + + return 0; +} + /* Common entry point for both prctl and syscall. */ static long do_seccomp(unsigned int op, unsigned int flags, - const char __user *uargs) + void __user *uargs) { switch (op) { case SECCOMP_SET_MODE_STRICT: @@ -938,13 +1373,18 @@ static long do_seccomp(unsigned int op, unsigned int flags, return -EINVAL; return seccomp_get_action_avail(uargs); + case SECCOMP_GET_NOTIF_SIZES: + if (flags != 0) + return -EINVAL; + + return seccomp_get_notif_sizes(uargs); default: return -EINVAL; } } SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags, - const char __user *, uargs) + void __user *, uargs) { return do_seccomp(op, flags, uargs); } @@ -956,10 +1396,10 @@ SYSCALL_DEFINE3(seccomp, unsigned int, op, unsigned int, flags, * * Returns 0 on success or -EINVAL on failure. */ -long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter) +long prctl_set_seccomp(unsigned long seccomp_mode, void __user *filter) { unsigned int op; - char __user *uargs; + void __user *uargs; switch (seccomp_mode) { case SECCOMP_MODE_STRICT: @@ -1111,6 +1551,7 @@ long seccomp_get_metadata(struct task_struct *task, #define SECCOMP_RET_KILL_THREAD_NAME "kill_thread" #define SECCOMP_RET_TRAP_NAME "trap" #define SECCOMP_RET_ERRNO_NAME "errno" +#define SECCOMP_RET_USER_NOTIF_NAME "user_notif" #define SECCOMP_RET_TRACE_NAME "trace" #define SECCOMP_RET_LOG_NAME "log" #define SECCOMP_RET_ALLOW_NAME "allow" @@ -1120,6 +1561,7 @@ static const char seccomp_actions_avail[] = SECCOMP_RET_KILL_THREAD_NAME " " SECCOMP_RET_TRAP_NAME " " SECCOMP_RET_ERRNO_NAME " " + SECCOMP_RET_USER_NOTIF_NAME " " SECCOMP_RET_TRACE_NAME " " SECCOMP_RET_LOG_NAME " " SECCOMP_RET_ALLOW_NAME; @@ -1134,6 +1576,7 @@ static const struct seccomp_log_name seccomp_log_names[] = { { 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_USER_NOTIF, SECCOMP_RET_USER_NOTIF_NAME }, { SECCOMP_LOG_TRACE, SECCOMP_RET_TRACE_NAME }, { SECCOMP_LOG_LOG, SECCOMP_RET_LOG_NAME }, { SECCOMP_LOG_ALLOW, SECCOMP_RET_ALLOW_NAME }, diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c index ab719495e2cb..8be59f84eaea 100644 --- a/lib/bust_spinlocks.c +++ b/lib/bust_spinlocks.c @@ -2,7 +2,8 @@ /* * lib/bust_spinlocks.c * - * Provides a minimal bust_spinlocks for architectures which don't have one of their own. + * Provides a minimal bust_spinlocks for architectures which don't + * have one of their own. * * bust_spinlocks() clears any spinlocks which would prevent oops, die(), BUG() * and panic() information from reaching the user. @@ -16,8 +17,7 @@ #include <linux/vt_kern.h> #include <linux/console.h> - -void __attribute__((weak)) bust_spinlocks(int yes) +void bust_spinlocks(int yes) { if (yes) { ++oops_in_progress; diff --git a/mm/page_io.c b/mm/page_io.c index 3475733b1926..d975fa3f02aa 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -405,8 +405,7 @@ int swap_readpage(struct page *page, bool synchronous) bio_get(bio); qc = submit_bio(bio); while (synchronous) { - __set_current_state(TASK_UNINTERRUPTIBLE); - + set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio->bi_private)) break; diff --git a/net/9p/client.c b/net/9p/client.c index 2c9a17b9b46b..357214a51f13 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -181,6 +181,12 @@ static int parse_opts(char *opts, struct p9_client *clnt) ret = r; continue; } + if (option < 4096) { + p9_debug(P9_DEBUG_ERROR, + "msize should be at least 4k\n"); + ret = -EINVAL; + continue; + } clnt->msize = option; break; case Opt_trans: @@ -983,10 +989,18 @@ static int p9_client_version(struct p9_client *c) else if (!strncmp(version, "9P2000", 6)) c->proto_version = p9_proto_legacy; else { + p9_debug(P9_DEBUG_ERROR, + "server returned an unknown version: %s\n", version); err = -EREMOTEIO; goto error; } + if (msize < 4096) { + p9_debug(P9_DEBUG_ERROR, + "server returned a msize < 4096: %d\n", msize); + err = -EREMOTEIO; + goto error; + } if (msize < c->msize) c->msize = msize; @@ -1043,6 +1057,13 @@ struct p9_client *p9_client_create(const char *dev_name, char *options) if (clnt->msize > clnt->trans_mod->maxsize) clnt->msize = clnt->trans_mod->maxsize; + if (clnt->msize < 4096) { + p9_debug(P9_DEBUG_ERROR, + "Please specify a msize of at least 4k\n"); + err = -EINVAL; + goto free_client; + } + err = p9_client_version(clnt); if (err) goto close_trans; diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index b718db2085b2..3dff68f05fb9 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -14,6 +14,7 @@ #include <linux/mm.h> #include <linux/module.h> +#include "trans_common.h" /** * p9_release_pages - Release pages after the transaction. diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index c603d33d5410..5d01edf8d819 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -653,15 +653,22 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; } - dev = dev_get_by_name(&init_net, devname); + rtnl_lock(); + dev = __dev_get_by_name(&init_net, devname); if (!dev) { + rtnl_unlock(); res = -ENODEV; break; } ax25->ax25_dev = ax25_dev_ax25dev(dev); + if (!ax25->ax25_dev) { + rtnl_unlock(); + res = -ENODEV; + break; + } ax25_fillin_cb(ax25, ax25->ax25_dev); - dev_put(dev); + rtnl_unlock(); break; default: diff --git a/net/ax25/ax25_dev.c b/net/ax25/ax25_dev.c index 9a3a301e1e2f..d92195cd7834 100644 --- a/net/ax25/ax25_dev.c +++ b/net/ax25/ax25_dev.c @@ -116,6 +116,7 @@ void ax25_dev_device_down(struct net_device *dev) if ((s = ax25_dev_list) == ax25_dev) { ax25_dev_list = s->next; spin_unlock_bh(&ax25_dev_lock); + dev->ax25_ptr = NULL; dev_put(dev); kfree(ax25_dev); return; @@ -125,6 +126,7 @@ void ax25_dev_device_down(struct net_device *dev) if (s->next == ax25_dev) { s->next = ax25_dev->next; spin_unlock_bh(&ax25_dev_lock); + dev->ax25_ptr = NULL; dev_put(dev); kfree(ax25_dev); return; diff --git a/net/compat.c b/net/compat.c index f7084780a8f8..c3a2f868e8af 100644 --- a/net/compat.c +++ b/net/compat.c @@ -467,12 +467,14 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) ctv = (struct compat_timeval __user *) userstamp; err = -ENOENT; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sk->sk_stamp); + tv = ktime_to_timeval(sock_read_timestamp(sk)); + if (tv.tv_sec == -1) return err; if (tv.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - tv = ktime_to_timeval(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + tv = ktime_to_timeval(kt); } err = 0; if (put_user(tv.tv_sec, &ctv->tv_sec) || @@ -494,12 +496,13 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta ctv = (struct compat_timespec __user *) userstamp; err = -ENOENT; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sk->sk_stamp); + ts = ktime_to_timespec(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return err; if (ts.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - ts = ktime_to_timespec(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + ts = ktime_to_timespec(kt); } err = 0; if (put_user(ts.tv_sec, &ctv->tv_sec) || diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d05402868575..158264f7cfaf 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -793,8 +793,13 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops->get_regs_len) - info.regdump_len = ops->get_regs_len(dev); + if (ops->get_regs_len) { + int ret = ops->get_regs_len(dev); + + if (ret > 0) + info.regdump_len = ret; + } + if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); @@ -1337,6 +1342,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) return -EFAULT; reglen = ops->get_regs_len(dev); + if (reglen <= 0) + return reglen; + if (regs.len > reglen) regs.len = reglen; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 48f61885fd6f..5ea1bed08ede 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4104,6 +4104,11 @@ static int rtnl_fdb_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (!addr) { + NL_SET_ERR_MSG(extack, "Missing lookup address for fdb get request"); + return -EINVAL; + } + if (brport_idx) { dev = __dev_get_by_index(net, brport_idx); if (!dev) { diff --git a/net/core/sock.c b/net/core/sock.c index f00902c532cc..6aa2e7e0b4fb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2751,6 +2751,9 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; sk->sk_stamp = SK_DEFAULT_STAMP; +#if BITS_PER_LONG==32 + seqlock_init(&sk->sk_stamp_seq); +#endif atomic_set(&sk->sk_zckey, 0); #ifdef CONFIG_NET_RX_BUSY_POLL @@ -2850,12 +2853,13 @@ int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) struct timeval tv; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - tv = ktime_to_timeval(sk->sk_stamp); + tv = ktime_to_timeval(sock_read_timestamp(sk)); if (tv.tv_sec == -1) return -ENOENT; if (tv.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); - tv = ktime_to_timeval(sk->sk_stamp); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); + tv = ktime_to_timeval(kt); } return copy_to_user(userstamp, &tv, sizeof(tv)) ? -EFAULT : 0; } @@ -2866,11 +2870,12 @@ int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) struct timespec ts; sock_enable_timestamp(sk, SOCK_TIMESTAMP); - ts = ktime_to_timespec(sk->sk_stamp); + ts = ktime_to_timespec(sock_read_timestamp(sk)); if (ts.tv_sec == -1) return -ENOENT; if (ts.tv_sec == 0) { - sk->sk_stamp = ktime_get_real(); + ktime_t kt = ktime_get_real(); + sock_write_timestamp(sk, kt); ts = ktime_to_timespec(sk->sk_stamp); } return copy_to_user(userstamp, &ts, sizeof(ts)) ? -EFAULT : 0; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index f8eb78d042a4..cfec3af54c8d 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -198,11 +198,15 @@ static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) static struct fib_table *fib_empty_table(struct net *net) { - u32 id; + u32 id = 1; - for (id = 1; id <= RT_TABLE_MAX; id++) + while (1) { if (!fib_get_table(net, id)) return fib_new_table(net, id); + + if (id++ == RT_TABLE_MAX) + break; + } return NULL; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index c7a7bd58a23c..d1d09f3e5f9e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -676,6 +676,9 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; + if (!pskb_inet_may_pull(skb)) + goto free_skb; + if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; @@ -719,6 +722,9 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; + if (!pskb_inet_may_pull(skb)) + goto free_skb; + if (tunnel->collect_md) { erspan_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; @@ -762,6 +768,9 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); + if (!pskb_inet_may_pull(skb)) + goto free_skb; + if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 284a22154b4e..c4f5602308ed 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -627,7 +627,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, u8 protocol) { struct ip_tunnel *tunnel = netdev_priv(dev); - unsigned int inner_nhdr_len = 0; const struct iphdr *inner_iph; struct flowi4 fl4; u8 tos, ttl; @@ -637,14 +636,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, __be32 dst; bool connected; - /* ensure we can access the inner net header, for several users below */ - if (skb->protocol == htons(ETH_P_IP)) - inner_nhdr_len = sizeof(struct iphdr); - else if (skb->protocol == htons(ETH_P_IPV6)) - inner_nhdr_len = sizeof(struct ipv6hdr); - if (unlikely(!pskb_may_pull(skb, inner_nhdr_len))) - goto tx_error; - inner_iph = (const struct iphdr *)skb_inner_network_header(skb); connected = (tunnel->parms.iph.daddr != 0); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index de31b302d69c..d7b43e700023 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -241,6 +241,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); struct flowi fl; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { @@ -253,15 +256,18 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); break; default: - dev->stats.tx_errors++; - dev_kfree_skb(skb); - return NETDEV_TX_OK; + goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); return vti_xmit(skb, dev, &fl); + +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; } static int vti4_err(struct sk_buff *skb, u32 info) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 521e471f1cf9..8eeec6eb2bd3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4736,8 +4736,8 @@ inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, IFA_F_MCAUTOJOIN | IFA_F_OPTIMISTIC; idev = ipv6_find_idev(dev); - if (IS_ERR(idev)) - return PTR_ERR(idev); + if (!idev) + return -ENOBUFS; if (!ipv6_allow_optimistic_dad(net, idev)) cfg.ifa_flags &= ~IFA_F_OPTIMISTIC; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index f0cd291034f0..0bfb6cc0a30a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -350,6 +350,9 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, err = -EINVAL; goto out_unlock; } + } + + if (sk->sk_bound_dev_if) { dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ae3786132c23..6613d8dbb0e5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -627,7 +627,11 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) return -ENOENT; } - res = fib6_dump_table(tb, skb, cb); + if (!cb->args[0]) { + res = fib6_dump_table(tb, skb, cb); + if (!res) + cb->args[0] = 1; + } goto out; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 229e55c99021..09d0826742f8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -881,6 +881,9 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb, struct net_device_stats *stats = &t->dev->stats; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -923,6 +926,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, int nhoff; int thoff; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -995,8 +1001,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; } } else { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); - switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1004,7 +1008,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, &dsfield, &encap_limit); break; case htons(ETH_P_IPV6): - if (ipv6_addr_equal(&t->parms.raddr, &ipv6h->saddr)) + if (ipv6_addr_equal(&t->parms.raddr, &ipv6_hdr(skb)->saddr)) goto tx_err; if (prepare_ip6gre_xmit_ipv6(skb, dev, &fl6, &dsfield, &encap_limit)) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 99179b9c8384..0c6403cf8b52 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1243,10 +1243,6 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - /* ensure we can access the full inner ip header */ - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return -1; - iph = ip_hdr(skb); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); @@ -1321,9 +1317,6 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; - if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h)))) - return -1; - ipv6h = ipv6_hdr(skb); tproto = READ_ONCE(t->parms.proto); if ((tproto != IPPROTO_IPV6 && tproto != 0) || @@ -1405,6 +1398,9 @@ ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) struct net_device_stats *stats = &t->dev->stats; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + switch (skb->protocol) { case htons(ETH_P_IP): ret = ip4ip6_tnl_xmit(skb, dev); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 706fe42e4928..8b6eefff2f7e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -522,18 +522,18 @@ vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; - struct ipv6hdr *ipv6h; struct flowi fl; int ret; + if (!pskb_inet_may_pull(skb)) + goto tx_err; + memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): - ipv6h = ipv6_hdr(skb); - if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || - vti6_addr_conflict(t, ipv6h)) + vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; xfrm_decode_session(skb, &fl, AF_INET6); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 8276f1224f16..30337b38274b 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -51,6 +51,7 @@ #include <linux/export.h> #include <net/ip6_checksum.h> #include <linux/netconf.h> +#include <net/ip_tunnels.h> #include <linux/nospec.h> @@ -599,13 +600,12 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX, .flowi6_mark = skb->mark, }; - int err; - err = ip6mr_fib_lookup(net, &fl6, &mrt); - if (err < 0) { - kfree_skb(skb); - return err; - } + if (!pskb_inet_may_pull(skb)) + goto tx_err; + + if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0) + goto tx_err; read_lock(&mrt_lock); dev->stats.tx_bytes += skb->len; @@ -614,6 +614,11 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb, read_unlock(&mrt_lock); kfree_skb(skb); return NETDEV_TX_OK; + +tx_err: + dev->stats.tx_errors++; + kfree_skb(skb); + return NETDEV_TX_OK; } static int reg_vif_get_iflink(const struct net_device *dev) diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index a5bb59ee50ac..36a3d8dc61f5 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -210,7 +210,7 @@ found: if (next && next->ip_defrag_offset < end) goto discard_fq; - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ + /* Note : skb->ip_defrag_offset and skb->sk share the same location */ dev = skb->dev; if (dev) fq->iif = dev->ifindex; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 194bc162866d..40b225f87d5e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -210,7 +210,9 @@ struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; - return neigh_create(&nd_tbl, daddr, dev); + + n = neigh_create(&nd_tbl, daddr, dev); + return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, @@ -5054,12 +5056,16 @@ int ipv6_sysctl_rtcache_flush(struct ctl_table *ctl, int write, { struct net *net; int delay; + int ret; if (!write) return -EINVAL; net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; - proc_dointvec(ctl, write, buffer, lenp, ppos); + ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + if (ret) + return ret; + fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 51c9f75f34b9..1e03305c0549 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1021,6 +1021,9 @@ tx_error: static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + if (!pskb_inet_may_pull(skb)) + goto tx_err; + switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 9cd180bda092..7554c56b2e63 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -33,12 +33,6 @@ #define CONNCOUNT_SLOTS 256U -#ifdef CONFIG_LOCKDEP -#define CONNCOUNT_LOCK_SLOTS 8U -#else -#define CONNCOUNT_LOCK_SLOTS 256U -#endif - #define CONNCOUNT_GC_MAX_NODES 8 #define MAX_KEYLEN 5 @@ -49,8 +43,6 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; - bool dead; - struct rcu_head rcu_head; }; struct nf_conncount_rb { @@ -60,7 +52,7 @@ struct nf_conncount_rb { struct rcu_head rcu_head; }; -static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp; +static spinlock_t nf_conncount_locks[CONNCOUNT_SLOTS] __cacheline_aligned_in_smp; struct nf_conncount_data { unsigned int keylen; @@ -89,79 +81,25 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen) return memcmp(a, b, klen * sizeof(u32)); } -enum nf_conncount_list_add -nf_conncount_add(struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone) -{ - struct nf_conncount_tuple *conn; - - if (WARN_ON_ONCE(list->count > INT_MAX)) - return NF_CONNCOUNT_ERR; - - conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); - if (conn == NULL) - return NF_CONNCOUNT_ERR; - - conn->tuple = *tuple; - conn->zone = *zone; - conn->cpu = raw_smp_processor_id(); - conn->jiffies32 = (u32)jiffies; - conn->dead = false; - spin_lock_bh(&list->list_lock); - if (list->dead == true) { - kmem_cache_free(conncount_conn_cachep, conn); - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_SKIP; - } - list_add_tail(&conn->node, &list->head); - list->count++; - spin_unlock_bh(&list->list_lock); - return NF_CONNCOUNT_ADDED; -} -EXPORT_SYMBOL_GPL(nf_conncount_add); - -static void __conn_free(struct rcu_head *h) -{ - struct nf_conncount_tuple *conn; - - conn = container_of(h, struct nf_conncount_tuple, rcu_head); - kmem_cache_free(conncount_conn_cachep, conn); -} - -static bool conn_free(struct nf_conncount_list *list, +static void conn_free(struct nf_conncount_list *list, struct nf_conncount_tuple *conn) { - bool free_entry = false; - - spin_lock_bh(&list->list_lock); - - if (conn->dead) { - spin_unlock_bh(&list->list_lock); - return free_entry; - } + lockdep_assert_held(&list->list_lock); list->count--; - conn->dead = true; - list_del_rcu(&conn->node); - if (list->count == 0) { - list->dead = true; - free_entry = true; - } + list_del(&conn->node); - spin_unlock_bh(&list->list_lock); - call_rcu(&conn->rcu_head, __conn_free); - return free_entry; + kmem_cache_free(conncount_conn_cachep, conn); } static const struct nf_conntrack_tuple_hash * find_or_evict(struct net *net, struct nf_conncount_list *list, - struct nf_conncount_tuple *conn, bool *free_entry) + struct nf_conncount_tuple *conn) { const struct nf_conntrack_tuple_hash *found; unsigned long a, b; int cpu = raw_smp_processor_id(); - __s32 age; + u32 age; found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); if (found) @@ -176,52 +114,45 @@ find_or_evict(struct net *net, struct nf_conncount_list *list, */ age = a - b; if (conn->cpu == cpu || age >= 2) { - *free_entry = conn_free(list, conn); + conn_free(list, conn); return ERR_PTR(-ENOENT); } return ERR_PTR(-EAGAIN); } -void nf_conncount_lookup(struct net *net, - struct nf_conncount_list *list, - const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_zone *zone, - bool *addit) +static int __nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collect = 0; - bool free_entry = false; - - /* best effort only */ - *addit = tuple ? true : false; /* check the saved connections */ list_for_each_entry_safe(conn, conn_n, &list->head, node) { if (collect > CONNCOUNT_GC_MAX_NODES) break; - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { /* Not found, but might be about to be confirmed */ if (PTR_ERR(found) == -EAGAIN) { - if (!tuple) - continue; - if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_id(&conn->zone, conn->zone.dir) == nf_ct_zone_id(zone, zone->dir)) - *addit = false; - } else if (PTR_ERR(found) == -ENOENT) + return 0; /* already exists */ + } else { collect++; + } continue; } found_ct = nf_ct_tuplehash_to_ctrack(found); - if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) && + if (nf_ct_tuple_equal(&conn->tuple, tuple) && nf_ct_zone_equal(found_ct, zone, zone->dir)) { /* * We should not see tuples twice unless someone hooks @@ -229,7 +160,8 @@ void nf_conncount_lookup(struct net *net, * * Attempt to avoid a re-add in this case. */ - *addit = false; + nf_ct_put(found_ct); + return 0; } else if (already_closed(found_ct)) { /* * we do not care about connections which are @@ -243,19 +175,48 @@ void nf_conncount_lookup(struct net *net, nf_ct_put(found_ct); } + + if (WARN_ON_ONCE(list->count > INT_MAX)) + return -EOVERFLOW; + + conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC); + if (conn == NULL) + return -ENOMEM; + + conn->tuple = *tuple; + conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; + list_add_tail(&conn->node, &list->head); + list->count++; + return 0; } -EXPORT_SYMBOL_GPL(nf_conncount_lookup); + +int nf_conncount_add(struct net *net, + struct nf_conncount_list *list, + const struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_zone *zone) +{ + int ret; + + /* check the saved connections */ + spin_lock_bh(&list->list_lock); + ret = __nf_conncount_add(net, list, tuple, zone); + spin_unlock_bh(&list->list_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(nf_conncount_add); void nf_conncount_list_init(struct nf_conncount_list *list) { spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); list->count = 0; - list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); -/* Return true if the list is empty */ +/* Return true if the list is empty. Must be called with BH disabled. */ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_list *list) { @@ -263,17 +224,17 @@ bool nf_conncount_gc_list(struct net *net, struct nf_conncount_tuple *conn, *conn_n; struct nf_conn *found_ct; unsigned int collected = 0; - bool free_entry = false; bool ret = false; + /* don't bother if other cpu is already doing GC */ + if (!spin_trylock(&list->list_lock)) + return false; + list_for_each_entry_safe(conn, conn_n, &list->head, node) { - found = find_or_evict(net, list, conn, &free_entry); + found = find_or_evict(net, list, conn); if (IS_ERR(found)) { - if (PTR_ERR(found) == -ENOENT) { - if (free_entry) - return true; + if (PTR_ERR(found) == -ENOENT) collected++; - } continue; } @@ -284,23 +245,19 @@ bool nf_conncount_gc_list(struct net *net, * closed already -> ditch it */ nf_ct_put(found_ct); - if (conn_free(list, conn)) - return true; + conn_free(list, conn); collected++; continue; } nf_ct_put(found_ct); if (collected > CONNCOUNT_GC_MAX_NODES) - return false; + break; } - spin_lock_bh(&list->list_lock); - if (!list->count) { - list->dead = true; + if (!list->count) ret = true; - } - spin_unlock_bh(&list->list_lock); + spin_unlock(&list->list_lock); return ret; } @@ -314,6 +271,7 @@ static void __tree_nodes_free(struct rcu_head *h) kmem_cache_free(conncount_rb_cachep, rbconn); } +/* caller must hold tree nf_conncount_locks[] lock */ static void tree_nodes_free(struct rb_root *root, struct nf_conncount_rb *gc_nodes[], unsigned int gc_count) @@ -323,8 +281,10 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; spin_lock(&rbconn->list.list_lock); - rb_erase(&rbconn->node, root); - call_rcu(&rbconn->rcu_head, __tree_nodes_free); + if (!rbconn->list.count) { + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); + } spin_unlock(&rbconn->list.list_lock); } } @@ -341,20 +301,19 @@ insert_tree(struct net *net, struct rb_root *root, unsigned int hash, const u32 *key, - u8 keylen, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES]; struct rb_node **rbnode, *parent; struct nf_conncount_rb *rbconn; struct nf_conncount_tuple *conn; unsigned int count = 0, gc_count = 0; - bool node_found = false; - - spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + u8 keylen = data->keylen; + bool do_gc = true; + spin_lock_bh(&nf_conncount_locks[hash]); +restart: parent = NULL; rbnode = &(root->rb_node); while (*rbnode) { @@ -368,45 +327,32 @@ insert_tree(struct net *net, } else if (diff > 0) { rbnode = &((*rbnode)->rb_right); } else { - /* unlikely: other cpu added node already */ - node_found = true; - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { + int ret; + + ret = nf_conncount_add(net, &rbconn->list, tuple, zone); + if (ret) count = 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { + else count = rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ - node_found = false; - } - break; + tree_nodes_free(root, gc_nodes, gc_count); + goto out_unlock; } if (gc_count >= ARRAY_SIZE(gc_nodes)) continue; - if (nf_conncount_gc_list(net, &rbconn->list)) + if (do_gc && nf_conncount_gc_list(net, &rbconn->list)) gc_nodes[gc_count++] = rbconn; } if (gc_count) { tree_nodes_free(root, gc_nodes, gc_count); - /* tree_node_free before new allocation permits - * allocator to re-use newly free'd object. - * - * This is a rare event; in most cases we will find - * existing node to re-use. (or gc_count is 0). - */ - - if (gc_count >= ARRAY_SIZE(gc_nodes)) - schedule_gc_worker(data, hash); + schedule_gc_worker(data, hash); + gc_count = 0; + do_gc = false; + goto restart; } - if (node_found) - goto out_unlock; - /* expected case: match, insert new node */ rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC); if (rbconn == NULL) @@ -430,7 +376,7 @@ insert_tree(struct net *net, rb_link_node_rcu(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); out_unlock: - spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]); + spin_unlock_bh(&nf_conncount_locks[hash]); return count; } @@ -441,7 +387,6 @@ count_tree(struct net *net, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone) { - enum nf_conncount_list_add ret; struct rb_root *root; struct rb_node *parent; struct nf_conncount_rb *rbconn; @@ -454,7 +399,6 @@ count_tree(struct net *net, parent = rcu_dereference_raw(root->rb_node); while (parent) { int diff; - bool addit; rbconn = rb_entry(parent, struct nf_conncount_rb, node); @@ -464,31 +408,36 @@ count_tree(struct net *net, } else if (diff > 0) { parent = rcu_dereference_raw(parent->rb_right); } else { - /* same source network -> be counted! */ - nf_conncount_lookup(net, &rbconn->list, tuple, zone, - &addit); + int ret; - if (!addit) + if (!tuple) { + nf_conncount_gc_list(net, &rbconn->list); return rbconn->list.count; + } - ret = nf_conncount_add(&rbconn->list, tuple, zone); - if (ret == NF_CONNCOUNT_ERR) { - return 0; /* hotdrop */ - } else if (ret == NF_CONNCOUNT_ADDED) { - return rbconn->list.count; - } else { - /* NF_CONNCOUNT_SKIP, rbconn is already - * reclaimed by gc, insert a new tree node - */ + spin_lock_bh(&rbconn->list.list_lock); + /* Node might be about to be free'd. + * We need to defer to insert_tree() in this case. + */ + if (rbconn->list.count == 0) { + spin_unlock_bh(&rbconn->list.list_lock); break; } + + /* same source network -> be counted! */ + ret = __nf_conncount_add(net, &rbconn->list, tuple, zone); + spin_unlock_bh(&rbconn->list.list_lock); + if (ret) + return 0; /* hotdrop */ + else + return rbconn->list.count; } } if (!tuple) return 0; - return insert_tree(net, data, root, hash, key, keylen, tuple, zone); + return insert_tree(net, data, root, hash, key, tuple, zone); } static void tree_gc_worker(struct work_struct *work) @@ -499,27 +448,47 @@ static void tree_gc_worker(struct work_struct *work) struct rb_node *node; unsigned int tree, next_tree, gc_count = 0; - tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS; + tree = data->gc_tree % CONNCOUNT_SLOTS; root = &data->root[tree]; + local_bh_disable(); rcu_read_lock(); for (node = rb_first(root); node != NULL; node = rb_next(node)) { rbconn = rb_entry(node, struct nf_conncount_rb, node); if (nf_conncount_gc_list(data->net, &rbconn->list)) - gc_nodes[gc_count++] = rbconn; + gc_count++; } rcu_read_unlock(); + local_bh_enable(); + + cond_resched(); spin_lock_bh(&nf_conncount_locks[tree]); + if (gc_count < ARRAY_SIZE(gc_nodes)) + goto next; /* do not bother */ - if (gc_count) { - tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + node = rb_first(root); + while (node != NULL) { + rbconn = rb_entry(node, struct nf_conncount_rb, node); + node = rb_next(node); + + if (rbconn->list.count > 0) + continue; + + gc_nodes[gc_count++] = rbconn; + if (gc_count >= ARRAY_SIZE(gc_nodes)) { + tree_nodes_free(root, gc_nodes, gc_count); + gc_count = 0; + } } + tree_nodes_free(root, gc_nodes, gc_count); +next: clear_bit(tree, data->pending_trees); next_tree = (tree + 1) % CONNCOUNT_SLOTS; - next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS); + next_tree = find_next_bit(data->pending_trees, CONNCOUNT_SLOTS, next_tree); if (next_tree < CONNCOUNT_SLOTS) { data->gc_tree = next_tree; @@ -621,10 +590,7 @@ static int __init nf_conncount_modinit(void) { int i; - BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS); - BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0); - - for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i) + for (i = 0; i < CONNCOUNT_SLOTS; ++i) spin_lock_init(&nf_conncount_locks[i]); conncount_conn_cachep = kmem_cache_create("nf_conncount_tuple", diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fec814dace5a..2b0a93300dd7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5727,6 +5727,8 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; nest = nla_nest_start(skb, NFTA_FLOWTABLE_HOOK); + if (!nest) + goto nla_put_failure; if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) || nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority))) goto nla_put_failure; diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index b90d96ba4a12..af1497ab9464 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -30,7 +30,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, enum ip_conntrack_info ctinfo; const struct nf_conn *ct; unsigned int count; - bool addit; tuple_ptr = &tuple; @@ -44,19 +43,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv, return; } - nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone, - &addit); - count = priv->list.count; - - if (!addit) - goto out; - - if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) { + if (nf_conncount_add(nft_net(pkt), &priv->list, tuple_ptr, zone)) { regs->verdict.code = NF_DROP; return; } - count++; -out: + + count = priv->list.count; if ((count > priv->limit) ^ priv->invert) { regs->verdict.code = NFT_BREAK; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 03f37c4e64fe..1d3144d19903 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -153,7 +153,7 @@ static struct sock *nr_find_listener(ax25_address *addr) sk_for_each(s, &nr_list) if (!ax25cmp(&nr_sk(s)->source_addr, addr) && s->sk_state == TCP_LISTEN) { - bh_lock_sock(s); + sock_hold(s); goto found; } s = NULL; @@ -174,7 +174,7 @@ static struct sock *nr_find_socket(unsigned char index, unsigned char id) struct nr_sock *nr = nr_sk(s); if (nr->my_index == index && nr->my_id == id) { - bh_lock_sock(s); + sock_hold(s); goto found; } } @@ -198,7 +198,7 @@ static struct sock *nr_find_peer(unsigned char index, unsigned char id, if (nr->your_index == index && nr->your_id == id && !ax25cmp(&nr->dest_addr, dest)) { - bh_lock_sock(s); + sock_hold(s); goto found; } } @@ -224,7 +224,7 @@ static unsigned short nr_find_next_circuit(void) if (i != 0 && j != 0) { if ((sk=nr_find_socket(i, j)) == NULL) break; - bh_unlock_sock(sk); + sock_put(sk); } id++; @@ -920,6 +920,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) } if (sk != NULL) { + bh_lock_sock(sk); skb_reset_transport_header(skb); if (frametype == NR_CONNACK && skb->len == 22) @@ -929,6 +930,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) ret = nr_process_rx_frame(sk, skb); bh_unlock_sock(sk); + sock_put(sk); return ret; } @@ -960,10 +962,12 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) (make = nr_make_new(sk)) == NULL) { nr_transmit_refusal(skb, 0); if (sk) - bh_unlock_sock(sk); + sock_put(sk); return 0; } + bh_lock_sock(sk); + window = skb->data[20]; skb->sk = make; @@ -1016,6 +1020,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) sk->sk_data_ready(sk); bh_unlock_sock(sk); + sock_put(sk); nr_insert_socket(make); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index b9bbcf3d6c63..c16f0a362c32 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -623,7 +623,7 @@ static void __net_exit rds_tcp_exit_net(struct net *net) if (rtn->rds_tcp_sysctl) unregister_net_sysctl_table(rtn->rds_tcp_sysctl); - if (net != &init_net && rtn->ctl_table) + if (net != &init_net) kfree(rtn->ctl_table); } diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 090658c3da12..9488600451e8 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ - auth.o auth_null.o auth_unix.o auth_generic.o \ + auth.o auth_null.o auth_unix.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o \ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index ad8ead738981..1ff9768f5456 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -39,6 +39,20 @@ static const struct rpc_authops __rcu *auth_flavors[RPC_AUTH_MAXFLAVOR] = { static LIST_HEAD(cred_unused); static unsigned long number_cred_unused; +static struct cred machine_cred = { + .usage = ATOMIC_INIT(1), +}; + +/* + * Return the machine_cred pointer to be used whenever + * the a generic machine credential is needed. + */ +const struct cred *rpc_machine_cred(void) +{ + return &machine_cred; +} +EXPORT_SYMBOL_GPL(rpc_machine_cred); + #define MAX_HASHTABLE_BITS (14) static int param_set_hashtbl_sz(const char *val, const struct kernel_param *kp) { @@ -346,29 +360,6 @@ out_nocache: } EXPORT_SYMBOL_GPL(rpcauth_init_credcache); -/* - * Setup a credential key lifetime timeout notification - */ -int -rpcauth_key_timeout_notify(struct rpc_auth *auth, struct rpc_cred *cred) -{ - if (!cred->cr_auth->au_ops->key_timeout) - return 0; - return cred->cr_auth->au_ops->key_timeout(auth, cred); -} -EXPORT_SYMBOL_GPL(rpcauth_key_timeout_notify); - -bool -rpcauth_cred_key_to_expire(struct rpc_auth *auth, struct rpc_cred *cred) -{ - if (auth->au_flags & RPCAUTH_AUTH_NO_CRKEY_TIMEOUT) - return false; - if (!cred->cr_ops->crkey_to_expire) - return false; - return cred->cr_ops->crkey_to_expire(cred); -} -EXPORT_SYMBOL_GPL(rpcauth_cred_key_to_expire); - char * rpcauth_stringify_acceptor(struct rpc_cred *cred) { @@ -587,13 +578,6 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, hlist_for_each_entry_rcu(entry, &cache->hashtable[nr], cr_hash) { if (!entry->cr_ops->crmatch(acred, entry, flags)) continue; - if (flags & RPCAUTH_LOOKUP_RCU) { - if (test_bit(RPCAUTH_CRED_NEW, &entry->cr_flags) || - refcount_read(&entry->cr_count) == 0) - continue; - cred = entry; - break; - } cred = get_rpccred(entry); if (cred) break; @@ -603,9 +587,6 @@ rpcauth_lookup_credcache(struct rpc_auth *auth, struct auth_cred * acred, if (cred != NULL) goto found; - if (flags & RPCAUTH_LOOKUP_RCU) - return ERR_PTR(-ECHILD); - new = auth->au_ops->crcreate(auth, acred, flags, gfp); if (IS_ERR(new)) { cred = new; @@ -656,9 +637,7 @@ rpcauth_lookupcred(struct rpc_auth *auth, int flags) auth->au_ops->au_name); memset(&acred, 0, sizeof(acred)); - acred.uid = cred->fsuid; - acred.gid = cred->fsgid; - acred.group_info = cred->group_info; + acred.cred = cred; ret = auth->au_ops->lookup_cred(auth, &acred, flags); return ret; } @@ -672,31 +651,41 @@ rpcauth_init_cred(struct rpc_cred *cred, const struct auth_cred *acred, INIT_LIST_HEAD(&cred->cr_lru); refcount_set(&cred->cr_count, 1); cred->cr_auth = auth; + cred->cr_flags = 0; cred->cr_ops = ops; cred->cr_expire = jiffies; - cred->cr_uid = acred->uid; + cred->cr_cred = get_cred(acred->cred); } EXPORT_SYMBOL_GPL(rpcauth_init_cred); -struct rpc_cred * -rpcauth_generic_bind_cred(struct rpc_task *task, struct rpc_cred *cred, int lookupflags) +static struct rpc_cred * +rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) { - dprintk("RPC: %5u holding %s cred %p\n", task->tk_pid, - cred->cr_auth->au_ops->au_name, cred); - return get_rpccred(cred); + struct rpc_auth *auth = task->tk_client->cl_auth; + struct auth_cred acred = { + .cred = get_task_cred(&init_task), + }; + struct rpc_cred *ret; + + dprintk("RPC: %5u looking up %s cred\n", + task->tk_pid, task->tk_client->cl_auth->au_ops->au_name); + ret = auth->au_ops->lookup_cred(auth, &acred, lookupflags); + put_cred(acred.cred); + return ret; } -EXPORT_SYMBOL_GPL(rpcauth_generic_bind_cred); static struct rpc_cred * -rpcauth_bind_root_cred(struct rpc_task *task, int lookupflags) +rpcauth_bind_machine_cred(struct rpc_task *task, int lookupflags) { struct rpc_auth *auth = task->tk_client->cl_auth; struct auth_cred acred = { - .uid = GLOBAL_ROOT_UID, - .gid = GLOBAL_ROOT_GID, + .principal = task->tk_client->cl_principal, + .cred = init_task.cred, }; - dprintk("RPC: %5u looking up %s cred\n", + if (!acred.principal) + return NULL; + dprintk("RPC: %5u looking up %s machine cred\n", task->tk_pid, task->tk_client->cl_auth->au_ops->au_name); return auth->au_ops->lookup_cred(auth, &acred, lookupflags); } @@ -712,18 +701,33 @@ rpcauth_bind_new_cred(struct rpc_task *task, int lookupflags) } static int -rpcauth_bindcred(struct rpc_task *task, struct rpc_cred *cred, int flags) +rpcauth_bindcred(struct rpc_task *task, const struct cred *cred, int flags) { struct rpc_rqst *req = task->tk_rqstp; - struct rpc_cred *new; + struct rpc_cred *new = NULL; int lookupflags = 0; + struct rpc_auth *auth = task->tk_client->cl_auth; + struct auth_cred acred = { + .cred = cred, + }; if (flags & RPC_TASK_ASYNC) lookupflags |= RPCAUTH_LOOKUP_NEW; - if (cred != NULL) - new = cred->cr_ops->crbind(task, cred, lookupflags); - else if (flags & RPC_TASK_ROOTCREDS) + if (task->tk_op_cred) + /* Task must use exactly this rpc_cred */ + new = get_rpccred(task->tk_op_cred); + else if (cred != NULL && cred != &machine_cred) + new = auth->au_ops->lookup_cred(auth, &acred, lookupflags); + else if (cred == &machine_cred) + new = rpcauth_bind_machine_cred(task, lookupflags); + + /* If machine cred couldn't be bound, try a root cred */ + if (new) + ; + else if (cred == &machine_cred || (flags & RPC_TASK_ROOTCREDS)) new = rpcauth_bind_root_cred(task, lookupflags); + else if (flags & RPC_TASK_NULLCREDS) + new = authnull_ops.lookup_cred(NULL, NULL, 0); else new = rpcauth_bind_new_cred(task, lookupflags); if (IS_ERR(new)) @@ -901,15 +905,10 @@ int __init rpcauth_init_module(void) err = rpc_init_authunix(); if (err < 0) goto out1; - err = rpc_init_generic_auth(); - if (err < 0) - goto out2; err = register_shrinker(&rpc_cred_shrinker); if (err < 0) - goto out3; + goto out2; return 0; -out3: - rpc_destroy_generic_auth(); out2: rpc_destroy_authunix(); out1: @@ -919,6 +918,5 @@ out1: void rpcauth_remove_module(void) { rpc_destroy_authunix(); - rpc_destroy_generic_auth(); unregister_shrinker(&rpc_cred_shrinker); } diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c deleted file mode 100644 index ab4a3be1542a..000000000000 --- a/net/sunrpc/auth_generic.c +++ /dev/null @@ -1,293 +0,0 @@ -/* - * Generic RPC credential - * - * Copyright (C) 2008, Trond Myklebust <Trond.Myklebust@netapp.com> - */ - -#include <linux/err.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/sunrpc/auth.h> -#include <linux/sunrpc/clnt.h> -#include <linux/sunrpc/debug.h> -#include <linux/sunrpc/sched.h> - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_AUTH -#endif - -#define RPC_MACHINE_CRED_USERID GLOBAL_ROOT_UID -#define RPC_MACHINE_CRED_GROUPID GLOBAL_ROOT_GID - -struct generic_cred { - struct rpc_cred gc_base; - struct auth_cred acred; -}; - -static struct rpc_auth generic_auth; -static const struct rpc_credops generic_credops; - -/* - * Public call interface - */ -struct rpc_cred *rpc_lookup_cred(void) -{ - return rpcauth_lookupcred(&generic_auth, 0); -} -EXPORT_SYMBOL_GPL(rpc_lookup_cred); - -struct rpc_cred * -rpc_lookup_generic_cred(struct auth_cred *acred, int flags, gfp_t gfp) -{ - return rpcauth_lookup_credcache(&generic_auth, acred, flags, gfp); -} -EXPORT_SYMBOL_GPL(rpc_lookup_generic_cred); - -struct rpc_cred *rpc_lookup_cred_nonblock(void) -{ - return rpcauth_lookupcred(&generic_auth, RPCAUTH_LOOKUP_RCU); -} -EXPORT_SYMBOL_GPL(rpc_lookup_cred_nonblock); - -/* - * Public call interface for looking up machine creds. - */ -struct rpc_cred *rpc_lookup_machine_cred(const char *service_name) -{ - struct auth_cred acred = { - .uid = RPC_MACHINE_CRED_USERID, - .gid = RPC_MACHINE_CRED_GROUPID, - .principal = service_name, - .machine_cred = 1, - }; - - dprintk("RPC: looking up machine cred for service %s\n", - service_name); - return generic_auth.au_ops->lookup_cred(&generic_auth, &acred, 0); -} -EXPORT_SYMBOL_GPL(rpc_lookup_machine_cred); - -static struct rpc_cred *generic_bind_cred(struct rpc_task *task, - struct rpc_cred *cred, int lookupflags) -{ - struct rpc_auth *auth = task->tk_client->cl_auth; - struct auth_cred *acred = &container_of(cred, struct generic_cred, gc_base)->acred; - - return auth->au_ops->lookup_cred(auth, acred, lookupflags); -} - -static int -generic_hash_cred(struct auth_cred *acred, unsigned int hashbits) -{ - return hash_64(from_kgid(&init_user_ns, acred->gid) | - ((u64)from_kuid(&init_user_ns, acred->uid) << - (sizeof(gid_t) * 8)), hashbits); -} - -/* - * Lookup generic creds for current process - */ -static struct rpc_cred * -generic_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) -{ - return rpcauth_lookup_credcache(&generic_auth, acred, flags, GFP_KERNEL); -} - -static struct rpc_cred * -generic_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp) -{ - struct generic_cred *gcred; - - gcred = kmalloc(sizeof(*gcred), gfp); - if (gcred == NULL) - return ERR_PTR(-ENOMEM); - - rpcauth_init_cred(&gcred->gc_base, acred, &generic_auth, &generic_credops); - gcred->gc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; - - gcred->acred.uid = acred->uid; - gcred->acred.gid = acred->gid; - gcred->acred.group_info = acred->group_info; - gcred->acred.ac_flags = 0; - if (gcred->acred.group_info != NULL) - get_group_info(gcred->acred.group_info); - gcred->acred.machine_cred = acred->machine_cred; - gcred->acred.principal = acred->principal; - - dprintk("RPC: allocated %s cred %p for uid %d gid %d\n", - gcred->acred.machine_cred ? "machine" : "generic", - gcred, - from_kuid(&init_user_ns, acred->uid), - from_kgid(&init_user_ns, acred->gid)); - return &gcred->gc_base; -} - -static void -generic_free_cred(struct rpc_cred *cred) -{ - struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); - - dprintk("RPC: generic_free_cred %p\n", gcred); - if (gcred->acred.group_info != NULL) - put_group_info(gcred->acred.group_info); - kfree(gcred); -} - -static void -generic_free_cred_callback(struct rcu_head *head) -{ - struct rpc_cred *cred = container_of(head, struct rpc_cred, cr_rcu); - generic_free_cred(cred); -} - -static void -generic_destroy_cred(struct rpc_cred *cred) -{ - call_rcu(&cred->cr_rcu, generic_free_cred_callback); -} - -static int -machine_cred_match(struct auth_cred *acred, struct generic_cred *gcred, int flags) -{ - if (!gcred->acred.machine_cred || - gcred->acred.principal != acred->principal || - !uid_eq(gcred->acred.uid, acred->uid) || - !gid_eq(gcred->acred.gid, acred->gid)) - return 0; - return 1; -} - -/* - * Match credentials against current process creds. - */ -static int -generic_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) -{ - struct generic_cred *gcred = container_of(cred, struct generic_cred, gc_base); - int i; - - if (acred->machine_cred) - return machine_cred_match(acred, gcred, flags); - - if (!uid_eq(gcred->acred.uid, acred->uid) || - !gid_eq(gcred->acred.gid, acred->gid) || - gcred->acred.machine_cred != 0) - goto out_nomatch; - - /* Optimisation in the case where pointers are identical... */ - if (gcred->acred.group_info == acred->group_info) - goto out_match; - - /* Slow path... */ - if (gcred->acred.group_info->ngroups != acred->group_info->ngroups) - goto out_nomatch; - for (i = 0; i < gcred->acred.group_info->ngroups; i++) { - if (!gid_eq(gcred->acred.group_info->gid[i], - acred->group_info->gid[i])) - goto out_nomatch; - } -out_match: - return 1; -out_nomatch: - return 0; -} - -int __init rpc_init_generic_auth(void) -{ - return rpcauth_init_credcache(&generic_auth); -} - -void rpc_destroy_generic_auth(void) -{ - rpcauth_destroy_credcache(&generic_auth); -} - -/* - * Test the the current time (now) against the underlying credential key expiry - * minus a timeout and setup notification. - * - * The normal case: - * If 'now' is before the key expiry minus RPC_KEY_EXPIRE_TIMEO, set - * the RPC_CRED_NOTIFY_TIMEOUT flag to setup the underlying credential - * rpc_credops crmatch routine to notify this generic cred when it's key - * expiration is within RPC_KEY_EXPIRE_TIMEO, and return 0. - * - * The error case: - * If the underlying cred lookup fails, return -EACCES. - * - * The 'almost' error case: - * If 'now' is within key expiry minus RPC_KEY_EXPIRE_TIMEO, but not within - * key expiry minus RPC_KEY_EXPIRE_FAIL, set the RPC_CRED_EXPIRE_SOON bit - * on the acred ac_flags and return 0. - */ -static int -generic_key_timeout(struct rpc_auth *auth, struct rpc_cred *cred) -{ - struct auth_cred *acred = &container_of(cred, struct generic_cred, - gc_base)->acred; - struct rpc_cred *tcred; - int ret = 0; - - - /* Fast track for non crkey_timeout (no key) underlying credentials */ - if (auth->au_flags & RPCAUTH_AUTH_NO_CRKEY_TIMEOUT) - return 0; - - /* Fast track for the normal case */ - if (test_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags)) - return 0; - - /* lookup_cred either returns a valid referenced rpc_cred, or PTR_ERR */ - tcred = auth->au_ops->lookup_cred(auth, acred, 0); - if (IS_ERR(tcred)) - return -EACCES; - - /* Test for the almost error case */ - ret = tcred->cr_ops->crkey_timeout(tcred); - if (ret != 0) { - set_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); - ret = 0; - } else { - /* In case underlying cred key has been reset */ - if (test_and_clear_bit(RPC_CRED_KEY_EXPIRE_SOON, - &acred->ac_flags)) - dprintk("RPC: UID %d Credential key reset\n", - from_kuid(&init_user_ns, tcred->cr_uid)); - /* set up fasttrack for the normal case */ - set_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags); - } - - put_rpccred(tcred); - return ret; -} - -static const struct rpc_authops generic_auth_ops = { - .owner = THIS_MODULE, - .au_name = "Generic", - .hash_cred = generic_hash_cred, - .lookup_cred = generic_lookup_cred, - .crcreate = generic_create_cred, - .key_timeout = generic_key_timeout, -}; - -static struct rpc_auth generic_auth = { - .au_ops = &generic_auth_ops, - .au_count = REFCOUNT_INIT(1), -}; - -static bool generic_key_to_expire(struct rpc_cred *cred) -{ - struct auth_cred *acred = &container_of(cred, struct generic_cred, - gc_base)->acred; - return test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); -} - -static const struct rpc_credops generic_credops = { - .cr_name = "Generic cred", - .crdestroy = generic_destroy_cred, - .crbind = generic_bind_cred, - .crmatch = generic_match, - .crkey_to_expire = generic_key_to_expire, -}; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index ba765473d1f0..dc86713b32b6 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -565,7 +565,7 @@ gss_setup_upcall(struct gss_auth *gss_auth, struct rpc_cred *cred) struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base); struct gss_upcall_msg *gss_new, *gss_msg; - kuid_t uid = cred->cr_uid; + kuid_t uid = cred->cr_cred->fsuid; gss_new = gss_alloc_msg(gss_auth, uid, gss_cred->gc_principal); if (IS_ERR(gss_new)) @@ -604,7 +604,7 @@ gss_refresh_upcall(struct rpc_task *task) int err = 0; dprintk("RPC: %5u %s for uid %u\n", - task->tk_pid, __func__, from_kuid(&init_user_ns, cred->cr_uid)); + task->tk_pid, __func__, from_kuid(&init_user_ns, cred->cr_cred->fsuid)); gss_msg = gss_setup_upcall(gss_auth, cred); if (PTR_ERR(gss_msg) == -EAGAIN) { /* XXX: warning on the first, under the assumption we @@ -637,7 +637,7 @@ gss_refresh_upcall(struct rpc_task *task) out: dprintk("RPC: %5u %s for uid %u result %d\n", task->tk_pid, __func__, - from_kuid(&init_user_ns, cred->cr_uid), err); + from_kuid(&init_user_ns, cred->cr_cred->fsuid), err); return err; } @@ -653,7 +653,7 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred) int err; dprintk("RPC: %s for uid %u\n", - __func__, from_kuid(&init_user_ns, cred->cr_uid)); + __func__, from_kuid(&init_user_ns, cred->cr_cred->fsuid)); retry: err = 0; /* if gssd is down, just skip upcalling altogether */ @@ -701,7 +701,7 @@ out_intr: gss_release_msg(gss_msg); out: dprintk("RPC: %s for uid %u result %d\n", - __func__, from_kuid(&init_user_ns, cred->cr_uid), err); + __func__, from_kuid(&init_user_ns, cred->cr_cred->fsuid), err); return err; } @@ -1248,7 +1248,7 @@ gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred) new = kzalloc(sizeof(*gss_cred), GFP_NOIO); if (new) { struct auth_cred acred = { - .uid = gss_cred->gc_base.cr_uid, + .cred = gss_cred->gc_base.cr_cred, }; struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1); @@ -1343,6 +1343,7 @@ gss_destroy_nullcred(struct rpc_cred *cred) struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1); RCU_INIT_POINTER(gss_cred->gc_ctx, NULL); + put_cred(cred->cr_cred); call_rcu(&cred->cr_rcu, gss_free_cred_callback); if (ctx) gss_put_ctx(ctx); @@ -1361,7 +1362,7 @@ gss_destroy_cred(struct rpc_cred *cred) static int gss_hash_cred(struct auth_cred *acred, unsigned int hashbits) { - return hash_64(from_kuid(&init_user_ns, acred->uid), hashbits); + return hash_64(from_kuid(&init_user_ns, acred->cred->fsuid), hashbits); } /* @@ -1381,7 +1382,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t int err = -ENOMEM; dprintk("RPC: %s for uid %d, flavor %d\n", - __func__, from_kuid(&init_user_ns, acred->uid), + __func__, from_kuid(&init_user_ns, acred->cred->fsuid), auth->au_flavor); if (!(cred = kzalloc(sizeof(*cred), gfp))) @@ -1394,9 +1395,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t */ cred->gc_base.cr_flags = 1UL << RPCAUTH_CRED_NEW; cred->gc_service = gss_auth->service; - cred->gc_principal = NULL; - if (acred->machine_cred) - cred->gc_principal = acred->principal; + cred->gc_principal = acred->principal; kref_get(&gss_auth->kref); return &cred->gc_base; @@ -1518,23 +1517,10 @@ out: if (gss_cred->gc_principal == NULL) return 0; ret = strcmp(acred->principal, gss_cred->gc_principal) == 0; - goto check_expire; - } - if (gss_cred->gc_principal != NULL) - return 0; - ret = uid_eq(rc->cr_uid, acred->uid); - -check_expire: - if (ret == 0) - return ret; - - /* Notify acred users of GSS context expiration timeout */ - if (test_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags) && - (gss_key_timeout(rc) != 0)) { - /* test will now be done from generic cred */ - test_and_clear_bit(RPC_CRED_NOTIFY_TIMEOUT, &acred->ac_flags); - /* tell NFS layer that key will expire soon */ - set_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags); + } else { + if (gss_cred->gc_principal != NULL) + return 0; + ret = uid_eq(rc->cr_cred->fsuid, acred->cred->fsuid); } return ret; } @@ -1607,9 +1593,8 @@ static int gss_renew_cred(struct rpc_task *task) gc_base); struct rpc_auth *auth = oldcred->cr_auth; struct auth_cred acred = { - .uid = oldcred->cr_uid, + .cred = oldcred->cr_cred, .principal = gss_cred->gc_principal, - .machine_cred = (gss_cred->gc_principal != NULL ? 1 : 0), }; struct rpc_cred *new; @@ -2110,7 +2095,6 @@ static const struct rpc_credops gss_credops = { .cr_name = "AUTH_GSS", .crdestroy = gss_destroy_cred, .cr_init = gss_cred_init, - .crbind = rpcauth_generic_bind_cred, .crmatch = gss_match, .crmarshal = gss_marshal, .crrefresh = gss_refresh, @@ -2125,7 +2109,6 @@ static const struct rpc_credops gss_credops = { static const struct rpc_credops gss_nullops = { .cr_name = "AUTH_GSS", .crdestroy = gss_destroy_nullcred, - .crbind = rpcauth_generic_bind_cred, .crmatch = gss_match, .crmarshal = gss_marshal, .crrefresh = gss_refresh_null, diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 16ac0f4cb7d8..379318dff534 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -244,7 +244,7 @@ gss_mech_get_by_pseudoflavor(u32 pseudoflavor) /** * gss_mech_list_pseudoflavors - Discover registered GSS pseudoflavors - * @array: array to fill in + * @array_ptr: array to fill in * @size: size of "array" * * Returns the number of array items filled in, or a negative errno. diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 1ece4bc3eb8d..152790ed309c 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1142,7 +1142,7 @@ static int svcauth_gss_legacy_init(struct svc_rqst *rqstp, struct kvec *resv = &rqstp->rq_res.head[0]; struct rsi *rsip, rsikey; int ret; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); memset(&rsikey, 0, sizeof(rsikey)); ret = gss_read_verf(gc, argv, authp, @@ -1253,7 +1253,7 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, uint64_t handle; int status; int ret; - struct net *net = rqstp->rq_xprt->xpt_net; + struct net *net = SVC_NET(rqstp); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); memset(&ud, 0, sizeof(ud)); @@ -1444,7 +1444,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) __be32 *rpcstart; __be32 *reject_stat = resv->iov_base + resv->iov_len; int ret; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); dprintk("RPC: svcauth_gss: argv->iov_len = %zd\n", argv->iov_len); @@ -1734,7 +1734,7 @@ svcauth_gss_release(struct svc_rqst *rqstp) struct rpc_gss_wire_cred *gc = &gsd->clcred; struct xdr_buf *resbuf = &rqstp->rq_res; int stat = -EINVAL; - struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); + struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id); if (gc->gc_proc != RPC_GSS_PROC_DATA) goto out; diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index 2694a1bc026b..d0ceac57c06e 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -36,8 +36,6 @@ nul_destroy(struct rpc_auth *auth) static struct rpc_cred * nul_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { - if (flags & RPCAUTH_LOOKUP_RCU) - return &null_cred; return get_rpccred(&null_cred); } @@ -116,7 +114,6 @@ static struct rpc_auth null_auth = { .au_cslack = NUL_CALLSLACK, .au_rslack = NUL_REPLYSLACK, - .au_flags = RPCAUTH_AUTH_NO_CRKEY_TIMEOUT, .au_ops = &authnull_ops, .au_flavor = RPC_AUTH_NULL, .au_count = REFCOUNT_INIT(1), @@ -126,7 +123,6 @@ static const struct rpc_credops null_credops = { .cr_name = "AUTH_NULL", .crdestroy = nul_destroy_cred, - .crbind = rpcauth_generic_bind_cred, .crmatch = nul_match, .crmarshal = nul_marshal, .crrefresh = nul_refresh, diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 4c1c7e56288f..387f6b3ffbea 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -11,16 +11,11 @@ #include <linux/types.h> #include <linux/sched.h> #include <linux/module.h> +#include <linux/mempool.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/auth.h> #include <linux/user_namespace.h> -struct unx_cred { - struct rpc_cred uc_base; - kgid_t uc_gid; - kgid_t uc_gids[UNX_NGROUPS]; -}; -#define uc_uid uc_base.cr_uid #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # define RPCDBG_FACILITY RPCDBG_AUTH @@ -28,6 +23,7 @@ struct unx_cred { static struct rpc_auth unix_auth; static const struct rpc_credops unix_credops; +static mempool_t *unix_pool; static struct rpc_auth * unx_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) @@ -42,15 +38,6 @@ static void unx_destroy(struct rpc_auth *auth) { dprintk("RPC: destroying UNIX authenticator %p\n", auth); - rpcauth_clear_credcache(auth->au_credcache); -} - -static int -unx_hash_cred(struct auth_cred *acred, unsigned int hashbits) -{ - return hash_64(from_kgid(&init_user_ns, acred->gid) | - ((u64)from_kuid(&init_user_ns, acred->uid) << - (sizeof(gid_t) * 8)), hashbits); } /* @@ -59,52 +46,24 @@ unx_hash_cred(struct auth_cred *acred, unsigned int hashbits) static struct rpc_cred * unx_lookup_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) { - return rpcauth_lookup_credcache(auth, acred, flags, GFP_NOFS); -} - -static struct rpc_cred * -unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags, gfp_t gfp) -{ - struct unx_cred *cred; - unsigned int groups = 0; - unsigned int i; + struct rpc_cred *ret = mempool_alloc(unix_pool, GFP_NOFS); dprintk("RPC: allocating UNIX cred for uid %d gid %d\n", - from_kuid(&init_user_ns, acred->uid), - from_kgid(&init_user_ns, acred->gid)); - - if (!(cred = kmalloc(sizeof(*cred), gfp))) - return ERR_PTR(-ENOMEM); + from_kuid(&init_user_ns, acred->cred->fsuid), + from_kgid(&init_user_ns, acred->cred->fsgid)); - rpcauth_init_cred(&cred->uc_base, acred, auth, &unix_credops); - cred->uc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; - - if (acred->group_info != NULL) - groups = acred->group_info->ngroups; - if (groups > UNX_NGROUPS) - groups = UNX_NGROUPS; - - cred->uc_gid = acred->gid; - for (i = 0; i < groups; i++) - cred->uc_gids[i] = acred->group_info->gid[i]; - if (i < UNX_NGROUPS) - cred->uc_gids[i] = INVALID_GID; - - return &cred->uc_base; -} - -static void -unx_free_cred(struct unx_cred *unx_cred) -{ - dprintk("RPC: unx_free_cred %p\n", unx_cred); - kfree(unx_cred); + rpcauth_init_cred(ret, acred, auth, &unix_credops); + ret->cr_flags = 1UL << RPCAUTH_CRED_UPTODATE; + return ret; } static void unx_free_cred_callback(struct rcu_head *head) { - struct unx_cred *unx_cred = container_of(head, struct unx_cred, uc_base.cr_rcu); - unx_free_cred(unx_cred); + struct rpc_cred *rpc_cred = container_of(head, struct rpc_cred, cr_rcu); + dprintk("RPC: unx_free_cred %p\n", rpc_cred); + put_cred(rpc_cred->cr_cred); + mempool_free(rpc_cred, unix_pool); } static void @@ -114,30 +73,32 @@ unx_destroy_cred(struct rpc_cred *cred) } /* - * Match credentials against current process creds. - * The root_override argument takes care of cases where the caller may - * request root creds (e.g. for NFS swapping). + * Match credentials against current the auth_cred. */ static int -unx_match(struct auth_cred *acred, struct rpc_cred *rcred, int flags) +unx_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) { - struct unx_cred *cred = container_of(rcred, struct unx_cred, uc_base); unsigned int groups = 0; unsigned int i; + if (cred->cr_cred == acred->cred) + return 1; - if (!uid_eq(cred->uc_uid, acred->uid) || !gid_eq(cred->uc_gid, acred->gid)) + if (!uid_eq(cred->cr_cred->fsuid, acred->cred->fsuid) || !gid_eq(cred->cr_cred->fsgid, acred->cred->fsgid)) return 0; - if (acred->group_info != NULL) - groups = acred->group_info->ngroups; + if (acred->cred && acred->cred->group_info != NULL) + groups = acred->cred->group_info->ngroups; if (groups > UNX_NGROUPS) groups = UNX_NGROUPS; + if (cred->cr_cred->group_info == NULL) + return groups == 0; + if (groups != cred->cr_cred->group_info->ngroups) + return 0; + for (i = 0; i < groups ; i++) - if (!gid_eq(cred->uc_gids[i], acred->group_info->gid[i])) + if (!gid_eq(cred->cr_cred->group_info->gid[i], acred->cred->group_info->gid[i])) return 0; - if (groups < UNX_NGROUPS && gid_valid(cred->uc_gids[groups])) - return 0; return 1; } @@ -149,9 +110,10 @@ static __be32 * unx_marshal(struct rpc_task *task, __be32 *p) { struct rpc_clnt *clnt = task->tk_client; - struct unx_cred *cred = container_of(task->tk_rqstp->rq_cred, struct unx_cred, uc_base); + struct rpc_cred *cred = task->tk_rqstp->rq_cred; __be32 *base, *hold; int i; + struct group_info *gi = cred->cr_cred->group_info; *p++ = htonl(RPC_AUTH_UNIX); base = p++; @@ -162,11 +124,12 @@ unx_marshal(struct rpc_task *task, __be32 *p) */ p = xdr_encode_array(p, clnt->cl_nodename, clnt->cl_nodelen); - *p++ = htonl((u32) from_kuid(&init_user_ns, cred->uc_uid)); - *p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gid)); + *p++ = htonl((u32) from_kuid(&init_user_ns, cred->cr_cred->fsuid)); + *p++ = htonl((u32) from_kgid(&init_user_ns, cred->cr_cred->fsgid)); hold = p++; - for (i = 0; i < UNX_NGROUPS && gid_valid(cred->uc_gids[i]); i++) - *p++ = htonl((u32) from_kgid(&init_user_ns, cred->uc_gids[i])); + if (gi) + for (i = 0; i < UNX_NGROUPS && i < gi->ngroups; i++) + *p++ = htonl((u32) from_kgid(&init_user_ns, gi->gid[i])); *hold = htonl(p - hold - 1); /* gid array length */ *base = htonl((p - base - 1) << 2); /* cred length */ @@ -213,12 +176,13 @@ unx_validate(struct rpc_task *task, __be32 *p) int __init rpc_init_authunix(void) { - return rpcauth_init_credcache(&unix_auth); + unix_pool = mempool_create_kmalloc_pool(16, sizeof(struct rpc_cred)); + return unix_pool ? 0 : -ENOMEM; } void rpc_destroy_authunix(void) { - rpcauth_destroy_credcache(&unix_auth); + mempool_destroy(unix_pool); } const struct rpc_authops authunix_ops = { @@ -227,16 +191,13 @@ const struct rpc_authops authunix_ops = { .au_name = "UNIX", .create = unx_create, .destroy = unx_destroy, - .hash_cred = unx_hash_cred, .lookup_cred = unx_lookup_cred, - .crcreate = unx_create_cred, }; static struct rpc_auth unix_auth = { .au_cslack = UNX_CALLSLACK, .au_rslack = NUL_REPLYSLACK, - .au_flags = RPCAUTH_AUTH_NO_CRKEY_TIMEOUT, .au_ops = &authunix_ops, .au_flavor = RPC_AUTH_UNIX, .au_count = REFCOUNT_INIT(1), @@ -246,7 +207,6 @@ static const struct rpc_credops unix_credops = { .cr_name = "AUTH_UNIX", .crdestroy = unx_destroy_cred, - .crbind = rpcauth_generic_bind_cred, .crmatch = unx_match, .crmarshal = unx_marshal, .crrefresh = unx_refresh, diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index fa5ba6ed3197..ec451b8114b0 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -197,7 +197,7 @@ out_free: /** * xprt_destroy_backchannel - Destroys the backchannel preallocated structures. * @xprt: the transport holding the preallocated strucures - * @max_reqs the maximum number of preallocated structures to destroy + * @max_reqs: the maximum number of preallocated structures to destroy * * Since these structures may have been allocated by multiple calls * to xprt_setup_backchannel, we only destroy up to the maximum number diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index f96345b1180e..12bb23b8e0c5 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -54,6 +54,11 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } +static void cache_fresh_locked(struct cache_head *head, time_t expiry, + struct cache_detail *detail); +static void cache_fresh_unlocked(struct cache_head *head, + struct cache_detail *detail); + static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail, struct cache_head *key, int hash) @@ -100,6 +105,7 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; + cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; } @@ -115,8 +121,10 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, cache_get(new); spin_unlock(&detail->hash_lock); - if (freeme) + if (freeme) { + cache_fresh_unlocked(freeme, detail); cache_put(freeme, detail); + } return new; } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 24cbddc44c88..71d9599b5816 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -627,6 +627,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new->cl_noretranstimeo = clnt->cl_noretranstimeo; new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; + new->cl_principal = clnt->cl_principal; return new; out_err: @@ -1029,7 +1030,7 @@ rpc_task_set_rpc_message(struct rpc_task *task, const struct rpc_message *msg) task->tk_msg.rpc_argp = msg->rpc_argp; task->tk_msg.rpc_resp = msg->rpc_resp; if (msg->rpc_cred != NULL) - task->tk_msg.rpc_cred = get_rpccred(msg->rpc_cred); + task->tk_msg.rpc_cred = get_cred(msg->rpc_cred); } } @@ -2521,9 +2522,8 @@ static int rpc_ping(struct rpc_clnt *clnt) .rpc_proc = &rpcproc_null, }; int err; - msg.rpc_cred = authnull_ops.lookup_cred(NULL, NULL, 0); - err = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN); - put_rpccred(msg.rpc_cred); + err = rpc_call_sync(clnt, &msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN | + RPC_TASK_NULLCREDS); return err; } @@ -2534,15 +2534,15 @@ struct rpc_task *rpc_call_null_helper(struct rpc_clnt *clnt, { struct rpc_message msg = { .rpc_proc = &rpcproc_null, - .rpc_cred = cred, }; struct rpc_task_setup task_setup_data = { .rpc_client = clnt, .rpc_xprt = xprt, .rpc_message = &msg, + .rpc_op_cred = cred, .callback_ops = (ops != NULL) ? ops : &rpc_default_ops, .callback_data = data, - .flags = flags, + .flags = flags | RPC_TASK_NULLCREDS, }; return rpc_run_task(&task_setup_data); @@ -2593,7 +2593,6 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, void *dummy) { struct rpc_cb_add_xprt_calldata *data; - struct rpc_cred *cred; struct rpc_task *task; data = kmalloc(sizeof(*data), GFP_NOFS); @@ -2602,11 +2601,9 @@ int rpc_clnt_test_and_add_xprt(struct rpc_clnt *clnt, data->xps = xprt_switch_get(xps); data->xprt = xprt_get(xprt); - cred = authnull_ops.lookup_cred(NULL, NULL, 0); - task = rpc_call_null_helper(clnt, xprt, cred, - RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC, + task = rpc_call_null_helper(clnt, xprt, NULL, + RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC|RPC_TASK_NULLCREDS, &rpc_cb_add_xprt_call_ops, data); - put_rpccred(cred); if (IS_ERR(task)) return PTR_ERR(task); rpc_put_task(task); @@ -2637,7 +2634,6 @@ int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *data) { - struct rpc_cred *cred; struct rpc_task *task; struct rpc_add_xprt_test *xtest = (struct rpc_add_xprt_test *)data; int status = -EADDRINUSE; @@ -2649,11 +2645,9 @@ int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *clnt, goto out_err; /* Test the connection */ - cred = authnull_ops.lookup_cred(NULL, NULL, 0); - task = rpc_call_null_helper(clnt, xprt, cred, - RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + task = rpc_call_null_helper(clnt, xprt, NULL, + RPC_TASK_SOFT | RPC_TASK_SOFTCONN | RPC_TASK_NULLCREDS, NULL, NULL); - put_rpccred(cred); if (IS_ERR(task)) { status = PTR_ERR(task); goto out_err; @@ -2667,6 +2661,9 @@ int rpc_clnt_setup_test_and_add_xprt(struct rpc_clnt *clnt, /* rpc_xprt_switch and rpc_xprt are deferrenced by add_xprt_test() */ xtest->add_xprt_test(clnt, xprt, xtest->data); + xprt_put(xprt); + xprt_switch_put(xps); + /* so that rpc_clnt_add_xprt does not call rpc_xprt_switch_add_xprt */ return 1; out_err: diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 4fda18d47e2c..69663681bf9d 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1266,7 +1266,7 @@ static const struct rpc_pipe_ops gssd_dummy_pipe_ops = { * that this file will be there and have a certain format. */ static int -rpc_show_dummy_info(struct seq_file *m, void *v) +rpc_dummy_info_show(struct seq_file *m, void *v) { seq_printf(m, "RPC server: %s\n", utsname()->nodename); seq_printf(m, "service: foo (1) version 0\n"); @@ -1275,25 +1275,12 @@ rpc_show_dummy_info(struct seq_file *m, void *v) seq_printf(m, "port: 0\n"); return 0; } - -static int -rpc_dummy_info_open(struct inode *inode, struct file *file) -{ - return single_open(file, rpc_show_dummy_info, NULL); -} - -static const struct file_operations rpc_dummy_info_operations = { - .owner = THIS_MODULE, - .open = rpc_dummy_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(rpc_dummy_info); static const struct rpc_filelist gssd_dummy_info_file[] = { [0] = { .name = "info", - .i_fop = &rpc_dummy_info_operations, + .i_fop = &rpc_dummy_info_fops, .mode = S_IFREG | 0400, }, }; diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index c7872bc13860..41a971ac1c63 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -752,7 +752,7 @@ void rpcb_getport_async(struct rpc_task *task) goto bailout_nofree; } - map = kzalloc(sizeof(struct rpcbind_args), GFP_ATOMIC); + map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS); if (!map) { status = -ENOMEM; dprintk("RPC: %5u %s: no memory available\n", @@ -770,7 +770,13 @@ void rpcb_getport_async(struct rpc_task *task) case RPCBVERS_4: case RPCBVERS_3: map->r_netid = xprt->address_strings[RPC_DISPLAY_NETID]; - map->r_addr = rpc_sockaddr2uaddr(sap, GFP_ATOMIC); + map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS); + if (!map->r_addr) { + status = -ENOMEM; + dprintk("RPC: %5u %s: no memory available\n", + task->tk_pid, __func__); + goto bailout_free_args; + } map->r_owner = ""; break; case RPCBVERS_2: @@ -793,6 +799,8 @@ void rpcb_getport_async(struct rpc_task *task) rpc_put_task(child); return; +bailout_free_args: + kfree(map); bailout_release_client: rpc_release_client(rpcb_clnt); bailout_nofree: diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 57ca5bead1cb..adc3c40cc733 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -997,6 +997,8 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta task->tk_xprt = xprt_get(task_setup_data->rpc_xprt); + task->tk_op_cred = get_rpccred(task_setup_data->rpc_op_cred); + if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; @@ -1054,6 +1056,7 @@ static void rpc_free_task(struct rpc_task *task) { unsigned short tk_flags = task->tk_flags; + put_rpccred(task->tk_op_cred); rpc_release_calldata(task->tk_ops, task->tk_calldata); if (tk_flags & RPC_TASK_DYNAMIC) { @@ -1071,7 +1074,7 @@ static void rpc_release_resources_task(struct rpc_task *task) { xprt_release(task); if (task->tk_msg.rpc_cred) { - put_rpccred(task->tk_msg.rpc_cred); + put_cred(task->tk_msg.rpc_cred); task->tk_msg.rpc_cred = NULL; } rpc_task_release_client(task); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index d13e05f1a990..e87ddb9f7feb 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1145,6 +1145,17 @@ static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, .. #endif /* + * Setup response header for TCP, it has a 4B record length field. + */ +static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) +{ + struct kvec *resv = &rqstp->rq_res.head[0]; + + /* tcp needs a space for the record length... */ + svc_putnl(resv, 0); +} + +/* * Common routine for processing the RPC request. */ static int @@ -1172,7 +1183,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) clear_bit(RQ_DROPME, &rqstp->rq_flags); /* Setup reply header */ - rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp); + if (rqstp->rq_prot == IPPROTO_TCP) + svc_tcp_prep_reply_hdr(rqstp); svc_putu32(resv, rqstp->rq_xid); @@ -1244,7 +1256,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) * for lower versions. RPC_PROG_MISMATCH seems to be the closest * fit. */ - if (versp->vs_need_cong_ctrl && + if (versp->vs_need_cong_ctrl && rqstp->rq_xprt && !test_bit(XPT_CONG_CTRL, &rqstp->rq_xprt->xpt_flags)) goto err_bad_vers; @@ -1336,7 +1348,7 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) return 0; close: - if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) + if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags)) svc_close_xprt(rqstp->rq_xprt); dprintk("svc: svc_process close\n"); return 0; @@ -1459,10 +1471,10 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, dprintk("svc: %s(%p)\n", __func__, req); /* Build the svc_rqst used by the common processing routine */ - rqstp->rq_xprt = serv->sv_bc_xprt; rqstp->rq_xid = req->rq_xid; rqstp->rq_prot = req->rq_xprt->prot; rqstp->rq_server = serv; + rqstp->rq_bc_net = req->rq_xprt->xprt_net; rqstp->rq_addrlen = sizeof(req->rq_xprt->addr); memcpy(&rqstp->rq_addr, &req->rq_xprt->addr, rqstp->rq_addrlen); @@ -1499,9 +1511,9 @@ bc_svc_process(struct svc_serv *serv, struct rpc_rqst *req, if (!proc_error) { /* Processing error: drop the request */ xprt_free_bc_request(req); - return 0; + error = -EINVAL; + goto out; } - /* Finally, send the reply synchronously */ memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); task = rpc_run_bc_task(req); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 51d36230b6e3..4eb8fbf2508d 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -296,9 +296,9 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, request_module("svc%s", xprt_name); err = _svc_create_xprt(serv, xprt_name, net, family, port, flags); } - if (err) + if (err < 0) dprintk("svc: transport %s not found, err %d\n", - xprt_name, err); + xprt_name, -err); return err; } EXPORT_SYMBOL_GPL(svc_create_xprt); @@ -468,10 +468,11 @@ out: */ void svc_reserve(struct svc_rqst *rqstp, int space) { + struct svc_xprt *xprt = rqstp->rq_xprt; + space += rqstp->rq_res.head[0].iov_len; - if (space < rqstp->rq_reserved) { - struct svc_xprt *xprt = rqstp->rq_xprt; + if (xprt && space < rqstp->rq_reserved) { atomic_sub((rqstp->rq_reserved - space), &xprt->xpt_reserved); rqstp->rq_reserved = space; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 986f3ed7d1a2..a6a060925e5d 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -70,13 +70,6 @@ static void svc_sock_free(struct svc_xprt *); static struct svc_xprt *svc_create_socket(struct svc_serv *, int, struct net *, struct sockaddr *, int, int); -#if defined(CONFIG_SUNRPC_BACKCHANNEL) -static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, - struct net *, struct sockaddr *, - int, int); -static void svc_bc_sock_free(struct svc_xprt *xprt); -#endif /* CONFIG_SUNRPC_BACKCHANNEL */ - #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key svc_key[2]; static struct lock_class_key svc_slock_key[2]; @@ -549,7 +542,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) /* Don't enable netstamp, sunrpc doesn't need that much accuracy */ } - svsk->sk_sk->sk_stamp = skb->tstamp; + sock_write_timestamp(svsk->sk_sk, skb->tstamp); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */ len = skb->len; @@ -617,10 +610,6 @@ svc_udp_sendto(struct svc_rqst *rqstp) return error; } -static void svc_udp_prep_reply_hdr(struct svc_rqst *rqstp) -{ -} - static int svc_udp_has_wspace(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); @@ -664,7 +653,6 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_release_rqst = svc_release_udp_skb, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, - .xpo_prep_reply_hdr = svc_udp_prep_reply_hdr, .xpo_has_wspace = svc_udp_has_wspace, .xpo_accept = svc_udp_accept, .xpo_secure_port = svc_sock_secure_port, @@ -1170,17 +1158,6 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) return sent; } -/* - * Setup response header. TCP has a 4B record length field. - */ -static void svc_tcp_prep_reply_hdr(struct svc_rqst *rqstp) -{ - struct kvec *resv = &rqstp->rq_res.head[0]; - - /* tcp needs a space for the record length... */ - svc_putnl(resv, 0); -} - static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, struct net *net, struct sockaddr *sa, int salen, @@ -1189,58 +1166,6 @@ static struct svc_xprt *svc_tcp_create(struct svc_serv *serv, return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); } -#if defined(CONFIG_SUNRPC_BACKCHANNEL) -static struct svc_xprt *svc_bc_create_socket(struct svc_serv *, int, - struct net *, struct sockaddr *, - int, int); -static void svc_bc_sock_free(struct svc_xprt *xprt); - -static struct svc_xprt *svc_bc_tcp_create(struct svc_serv *serv, - struct net *net, - struct sockaddr *sa, int salen, - int flags) -{ - return svc_bc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags); -} - -static void svc_bc_tcp_sock_detach(struct svc_xprt *xprt) -{ -} - -static const struct svc_xprt_ops svc_tcp_bc_ops = { - .xpo_create = svc_bc_tcp_create, - .xpo_detach = svc_bc_tcp_sock_detach, - .xpo_free = svc_bc_sock_free, - .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, - .xpo_secure_port = svc_sock_secure_port, -}; - -static struct svc_xprt_class svc_tcp_bc_class = { - .xcl_name = "tcp-bc", - .xcl_owner = THIS_MODULE, - .xcl_ops = &svc_tcp_bc_ops, - .xcl_max_payload = RPCSVC_MAXPAYLOAD_TCP, -}; - -static void svc_init_bc_xprt_sock(void) -{ - svc_reg_xprt_class(&svc_tcp_bc_class); -} - -static void svc_cleanup_bc_xprt_sock(void) -{ - svc_unreg_xprt_class(&svc_tcp_bc_class); -} -#else /* CONFIG_SUNRPC_BACKCHANNEL */ -static void svc_init_bc_xprt_sock(void) -{ -} - -static void svc_cleanup_bc_xprt_sock(void) -{ -} -#endif /* CONFIG_SUNRPC_BACKCHANNEL */ - static const struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, @@ -1248,7 +1173,6 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_release_rqst = svc_release_skb, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, - .xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr, .xpo_has_wspace = svc_tcp_has_wspace, .xpo_accept = svc_tcp_accept, .xpo_secure_port = svc_sock_secure_port, @@ -1267,14 +1191,12 @@ void svc_init_xprt_sock(void) { svc_reg_xprt_class(&svc_tcp_class); svc_reg_xprt_class(&svc_udp_class); - svc_init_bc_xprt_sock(); } void svc_cleanup_xprt_sock(void) { svc_unreg_xprt_class(&svc_tcp_class); svc_unreg_xprt_class(&svc_udp_class); - svc_cleanup_bc_xprt_sock(); } static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) @@ -1595,45 +1517,3 @@ static void svc_sock_free(struct svc_xprt *xprt) sock_release(svsk->sk_sock); kfree(svsk); } - -#if defined(CONFIG_SUNRPC_BACKCHANNEL) -/* - * Create a back channel svc_xprt which shares the fore channel socket. - */ -static struct svc_xprt *svc_bc_create_socket(struct svc_serv *serv, - int protocol, - struct net *net, - struct sockaddr *sin, int len, - int flags) -{ - struct svc_sock *svsk; - struct svc_xprt *xprt; - - if (protocol != IPPROTO_TCP) { - printk(KERN_WARNING "svc: only TCP sockets" - " supported on shared back channel\n"); - return ERR_PTR(-EINVAL); - } - - svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); - if (!svsk) - return ERR_PTR(-ENOMEM); - - xprt = &svsk->sk_xprt; - svc_xprt_init(net, &svc_tcp_bc_class, xprt, serv); - set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags); - - serv->sv_bc_xprt = xprt; - - return xprt; -} - -/* - * Free a back channel svc_sock. - */ -static void svc_bc_sock_free(struct svc_xprt *xprt) -{ - if (xprt) - kfree(container_of(xprt, struct svc_sock, sk_xprt)); -} -#endif /* CONFIG_SUNRPC_BACKCHANNEL */ diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index e2d64c7138c3..8394124126f8 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -383,7 +383,7 @@ void xprt_iter_init_listall(struct rpc_xprt_iter *xpi, /** * xprt_iter_xchg_switch - Atomically swap out the rpc_xprt_switch * @xpi: pointer to rpc_xprt_iter - * @xps: pointer to a new rpc_xprt_switch or NULL + * @newswitch: pointer to a new rpc_xprt_switch or NULL * * Swaps out the existing xpi->xpi_xpswitch with a new value. */ @@ -401,7 +401,7 @@ struct rpc_xprt_switch *xprt_iter_xchg_switch(struct rpc_xprt_iter *xpi, /** * xprt_iter_destroy - Destroys the xprt iterator - * @xpi pointer to rpc_xprt_iter + * @xpi: pointer to rpc_xprt_iter */ void xprt_iter_destroy(struct rpc_xprt_iter *xpi) { diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 8bf19e142b6b..8ed0377d7a18 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,8 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o -rpcrdma-y := transport.o rpc_rdma.o verbs.o \ - fmr_ops.o frwr_ops.o \ +rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o \ svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \ module.o diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index e5b367a3e517..0de9b3e63770 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -5,7 +5,6 @@ * Support for backward direction RPCs on RPC/RDMA. */ -#include <linux/module.h> #include <linux/sunrpc/xprt.h> #include <linux/sunrpc/svc.h> #include <linux/sunrpc/svc_xprt.h> @@ -20,29 +19,16 @@ #undef RPCRDMA_BACKCHANNEL_DEBUG -static void rpcrdma_bc_free_rqst(struct rpcrdma_xprt *r_xprt, - struct rpc_rqst *rqst) -{ - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct rpcrdma_req *req = rpcr_to_rdmar(rqst); - - spin_lock(&buf->rb_reqslock); - list_del(&req->rl_all); - spin_unlock(&buf->rb_reqslock); - - rpcrdma_destroy_req(req); -} - static int rpcrdma_bc_setup_reqs(struct rpcrdma_xprt *r_xprt, unsigned int count) { struct rpc_xprt *xprt = &r_xprt->rx_xprt; + struct rpcrdma_req *req; struct rpc_rqst *rqst; unsigned int i; for (i = 0; i < (count << 1); i++) { struct rpcrdma_regbuf *rb; - struct rpcrdma_req *req; size_t size; req = rpcrdma_create_req(r_xprt); @@ -68,7 +54,7 @@ static int rpcrdma_bc_setup_reqs(struct rpcrdma_xprt *r_xprt, return 0; out_fail: - rpcrdma_bc_free_rqst(r_xprt, rqst); + rpcrdma_req_destroy(req); return -ENOMEM; } @@ -101,7 +87,6 @@ int xprt_rdma_bc_setup(struct rpc_xprt *xprt, unsigned int reqs) goto out_free; r_xprt->rx_buf.rb_bc_srv_max_requests = reqs; - request_module("svcrdma"); trace_xprtrdma_cb_setup(r_xprt, reqs); return 0; @@ -114,26 +99,6 @@ out_err: } /** - * xprt_rdma_bc_up - Create transport endpoint for backchannel service - * @serv: server endpoint - * @net: network namespace - * - * The "xprt" is an implied argument: it supplies the name of the - * backchannel transport class. - * - * Returns zero on success, negative errno on failure - */ -int xprt_rdma_bc_up(struct svc_serv *serv, struct net *net) -{ - int ret; - - ret = svc_create_xprt(serv, "rdma-bc", net, PF_INET, 0, 0); - if (ret < 0) - return ret; - return 0; -} - -/** * xprt_rdma_bc_maxpayload - Return maximum backchannel message size * @xprt: transport * @@ -193,21 +158,21 @@ static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst) */ int xprt_rdma_bc_send_reply(struct rpc_rqst *rqst) { - struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt); + struct rpc_xprt *xprt = rqst->rq_xprt; + struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); struct rpcrdma_req *req = rpcr_to_rdmar(rqst); int rc; - if (!xprt_connected(rqst->rq_xprt)) - goto drop_connection; + if (!xprt_connected(xprt)) + return -ENOTCONN; - if (!xprt_request_get_cong(rqst->rq_xprt, rqst)) + if (!xprt_request_get_cong(xprt, rqst)) return -EBADSLT; rc = rpcrdma_bc_marshal_reply(rqst); if (rc < 0) goto failed_marshal; - rpcrdma_post_recvs(r_xprt, true); if (rpcrdma_ep_post(&r_xprt->rx_ia, &r_xprt->rx_ep, req)) goto drop_connection; return 0; @@ -216,7 +181,7 @@ failed_marshal: if (rc != -ENOTCONN) return rc; drop_connection: - xprt_disconnect_done(rqst->rq_xprt); + xprt_rdma_close(xprt); return -ENOTCONN; } @@ -227,7 +192,6 @@ drop_connection: */ void xprt_rdma_bc_destroy(struct rpc_xprt *xprt, unsigned int reqs) { - struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); struct rpc_rqst *rqst, *tmp; spin_lock(&xprt->bc_pa_lock); @@ -235,7 +199,7 @@ void xprt_rdma_bc_destroy(struct rpc_xprt *xprt, unsigned int reqs) list_del(&rqst->rq_bc_pa_list); spin_unlock(&xprt->bc_pa_lock); - rpcrdma_bc_free_rqst(r_xprt, rqst); + rpcrdma_req_destroy(rpcr_to_rdmar(rqst)); spin_lock(&xprt->bc_pa_lock); } @@ -251,9 +215,6 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) struct rpcrdma_req *req = rpcr_to_rdmar(rqst); struct rpc_xprt *xprt = rqst->rq_xprt; - dprintk("RPC: %s: freeing rqst %p (req %p)\n", - __func__, rqst, req); - rpcrdma_recv_buffer_put(req->rl_reply); req->rl_reply = NULL; @@ -339,7 +300,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, out_overflow: pr_warn("RPC/RDMA backchannel overflow\n"); - xprt_disconnect_done(xprt); + xprt_force_disconnect(xprt); /* This receive buffer gets reposted automatically * when the connection is re-established. */ diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c deleted file mode 100644 index fd8fea59fe92..000000000000 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ /dev/null @@ -1,337 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2015, 2017 Oracle. All rights reserved. - * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. - */ - -/* Lightweight memory registration using Fast Memory Regions (FMR). - * Referred to sometimes as MTHCAFMR mode. - * - * FMR uses synchronous memory registration and deregistration. - * FMR registration is known to be fast, but FMR deregistration - * can take tens of usecs to complete. - */ - -/* Normal operation - * - * A Memory Region is prepared for RDMA READ or WRITE using the - * ib_map_phys_fmr verb (fmr_op_map). When the RDMA operation is - * finished, the Memory Region is unmapped using the ib_unmap_fmr - * verb (fmr_op_unmap). - */ - -#include <linux/sunrpc/svc_rdma.h> - -#include "xprt_rdma.h" -#include <trace/events/rpcrdma.h> - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - -/* Maximum scatter/gather per FMR */ -#define RPCRDMA_MAX_FMR_SGES (64) - -/* Access mode of externally registered pages */ -enum { - RPCRDMA_FMR_ACCESS_FLAGS = IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ, -}; - -bool -fmr_is_supported(struct rpcrdma_ia *ia) -{ - if (!ia->ri_device->ops.alloc_fmr) { - pr_info("rpcrdma: 'fmr' mode is not supported by device %s\n", - ia->ri_device->name); - return false; - } - return true; -} - -static void -__fmr_unmap(struct rpcrdma_mr *mr) -{ - LIST_HEAD(l); - int rc; - - list_add(&mr->fmr.fm_mr->list, &l); - rc = ib_unmap_fmr(&l); - list_del(&mr->fmr.fm_mr->list); - if (rc) - pr_err("rpcrdma: final ib_unmap_fmr for %p failed %i\n", - mr, rc); -} - -/* Release an MR. - */ -static void -fmr_op_release_mr(struct rpcrdma_mr *mr) -{ - int rc; - - kfree(mr->fmr.fm_physaddrs); - kfree(mr->mr_sg); - - /* In case this one was left mapped, try to unmap it - * to prevent dealloc_fmr from failing with EBUSY - */ - __fmr_unmap(mr); - - rc = ib_dealloc_fmr(mr->fmr.fm_mr); - if (rc) - pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", - mr, rc); - - kfree(mr); -} - -/* MRs are dynamically allocated, so simply clean up and release the MR. - * A replacement MR will subsequently be allocated on demand. - */ -static void -fmr_mr_recycle_worker(struct work_struct *work) -{ - struct rpcrdma_mr *mr = container_of(work, struct rpcrdma_mr, mr_recycle); - struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - - trace_xprtrdma_mr_recycle(mr); - - trace_xprtrdma_mr_unmap(mr); - ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, - mr->mr_sg, mr->mr_nents, mr->mr_dir); - - spin_lock(&r_xprt->rx_buf.rb_mrlock); - list_del(&mr->mr_all); - r_xprt->rx_stats.mrs_recycled++; - spin_unlock(&r_xprt->rx_buf.rb_mrlock); - fmr_op_release_mr(mr); -} - -static int -fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) -{ - static struct ib_fmr_attr fmr_attr = { - .max_pages = RPCRDMA_MAX_FMR_SGES, - .max_maps = 1, - .page_shift = PAGE_SHIFT - }; - - mr->fmr.fm_physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES, - sizeof(u64), GFP_KERNEL); - if (!mr->fmr.fm_physaddrs) - goto out_free; - - mr->mr_sg = kcalloc(RPCRDMA_MAX_FMR_SGES, - sizeof(*mr->mr_sg), GFP_KERNEL); - if (!mr->mr_sg) - goto out_free; - - sg_init_table(mr->mr_sg, RPCRDMA_MAX_FMR_SGES); - - mr->fmr.fm_mr = ib_alloc_fmr(ia->ri_pd, RPCRDMA_FMR_ACCESS_FLAGS, - &fmr_attr); - if (IS_ERR(mr->fmr.fm_mr)) - goto out_fmr_err; - - INIT_LIST_HEAD(&mr->mr_list); - INIT_WORK(&mr->mr_recycle, fmr_mr_recycle_worker); - return 0; - -out_fmr_err: - dprintk("RPC: %s: ib_alloc_fmr returned %ld\n", __func__, - PTR_ERR(mr->fmr.fm_mr)); - -out_free: - kfree(mr->mr_sg); - kfree(mr->fmr.fm_physaddrs); - return -ENOMEM; -} - -/* On success, sets: - * ep->rep_attr.cap.max_send_wr - * ep->rep_attr.cap.max_recv_wr - * cdata->max_requests - * ia->ri_max_segs - */ -static int -fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, - struct rpcrdma_create_data_internal *cdata) -{ - int max_qp_wr; - - max_qp_wr = ia->ri_device->attrs.max_qp_wr; - max_qp_wr -= RPCRDMA_BACKWARD_WRS; - max_qp_wr -= 1; - if (max_qp_wr < RPCRDMA_MIN_SLOT_TABLE) - return -ENOMEM; - if (cdata->max_requests > max_qp_wr) - cdata->max_requests = max_qp_wr; - ep->rep_attr.cap.max_send_wr = cdata->max_requests; - ep->rep_attr.cap.max_send_wr += RPCRDMA_BACKWARD_WRS; - ep->rep_attr.cap.max_send_wr += 1; /* for ib_drain_sq */ - ep->rep_attr.cap.max_recv_wr = cdata->max_requests; - ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS; - ep->rep_attr.cap.max_recv_wr += 1; /* for ib_drain_rq */ - - ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS / - RPCRDMA_MAX_FMR_SGES); - ia->ri_max_segs += 2; /* segments for head and tail buffers */ - return 0; -} - -/* FMR mode conveys up to 64 pages of payload per chunk segment. - */ -static size_t -fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) -{ - return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, - RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES); -} - -/* Use the ib_map_phys_fmr() verb to register a memory region - * for remote access via RDMA READ or RDMA WRITE. - */ -static struct rpcrdma_mr_seg * -fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, - int nsegs, bool writing, struct rpcrdma_mr **out) -{ - struct rpcrdma_mr_seg *seg1 = seg; - int len, pageoff, i, rc; - struct rpcrdma_mr *mr; - u64 *dma_pages; - - mr = rpcrdma_mr_get(r_xprt); - if (!mr) - return ERR_PTR(-EAGAIN); - - pageoff = offset_in_page(seg1->mr_offset); - seg1->mr_offset -= pageoff; /* start of page */ - seg1->mr_len += pageoff; - len = -pageoff; - if (nsegs > RPCRDMA_MAX_FMR_SGES) - nsegs = RPCRDMA_MAX_FMR_SGES; - for (i = 0; i < nsegs;) { - if (seg->mr_page) - sg_set_page(&mr->mr_sg[i], - seg->mr_page, - seg->mr_len, - offset_in_page(seg->mr_offset)); - else - sg_set_buf(&mr->mr_sg[i], seg->mr_offset, - seg->mr_len); - len += seg->mr_len; - ++seg; - ++i; - /* Check for holes */ - if ((i < nsegs && offset_in_page(seg->mr_offset)) || - offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) - break; - } - mr->mr_dir = rpcrdma_data_dir(writing); - - mr->mr_nents = ib_dma_map_sg(r_xprt->rx_ia.ri_device, - mr->mr_sg, i, mr->mr_dir); - if (!mr->mr_nents) - goto out_dmamap_err; - trace_xprtrdma_mr_map(mr); - - for (i = 0, dma_pages = mr->fmr.fm_physaddrs; i < mr->mr_nents; i++) - dma_pages[i] = sg_dma_address(&mr->mr_sg[i]); - rc = ib_map_phys_fmr(mr->fmr.fm_mr, dma_pages, mr->mr_nents, - dma_pages[0]); - if (rc) - goto out_maperr; - - mr->mr_handle = mr->fmr.fm_mr->rkey; - mr->mr_length = len; - mr->mr_offset = dma_pages[0] + pageoff; - - *out = mr; - return seg; - -out_dmamap_err: - pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", - mr->mr_sg, i); - rpcrdma_mr_put(mr); - return ERR_PTR(-EIO); - -out_maperr: - pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", - len, (unsigned long long)dma_pages[0], - pageoff, mr->mr_nents, rc); - rpcrdma_mr_unmap_and_put(mr); - return ERR_PTR(-EIO); -} - -/* Post Send WR containing the RPC Call message. - */ -static int -fmr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) -{ - return ib_post_send(ia->ri_id->qp, &req->rl_sendctx->sc_wr, NULL); -} - -/* Invalidate all memory regions that were registered for "req". - * - * Sleeps until it is safe for the host CPU to access the - * previously mapped memory regions. - * - * Caller ensures that @mrs is not empty before the call. This - * function empties the list. - */ -static void -fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs) -{ - struct rpcrdma_mr *mr; - LIST_HEAD(unmap_list); - int rc; - - /* ORDER: Invalidate all of the req's MRs first - * - * ib_unmap_fmr() is slow, so use a single call instead - * of one call per mapped FMR. - */ - list_for_each_entry(mr, mrs, mr_list) { - dprintk("RPC: %s: unmapping fmr %p\n", - __func__, &mr->fmr); - trace_xprtrdma_mr_localinv(mr); - list_add_tail(&mr->fmr.fm_mr->list, &unmap_list); - } - r_xprt->rx_stats.local_inv_needed++; - rc = ib_unmap_fmr(&unmap_list); - if (rc) - goto out_release; - - /* ORDER: Now DMA unmap all of the req's MRs, and return - * them to the free MW list. - */ - while (!list_empty(mrs)) { - mr = rpcrdma_mr_pop(mrs); - list_del(&mr->fmr.fm_mr->list); - rpcrdma_mr_unmap_and_put(mr); - } - - return; - -out_release: - pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); - - while (!list_empty(mrs)) { - mr = rpcrdma_mr_pop(mrs); - list_del(&mr->fmr.fm_mr->list); - rpcrdma_mr_recycle(mr); - } -} - -const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { - .ro_map = fmr_op_map, - .ro_send = fmr_op_send, - .ro_unmap_sync = fmr_op_unmap_sync, - .ro_open = fmr_op_open, - .ro_maxpages = fmr_op_maxpages, - .ro_init_mr = fmr_op_init_mr, - .ro_release_mr = fmr_op_release_mr, - .ro_displayname = "fmr", - .ro_send_w_inv_ok = 0, -}; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index fc6378cc0c1c..6a561056b538 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -15,21 +15,21 @@ /* Normal operation * * A Memory Region is prepared for RDMA READ or WRITE using a FAST_REG - * Work Request (frwr_op_map). When the RDMA operation is finished, this + * Work Request (frwr_map). When the RDMA operation is finished, this * Memory Region is invalidated using a LOCAL_INV Work Request - * (frwr_op_unmap_sync). + * (frwr_unmap_sync). * * Typically these Work Requests are not signaled, and neither are RDMA * SEND Work Requests (with the exception of signaling occasionally to * prevent provider work queue overflows). This greatly reduces HCA * interrupt workload. * - * As an optimization, frwr_op_unmap marks MRs INVALID before the + * As an optimization, frwr_unmap marks MRs INVALID before the * LOCAL_INV WR is posted. If posting succeeds, the MR is placed on * rb_mrs immediately so that no work (like managing a linked list * under a spinlock) is needed in the completion upcall. * - * But this means that frwr_op_map() can occasionally encounter an MR + * But this means that frwr_map() can occasionally encounter an MR * that is INVALID but the LOCAL_INV WR has not completed. Work Queue * ordering prevents a subsequent FAST_REG WR from executing against * that MR while it is still being invalidated. @@ -57,14 +57,14 @@ * FLUSHED_LI: The MR was being invalidated when the QP entered ERROR * state, and the pending WR was flushed. * - * When frwr_op_map encounters FLUSHED and VALID MRs, they are recovered + * When frwr_map encounters FLUSHED and VALID MRs, they are recovered * with ib_dereg_mr and then are re-initialized. Because MR recovery * allocates fresh resources, it is deferred to a workqueue, and the * recovered MRs are placed back on the rb_mrs list when recovery is - * complete. frwr_op_map allocates another MR for the current RPC while + * complete. frwr_map allocates another MR for the current RPC while * the broken MR is reset. * - * To ensure that frwr_op_map doesn't encounter an MR that is marked + * To ensure that frwr_map doesn't encounter an MR that is marked * INVALID but that is about to be flushed due to a previous transport * disconnect, the transport connect worker attempts to drain all * pending send queue WRs before the transport is reconnected. @@ -80,8 +80,13 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -bool -frwr_is_supported(struct rpcrdma_ia *ia) +/** + * frwr_is_supported - Check if device supports FRWR + * @ia: interface adapter to check + * + * Returns true if device supports FRWR, otherwise false + */ +bool frwr_is_supported(struct rpcrdma_ia *ia) { struct ib_device_attr *attrs = &ia->ri_device->attrs; @@ -97,15 +102,18 @@ out_not_supported: return false; } -static void -frwr_op_release_mr(struct rpcrdma_mr *mr) +/** + * frwr_release_mr - Destroy one MR + * @mr: MR allocated by frwr_init_mr + * + */ +void frwr_release_mr(struct rpcrdma_mr *mr) { int rc; rc = ib_dereg_mr(mr->frwr.fr_mr); if (rc) - pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", - mr, rc); + trace_xprtrdma_frwr_dereg(mr, rc); kfree(mr->mr_sg); kfree(mr); } @@ -117,60 +125,78 @@ static void frwr_mr_recycle_worker(struct work_struct *work) { struct rpcrdma_mr *mr = container_of(work, struct rpcrdma_mr, mr_recycle); - enum rpcrdma_frwr_state state = mr->frwr.fr_state; struct rpcrdma_xprt *r_xprt = mr->mr_xprt; trace_xprtrdma_mr_recycle(mr); - if (state != FRWR_FLUSHED_LI) { + if (mr->mr_dir != DMA_NONE) { trace_xprtrdma_mr_unmap(mr); ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, mr->mr_sg, mr->mr_nents, mr->mr_dir); + mr->mr_dir = DMA_NONE; } spin_lock(&r_xprt->rx_buf.rb_mrlock); list_del(&mr->mr_all); r_xprt->rx_stats.mrs_recycled++; spin_unlock(&r_xprt->rx_buf.rb_mrlock); - frwr_op_release_mr(mr); + + frwr_release_mr(mr); } -static int -frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) +/** + * frwr_init_mr - Initialize one MR + * @ia: interface adapter + * @mr: generic MR to prepare for FRWR + * + * Returns zero if successful. Otherwise a negative errno + * is returned. + */ +int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) { unsigned int depth = ia->ri_max_frwr_depth; - struct rpcrdma_frwr *frwr = &mr->frwr; + struct scatterlist *sg; + struct ib_mr *frmr; int rc; - frwr->fr_mr = ib_alloc_mr(ia->ri_pd, ia->ri_mrtype, depth); - if (IS_ERR(frwr->fr_mr)) + frmr = ib_alloc_mr(ia->ri_pd, ia->ri_mrtype, depth); + if (IS_ERR(frmr)) goto out_mr_err; - mr->mr_sg = kcalloc(depth, sizeof(*mr->mr_sg), GFP_KERNEL); - if (!mr->mr_sg) + sg = kcalloc(depth, sizeof(*sg), GFP_KERNEL); + if (!sg) goto out_list_err; + mr->frwr.fr_mr = frmr; + mr->frwr.fr_state = FRWR_IS_INVALID; + mr->mr_dir = DMA_NONE; INIT_LIST_HEAD(&mr->mr_list); INIT_WORK(&mr->mr_recycle, frwr_mr_recycle_worker); - sg_init_table(mr->mr_sg, depth); - init_completion(&frwr->fr_linv_done); + init_completion(&mr->frwr.fr_linv_done); + + sg_init_table(sg, depth); + mr->mr_sg = sg; return 0; out_mr_err: - rc = PTR_ERR(frwr->fr_mr); - dprintk("RPC: %s: ib_alloc_mr status %i\n", - __func__, rc); + rc = PTR_ERR(frmr); + trace_xprtrdma_frwr_alloc(mr, rc); return rc; out_list_err: - rc = -ENOMEM; dprintk("RPC: %s: sg allocation failure\n", __func__); - ib_dereg_mr(frwr->fr_mr); - return rc; + ib_dereg_mr(frmr); + return -ENOMEM; } -/* On success, sets: +/** + * frwr_open - Prepare an endpoint for use with FRWR + * @ia: interface adapter this endpoint will use + * @ep: endpoint to prepare + * @cdata: transport parameters + * + * On success, sets: * ep->rep_attr.cap.max_send_wr * ep->rep_attr.cap.max_recv_wr * cdata->max_requests @@ -179,10 +205,11 @@ out_list_err: * And these FRWR-related fields: * ia->ri_max_frwr_depth * ia->ri_mrtype + * + * On failure, a negative errno is returned. */ -static int -frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, - struct rpcrdma_create_data_internal *cdata) +int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata) { struct ib_device_attr *attrs = &ia->ri_device->attrs; int max_qp_wr, depth, delta; @@ -191,10 +218,17 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, if (attrs->device_cap_flags & IB_DEVICE_SG_GAPS_REG) ia->ri_mrtype = IB_MR_TYPE_SG_GAPS; - ia->ri_max_frwr_depth = - min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, - attrs->max_fast_reg_page_list_len); - dprintk("RPC: %s: device's max FR page list len = %u\n", + /* Quirk: Some devices advertise a large max_fast_reg_page_list_len + * capability, but perform optimally when the MRs are not larger + * than a page. + */ + if (attrs->max_sge_rd > 1) + ia->ri_max_frwr_depth = attrs->max_sge_rd; + else + ia->ri_max_frwr_depth = attrs->max_fast_reg_page_list_len; + if (ia->ri_max_frwr_depth > RPCRDMA_MAX_DATA_SEGS) + ia->ri_max_frwr_depth = RPCRDMA_MAX_DATA_SEGS; + dprintk("RPC: %s: max FR page list depth = %u\n", __func__, ia->ri_max_frwr_depth); /* Add room for frwr register and invalidate WRs. @@ -242,20 +276,28 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS / ia->ri_max_frwr_depth); - ia->ri_max_segs += 2; /* segments for head and tail buffers */ + /* Reply chunks require segments for head and tail buffers */ + ia->ri_max_segs += 2; + if (ia->ri_max_segs > RPCRDMA_MAX_HDR_SEGS) + ia->ri_max_segs = RPCRDMA_MAX_HDR_SEGS; return 0; } -/* FRWR mode conveys a list of pages per chunk segment. The +/** + * frwr_maxpages - Compute size of largest payload + * @r_xprt: transport + * + * Returns maximum size of an RPC message, in pages. + * + * FRWR mode conveys a list of pages per chunk segment. The * maximum length of that list is the FRWR page list depth. */ -static size_t -frwr_op_maxpages(struct rpcrdma_xprt *r_xprt) +size_t frwr_maxpages(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, - RPCRDMA_MAX_HDR_SEGS * ia->ri_max_frwr_depth); + (ia->ri_max_segs - 2) * ia->ri_max_frwr_depth); } static void @@ -332,12 +374,25 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) trace_xprtrdma_wc_li_wake(wc, frwr); } -/* Post a REG_MR Work Request to register a memory region +/** + * frwr_map - Register a memory region + * @r_xprt: controlling transport + * @seg: memory region co-ordinates + * @nsegs: number of segments remaining + * @writing: true when RDMA Write will be used + * @xid: XID of RPC using the registered memory + * @out: initialized MR + * + * Prepare a REG_MR Work Request to register a memory region * for remote access via RDMA READ or RDMA WRITE. + * + * Returns the next segment or a negative errno pointer. + * On success, the prepared MR is planted in @out. */ -static struct rpcrdma_mr_seg * -frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, - int nsegs, bool writing, struct rpcrdma_mr **out) +struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_mr_seg *seg, + int nsegs, bool writing, u32 xid, + struct rpcrdma_mr **out) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; bool holes_ok = ia->ri_mrtype == IB_MR_TYPE_SG_GAPS; @@ -384,13 +439,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mr->mr_nents = ib_dma_map_sg(ia->ri_device, mr->mr_sg, i, mr->mr_dir); if (!mr->mr_nents) goto out_dmamap_err; - trace_xprtrdma_mr_map(mr); ibmr = frwr->fr_mr; n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE); if (unlikely(n != mr->mr_nents)) goto out_mapmr_err; + ibmr->iova &= 0x00000000ffffffff; + ibmr->iova |= ((u64)cpu_to_be32(xid)) << 32; key = (u8)(ibmr->rkey & 0x000000FF); ib_update_fast_reg_key(ibmr, ++key); @@ -404,32 +460,35 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mr->mr_handle = ibmr->rkey; mr->mr_length = ibmr->length; mr->mr_offset = ibmr->iova; + trace_xprtrdma_mr_map(mr); *out = mr; return seg; out_dmamap_err: - pr_err("rpcrdma: failed to DMA map sg %p sg_nents %d\n", - mr->mr_sg, i); frwr->fr_state = FRWR_IS_INVALID; + trace_xprtrdma_frwr_sgerr(mr, i); rpcrdma_mr_put(mr); return ERR_PTR(-EIO); out_mapmr_err: - pr_err("rpcrdma: failed to map mr %p (%d/%d)\n", - frwr->fr_mr, n, mr->mr_nents); + trace_xprtrdma_frwr_maperr(mr, n); rpcrdma_mr_recycle(mr); return ERR_PTR(-EIO); } -/* Post Send WR containing the RPC Call message. +/** + * frwr_send - post Send WR containing the RPC Call message + * @ia: interface adapter + * @req: Prepared RPC Call * - * For FRMR, chain any FastReg WRs to the Send WR. Only a + * For FRWR, chain any FastReg WRs to the Send WR. Only a * single ib_post_send call is needed to register memory * and then post the Send WR. + * + * Returns the result of ib_post_send. */ -static int -frwr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) +int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) { struct ib_send_wr *post_wr; struct rpcrdma_mr *mr; @@ -451,15 +510,18 @@ frwr_op_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req) } /* If ib_post_send fails, the next ->send_request for - * @req will queue these MWs for recovery. + * @req will queue these MRs for recovery. */ return ib_post_send(ia->ri_id->qp, post_wr, NULL); } -/* Handle a remotely invalidated mr on the @mrs list +/** + * frwr_reminv - handle a remotely invalidated mr on the @mrs list + * @rep: Received reply + * @mrs: list of MRs to check + * */ -static void -frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) +void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) { struct rpcrdma_mr *mr; @@ -473,7 +535,10 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) } } -/* Invalidate all memory regions that were registered for "req". +/** + * frwr_unmap_sync - invalidate memory regions that were registered for @req + * @r_xprt: controlling transport + * @mrs: list of MRs to process * * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. @@ -481,8 +546,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) * Caller ensures that @mrs is not empty before the call. This * function empties the list. */ -static void -frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs) +void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct list_head *mrs) { struct ib_send_wr *first, **prev, *last; const struct ib_send_wr *bad_wr; @@ -561,20 +625,7 @@ out_release: mr = container_of(frwr, struct rpcrdma_mr, frwr); bad_wr = bad_wr->next; - list_del(&mr->mr_list); - frwr_op_release_mr(mr); + list_del_init(&mr->mr_list); + rpcrdma_mr_recycle(mr); } } - -const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { - .ro_map = frwr_op_map, - .ro_send = frwr_op_send, - .ro_reminv = frwr_op_reminv, - .ro_unmap_sync = frwr_op_unmap_sync, - .ro_open = frwr_op_open, - .ro_maxpages = frwr_op_maxpages, - .ro_init_mr = frwr_op_init_mr, - .ro_release_mr = frwr_op_release_mr, - .ro_displayname = "frwr", - .ro_send_w_inv_ok = RPCRDMA_CMP_F_SND_W_INV_OK, -}; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 9f53e0240035..d18614e02b4e 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -218,11 +218,12 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT); page_base = offset_in_page(xdrbuf->page_base); while (len) { - if (unlikely(!*ppages)) { - /* XXX: Certain upper layer operations do - * not provide receive buffer pages. - */ - *ppages = alloc_page(GFP_ATOMIC); + /* ACL likes to be lazy in allocating pages - ACLs + * are small by default but can get huge. + */ + if (unlikely(xdrbuf->flags & XDRBUF_SPARSE_PAGES)) { + if (!*ppages) + *ppages = alloc_page(GFP_ATOMIC); if (!*ppages) return -ENOBUFS; } @@ -356,8 +357,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, return nsegs; do { - seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, - false, &mr); + seg = frwr_map(r_xprt, seg, nsegs, false, rqst->rq_xid, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); rpcrdma_mr_push(mr, &req->rl_registered); @@ -365,7 +365,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, if (encode_read_segment(xdr, mr, pos) < 0) return -EMSGSIZE; - trace_xprtrdma_read_chunk(rqst->rq_task, pos, mr, nsegs); + trace_xprtrdma_chunk_read(rqst->rq_task, pos, mr, nsegs); r_xprt->rx_stats.read_chunk_count++; nsegs -= mr->mr_nents; } while (nsegs); @@ -414,8 +414,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { - seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, - true, &mr); + seg = frwr_map(r_xprt, seg, nsegs, true, rqst->rq_xid, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); rpcrdma_mr_push(mr, &req->rl_registered); @@ -423,7 +422,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, if (encode_rdma_segment(xdr, mr) < 0) return -EMSGSIZE; - trace_xprtrdma_write_chunk(rqst->rq_task, mr, nsegs); + trace_xprtrdma_chunk_write(rqst->rq_task, mr, nsegs); r_xprt->rx_stats.write_chunk_count++; r_xprt->rx_stats.total_rdma_request += mr->mr_length; nchunks++; @@ -472,8 +471,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { - seg = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, - true, &mr); + seg = frwr_map(r_xprt, seg, nsegs, true, rqst->rq_xid, &mr); if (IS_ERR(seg)) return PTR_ERR(seg); rpcrdma_mr_push(mr, &req->rl_registered); @@ -481,7 +479,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, if (encode_rdma_segment(xdr, mr) < 0) return -EMSGSIZE; - trace_xprtrdma_reply_chunk(rqst->rq_task, mr, nsegs); + trace_xprtrdma_chunk_reply(rqst->rq_task, mr, nsegs); r_xprt->rx_stats.reply_chunk_count++; r_xprt->rx_stats.total_rdma_request += mr->mr_length; nchunks++; @@ -667,7 +665,7 @@ out_mapping_overflow: out_mapping_err: rpcrdma_unmap_sendctx(sc); - pr_err("rpcrdma: Send mapping error\n"); + trace_xprtrdma_dma_maperr(sge[sge_no].addr); return false; } @@ -1188,17 +1186,20 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, p = xdr_inline_decode(xdr, 2 * sizeof(*p)); if (!p) break; - dprintk("RPC: %5u: %s: server reports version error (%u-%u)\n", - rqst->rq_task->tk_pid, __func__, - be32_to_cpup(p), be32_to_cpu(*(p + 1))); + dprintk("RPC: %s: server reports " + "version error (%u-%u), xid %08x\n", __func__, + be32_to_cpup(p), be32_to_cpu(*(p + 1)), + be32_to_cpu(rep->rr_xid)); break; case err_chunk: - dprintk("RPC: %5u: %s: server reports header decoding error\n", - rqst->rq_task->tk_pid, __func__); + dprintk("RPC: %s: server reports " + "header decoding error, xid %08x\n", __func__, + be32_to_cpu(rep->rr_xid)); break; default: - dprintk("RPC: %5u: %s: server reports unrecognized error %d\n", - rqst->rq_task->tk_pid, __func__, be32_to_cpup(p)); + dprintk("RPC: %s: server reports " + "unrecognized error %d, xid %08x\n", __func__, + be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } r_xprt->rx_stats.bad_reply_count++; @@ -1248,7 +1249,6 @@ out: out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; - status = -EIO; goto out; } @@ -1262,8 +1262,7 @@ void rpcrdma_release_rqst(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * RPC has relinquished all its Send Queue entries. */ if (!list_empty(&req->rl_registered)) - r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, - &req->rl_registered); + frwr_unmap_sync(r_xprt, &req->rl_registered); /* Ensure that any DMA mapped pages associated with * the Send of the RPC Call have been unmapped before @@ -1292,7 +1291,7 @@ void rpcrdma_deferred_completion(struct work_struct *work) trace_xprtrdma_defer_cmp(rep); if (rep->rr_wc_flags & IB_WC_WITH_INVALIDATE) - r_xprt->rx_ia.ri_ops->ro_reminv(rep, &req->rl_registered); + frwr_reminv(rep, &req->rl_registered); rpcrdma_release_rqst(r_xprt, req); rpcrdma_complete_rqst(rep); } @@ -1312,11 +1311,6 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) u32 credits; __be32 *p; - --buf->rb_posted_receives; - - if (rep->rr_hdrbuf.head[0].iov_len == 0) - goto out_badstatus; - /* Fixed transport header fields */ xdr_init_decode(&rep->rr_stream, &rep->rr_hdrbuf, rep->rr_hdrbuf.head[0].iov_base); @@ -1356,36 +1350,30 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) } req = rpcr_to_rdmar(rqst); + if (req->rl_reply) { + trace_xprtrdma_leaked_rep(rqst, req->rl_reply); + rpcrdma_recv_buffer_put(req->rl_reply); + } req->rl_reply = rep; rep->rr_rqst = rqst; clear_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags); trace_xprtrdma_reply(rqst->rq_task, rep, req, credits); - - rpcrdma_post_recvs(r_xprt, false); - queue_work(rpcrdma_receive_wq, &rep->rr_work); + queue_work(buf->rb_completion_wq, &rep->rr_work); return; out_badversion: trace_xprtrdma_reply_vers(rep); - goto repost; + goto out; -/* The RPC transaction has already been terminated, or the header - * is corrupt. - */ out_norqst: spin_unlock(&xprt->queue_lock); trace_xprtrdma_reply_rqst(rep); - goto repost; + goto out; out_shortreply: trace_xprtrdma_reply_short(rep); -/* If no pending RPC transaction was matched, post a replacement - * receive buffer before returning. - */ -repost: - rpcrdma_post_recvs(r_xprt, false); -out_badstatus: +out: rpcrdma_recv_buffer_put(rep); } diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 134bef6a451e..abdb3004a1e3 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -235,9 +235,6 @@ void svc_rdma_cleanup(void) unregister_sysctl_table(svcrdma_table_header); svcrdma_table_header = NULL; } -#if defined(CONFIG_SUNRPC_BACKCHANNEL) - svc_unreg_xprt_class(&svc_rdma_bc_class); -#endif svc_unreg_xprt_class(&svc_rdma_class); } @@ -259,8 +256,5 @@ int svc_rdma_init(void) /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); -#if defined(CONFIG_SUNRPC_BACKCHANNEL) - svc_reg_xprt_class(&svc_rdma_bc_class); -#endif return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index f3c147d70286..b908f2ca08fd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -200,11 +200,10 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst) svc_rdma_send_ctxt_put(rdma, ctxt); goto drop_connection; } - return rc; + return 0; drop_connection: dprintk("svcrdma: failed to send bc call\n"); - xprt_disconnect_done(xprt); return -ENOTCONN; } @@ -225,8 +224,11 @@ xprt_rdma_bc_send_request(struct rpc_rqst *rqst) ret = -ENOTCONN; rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt); - if (!test_bit(XPT_DEAD, &sxprt->xpt_flags)) + if (!test_bit(XPT_DEAD, &sxprt->xpt_flags)) { ret = rpcrdma_bc_send_request(rdma, rqst); + if (ret == -ENOTCONN) + svc_close_xprt(sxprt); + } mutex_unlock(&sxprt->xpt_mutex); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index b24d5b8f2fee..828b149eaaef 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -485,6 +485,68 @@ static __be32 *xdr_check_reply_chunk(__be32 *p, const __be32 *end) return p; } +/* RPC-over-RDMA Version One private extension: Remote Invalidation. + * Responder's choice: requester signals it can handle Send With + * Invalidate, and responder chooses one R_key to invalidate. + * + * If there is exactly one distinct R_key in the received transport + * header, set rc_inv_rkey to that R_key. Otherwise, set it to zero. + * + * Perform this operation while the received transport header is + * still in the CPU cache. + */ +static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma, + struct svc_rdma_recv_ctxt *ctxt) +{ + __be32 inv_rkey, *p; + u32 i, segcount; + + ctxt->rc_inv_rkey = 0; + + if (!rdma->sc_snd_w_inv) + return; + + inv_rkey = xdr_zero; + p = ctxt->rc_recv_buf; + p += rpcrdma_fixed_maxsz; + + /* Read list */ + while (*p++ != xdr_zero) { + p++; /* position */ + if (inv_rkey == xdr_zero) + inv_rkey = *p; + else if (inv_rkey != *p) + return; + p += 4; + } + + /* Write list */ + while (*p++ != xdr_zero) { + segcount = be32_to_cpup(p++); + for (i = 0; i < segcount; i++) { + if (inv_rkey == xdr_zero) + inv_rkey = *p; + else if (inv_rkey != *p) + return; + p += 4; + } + } + + /* Reply chunk */ + if (*p++ != xdr_zero) { + segcount = be32_to_cpup(p++); + for (i = 0; i < segcount; i++) { + if (inv_rkey == xdr_zero) + inv_rkey = *p; + else if (inv_rkey != *p) + return; + p += 4; + } + } + + ctxt->rc_inv_rkey = be32_to_cpu(inv_rkey); +} + /* On entry, xdr->head[0].iov_base points to first byte in the * RPC-over-RDMA header. * @@ -746,6 +808,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return ret; } + svc_rdma_get_inv_rkey(rdma_xprt, ctxt); p += rpcrdma_fixed_maxsz; if (*p != xdr_zero) diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 8602a5f1b515..cf51b8f9b15f 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -484,32 +484,6 @@ static void svc_rdma_get_write_arrays(__be32 *rdma_argp, *reply = NULL; } -/* RPC-over-RDMA Version One private extension: Remote Invalidation. - * Responder's choice: requester signals it can handle Send With - * Invalidate, and responder chooses one rkey to invalidate. - * - * Find a candidate rkey to invalidate when sending a reply. Picks the - * first R_key it finds in the chunk lists. - * - * Returns zero if RPC's chunk lists are empty. - */ -static u32 svc_rdma_get_inv_rkey(__be32 *rdma_argp, - __be32 *wr_lst, __be32 *rp_ch) -{ - __be32 *p; - - p = rdma_argp + rpcrdma_fixed_maxsz; - if (*p != xdr_zero) - p += 2; - else if (wr_lst && be32_to_cpup(wr_lst + 1)) - p = wr_lst + 2; - else if (rp_ch && be32_to_cpup(rp_ch + 1)) - p = rp_ch + 2; - else - return 0; - return be32_to_cpup(p); -} - static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt, struct page *page, @@ -672,7 +646,7 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, * * RDMA Send is the last step of transmitting an RPC reply. Pages * involved in the earlier RDMA Writes are here transferred out - * of the rqstp and into the ctxt's page array. These pages are + * of the rqstp and into the sctxt's page array. These pages are * DMA unmapped by each Write completion, but the subsequent Send * completion finally releases these pages. * @@ -680,32 +654,31 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, * - The Reply's transport header will never be larger than a page. */ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt, - __be32 *rdma_argp, + struct svc_rdma_send_ctxt *sctxt, + struct svc_rdma_recv_ctxt *rctxt, struct svc_rqst *rqstp, __be32 *wr_lst, __be32 *rp_ch) { int ret; if (!rp_ch) { - ret = svc_rdma_map_reply_msg(rdma, ctxt, + ret = svc_rdma_map_reply_msg(rdma, sctxt, &rqstp->rq_res, wr_lst); if (ret < 0) return ret; } - svc_rdma_save_io_pages(rqstp, ctxt); + svc_rdma_save_io_pages(rqstp, sctxt); - ctxt->sc_send_wr.opcode = IB_WR_SEND; - if (rdma->sc_snd_w_inv) { - ctxt->sc_send_wr.ex.invalidate_rkey = - svc_rdma_get_inv_rkey(rdma_argp, wr_lst, rp_ch); - if (ctxt->sc_send_wr.ex.invalidate_rkey) - ctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV; + if (rctxt->rc_inv_rkey) { + sctxt->sc_send_wr.opcode = IB_WR_SEND_WITH_INV; + sctxt->sc_send_wr.ex.invalidate_rkey = rctxt->rc_inv_rkey; + } else { + sctxt->sc_send_wr.opcode = IB_WR_SEND; } dprintk("svcrdma: posting Send WR with %u sge(s)\n", - ctxt->sc_send_wr.num_sge); - return svc_rdma_send(rdma, &ctxt->sc_send_wr); + sctxt->sc_send_wr.num_sge); + return svc_rdma_send(rdma, &sctxt->sc_send_wr); } /* Given the client-provided Write and Reply chunks, the server was not @@ -741,10 +714,6 @@ static int svc_rdma_send_error_msg(struct svcxprt_rdma *rdma, return 0; } -void svc_rdma_prep_reply_hdr(struct svc_rqst *rqstp) -{ -} - /** * svc_rdma_sendto - Transmit an RPC reply * @rqstp: processed RPC request, reply XDR already in ::rq_res @@ -809,7 +778,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) } svc_rdma_sync_reply_hdr(rdma, sctxt, svc_rdma_reply_hdr_len(rdma_resp)); - ret = svc_rdma_send_reply_msg(rdma, sctxt, rdma_argp, rqstp, + ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp, wr_lst, rp_ch); if (ret < 0) goto err1; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 2f7ec8912f49..924c17d46903 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -85,7 +85,6 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_release_rqst = svc_rdma_release_rqst, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, - .xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr, .xpo_has_wspace = svc_rdma_has_wspace, .xpo_accept = svc_rdma_accept, .xpo_secure_port = svc_rdma_secure_port, @@ -100,64 +99,6 @@ struct svc_xprt_class svc_rdma_class = { .xcl_ident = XPRT_TRANSPORT_RDMA, }; -#if defined(CONFIG_SUNRPC_BACKCHANNEL) -static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *, struct net *, - struct sockaddr *, int, int); -static void svc_rdma_bc_detach(struct svc_xprt *); -static void svc_rdma_bc_free(struct svc_xprt *); - -static const struct svc_xprt_ops svc_rdma_bc_ops = { - .xpo_create = svc_rdma_bc_create, - .xpo_detach = svc_rdma_bc_detach, - .xpo_free = svc_rdma_bc_free, - .xpo_prep_reply_hdr = svc_rdma_prep_reply_hdr, - .xpo_secure_port = svc_rdma_secure_port, -}; - -struct svc_xprt_class svc_rdma_bc_class = { - .xcl_name = "rdma-bc", - .xcl_owner = THIS_MODULE, - .xcl_ops = &svc_rdma_bc_ops, - .xcl_max_payload = (1024 - RPCRDMA_HDRLEN_MIN) -}; - -static struct svc_xprt *svc_rdma_bc_create(struct svc_serv *serv, - struct net *net, - struct sockaddr *sa, int salen, - int flags) -{ - struct svcxprt_rdma *cma_xprt; - struct svc_xprt *xprt; - - cma_xprt = svc_rdma_create_xprt(serv, net); - if (!cma_xprt) - return ERR_PTR(-ENOMEM); - xprt = &cma_xprt->sc_xprt; - - svc_xprt_init(net, &svc_rdma_bc_class, xprt, serv); - set_bit(XPT_CONG_CTRL, &xprt->xpt_flags); - serv->sv_bc_xprt = xprt; - - dprintk("svcrdma: %s(%p)\n", __func__, xprt); - return xprt; -} - -static void svc_rdma_bc_detach(struct svc_xprt *xprt) -{ - dprintk("svcrdma: %s(%p)\n", __func__, xprt); -} - -static void svc_rdma_bc_free(struct svc_xprt *xprt) -{ - struct svcxprt_rdma *rdma = - container_of(xprt, struct svcxprt_rdma, sc_xprt); - - dprintk("svcrdma: %s(%p)\n", __func__, xprt); - if (xprt) - kfree(rdma); -} -#endif /* CONFIG_SUNRPC_BACKCHANNEL */ - /* QP event handler */ static void qp_event_handler(struct ib_event *event, void *context) { diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index ae2a83828953..fbc171ebfe91 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -268,7 +268,7 @@ xprt_rdma_inject_disconnect(struct rpc_xprt *xprt) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); - trace_xprtrdma_inject_dsc(r_xprt); + trace_xprtrdma_op_inject_dsc(r_xprt); rdma_disconnect(r_xprt->rx_ia.ri_id); } @@ -284,7 +284,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); - trace_xprtrdma_destroy(r_xprt); + trace_xprtrdma_op_destroy(r_xprt); cancel_delayed_work_sync(&r_xprt->rx_connect_worker); @@ -318,17 +318,12 @@ xprt_setup_rdma(struct xprt_create *args) struct sockaddr *sap; int rc; - if (args->addrlen > sizeof(xprt->addr)) { - dprintk("RPC: %s: address too large\n", __func__); + if (args->addrlen > sizeof(xprt->addr)) return ERR_PTR(-EBADF); - } xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt), 0, 0); - if (xprt == NULL) { - dprintk("RPC: %s: couldn't allocate rpcrdma_xprt\n", - __func__); + if (!xprt) return ERR_PTR(-ENOMEM); - } /* 60 second timeout, no retries */ xprt->timeout = &xprt_rdma_default_timeout; @@ -399,7 +394,7 @@ xprt_setup_rdma(struct xprt_create *args) INIT_DELAYED_WORK(&new_xprt->rx_connect_worker, xprt_rdma_connect_worker); - xprt->max_payload = new_xprt->rx_ia.ri_ops->ro_maxpages(new_xprt); + xprt->max_payload = frwr_maxpages(new_xprt); if (xprt->max_payload == 0) goto out4; xprt->max_payload <<= PAGE_SHIFT; @@ -423,7 +418,7 @@ out3: out2: rpcrdma_ia_close(&new_xprt->rx_ia); out1: - trace_xprtrdma_destroy(new_xprt); + trace_xprtrdma_op_destroy(new_xprt); xprt_rdma_free_addresses(xprt); xprt_free(xprt); return ERR_PTR(rc); @@ -433,29 +428,33 @@ out1: * xprt_rdma_close - close a transport connection * @xprt: transport context * - * Called during transport shutdown, reconnect, or device removal. + * Called during autoclose or device removal. + * * Caller holds @xprt's send lock to prevent activity on this * transport while the connection is torn down. */ -static void -xprt_rdma_close(struct rpc_xprt *xprt) +void xprt_rdma_close(struct rpc_xprt *xprt) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); struct rpcrdma_ep *ep = &r_xprt->rx_ep; struct rpcrdma_ia *ia = &r_xprt->rx_ia; - dprintk("RPC: %s: closing xprt %p\n", __func__, xprt); + might_sleep(); + + trace_xprtrdma_op_close(r_xprt); + + /* Prevent marshaling and sending of new requests */ + xprt_clear_connected(xprt); if (test_and_clear_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags)) { - xprt_clear_connected(xprt); rpcrdma_ia_remove(ia); - return; + goto out; } + if (ep->rep_connected == -ENODEV) return; if (ep->rep_connected > 0) xprt->reestablish_timeout = 0; - xprt_disconnect_done(xprt); rpcrdma_ep_disconnect(ep, ia); /* Prepare @xprt for the next connection by reinitializing @@ -463,6 +462,10 @@ xprt_rdma_close(struct rpc_xprt *xprt) */ r_xprt->rx_buf.rb_credits = 1; xprt->cwnd = RPC_CWNDSHIFT; + +out: + ++xprt->connect_cookie; + xprt_disconnect_done(xprt); } /** @@ -525,6 +528,7 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + trace_xprtrdma_op_connect(r_xprt); if (r_xprt->rx_ep.rep_connected != 0) { /* Reconnect */ schedule_delayed_work(&r_xprt->rx_connect_worker, @@ -659,11 +663,11 @@ xprt_rdma_allocate(struct rpc_task *task) rqst->rq_buffer = req->rl_sendbuf->rg_base; rqst->rq_rbuffer = req->rl_recvbuf->rg_base; - trace_xprtrdma_allocate(task, req); + trace_xprtrdma_op_allocate(task, req); return 0; out_fail: - trace_xprtrdma_allocate(task, NULL); + trace_xprtrdma_op_allocate(task, NULL); return -ENOMEM; } @@ -682,7 +686,7 @@ xprt_rdma_free(struct rpc_task *task) if (test_bit(RPCRDMA_REQ_F_PENDING, &req->rl_flags)) rpcrdma_release_rqst(r_xprt, req); - trace_xprtrdma_rpc_done(task, req); + trace_xprtrdma_op_free(task, req); } /** @@ -696,8 +700,10 @@ xprt_rdma_free(struct rpc_task *task) * %-ENOTCONN if the caller should reconnect and call again * %-EAGAIN if the caller should call again * %-ENOBUFS if the caller should call again after a delay - * %-EIO if a permanent error occurred and the request was not - * sent. Do not try to send this message again. + * %-EMSGSIZE if encoding ran out of buffer space. The request + * was not sent. Do not try to send this message again. + * %-EIO if an I/O error occurred. The request was not sent. + * Do not try to send this message again. */ static int xprt_rdma_send_request(struct rpc_rqst *rqst) @@ -713,7 +719,7 @@ xprt_rdma_send_request(struct rpc_rqst *rqst) #endif /* CONFIG_SUNRPC_BACKCHANNEL */ if (!xprt_connected(xprt)) - goto drop_connection; + return -ENOTCONN; if (!xprt_request_get_cong(xprt, rqst)) return -EBADSLT; @@ -745,8 +751,8 @@ failed_marshal: if (rc != -ENOTCONN) return rc; drop_connection: - xprt_disconnect_done(xprt); - return -ENOTCONN; /* implies disconnect */ + xprt_rdma_close(xprt); + return -ENOTCONN; } void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) @@ -827,7 +833,6 @@ static const struct rpc_xprt_ops xprt_rdma_procs = { .inject_disconnect = xprt_rdma_inject_disconnect, #if defined(CONFIG_SUNRPC_BACKCHANNEL) .bc_setup = xprt_rdma_bc_setup, - .bc_up = xprt_rdma_bc_up, .bc_maxpayload = xprt_rdma_bc_maxpayload, .bc_free_rqst = xprt_rdma_bc_free_rqst, .bc_destroy = xprt_rdma_bc_destroy, @@ -844,58 +849,31 @@ static struct xprt_class xprt_rdma = { void xprt_rdma_cleanup(void) { - int rc; - - dprintk("RPCRDMA Module Removed, deregister RPC RDMA transport\n"); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; } #endif - rc = xprt_unregister_transport(&xprt_rdma); - if (rc) - dprintk("RPC: %s: xprt_unregister returned %i\n", - __func__, rc); - - rpcrdma_destroy_wq(); - rc = xprt_unregister_transport(&xprt_rdma_bc); - if (rc) - dprintk("RPC: %s: xprt_unregister(bc) returned %i\n", - __func__, rc); + xprt_unregister_transport(&xprt_rdma); + xprt_unregister_transport(&xprt_rdma_bc); } int xprt_rdma_init(void) { int rc; - rc = rpcrdma_alloc_wq(); - if (rc) - return rc; - rc = xprt_register_transport(&xprt_rdma); - if (rc) { - rpcrdma_destroy_wq(); + if (rc) return rc; - } rc = xprt_register_transport(&xprt_rdma_bc); if (rc) { xprt_unregister_transport(&xprt_rdma); - rpcrdma_destroy_wq(); return rc; } - dprintk("RPCRDMA Module Init, register RPC RDMA transport\n"); - - dprintk("Defaults:\n"); - dprintk("\tSlots %d\n" - "\tMaxInlineRead %d\n\tMaxInlineWrite %d\n", - xprt_rdma_slot_table_entries, - xprt_rdma_max_inline_read, xprt_rdma_max_inline_write); - dprintk("\tPadding 0\n\tMemreg %d\n", xprt_rdma_memreg_strategy); - #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3ddba94c939f..7749a2bf6887 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -78,53 +78,25 @@ static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf); static int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp); static void rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb); +static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); -struct workqueue_struct *rpcrdma_receive_wq __read_mostly; - -int -rpcrdma_alloc_wq(void) -{ - struct workqueue_struct *recv_wq; - - recv_wq = alloc_workqueue("xprtrdma_receive", - WQ_MEM_RECLAIM | WQ_HIGHPRI, - 0); - if (!recv_wq) - return -ENOMEM; - - rpcrdma_receive_wq = recv_wq; - return 0; -} - -void -rpcrdma_destroy_wq(void) -{ - struct workqueue_struct *wq; - - if (rpcrdma_receive_wq) { - wq = rpcrdma_receive_wq; - rpcrdma_receive_wq = NULL; - destroy_workqueue(wq); - } -} - -/** - * rpcrdma_disconnect_worker - Force a disconnect - * @work: endpoint to be disconnected - * - * Provider callbacks can possibly run in an IRQ context. This function - * is invoked in a worker thread to guarantee that disconnect wake-up - * calls are always done in process context. +/* Wait for outstanding transport work to finish. */ -static void -rpcrdma_disconnect_worker(struct work_struct *work) +static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt) { - struct rpcrdma_ep *ep = container_of(work, struct rpcrdma_ep, - rep_disconnect_worker.work); - struct rpcrdma_xprt *r_xprt = - container_of(ep, struct rpcrdma_xprt, rx_ep); + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; - xprt_force_disconnect(&r_xprt->rx_xprt); + /* Flush Receives, then wait for deferred Reply work + * to complete. + */ + ib_drain_qp(ia->ri_id->qp); + drain_workqueue(buf->rb_completion_wq); + + /* Deferred Reply processing might have scheduled + * local invalidations. + */ + ib_drain_sq(ia->ri_id->qp); } /** @@ -143,15 +115,6 @@ rpcrdma_qp_event_handler(struct ib_event *event, void *context) rx_ep); trace_xprtrdma_qp_event(r_xprt, event); - pr_err("rpcrdma: %s on device %s connected to %s:%s\n", - ib_event_msg(event->event), event->device->name, - rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt)); - - if (ep->rep_connected == 1) { - ep->rep_connected = -EIO; - schedule_delayed_work(&ep->rep_disconnect_worker, 0); - wake_up_all(&ep->rep_connect_wait); - } } /** @@ -189,11 +152,13 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) struct ib_cqe *cqe = wc->wr_cqe; struct rpcrdma_rep *rep = container_of(cqe, struct rpcrdma_rep, rr_cqe); + struct rpcrdma_xprt *r_xprt = rep->rr_rxprt; - /* WARNING: Only wr_id and status are reliable at this point */ + /* WARNING: Only wr_cqe and status are reliable at this point */ trace_xprtrdma_wc_receive(wc); + --r_xprt->rx_ep.rep_receive_count; if (wc->status != IB_WC_SUCCESS) - goto out_fail; + goto out_flushed; /* status == SUCCESS means all fields in wc are trustworthy */ rpcrdma_set_xdrlen(&rep->rr_hdrbuf, wc->byte_len); @@ -204,17 +169,16 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) rdmab_addr(rep->rr_rdmabuf), wc->byte_len, DMA_FROM_DEVICE); -out_schedule: + rpcrdma_post_recvs(r_xprt, false); rpcrdma_reply_handler(rep); return; -out_fail: +out_flushed: if (wc->status != IB_WC_WR_FLUSH_ERR) pr_err("rpcrdma: Recv: %s (%u/0x%x)\n", ib_wc_status_msg(wc->status), wc->status, wc->vendor_err); - rpcrdma_set_xdrlen(&rep->rr_hdrbuf, 0); - goto out_schedule; + rpcrdma_recv_buffer_put(rep); } static void @@ -316,7 +280,6 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ep->rep_connected = -EAGAIN; goto disconnected; case RDMA_CM_EVENT_DISCONNECTED: - ++xprt->connect_cookie; ep->rep_connected = -ECONNABORTED; disconnected: xprt_force_disconnect(xprt); @@ -326,10 +289,9 @@ disconnected: break; } - dprintk("RPC: %s: %s:%s on %s/%s: %s\n", __func__, + dprintk("RPC: %s: %s:%s on %s/frwr: %s\n", __func__, rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt), - ia->ri_device->name, ia->ri_ops->ro_displayname, - rdma_event_msg(event->event)); + ia->ri_device->name, rdma_event_msg(event->event)); return 0; } @@ -347,22 +309,15 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_cm_event_handler, xprt, RDMA_PS_TCP, IB_QPT_RC); - if (IS_ERR(id)) { - rc = PTR_ERR(id); - dprintk("RPC: %s: rdma_create_id() failed %i\n", - __func__, rc); + if (IS_ERR(id)) return id; - } ia->ri_async_rc = -ETIMEDOUT; rc = rdma_resolve_addr(id, NULL, (struct sockaddr *)&xprt->rx_xprt.addr, RDMA_RESOLVE_TIMEOUT); - if (rc) { - dprintk("RPC: %s: rdma_resolve_addr() failed %i\n", - __func__, rc); + if (rc) goto out; - } rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); if (rc < 0) { trace_xprtrdma_conn_tout(xprt); @@ -375,11 +330,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) ia->ri_async_rc = -ETIMEDOUT; rc = rdma_resolve_route(id, RDMA_RESOLVE_TIMEOUT); - if (rc) { - dprintk("RPC: %s: rdma_resolve_route() failed %i\n", - __func__, rc); + if (rc) goto out; - } rc = wait_for_completion_interruptible_timeout(&ia->ri_done, wtimeout); if (rc < 0) { trace_xprtrdma_conn_tout(xprt); @@ -429,16 +381,8 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt) switch (xprt_rdma_memreg_strategy) { case RPCRDMA_FRWR: - if (frwr_is_supported(ia)) { - ia->ri_ops = &rpcrdma_frwr_memreg_ops; - break; - } - /*FALLTHROUGH*/ - case RPCRDMA_MTHCAFMR: - if (fmr_is_supported(ia)) { - ia->ri_ops = &rpcrdma_fmr_memreg_ops; + if (frwr_is_supported(ia)) break; - } /*FALLTHROUGH*/ default: pr_err("rpcrdma: Device %s does not support memreg mode %d\n", @@ -481,7 +425,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) * connection is already gone. */ if (ia->ri_id->qp) { - ib_drain_qp(ia->ri_id->qp); + rpcrdma_xprt_drain(r_xprt); rdma_destroy_qp(ia->ri_id); ia->ri_id->qp = NULL; } @@ -552,7 +496,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, } ia->ri_max_send_sges = max_sge; - rc = ia->ri_ops->ro_open(ia, ep, cdata); + rc = frwr_open(ia, ep, cdata); if (rc) return rc; @@ -579,16 +523,13 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, cdata->max_requests >> 2); ep->rep_send_count = ep->rep_send_batch; init_waitqueue_head(&ep->rep_connect_wait); - INIT_DELAYED_WORK(&ep->rep_disconnect_worker, - rpcrdma_disconnect_worker); + ep->rep_receive_count = 0; sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, 1, IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); - dprintk("RPC: %s: failed to create send CQ: %i\n", - __func__, rc); goto out1; } @@ -597,8 +538,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, 0, IB_POLL_WORKQUEUE); if (IS_ERR(recvcq)) { rc = PTR_ERR(recvcq); - dprintk("RPC: %s: failed to create recv CQ: %i\n", - __func__, rc); goto out2; } @@ -611,7 +550,7 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* Prepare RDMA-CM private message */ pmsg->cp_magic = rpcrdma_cmp_magic; pmsg->cp_version = RPCRDMA_CMP_VERSION; - pmsg->cp_flags |= ia->ri_ops->ro_send_w_inv_ok; + pmsg->cp_flags |= RPCRDMA_CMP_F_SND_W_INV_OK; pmsg->cp_send_size = rpcrdma_encode_buffer_size(cdata->inline_wsize); pmsg->cp_recv_size = rpcrdma_encode_buffer_size(cdata->inline_rsize); ep->rep_remote_cma.private_data = pmsg; @@ -653,8 +592,6 @@ out1: void rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { - cancel_delayed_work_sync(&ep->rep_disconnect_worker); - if (ia->ri_id && ia->ri_id->qp) { rpcrdma_ep_disconnect(ep, ia); rdma_destroy_qp(ia->ri_id); @@ -740,11 +677,8 @@ rpcrdma_ep_reconnect(struct rpcrdma_xprt *r_xprt, struct rpcrdma_ep *ep, } err = rdma_create_qp(id, ia->ri_pd, &ep->rep_attr); - if (err) { - dprintk("RPC: %s: rdma_create_qp returned %d\n", - __func__, err); + if (err) goto out_destroy; - } /* Atomically replace the transport's ID and QP. */ rc = 0; @@ -775,8 +709,6 @@ retry: dprintk("RPC: %s: connecting...\n", __func__); rc = rdma_create_qp(ia->ri_id, ia->ri_pd, &ep->rep_attr); if (rc) { - dprintk("RPC: %s: rdma_create_qp failed %i\n", - __func__, rc); rc = -ENETUNREACH; goto out_noupdate; } @@ -798,11 +730,8 @@ retry: rpcrdma_post_recvs(r_xprt, true); rc = rdma_connect(ia->ri_id, &ep->rep_remote_cma); - if (rc) { - dprintk("RPC: %s: rdma_connect() failed with %i\n", - __func__, rc); + if (rc) goto out; - } wait_event_interruptible(ep->rep_connect_wait, ep->rep_connected != 0); if (ep->rep_connected <= 0) { @@ -822,8 +751,10 @@ out_noupdate: return rc; } -/* - * rpcrdma_ep_disconnect +/** + * rpcrdma_ep_disconnect - Disconnect underlying transport + * @ep: endpoint to disconnect + * @ia: associated interface adapter * * This is separate from destroy to facilitate the ability * to reconnect without recreating the endpoint. @@ -834,19 +765,20 @@ out_noupdate: void rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { + struct rpcrdma_xprt *r_xprt = container_of(ep, struct rpcrdma_xprt, + rx_ep); int rc; + /* returns without wait if ID is not connected */ rc = rdma_disconnect(ia->ri_id); if (!rc) - /* returns without wait if not connected */ wait_event_interruptible(ep->rep_connect_wait, ep->rep_connected != 1); else ep->rep_connected = rc; - trace_xprtrdma_disconnect(container_of(ep, struct rpcrdma_xprt, - rx_ep), rc); + trace_xprtrdma_disconnect(r_xprt, rc); - ib_drain_qp(ia->ri_id->qp); + rpcrdma_xprt_drain(r_xprt); } /* Fixed-size circular FIFO queue. This implementation is wait-free and @@ -1034,7 +966,7 @@ rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt) if (!mr) break; - rc = ia->ri_ops->ro_init_mr(ia, mr); + rc = frwr_init_mr(ia, mr); if (rc) { kfree(mr); break; @@ -1089,9 +1021,9 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) req->rl_buffer = buffer; INIT_LIST_HEAD(&req->rl_registered); - spin_lock(&buffer->rb_reqslock); + spin_lock(&buffer->rb_lock); list_add(&req->rl_all, &buffer->rb_allreqs); - spin_unlock(&buffer->rb_reqslock); + spin_unlock(&buffer->rb_lock); return req; } @@ -1134,8 +1066,6 @@ rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt, bool temp) out_free: kfree(rep); out: - dprintk("RPC: %s: reply buffer %d alloc failed\n", - __func__, rc); return rc; } @@ -1159,7 +1089,6 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); - spin_lock_init(&buf->rb_reqslock); for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_req *req; @@ -1174,13 +1103,19 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) } buf->rb_credits = 1; - buf->rb_posted_receives = 0; INIT_LIST_HEAD(&buf->rb_recv_bufs); rc = rpcrdma_sendctxs_create(r_xprt); if (rc) goto out; + buf->rb_completion_wq = alloc_workqueue("rpcrdma-%s", + WQ_MEM_RECLAIM | WQ_HIGHPRI, + 0, + r_xprt->rx_xprt.address_strings[RPC_DISPLAY_ADDR]); + if (!buf->rb_completion_wq) + goto out; + return 0; out: rpcrdma_buffer_destroy(buf); @@ -1194,9 +1129,18 @@ rpcrdma_destroy_rep(struct rpcrdma_rep *rep) kfree(rep); } +/** + * rpcrdma_req_destroy - Destroy an rpcrdma_req object + * @req: unused object to be destroyed + * + * This function assumes that the caller prevents concurrent device + * unload and transport tear-down. + */ void -rpcrdma_destroy_req(struct rpcrdma_req *req) +rpcrdma_req_destroy(struct rpcrdma_req *req) { + list_del(&req->rl_all); + rpcrdma_free_regbuf(req->rl_recvbuf); rpcrdma_free_regbuf(req->rl_sendbuf); rpcrdma_free_regbuf(req->rl_rdmabuf); @@ -1208,7 +1152,6 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) { struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, rx_buf); - struct rpcrdma_ia *ia = rdmab_to_ia(buf); struct rpcrdma_mr *mr; unsigned int count; @@ -1224,7 +1167,7 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) if (!list_empty(&mr->mr_list)) list_del(&mr->mr_list); - ia->ri_ops->ro_release_mr(mr); + frwr_release_mr(mr); count++; spin_lock(&buf->rb_mrlock); } @@ -1234,11 +1177,24 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) dprintk("RPC: %s: released %u MRs\n", __func__, count); } +/** + * rpcrdma_buffer_destroy - Release all hw resources + * @buf: root control block for resources + * + * ORDERING: relies on a prior ib_drain_qp : + * - No more Send or Receive completions can occur + * - All MRs, reps, and reqs are returned to their free lists + */ void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { cancel_delayed_work_sync(&buf->rb_refresh_worker); + if (buf->rb_completion_wq) { + destroy_workqueue(buf->rb_completion_wq); + buf->rb_completion_wq = NULL; + } + rpcrdma_sendctxs_destroy(buf); while (!list_empty(&buf->rb_recv_bufs)) { @@ -1250,19 +1206,14 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) rpcrdma_destroy_rep(rep); } - spin_lock(&buf->rb_reqslock); - while (!list_empty(&buf->rb_allreqs)) { + while (!list_empty(&buf->rb_send_bufs)) { struct rpcrdma_req *req; - req = list_first_entry(&buf->rb_allreqs, - struct rpcrdma_req, rl_all); - list_del(&req->rl_all); - - spin_unlock(&buf->rb_reqslock); - rpcrdma_destroy_req(req); - spin_lock(&buf->rb_reqslock); + req = list_first_entry(&buf->rb_send_bufs, + struct rpcrdma_req, rl_list); + list_del(&req->rl_list); + rpcrdma_req_destroy(req); } - spin_unlock(&buf->rb_reqslock); rpcrdma_mrs_destroy(buf); } @@ -1329,9 +1280,12 @@ rpcrdma_mr_unmap_and_put(struct rpcrdma_mr *mr) { struct rpcrdma_xprt *r_xprt = mr->mr_xprt; - trace_xprtrdma_mr_unmap(mr); - ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, - mr->mr_sg, mr->mr_nents, mr->mr_dir); + if (mr->mr_dir != DMA_NONE) { + trace_xprtrdma_mr_unmap(mr); + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mr->mr_sg, mr->mr_nents, mr->mr_dir); + mr->mr_dir = DMA_NONE; + } __rpcrdma_mr_put(&r_xprt->rx_buf, mr); } @@ -1410,7 +1364,7 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) * * xprtrdma uses a regbuf for posting an outgoing RDMA SEND, or for * receiving the payload of RDMA RECV operations. During Long Calls - * or Replies they may be registered externally via ro_map. + * or Replies they may be registered externally via frwr_map. */ struct rpcrdma_regbuf * rpcrdma_alloc_regbuf(size_t size, enum dma_data_direction direction, @@ -1446,8 +1400,10 @@ __rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) (void *)rb->rg_base, rdmab_length(rb), rb->rg_direction); - if (ib_dma_mapping_error(device, rdmab_addr(rb))) + if (ib_dma_mapping_error(device, rdmab_addr(rb))) { + trace_xprtrdma_dma_maperr(rdmab_addr(rb)); return false; + } rb->rg_device = device; rb->rg_iov.lkey = ia->ri_pd->local_dma_lkey; @@ -1479,10 +1435,14 @@ rpcrdma_free_regbuf(struct rpcrdma_regbuf *rb) kfree(rb); } -/* - * Prepost any receive buffer, then post send. +/** + * rpcrdma_ep_post - Post WRs to a transport's Send Queue + * @ia: transport's device information + * @ep: transport's RDMA endpoint information + * @req: rpcrdma_req containing the Send WR to post * - * Receive buffer is donated to hardware, reclaimed upon recv completion. + * Returns 0 if the post was successful, otherwise -ENOTCONN + * is returned. */ int rpcrdma_ep_post(struct rpcrdma_ia *ia, @@ -1501,32 +1461,27 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, --ep->rep_send_count; } - rc = ia->ri_ops->ro_send(ia, req); + rc = frwr_send(ia, req); trace_xprtrdma_post_send(req, rc); if (rc) return -ENOTCONN; return 0; } -/** - * rpcrdma_post_recvs - Maybe post some Receive buffers - * @r_xprt: controlling transport - * @temp: when true, allocate temp rpcrdma_rep objects - * - */ -void +static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; struct ib_recv_wr *wr, *bad_wr; int needed, count, rc; rc = 0; count = 0; needed = buf->rb_credits + (buf->rb_bc_srv_max_requests << 1); - if (buf->rb_posted_receives > needed) + if (ep->rep_receive_count > needed) goto out; - needed -= buf->rb_posted_receives; + needed -= ep->rep_receive_count; count = 0; wr = NULL; @@ -1574,7 +1529,7 @@ rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) --count; } } - buf->rb_posted_receives += count; + ep->rep_receive_count += count; out: trace_xprtrdma_post_recvs(r_xprt, count, rc); } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index a13ccb643ce0..5a18472f2c9c 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -66,7 +66,6 @@ * Interface Adapter -- one per transport instance */ struct rpcrdma_ia { - const struct rpcrdma_memreg_ops *ri_ops; struct ib_device *ri_device; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; @@ -81,8 +80,6 @@ struct rpcrdma_ia { bool ri_implicit_roundup; enum ib_mr_type ri_mrtype; unsigned long ri_flags; - struct ib_qp_attr ri_qp_attr; - struct ib_qp_init_attr ri_qp_init_attr; }; enum { @@ -101,7 +98,7 @@ struct rpcrdma_ep { wait_queue_head_t rep_connect_wait; struct rpcrdma_connect_private rep_cm_private; struct rdma_conn_param rep_remote_cma; - struct delayed_work rep_disconnect_worker; + int rep_receive_count; }; /* Pre-allocate extra Work Requests for handling backward receives @@ -262,20 +259,12 @@ struct rpcrdma_frwr { }; }; -struct rpcrdma_fmr { - struct ib_fmr *fm_mr; - u64 *fm_physaddrs; -}; - struct rpcrdma_mr { struct list_head mr_list; struct scatterlist *mr_sg; int mr_nents; enum dma_data_direction mr_dir; - union { - struct rpcrdma_fmr fmr; - struct rpcrdma_frwr frwr; - }; + struct rpcrdma_frwr frwr; struct rpcrdma_xprt *mr_xprt; u32 mr_handle; u32 mr_length; @@ -401,20 +390,18 @@ struct rpcrdma_buffer { spinlock_t rb_lock; /* protect buf lists */ struct list_head rb_send_bufs; struct list_head rb_recv_bufs; + struct list_head rb_allreqs; + unsigned long rb_flags; u32 rb_max_requests; u32 rb_credits; /* most recent credit grant */ - int rb_posted_receives; u32 rb_bc_srv_max_requests; - spinlock_t rb_reqslock; /* protect rb_allreqs */ - struct list_head rb_allreqs; - u32 rb_bc_max_requests; + struct workqueue_struct *rb_completion_wq; struct delayed_work rb_refresh_worker; }; -#define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) /* rb_flags */ enum { @@ -465,35 +452,6 @@ struct rpcrdma_stats { }; /* - * Per-registration mode operations - */ -struct rpcrdma_xprt; -struct rpcrdma_memreg_ops { - struct rpcrdma_mr_seg * - (*ro_map)(struct rpcrdma_xprt *, - struct rpcrdma_mr_seg *, int, bool, - struct rpcrdma_mr **); - int (*ro_send)(struct rpcrdma_ia *ia, - struct rpcrdma_req *req); - void (*ro_reminv)(struct rpcrdma_rep *rep, - struct list_head *mrs); - void (*ro_unmap_sync)(struct rpcrdma_xprt *, - struct list_head *); - int (*ro_open)(struct rpcrdma_ia *, - struct rpcrdma_ep *, - struct rpcrdma_create_data_internal *); - size_t (*ro_maxpages)(struct rpcrdma_xprt *); - int (*ro_init_mr)(struct rpcrdma_ia *, - struct rpcrdma_mr *); - void (*ro_release_mr)(struct rpcrdma_mr *mr); - const char *ro_displayname; - const int ro_send_w_inv_ok; -}; - -extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops; -extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops; - -/* * RPCRDMA transport -- encapsulates the structures above for * integration with RPC. * @@ -544,10 +502,6 @@ extern unsigned int xprt_rdma_memreg_strategy; int rpcrdma_ia_open(struct rpcrdma_xprt *xprt); void rpcrdma_ia_remove(struct rpcrdma_ia *ia); void rpcrdma_ia_close(struct rpcrdma_ia *); -bool frwr_is_supported(struct rpcrdma_ia *); -bool fmr_is_supported(struct rpcrdma_ia *); - -extern struct workqueue_struct *rpcrdma_receive_wq; /* * Endpoint calls - xprtrdma/verbs.c @@ -560,13 +514,12 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); -void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c */ struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *); -void rpcrdma_destroy_req(struct rpcrdma_req *); +void rpcrdma_req_destroy(struct rpcrdma_req *req); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf); @@ -604,9 +557,6 @@ rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb) return __rpcrdma_dma_map_regbuf(ia, rb); } -int rpcrdma_alloc_wq(void); -void rpcrdma_destroy_wq(void); - /* * Wrappers for chunk registration, shared by read/write chunk code. */ @@ -617,6 +567,23 @@ rpcrdma_data_dir(bool writing) return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; } +/* Memory registration calls xprtrdma/frwr_ops.c + */ +bool frwr_is_supported(struct rpcrdma_ia *); +int frwr_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, + struct rpcrdma_create_data_internal *cdata); +int frwr_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr); +void frwr_release_mr(struct rpcrdma_mr *mr); +size_t frwr_maxpages(struct rpcrdma_xprt *r_xprt); +struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, + struct rpcrdma_mr_seg *seg, + int nsegs, bool writing, u32 xid, + struct rpcrdma_mr **mr); +int frwr_send(struct rpcrdma_ia *ia, struct rpcrdma_req *req); +void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs); +void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, + struct list_head *mrs); + /* * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c */ @@ -653,6 +620,7 @@ static inline void rpcrdma_set_xdrlen(struct xdr_buf *xdr, size_t len) extern unsigned int xprt_rdma_max_inline_read; void xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap); void xprt_rdma_free_addresses(struct rpc_xprt *xprt); +void xprt_rdma_close(struct rpc_xprt *xprt); void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq); int xprt_rdma_init(void); void xprt_rdma_cleanup(void); @@ -661,7 +629,6 @@ void xprt_rdma_cleanup(void); */ #if defined(CONFIG_SUNRPC_BACKCHANNEL) int xprt_rdma_bc_setup(struct rpc_xprt *, unsigned int); -int xprt_rdma_bc_up(struct svc_serv *, struct net *); size_t xprt_rdma_bc_maxpayload(struct rpc_xprt *); int rpcrdma_bc_post_recv(struct rpcrdma_xprt *, unsigned int); void rpcrdma_bc_receive_call(struct rpcrdma_xprt *, struct rpcrdma_rep *); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index f0b3700cec95..13559e6a460b 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -68,8 +68,6 @@ static unsigned int xprt_max_tcp_slot_table_entries = RPC_MAX_SLOT_TABLE; static unsigned int xprt_min_resvport = RPC_DEF_MIN_RESVPORT; static unsigned int xprt_max_resvport = RPC_DEF_MAX_RESVPORT; -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - #define XS_TCP_LINGER_TO (15U * HZ) static unsigned int xs_tcp_fin_timeout __read_mostly = XS_TCP_LINGER_TO; @@ -159,8 +157,6 @@ static struct ctl_table sunrpc_table[] = { { }, }; -#endif - /* * Wait duration for a reply from the RPC portmapper. */ @@ -1400,17 +1396,6 @@ static void xs_tcp_force_close(struct rpc_xprt *xprt) } #if defined(CONFIG_SUNRPC_BACKCHANNEL) -static int xs_tcp_bc_up(struct svc_serv *serv, struct net *net) -{ - int ret; - - ret = svc_create_xprt(serv, "tcp-bc", net, PF_INET, 0, - SVC_SOCK_ANONYMOUS); - if (ret < 0) - return ret; - return 0; -} - static size_t xs_tcp_bc_maxpayload(struct rpc_xprt *xprt) { return PAGE_SIZE; @@ -1600,6 +1585,7 @@ static void xs_udp_set_buffer_size(struct rpc_xprt *xprt, size_t sndsize, size_t /** * xs_udp_timer - called when a retransmit timeout occurs on a UDP transport + * @xprt: controlling transport * @task: task that timed out * * Adjust the congestion window after a retransmit timeout has occurred. @@ -2257,6 +2243,7 @@ out: /** * xs_tcp_setup_socket - create a TCP socket and connect to a remote endpoint + * @work: queued work item * * Invoked by a work queue tasklet. */ @@ -2665,7 +2652,6 @@ static const struct rpc_xprt_ops xs_tcp_ops = { .inject_disconnect = xs_inject_disconnect, #ifdef CONFIG_SUNRPC_BACKCHANNEL .bc_setup = xprt_setup_bc, - .bc_up = xs_tcp_bc_up, .bc_maxpayload = xs_tcp_bc_maxpayload, .bc_free_rqst = xprt_free_bc_rqst, .bc_destroy = xprt_destroy_bc, @@ -3107,10 +3093,8 @@ static struct xprt_class xs_bc_tcp_transport = { */ int init_socket_xprt(void) { -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (!sunrpc_table_header) sunrpc_table_header = register_sysctl_table(sunrpc_table); -#endif xprt_register_transport(&xs_local_transport); xprt_register_transport(&xs_udp_transport); @@ -3126,12 +3110,10 @@ int init_socket_xprt(void) */ void cleanup_socket_xprt(void) { -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) if (sunrpc_table_header) { unregister_sysctl_table(sunrpc_table_header); sunrpc_table_header = NULL; } -#endif xprt_unregister_transport(&xs_local_transport); xprt_unregister_transport(&xs_udp_transport); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index fb2c0d8f359f..d27f30a9a01d 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -319,7 +319,6 @@ static int tipc_enable_bearer(struct net *net, const char *name, res = tipc_disc_create(net, b, &b->bcast_addr, &skb); if (res) { bearer_disable(net, b); - kfree(b); errstr = "failed to create discoverer"; goto rejected; } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 21f6ccc89401..40f5cae623a7 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -904,6 +904,8 @@ static int tipc_nl_compat_publ_dump(struct tipc_nl_compat_msg *msg, u32 sock) hdr = genlmsg_put(args, 0, 0, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_PUBL_GET); + if (!hdr) + return -EMSGSIZE; nest = nla_nest_start(args, TIPC_NLA_SOCK); if (!nest) { diff --git a/samples/seccomp/.gitignore b/samples/seccomp/.gitignore index 78fb78184291..d1e2e817d556 100644 --- a/samples/seccomp/.gitignore +++ b/samples/seccomp/.gitignore @@ -1,3 +1,4 @@ bpf-direct bpf-fancy dropper +user-trap diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile index cf34ff6b4065..4920903c8009 100644 --- a/samples/seccomp/Makefile +++ b/samples/seccomp/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 ifndef CROSS_COMPILE -hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct +hostprogs-$(CONFIG_SAMPLE_SECCOMP) := bpf-fancy dropper bpf-direct user-trap HOSTCFLAGS_bpf-fancy.o += -I$(objtree)/usr/include HOSTCFLAGS_bpf-fancy.o += -idirafter $(objtree)/include @@ -16,6 +16,10 @@ HOSTCFLAGS_bpf-direct.o += -I$(objtree)/usr/include HOSTCFLAGS_bpf-direct.o += -idirafter $(objtree)/include bpf-direct-objs := bpf-direct.o +HOSTCFLAGS_user-trap.o += -I$(objtree)/usr/include +HOSTCFLAGS_user-trap.o += -idirafter $(objtree)/include +user-trap-objs := user-trap.o + # Try to match the kernel target. ifndef CONFIG_64BIT @@ -33,6 +37,7 @@ HOSTCFLAGS_bpf-fancy.o += $(MFLAG) HOSTLDLIBS_bpf-direct += $(MFLAG) HOSTLDLIBS_bpf-fancy += $(MFLAG) HOSTLDLIBS_dropper += $(MFLAG) +HOSTLDLIBS_user-trap += $(MFLAG) endif always := $(hostprogs-m) endif diff --git a/samples/seccomp/user-trap.c b/samples/seccomp/user-trap.c new file mode 100644 index 000000000000..6d0125ca8af7 --- /dev/null +++ b/samples/seccomp/user-trap.c @@ -0,0 +1,375 @@ +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <string.h> +#include <stddef.h> +#include <sys/sysmacros.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <sys/user.h> +#include <sys/ioctl.h> +#include <sys/ptrace.h> +#include <sys/mount.h> +#include <linux/limits.h> +#include <linux/filter.h> +#include <linux/seccomp.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + +static int seccomp(unsigned int op, unsigned int flags, void *args) +{ + errno = 0; + return syscall(__NR_seccomp, op, flags, args); +} + +static int send_fd(int sock, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + *((int *)CMSG_DATA(cmsg)) = fd; + msg.msg_controllen = cmsg->cmsg_len; + + if (sendmsg(sock, &msg, 0) < 0) { + perror("sendmsg"); + return -1; + } + + return 0; +} + +static int recv_fd(int sock) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + char buf[CMSG_SPACE(sizeof(int))] = {0}, c = 'c'; + struct iovec io = { + .iov_base = &c, + .iov_len = 1, + }; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = buf; + msg.msg_controllen = sizeof(buf); + + if (recvmsg(sock, &msg, 0) < 0) { + perror("recvmsg"); + return -1; + } + + cmsg = CMSG_FIRSTHDR(&msg); + + return *((int *)CMSG_DATA(cmsg)); +} + +static int user_trap_syscall(int nr, unsigned int flags) +{ + 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, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); +} + +static int handle_req(struct seccomp_notif *req, + struct seccomp_notif_resp *resp, int listener) +{ + char path[PATH_MAX], source[PATH_MAX], target[PATH_MAX]; + int ret = -1, mem; + + resp->id = req->id; + resp->error = -EPERM; + resp->val = 0; + + if (req->data.nr != __NR_mount) { + fprintf(stderr, "huh? trapped something besides mount? %d\n", req->data.nr); + return -1; + } + + /* Only allow bind mounts. */ + if (!(req->data.args[3] & MS_BIND)) + return 0; + + /* + * Ok, let's read the task's memory to see where they wanted their + * mount to go. + */ + snprintf(path, sizeof(path), "/proc/%d/mem", req->pid); + mem = open(path, O_RDONLY); + if (mem < 0) { + perror("open mem"); + return -1; + } + + /* + * Now we avoid a TOCTOU: we referred to a pid by its pid, but since + * the pid that made the syscall may have died, we need to confirm that + * the pid is still valid after we open its /proc/pid/mem file. We can + * ask the listener fd this as follows. + * + * Note that this check should occur *after* any task-specific + * resources are opened, to make sure that the task has not died and + * we're not wrongly reading someone else's state in order to make + * decisions. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req->id) < 0) { + fprintf(stderr, "task died before we could map its memory\n"); + goto out; + } + + /* + * Phew, we've got the right /proc/pid/mem. Now we can read it. Note + * that to avoid another TOCTOU, we should read all of the pointer args + * before we decide to allow the syscall. + */ + if (lseek(mem, req->data.args[0], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, source, sizeof(source)); + if (ret < 0) { + perror("read"); + goto out; + } + + if (lseek(mem, req->data.args[1], SEEK_SET) < 0) { + perror("seek"); + goto out; + } + + ret = read(mem, target, sizeof(target)); + if (ret < 0) { + perror("read"); + goto out; + } + + /* + * Our policy is to only allow bind mounts inside /tmp. This isn't very + * interesting, because we could do unprivlieged bind mounts with user + * namespaces already, but you get the idea. + */ + if (!strncmp(source, "/tmp/", 5) && !strncmp(target, "/tmp/", 5)) { + if (mount(source, target, NULL, req->data.args[3], NULL) < 0) { + ret = -1; + perror("actual mount"); + goto out; + } + resp->error = 0; + } + + /* Even if we didn't allow it because of policy, generating the + * response was be a success, because we want to tell the worker EPERM. + */ + ret = 0; + +out: + close(mem); + return ret; +} + +int main(void) +{ + int sk_pair[2], ret = 1, status, listener; + pid_t worker = 0 , tracer = 0; + + if (socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair) < 0) { + perror("socketpair"); + return 1; + } + + worker = fork(); + if (worker < 0) { + perror("fork"); + goto close_pair; + } + + if (worker == 0) { + listener = user_trap_syscall(__NR_mount, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + if (listener < 0) { + perror("seccomp"); + exit(1); + } + + /* + * Drop privileges. We definitely can't mount as uid 1000. + */ + if (setuid(1000) < 0) { + perror("setuid"); + exit(1); + } + + /* + * Send the listener to the parent; also serves as + * synchronization. + */ + if (send_fd(sk_pair[1], listener) < 0) + exit(1); + close(listener); + + if (mkdir("/tmp/foo", 0755) < 0) { + perror("mkdir"); + exit(1); + } + + /* + * Try a bad mount just for grins. + */ + if (mount("/dev/sda", "/tmp/foo", NULL, 0, NULL) != -1) { + fprintf(stderr, "huh? mounted /dev/sda?\n"); + exit(1); + } + + if (errno != EPERM) { + perror("bad error from mount"); + exit(1); + } + + /* + * Ok, we expect this one to succeed. + */ + if (mount("/tmp/foo", "/tmp/foo", NULL, MS_BIND, NULL) < 0) { + perror("mount"); + exit(1); + } + + exit(0); + } + + /* + * Get the listener from the child. + */ + listener = recv_fd(sk_pair[0]); + if (listener < 0) + goto out_kill; + + /* + * Fork a task to handle the requests. This isn't strictly necessary, + * but it makes the particular writing of this sample easier, since we + * can just wait ofr the tracee to exit and kill the tracer. + */ + tracer = fork(); + if (tracer < 0) { + perror("fork"); + goto out_kill; + } + + if (tracer == 0) { + struct seccomp_notif *req; + struct seccomp_notif_resp *resp; + struct seccomp_notif_sizes sizes; + + if (seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes) < 0) { + perror("seccomp(GET_NOTIF_SIZES)"); + goto out_close; + } + + req = malloc(sizes.seccomp_notif); + if (!req) + goto out_close; + memset(req, 0, sizeof(*req)); + + resp = malloc(sizes.seccomp_notif_resp); + if (!resp) + goto out_req; + memset(resp, 0, sizeof(*resp)); + + while (1) { + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, req)) { + perror("ioctl recv"); + goto out_resp; + } + + if (handle_req(req, resp, listener) < 0) + goto out_resp; + + /* + * ENOENT here means that the task may have gotten a + * signal and restarted the syscall. It's up to the + * handler to decide what to do in this case, but for + * the sample code, we just ignore it. Probably + * something better should happen, like undoing the + * mount, or keeping track of the args to make sure we + * don't do it again. + */ + if (ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, resp) < 0 && + errno != ENOENT) { + perror("ioctl send"); + goto out_resp; + } + } +out_resp: + free(resp); +out_req: + free(req); +out_close: + close(listener); + exit(1); + } + + close(listener); + + if (waitpid(worker, &status, 0) != worker) { + perror("waitpid"); + goto out_kill; + } + + if (umount2("/tmp/foo", MNT_DETACH) < 0 && errno != EINVAL) { + perror("umount2"); + goto out_kill; + } + + if (remove("/tmp/foo") < 0 && errno != ENOENT) { + perror("remove"); + exit(1); + } + + if (!WIFEXITED(status) || WEXITSTATUS(status)) { + fprintf(stderr, "worker exited nonzero\n"); + goto out_kill; + } + + ret = 0; + +out_kill: + if (tracer > 0) + kill(tracer, SIGKILL); + if (worker > 0) + kill(worker, SIGKILL); + +close_pair: + close(sk_pair[0]); + close(sk_pair[1]); + return ret; +} diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig index 877af1f2d904..2ea4ec9991d5 100644 --- a/security/integrity/Kconfig +++ b/security/integrity/Kconfig @@ -51,6 +51,17 @@ config INTEGRITY_TRUSTED_KEYRING .evm keyrings be signed by a key on the system trusted keyring. +config INTEGRITY_PLATFORM_KEYRING + bool "Provide keyring for platform/firmware trusted keys" + depends on INTEGRITY_ASYMMETRIC_KEYS + depends on SYSTEM_BLACKLIST_KEYRING + depends on EFI + help + Provide a separate, distinct keyring for platform trusted keys, which + the kernel automatically populates during initialization from values + provided by the platform for verifying the kexec'ed kerned image + and, possibly, the initramfs signature. + config INTEGRITY_AUDIT bool "Enables integrity auditing support " depends on AUDIT diff --git a/security/integrity/Makefile b/security/integrity/Makefile index 04d6e462b079..86df9aba8c0f 100644 --- a/security/integrity/Makefile +++ b/security/integrity/Makefile @@ -9,6 +9,11 @@ integrity-y := iint.o integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o +integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o \ + platform_certs/efi_parser.o \ + platform_certs/load_uefi.o +obj-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/load_uefi.o +$(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar subdir-$(CONFIG_IMA) += ima obj-$(CONFIG_IMA) += ima/ diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index 5eacba858e4b..f45d6edecf99 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -34,7 +34,7 @@ static const char * const keyring_name[INTEGRITY_KEYRING_MAX] = { ".evm", ".ima", #endif - "_module", + ".platform", }; #ifdef CONFIG_IMA_KEYRINGS_PERMIT_SIGNED_BY_BUILTIN_OR_SECONDARY @@ -73,12 +73,38 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, return -EOPNOTSUPP; } -int __init integrity_init_keyring(const unsigned int id) +static int __integrity_init_keyring(const unsigned int id, key_perm_t perm, + struct key_restriction *restriction) { const struct cred *cred = current_cred(); - struct key_restriction *restriction; int err = 0; + keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), + KGIDT_INIT(0), cred, perm, + KEY_ALLOC_NOT_IN_QUOTA, restriction, NULL); + if (IS_ERR(keyring[id])) { + err = PTR_ERR(keyring[id]); + pr_info("Can't allocate %s keyring (%d)\n", + keyring_name[id], err); + keyring[id] = NULL; + } + + return err; +} + +int __init integrity_init_keyring(const unsigned int id) +{ + struct key_restriction *restriction; + key_perm_t perm; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW + | KEY_USR_READ | KEY_USR_SEARCH; + + if (id == INTEGRITY_KEYRING_PLATFORM) { + restriction = NULL; + goto out; + } + if (!IS_ENABLED(CONFIG_INTEGRITY_TRUSTED_KEYRING)) return 0; @@ -87,32 +113,43 @@ int __init integrity_init_keyring(const unsigned int id) return -ENOMEM; restriction->check = restrict_link_to_ima; + perm |= KEY_USR_WRITE; - keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0), - KGIDT_INIT(0), cred, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ | - KEY_USR_WRITE | KEY_USR_SEARCH), - KEY_ALLOC_NOT_IN_QUOTA, - restriction, NULL); - if (IS_ERR(keyring[id])) { - err = PTR_ERR(keyring[id]); - pr_info("Can't allocate %s keyring (%d)\n", - keyring_name[id], err); - keyring[id] = NULL; +out: + return __integrity_init_keyring(id, perm, restriction); +} + +int __init integrity_add_key(const unsigned int id, const void *data, + off_t size, key_perm_t perm) +{ + key_ref_t key; + int rc = 0; + + if (!keyring[id]) + return -EINVAL; + + key = key_create_or_update(make_key_ref(keyring[id], 1), "asymmetric", + NULL, data, size, perm, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(key)) { + rc = PTR_ERR(key); + pr_err("Problem loading X.509 certificate %d\n", rc); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); } - return err; + + return rc; + } int __init integrity_load_x509(const unsigned int id, const char *path) { - key_ref_t key; void *data; loff_t size; int rc; - - if (!keyring[id]) - return -EINVAL; + key_perm_t perm; rc = kernel_read_file_from_path(path, &data, &size, 0, READING_X509_CERTIFICATE); @@ -121,23 +158,21 @@ int __init integrity_load_x509(const unsigned int id, const char *path) return rc; } - key = key_create_or_update(make_key_ref(keyring[id], 1), - "asymmetric", - NULL, - data, - size, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA); - if (IS_ERR(key)) { - rc = PTR_ERR(key); - pr_err("Problem loading X.509 certificate (%d): %s\n", - rc, path); - } else { - pr_notice("Loaded X.509 cert '%s': %s\n", - key_ref_to_ptr(key)->description, path); - key_ref_put(key); - } + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW | KEY_USR_READ; + + pr_info("Loading X.509 certificate: %s\n", path); + rc = integrity_add_key(id, (const void *)data, size, perm); + vfree(data); - return 0; + return rc; +} + +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm) +{ + if (!data) + return -EINVAL; + + pr_info("Loading X.509 certificate: %s\n", source); + return integrity_add_key(id, data, len, perm); } diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig index 13b446328dda..a18f8c6d13b5 100644 --- a/security/integrity/ima/Kconfig +++ b/security/integrity/ima/Kconfig @@ -157,6 +157,14 @@ config IMA_APPRAISE <http://linux-ima.sourceforge.net> If unsure, say N. +config IMA_ARCH_POLICY + bool "Enable loading an IMA architecture specific policy" + depends on KEXEC_VERIFY_SIG || IMA_APPRAISE && INTEGRITY_ASYMMETRIC_KEYS + default n + help + This option enables loading an IMA architecture specific policy + based on run time secure boot flags. + config IMA_APPRAISE_BUILD_POLICY bool "IMA build time configured policy rules" depends on IMA_APPRAISE && INTEGRITY_ASYMMETRIC_KEYS @@ -217,7 +225,7 @@ config IMA_APPRAISE_REQUIRE_POLICY_SIGS config IMA_APPRAISE_BOOTPARAM bool "ima_appraise boot parameter" - depends on IMA_APPRAISE + depends on IMA_APPRAISE && !IMA_ARCH_POLICY default y help This option enables the different "ima_appraise=" modes diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index 2e11e750a067..a2baa85ea2f5 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -289,12 +289,22 @@ int ima_appraise_measurement(enum ima_hooks func, case EVM_IMA_XATTR_DIGSIG: set_bit(IMA_DIGSIG, &iint->atomic_flags); rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA, - (const char *)xattr_value, rc, + (const char *)xattr_value, + xattr_len, iint->ima_hash->digest, iint->ima_hash->length); if (rc == -EOPNOTSUPP) { status = INTEGRITY_UNKNOWN; - } else if (rc) { + break; + } + if (IS_ENABLED(CONFIG_INTEGRITY_PLATFORM_KEYRING) && rc && + func == KEXEC_KERNEL_CHECK) + rc = integrity_digsig_verify(INTEGRITY_KEYRING_PLATFORM, + (const char *)xattr_value, + xattr_len, + iint->ima_hash->digest, + iint->ima_hash->length); + if (rc) { cause = "invalid-signature"; status = INTEGRITY_FAIL; } else { diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c index d9e7728027c6..acf2c7df7145 100644 --- a/security/integrity/ima/ima_crypto.c +++ b/security/integrity/ima/ima_crypto.c @@ -643,7 +643,7 @@ int ima_calc_buffer_hash(const void *buf, loff_t len, return calc_buffer_shash(buf, len, hash); } -static void __init ima_pcrread(int idx, u8 *pcr) +static void __init ima_pcrread(u32 idx, u8 *pcr) { if (!ima_tpm_chip) return; @@ -659,7 +659,8 @@ static int __init ima_calc_boot_aggregate_tfm(char *digest, struct crypto_shash *tfm) { u8 pcr_i[TPM_DIGEST_SIZE]; - int rc, i; + int rc; + u32 i; SHASH_DESC_ON_STACK(shash, tfm); shash->tfm = tfm; diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 616a88f95b92..4ffac4f5c647 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -105,7 +105,7 @@ static void ima_rdwr_violation_check(struct file *file, } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); - if ((atomic_read(&inode->i_writecount) > 0) && must_measure) + if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } @@ -507,20 +507,26 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, */ int ima_load_data(enum kernel_load_data_id id) { - bool sig_enforce; + bool ima_enforce, sig_enforce; - if ((ima_appraise & IMA_APPRAISE_ENFORCE) != IMA_APPRAISE_ENFORCE) - return 0; + ima_enforce = + (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: - if (ima_appraise & IMA_APPRAISE_KEXEC) { + if (IS_ENABLED(CONFIG_KEXEC_VERIFY_SIG) + && arch_ima_get_secureboot()) { + pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); + return -EACCES; + } + + if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: - if (ima_appraise & IMA_APPRAISE_FIRMWARE) { + if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE)) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } @@ -528,7 +534,8 @@ int ima_load_data(enum kernel_load_data_id id) case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); - if (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES)) { + if (ima_enforce && (!sig_enforce + && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index fcf5b2729063..8bc8a1c8cb3f 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -20,6 +20,7 @@ #include <linux/rculist.h> #include <linux/genhd.h> #include <linux/seq_file.h> +#include <linux/ima.h> #include "ima.h" @@ -58,6 +59,8 @@ enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE, enum policy_types { ORIGINAL_TCB = 1, DEFAULT_TCB }; +enum policy_rule_list { IMA_DEFAULT_POLICY = 1, IMA_CUSTOM_POLICY }; + struct ima_rule_entry { struct list_head list; int action; @@ -104,7 +107,8 @@ static struct ima_rule_entry dont_measure_rules[] __ro_after_init = { .flags = IMA_FSMAGIC}, {.action = DONT_MEASURE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, - {.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC} + {.action = DONT_MEASURE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, + {.action = DONT_MEASURE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC} }; static struct ima_rule_entry original_measurement_rules[] __ro_after_init = { @@ -147,6 +151,7 @@ static struct ima_rule_entry default_appraise_rules[] __ro_after_init = { {.action = DONT_APPRAISE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = SMACK_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = NSFS_MAGIC, .flags = IMA_FSMAGIC}, + {.action = DONT_APPRAISE, .fsmagic = EFIVARFS_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC}, {.action = DONT_APPRAISE, .fsmagic = CGROUP2_SUPER_MAGIC, .flags = IMA_FSMAGIC}, #ifdef CONFIG_IMA_WRITE_POLICY @@ -193,6 +198,9 @@ static struct ima_rule_entry secure_boot_rules[] __ro_after_init = { .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED}, }; +/* An array of architecture specific rules */ +struct ima_rule_entry *arch_policy_entry __ro_after_init; + static LIST_HEAD(ima_default_rules); static LIST_HEAD(ima_policy_rules); static LIST_HEAD(ima_temp_rules); @@ -473,6 +481,75 @@ static int ima_appraise_flag(enum ima_hooks func) return 0; } +static void add_rules(struct ima_rule_entry *entries, int count, + enum policy_rule_list policy_rule) +{ + int i = 0; + + for (i = 0; i < count; i++) { + struct ima_rule_entry *entry; + + if (policy_rule & IMA_DEFAULT_POLICY) + list_add_tail(&entries[i].list, &ima_default_rules); + + if (policy_rule & IMA_CUSTOM_POLICY) { + entry = kmemdup(&entries[i], sizeof(*entry), + GFP_KERNEL); + if (!entry) + continue; + + list_add_tail(&entry->list, &ima_policy_rules); + } + if (entries[i].action == APPRAISE) + temp_ima_appraise |= ima_appraise_flag(entries[i].func); + if (entries[i].func == POLICY_CHECK) + temp_ima_appraise |= IMA_APPRAISE_POLICY; + } +} + +static int ima_parse_rule(char *rule, struct ima_rule_entry *entry); + +static int __init ima_init_arch_policy(void) +{ + const char * const *arch_rules; + const char * const *rules; + int arch_entries = 0; + int i = 0; + + arch_rules = arch_get_ima_policy(); + if (!arch_rules) + return arch_entries; + + /* Get number of rules */ + for (rules = arch_rules; *rules != NULL; rules++) + arch_entries++; + + arch_policy_entry = kcalloc(arch_entries + 1, + sizeof(*arch_policy_entry), GFP_KERNEL); + if (!arch_policy_entry) + return 0; + + /* Convert each policy string rules to struct ima_rule_entry format */ + for (rules = arch_rules, i = 0; *rules != NULL; rules++) { + char rule[255]; + int result; + + result = strlcpy(rule, *rules, sizeof(rule)); + + INIT_LIST_HEAD(&arch_policy_entry[i].list); + result = ima_parse_rule(rule, &arch_policy_entry[i]); + if (result) { + pr_warn("Skipping unknown architecture policy rule: %s\n", + rule); + memset(&arch_policy_entry[i], 0, + sizeof(*arch_policy_entry)); + continue; + } + i++; + } + return i; +} + /** * ima_init_policy - initialize the default measure rules. * @@ -481,68 +558,68 @@ static int ima_appraise_flag(enum ima_hooks func) */ void __init ima_init_policy(void) { - int i, measure_entries, appraise_entries, secure_boot_entries; + int build_appraise_entries, arch_entries; - /* if !ima_policy set entries = 0 so we load NO default rules */ - measure_entries = ima_policy ? ARRAY_SIZE(dont_measure_rules) : 0; - appraise_entries = ima_use_appraise_tcb ? - ARRAY_SIZE(default_appraise_rules) : 0; - secure_boot_entries = ima_use_secure_boot ? - ARRAY_SIZE(secure_boot_rules) : 0; - - for (i = 0; i < measure_entries; i++) - list_add_tail(&dont_measure_rules[i].list, &ima_default_rules); + /* if !ima_policy, we load NO default rules */ + if (ima_policy) + add_rules(dont_measure_rules, ARRAY_SIZE(dont_measure_rules), + IMA_DEFAULT_POLICY); switch (ima_policy) { case ORIGINAL_TCB: - for (i = 0; i < ARRAY_SIZE(original_measurement_rules); i++) - list_add_tail(&original_measurement_rules[i].list, - &ima_default_rules); + add_rules(original_measurement_rules, + ARRAY_SIZE(original_measurement_rules), + IMA_DEFAULT_POLICY); break; case DEFAULT_TCB: - for (i = 0; i < ARRAY_SIZE(default_measurement_rules); i++) - list_add_tail(&default_measurement_rules[i].list, - &ima_default_rules); + add_rules(default_measurement_rules, + ARRAY_SIZE(default_measurement_rules), + IMA_DEFAULT_POLICY); default: break; } /* + * Based on runtime secure boot flags, insert arch specific measurement + * and appraise rules requiring file signatures for both the initial + * and custom policies, prior to other appraise rules. + * (Highest priority) + */ + arch_entries = ima_init_arch_policy(); + if (!arch_entries) + pr_info("No architecture policies found\n"); + else + add_rules(arch_policy_entry, arch_entries, + IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY); + + /* * Insert the builtin "secure_boot" policy rules requiring file - * signatures, prior to any other appraise rules. + * signatures, prior to other appraise rules. */ - for (i = 0; i < secure_boot_entries; i++) { - list_add_tail(&secure_boot_rules[i].list, &ima_default_rules); - temp_ima_appraise |= - ima_appraise_flag(secure_boot_rules[i].func); - } + if (ima_use_secure_boot) + add_rules(secure_boot_rules, ARRAY_SIZE(secure_boot_rules), + IMA_DEFAULT_POLICY); /* * Insert the build time appraise rules requiring file signatures * for both the initial and custom policies, prior to other appraise - * rules. + * rules. As the secure boot rules includes all of the build time + * rules, include either one or the other set of rules, but not both. */ - for (i = 0; i < ARRAY_SIZE(build_appraise_rules); i++) { - struct ima_rule_entry *entry; - - if (!secure_boot_entries) - list_add_tail(&build_appraise_rules[i].list, - &ima_default_rules); - - entry = kmemdup(&build_appraise_rules[i], sizeof(*entry), - GFP_KERNEL); - if (entry) - list_add_tail(&entry->list, &ima_policy_rules); - build_ima_appraise |= - ima_appraise_flag(build_appraise_rules[i].func); + build_appraise_entries = ARRAY_SIZE(build_appraise_rules); + if (build_appraise_entries) { + if (ima_use_secure_boot) + add_rules(build_appraise_rules, build_appraise_entries, + IMA_CUSTOM_POLICY); + else + add_rules(build_appraise_rules, build_appraise_entries, + IMA_DEFAULT_POLICY | IMA_CUSTOM_POLICY); } - for (i = 0; i < appraise_entries; i++) { - list_add_tail(&default_appraise_rules[i].list, - &ima_default_rules); - if (default_appraise_rules[i].func == POLICY_CHECK) - temp_ima_appraise |= IMA_APPRAISE_POLICY; - } + if (ima_use_appraise_tcb) + add_rules(default_appraise_rules, + ARRAY_SIZE(default_appraise_rules), + IMA_DEFAULT_POLICY); ima_rules = &ima_default_rules; ima_update_policy_flag(); @@ -576,6 +653,14 @@ void ima_update_policy(void) if (ima_rules != policy) { ima_policy_flag = 0; ima_rules = policy; + + /* + * IMA architecture specific policy rules are specified + * as strings and converted to an array of ima_entry_rules + * on boot. After loading a custom policy, free the + * architecture specific rules stored as an array. + */ + kfree(arch_policy_entry); } ima_update_policy_flag(); } diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index e60473b13a8d..7de59f44cba3 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -141,7 +141,7 @@ int integrity_kernel_read(struct file *file, loff_t offset, #define INTEGRITY_KEYRING_EVM 0 #define INTEGRITY_KEYRING_IMA 1 -#define INTEGRITY_KEYRING_MODULE 2 +#define INTEGRITY_KEYRING_PLATFORM 2 #define INTEGRITY_KEYRING_MAX 3 extern struct dentry *integrity_dir; @@ -153,6 +153,8 @@ int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen, int __init integrity_init_keyring(const unsigned int id); int __init integrity_load_x509(const unsigned int id, const char *path); +int __init integrity_load_cert(const unsigned int id, const char *source, + const void *data, size_t len, key_perm_t perm); #else static inline int integrity_digsig_verify(const unsigned int id, @@ -166,6 +168,14 @@ static inline int integrity_init_keyring(const unsigned int id) { return 0; } + +static inline int __init integrity_load_cert(const unsigned int id, + const char *source, + const void *data, size_t len, + key_perm_t perm) +{ + return 0; +} #endif /* CONFIG_INTEGRITY_SIGNATURE */ #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS @@ -222,3 +232,13 @@ integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) } #endif + +#ifdef CONFIG_INTEGRITY_PLATFORM_KEYRING +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len); +#else +static inline void __init add_to_platform_keyring(const char *source, + const void *data, size_t len) +{ +} +#endif diff --git a/security/integrity/platform_certs/efi_parser.c b/security/integrity/platform_certs/efi_parser.c new file mode 100644 index 000000000000..18f01f36fe6a --- /dev/null +++ b/security/integrity/platform_certs/efi_parser.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* EFI signature/key/certificate list parser + * + * Copyright (C) 2012, 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) "EFI: "fmt +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/err.h> +#include <linux/efi.h> + +/** + * parse_efi_signature_list - Parse an EFI signature list for certificates + * @source: The source of the key + * @data: The data blob to parse + * @size: The size of the data blob + * @get_handler_for_guid: Get the handler func for the sig type (or NULL) + * + * Parse an EFI signature list looking for elements of interest. A list is + * made up of a series of sublists, where all the elements in a sublist are of + * the same type, but sublists can be of different types. + * + * For each sublist encountered, the @get_handler_for_guid function is called + * with the type specifier GUID and returns either a pointer to a function to + * handle elements of that type or NULL if the type is not of interest. + * + * If the sublist is of interest, each element is passed to the handler + * function in turn. + * + * Error EBADMSG is returned if the list doesn't parse correctly and 0 is + * returned if the list was parsed correctly. No error can be returned from + * the @get_handler_for_guid function or the element handler function it + * returns. + */ +int __init parse_efi_signature_list( + const char *source, + const void *data, size_t size, + efi_element_handler_t (*get_handler_for_guid)(const efi_guid_t *)) +{ + efi_element_handler_t handler; + unsigned int offs = 0; + + pr_devel("-->%s(,%zu)\n", __func__, size); + + while (size > 0) { + const efi_signature_data_t *elem; + efi_signature_list_t list; + size_t lsize, esize, hsize, elsize; + + if (size < sizeof(list)) + return -EBADMSG; + + memcpy(&list, data, sizeof(list)); + pr_devel("LIST[%04x] guid=%pUl ls=%x hs=%x ss=%x\n", + offs, + list.signature_type.b, list.signature_list_size, + list.signature_header_size, list.signature_size); + + lsize = list.signature_list_size; + hsize = list.signature_header_size; + esize = list.signature_size; + elsize = lsize - sizeof(list) - hsize; + + if (lsize > size) { + pr_devel("<--%s() = -EBADMSG [overrun @%x]\n", + __func__, offs); + return -EBADMSG; + } + + if (lsize < sizeof(list) || + lsize - sizeof(list) < hsize || + esize < sizeof(*elem) || + elsize < esize || + elsize % esize != 0) { + pr_devel("- bad size combo @%x\n", offs); + return -EBADMSG; + } + + handler = get_handler_for_guid(&list.signature_type); + if (!handler) { + data += lsize; + size -= lsize; + offs += lsize; + continue; + } + + data += sizeof(list) + hsize; + size -= sizeof(list) + hsize; + offs += sizeof(list) + hsize; + + for (; elsize > 0; elsize -= esize) { + elem = data; + + pr_devel("ELEM[%04x]\n", offs); + handler(source, + &elem->signature_data, + esize - sizeof(*elem)); + + data += esize; + size -= esize; + offs += esize; + } + } + + return 0; +} diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c new file mode 100644 index 000000000000..81b19c52832b --- /dev/null +++ b/security/integrity/platform_certs/load_uefi.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/efi.h> +#include <linux/slab.h> +#include <keys/asymmetric-type.h> +#include <keys/system_keyring.h> +#include "../integrity.h" + +static efi_guid_t efi_cert_x509_guid __initdata = EFI_CERT_X509_GUID; +static efi_guid_t efi_cert_x509_sha256_guid __initdata = + EFI_CERT_X509_SHA256_GUID; +static efi_guid_t efi_cert_sha256_guid __initdata = EFI_CERT_SHA256_GUID; + +/* + * Look to see if a UEFI variable called MokIgnoreDB exists and return true if + * it does. + * + * This UEFI variable is set by the shim if a user tells the shim to not use + * the certs/hashes in the UEFI db variable for verification purposes. If it + * is set, we should ignore the db variable also and the true return indicates + * this. + */ +static __init bool uefi_check_ignore_db(void) +{ + efi_status_t status; + unsigned int db = 0; + unsigned long size = sizeof(db); + efi_guid_t guid = EFI_SHIM_LOCK_GUID; + + status = efi.get_variable(L"MokIgnoreDB", &guid, NULL, &size, &db); + return status == EFI_SUCCESS; +} + +/* + * Get a certificate list blob from the named EFI variable. + */ +static __init void *get_cert_list(efi_char16_t *name, efi_guid_t *guid, + unsigned long *size) +{ + efi_status_t status; + unsigned long lsize = 4; + unsigned long tmpdb[4]; + void *db; + + status = efi.get_variable(name, guid, NULL, &lsize, &tmpdb); + if (status != EFI_BUFFER_TOO_SMALL) { + pr_err("Couldn't get size: 0x%lx\n", status); + return NULL; + } + + db = kmalloc(lsize, GFP_KERNEL); + if (!db) + return NULL; + + status = efi.get_variable(name, guid, NULL, &lsize, db); + if (status != EFI_SUCCESS) { + kfree(db); + pr_err("Error reading db var: 0x%lx\n", status); + return NULL; + } + + *size = lsize; + return db; +} + +/* + * Blacklist a hash. + */ +static __init void uefi_blacklist_hash(const char *source, const void *data, + size_t len, const char *type, + size_t type_len) +{ + char *hash, *p; + + hash = kmalloc(type_len + len * 2 + 1, GFP_KERNEL); + if (!hash) + return; + p = memcpy(hash, type, type_len); + p += type_len; + bin2hex(p, data, len); + p += len * 2; + *p = 0; + + mark_hash_blacklisted(hash); + kfree(hash); +} + +/* + * Blacklist an X509 TBS hash. + */ +static __init void uefi_blacklist_x509_tbs(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "tbs:", 4); +} + +/* + * Blacklist the hash of an executable. + */ +static __init void uefi_blacklist_binary(const char *source, + const void *data, size_t len) +{ + uefi_blacklist_hash(source, data, len, "bin:", 4); +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI db and MokListRT tables. + */ +static __init efi_element_handler_t get_handler_for_db(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return add_to_platform_keyring; + return 0; +} + +/* + * Return the appropriate handler for particular signature list types found in + * the UEFI dbx and MokListXRT tables. + */ +static __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t * + sig_type) +{ + if (efi_guidcmp(*sig_type, efi_cert_x509_sha256_guid) == 0) + return uefi_blacklist_x509_tbs; + if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) + return uefi_blacklist_binary; + return 0; +} + +/* + * Load the certs contained in the UEFI databases into the platform trusted + * keyring and the UEFI blacklisted X.509 cert SHA256 hashes into the blacklist + * keyring. + */ +static int __init load_uefi_certs(void) +{ + efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; + efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; + void *db = NULL, *dbx = NULL, *mok = NULL; + unsigned long dbsize = 0, dbxsize = 0, moksize = 0; + int rc = 0; + + if (!efi.get_variable) + return false; + + /* Get db, MokListRT, and dbx. They might not exist, so it isn't + * an error if we can't get them. + */ + if (!uefi_check_ignore_db()) { + db = get_cert_list(L"db", &secure_var, &dbsize); + if (!db) { + pr_err("MODSIGN: Couldn't get UEFI db list\n"); + } else { + rc = parse_efi_signature_list("UEFI:db", + db, dbsize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse db signatures: %d\n", + rc); + kfree(db); + } + } + + mok = get_cert_list(L"MokListRT", &mok_var, &moksize); + if (!mok) { + pr_info("Couldn't get UEFI MokListRT\n"); + } else { + rc = parse_efi_signature_list("UEFI:MokListRT", + mok, moksize, get_handler_for_db); + if (rc) + pr_err("Couldn't parse MokListRT signatures: %d\n", rc); + kfree(mok); + } + + dbx = get_cert_list(L"dbx", &secure_var, &dbxsize); + if (!dbx) { + pr_info("Couldn't get UEFI dbx list\n"); + } else { + rc = parse_efi_signature_list("UEFI:dbx", + dbx, dbxsize, + get_handler_for_dbx); + if (rc) + pr_err("Couldn't parse dbx signatures: %d\n", rc); + kfree(dbx); + } + + return rc; +} +late_initcall(load_uefi_certs); diff --git a/security/integrity/platform_certs/platform_keyring.c b/security/integrity/platform_certs/platform_keyring.c new file mode 100644 index 000000000000..bcafd7387729 --- /dev/null +++ b/security/integrity/platform_certs/platform_keyring.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Platform keyring for firmware/platform keys + * + * Copyright IBM Corporation, 2018 + * Author(s): Nayna Jain <nayna@linux.ibm.com> + */ + +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <linux/slab.h> +#include "../integrity.h" + +/** + * add_to_platform_keyring - Add to platform keyring without validation. + * @source: Source of key + * @data: The blob holding the key + * @len: The length of the data blob + * + * Add a key to the platform keyring without checking its trust chain. This + * is available only during kernel initialisation. + */ +void __init add_to_platform_keyring(const char *source, const void *data, + size_t len) +{ + key_perm_t perm; + int rc; + + perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW; + + rc = integrity_load_cert(INTEGRITY_KEYRING_PLATFORM, source, data, len, + perm); + if (rc) + pr_info("Error adding keys to platform keyring %s\n", source); +} + +/* + * Create the trusted keyrings. + */ +static __init int platform_keyring_init(void) +{ + int rc; + + rc = integrity_init_keyring(INTEGRITY_KEYRING_PLATFORM); + if (rc) + return rc; + + pr_notice("Platform Keyring initialized\n"); + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(platform_keyring_init); diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 81fb4c1631e9..cd720c06b78c 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -4333,6 +4333,12 @@ static int smack_key_permission(key_ref_t key_ref, int request = 0; int rc; + /* + * Validate requested permissions + */ + if (perm & ~KEY_NEED_ALL) + return -EINVAL; + keyp = key_ref_to_ptr(key_ref); if (keyp == NULL) return -EINVAL; @@ -4356,10 +4362,10 @@ static int smack_key_permission(key_ref_t key_ref, ad.a.u.key_struct.key = keyp->serial; ad.a.u.key_struct.key_desc = keyp->description; #endif - if (perm & KEY_NEED_READ) - request = MAY_READ; + if (perm & (KEY_NEED_READ | KEY_NEED_SEARCH | KEY_NEED_VIEW)) + request |= MAY_READ; if (perm & (KEY_NEED_WRITE | KEY_NEED_LINK | KEY_NEED_SETATTR)) - request = MAY_WRITE; + request |= MAY_WRITE; rc = smk_access(tkp, keyp->security, request, &ad); rc = smk_bu_note("key access", tkp, keyp->security, request, rc); return rc; diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig index 0d38c006e182..4235907b7858 100644 --- a/sound/pci/hda/Kconfig +++ b/sound/pci/hda/Kconfig @@ -226,68 +226,6 @@ config SND_HDA_POWER_SAVE_DEFAULT The default time-out value in seconds for HD-audio automatic power-save mode. 0 means to disable the power-save mode. -if SND_HDA_INTEL - -# The options below should not be enabled by distributions or -# users. They are selected by Intel/Skylake or SOF drivers when they -# register for a PCI ID which is also handled by the HDAudio legacy -# driver. When this option is selected and the DSP is detected based on -# the PCI class/subclass/prog-if, the probe of the HDAudio legacy -# aborts. This mechanism removes the need for distributions to use -# blacklists. It can be bypassed with module parameters should the -# Intel/Skylake or SOF drivers fail to handle a specific platform. - -config SND_HDA_INTEL_DSP_DETECTION_SKL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - Skylake machines. - -config SND_HDA_INTEL_DSP_DETECTION_APL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - Broxton/ApolloLake machines - -config SND_HDA_INTEL_DSP_DETECTION_KBL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - KabyLake machines - -config SND_HDA_INTEL_DSP_DETECTION_GLK - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - GeminiLake machines - -config SND_HDA_INTEL_DSP_DETECTION_CNL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - CannonLake machines - -config SND_HDA_INTEL_DSP_DETECTION_CFL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - CoffeeLake machines - -config SND_HDA_INTEL_DSP_DETECTION_ICL - bool - help - This option is selected by SOF or SST drivers, not users or distros. - It enables DSP detection based on PCI class information for - IceLake machines - -endif ## SND_HDA_INTEL - endif endmenu diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index e0c3fcbaa028..7185ed574b41 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -37,7 +37,7 @@ #else #define AZX_DCAPS_I915_COMPONENT 0 /* NOP */ #endif -#define AZX_DCAPS_INTEL_SHARED (1 << 14) /* shared with ASoC */ +/* 14 unused */ #define AZX_DCAPS_CTX_WORKAROUND (1 << 15) /* X-Fi workaround */ #define AZX_DCAPS_POSFIX_LPIB (1 << 16) /* Use LPIB as default */ /* 17 unused */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e42cc2230977..e784130ea4e0 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -172,9 +172,6 @@ module_param_array(beep_mode, bool, NULL, 0444); MODULE_PARM_DESC(beep_mode, "Select HDA Beep registration mode " "(0=off, 1=on) (default=1)."); #endif -static int skl_pci_binding; -module_param_named(pci_binding, skl_pci_binding, int, 0444); -MODULE_PARM_DESC(pci_binding, "PCI binding (0=auto, 1=only legacy, 2=only asoc"); #ifdef CONFIG_PM static int param_set_xint(const char *val, const struct kernel_param *kp); @@ -360,7 +357,6 @@ enum { AZX_DCAPS_NO_64BIT |\ AZX_DCAPS_4K_BDLE_BOUNDARY | AZX_DCAPS_SNOOP_OFF) -#define AZX_DCAPS_INTEL_DSP_DETECTION(conf) (IS_ENABLED(CONFIG_SND_HDA_INTEL_DSP_DETECTION_##conf) ? AZX_DCAPS_INTEL_SHARED : 0) /* * vga_switcheroo support */ @@ -2052,28 +2048,6 @@ static int azx_probe(struct pci_dev *pci, bool schedule_probe; int err; - /* check if this driver can be used on SKL+ Intel platforms */ - if (pci_id->driver_data & AZX_DCAPS_INTEL_SHARED) { - switch (skl_pci_binding) { - case SND_SKL_PCI_BIND_AUTO: - if (pci->class != 0x040300) { - dev_info(&pci->dev, "The DSP is enabled on this platform, aborting probe\n"); - return -ENODEV; - } - dev_info(&pci->dev, "No DSP detected, continuing HDaudio legacy probe\n"); - break; - case SND_SKL_PCI_BIND_LEGACY: - dev_info(&pci->dev, "Module parameter forced binding with HDaudio legacy, bypassed detection logic\n"); - break; - case SND_SKL_PCI_BIND_ASOC: - dev_info(&pci->dev, "Module parameter forced binding with SKL+ ASoC driver, aborting probe\n"); - return -ENODEV; - default: - dev_err(&pci->dev, "invalid value for skl_pci_binding module parameter, ignored\n"); - break; - } - } - if (dev >= SNDRV_CARDS) return -ENODEV; if (!enable[dev]) { @@ -2380,48 +2354,34 @@ static const struct pci_device_id azx_ids[] = { .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE }, /* Sunrise Point-LP */ { PCI_DEVICE(0x8086, 0x9d70), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE | - AZX_DCAPS_INTEL_DSP_DETECTION(SKL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE }, /* Kabylake */ { PCI_DEVICE(0x8086, 0xa171), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE }, /* Kabylake-LP */ { PCI_DEVICE(0x8086, 0x9d71), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE | - AZX_DCAPS_INTEL_DSP_DETECTION(KBL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE }, /* Kabylake-H */ { PCI_DEVICE(0x8086, 0xa2f0), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE }, /* Coffelake */ { PCI_DEVICE(0x8086, 0xa348), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE | - AZX_DCAPS_INTEL_DSP_DETECTION(CFL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Cannonlake */ { PCI_DEVICE(0x8086, 0x9dc8), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE | - AZX_DCAPS_INTEL_DSP_DETECTION(CNL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Icelake */ { PCI_DEVICE(0x8086, 0x34c8), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE | - AZX_DCAPS_INTEL_DSP_DETECTION(ICL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE}, /* Broxton-P(Apollolake) */ { PCI_DEVICE(0x8086, 0x5a98), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON | - AZX_DCAPS_INTEL_DSP_DETECTION(APL) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, /* Broxton-T */ { PCI_DEVICE(0x8086, 0x1a98), .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, /* Gemini-Lake */ { PCI_DEVICE(0x8086, 0x3198), - .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON | - AZX_DCAPS_INTEL_DSP_DETECTION(GLK) - }, + .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON }, /* Haswell */ { PCI_DEVICE(0x8086, 0x0a0c), .driver_data = AZX_DRIVER_HDMI | AZX_DCAPS_INTEL_HASWELL }, diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c index 83befd8d43e8..97a176d817a0 100644 --- a/sound/pci/hda/hda_tegra.c +++ b/sound/pci/hda/hda_tegra.c @@ -234,10 +234,12 @@ static int hda_tegra_suspend(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip = card->private_data; struct hda_tegra *hda = container_of(chip, struct hda_tegra, chip); + struct hdac_bus *bus = azx_bus(chip); snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); azx_stop_chip(chip); + synchronize_irq(bus->irq); azx_enter_link_reset(chip); hda_tegra_disable_clocks(hda); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a4f4a9dd488d..aee4cbd29d53 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6501,7 +6501,7 @@ static const struct hda_fixup alc269_fixups[] = { [ALC294_FIXUP_ASUS_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { - { 0x19, 0x01a1113c }, /* use as headset mic, without its own jack detect */ + { 0x19, 0x01a1103c }, /* use as headset mic */ { } }, .chained = true, diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index 2fd1b61e8331..99a62ba409df 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -188,12 +188,6 @@ config SND_SOC_INTEL_SKYLAKE_COMMON select SND_SOC_TOPOLOGY select SND_SOC_INTEL_SST select SND_SOC_HDAC_HDA if SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC - select SND_HDA_INTEL_DSP_DETECTION_SKL if SND_SOC_INTEL_SKL - select SND_HDA_INTEL_DSP_DETECTION_APL if SND_SOC_INTEL_APL - select SND_HDA_INTEL_DSP_DETECTION_KBL if SND_SOC_INTEL_KBL - select SND_HDA_INTEL_DSP_DETECTION_GLK if SND_SOC_INTEL_GLK - select SND_HDA_INTEL_DSP_DETECTION_CNL if SND_SOC_INTEL_CNL - select SND_HDA_INTEL_DSP_DETECTION_CFL if SND_SOC_INTEL_CFL select SND_SOC_ACPI_INTEL_MATCH help If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/ diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index eb54df682d56..1a2bd15c5b6e 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -14,6 +14,7 @@ TARGETS += firmware TARGETS += ftrace TARGETS += futex TARGETS += gpio +TARGETS += ima TARGETS += intel_pstate TARGETS += ipc TARGETS += ir diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 9c79ee017df3..e2b9eee37187 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -510,7 +510,7 @@ static void test_devmap(int task, void *data) fd = bpf_create_map(BPF_MAP_TYPE_DEVMAP, sizeof(key), sizeof(value), 2, 0); if (fd < 0) { - printf("Failed to create arraymap '%s'!\n", strerror(errno)); + printf("Failed to create devmap '%s'!\n", strerror(errno)); exit(1); } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 33f7d38849b8..10d44446e801 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -23,6 +23,7 @@ #include <stdbool.h> #include <sched.h> #include <limits.h> +#include <assert.h> #include <sys/capability.h> @@ -2577,6 +2578,7 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "invalid stack off=-79992 size=8", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", }, { "PTR_TO_STACK store/load - out of bounds high", @@ -3104,6 +3106,8 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -3206,6 +3210,243 @@ static struct bpf_test tests[] = { .retval_unpriv = 2, }, { + "PTR_TO_STACK check high 1", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -1), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK check high 2", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ST_MEM(BPF_B, BPF_REG_1, -1, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, -1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK check high 3", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0), + BPF_ST_MEM(BPF_B, BPF_REG_1, -1, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, -1), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result_unpriv = REJECT, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK check high 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .errstr = "invalid stack off=0 size=1", + .result = REJECT, + }, + { + "PTR_TO_STACK check high 5", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off", + }, + { + "PTR_TO_STACK check high 6", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1), + BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MAX, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MAX), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off", + }, + { + "PTR_TO_STACK check high 7", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, (1 << 29) - 1), + BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MAX, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MAX), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .errstr = "fp pointer offset", + }, + { + "PTR_TO_STACK check low 1", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -512), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK check low 2", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -513), + BPF_ST_MEM(BPF_B, BPF_REG_1, 1, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 1), + BPF_EXIT_INSN(), + }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK check low 3", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -513), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .errstr = "invalid stack off=-513 size=1", + .result = REJECT, + }, + { + "PTR_TO_STACK check low 4", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, INT_MIN), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "math between fp pointer", + }, + { + "PTR_TO_STACK check low 5", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off", + }, + { + "PTR_TO_STACK check low 6", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)), + BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MIN, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MIN), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "invalid stack off", + }, + { + "PTR_TO_STACK check low 7", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -((1 << 29) - 1)), + BPF_ST_MEM(BPF_B, BPF_REG_1, SHRT_MIN, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, SHRT_MIN), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .errstr = "fp pointer offset", + }, + { + "PTR_TO_STACK mixed reg/k, 1", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3), + BPF_MOV64_IMM(BPF_REG_2, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK mixed reg/k, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3), + BPF_MOV64_IMM(BPF_REG_2, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_MOV64_REG(BPF_REG_5, BPF_REG_10), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_5, -6), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 42, + }, + { + "PTR_TO_STACK mixed reg/k, 3", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -3), + BPF_MOV64_IMM(BPF_REG_2, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = -3, + }, + { + "PTR_TO_STACK reg", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_MOV64_IMM(BPF_REG_2, -3), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .result_unpriv = REJECT, + .errstr_unpriv = "invalid stack off=0 size=1", + .result = ACCEPT, + .retval = 42, + }, + { "stack pointer arithmetic", .insns = { BPF_MOV64_IMM(BPF_REG_1, 4), @@ -6610,6 +6851,232 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map access: known scalar += value_ptr from different maps", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 tried to add from different maps", + .retval = 1, + }, + { + "map access: value_ptr -= known scalar from different maps", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_16b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 min value is outside of the array range", + .retval = 1, + }, + { + "map access: known scalar += value_ptr from different maps, but same value properties", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, len)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_48b = { 5 }, + .fixup_map_array_48b = { 8 }, + .result = ACCEPT, + .retval = 1, + }, + { + "map access: value_ptr += known scalar, upper oob arith, test 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 48), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { + "map access: value_ptr += known scalar, upper oob arith, test 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 49), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { + "map access: value_ptr += known scalar, upper oob arith, test 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_IMM(BPF_REG_1, 47), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { + "map access: value_ptr -= known scalar, lower oob arith, test 1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_IMM(BPF_REG_1, 47), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 48), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R0 min value is outside of the array range", + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + }, + { + "map access: value_ptr -= known scalar, lower oob arith, test 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_IMM(BPF_REG_1, 47), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 48), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { + "map access: value_ptr -= known scalar, lower oob arith, test 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_IMM(BPF_REG_1, 47), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 47), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { "map access: known scalar += value_ptr", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -6630,7 +7097,7 @@ static struct bpf_test tests[] = { .retval = 1, }, { - "map access: value_ptr += known scalar", + "map access: value_ptr += known scalar, 1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -6650,7 +7117,113 @@ static struct bpf_test tests[] = { .retval = 1, }, { - "map access: unknown scalar += value_ptr", + "map access: value_ptr += known scalar, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, 49), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "invalid access to map value", + }, + { + "map access: value_ptr += known scalar, 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "invalid access to map value", + }, + { + "map access: value_ptr += known scalar, 4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, -2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 1, + }, + { + "map access: value_ptr += known scalar, 5", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), + BPF_MOV64_IMM(BPF_REG_1, (6 + 1) * sizeof(int)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 0xabcdef12, + }, + { + "map access: value_ptr += known scalar, 6", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_IMM(BPF_REG_1, (3 + 1) * sizeof(int)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 3 * sizeof(int)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 0xabcdef12, + }, + { + "map access: unknown scalar += value_ptr, 1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -6671,7 +7244,76 @@ static struct bpf_test tests[] = { .retval = 1, }, { - "map access: value_ptr += unknown scalar", + "map access: unknown scalar += value_ptr, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 0xabcdef12, + }, + { + "map access: unknown scalar += value_ptr, 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8), + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", + .retval = 0xabcdef12, + }, + { + "map access: unknown scalar += value_ptr, 4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_1, 19), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = REJECT, + .errstr = "R1 max value is outside of the array range", + .errstr_unpriv = "R1 pointer arithmetic of map value goes out of range", + }, + { + "map access: value_ptr += unknown scalar, 1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -6692,6 +7334,54 @@ static struct bpf_test tests[] = { .retval = 1, }, { + "map access: value_ptr += unknown scalar, 2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 31), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 0xabcdef12, + }, + { + "map access: value_ptr += unknown scalar, 3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 8), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 16), + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xf), + BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 1), + BPF_ALU64_IMM(BPF_OR, BPF_REG_3, 1), + BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_3), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_0, 2), + BPF_JMP_IMM(BPF_JA, 0, 0, -3), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 1, + }, + { "map access: value_ptr += value_ptr", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -6770,6 +7460,8 @@ static struct bpf_test tests[] = { }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -6837,6 +7529,8 @@ static struct bpf_test tests[] = { }, .fixup_map_array_48b = { 3 }, .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 1, }, { @@ -8376,6 +9070,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8400,6 +9095,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8426,6 +9122,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8451,6 +9148,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8499,6 +9197,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8570,6 +9269,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8621,6 +9321,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8648,6 +9349,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8674,6 +9376,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8703,6 +9406,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R7 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8733,6 +9437,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 4 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -8761,6 +9466,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, .result_unpriv = REJECT, }, @@ -8813,9 +9519,39 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "R0 min value is negative, either use unsigned index or do a if (index >=0) check.", + .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { + "check subtraction on pointers for unpriv", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_LD_MAP_FD(BPF_REG_ARG1, 0), + BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_ARG2, 0, 9), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_REG(BPF_REG_9, BPF_REG_FP), + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_ARG1, 0), + BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_FP), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_ARG2, 0, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 1, 9 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R9 pointer -= pointer prohibited", + }, + { "bounds check based on zero-extended MOV", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -9146,6 +9882,36 @@ static struct bpf_test tests[] = { .result = REJECT }, { + "bounds check after 32-bit right shift with 64-bit input", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + /* r1 = 2 */ + BPF_MOV64_IMM(BPF_REG_1, 2), + /* r1 = 1<<32 */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 31), + /* r1 = 0 (NOT 2!) */ + BPF_ALU32_IMM(BPF_RSH, BPF_REG_1, 31), + /* r1 = 0xffff'fffe (NOT 0!) */ + BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 2), + /* computes OOB pointer */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_hash_8b = { 3 }, + .errstr = "R0 invalid mem access", + .result = REJECT, + }, + { "bounds check map access with off+size signed 32bit overflow. test1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), @@ -9185,6 +9951,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "pointer offset 1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -9206,6 +9973,7 @@ static struct bpf_test tests[] = { }, .fixup_map_hash_8b = { 3 }, .errstr = "pointer offset -1073741822", + .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .result = REJECT }, { @@ -9377,6 +10145,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN() }, .errstr = "fp pointer offset 1073741822", + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", .result = REJECT }, { @@ -13719,6 +14488,328 @@ static struct bpf_test tests[] = { .insn_processed = 15, }, { + "masking, test out of bounds 1", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 5), + BPF_MOV32_IMM(BPF_REG_2, 5 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 2", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 3", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0xffffffff), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 4", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0xffffffff), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 5", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, -1), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 6", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, -1), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 7", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_MOV32_IMM(BPF_REG_2, 5 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 8", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 1), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 9", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0xffffffff), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 10", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, 0xffffffff), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 11", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test out of bounds 12", + .insns = { + BPF_MOV64_IMM(BPF_REG_1, -1), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test in bounds 1", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 4), + BPF_MOV32_IMM(BPF_REG_2, 5 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 4, + }, + { + "masking, test in bounds 2", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test in bounds 3", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0xfffffffe), + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0xfffffffe, + }, + { + "masking, test in bounds 4", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0xabcde), + BPF_MOV32_IMM(BPF_REG_2, 0xabcdef - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0xabcde, + }, + { + "masking, test in bounds 5", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 0), + BPF_MOV32_IMM(BPF_REG_2, 1 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { + "masking, test in bounds 6", + .insns = { + BPF_MOV32_IMM(BPF_REG_1, 46), + BPF_MOV32_IMM(BPF_REG_2, 47 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_1), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_1, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 46, + }, + { + "masking, test in bounds 7", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, -46), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, -1), + BPF_MOV32_IMM(BPF_REG_2, 47 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_3), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_3), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_3, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 46, + }, + { + "masking, test in bounds 8", + .insns = { + BPF_MOV64_IMM(BPF_REG_3, -47), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, -1), + BPF_MOV32_IMM(BPF_REG_2, 47 - 1), + BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_3), + BPF_ALU64_REG(BPF_OR, BPF_REG_2, BPF_REG_3), + BPF_ALU64_IMM(BPF_NEG, BPF_REG_2, 0), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_2, 63), + BPF_ALU64_REG(BPF_AND, BPF_REG_3, BPF_REG_2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_3), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .retval = 0, + }, + { "reference tracking in call: free reference in subprog and outside", .insns = { BPF_SK_LOOKUP, @@ -14413,6 +15504,16 @@ static int create_map(uint32_t type, uint32_t size_key, return fd; } +static void update_map(int fd, int index) +{ + struct test_val value = { + .index = (6 + 1) * sizeof(int), + .foo[6] = 0xabcdef12, + }; + + assert(!bpf_map_update_elem(fd, &index, &value, 0)); +} + static int create_prog_dummy1(enum bpf_prog_type prog_type) { struct bpf_insn prog[] = { @@ -14564,6 +15665,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, if (*fixup_map_array_48b) { map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), sizeof(struct test_val), 1); + update_map(map_fds[3], 0); do { prog[*fixup_map_array_48b].imm = map_fds[3]; fixup_map_array_48b++; diff --git a/tools/testing/selftests/ima/Makefile b/tools/testing/selftests/ima/Makefile new file mode 100644 index 000000000000..0b3adf5444b6 --- /dev/null +++ b/tools/testing/selftests/ima/Makefile @@ -0,0 +1,11 @@ +# Makefile for kexec_load + +uname_M := $(shell uname -m 2>/dev/null || echo not) +ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) + +ifeq ($(ARCH),x86) +TEST_PROGS := test_kexec_load.sh + +include ../lib.mk + +endif diff --git a/tools/testing/selftests/ima/config b/tools/testing/selftests/ima/config new file mode 100644 index 000000000000..6bc86d4d9bb4 --- /dev/null +++ b/tools/testing/selftests/ima/config @@ -0,0 +1,4 @@ +CONFIG_IMA_APPRAISE +CONFIG_IMA_ARCH_POLICY +CONFIG_SECURITYFS +CONFIG_KEXEC_VERIFY_SIG diff --git a/tools/testing/selftests/ima/test_kexec_load.sh b/tools/testing/selftests/ima/test_kexec_load.sh new file mode 100755 index 000000000000..1c10093fb526 --- /dev/null +++ b/tools/testing/selftests/ima/test_kexec_load.sh @@ -0,0 +1,54 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# Loading a kernel image via the kexec_load syscall should fail +# when the kerne is CONFIG_KEXEC_VERIFY_SIG enabled and the system +# is booted in secureboot mode. + +TEST="$0" +EFIVARFS="/sys/firmware/efi/efivars" +rc=0 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +# kexec requires root privileges +if [ $UID != 0 ]; then + echo "$TEST: must be run as root" >&2 + exit $ksft_skip +fi + +# Make sure that efivars is mounted in the normal location +if ! grep -q "^\S\+ $EFIVARFS efivarfs" /proc/mounts; then + echo "$TEST: efivars is not mounted on $EFIVARFS" >&2 + exit $ksft_skip +fi + +# Get secureboot mode +file="$EFIVARFS/SecureBoot-*" +if [ ! -e $file ]; then + echo "$TEST: unknown secureboot mode" >&2 + exit $ksft_skip +fi +secureboot=`hexdump $file | awk '{print substr($4,length($4),1)}'` + +# kexec_load should fail in secure boot mode +KERNEL_IMAGE="/boot/vmlinuz-`uname -r`" +kexec -l $KERNEL_IMAGE &>> /dev/null +if [ $? == 0 ]; then + kexec -u + if [ "$secureboot" == "1" ]; then + echo "$TEST: kexec_load succeeded [FAIL]" + rc=1 + else + echo "$TEST: kexec_load succeeded [PASS]" + fi +else + if [ "$secureboot" == "1" ]; then + echo "$TEST: kexec_load failed [PASS]" + else + echo "$TEST: kexec_load failed [FAIL]" + rc=1 + fi +fi + +exit $rc diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index c9a2abf8be1b..067cb4607d6c 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -5,6 +5,7 @@ * Test code for seccomp bpf. */ +#define _GNU_SOURCE #include <sys/types.h> /* @@ -40,10 +41,12 @@ #include <sys/fcntl.h> #include <sys/mman.h> #include <sys/times.h> +#include <sys/socket.h> +#include <sys/ioctl.h> -#define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> +#include <poll.h> #include "../kselftest_harness.h" @@ -133,6 +136,10 @@ struct seccomp_data { #define SECCOMP_GET_ACTION_AVAIL 2 #endif +#ifndef SECCOMP_GET_NOTIF_SIZES +#define SECCOMP_GET_NOTIF_SIZES 3 +#endif + #ifndef SECCOMP_FILTER_FLAG_TSYNC #define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0) #endif @@ -154,6 +161,44 @@ struct seccomp_metadata { }; #endif +#ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER +#define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) + +#define SECCOMP_RET_USER_NOTIF 0x7fc00000U + +#define SECCOMP_IOC_MAGIC '!' +#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr) +#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOW(nr, type) _IOW(SECCOMP_IOC_MAGIC, nr, type) +#define SECCOMP_IOWR(nr, type) _IOWR(SECCOMP_IOC_MAGIC, nr, type) + +/* Flags for seccomp notification fd ioctl. */ +#define SECCOMP_IOCTL_NOTIF_RECV SECCOMP_IOWR(0, struct seccomp_notif) +#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \ + struct seccomp_notif_resp) +#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOR(2, __u64) + +struct seccomp_notif { + __u64 id; + __u32 pid; + __u32 flags; + struct seccomp_data data; +}; + +struct seccomp_notif_resp { + __u64 id; + __s64 val; + __s32 error; + __u32 flags; +}; + +struct seccomp_notif_sizes { + __u16 seccomp_notif; + __u16 seccomp_notif_resp; + __u16 seccomp_data; +}; +#endif + #ifndef seccomp int seccomp(unsigned int op, unsigned int flags, void *args) { @@ -2077,7 +2122,8 @@ TEST(detect_seccomp_filter_flags) { unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC, SECCOMP_FILTER_FLAG_LOG, - SECCOMP_FILTER_FLAG_SPEC_ALLOW }; + SECCOMP_FILTER_FLAG_SPEC_ALLOW, + SECCOMP_FILTER_FLAG_NEW_LISTENER }; unsigned int flag, all_flags; int i; long ret; @@ -2938,6 +2984,403 @@ skip: ASSERT_EQ(0, kill(pid, SIGKILL)); } +static int user_trap_syscall(int nr, unsigned int flags) +{ + 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, 0, 1), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_USER_NOTIF), + BPF_STMT(BPF_RET+BPF_K, SECCOMP_RET_ALLOW), + }; + + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + return seccomp(SECCOMP_SET_MODE_FILTER, flags, &prog); +} + +#define USER_NOTIF_MAGIC 116983961184613L +TEST(user_notification_basic) +{ + pid_t pid; + long ret; + int status, listener; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + struct pollfd pollfd; + + 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, + }; + + pid = fork(); + ASSERT_GE(pid, 0); + + /* Check that we get -ENOSYS with no listener attached */ + if (pid == 0) { + if (user_trap_syscall(__NR_getpid, 0) < 0) + exit(1); + ret = syscall(__NR_getpid); + exit(ret >= 0 || errno != ENOSYS); + } + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + /* Add some no-op filters so for grins. */ + EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); + EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); + EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); + EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0); + + /* Check that the basic notification machinery works */ + listener = user_trap_syscall(__NR_getpid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + EXPECT_GE(listener, 0); + + /* Installing a second listener in the chain should EBUSY */ + EXPECT_EQ(user_trap_syscall(__NR_getpid, + SECCOMP_FILTER_FLAG_NEW_LISTENER), + -1); + EXPECT_EQ(errno, EBUSY); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = syscall(__NR_getpid); + exit(ret != USER_NOTIF_MAGIC); + } + + pollfd.fd = listener; + pollfd.events = POLLIN | POLLOUT; + + EXPECT_GT(poll(&pollfd, 1, -1), 0); + EXPECT_EQ(pollfd.revents, POLLIN); + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + pollfd.fd = listener; + pollfd.events = POLLIN | POLLOUT; + + EXPECT_GT(poll(&pollfd, 1, -1), 0); + EXPECT_EQ(pollfd.revents, POLLOUT); + + EXPECT_EQ(req.data.nr, __NR_getpid); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + /* check that we make sure flags == 0 */ + resp.flags = 1; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1); + EXPECT_EQ(errno, EINVAL); + + resp.flags = 0; + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(user_notification_kill_in_middle) +{ + pid_t pid; + long ret; + int listener; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + + listener = user_trap_syscall(__NR_getpid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + EXPECT_GE(listener, 0); + + /* + * Check that nothing bad happens when we kill the task in the middle + * of a syscall. + */ + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ret = syscall(__NR_getpid); + exit(ret != USER_NOTIF_MAGIC); + } + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req.id), 0); + + EXPECT_EQ(kill(pid, SIGKILL), 0); + EXPECT_EQ(waitpid(pid, NULL, 0), pid); + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ID_VALID, &req.id), -1); + + resp.id = req.id; + ret = ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp); + EXPECT_EQ(ret, -1); + EXPECT_EQ(errno, ENOENT); +} + +static int handled = -1; + +static void signal_handler(int signal) +{ + if (write(handled, "c", 1) != 1) + perror("write from signal"); +} + +TEST(user_notification_signal) +{ + pid_t pid; + long ret; + int status, listener, sk_pair[2]; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + char c; + + ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0); + + listener = user_trap_syscall(__NR_gettid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + EXPECT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + close(sk_pair[0]); + handled = sk_pair[1]; + if (signal(SIGUSR1, signal_handler) == SIG_ERR) { + perror("signal"); + exit(1); + } + /* + * ERESTARTSYS behavior is a bit hard to test, because we need + * to rely on a signal that has not yet been handled. Let's at + * least check that the error code gets propagated through, and + * hope that it doesn't break when there is actually a signal :) + */ + ret = syscall(__NR_gettid); + exit(!(ret == -1 && errno == 512)); + } + + close(sk_pair[1]); + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + EXPECT_EQ(kill(pid, SIGUSR1), 0); + + /* + * Make sure the signal really is delivered, which means we're not + * stuck in the user notification code any more and the notification + * should be dead. + */ + EXPECT_EQ(read(sk_pair[0], &c, 1), 1); + + resp.id = req.id; + resp.error = -EPERM; + resp.val = 0; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), -1); + EXPECT_EQ(errno, ENOENT); + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + + resp.id = req.id; + resp.error = -512; /* -ERESTARTSYS */ + resp.val = 0; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(user_notification_closed_listener) +{ + pid_t pid; + long ret; + int status, listener; + + listener = user_trap_syscall(__NR_getpid, + SECCOMP_FILTER_FLAG_NEW_LISTENER); + EXPECT_GE(listener, 0); + + /* + * Check that we get an ENOSYS when the listener is closed. + */ + pid = fork(); + ASSERT_GE(pid, 0); + if (pid == 0) { + close(listener); + ret = syscall(__NR_getpid); + exit(ret != -1 && errno != ENOSYS); + } + + close(listener); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +/* + * Check that a pid in a child namespace still shows up as valid in ours. + */ +TEST(user_notification_child_pid_ns) +{ + pid_t pid; + int status, listener; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + + ASSERT_EQ(unshare(CLONE_NEWPID), 0); + + listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC); + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + EXPECT_EQ(req.pid, pid); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + close(listener); +} + +/* + * Check that a pid in a sibling (i.e. unrelated) namespace shows up as 0, i.e. + * invalid. + */ +TEST(user_notification_sibling_pid_ns) +{ + pid_t pid, pid2; + int status, listener; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + + listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) { + ASSERT_EQ(unshare(CLONE_NEWPID), 0); + + pid2 = fork(); + ASSERT_GE(pid2, 0); + + if (pid2 == 0) + exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC); + + EXPECT_EQ(waitpid(pid2, &status, 0), pid2); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + exit(WEXITSTATUS(status)); + } + + /* Create the sibling ns, and sibling in it. */ + EXPECT_EQ(unshare(CLONE_NEWPID), 0); + EXPECT_EQ(errno, 0); + + pid2 = fork(); + EXPECT_GE(pid2, 0); + + if (pid2 == 0) { + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + /* + * The pid should be 0, i.e. the task is in some namespace that + * we can't "see". + */ + ASSERT_EQ(req.pid, 0); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + exit(0); + } + + close(listener); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); + + EXPECT_EQ(waitpid(pid2, &status, 0), pid2); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(user_notification_fault_recv) +{ + pid_t pid; + int status, listener; + struct seccomp_notif req = {}; + struct seccomp_notif_resp resp = {}; + + listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER); + ASSERT_GE(listener, 0); + + pid = fork(); + ASSERT_GE(pid, 0); + + if (pid == 0) + exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC); + + /* Do a bad recv() */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, NULL), -1); + EXPECT_EQ(errno, EFAULT); + + /* We should still be able to receive this notification, though. */ + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0); + EXPECT_EQ(req.pid, pid); + + resp.id = req.id; + resp.error = 0; + resp.val = USER_NOTIF_MAGIC; + + EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0); + + EXPECT_EQ(waitpid(pid, &status, 0), pid); + EXPECT_EQ(true, WIFEXITED(status)); + EXPECT_EQ(0, WEXITSTATUS(status)); +} + +TEST(seccomp_get_notif_sizes) +{ + struct seccomp_notif_sizes sizes; + + EXPECT_EQ(seccomp(SECCOMP_GET_NOTIF_SIZES, 0, &sizes), 0); + EXPECT_EQ(sizes.seccomp_notif, sizeof(struct seccomp_notif)); + EXPECT_EQ(sizes.seccomp_notif_resp, sizeof(struct seccomp_notif_resp)); +} + /* * TODO: * - add microbenchmarks |