DCMD_INIT is introduced to indicate the initial DCMD status, which was
earlier set to MFI status. DCMD_BUSY indicates the resource is busy or
locked.
Link: https://lore.kernel.org/r/1579000882-20246-8-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
After issuing a adapter reset, driver blindly used to set adprecovery flag
to OPERATIONAL state. Add a check to see if the FW is operational before
setting the flag and marking reset adapter successful.
Link: https://lore.kernel.org/r/1579000882-20246-7-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
At the time of firmware initialization, if JBOD map or RAID map is not
available, driver can function without these features in a limited
functionality mode.
Link: https://lore.kernel.org/r/1579000882-20246-6-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Ideally, optimal queue depth will be provided by firmware. The driver
defines will be used as a fallback mechanism in case the FW assisted QD is
not supported. The driver defined values provide optimal queue depth for
most of the drives and the workloads, as is learned from the firmware
assisted QD results.
Link: https://lore.kernel.org/r/1579000882-20246-4-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Chandrakanth Patil <chandrakanth.patil@broadcom.com>
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Disable WRITE_SAME (no_write_same) for Virtual Disks only. For System PDs
and EPDs (Enhanced PDs), WRITE_SAME need not be disabled by default.
Link: https://lore.kernel.org/r/1579000882-20246-3-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
After device resume we expect the firmware to be in READY state.
Transition to READY might fail due to unhandled exceptions, such as an
internal error or a hardware failure. Retry initiating chip reset and wait
for the controller to come to ready state.
Link: https://lore.kernel.org/r/1579000882-20246-2-git-send-email-anand.lodnoor@broadcom.com
Signed-off-by: Chandrakanth Patil <chandrakanth.patil@broadcom.com>
Signed-off-by: Anand Lodnoor <anand.lodnoor@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Do firmware download with 64bit LOAD_RAM command, if driver is using
64bit addressing.
Link: https://lore.kernel.org/r/20200114160936.1517-1-tbogendoerfer@suse.de
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Tom Hatskevich reported that we look up "iocp" then, in the called
functions we do a second copy_from_user() and look it up again.
The problem that could cause is:
drivers/message/fusion/mptctl.c
674 /* All of these commands require an interrupt or
675 * are unknown/illegal.
676 */
677 if ((ret = mptctl_syscall_down(iocp, nonblock)) != 0)
^^^^
We take this lock.
678 return ret;
679
680 if (cmd == MPTFWDOWNLOAD)
681 ret = mptctl_fw_download(arg);
^^^
Then the user memory changes and we look up "iocp" again but a different
one so now we are holding the incorrect lock and have a race condition.
682 else if (cmd == MPTCOMMAND)
683 ret = mptctl_mpt_command(arg);
The security impact of this bug is not as bad as it could have been
because these operations are all privileged and root already has
enormous destructive power. But it's still worth fixing.
This patch passes the "iocp" pointer to the functions to avoid the
second lookup. That deletes 100 lines of code from the driver so
it's a nice clean up as well.
Link: https://lore.kernel.org/r/20200114123414.GA7957@kadam
Reported-by: Tom Hatskevich <tom2001tom.23@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Commit 0ed8810276 ("scsi: storvsc: setup 1:1 mapping between hardware
queue and CPU queue") introduced a regression for disks attached to
IDE. For these disks the host VSP only offers one VMBUS channel. Setting
multiple queues can overload the VMBUS channel and result in performance
drop for high queue depth workload on system with large number of CPUs.
Fix it by leaving the number of hardware queues to 1 (default value) for
IDE disks.
Fixes: 0ed8810276 ("scsi: storvsc: setup 1:1 mapping between hardware queue and CPU queue")
Link: https://lore.kernel.org/r/1578960516-108228-1-git-send-email-longli@linuxonhyperv.com
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
gcc -O3 warns that some local variables are not properly initialized:
drivers/scsi/fnic/vnic_dev.c: In function 'fnic_dev_hang_notify':
drivers/scsi/fnic/vnic_dev.c:511:16: error: 'a0' is used uninitialized in this function [-Werror=uninitialized]
vdev->args[0] = *a0;
~~~~~~~~~~~~~~^~~~~
drivers/scsi/fnic/vnic_dev.c:691:6: note: 'a0' was declared here
u64 a0, a1;
^~
drivers/scsi/fnic/vnic_dev.c:512:16: error: 'a1' is used uninitialized in this function [-Werror=uninitialized]
vdev->args[1] = *a1;
~~~~~~~~~~~~~~^~~~~
drivers/scsi/fnic/vnic_dev.c:691:10: note: 'a1' was declared here
u64 a0, a1;
^~
drivers/scsi/fnic/vnic_dev.c: In function 'fnic_dev_mac_addr':
drivers/scsi/fnic/vnic_dev.c:512:16: error: 'a1' is used uninitialized in this function [-Werror=uninitialized]
vdev->args[1] = *a1;
~~~~~~~~~~~~~~^~~~~
drivers/scsi/fnic/vnic_dev.c:698:10: note: 'a1' was declared here
u64 a0, a1;
^~
Apparently the code relies on the local variables occupying adjacent memory
locations in the same order, but this is of course not guaranteed.
Use an array of two u64 variables where needed to make it work correctly.
I suspect there is also an endianness bug here, but have not digged in deep
enough to be sure.
Fixes: 5df6d737dd ("[SCSI] fnic: Add new Cisco PCI-Express FCoE HBA")
Fixes: mmtom ("init/Kconfig: enable -O3 for all arches")
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20200107201602.4096790-1-arnd@arndb.de
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
If the transport cannot be registered, the session/connection creation
needs to be failed early to let the initiator know. Otherwise, the system
will have an outstanding connection that cannot be used nor removed by
open-iscsi. The result is similar to the error below, triggered by
injecting a failure in the transport's registration path.
openiscsi reports success:
root@debian-vm:~# iscsiadm -m node -T iqn:lun1 -p 127.0.0.1 -l
Logging in to [iface: default, target: iqn:lun1, portal: 127.0.0.1,3260]
Login to [iface: default, target: iqn:lun1, portal:127.0.0.1,3260] successful.
But cannot remove the session afterwards, since the kernel is in an
inconsistent state.
root@debian-vm:~# iscsiadm -m node -T iqn:lun1 -p 127.0.0.1 -u
iscsiadm: No matching sessions found
Link: https://lore.kernel.org/r/20200106185817.640331-4-krisman@collabora.com
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
The transport registration may fail. Make sure the errors are propagated
to the callers.
Link: https://lore.kernel.org/r/20200106185817.640331-3-krisman@collabora.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
attribute_container_device_trigger invokes callbacks that may fail for one
or more classdevs, for instance, the transport_add_class_device callback,
called during transport creation, does memory allocation. This
information, though, is not propagated to upper layers, and any driver
using the attribute_container_device_trigger API will not know whether any,
some, or all callbacks succeeded.
This patch implements a safe version of this dispatcher, to either succeed
all the callbacks or revert to the original state.
Link: https://lore.kernel.org/r/20200106185817.640331-2-krisman@collabora.com
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Pass UFS device information to vendor-specific variant callback
"apply_dev_quirks" because some platform vendors need to know such
information to apply special handling or quirks in specific devices.
At the same time, modify existing vendor implementations according to the
new interface for those vendor drivers which will be built-in or built as a
module alone with UFS core driver.
[mkp: clarified commit desc]
Cc: Alim Akhtar <alim.akhtar@samsung.com>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Cc: Avri Altman <avri.altman@wdc.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Bean Huo <beanhuo@micron.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/1578726707-6596-2-git-send-email-stanley.chu@mediatek.com
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Currently the incorrect %X print format specifier is being used for several
unsigned longs. Fix these by using %lX instead. Also join up some literal
strings that are split.
Link: https://lore.kernel.org/r/20200108193800.96706-1-colin.king@canonical.com
Addresses-Coverity: ("Invalid type in argument to printf format specifier")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Khalid Aziz <khalid@gonehiking.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Remove "errors" word in output string by ufshcd_print_err_hist() since not
all printed targets are "errors". Sometimes they are just "events".
In addition, all events which can be treated as "errors" already have "err"
or "fail" words in their names.
Cc: Alim Akhtar <alim.akhtar@samsung.com>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Cc: Avri Altman <avri.altman@wdc.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Bean Huo <beanhuo@micron.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/1578147968-30938-4-git-send-email-stanley.chu@mediatek.com
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Device reset history shall be also added for vendor's device reset variant
operation implementation.
Cc: Alim Akhtar <alim.akhtar@samsung.com>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Cc: Avri Altman <avri.altman@wdc.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Bean Huo <beanhuo@micron.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/1578147968-30938-3-git-send-email-stanley.chu@mediatek.com
Reviewed-by: Bean Huo <beanhuo@micron.com>
Reviewed-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Currently checking if an error history element is empty or not is by its
"value". In most cases, value is error code.
However this checking is not correct because some errors or events do not
specify any values in error history so values remain as 0, and this will
lead to incorrect empty checking.
Fix it by checking "timestamp" instead of "value" because timestamp will be
always assigned for all history elements
Cc: Alim Akhtar <alim.akhtar@samsung.com>
Cc: Asutosh Das <asutoshd@codeaurora.org>
Cc: Avri Altman <avri.altman@wdc.com>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Bean Huo <beanhuo@micron.com>
Cc: Can Guo <cang@codeaurora.org>
Cc: Matthias Brugger <matthias.bgg@gmail.com>
Link: https://lore.kernel.org/r/1578147968-30938-2-git-send-email-stanley.chu@mediatek.com
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Add ability to specify a list of test name substrings for selecting which
tests to run. So now -t is accepting a comma-separated list of strings,
similarly to how -n accepts a comma-separated list of test numbers.
Additionally, add ability to blacklist tests by name. Blacklist takes
precedence over whitelist. Blacklisting is important for cases where it's
known that some tests can't pass (e.g., due to perf hardware events that are
not available within VM). This is going to be used for libbpf testing in
Travis CI in its Github repo.
Example runs with just whitelist and whitelist + blacklist:
$ sudo ./test_progs -tattach,core/existence
#1 attach_probe:OK
#6 cgroup_attach_autodetach:OK
#7 cgroup_attach_multi:OK
#8 cgroup_attach_override:OK
#9 core_extern:OK
#10/44 existence:OK
#10/45 existence___minimal:OK
#10/46 existence__err_int_sz:OK
#10/47 existence__err_int_type:OK
#10/48 existence__err_int_kind:OK
#10/49 existence__err_arr_kind:OK
#10/50 existence__err_arr_value_type:OK
#10/51 existence__err_struct_type:OK
#10 core_reloc:OK
#19 flow_dissector_reattach:OK
#60 tp_attach_query:OK
Summary: 8/8 PASSED, 0 SKIPPED, 0 FAILED
$ sudo ./test_progs -tattach,core/existence -bcgroup,flow/arr
#1 attach_probe:OK
#9 core_extern:OK
#10/44 existence:OK
#10/45 existence___minimal:OK
#10/46 existence__err_int_sz:OK
#10/47 existence__err_int_type:OK
#10/48 existence__err_int_kind:OK
#10/51 existence__err_struct_type:OK
#10 core_reloc:OK
#60 tp_attach_query:OK
Summary: 4/6 PASSED, 0 SKIPPED, 0 FAILED
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Cc: Julia Kartseva <hex@fb.com>
Link: https://lore.kernel.org/bpf/20200116005549.3644118-1-andriin@fb.com
The code in secondary_park is currently placed in the .init section. The
kernel reclaims and clears this code when it finishes booting. That
causes the cores parked in it to go to somewhere unpredictable, so we
move this function out of init to make sure the cores stay looping there.
The instruction bgeu a0, t0, .Lsecondary_park may have "a relocation
truncated to fit" issue during linking time. It is because that sections
are too far to jump. Let's use tail to jump to the .Lsecondary_park.
Signed-off-by: Greentime Hu <greentime.hu@sifive.com>
Reviewed-by: Anup Patel <anup.patel@sifive.com>
Cc: Andreas Schwab <schwab@suse.de>
Cc: stable@vger.kernel.org
Fixes: 76d2a0493a ("RISC-V: Init and Halt Code")
Signed-off-by: Paul Walmsley <paul.walmsley@sifive.com>
This enables bcm2711's PCIe bus, which is hardwired to a VIA
Technologies XHCI USB 3.0 controller.
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
With the introduction of the Raspberry Pi 4 we were forced to explicitly
configure CMA's location, since arm64 defaults it into the ZONE_DMA32
memory area, which is not good enough to perform DMA operations on that
device. To bypass this limitation a dedicated CMA DT node was created,
explicitly indicating the acceptable memory range and size.
That said, compatibility between boards is a must on the Raspberry Pi
ecosystem so this creates a common CMA DT node so as for DT overlays to
be able to update CMA's properties regardless of the board being used.
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
Reviewed-by: Phil Elwell <phil@raspberrypi.org>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Martin Lau says:
====================
When a map is storing a kernel's struct, its
map_info->btf_vmlinux_value_type_id is set. The first map type
supporting it is BPF_MAP_TYPE_STRUCT_OPS.
This series adds support to dump this kind of map with BTF.
The first two patches are bug fixes which are only applicable to
bpf-next.
Please see individual patches for details.
v3:
- Remove unnecessary #include "libbpf_internal.h" from patch 5
v2:
- Expose bpf_find_kernel_btf() as a LIBBPF_API in patch 3 (Andrii)
- Cache btf_vmlinux in bpftool/map.c (Andrii)
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This patch makes bpftool support dumping a map's value properly
when the map's value type is a type of the running kernel's btf.
(i.e. map_info.btf_vmlinux_value_type_id is set instead of
map_info.btf_value_type_id). The first usecase is for the
BPF_MAP_TYPE_STRUCT_OPS.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200115230044.1103008-1-kafai@fb.com
This patch adds BPF_MAP_TYPE_STRUCT_OPS to "struct_ops" name mapping
so that "bpftool map show" can print the "struct_ops" map type
properly.
[root@arch-fb-vm1 bpf]# ~/devshare/fb-kernel/linux/tools/bpf/bpftool/bpftool map show id 8
8: struct_ops name dctcp flags 0x0
key 4B value 256B max_entries 1 memlock 4096B
btf_id 7
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200115230037.1102674-1-kafai@fb.com
This patch exposes bpf_find_kernel_btf() as a LIBBPF_API.
It will be used in 'bpftool map dump' in a following patch
to dump a map with btf_vmlinux_value_type_id set.
bpf_find_kernel_btf() is renamed to libbpf_find_kernel_btf()
and moved to btf.c. As <linux/kernel.h> is included,
some of the max/min type casting needs to be fixed.
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200115230031.1102305-1-kafai@fb.com
The btf availability check is only done for plain text output.
It causes the whole BTF output went missing when json_output
is used.
This patch simplifies the logic a little by avoiding passing "int btf" to
map_dump().
For plain text output, the btf_wtr is only created when the map has
BTF (i.e. info->btf_id != 0). The nullness of "json_writer_t *wtr"
in map_dump() alone can decide if dumping BTF output is needed.
As long as wtr is not NULL, map_dump() will print out the BTF-described
data whenever a map has BTF available (i.e. info->btf_id != 0)
regardless of json or plain-text output.
In do_dump(), the "int btf" is also renamed to "int do_plain_btf".
Fixes: 99f9863a0c ("bpftool: Match maps by name")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: Paul Chaignon <paul.chaignon@orange.com>
Link: https://lore.kernel.org/bpf/20200115230025.1101828-1-kafai@fb.com
When testing a map has btf or not, maps_have_btf() tests it by actually
getting a btf_fd from sys_bpf(BPF_BTF_GET_FD_BY_ID). However, it
forgot to btf__free() it.
In maps_have_btf() stage, there is no need to test it by really
calling sys_bpf(BPF_BTF_GET_FD_BY_ID). Testing non zero
info.btf_id is good enough.
Also, the err_close case is unnecessary, and also causes double
close() because the calling func do_dump() will close() all fds again.
Fixes: 99f9863a0c ("bpftool: Match maps by name")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Cc: Paul Chaignon <paul.chaignon@orange.com>
Link: https://lore.kernel.org/bpf/20200115230019.1101352-1-kafai@fb.com
read_current_link_settings_on_detect() on eDP 1.4+ may use the
edp_supported_link_rates table which is set up by
detect_edp_sink_caps(), so that function needs to be called first.
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Martin Leung <martin.leung@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Update mmSDMA0_UTCL1_WATERMK golden setting for renoir.
Signed-off-by: Aaron Liu <aaron.liu@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
QEMU running in a stubdom needs to be able to set INTX_DISABLE, and the
MSI(-X) enable flags in the PCI config space. This adds an attribute
'allow_interrupt_control' which when set for a PCI device allows writes
to this flag(s). The toolstack will need to set this for stubdoms.
When enabled, guest (stubdomain) will be allowed to set relevant enable
flags, but only one at a time - i.e. it refuses to enable more than one
of INTx, MSI, MSI-X at a time.
This functionality is needed only for config space access done by device
model (stubdomain) serving a HVM with the actual PCI device. It is not
necessary and unsafe to enable direct access to those bits for PV domain
with the device attached. For PV domains, there are separate protocol
messages (XEN_PCI_OP_{enable,disable}_{msi,msix}) for this purpose.
Those ops in addition to setting enable bits, also configure MSI(-X) in
dom0 kernel - which is undesirable for PCI passthrough to HVM guests.
This should not introduce any new security issues since a malicious
guest (or stubdom) can already generate MSIs through other ways, see
[1] page 8. Additionally, when qemu runs in dom0, it already have direct
access to those bits.
This is the second iteration of this feature. First was proposed as a
direct Xen interface through a new hypercall, but ultimately it was
rejected by the maintainer, because of mixing pciback and hypercalls for
PCI config space access isn't a good design. Full discussion at [2].
[1]: https://invisiblethingslab.com/resources/2011/Software%20Attacks%20on%20Intel%20VT-d.pdf
[2]: https://xen.markmail.org/thread/smpgpws4umdzizze
[part of the commit message and sysfs handling]
Signed-off-by: Simon Gaiser <simon@invisiblethingslab.com>
[the rest]
Signed-off-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
[boris: A few small changes suggested by Roger, some formatting changes]
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
John Fastabend says:
====================
To date our usage of sockmap/tls has been fairly simple, the BPF programs
did only well-defined pop, push, pull and apply/cork operations.
Now that we started to push more complex programs into sockmap we uncovered
a series of issues addressed here. Further OpenSSL3.0 version should be
released soon with kTLS support so its important to get any remaining
issues on BPF and kTLS support resolved.
Additionally, I have a patch under development to allow sockmap to be
enabled/disabled at runtime for Cilium endpoints. This allows us to stress
the map insert/delete with kTLS more than previously where Cilium only
added the socket to the map when it entered ESTABLISHED state and never
touched it from the control path side again relying on the sockets own
close() hook to remove it.
To test I have a set of test cases in test_sockmap.c that expose these
issues. Once we get fixes here merged and in bpf-next I'll submit the
tests to bpf-next tree to ensure we don't regress again. Also I've run
these patches in the Cilium CI with OpenSSL (master branch) this will
run tools such as netperf, ab, wrk2, curl, etc. to get a broad set of
testing.
I'm aware of two more issues that we are working to resolve in another
couple (probably two) patches. First we see an auth tag corruption in
kTLS when sending small 1byte chunks under stress. I've not pinned this
down yet. But, guessing because its under 1B stress tests it must be
some error path being triggered. And second we need to ensure BPF RX
programs are not skipped when kTLS ULP is loaded. This breaks some of the
sockmap selftests when running with kTLS. I'll send a follow up for this.
v2: I dropped a patch that added !0 size check in tls_push_record
this originated from a panic I caught awhile ago with a trace
in the crypto stack. But I can not reproduce it anymore so will
dig into that and send another patch later if needed. Anyways
after a bit of thought it would be nicer if tls/crypto/bpf didn't
require special case handling for the !0 size.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
When user returns SK_DROP we need to reset the number of copied bytes
to indicate to the user the bytes were dropped and not sent. If we
don't reset the copied arg sendmsg will return as if those bytes were
copied giving the user a positive return value.
This works as expected today except in the case where the user also
pops bytes. In the pop case the sg.size is reduced but we don't correctly
account for this when copied bytes is reset. The popped bytes are not
accounted for and we return a small positive value potentially confusing
the user.
The reason this happens is due to a typo where we do the wrong comparison
when accounting for pop bytes. In this fix notice the if/else is not
needed and that we have a similar problem if we push data except its not
visible to the user because if delta is larger the sg.size we return a
negative value so it appears as an error regardless.
Fixes: 7246d8ed4d ("bpf: helper to pop data from messages")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-9-john.fastabend@gmail.com
Its possible through a set of push, pop, apply helper calls to construct
a skmsg, which is just a ring of scatterlist elements, with the start
value larger than the end value. For example,
end start
|_0_|_1_| ... |_n_|_n+1_|
Where end points at 1 and start points and n so that valid elements is
the set {n, n+1, 0, 1}.
Currently, because we don't build the correct chain only {n, n+1} will
be sent. This adds a check and sg_chain call to correctly submit the
above to the crypto and tls send path.
Fixes: d3b18ad31f ("tls: add bpf support to sk_msg handling")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-8-john.fastabend@gmail.com
It is possible to build a plaintext buffer using push helper that is larger
than the allocated encrypt buffer. When this record is pushed to crypto
layers this can result in a NULL pointer dereference because the crypto
API expects the encrypt buffer is large enough to fit the plaintext
buffer. Kernel splat below.
To resolve catch the cases this can happen and split the buffer into two
records to send individually. Unfortunately, there is still one case to
handle where the split creates a zero sized buffer. In this case we merge
the buffers and unmark the split. This happens when apply is zero and user
pushed data beyond encrypt buffer. This fixes the original case as well
because the split allocated an encrypt buffer larger than the plaintext
buffer and the merge simply moves the pointers around so we now have
a reference to the new (larger) encrypt buffer.
Perhaps its not ideal but it seems the best solution for a fixes branch
and avoids handling these two cases, (a) apply that needs split and (b)
non apply case. The are edge cases anyways so optimizing them seems not
necessary unless someone wants later in next branches.
[ 306.719107] BUG: kernel NULL pointer dereference, address: 0000000000000008
[...]
[ 306.747260] RIP: 0010:scatterwalk_copychunks+0x12f/0x1b0
[...]
[ 306.770350] Call Trace:
[ 306.770956] scatterwalk_map_and_copy+0x6c/0x80
[ 306.772026] gcm_enc_copy_hash+0x4b/0x50
[ 306.772925] gcm_hash_crypt_remain_continue+0xef/0x110
[ 306.774138] gcm_hash_crypt_continue+0xa1/0xb0
[ 306.775103] ? gcm_hash_crypt_continue+0xa1/0xb0
[ 306.776103] gcm_hash_assoc_remain_continue+0x94/0xa0
[ 306.777170] gcm_hash_assoc_continue+0x9d/0xb0
[ 306.778239] gcm_hash_init_continue+0x8f/0xa0
[ 306.779121] gcm_hash+0x73/0x80
[ 306.779762] gcm_encrypt_continue+0x6d/0x80
[ 306.780582] crypto_gcm_encrypt+0xcb/0xe0
[ 306.781474] crypto_aead_encrypt+0x1f/0x30
[ 306.782353] tls_push_record+0x3b9/0xb20 [tls]
[ 306.783314] ? sk_psock_msg_verdict+0x199/0x300
[ 306.784287] bpf_exec_tx_verdict+0x3f2/0x680 [tls]
[ 306.785357] tls_sw_sendmsg+0x4a3/0x6a0 [tls]
test_sockmap test signature to trigger bug,
[TEST]: (1, 1, 1, sendmsg, pass,redir,start 1,end 2,pop (1,2),ktls,):
Fixes: d3b18ad31f ("tls: add bpf support to sk_msg handling")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-7-john.fastabend@gmail.com
Leaving an incorrect end mark in place when passing to crypto
layer will cause crypto layer to stop processing data before
all data is encrypted. To fix clear the end mark on push
data instead of expecting users of the helper to clear the
mark value after the fact.
This happens when we push data into the middle of a skmsg and
have room for it so we don't do a set of copies that already
clear the end flag.
Fixes: 6fff607e2f ("bpf: sk_msg program helper bpf_msg_push_data")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-6-john.fastabend@gmail.com
In the push, pull, and pop helpers operating on skmsg objects to make
data writable or insert/remove data we use this bounds check to ensure
specified data is valid,
/* Bounds checks: start and pop must be inside message */
if (start >= offset + l || last >= msg->sg.size)
return -EINVAL;
The problem here is offset has already included the length of the
current element the 'l' above. So start could be past the end of
the scatterlist element in the case where start also points into an
offset on the last skmsg element.
To fix do the accounting slightly different by adding the length of
the previous entry to offset at the start of the iteration. And
ensure its initialized to zero so that the first iteration does
nothing.
Fixes: 604326b41a ("bpf, sockmap: convert to generic sk_msg interface")
Fixes: 6fff607e2f ("bpf: sk_msg program helper bpf_msg_push_data")
Fixes: 7246d8ed4d ("bpf: helper to pop data from messages")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-5-john.fastabend@gmail.com
When sockmap sock with TLS enabled is removed we cleanup bpf/psock state
and call tcp_update_ulp() to push updates to TLS ULP on top. However, we
don't push the write_space callback up and instead simply overwrite the
op with the psock stored previous op. This may or may not be correct so
to ensure we don't overwrite the TLS write space hook pass this field to
the ULP and have it fixup the ctx.
This completes a previous fix that pushed the ops through to the ULP
but at the time missed doing this for write_space, presumably because
write_space TLS hook was added around the same time.
Fixes: 95fa145479 ("bpf: sockmap/tls, close can race with map free")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-4-john.fastabend@gmail.com
The sock_map_free() and sock_hash_free() paths used to delete sockmap
and sockhash maps walk the maps and destroy psock and bpf state associated
with the socks in the map. When done the socks no longer have BPF programs
attached and will function normally. This can happen while the socks in
the map are still "live" meaning data may be sent/received during the walk.
Currently, though we don't take the sock_lock when the psock and bpf state
is removed through this path. Specifically, this means we can be writing
into the ops structure pointers such as sendmsg, sendpage, recvmsg, etc.
while they are also being called from the networking side. This is not
safe, we never used proper READ_ONCE/WRITE_ONCE semantics here if we
believed it was safe. Further its not clear to me its even a good idea
to try and do this on "live" sockets while networking side might also
be using the socket. Instead of trying to reason about using the socks
from both sides lets realize that every use case I'm aware of rarely
deletes maps, in fact kubernetes/Cilium case builds map at init and
never tears it down except on errors. So lets do the simple fix and
grab sock lock.
This patch wraps sock deletes from maps in sock lock and adds some
annotations so we catch any other cases easier.
Fixes: 604326b41a ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-3-john.fastabend@gmail.com
When a sockmap is free'd and a socket in the map is enabled with tls
we tear down the bpf context on the socket, the psock struct and state,
and then call tcp_update_ulp(). The tcp_update_ulp() call is to inform
the tls stack it needs to update its saved sock ops so that when the tls
socket is later destroyed it doesn't try to call the now destroyed psock
hooks.
This is about keeping stacked ULPs in good shape so they always have
the right set of stacked ops.
However, recently unhash() hook was removed from TLS side. But, the
sockmap/bpf side is not doing any extra work to update the unhash op
when is torn down instead expecting TLS side to manage it. So both
TLS and sockmap believe the other side is managing the op and instead
no one updates the hook so it continues to point at tcp_bpf_unhash().
When unhash hook is called we call tcp_bpf_unhash() which detects the
psock has already been destroyed and calls sk->sk_prot_unhash() which
calls tcp_bpf_unhash() yet again and so on looping and hanging the core.
To fix have sockmap tear down logic fixup the stale pointer.
Fixes: 5d92e631b8 ("net/tls: partially revert fix transition through disconnect with close")
Reported-by: syzbot+83979935eb6304f8cd46@syzkaller.appspotmail.com
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20200111061206.8028-2-john.fastabend@gmail.com
To account for parts of the chip that are "harvested" (disabled) due to
silicon flaws, caches on some AMD GPUs must be initialized before ATS is
enabled.
ATS is normally enabled by the IOMMU driver before the GPU driver loads, so
this cache initialization would have to be done in a quirk, but that's too
complex to be practical.
For Navi14 (device ID 0x7340), this initialization is done by the VBIOS,
but apparently some boards went to production with an older VBIOS that
doesn't do it. Disable ATS for those boards.
Link: https://lore.kernel.org/r/20200114205523.1054271-3-alexander.deucher@amd.com
Bug: https://gitlab.freedesktop.org/drm/amd/issues/1015
See-also: d28ca864c4 ("PCI: Mark AMD Stoney Radeon R7 GPU ATS as broken")
See-also: 9b44b0b09d ("PCI: Mark AMD Stoney GPU ATS as broken")
[bhelgaas: squash into one patch, simplify slightly, commit log]
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
Review of the recently added documentation file for the qed driver
noticed a couple of typos. Fix them now.
Noticed-by: Michal Kalderon <mkalderon@marvell.com>
Fixes: 0f261c3ca0 ("devlink: add a driver-specific file for the qed driver")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
use sk_bound_dev_if for route lookup as already done
in most of the other ip_route_output_ports() calls.
Since most PPPoA providers use 10.0.0.138 as default gateway IP
this will allow connections to multiple PPTP providers with the
same IP address over different interfaces.
Signed-off-by: Ulrich Weber <ulrich.weber@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Jose Abreu says:
====================
net: stmmac: Fix selftests in Synopsys AXS101 board
Set of fixes for sefltests so that they work in Synopsys AXS101 board.
Final output:
$ ethtool -t eth0
The test result is PASS
The test extra info:
1. MAC Loopback 0
2. PHY Loopback -95
3. MMC Counters 0
4. EEE -95
5. Hash Filter MC 0
6. Perfect Filter UC 0
7. MC Filter 0
8. UC Filter 0
9. Flow Control -95
10. RSS -95
11. VLAN Filtering -95
12. VLAN Filtering (perf) -95
13. Double VLAN Filter -95
14. Double VLAN Filter (perf) -95
15. Flexible RX Parser -95
16. SA Insertion (desc) -95
17. SA Replacement (desc) -95
18. SA Insertion (reg) -95
19. SA Replacement (reg) -95
20. VLAN TX Insertion -95
21. SVLAN TX Insertion -95
22. L3 DA Filtering -95
23. L3 SA Filtering -95
24. L4 DA TCP Filtering -95
25. L4 SA TCP Filtering -95
26. L4 DA UDP Filtering -95
27. L4 SA UDP Filtering -95
28. ARP Offload -95
29. Jumbo Frame 0
30. Multichannel Jumbo -95
31. Split Header -95
Description:
1) Fixes the unaligned accesses that caused CPU halt in Synopsys AXS101
boards.
2) Fixes the VLAN tests when filtering failed to work.
3) Fixes the VLAN Perfect tests when filtering is not available in HW.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
When HW does not support perfect filtering the feature will not be
enabled in the net_device. Add a check for this to prevent failures.
Fixes: 1b2250a04c ("net: stmmac: selftests: Add tests for VLAN Perfect Filtering")
Signed-off-by: Jose Abreu <Jose.Abreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
