xen/netback: avoid entering xenvif_rx_next_skb() with an empty rx queue
xenvif_rx_next_skb() is expecting the rx queue not being empty, but
in case the loop in xenvif_rx_action() is doing multiple iterations,
the availability of another skb in the rx queue is not being checked.
amdgpu: disable powerpc support for the newer display engine
The DRM_AMD_DC_DCN display engine support (Raven, Navi, and newer) has
not been building cleanly on powerpc and causes link errors due to
mixing hard- and soft-float object files:
powerpc64-linux-ld: drivers/gpu/drm/amd/amdgpu/../display/dc/dml/display_mode_lib.o uses hard float, drivers/gpu/drm/amd/amdgpu/../display/dc/dcn31/dcn31_resource.o uses soft float
powerpc64-linux-ld: failed to merge target specific data of file drivers/gpu/drm/amd/amdgpu/../display/dc/dcn31/dcn31_resource.o
[..]
and while patches are floating around, it's not exactly obvious what is
going on.
The problem bisects to commit 41b7a347bf14 ("powerpc: Book3S 64-bit
outline-only KASAN support") but that is probably more about changing
config variables than the fundamental cause.
Despite the bisection result, a more directly related commit seems to be 26f4712aedbd ("drm/amd/display: move FPU related code from dcn31 to
dml/dcn31 folder"). It's probably a combination of the two.
This has been going on since the merge window, without any final word.
So instead of blindly applying patches that may or may not be the right
thing, let's disable this for now.
As Michael Ellerman says:
"IIUIC this code was never enabled on ppc before, so disabling it seems
like a reasonable fix to get the build clean"
and once we have more actual feedback (and find any potential users) we
can always re-enable it with the patch that fixes the issues and
back-port as necessary.
Muchun Song [Wed, 13 Jul 2022 14:02:26 +0000 (22:02 +0800)]
block: fix missing blkcg_bio_issue_init
The commit 513616843d73 ("block: remove superfluous calls to
blkcg_bio_issue_init") has removed blkcg_bio_issue_init from
__bio_clone since submit_bio will override ->bi_issue.
However, __blk_queue_split is called after blkcg_bio_issue_init
(see blk_mq_submit_bio) in submit_bio. In this case, the
->bi_issue is 0. Fix it.
KVM: x86: Fully initialize 'struct kvm_lapic_irq' in kvm_pv_kick_cpu_op()
'vector' and 'trig_mode' fields of 'struct kvm_lapic_irq' are left
uninitialized in kvm_pv_kick_cpu_op(). While these fields are normally
not needed for APIC_DM_REMRD, they're still referenced by
__apic_accept_irq() for trace_kvm_apic_accept_irq(). Fully initialize
the structure to avoid consuming random stack memory.
Israel Rukshin [Thu, 14 Jul 2022 12:42:10 +0000 (12:42 +0000)]
nvme: fix block device naming collision
The issue exists when multipath is enabled and the namespace is
shared, but all the other controller checks at nvme_is_unique_nsid()
are false. The reason for this issue is that nvme_is_unique_nsid()
returns false when is called from nvme_mpath_alloc_disk() due to an
uninitialized value of head->shared. The patch fixes it by setting
head->shared before nvme_mpath_alloc_disk() is called.
Keith Busch [Tue, 12 Jul 2022 15:16:32 +0000 (08:16 -0700)]
nvme-pci: fix freeze accounting for error handling
A reset on a live device experiencing a link error still needs to have
the queue freeze state started for the subsequent reinitialization. Skip
only the register read if the device is not present instead of bypassing
the freeze checks.
Fixes: b98235d3a471e ("nvme-pci: harden drive presence detect in nvme_dev_disable()") Reported-by: Niklas Schnelle <[email protected]> Signed-off-by: Keith Busch <[email protected]> Tested-by: Niklas Schnelle <[email protected]> Signed-off-by: Christoph Hellwig <[email protected]>
Nicolas Dichtel [Wed, 13 Jul 2022 11:48:53 +0000 (13:48 +0200)]
selftests/net: test nexthop without gw
This test implement the scenario described in the commit
"ip: fix dflt addr selection for connected nexthop".
The test configures a nexthop object with an output device only (no gateway
address) and a route that uses this nexthop. The goal is to check if the
kernel selects a valid source address.
Nicolas Dichtel [Wed, 13 Jul 2022 11:48:52 +0000 (13:48 +0200)]
ip: fix dflt addr selection for connected nexthop
When a nexthop is added, without a gw address, the default scope was set
to 'host'. Thus, when a source address is selected, 127.0.0.1 may be chosen
but rejected when the route is used.
When using a route without a nexthop id, the scope can be configured in the
route, thus the problem doesn't exist.
To explain more deeply: when a user creates a nexthop, it cannot specify
the scope. To create it, the function nh_create_ipv4() calls fib_check_nh()
with scope set to 0. fib_check_nh() calls fib_check_nh_nongw() wich was
setting scope to 'host'. Then, nh_create_ipv4() calls
fib_info_update_nhc_saddr() with scope set to 'host'. The src addr is
chosen before the route is inserted.
When a 'standard' route (ie without a reference to a nexthop) is added,
fib_create_info() calls fib_info_update_nhc_saddr() with the scope set by
the user. iproute2 set the scope to 'link' by default.
Here is a way to reproduce the problem:
ip netns add foo
ip -n foo link set lo up
ip netns add bar
ip -n bar link set lo up
sleep 1
ip -n foo link add name eth0 type dummy
ip -n foo link set eth0 up
ip -n foo address add 192.168.0.1/24 dev eth0
ip -n foo link add name veth0 type veth peer name veth1 netns bar
ip -n foo link set veth0 up
ip -n bar link set veth1 up
ip -n bar address add 192.168.1.1/32 dev veth1
ip -n bar route add default dev veth1
ip -n foo nexthop add id 1 dev veth0
ip -n foo route add 192.168.1.1 nhid 1
Try to get/use the route:
> $ ip -n foo route get 192.168.1.1
> RTNETLINK answers: Invalid argument
> $ ip netns exec foo ping -c1 192.168.1.1
> ping: connect: Invalid argument
Try without nexthop group (iproute2 sets scope to 'link' by dflt):
ip -n foo route del 192.168.1.1
ip -n foo route add 192.168.1.1 dev veth0
Try to get/use the route:
> $ ip -n foo route get 192.168.1.1
> 192.168.1.1 dev veth0 src 192.168.0.1 uid 0
> cache
> $ ip netns exec foo ping -c1 192.168.1.1
> PING 192.168.1.1 (192.168.1.1) 56(84) bytes of data.
> 64 bytes from 192.168.1.1: icmp_seq=1 ttl=64 time=0.039 ms
>
> --- 192.168.1.1 ping statistics ---
> 1 packets transmitted, 1 received, 0% packet loss, time 0ms
> rtt min/avg/max/mdev = 0.039/0.039/0.039/0.000 ms
Vaishnav Achath [Wed, 1 Jun 2022 07:16:11 +0000 (12:46 +0530)]
spi: cadence-quadspi: Remove spi_master_put() in probe failure path
Currently the spi_master is allocated by devm_spi_alloc_master()
and devres core manages the deallocation, but in probe failure
path spi_master_put() is being handled manually which causes
"refcount underflow use-after-free" warning when probe failure happens
after allocating spi_master.
Ard Biesheuvel [Tue, 31 May 2022 08:49:24 +0000 (09:49 +0100)]
ARM: 9208/1: entry: add .ltorg directive to keep literals in range
LKP reports a build issue on Clang, related to a literal load of
__current issued through the ldr_va macro. This turns out to be due to
the fact that group relocations are disabled when CONFIG_COMPILE_TEST=y,
which means that the ldr_va macro resolves to a pair of LDR
instructions, the first one being a literal load issued too far from its
literal pool.
Due to the introduction of a couple of new uses of this macro in commit 508074607c7b95b2 ("ARM: 9195/1: entry: avoid explicit literal loads"),
the literal pools end up getting rearranged in a way that causes the
literal for __current to go out of range. Let's fix this up by putting a
.ltorg directive in a suitable place in the code.
Wang Kefeng [Tue, 24 May 2022 08:03:46 +0000 (09:03 +0100)]
ARM: 9207/1: amba: fix refcount underflow if amba_device_add() fails
"ARM: 9192/1: amba: fix memory leak in amba_device_try_add()" leads
to a refcount underflow if amba_device_add() fails, which called by
of_amba_device_create(), the of_amba_device_create() already exists
the error handling, so amba_put_device() only need to be added into
amba_deferred_retry().
Fixes: 7719a68b2fa4 ("ARM: 9192/1: amba: fix memory leak in amba_device_try_add()") Reported-by: Guenter Roeck <[email protected]> Tested-by: Guenter Roeck <[email protected]> Signed-off-by: Kefeng Wang <[email protected]> Signed-off-by: Russell King (Oracle) <[email protected]>
Paolo Bonzini [Thu, 14 Jul 2022 11:29:57 +0000 (07:29 -0400)]
Documentation: kvm: clarify histogram units
In the case of histogram statistics, the values are always sample
counts; the unit instead applies to the bucket range. For example,
halt_poll_success_hist is a nanosecond statistic because the buckets are
for 0ns, 1ns, 2-3ns, 4-7ns etc. There isn't really any other sensible
interpretation, but clarify this anyway in the Documentation.
Paolo Bonzini [Thu, 14 Jul 2022 11:27:31 +0000 (07:27 -0400)]
kvm: stats: tell userspace which values are boolean
Some of the statistics values exported by KVM are always only 0 or 1.
It can be useful to export this fact to userspace so that it can track
them specially (for example by polling the value every now and then to
compute a % of time spent in a specific state).
Therefore, add "boolean value" as a new "unit". While it is not exactly
a unit, it walks and quacks like one. In particular, using the type
would be wrong because boolean values could be instantaneous or peak
values (e.g. "is the rmap allocated?") or even two-bucket histograms
(e.g. "number of posted vs. non-posted interrupt injections").
x86/kvm: fix FASTOP_SIZE when return thunks are enabled
The return thunk call makes the fastop functions larger, just like IBT
does. Consider a 16-byte FASTOP_SIZE when CONFIG_RETHUNK is enabled.
Otherwise, functions will be incorrectly aligned and when computing their
position for differently sized operators, they will executed in the middle
or end of a function, which may as well be an int3, leading to a crash
like:
KVM: nVMX: Always enable TSC scaling for L2 when it was enabled for L1
Windows 10/11 guests with Hyper-V role (WSL2) enabled are observed to
hang upon boot or shortly after when a non-default TSC frequency was
set for L1. The issue is observed on a host where TSC scaling is
supported. The problem appears to be that Windows doesn't use TSC
frequency for its guests even when the feature is advertised and KVM
filters SECONDARY_EXEC_TSC_SCALING out when creating L2 controls from
L1's. This leads to L2 running with the default frequency (matching
host's) while L1 is running with an altered one.
Keep SECONDARY_EXEC_TSC_SCALING in secondary exec controls for L2 when
it was set for L1. TSC_MULTIPLIER is already correctly computed and
written by prepare_vmcs02().
aq_nic_deinit() has been called while suspending, so we don't have to call
it again on resume.
Actually, call it again leads to another hang issue when resuming from
S3.
net: atlantic: remove deep parameter on suspend/resume functions
Below commit claims that atlantic NIC requires to reset the device on pm
op, and had set the deep to true for all suspend/resume functions.
commit 1809c30b6e5a ("net: atlantic: always deep reset on pm op, fixing up my null deref regression")
So, we could remove deep parameter on suspend/resume functions without
any functional change.
When creating VFs a kernel panic can happen when calling to
efx_ef10_try_update_nic_stats_vf.
When releasing a DMA coherent buffer, sometimes, I don't know in what
specific circumstances, it has to unmap memory with vunmap. It is
disallowed to do that in IRQ context or with BH disabled. Otherwise, we
hit this line in vunmap, causing the crash:
BUG_ON(in_interrupt());
This patch reenables BH to release the buffer.
Log messages when the bug is hit:
kernel BUG at mm/vmalloc.c:2727!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
CPU: 6 PID: 1462 Comm: NetworkManager Kdump: loaded Tainted: G I --------- --- 5.14.0-119.el9.x86_64 #1
Hardware name: Dell Inc. PowerEdge R740/06WXJT, BIOS 2.8.2 08/27/2020
RIP: 0010:vunmap+0x2e/0x30
...skip...
Call Trace:
__iommu_dma_free+0x96/0x100
efx_nic_free_buffer+0x2b/0x40 [sfc]
efx_ef10_try_update_nic_stats_vf+0x14a/0x1c0 [sfc]
efx_ef10_update_stats_vf+0x18/0x40 [sfc]
efx_start_all+0x15e/0x1d0 [sfc]
efx_net_open+0x5a/0xe0 [sfc]
__dev_open+0xe7/0x1a0
__dev_change_flags+0x1d7/0x240
dev_change_flags+0x21/0x60
...skip...
====================
seg6: fix skb checksum for SRH encapsulation/insertion
The Linux kernel supports Segment Routing Header (SRH)
encapsulation/insertion operations by providing the capability to: i)
encapsulate a packet in an outer IPv6 header with a specified SRH; ii)
insert a specified SRH directly after the IPv6 header of the packet.
Note that the insertion operation is also referred to as 'injection'.
The two operations are respectively supported by seg6_do_srh_encap() and
seg6_do_srh_inline(), which operate on the skb associated to the packet as
needed (e.g. adding the necessary headers and initializing them, while
taking care to recalculate the skb checksum).
seg6_do_srh_encap() and seg6_do_srh_inline() do not initialize the payload
length of the IPv6 header, which is carried out by the caller functions.
However, this approach causes the corruption of the skb checksum which
needs to be updated only after initialization of headers is completed
(thanks to Paolo Abeni for detecting this issue).
The patchset fixes the skb checksum corruption by moving the IPv6 header
payload length initialization from the callers of seg6_do_srh_encap() and
seg6_do_srh_inline() directly into these functions.
This patchset is organized as follows:
- patch 1/3, seg6: fix skb checksum evaluation in SRH
encapsulation/insertion;
(* SRH encapsulation/insertion available since v4.10)
- patch 2/3, seg6: fix skb checksum in SRv6 End.B6 and End.B6.Encaps
behaviors;
(* SRv6 End.B6 and End.B6.Encaps behaviors available since v4.14)
- patch 3/3, seg6: bpf: fix skb checksum in bpf_push_seg6_encap();
(* bpf IPv6 Segment Routing helpers available since v4.18)
Andrea Mayer [Tue, 12 Jul 2022 17:58:37 +0000 (19:58 +0200)]
seg6: bpf: fix skb checksum in bpf_push_seg6_encap()
Both helper functions bpf_lwt_seg6_action() and bpf_lwt_push_encap() use
the bpf_push_seg6_encap() to encapsulate the packet in an IPv6 with Segment
Routing Header (SRH) or insert an SRH between the IPv6 header and the
payload.
To achieve this result, such helper functions rely on bpf_push_seg6_encap()
which, in turn, leverages seg6_do_srh_{encap,inline}() to perform the
required operation (i.e. encap/inline).
This patch removes the initialization of the IPv6 header payload length
from bpf_push_seg6_encap(), as it is now handled properly by
seg6_do_srh_{encap,inline}() to prevent corruption of the skb checksum.
Fixes: fe94cc290f53 ("bpf: Add IPv6 Segment Routing helpers") Signed-off-by: Andrea Mayer <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
Andrea Mayer [Tue, 12 Jul 2022 17:58:36 +0000 (19:58 +0200)]
seg6: fix skb checksum in SRv6 End.B6 and End.B6.Encaps behaviors
The SRv6 End.B6 and End.B6.Encaps behaviors rely on functions
seg6_do_srh_{encap,inline}() to, respectively: i) encapsulate the
packet within an outer IPv6 header with the specified Segment Routing
Header (SRH); ii) insert the specified SRH directly after the IPv6
header of the packet.
This patch removes the initialization of the IPv6 header payload length
from the input_action_end_b6{_encap}() functions, as it is now handled
properly by seg6_do_srh_{encap,inline}() to avoid corruption of the skb
checksum.
Fixes: 140f04c33bbc ("ipv6: sr: implement several seg6local actions") Signed-off-by: Andrea Mayer <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
Andrea Mayer [Tue, 12 Jul 2022 17:58:35 +0000 (19:58 +0200)]
seg6: fix skb checksum evaluation in SRH encapsulation/insertion
Support for SRH encapsulation and insertion was introduced with
commit 6c8702c60b88 ("ipv6: sr: add support for SRH encapsulation and
injection with lwtunnels"), through the seg6_do_srh_encap() and
seg6_do_srh_inline() functions, respectively.
The former encapsulates the packet in an outer IPv6 header along with
the SRH, while the latter inserts the SRH between the IPv6 header and
the payload. Then, the headers are initialized/updated according to the
operating mode (i.e., encap/inline).
Finally, the skb checksum is calculated to reflect the changes applied
to the headers.
The IPv6 payload length ('payload_len') is not initialized
within seg6_do_srh_{inline,encap}() but is deferred in seg6_do_srh(), i.e.
the caller of seg6_do_srh_{inline,encap}().
However, this operation invalidates the skb checksum, since the
'payload_len' is updated only after the checksum is evaluated.
To solve this issue, the initialization of the IPv6 payload length is
moved from seg6_do_srh() directly into the seg6_do_srh_{inline,encap}()
functions and before the skb checksum update takes place.
Xiubo Li [Mon, 11 Jul 2022 04:11:21 +0000 (12:11 +0800)]
netfs: do not unlock and put the folio twice
check_write_begin() will unlock and put the folio when return
non-zero. So we should avoid unlocking and putting it twice in
netfs layer.
Change the way ->check_write_begin() works in the following two ways:
(1) Pass it a pointer to the folio pointer, allowing it to unlock and put
the folio prior to doing the stuff it wants to do, provided it clears
the folio pointer.
(2) Change the return values such that 0 with folio pointer set means
continue, 0 with folio pointer cleared means re-get and all error
codes indicating an error (no special treatment for -EAGAIN).
[ bagasdotme: use Sphinx code text syntax for *foliop pointer ]
x86/entry: Remove UNTRAIN_RET from native_irq_return_ldt
UNTRAIN_RET is not needed in native_irq_return_ldt because RET
untraining has already been done at this point.
In addition, when the RETBleed mitigation is IBPB, UNTRAIN_RET clobbers
several registers (AX, CX, DX) so here it trashes user values which are
in these registers.
Currently, the data flow of the max/min linkrate in the driver is
* in pm8001_get_lrate_mode():
hardcoded value ==> struct sas_phy
* in pm8001_bytes_dmaed():
struct pm8001_phy ==> struct sas_phy
* in pm8001_phy_control():
libsas data ==> struct pm8001_phy
Since pm8001_bytes_dmaed() follows pm8001_get_lrate_mode(), and the fields
in struct pm8001_phy are not initialized, sysfs
`/sys/class/sas_phy/phy-*/maximum_linkrate` always shows `Unknown`.
To fix the issue, change the dataflow to the following:
* in pm8001_phy_init():
initial value ==> struct pm8001_phy
* in pm8001_get_lrate_mode():
struct pm8001_phy ==> struct sas_phy
* in pm8001_phy_control():
libsas data ==> struct pm8001_phy
For negotiated linkrate, the current dataflow is:
* in pm8001_get_lrate_mode():
iomb data ==> struct asd_sas_phy ==> struct sas_phy
* in pm8001_bytes_dmaed():
struct asd_sas_phy ==> struct sas_phy
Since pm8001_bytes_dmaed() follows pm8001_get_lrate_mode(), the assignment
statements in pm8001_bytes_dmaed() are unnecessary and cleaned up.
In ufshcd_host_reset_and_restore(), ufshcd_set_clk_freq() is called to
scale clock rate. However, this did not call vops->clk_scale_notify() to
inform platform driver of clock change.
Call ufshcd_scale_clks() instead so that clock change can be properly
handled.
scsi: ufs: core: Drop loglevel of WriteBoost message
Commit '3b5f3c0d0548 ("scsi: ufs: core: Tidy up WB configuration code")'
changed the log level of the write boost enable/disable notification from
debug to info. This results in a lot of noise in the kernel log during
normal operation.
Jakub Kicinski [Thu, 14 Jul 2022 03:16:03 +0000 (20:16 -0700)]
Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2022-07-12
This series contains updates to ice driver only.
Paul fixes detection of E822 devices for firmware update and changes NVM
read for snapshot creation to be done in chunks as some systems cannot
read the entire NVM in the allotted time.
====================
Ming Lei [Wed, 6 Jul 2022 12:59:42 +0000 (20:59 +0800)]
scsi: megaraid: Clear READ queue map's nr_queues
The megaraid SCSI driver sets set->nr_maps as 3 if poll_queues is > 0, and
blk-mq actually initializes each map's nr_queues as nr_hw_queues.
Consequently the driver has to clear READ queue map's nr_queues, otherwise
the queue map becomes broken if poll_queues is set as non-zero.
Use after free is detected by kfence when disabling sriov. What was read
after being freed was vf->pci_dev: it was freed from pci_disable_sriov
and later read in efx_ef10_sriov_free_vf_vports, called from
efx_ef10_sriov_free_vf_vswitching.
Set the pointer to NULL at release time to not trying to read it later.
Reproducer and dmesg log (note that kfence doesn't detect it every time):
$ echo 1 > /sys/class/net/enp65s0f0np0/device/sriov_numvfs
$ echo 0 > /sys/class/net/enp65s0f0np0/device/sriov_numvfs
BUG: KFENCE: use-after-free read in efx_ef10_sriov_free_vf_vswitching+0x82/0x170 [sfc]
Use-after-free read at 0x00000000ff3c1ba5 (in kfence-#224):
efx_ef10_sriov_free_vf_vswitching+0x82/0x170 [sfc]
efx_ef10_pci_sriov_disable+0x38/0x70 [sfc]
efx_pci_sriov_configure+0x24/0x40 [sfc]
sriov_numvfs_store+0xfe/0x140
kernfs_fop_write_iter+0x11c/0x1b0
new_sync_write+0x11f/0x1b0
vfs_write+0x1eb/0x280
ksys_write+0x5f/0xe0
do_syscall_64+0x5c/0x80
entry_SYSCALL_64_after_hwframe+0x44/0xae
Steve French [Tue, 12 Jul 2022 05:11:42 +0000 (00:11 -0500)]
smb3: workaround negprot bug in some Samba servers
Mount can now fail to older Samba servers due to a server
bug handling padding at the end of the last negotiate
context (negotiate contexts typically are rounded up to 8
bytes by adding padding if needed). This server bug can
be avoided by switching the order of negotiate contexts,
placing a negotiate context at the end that does not
require padding (prior to the recent netname context fix
this was the case on the client).
ACPI: CPPC: Fix enabling CPPC on AMD systems with shared memory
When commit 72f2ecb7ece7 ("ACPI: bus: Set CPPC _OSC bits for all
and when CPPC_LIB is supported") was introduced, we found collateral
damage that a number of AMD systems that supported CPPC but
didn't advertise support in _OSC stopped having a functional
amd-pstate driver. The _OSC was only enforced on Intel systems at that
time.
This was fixed for the MSR based designs by commit 8b356e536e69f
("ACPI: CPPC: Don't require _OSC if X86_FEATURE_CPPC is supported")
but some shared memory based designs also support CPPC but haven't
advertised support in the _OSC. Add support for those designs as well by
hardcoding the list of systems.
vf/remap: return the amount of bytes actually deduplicated
When using the FIDEDUPRANGE ioctl, in case of success the requested size
is returned. In some cases this might not be the actual amount of bytes
deduplicated.
This change modifies vfs_dedupe_file_range() to report the actual amount
of bytes deduplicated, instead of the requested amount.
Merge tag 'cgroup-for-5.19-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fix from Tejun Heo:
"Fix an old and subtle bug in the migration path.
css_sets are used to track tasks and migrations are tasks moving from
a group of css_sets to another group of css_sets. The migration path
pins all source and destination css_sets in the prep stage.
Unfortunately, it was overloading the same list_head entry to track
sources and destinations, which got confused for migrations which are
partially identity leading to use-after-frees.
Fixed by using dedicated list_heads for tracking sources and
destinations"
* tag 'cgroup-for-5.19-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: Use separate src/dst nodes when preloading css_sets for migration
Merge tag 'dt-fixes-for-palmer-5.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git into fixes
Microchip RISC-V devicetree fixes for 5.19-rc6
A single fix for mpfs.dtsi:
- The l2 cache controller was never hooked up in the dt, so userspace
is presented with the wrong topology information, so it has been
hooked up.
* tag 'dt-fixes-for-palmer-5.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git:
riscv: dts: microchip: hook up the mpfs' l2cache
Dave Chinner [Wed, 13 Jul 2022 07:49:15 +0000 (17:49 +1000)]
fs/remap: constrain dedupe of EOF blocks
If dedupe of an EOF block is not constrainted to match against only
other EOF blocks with the same EOF offset into the block, it can
match against any other block that has the same matching initial
bytes in it, even if the bytes beyond EOF in the source file do
not match.
Fix this by constraining the EOF block matching to only match
against other EOF blocks that have identical EOF offsets and data.
This allows "whole file dedupe" to continue to work without allowing
eof blocks to randomly match against partial full blocks with the
same data.
Mario Kleiner [Mon, 11 Jul 2022 17:39:28 +0000 (19:39 +0200)]
drm/amd/display: Only use depth 36 bpp linebuffers on DCN display engines.
Various DCE versions had trouble with 36 bpp lb depth, requiring fixes,
last time in commit 353ca0fa5630 ("drm/amd/display: Fix 10bit 4K display
on CIK GPUs") for DCE-8. So far >= DCE-11.2 was considered ok, but now I
found out that on DCE-11.2 it causes dithering when there shouldn't be
any, so identity pixel passthrough with identity gamma LUTs doesn't work
when it should. This breaks various important neuroscience applications,
as reported to me by scientific users of Polaris cards under Ubuntu 22.04
with Linux 5.15, and confirmed by testing it myself on DCE-11.2.
Lets only use depth 36 for DCN engines, where my testing showed that it
is both necessary for high color precision output, e.g., RGBA16 fb's,
and not harmful, as far as more than one year in real-world use showed.
DCE engines seem to work fine for high precision output at 30 bpp, so
this ("famous last words") depth 30 should hopefully fix all known problems
without introducing new ones.
Successfully retested on DCE-11.2 Polaris and DCN-1.0 Raven Ridge on
top of Linux 5.19.0-rc2 + drm-next.
drm/amdkfd: correct the MEC atomic support firmware checking for GC 10.3.7
On the GC 10.3.7 platform the initial MEC release version #3 can support
atomic operation,so need correct and set its MEC atomic support version to #3.
drm/amd/display: Ignore First MST Sideband Message Return Error
[why]
First MST sideband message returns AUX_RET_ERROR_HPD_DISCON
on certain intel platform. Aux transaction considered failure
if HPD unexpected pulled low. The actual aux transaction success
in such case, hence do not return error.
[how]
Not returning error when AUX_RET_ERROR_HPD_DISCON detected
on the first sideband message.
v2: squash in additional DMI entries
v3: squash in static fix
Jianglei Nie [Tue, 12 Jul 2022 01:10:37 +0000 (09:10 +0800)]
ima: Fix potential memory leak in ima_init_crypto()
On failure to allocate the SHA1 tfm, IMA fails to initialize and exits
without freeing the ima_algo_array. Add the missing kfree() for
ima_algo_array to avoid the potential memory leak.
Signed-off-by: Jianglei Nie <[email protected]> Fixes: 6d94809af6b0 ("ima: Allocate and initialize tfm for each PCR bank") Signed-off-by: Mimi Zohar <[email protected]>
ima: force signature verification when CONFIG_KEXEC_SIG is configured
Currently, an unsigned kernel could be kexec'ed when IMA arch specific
policy is configured unless lockdown is enabled. Enforce kernel
signature verification check in the kexec_file_load syscall when IMA
arch specific policy is configured.
Nick Bowler [Wed, 13 Jul 2022 01:58:35 +0000 (21:58 -0400)]
net: sunhme: output link status with a single print.
This driver currently prints the link status using four separate
printk calls, which these days gets presented to the user as four
distinct messages, not exactly ideal:
[ 32.582778] eth0: Link is up using
[ 32.582828] internal
[ 32.582837] transceiver at
[ 32.582888] 100Mb/s, Full Duplex.
Restructure the display_link_mode function to use a single netdev_info
call to present all this information as a single message, which is much
nicer:
[ 33.640143] hme 0000:00:01.1 eth0: Link is up using internal transceiver at 100Mb/s, Full Duplex.
The display_forced_link_mode function has a similar structure, so adjust
it in a similar fashion.
Hayes Wang [Wed, 13 Jul 2022 03:31:11 +0000 (11:31 +0800)]
r8152: fix accessing unset transport header
A warning is triggered by commit 66e4c8d95008 ("net: warn if transport
header was not set"). The warning is harmless, because the value from
skb_transport_offset() is only used for skb_is_gso() is true or the
skb->ip_summed is equal to CHECKSUM_PARTIAL.
Fixes: 66e4c8d95008 ("net: warn if transport header was not set") Signed-off-by: Hayes Wang <[email protected]> Signed-off-by: David S. Miller <[email protected]>
David S. Miller [Wed, 13 Jul 2022 13:27:38 +0000 (14:27 +0100)]
Merge tag 'wireless-2022-07-13' of git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless
Johannes Berg says:
====================
A small set of fixes for
* queue selection in mesh/ocb
* queue handling on interface stop
* hwsim virtio device vs. some other virtio changes
* dt-bindings email addresses
* color collision memory allocation
* a const variable in rtw88
* shared SKB transmit in the ethernet format path
* P2P client port authorization
====================
Vasily Gorbik [Mon, 27 Jun 2022 12:50:56 +0000 (14:50 +0200)]
s390/nospec: remove unneeded header includes
Commit 4efd417f298b ("s390: raise minimum supported machine generation
to z10") removed the usage of alternatives and lowcore in expolines
macros. Remove unneeded header includes as well.
With that, expoline.S doesn't require asm-offsets.h and
expoline_prepare target dependency could be removed.
Vasily Gorbik [Mon, 27 Jun 2022 12:50:53 +0000 (14:50 +0200)]
s390/nospec: build expoline.o for modules_prepare target
When CONFIG_EXPOLINE_EXTERN is used expoline thunks are generated
from arch/s390/lib/expoline.S and postlinked into every module.
This is also true for external modules. Add expoline.o build to
the modules_prepare target.
Dan Carpenter [Tue, 12 Jul 2022 14:42:25 +0000 (17:42 +0300)]
net: stmmac: fix leaks in probe
These two error paths should clean up before returning.
Fixes: 2bb4b98b60d7 ("net: stmmac: Add Ingenic SoCs MAC support.") Signed-off-by: Dan Carpenter <[email protected]> Signed-off-by: David S. Miller <[email protected]>
Liang He [Tue, 12 Jul 2022 06:14:17 +0000 (14:14 +0800)]
net: ftgmac100: Hold reference returned by of_get_child_by_name()
In ftgmac100_probe(), we should hold the refernece returned by
of_get_child_by_name() and use it to call of_node_put() for
reference balance.
Fixes: 39bfab8844a0 ("net: ftgmac100: Add support for DT phy-handle property") Signed-off-by: Liang He <[email protected]> Signed-off-by: David S. Miller <[email protected]>
nexthop: Fix data-races around nexthop_compat_mode.
While reading nexthop_compat_mode, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its readers.
Fixes: 4f80116d3df3 ("net: ipv4: add sysctl for nexthop api compatibility mode") Signed-off-by: Kuniyuki Iwashima <[email protected]> Signed-off-by: David S. Miller <[email protected]>
raw: Fix a data-race around sysctl_raw_l3mdev_accept.
While reading sysctl_raw_l3mdev_accept, it can be changed concurrently.
Thus, we need to add READ_ONCE() to its reader.
Fixes: 6897445fb194 ("net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs") Signed-off-by: Kuniyuki Iwashima <[email protected]> Signed-off-by: David S. Miller <[email protected]>
sysctl: Fix data-races in proc_dointvec_ms_jiffies().
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dointvec_ms_jiffies() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dointvec_ms_jiffies() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima <[email protected]> Signed-off-by: David S. Miller <[email protected]>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dou8vec_minmax() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dou8vec_minmax() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: cb9444130662 ("sysctl: add proc_dou8vec_minmax()") Signed-off-by: Kuniyuki Iwashima <[email protected]> Signed-off-by: David S. Miller <[email protected]>
If the regulator_get_optional() call for the SRAM regulator returns
a probe deferral, we must bail out and retry probing later: failing
to do this will produce unstabilities on platforms requiring the
handling for this regulator.
Fixes: ffa7bdf7f344 ("cpufreq: mediatek: Make sram regulator optional") Signed-off-by: AngeloGioacchino Del Regno <[email protected]> Signed-off-by: Viresh Kumar <[email protected]>
x86_has_pat_wp() is using a wrong test, as it relies on the normal
PAT configuration used by the kernel. In case the PAT MSR has been
setup by another entity (e.g. Xen hypervisor) it might return false
even if the PAT configuration is allowing WP mappings. This due to the
fact that when running as Xen PV guest the PAT MSR is setup by the
hypervisor and cannot be changed by the guest. This results in the WP
related entry to be at a different position when running as Xen PV
guest compared to the bare metal or fully virtualized case.
The correct way to test for WP support is:
1. Get the PTE protection bits needed to select WP mode by reading
__cachemode2pte_tbl[_PAGE_CACHE_MODE_WP] (depending on the PAT MSR
setting this might return protection bits for a stronger mode, e.g.
UC-)
2. Translate those bits back into the real cache mode selected by those
PTE bits by reading __pte2cachemode_tbl[__pte2cm_idx(prot)]
3. Test for the cache mode to be _PAGE_CACHE_MODE_WP
After this; e1 is attached to an unmapped rb and a subsequent
perf_mmap() will loop forever more:
again:
mutex_lock(&e->mmap_mutex);
if (event->rb) {
...
if (!atomic_inc_not_zero(&e->rb->mmap_count)) {
...
mutex_unlock(&e->mmap_mutex);
goto again;
}
}
The loop in perf_mmap_close() holds e2->mmap_mutex, while the attach
in perf_event_set_output() holds e1->mmap_mutex. As such there is no
serialization to avoid this race.
Change perf_event_set_output() to take both e1->mmap_mutex and
e2->mmap_mutex to alleviate that problem. Additionally, have the loop
in perf_mmap() detach the rb directly, this avoids having to wait for
the concurrent perf_mmap_close() to get around to doing it to make
progress.
Merge tag 'arm-soc/for-5.19/devicetree-arm64-fixes' of https://github.com/Broadcom/stblinux into arm/fixes
This pull request contains Broadcom ARM64-based SoCs Device Tree fixes
for 5.19, please pull the following:
- William corrects the BCM4906 DTS to have an armv8-timer Device Tree,
necessary for booting, and fixes the BCM4908 DTS to have a proper
'enable-method' and 'cpu-release-addr' properties for the kernel to boot
when using u-boot
* tag 'arm-soc/for-5.19/devicetree-arm64-fixes' of https://github.com/Broadcom/stblinux:
arm64: dts: broadcom: bcm4908: Fix cpu node for smp boot
arm64: dts: broadcom: bcm4908: Fix timer node for BCM4906 SoC
ALSA: hda/realtek - Fix headset mic problem for a HP machine with alc221
On a HP 288 Pro G2 MT (X9W02AV), the front mic could not be detected.
In order to get it working, the pin configuration needs to be set
correctly, and the ALC221_FIXUP_HP_288PRO_MIC_NO_PRESENCE fixup needs
to be applied.
Jeremy Szu [Wed, 13 Jul 2022 02:27:04 +0000 (10:27 +0800)]
ALSA: hda/realtek: fix mute/micmute LEDs for HP machines
The HP ProBook 440/450 G9 and EliteBook 640/650 G9 have multiple
motherboard design and they are using different subsystem ID of audio
codec. Add the same quirk for other MBs.
Jakub Kicinski [Wed, 13 Jul 2022 03:36:00 +0000 (20:36 -0700)]
Merge branch 'bnxt_en-5-bug-fixes'
Michael Chan says:
====================
bnxt_en: 5 Bug fixes
This patchset fixes various issues, including SRIOV error unwinding,
one error recovery path, live patch reporting, XDP transmit path,
and PHC clock reading.
====================
The upper 32-bit PHC register is not latched when reading the lower
32-bit PHC register. Current code leaves a small window where we may
not read correct higher order bits if the lower order bits are just about
to wrap around.
This patch fixes this by reading higher order bits twice and makes
sure that final value is correctly paired with its lower 32 bits.
Michael Chan [Tue, 12 Jul 2022 02:26:17 +0000 (22:26 -0400)]
bnxt_en: Fix and simplify XDP transmit path
Fix the missing length hint in the TX BD for the XDP transmit path. The
length hint is required on legacy chips.
Also, simplify the code by eliminating the first_buf local variable.
tx_buf contains the same value. The opaque value only needs to be set
on the first BD. Fix this also for correctness.
Fixes: a7559bc8c17c ("bnxt: support transmit and free of aggregation buffers") Reviewed-by: Andy Gospodarek <[email protected]> Signed-off-by: Michael Chan <[email protected]> Signed-off-by: Jakub Kicinski <[email protected]>
Michael Chan [Tue, 12 Jul 2022 02:26:15 +0000 (22:26 -0400)]
bnxt_en: Fix bnxt_reinit_after_abort() code path
bnxt_reinit_after_abort() is called during ifup when a previous
FW reset sequence has aborted or a previous ifup has failed after
detecting FW reset. In all cases, it is safe to assume that a
previous FW reset has completed and the driver may not have fully
reinitialized.
Prior to this patch, it is assumed that the
FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE flag will always be
set by the firmware in bnxt_hwrm_if_change(). This may not be true if
the driver has already attempted to register with the firmware. The
firmware may not set the RESET_DONE flag again after the driver has
registered, assuming that the driver has seen the flag already.
Fix it to always go through the FW reset initialization path if
the BNXT_STATE_FW_RESET_DET flag is set. This flag is always set
by the driver after successfully going through bnxt_reinit_after_abort().
Fixes: 6882c36cf82e ("bnxt_en: attempt to reinitialize after aborted reset") Reviewed-by: Pavan Chebbi <[email protected]> Signed-off-by: Michael Chan <[email protected]> Signed-off-by: Jakub Kicinski <[email protected]>
bnxt_en: reclaim max resources if sriov enable fails
If bnxt_sriov_enable() fails after some resources have been reserved
for the VFs, the current code is not unwinding properly and the
reserved resources become unavailable afterwards. Fix it by
properly unwinding with a call to bnxt_hwrm_func_qcaps() to
reset all maximum resources.
Also, add the missing bnxt_ulp_sriov_cfg() call to let the RDMA
driver know to abort.
Fixes: c0c050c58d84 ("bnxt_en: New Broadcom ethernet driver.") Signed-off-by: Kashyap Desai <[email protected]> Signed-off-by: Michael Chan <[email protected]> Signed-off-by: Jakub Kicinski <[email protected]>
Merge tag 'trace-v5.19-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing fixes from Steven Rostedt:
"Fixes and minor clean ups for tracing:
- Fix memory leak by reverting what was thought to be a double free.
A static tool had gave a false positive that a double free was
possible in the error path, but it was actually a different
location that confused the static analyzer (and those of us that
reviewed it).
- Move use of static buffers by ftrace_dump() to a location that can
be used by kgdb's ftdump(), as it needs it for the same reasons.
- Clarify in the Kconfig description that function tracing has
negligible impact on x86, but may have a bit bigger impact on other
architectures.
- Remove unnecessary extra semicolon in trace event.
- Make a local variable static that is used in the fprobes sample
- Use KSYM_NAME_LEN for length of function in kprobe sample and get
rid of unneeded macro for the same purpose"
* tag 'trace-v5.19-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
samples: Use KSYM_NAME_LEN for kprobes
fprobe/samples: Make sample_probe static
blk-iocost: tracing: atomic64_read(&ioc->vtime_rate) is assigned an extra semicolon
ftrace: Be more specific about arch impact when function tracer is enabled
tracing: Fix sleeping while atomic in kdb ftdump
tracing/histograms: Fix memory leak problem
Andrzej Hajda [Fri, 24 Jun 2022 11:35:28 +0000 (13:35 +0200)]
drm/i915/selftests: fix subtraction overflow bug
On some machines hole_end can be small enough to cause subtraction
overflow. On the other side (addr + 2 * min_alignment) can overflow
in case of mock tests. This patch should handle both cases.
Chris Wilson [Fri, 8 Jul 2022 14:20:11 +0000 (16:20 +0200)]
drm/i915/gem: Look for waitboosting across the whole object prior to individual waits
We employ a "waitboost" heuristic to detect when userspace is stalled
waiting for results from earlier execution. Under latency sensitive work
mixed between the gpu/cpu, the GPU is typically under-utilised and so
RPS sees that low utilisation as a reason to downclock the frequency,
causing longer stalls and lower throughput. The user left waiting for
the results is not impressed.
On applying commit 047a1b877ed4 ("dma-buf & drm/amdgpu: remove dma_resv
workaround") it was observed that deinterlacing h264 on Haswell
performance dropped by 2-5x. The reason being that the natural workload
was not intense enough to trigger RPS (using HW evaluation intervals) to
upclock, and so it was depending on waitboosting for the throughput.
Commit 047a1b877ed4 ("dma-buf & drm/amdgpu: remove dma_resv workaround")
changes the composition of dma-resv from keeping a single write fence +
multiple read fences, to a single array of multiple write and read
fences (a maximum of one pair of write/read fences per context). The
iteration order was also changed implicitly from all-read fences then
the single write fence, to a mix of write fences followed by read
fences. It is that ordering change that belied the fragility of
waitboosting.
Currently, a waitboost is inspected at the point of waiting on an
outstanding fence. If the GPU is backlogged such that we haven't yet
stated the request we need to wait on, we force the GPU to upclock until
the completion of that request. By changing the order in which we waited
upon requests, we ended up waiting on those requests in sequence and as
such we saw that each request was already started and so not a suitable
candidate for waitboosting.
Instead of asking whether to boost each fence in turn, we can look at
whether boosting is required for the dma-resv ensemble prior to waiting
on any fence, making the heuristic more robust to the order in which
fences are stored in the dma-resv.
Chris Wilson [Tue, 12 Jul 2022 15:21:33 +0000 (16:21 +0100)]
drm/i915/gt: Serialize TLB invalidates with GT resets
Avoid trying to invalidate the TLB in the middle of performing an
engine reset, as this may result in the reset timing out. Currently,
the TLB invalidate is only serialised by its own mutex, forgoing the
uncore lock, but we can take the uncore->lock as well to serialise
the mmio access, thereby serialising with the GDRST.
Tested on a NUC5i7RYB, BIOS RYBDWi35.86A.0380.2019.0517.1530 with
i915 selftest/hangcheck.
Chris Wilson [Tue, 12 Jul 2022 15:21:32 +0000 (16:21 +0100)]
drm/i915/gt: Serialize GRDOM access between multiple engine resets
Don't allow two engines to be reset in parallel, as they would both
try to select a reset bit (and send requests to common registers)
and wait on that register, at the same time. Serialize control of
the reset requests/acks using the uncore->lock, which will also ensure
that no other GT state changes at the same time as the actual reset.
Matthew Auld [Mon, 11 Jul 2022 08:58:59 +0000 (09:58 +0100)]
drm/i915/ttm: fix sg_table construction
If we encounter some monster sized local-memory page that exceeds the
maximum sg length (UINT32_MAX), ensure that don't end up with some
misaligned address in the entry that follows, leading to fireworks
later. Also ensure we have some coverage of this in the selftests.
v2(Chris):
- Use round_down consistently to avoid udiv errors
v3(Nirmoy):
- Also update the max_segment in the selftest
projects / linux.git / log