added check for port num and channel iteration are lessthan 8
to avoid out of bound write to 8x8 map array.
Change-Id: I4c6fe13a5eb09be623a1c40ce16c5a5e4246e021
Signed-off-by: Abinath S <quic_abins@quicinc.com>
Check for the proper param size before copying,
to avoid buffer overflow.
Original-Change-Id: I70c52e6ab76f528ea3714784ab9013b070839c40
Signed-off-by: Shalini Manjunatha <quic_c_shalma@quicinc.com>
Change-Id: Ic7fa9b3dd047d8eeba3cea02b99d6bc5b9df8daf
Now that possible races are solved, it is safe to use A71 drivers.
M51 drivers is still susceptible to audio breakage.
Fixes out-of-tree build as well.
This reverts commit 904a06434c.
Change-Id: Ia3cc443408d874a97d62fa703a7c5c7ff10da247
`audio_notifier_init()` calls `audio_pdr_register()`
which registers an SRCU notifier. `audio_pdr_register()`
is called before the SRCU notifier chain is initialized.
Initialize the SRCU notifier chain earlier to avoid
this issue.
Change-Id: Ib605b95782eb9a23afd8d4b8f09ff63f3b65692b
Signed-off-by: Samuel Pascua <pascua.samuel.14@gmail.com>
Update SOC_SINGLE_SX_TLV to SOC_SINGLE_S8_TLV to make codec
driver compatiable with upstream driver.
Change-Id: I4061b015d715978f3b294ad630f53b64bf66c2b7
Signed-off-by: Meng Wang <mengw@codeaurora.org>
[dereference23: Backport to msm-4.14]
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
The reg in soc_dapm_mux is 32-bit. The BE DAI ID passed
as shift(to be operated on the reg) may be more than 31,
which may cause overflow.
Set reg field to SND_SOC_NOPM to avoid any DAPM operation
while passing BE IDs in shift_l field and hence avoid overflow.
Change-Id: I94a371bd95997e7cc09702c86bbb3e4b33bac516
Signed-off-by: Soumya Managoli <smanag@codeaurora.org>
[dereference23: Forward port to 4.14]
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
The on-stack th_vi_v_vali struct is not fully initialized by
afe_get_sp_th_vi_v_vali_data(), leaving members of the th_vi_v_vali
struct used despite not being initialized. Fix it by zeroing out the
memory in afe_get_sp_th_vi_v_vali_data().
Change-Id: I14e50ea3393c2c898d77bdf3e04933e905520126
Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
Signed-off-by: atndko <z1281552865@gmail.com>
Change-Id: I5ed5be34a7c4d6135b735965e1fb8070f0296242
Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
[dereference23: Extend to audio-kernel 4.0]
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
[dereference23: Extend to audio-kernel 4.0]
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
Change-Id: I6eda8759d8d8eb5441ff85d8e102d1bde111f8c4
The non-blocking if-statement here causes the AUDIO_GET_AMRWB_ENC_CONFIG
ioctl to always return -EFAULT, even upon success. Fix it by correctly
guarding the -EFAULT return value.
Change-Id: I23f732a79487abec63d47894ecdf87686d7a75be
Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
[dereference23: Extend to audio-kernel 4.0]
Signed-off-by: Alexander Winkowski <dereference23@outlook.com>
This causes parts of the audio module to be rebuilt during every
incremental build, even if there are no changes:
CC techpack/audio/ipc/apr.o - due to command line change
CC techpack/audio/ipc/apr_v2.o - due to command line change
CC techpack/audio/ipc/apr_tal_rpmsg.o - due to command line change
CC techpack/audio/ipc/wcd-dsp-glink.o - due to command line change
We're only experiencing this issue in techpack/audio/ipc at the moment,
but kill the timestamp injection in all the audio components to
eliminate the possibility of encountering this issue again in the
future. This is harmless since the injected BUILD_TIMESTAMP macro is
never used.
Change-Id: Ie964cc70b0575166804bf595c629a34ed68894c3
