On 4/11/25 8:37 AM, Krishna Chaitanya Chundru wrote:
>
>
> On 4/10/2025 8:26 PM, Muhammad Usama Anjum wrote:
>> Fix dma_direct_alloc() failure at resume time during bhie_table
>> allocation. There is a crash report where at resume time, the memory
>> from the dma doesn't get allocated and MHI fails to re-initialize.
>> There may be fragmentation of some kind which fails the allocation
>> call.
>>
>> To fix it, don't free the memory at power down during suspend /
>> hibernation. Instead, use the same allocated memory again after every
>> resume / hibernation. This patch has been tested with resume and
>> hibernation both.
>>
>> The rddm is of constant size for a given hardware. While the fbc_image
>> size depends on the firmware. If the firmware changes, we'll free and
> If firmware image will change between suspend and resume ?
Yes, correct.
>> allocate new memory for it.
>>
>> Here are the crash logs:
>>
>> [ 3029.338587] mhi mhi0: Requested to power ON
>> [ 3029.338621] mhi mhi0: Power on setup success
>> [ 3029.668654] kworker/u33:8: page allocation failure: order:7,
>> mode:0xc04(GFP_NOIO|GFP_DMA32), nodemask=(null),cpuset=/,mems_allowed=0
>> [ 3029.668682] CPU: 4 UID: 0 PID: 2744 Comm: kworker/u33:8 Not tainted
>> 6.11.11-valve10-1-neptune-611-gb69e902b4338
>> #1ed779c892334112fb968aaa3facf9686b5ff0bd7
>> [ 3029.668690] Hardware name: Valve Galileo/Galileo, BIOS F7G0112
>> 08/01/2024
>> [ 3029.668694] Workqueue: mhi_hiprio_wq mhi_pm_st_worker [mhi]
>> [ 3029.668717] Call Trace:
>> [ 3029.668722] <TASK>
>> [ 3029.668728] dump_stack_lvl+0x4e/0x70
>> [ 3029.668738] warn_alloc+0x164/0x190
>> [ 3029.668747] ? srso_return_thunk+0x5/0x5f
>> [ 3029.668754] ? __alloc_pages_direct_compact+0xaf/0x360
>> [ 3029.668761] __alloc_pages_slowpath.constprop.0+0xc75/0xd70
>> [ 3029.668774] __alloc_pages_noprof+0x321/0x350
>> [ 3029.668782] __dma_direct_alloc_pages.isra.0+0x14a/0x290
>> [ 3029.668790] dma_direct_alloc+0x70/0x270
>> [ 3029.668796] mhi_alloc_bhie_table+0xe8/0x190 [mhi
>> faa917c5aa23a5f5b12d6a2c597067e16d2fedc0]
>> [ 3029.668814] mhi_fw_load_handler+0x1bc/0x310 [mhi
>> faa917c5aa23a5f5b12d6a2c597067e16d2fedc0]
>> [ 3029.668830] mhi_pm_st_worker+0x5c8/0xaa0 [mhi
>> faa917c5aa23a5f5b12d6a2c597067e16d2fedc0]
>> [ 3029.668844] ? srso_return_thunk+0x5/0x5f
>> [ 3029.668853] process_one_work+0x17e/0x330
>> [ 3029.668861] worker_thread+0x2ce/0x3f0
>> [ 3029.668868] ? __pfx_worker_thread+0x10/0x10
>> [ 3029.668873] kthread+0xd2/0x100
>> [ 3029.668879] ? __pfx_kthread+0x10/0x10
>> [ 3029.668885] ret_from_fork+0x34/0x50
>> [ 3029.668892] ? __pfx_kthread+0x10/0x10
>> [ 3029.668898] ret_from_fork_asm+0x1a/0x30
>> [ 3029.668910] </TASK>
>>
>> Tested-on: QCNFA765 WLAN.HSP.1.1-03926.13-
>> QCAHSPSWPL_V2_SILICONZ_CE-2.52297.6
>>
>> Signed-off-by: Muhammad Usama Anjum <usama.anjum@xxxxxxxxxxxxx>
>> ---
>> Changes sice v1:
>> - Don't free bhie tables during suspend/hibernation only
>> - Handle fbc_image changed size correctly
>> - Remove fbc_image getting set to NULL in *free_bhie_table()
>> ---
>> drivers/bus/mhi/host/boot.c | 15 +++++++++++----
>> drivers/bus/mhi/host/init.c | 13 ++++++++++---
>> drivers/net/wireless/ath/ath11k/mhi.c | 9 +++++----
>> include/linux/mhi.h | 7 +++++++
>> 4 files changed, 33 insertions(+), 11 deletions(-)
>>
>> diff --git a/drivers/bus/mhi/host/boot.c b/drivers/bus/mhi/host/boot.c
>> index 9dcc7184817d5..0df26100c8f9c 100644
>> --- a/drivers/bus/mhi/host/boot.c
>> +++ b/drivers/bus/mhi/host/boot.c
>> @@ -487,10 +487,17 @@ void mhi_fw_load_handler(struct mhi_controller
>> *mhi_cntrl)
>> * device transitioning into MHI READY state
>> */
>> if (mhi_cntrl->fbc_download) {
>> - ret = mhi_alloc_bhie_table(mhi_cntrl, &mhi_cntrl->fbc_image,
>> fw_sz);
>> - if (ret) {
>> - release_firmware(firmware);
>> - goto error_fw_load;
>> + if (mhi_cntrl->fbc_image && fw_sz != mhi_cntrl->prev_fw_sz) {
>> + mhi_free_bhie_table(mhi_cntrl, mhi_cntrl->fbc_image);
>> + mhi_cntrl->fbc_image = NULL;
>> + }
>> + if (!mhi_cntrl->fbc_image) {
>> + ret = mhi_alloc_bhie_table(mhi_cntrl, &mhi_cntrl-
>> >fbc_image, fw_sz);
>> + if (ret) {
>> + release_firmware(firmware);
>> + goto error_fw_load;
>> + }
>> + mhi_cntrl->prev_fw_sz = fw_sz;
>> }
>> /* Load the firmware into BHIE vec table */
>> diff --git a/drivers/bus/mhi/host/init.c b/drivers/bus/mhi/host/init.c
>> index a9b1f8beee7bc..09b946b86ac46 100644
>> --- a/drivers/bus/mhi/host/init.c
>> +++ b/drivers/bus/mhi/host/init.c
>> @@ -1173,8 +1173,9 @@ int mhi_prepare_for_power_up(struct
>> mhi_controller *mhi_cntrl)
>> /*
>> * Allocate RDDM table for debugging purpose if specified
>> */
>> - mhi_alloc_bhie_table(mhi_cntrl, &mhi_cntrl->rddm_image,
>> - mhi_cntrl->rddm_size);
>> + if (!mhi_cntrl->rddm_image)
>> + mhi_alloc_bhie_table(mhi_cntrl, &mhi_cntrl->rddm_image,
>> + mhi_cntrl->rddm_size);
>> if (mhi_cntrl->rddm_image) {
>> ret = mhi_rddm_prepare(mhi_cntrl,
>> mhi_cntrl->rddm_image);
>> @@ -1212,12 +1213,18 @@ void mhi_unprepare_after_power_down(struct
>> mhi_controller *mhi_cntrl)
>> mhi_cntrl->rddm_image = NULL;
>> }
>> + mhi_partial_unprepare_after_power_down(mhi_cntrl);
>> +}
>> +EXPORT_SYMBOL_GPL(mhi_unprepare_after_power_down);
>> +
>> +void mhi_partial_unprepare_after_power_down(struct mhi_controller
>> *mhi_cntrl)
>> +{
>> mhi_cntrl->bhi = NULL;
>> mhi_cntrl->bhie = NULL;
>> mhi_deinit_dev_ctxt(mhi_cntrl);
>> }
>> -EXPORT_SYMBOL_GPL(mhi_unprepare_after_power_down);
>> +EXPORT_SYMBOL_GPL(mhi_partial_unprepare_after_power_down);
>>
> Instead of adding new API you can free memory from the unregister
> controller also.
>
> - Krishna Chaitanya.
>> static void mhi_release_device(struct device *dev)
>> {
>> diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/
>> wireless/ath/ath11k/mhi.c
>> index acd76e9392d31..f77cec79b5b80 100644
>> --- a/drivers/net/wireless/ath/ath11k/mhi.c
>> +++ b/drivers/net/wireless/ath/ath11k/mhi.c
>> @@ -460,12 +460,13 @@ void ath11k_mhi_stop(struct ath11k_pci *ab_pci,
>> bool is_suspend)
>> * workaround, otherwise ath11k_core_resume() will timeout
>> * during resume.
>> */
>> - if (is_suspend)
>> + if (is_suspend) {
>> mhi_power_down_keep_dev(ab_pci->mhi_ctrl, true);
>> - else
>> + mhi_partial_unprepare_after_power_down(ab_pci->mhi_ctrl);
>> + } else {
>> mhi_power_down(ab_pci->mhi_ctrl, true);
>> -
>> - mhi_unprepare_after_power_down(ab_pci->mhi_ctrl);
>> + mhi_unprepare_after_power_down(ab_pci->mhi_ctrl);
>> + }
>> }
>> int ath11k_mhi_suspend(struct ath11k_pci *ab_pci)
>> diff --git a/include/linux/mhi.h b/include/linux/mhi.h
>> index 059dc94d20bb6..65a47c712b3a0 100644
>> --- a/include/linux/mhi.h
>> +++ b/include/linux/mhi.h
>> @@ -382,6 +382,7 @@ struct mhi_controller {
>> const char *fw_image;
>> const u8 *fw_data;
>> size_t fw_sz;
>> + size_t prev_fw_sz;
>> const char *edl_image;
>> size_t rddm_size;
>> size_t sbl_size;
>> @@ -662,6 +663,12 @@ void mhi_power_down_keep_dev(struct
>> mhi_controller *mhi_cntrl, bool graceful);
>> */
>> void mhi_unprepare_after_power_down(struct mhi_controller *mhi_cntrl);
>> +/**
>> + * mhi_partial_unprepare_after_power_down - Free any allocated memory
>> after power down partially
>> + * @mhi_cntrl: MHI controller
>> + */
>> +void mhi_partial_unprepare_after_power_down(struct mhi_controller
>> *mhi_cntrl);
>> +
>> /**
>> * mhi_pm_suspend - Move MHI into a suspended state
>> * @mhi_cntrl: MHI controller
--
Regards,
Usama
