June 2025 - Linux-stable-mirror

[PATCH v3 01/11] platform/x86/intel: refactor endpoint usage

by Michael J. Ruhl

The use of an endpoint has introduced a dependency in all class/pmt drivers to have an endpoint allocated. The telemetry driver has this allocation, the crashlog does not. The current usage is very telemetry focused, but should be common code. With this in mind: rename the struct telemetry_endpoint to struct class_endpoint, refactor the common endpoint code to be in the class.c module Fixes: 416eeb2e1fc7 ("platform/x86/intel/pmt: telemetry: Export API to read telemetry") Cc: <stable(a)vger.kernel.org> Signed-off-by: Michael J. Ruhl <michael.j.ruhl(a)intel.com> --- drivers/platform/x86/intel/pmc/core.c | 3 +- drivers/platform/x86/intel/pmc/core.h | 4 +- drivers/platform/x86/intel/pmc/core_ssram.c | 2 +- drivers/platform/x86/intel/pmt/class.c | 45 ++++++++++++++++++ drivers/platform/x86/intel/pmt/class.h | 21 +++++++-- drivers/platform/x86/intel/pmt/telemetry.c | 51 ++++----------------- drivers/platform/x86/intel/pmt/telemetry.h | 23 ++++------ 7 files changed, 84 insertions(+), 65 deletions(-) diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 7a1d11f2914f..805f56665d1d 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -29,6 +29,7 @@ #include <asm/tsc.h> #include "core.h" +#include "../pmt/class.h" #include "../pmt/telemetry.h" /* Maximum number of modes supported by platfoms that has low power mode capability */ @@ -1198,7 +1199,7 @@ int get_primary_reg_base(struct pmc *pmc) void pmc_core_punit_pmt_init(struct pmc_dev *pmcdev, u32 guid) { - struct telem_endpoint *ep; + struct class_endpoint *ep; struct pci_dev *pcidev; pcidev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(10, 0)); diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h index 945a1c440cca..1c12ea7c3ce3 100644 --- a/drivers/platform/x86/intel/pmc/core.h +++ b/drivers/platform/x86/intel/pmc/core.h @@ -16,7 +16,7 @@ #include <linux/bits.h> #include <linux/platform_device.h> -struct telem_endpoint; +struct class_endpoint; #define SLP_S0_RES_COUNTER_MASK GENMASK(31, 0) @@ -432,7 +432,7 @@ struct pmc_dev { bool has_die_c6; u32 die_c6_offset; - struct telem_endpoint *punit_ep; + struct class_endpoint *punit_ep; struct pmc_info *regmap_list; }; diff --git a/drivers/platform/x86/intel/pmc/core_ssram.c b/drivers/platform/x86/intel/pmc/core_ssram.c index 739569803017..3e670fc380a5 100644 --- a/drivers/platform/x86/intel/pmc/core_ssram.c +++ b/drivers/platform/x86/intel/pmc/core_ssram.c @@ -42,7 +42,7 @@ static u32 pmc_core_find_guid(struct pmc_info *list, const struct pmc_reg_map *m static int pmc_core_get_lpm_req(struct pmc_dev *pmcdev, struct pmc *pmc) { - struct telem_endpoint *ep; + struct class_endpoint *ep; const u8 *lpm_indices; int num_maps, mode_offset = 0; int ret, mode; diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c index 7233b654bbad..bba552131bc2 100644 --- a/drivers/platform/x86/intel/pmt/class.c +++ b/drivers/platform/x86/intel/pmt/class.c @@ -76,6 +76,47 @@ int pmt_telem_read_mmio(struct pci_dev *pdev, struct pmt_callbacks *cb, u32 guid } EXPORT_SYMBOL_NS_GPL(pmt_telem_read_mmio, "INTEL_PMT"); +/* Called when all users unregister and the device is removed */ +static void pmt_class_ep_release(struct kref *kref) +{ + struct class_endpoint *ep; + + ep = container_of(kref, struct class_endpoint, kref); + kfree(ep); +} + +void intel_pmt_release_endpoint(struct class_endpoint *ep) +{ + kref_put(&ep->kref, pmt_class_ep_release); +} +EXPORT_SYMBOL_NS_GPL(intel_pmt_release_endpoint, "INTEL_PMT"); + +int intel_pmt_add_endpoint(struct intel_vsec_device *ivdev, + struct intel_pmt_entry *entry) +{ + struct class_endpoint *ep; + + ep = kzalloc(sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->pcidev = ivdev->pcidev; + ep->header.access_type = entry->header.access_type; + ep->header.guid = entry->header.guid; + ep->header.base_offset = entry->header.base_offset; + ep->header.size = entry->header.size; + ep->base = entry->base; + ep->present = true; + ep->cb = ivdev->priv_data; + + /* Endpoint lifetimes are managed by kref, not devres */ + kref_init(&ep->kref); + + entry->ep = ep; + + return 0; +} +EXPORT_SYMBOL_NS_GPL(intel_pmt_add_endpoint, "INTEL_PMT"); /* * sysfs */ @@ -97,6 +138,10 @@ intel_pmt_read(struct file *filp, struct kobject *kobj, if (count > entry->size - off) count = entry->size - off; + /* verify endpoint is available */ + if (!entry->ep) + return -ENODEV; + count = pmt_telem_read_mmio(entry->ep->pcidev, entry->cb, entry->header.guid, buf, entry->base, off, count); diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h index b2006d57779d..d2d8f9e31c9d 100644 --- a/drivers/platform/x86/intel/pmt/class.h +++ b/drivers/platform/x86/intel/pmt/class.h @@ -9,8 +9,6 @@ #include <linux/err.h> #include <linux/io.h> -#include "telemetry.h" - /* PMT access types */ #define ACCESS_BARID 2 #define ACCESS_LOCAL 3 @@ -19,11 +17,19 @@ #define GET_BIR(v) ((v) & GENMASK(2, 0)) #define GET_ADDRESS(v) ((v) & GENMASK(31, 3)) +struct kref; struct pci_dev; -struct telem_endpoint { +struct class_header { + u8 access_type; + u16 size; + u32 guid; + u32 base_offset; +}; + +struct class_endpoint { struct pci_dev *pcidev; - struct telem_header header; + struct class_header header; struct pmt_callbacks *cb; void __iomem *base; bool present; @@ -38,7 +44,7 @@ struct intel_pmt_header { }; struct intel_pmt_entry { - struct telem_endpoint *ep; + struct class_endpoint *ep; struct intel_pmt_header header; struct bin_attribute pmt_bin_attr; struct kobject *kobj; @@ -69,4 +75,9 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry, struct intel_vsec_device *dev, int idx); void intel_pmt_dev_destroy(struct intel_pmt_entry *entry, struct intel_pmt_namespace *ns); + +int intel_pmt_add_endpoint(struct intel_vsec_device *ivdev, + struct intel_pmt_entry *entry); +void intel_pmt_release_endpoint(struct class_endpoint *ep); + #endif diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c index ac3a9bdf5601..27d09867e6a3 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.c +++ b/drivers/platform/x86/intel/pmt/telemetry.c @@ -18,6 +18,7 @@ #include <linux/overflow.h> #include "class.h" +#include "telemetry.h" #define TELEM_SIZE_OFFSET 0x0 #define TELEM_GUID_OFFSET 0x4 @@ -93,48 +94,14 @@ static int pmt_telem_header_decode(struct intel_pmt_entry *entry, return 0; } -static int pmt_telem_add_endpoint(struct intel_vsec_device *ivdev, - struct intel_pmt_entry *entry) -{ - struct telem_endpoint *ep; - - /* Endpoint lifetimes are managed by kref, not devres */ - entry->ep = kzalloc(sizeof(*(entry->ep)), GFP_KERNEL); - if (!entry->ep) - return -ENOMEM; - - ep = entry->ep; - ep->pcidev = ivdev->pcidev; - ep->header.access_type = entry->header.access_type; - ep->header.guid = entry->header.guid; - ep->header.base_offset = entry->header.base_offset; - ep->header.size = entry->header.size; - ep->base = entry->base; - ep->present = true; - ep->cb = ivdev->priv_data; - - kref_init(&ep->kref); - - return 0; -} - static DEFINE_XARRAY_ALLOC(telem_array); static struct intel_pmt_namespace pmt_telem_ns = { .name = "telem", .xa = &telem_array, .pmt_header_decode = pmt_telem_header_decode, - .pmt_add_endpoint = pmt_telem_add_endpoint, + .pmt_add_endpoint = intel_pmt_add_endpoint, }; -/* Called when all users unregister and the device is removed */ -static void pmt_telem_ep_release(struct kref *kref) -{ - struct telem_endpoint *ep; - - ep = container_of(kref, struct telem_endpoint, kref); - kfree(ep); -} - unsigned long pmt_telem_get_next_endpoint(unsigned long start) { struct intel_pmt_entry *entry; @@ -155,7 +122,7 @@ unsigned long pmt_telem_get_next_endpoint(unsigned long start) } EXPORT_SYMBOL_NS_GPL(pmt_telem_get_next_endpoint, "INTEL_PMT_TELEMETRY"); -struct telem_endpoint *pmt_telem_register_endpoint(int devid) +struct class_endpoint *pmt_telem_register_endpoint(int devid) { struct intel_pmt_entry *entry; unsigned long index = devid; @@ -174,9 +141,9 @@ struct telem_endpoint *pmt_telem_register_endpoint(int devid) } EXPORT_SYMBOL_NS_GPL(pmt_telem_register_endpoint, "INTEL_PMT_TELEMETRY"); -void pmt_telem_unregister_endpoint(struct telem_endpoint *ep) +void pmt_telem_unregister_endpoint(struct class_endpoint *ep) { - kref_put(&ep->kref, pmt_telem_ep_release); + intel_pmt_release_endpoint(ep); } EXPORT_SYMBOL_NS_GPL(pmt_telem_unregister_endpoint, "INTEL_PMT_TELEMETRY"); @@ -206,7 +173,7 @@ int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info) } EXPORT_SYMBOL_NS_GPL(pmt_telem_get_endpoint_info, "INTEL_PMT_TELEMETRY"); -int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count) +int pmt_telem_read(struct class_endpoint *ep, u32 id, u64 *data, u32 count) { u32 offset, size; @@ -226,7 +193,7 @@ int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count) } EXPORT_SYMBOL_NS_GPL(pmt_telem_read, "INTEL_PMT_TELEMETRY"); -int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count) +int pmt_telem_read32(struct class_endpoint *ep, u32 id, u32 *data, u32 count) { u32 offset, size; @@ -245,7 +212,7 @@ int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count) } EXPORT_SYMBOL_NS_GPL(pmt_telem_read32, "INTEL_PMT_TELEMETRY"); -struct telem_endpoint * +struct class_endpoint * pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, u32 guid, u16 pos) { int devid = 0; @@ -279,7 +246,7 @@ static void pmt_telem_remove(struct auxiliary_device *auxdev) for (i = 0; i < priv->num_entries; i++) { struct intel_pmt_entry *entry = &priv->entry[i]; - kref_put(&entry->ep->kref, pmt_telem_ep_release); + pmt_telem_unregister_endpoint(entry->ep); intel_pmt_dev_destroy(entry, &pmt_telem_ns); } mutex_unlock(&ep_lock); diff --git a/drivers/platform/x86/intel/pmt/telemetry.h b/drivers/platform/x86/intel/pmt/telemetry.h index d45af5512b4e..e987dd32a58a 100644 --- a/drivers/platform/x86/intel/pmt/telemetry.h +++ b/drivers/platform/x86/intel/pmt/telemetry.h @@ -2,6 +2,8 @@ #ifndef _TELEMETRY_H #define _TELEMETRY_H +#include "class.h" + /* Telemetry types */ #define PMT_TELEM_TELEMETRY 0 #define PMT_TELEM_CRASHLOG 1 @@ -9,16 +11,9 @@ struct telem_endpoint; struct pci_dev; -struct telem_header { - u8 access_type; - u16 size; - u32 guid; - u32 base_offset; -}; - struct telem_endpoint_info { struct pci_dev *pdev; - struct telem_header header; + struct class_header header; }; /** @@ -47,7 +42,7 @@ unsigned long pmt_telem_get_next_endpoint(unsigned long start); * * endpoint - On success returns pointer to the telemetry endpoint * * -ENXIO - telemetry endpoint not found */ -struct telem_endpoint *pmt_telem_register_endpoint(int devid); +struct class_endpoint *pmt_telem_register_endpoint(int devid); /** * pmt_telem_unregister_endpoint() - Unregister a telemetry endpoint @@ -55,7 +50,7 @@ struct telem_endpoint *pmt_telem_register_endpoint(int devid); * * Decrements the kref usage counter for the endpoint. */ -void pmt_telem_unregister_endpoint(struct telem_endpoint *ep); +void pmt_telem_unregister_endpoint(struct class_endpoint *ep); /** * pmt_telem_get_endpoint_info() - Get info for an endpoint from its devid @@ -80,8 +75,8 @@ int pmt_telem_get_endpoint_info(int devid, struct telem_endpoint_info *info); * * endpoint - On success returns pointer to the telemetry endpoint * * -ENXIO - telemetry endpoint not found */ -struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, - u32 guid, u16 pos); +struct class_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcidev, + u32 guid, u16 pos); /** * pmt_telem_read() - Read qwords from counter sram using sample id @@ -101,7 +96,7 @@ struct telem_endpoint *pmt_telem_find_and_register_endpoint(struct pci_dev *pcid * * -EPIPE - The device was removed during the read. Data written * but should be considered invalid. */ -int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count); +int pmt_telem_read(struct class_endpoint *ep, u32 id, u64 *data, u32 count); /** * pmt_telem_read32() - Read qwords from counter sram using sample id @@ -121,6 +116,6 @@ int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count); * * -EPIPE - The device was removed during the read. Data written * but should be considered invalid. */ -int pmt_telem_read32(struct telem_endpoint *ep, u32 id, u32 *data, u32 count); +int pmt_telem_read32(struct class_endpoint *ep, u32 id, u32 *data, u32 count); #endif -- 2.49.0

2 weeks, 6 days

1
0
0 0

[PATCH net] gve: Fix stuck TX queue for DQ queue format

by Harshitha Ramamurthy

From: Praveen Kaligineedi <pkaligineedi(a)google.com> gve_tx_timeout was calculating missed completions in a way that is only relevant in the GQ queue format. Additionally, it was attempting to disable device interrupts, which is not needed in either GQ or DQ queue formats. As a result, TX timeouts with the DQ queue format likely would have triggered early resets without kicking the queue at all. This patch drops the check for pending work altogether and always kicks the queue after validating the queue has not seen a TX timeout too recently. Fixes: 87a7f321bb6a ("gve: Recover from queue stall due to missed IRQ") Co-developed-by: Tim Hostetler <thostet(a)google.com> Signed-off-by: Tim Hostetler <thostet(a)google.com> Signed-off-by: Praveen Kaligineedi <pkaligineedi(a)google.com> Signed-off-by: Harshitha Ramamurthy <hramamurthy(a)google.com> --- drivers/net/ethernet/google/gve/gve_main.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index c3791cf..0c6328b 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1921,7 +1921,6 @@ static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) struct gve_notify_block *block; struct gve_tx_ring *tx = NULL; struct gve_priv *priv; - u32 last_nic_done; u32 current_time; u32 ntfy_idx; @@ -1941,17 +1940,10 @@ static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) goto reset; - /* Check to see if there are missed completions, which will allow us to - * kick the queue. - */ - last_nic_done = gve_tx_load_event_counter(priv, tx); - if (last_nic_done - tx->done) { - netdev_info(dev, "Kicking queue %d", txqueue); - iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); - napi_schedule(&block->napi); - tx->last_kick_msec = current_time; - goto out; - } // Else reset. + netdev_info(dev, "Kicking queue %d", txqueue); + napi_schedule(&block->napi); + tx->last_kick_msec = current_time; + goto out; reset: gve_schedule_reset(priv); -- 2.49.0.805.g082f7c87e0-goog

2 weeks, 6 days

4
3
0 0

[PATCH] accel/ivpu: Reorder doorbell unregister and command queue destruction

by Maciej Falkowski

From: Karol Wachowski <karol.wachowski(a)intel.com> Refactor ivpu_cmdq_unregister() to ensure the doorbell is unregistered before destroying the command queue. The NPU firmware requires doorbells to be unregistered prior to command queue destruction. If doorbell remains registered when command queue destroy command is sent firmware will automatically unregister the doorbell, making subsequent unregister attempts no-operations (NOPs). Ensure compliance with firmware expectations by moving the doorbell unregister call ahead of the command queue destruction logic, thus preventing unnecessary NOP operation. Fixes: 2a18ceff9482 ("accel/ivpu: Implement support for hardware scheduler") Cc: <stable(a)vger.kernel.org> # v6.11+ Signed-off-by: Karol Wachowski <karol.wachowski(a)intel.com> Signed-off-by: Maciej Falkowski <maciej.falkowski(a)linux.intel.com> --- drivers/accel/ivpu/ivpu_job.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index bd351dd46d6b..060f1fc031d3 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -271,6 +271,10 @@ static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cm if (!cmdq->db_id) return 0; + ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id); + if (!ret) + ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id); + if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) { ret = ivpu_jsm_hws_destroy_cmdq(vdev, file_priv->ctx.id, cmdq->id); if (!ret) @@ -278,10 +282,6 @@ static int ivpu_cmdq_unregister(struct ivpu_file_priv *file_priv, struct ivpu_cm cmdq->id, file_priv->ctx.id); } - ret = ivpu_jsm_unregister_db(vdev, cmdq->db_id); - if (!ret) - ivpu_dbg(vdev, JOB, "DB %d unregistered\n", cmdq->db_id); - xa_erase(&file_priv->vdev->db_xa, cmdq->db_id); cmdq->db_id = 0; -- 2.43.0

2 weeks, 6 days

3
2
0 0

[PATCH 1/2] dmaengine: qcom_hidma: fix memory leak on probe failure

by Qasim Ijaz

hidma_ll_init() is invoked to create and initialise a struct hidma_lldev object during hidma probe. During this a FIFO buffer is allocated, but if some failure occurs after (like hidma_ll_setup failure) we should clean up the FIFO. Fixes: d1615ca2e085 ("dmaengine: qcom_hidma: implement lower level hardware interface") Cc: stable(a)vger.kernel.org Signed-off-by: Qasim Ijaz <qasdev00(a)gmail.com> --- drivers/dma/qcom/hidma_ll.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c index 53244e0e34a3..fee448499777 100644 --- a/drivers/dma/qcom/hidma_ll.c +++ b/drivers/dma/qcom/hidma_ll.c @@ -788,8 +788,10 @@ struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres, return NULL; rc = hidma_ll_setup(lldev); - if (rc) + if (rc) { + kfifo_free(&lldev->handoff_fifo); return NULL; + } spin_lock_init(&lldev->lock); tasklet_setup(&lldev->task, hidma_ll_tre_complete); -- 2.39.5

2 weeks, 6 days

2
1
0 0

[PATCH 6.12] Revert "cpufreq: tegra186: Share policy per cluster"

by Jon Hunter

This reverts commit d95fdee2253e612216e72f29c65b92ec42d254eb which is upstream commit be4ae8c19492cd6d5de61ccb34ffb3f5ede5eec8. This commit is causing a suspend regression on Tegra186 Jetson TX2 with Linux v6.12.y kernels. This is not seen with Linux v6.15 that includes this change but indicates that there are there changes missing. Therefore, revert this change. Fixes: d95fdee2253e ("cpufreq: tegra186: Share policy per cluster") Link: https://lore.kernel.org/linux-tegra/bf1dabf7-0337-40e9-8b8e-4e93a0ffd4cc@nv… Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- drivers/cpufreq/tegra186-cpufreq.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 4e5b6f9a56d1..7b8fcfa55038 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,18 +73,11 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; - u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; - /* set same policy for all cpus in a cluster */ - for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { - if (data->cpus[cpu].bpmp_cluster_id == cluster) - cpumask_set_cpu(cpu, policy->cpus); - } - return 0; } -- 2.43.0

2 weeks, 6 days

1
0
0 0

[PATCH 6.1] Revert "cpufreq: tegra186: Share policy per cluster"

by Jon Hunter

This reverts commit 89172666228de1cefcacf5bc6f61c6281751d2ed which is upstream commit be4ae8c19492cd6d5de61ccb34ffb3f5ede5eec8. This commit is causing a suspend regression on Tegra186 Jetson TX2 with Linux v6.12.y kernels. This is not seen with Linux v6.15 that includes this change but indicates that there are there changes missing. Therefore, revert this change. Link: https://lore.kernel.org/linux-tegra/bf1dabf7-0337-40e9-8b8e-4e93a0ffd4cc@nv… Fixes: 89172666228d ("cpufreq: tegra186: Share policy per cluster") Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- drivers/cpufreq/tegra186-cpufreq.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 1d6b54303723..6c88827f4e62 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,18 +73,11 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; - u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; - /* set same policy for all cpus in a cluster */ - for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { - if (data->cpus[cpu].bpmp_cluster_id == cluster) - cpumask_set_cpu(cpu, policy->cpus); - } - return 0; } -- 2.43.0

2 weeks, 6 days

1
0
0 0

[PATCH 5.15] Revert "cpufreq: tegra186: Share policy per cluster"

by Jon Hunter

This reverts commit 2592aeda794c9ea73193effdab69f1cf90d0851a which is upstream commit be4ae8c19492cd6d5de61ccb34ffb3f5ede5eec8. This commit is causing a suspend regression on Tegra186 Jetson TX2 with Linux v6.12.y kernels. This is not seen with Linux v6.15 that includes this change but indicates that there are there changes missing. Therefore, revert this change. Fixes: 2592aeda794c ("cpufreq: tegra186: Share policy per cluster") Link: https://lore.kernel.org/linux-tegra/bf1dabf7-0337-40e9-8b8e-4e93a0ffd4cc@nv… Signed-off-by: Jon Hunter <jonathanh(a)nvidia.com> --- drivers/cpufreq/tegra186-cpufreq.c | 7 ------- 1 file changed, 7 deletions(-) diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c index 19597246f9cc..5d1943e787b0 100644 --- a/drivers/cpufreq/tegra186-cpufreq.c +++ b/drivers/cpufreq/tegra186-cpufreq.c @@ -73,18 +73,11 @@ static int tegra186_cpufreq_init(struct cpufreq_policy *policy) { struct tegra186_cpufreq_data *data = cpufreq_get_driver_data(); unsigned int cluster = data->cpus[policy->cpu].bpmp_cluster_id; - u32 cpu; policy->freq_table = data->clusters[cluster].table; policy->cpuinfo.transition_latency = 300 * 1000; policy->driver_data = NULL; - /* set same policy for all cpus in a cluster */ - for (cpu = 0; cpu < ARRAY_SIZE(tegra186_cpus); cpu++) { - if (data->cpus[cpu].bpmp_cluster_id == cluster) - cpumask_set_cpu(cpu, policy->cpus); - } - return 0; } -- 2.43.0

2 weeks, 6 days

1
0
0 0

[PATCH v2] accel/ivpu: Fix warning in ivpu_gem_bo_free()

by Jacek Lawrynowicz

Don't WARN if imported buffers are in use in ivpu_gem_bo_free() as they can be indeed used in the original context/driver. Fixes: 647371a6609d ("accel/ivpu: Add GEM buffer object management") Cc: stable(a)vger.kernel.org # v6.3 Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- v2: Use drm_gem_is_imported() to check if the buffer is imported. --- drivers/accel/ivpu/ivpu_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index c193a80241f5f..5ff0bac739fc9 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -278,7 +278,8 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) list_del(&bo->bo_list_node); mutex_unlock(&vdev->bo_list_lock); - drm_WARN_ON(&vdev->drm, !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); + drm_WARN_ON(&vdev->drm, !drm_gem_is_imported(&bo->base.base) && + !dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)); drm_WARN_ON(&vdev->drm, ivpu_bo_size(bo) == 0); drm_WARN_ON(&vdev->drm, bo->base.vaddr); -- 2.45.1

2 weeks, 6 days

3
3
0 0

[PATCH] accel/ivpu: Trigger device recovery on engine reset/resume failure

by Jacek Lawrynowicz

From: Karol Wachowski <karol.wachowski(a)intel.com> Trigger full device recovery when the driver fails to restore device state via engine reset and resume operations. This is necessary because, even if submissions from a faulty context are blocked, the NPU may still process previously submitted faulty jobs if the engine reset fails to abort them. Such jobs can continue to generate faults and occupy device resources. When engine reset is ineffective, the only way to recover is to perform a full device recovery. Fixes: dad945c27a42 ("accel/ivpu: Add handling of VPU_JSM_STATUS_MVNCI_CONTEXT_VIOLATION_HW") Cc: <stable(a)vger.kernel.org> # v6.15+ Signed-off-by: Karol Wachowski <karol.wachowski(a)intel.com> Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- drivers/accel/ivpu/ivpu_job.c | 6 ++++-- drivers/accel/ivpu/ivpu_jsm_msg.c | 9 +++++++-- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_job.c b/drivers/accel/ivpu/ivpu_job.c index 1c8e283ad9854..fae8351aa3309 100644 --- a/drivers/accel/ivpu/ivpu_job.c +++ b/drivers/accel/ivpu/ivpu_job.c @@ -986,7 +986,8 @@ void ivpu_context_abort_work_fn(struct work_struct *work) return; if (vdev->fw->sched_mode == VPU_SCHEDULING_MODE_HW) - ivpu_jsm_reset_engine(vdev, 0); + if (ivpu_jsm_reset_engine(vdev, 0)) + return; mutex_lock(&vdev->context_list_lock); xa_for_each(&vdev->context_xa, ctx_id, file_priv) { @@ -1009,7 +1010,8 @@ void ivpu_context_abort_work_fn(struct work_struct *work) if (vdev->fw->sched_mode != VPU_SCHEDULING_MODE_HW) goto runtime_put; - ivpu_jsm_hws_resume_engine(vdev, 0); + if (ivpu_jsm_hws_resume_engine(vdev, 0)) + return; /* * In hardware scheduling mode NPU already has stopped processing jobs * and won't send us any further notifications, thus we have to free job related resources diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c index 219ab8afefabd..0256b2dfefc10 100644 --- a/drivers/accel/ivpu/ivpu_jsm_msg.c +++ b/drivers/accel/ivpu/ivpu_jsm_msg.c @@ -7,6 +7,7 @@ #include "ivpu_hw.h" #include "ivpu_ipc.h" #include "ivpu_jsm_msg.h" +#include "ivpu_pm.h" #include "vpu_jsm_api.h" const char *ivpu_jsm_msg_type_to_str(enum vpu_ipc_msg_type type) @@ -163,8 +164,10 @@ int ivpu_jsm_reset_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_ENGINE_RESET_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to reset engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine reset failed"); + } return ret; } @@ -354,8 +357,10 @@ int ivpu_jsm_hws_resume_engine(struct ivpu_device *vdev, u32 engine) ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_HWS_RESUME_ENGINE_DONE, &resp, VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm); - if (ret) + if (ret) { ivpu_err_ratelimited(vdev, "Failed to resume engine %d: %d\n", engine, ret); + ivpu_pm_trigger_recovery(vdev, "Engine resume failed"); + } return ret; } -- 2.45.1

2 weeks, 6 days

2
4
0 0

[PATCH] accel/ivpu: Use dma_resv_lock() instead of a custom mutex

by Jacek Lawrynowicz

This fixes a potential race conditions in: - ivpu_bo_unbind_locked() where we modified the shmem->sgt without holding the dma_resv_lock(). - ivpu_bo_print_info() where we read the shmem->pages without holding the dma_resv_lock(). Using dma_resv_lock() also protects against future syncronisation issues that may arise when accessing drm_gem_shmem_object or drm_gem_object members. Fixes: 42328003ecb6 ("accel/ivpu: Refactor BO creation functions") Cc: <stable(a)vger.kernel.org> # v6.9+ Signed-off-by: Jacek Lawrynowicz <jacek.lawrynowicz(a)linux.intel.com> --- drivers/accel/ivpu/ivpu_gem.c | 63 +++++++++++++++++++---------------- drivers/accel/ivpu/ivpu_gem.h | 1 - 2 files changed, 34 insertions(+), 30 deletions(-) diff --git a/drivers/accel/ivpu/ivpu_gem.c b/drivers/accel/ivpu/ivpu_gem.c index c193a80241f5f..5908268ca45e9 100644 --- a/drivers/accel/ivpu/ivpu_gem.c +++ b/drivers/accel/ivpu/ivpu_gem.c @@ -33,6 +33,16 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con (bool)bo->base.base.import_attach); } +static inline int ivpu_bo_lock(struct ivpu_bo *bo) +{ + return dma_resv_lock(bo->base.base.resv, NULL); +} + +static inline void ivpu_bo_unlock(struct ivpu_bo *bo) +{ + dma_resv_unlock(bo->base.base.resv); +} + /* * ivpu_bo_pin() - pin the backing physical pages and map them to VPU. * @@ -43,22 +53,22 @@ static inline void ivpu_dbg_bo(struct ivpu_device *vdev, struct ivpu_bo *bo, con int __must_check ivpu_bo_pin(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); + struct sg_table *sgt; int ret = 0; - mutex_lock(&bo->lock); - ivpu_dbg_bo(vdev, bo, "pin"); - drm_WARN_ON(&vdev->drm, !bo->ctx); - if (!bo->mmu_mapped) { - struct sg_table *sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + sgt = drm_gem_shmem_get_pages_sgt(&bo->base); + if (IS_ERR(sgt)) { + ret = PTR_ERR(sgt); + ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); + return ret; + } - if (IS_ERR(sgt)) { - ret = PTR_ERR(sgt); - ivpu_err(vdev, "Failed to map BO in IOMMU: %d\n", ret); - goto unlock; - } + ivpu_bo_lock(bo); + if (!bo->mmu_mapped) { + drm_WARN_ON(&vdev->drm, !bo->ctx); ret = ivpu_mmu_context_map_sgt(vdev, bo->ctx, bo->vpu_addr, sgt, ivpu_bo_is_snooped(bo)); if (ret) { @@ -69,7 +79,7 @@ int __must_check ivpu_bo_pin(struct ivpu_bo *bo) } unlock: - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); return ret; } @@ -84,7 +94,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, if (!drm_dev_enter(&vdev->drm, &idx)) return -ENODEV; - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); ret = ivpu_mmu_context_insert_node(ctx, range, ivpu_bo_size(bo), &bo->mm_node); if (!ret) { @@ -94,7 +104,7 @@ ivpu_bo_alloc_vpu_addr(struct ivpu_bo *bo, struct ivpu_mmu_context *ctx, ivpu_err(vdev, "Failed to add BO to context %u: %d\n", ctx->id, ret); } - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_dev_exit(idx); @@ -105,7 +115,7 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) { struct ivpu_device *vdev = ivpu_bo_to_vdev(bo); - lockdep_assert(lockdep_is_held(&bo->lock) || !kref_read(&bo->base.base.refcount)); + lockdep_assert(dma_resv_held(bo->base.base.resv) || !kref_read(&bo->base.base.refcount)); if (bo->mmu_mapped) { drm_WARN_ON(&vdev->drm, !bo->ctx); @@ -123,14 +133,12 @@ static void ivpu_bo_unbind_locked(struct ivpu_bo *bo) if (bo->base.base.import_attach) return; - dma_resv_lock(bo->base.base.resv, NULL); if (bo->base.sgt) { dma_unmap_sgtable(vdev->drm.dev, bo->base.sgt, DMA_BIDIRECTIONAL, 0); sg_free_table(bo->base.sgt); kfree(bo->base.sgt); bo->base.sgt = NULL; } - dma_resv_unlock(bo->base.base.resv); } void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx) @@ -142,12 +150,12 @@ void ivpu_bo_unbind_all_bos_from_context(struct ivpu_device *vdev, struct ivpu_m mutex_lock(&vdev->bo_list_lock); list_for_each_entry(bo, &vdev->bo_list, bo_list_node) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); if (bo->ctx == ctx) { ivpu_dbg_bo(vdev, bo, "unbind"); ivpu_bo_unbind_locked(bo); } - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } mutex_unlock(&vdev->bo_list_lock); } @@ -167,7 +175,6 @@ struct drm_gem_object *ivpu_gem_create_object(struct drm_device *dev, size_t siz bo->base.pages_mark_dirty_on_put = true; /* VPU can dirty a BO anytime */ INIT_LIST_HEAD(&bo->bo_list_node); - mutex_init(&bo->lock); return &bo->base.base; } @@ -286,8 +293,6 @@ static void ivpu_gem_bo_free(struct drm_gem_object *obj) drm_WARN_ON(&vdev->drm, bo->mmu_mapped); drm_WARN_ON(&vdev->drm, bo->ctx); - mutex_destroy(&bo->lock); - drm_WARN_ON(obj->dev, bo->base.pages_use_count > 1); drm_gem_shmem_free(&bo->base); } @@ -370,9 +375,9 @@ ivpu_bo_create(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, goto err_put; if (flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); ret = drm_gem_shmem_vmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); if (ret) goto err_put; @@ -395,9 +400,9 @@ void ivpu_bo_free(struct ivpu_bo *bo) struct iosys_map map = IOSYS_MAP_INIT_VADDR(bo->base.vaddr); if (bo->flags & DRM_IVPU_BO_MAPPABLE) { - dma_resv_lock(bo->base.base.resv, NULL); + ivpu_bo_lock(bo); drm_gem_shmem_vunmap(&bo->base, &map); - dma_resv_unlock(bo->base.base.resv); + ivpu_bo_unlock(bo); } drm_gem_object_put(&bo->base.base); @@ -416,12 +421,12 @@ int ivpu_bo_info_ioctl(struct drm_device *dev, void *data, struct drm_file *file bo = to_ivpu_bo(obj); - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); args->flags = bo->flags; args->mmap_offset = drm_vma_node_offset_addr(&obj->vma_node); args->vpu_addr = bo->vpu_addr; args->size = obj->size; - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); drm_gem_object_put(obj); return ret; @@ -458,7 +463,7 @@ int ivpu_bo_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) { - mutex_lock(&bo->lock); + ivpu_bo_lock(bo); drm_printf(p, "%-9p %-3u 0x%-12llx %-10lu 0x%-8x %-4u", bo, bo->ctx_id, bo->vpu_addr, bo->base.base.size, @@ -475,7 +480,7 @@ static void ivpu_bo_print_info(struct ivpu_bo *bo, struct drm_printer *p) drm_printf(p, "\n"); - mutex_unlock(&bo->lock); + ivpu_bo_unlock(bo); } void ivpu_bo_list(struct drm_device *dev, struct drm_printer *p) diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index 0c93118c85bd3..aa8ff14f7aae1 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -17,7 +17,6 @@ struct ivpu_bo { struct list_head bo_list_node; struct drm_mm_node mm_node; - struct mutex lock; /* Protects: ctx, mmu_mapped, vpu_addr */ u64 vpu_addr; u32 flags; u32 job_status; /* Valid only for command buffer */ -- 2.45.1

2 weeks, 6 days

2
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025