summaryrefslogtreecommitdiffstats
path: root/drivers/misc/habanalabs/common/habanalabs_drv.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 19:01:51 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 19:01:51 +0200
commit726eb70e0d34dc4bc4dada71f52bba8ed638431e (patch)
treee49674616f4513c8c6a4746a08e93c9441708d34 /drivers/misc/habanalabs/common/habanalabs_drv.c
parentMerge tag 'usb-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gre... (diff)
parentbinder: fix UAF when releasing todo list (diff)
downloadlinux-726eb70e0d34dc4bc4dada71f52bba8ed638431e.tar.xz
linux-726eb70e0d34dc4bc4dada71f52bba8ed638431e.zip
Merge tag 'char-misc-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char/misc driver updates from Greg KH: "Here is the big set of char, misc, and other assorted driver subsystem patches for 5.10-rc1. There's a lot of different things in here, all over the drivers/ directory. Some summaries: - soundwire driver updates - habanalabs driver updates - extcon driver updates - nitro_enclaves new driver - fsl-mc driver and core updates - mhi core and bus updates - nvmem driver updates - eeprom driver updates - binder driver updates and fixes - vbox minor bugfixes - fsi driver updates - w1 driver updates - coresight driver updates - interconnect driver updates - misc driver updates - other minor driver updates All of these have been in linux-next for a while with no reported issues" * tag 'char-misc-5.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (396 commits) binder: fix UAF when releasing todo list docs: w1: w1_therm: Fix broken xref, mistakes, clarify text misc: Kconfig: fix a HISI_HIKEY_USB dependency LSM: Fix type of id parameter in kernel_post_load_data prototype misc: Kconfig: add a new dependency for HISI_HIKEY_USB firmware_loader: fix a kernel-doc markup w1: w1_therm: make w1_poll_completion static binder: simplify the return expression of binder_mmap test_firmware: Test partial read support firmware: Add request_partial_firmware_into_buf() firmware: Store opt_flags in fw_priv fs/kernel_file_read: Add "offset" arg for partial reads IMA: Add support for file reads without contents LSM: Add "contents" flag to kernel_read_file hook module: Call security_kernel_post_load_data() firmware_loader: Use security_post_load_data() LSM: Introduce kernel_post_load_data() hook fs/kernel_read_file: Add file_size output argument fs/kernel_read_file: Switch buffer size arg to size_t fs/kernel_read_file: Remove redundant size argument ...
Diffstat (limited to 'drivers/misc/habanalabs/common/habanalabs_drv.c')
-rw-r--r--drivers/misc/habanalabs/common/habanalabs_drv.c76
1 files changed, 75 insertions, 1 deletions
diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
index c6b31e93fb5e..f9067d3ef437 100644
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -11,6 +11,7 @@
#include "habanalabs.h"
#include <linux/pci.h>
+#include <linux/aer.h>
#include <linux/module.h>
#define HL_DRIVER_AUTHOR "HabanaLabs Kernel Driver Team"
@@ -408,6 +409,8 @@ static int hl_pci_probe(struct pci_dev *pdev,
pci_set_drvdata(pdev, hdev);
+ pci_enable_pcie_error_reporting(pdev);
+
rc = hl_device_init(hdev, hl_class);
if (rc) {
dev_err(&pdev->dev, "Fatal error during habanalabs device init\n");
@@ -440,22 +443,93 @@ static void hl_pci_remove(struct pci_dev *pdev)
return;
hl_device_fini(hdev);
+ pci_disable_pcie_error_reporting(pdev);
pci_set_drvdata(pdev, NULL);
-
destroy_hdev(hdev);
}
+/**
+ * hl_pci_err_detected - a PCI bus error detected on this device
+ *
+ * @pdev: pointer to pci device
+ * @state: PCI error type
+ *
+ * Called by the PCI subsystem whenever a non-correctable
+ * PCI bus error is detected
+ */
+static pci_ers_result_t
+hl_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t state)
+{
+ struct hl_device *hdev = pci_get_drvdata(pdev);
+ enum pci_ers_result result;
+
+ switch (state) {
+ case pci_channel_io_normal:
+ return PCI_ERS_RESULT_CAN_RECOVER;
+
+ case pci_channel_io_frozen:
+ dev_warn(hdev->dev, "frozen state error detected\n");
+ result = PCI_ERS_RESULT_NEED_RESET;
+ break;
+
+ case pci_channel_io_perm_failure:
+ dev_warn(hdev->dev, "failure state error detected\n");
+ result = PCI_ERS_RESULT_DISCONNECT;
+ break;
+
+ default:
+ result = PCI_ERS_RESULT_NONE;
+ }
+
+ hdev->asic_funcs->halt_engines(hdev, true);
+
+ return result;
+}
+
+/**
+ * hl_pci_err_resume - resume after a PCI slot reset
+ *
+ * @pdev: pointer to pci device
+ *
+ */
+static void hl_pci_err_resume(struct pci_dev *pdev)
+{
+ struct hl_device *hdev = pci_get_drvdata(pdev);
+
+ dev_warn(hdev->dev, "Resuming device after PCI slot reset\n");
+ hl_device_resume(hdev);
+}
+
+/**
+ * hl_pci_err_slot_reset - a PCI slot reset has just happened
+ *
+ * @pdev: pointer to pci device
+ *
+ * Determine if the driver can recover from the PCI slot reset
+ */
+static pci_ers_result_t hl_pci_err_slot_reset(struct pci_dev *pdev)
+{
+ return PCI_ERS_RESULT_RECOVERED;
+}
+
static const struct dev_pm_ops hl_pm_ops = {
.suspend = hl_pmops_suspend,
.resume = hl_pmops_resume,
};
+static const struct pci_error_handlers hl_pci_err_handler = {
+ .error_detected = hl_pci_err_detected,
+ .slot_reset = hl_pci_err_slot_reset,
+ .resume = hl_pci_err_resume,
+};
+
static struct pci_driver hl_pci_driver = {
.name = HL_NAME,
.id_table = ids,
.probe = hl_pci_probe,
.remove = hl_pci_remove,
.driver.pm = &hl_pm_ops,
+ .err_handler = &hl_pci_err_handler,
};
/*