habanalabs: Use 'dma_set_mask_and_coherent()'
Subsystems (2)
PATCH 1/4 habanalabs: Use 'dma_set_mask_and_coherent()'
From: Christophe JAILLET <[email protected]>
Axe 'hl_pci_set_dma_mask()' and replace it with an equivalent 'dma_set_mask_and_coherent()' call.
This makes the code a bit less verbose.
It also removes an erroneous comment, because 'hl_pci_set_dma_mask()' does not try to use a fall-back value.
--- drivers/misc/habanalabs/common/pci/pci.c | 43 ++++-------------------- 1 file changed, 7 insertions(+), 36 deletions(-)
drivers/misc/habanalabs/common/pci/pci.c +7 -36
@@ -307,40 +307,6 @@ int hl_pci_set_outbound_region(struct hl_device *hdev,return rc; } -/** -* hl_pci_set_dma_mask() - Set DMA masks for the device. -* @hdev: Pointer to hl_device structure. -* -* This function sets the DMA masks (regular and consistent) for a specified -* value. If it doesn't succeed, it tries to set it to a fall-back value -* -* Return: 0 on success, non-zero for failure. -*/ -static int hl_pci_set_dma_mask (struct hl_device *hdev) -{ -struct pci_dev *pdev = hdev->pdev; -int rc; - -/* set DMA mask */ - rc =pci_set_dma_mask (pdev,DMA_BIT_MASK (hdev->dma_mask)); -if (rc) { -dev_err (hdev->dev, -"Failed to set pci dma mask to %d bits, error %d\n" , - hdev->dma_mask, rc); -return rc; - } - - rc =pci_set_consistent_dma_mask (pdev,DMA_BIT_MASK (hdev->dma_mask)); -if (rc) { -dev_err (hdev->dev, -"Failed to set pci consistent dma mask to %d bits, error %d\n" , - hdev->dma_mask, rc); -return rc; - } - -return 0 ; -} -/** * hl_pci_init() - PCI initialization code. * @hdev: Pointer to hl_device structure.
@@ -377,9 +343,14 @@ int hl_pci_init(struct hl_device *hdev) goto unmap_pci_bars; } - rc =hl_pci_set_dma_mask (hdev); -if (rc) + rc =dma_set_mask_and_coherent (&pdev->dev, +DMA_BIT_MASK (hdev->dma_mask)); +if (rc) { +dev_err (hdev->dev, +"Failed to set dma mask to %d bits, error %d\n" , + hdev->dma_mask, rc); goto unmap_pci_bars; + }return 0 ;
Signature · 1 line
2.25.1
PATCH 2/4 habanalabs/gaudi: print sync manager SEI interrupt info
From: Ofir Bitton <[email protected]>
Driver must print sync manager SEI information upon receiving interrupt from FW.
--- drivers/misc/habanalabs/gaudi/gaudi.c | 41 +++++++++++++++++++ .../misc/habanalabs/include/common/cpucp_if.h | 7 ++++ .../include/gaudi/gaudi_async_events.h | 4 ++ 3 files changed, 52 insertions(+)
drivers/misc/habanalabs/gaudi/gaudi.c +41 -0
@@ -225,6 +225,12 @@ gaudi_qman_arb_error_cause[GAUDI_NUM_OF_QM_ARB_ERR_CAUSE] = {"MSG AXI LBW returned with error" }; +enum gaudi_sm_sei_cause { +GAUDI_SM_SEI_SO_OVERFLOW , +GAUDI_SM_SEI_LBW_4B_UNALIGNED , +GAUDI_SM_SEI_AXI_RESPONSE_ERR +}; +static enum hl_queue_type gaudi_queue_type[GAUDI_QUEUE_ID_SIZE ] = {QUEUE_TYPE_EXT ,/* GAUDI_QUEUE_ID_DMA_0_0 */ QUEUE_TYPE_EXT ,/* GAUDI_QUEUE_ID_DMA_0_1 */
@@ -6845,6 +6851,34 @@ static void gaudi_handle_qman_err_generic(struct hl_device *hdev, } } +static void gaudi_print_sm_sei_info (struct hl_device *hdev,u16 event_type, +struct hl_eq_sm_sei_data *sei_data) +{ +u32 index = event_type -GAUDI_EVENT_DMA_IF_SEI_0 ; + +switch (sei_data->sei_cause) { +case GAUDI_SM_SEI_SO_OVERFLOW : +dev_err (hdev->dev, +"SM %u SEI Error: SO %u overflow/underflow" , + index,le16_to_cpu (sei_data->sei_log)); +break ; +case GAUDI_SM_SEI_LBW_4B_UNALIGNED : +dev_err (hdev->dev, +"SM %u SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x" , + index,le16_to_cpu (sei_data->sei_log)); +break ; +case GAUDI_SM_SEI_AXI_RESPONSE_ERR : +dev_err (hdev->dev, +"SM %u SEI Error: AXI ID %u response error" , + index,le16_to_cpu (sei_data->sei_log)); +break ; +default : +dev_err (hdev->dev,"Unknown SM SEI cause %u" , +le16_to_cpu (sei_data->sei_log)); +break ; + } +} +static void gaudi_handle_ecc_event (struct hl_device *hdev,u16 event_type,struct hl_eq_ecc_data *ecc_data) {
@@ -7468,6 +7502,13 @@ static void gaudi_handle_eqe(struct hl_device *hdev,hl_fw_unmask_irq (hdev, event_type);break ; + case GAUDI_EVENT_DMA_IF_SEI_0 ... GAUDI_EVENT_DMA_IF_SEI_3: +gaudi_print_irq_info (hdev, event_type, false); +gaudi_print_sm_sei_info (hdev, event_type, + &eq_entry->sm_sei_data); +hl_fw_unmask_irq (hdev, event_type); +break ; + case GAUDI_EVENT_FIX_POWER_ENV_S ... GAUDI_EVENT_FIX_THERMAL_ENV_E:gaudi_print_clk_change_info (hdev, event_type);hl_fw_unmask_irq (hdev, event_type);
drivers/misc/habanalabs/include/common/cpucp_if.h +7 -0
@@ -58,11 +58,18 @@ struct hl_eq_ecc_data {__u8 pad[7 ]; }; +struct hl_eq_sm_sei_data { +__le16 sei_log; +__u8 sei_cause; +__u8 pad[5 ]; +}; +struct hl_eq_entry {struct hl_eq_header hdr;union {struct hl_eq_ecc_data ecc_data;struct hl_eq_hbm_ecc_data hbm_ecc_data; +struct hl_eq_sm_sei_data sm_sei_data;__le64 data[7 ]; }; };
drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h +4 -0
@@ -212,6 +212,10 @@ enum gaudi_async_event_id {GAUDI_EVENT_NIC_SEI_2 =266 ,GAUDI_EVENT_NIC_SEI_3 =267 ,GAUDI_EVENT_NIC_SEI_4 =268 , +GAUDI_EVENT_DMA_IF_SEI_0 =277 , +GAUDI_EVENT_DMA_IF_SEI_1 =278 , +GAUDI_EVENT_DMA_IF_SEI_2 =279 , +GAUDI_EVENT_DMA_IF_SEI_3 =280 ,GAUDI_EVENT_PCIE_FLR =290 ,GAUDI_EVENT_TPC0_BMON_SPMU =300 , GAUDI_EVENT_TPC0_KRN_ERR = 301,
Signature · 1 line
2.25.1
PATCH 3/4 habanalabs: ignore F/W BMC errors in case no BMC present
In reply to Oded GabbayFrom: Ofir Bitton <[email protected]>
In order to support operation mode in which BMC is not active, driver must not take BMC errors into consideration.
--- drivers/misc/habanalabs/common/firmware_if.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-)
drivers/misc/habanalabs/common/firmware_if.c +9 -3
@@ -308,9 +308,15 @@ static int fw_read_errors(struct hl_device *hdev, u32 boot_err0_reg,if (err_val &CPU_BOOT_ERR0_DRAM_SKIPPED )dev_warn (hdev->dev,"Device boot warning - Skipped DRAM initialization\n" ); -if (err_val &CPU_BOOT_ERR0_BMC_WAIT_SKIPPED ) -dev_warn (hdev->dev, -"Device boot error - Skipped waiting for BMC\n" ); + +if (err_val &CPU_BOOT_ERR0_BMC_WAIT_SKIPPED ) { +if (hdev->bmc_enable) +dev_warn (hdev->dev, +"Device boot error - Skipped waiting for BMC\n" ); +else + err_val &= ~CPU_BOOT_ERR0_BMC_WAIT_SKIPPED ; + } +if (err_val &CPU_BOOT_ERR0_NIC_DATA_NOT_RDY )dev_err (hdev->dev,"Device boot error - Serdes data from BMC not available\n" );
Signature · 1 line
2.25.1
PATCH 4/4 habanalabs: add security violations dump to debugfs
In reply to Oded GabbayFrom: Ofir Bitton <[email protected]>
In order to improve driver security debuggability, we add security violations dump to debugfs.
--- .../ABI/testing/debugfs-driver-habanalabs | 8 +++++++ drivers/misc/habanalabs/common/debugfs.c | 22 +++++++++++++++++++ drivers/misc/habanalabs/common/habanalabs.h | 2 ++ drivers/misc/habanalabs/gaudi/gaudi.c | 3 ++- drivers/misc/habanalabs/gaudi/gaudiP.h | 1 + .../misc/habanalabs/gaudi/gaudi_security.c | 5 +++++ drivers/misc/habanalabs/goya/goya.c | 3 ++- drivers/misc/habanalabs/goya/goyaP.h | 1 + drivers/misc/habanalabs/goya/goya_security.c | 5 +++++ 9 files changed, 48 insertions(+), 2 deletions(-)
Documentation/ABI/testing/debugfs-driver-habanalabs +8 -0
@@ -182,3 +182,11 @@ KernelVersion: 5.6 Contact: [email protected] Description: Sets the stop-on_error option for the device engines. Value of "0" is for disable, otherwise enable. + +What: /sys/kernel/debug/habanalabs/hl<n>/dump_security_violations +Date: Jan 2021 +KernelVersion: 5.12 +Contact: [email protected] +Description: Dumps all security violations to dmesg. This will also ack + all security violations meanings those violations will not be + dumped next time user calls this API
drivers/misc/habanalabs/common/debugfs.c +22 -0
@@ -867,6 +867,17 @@ static ssize_t hl_stop_on_err_write(struct file *f, const char __user *buf,return count; } +static ssize_t hl_security_violations_read (struct file *f,char __user *buf, +size_t count,loff_t *ppos) +{ +struct hl_dbg_device_entry *entry =file_inode (f)->i_private; +struct hl_device *hdev = entry->hdev; + + hdev->asic_funcs->ack_protection_bits_errors (hdev); + +return 0 ; +} +static const struct file_operations hl_data32b_fops = { .owner =THIS_MODULE , .read = hl_data_read32,
@@ -924,6 +935,11 @@ static const struct file_operations hl_stop_on_err_fops = { .write = hl_stop_on_err_write }; +static const struct file_operations hl_security_violations_fops = { + .owner =THIS_MODULE , + .read = hl_security_violations_read +}; +static const struct hl_info_list hl_debugfs_list[] = { {"command_buffers" , command_buffers_show,NULL }, {"command_submission" , command_submission_show,NULL },
@@ -1073,6 +1089,12 @@ void hl_debugfs_add_device(struct hl_device *hdev) dev_entry, &hl_stop_on_err_fops); +debugfs_create_file ("dump_security_violations" , +0644 , + dev_entry->root, + dev_entry, + &hl_security_violations_fops); +for (i =0 , entry = dev_entry->entry_arr ; i < count ; i++, entry++) { ent = debugfs_create_file(hl_debugfs_list[i].name,
drivers/misc/habanalabs/common/habanalabs.h +2 -0
@@ -850,6 +850,7 @@ enum div_select_defs {* @collective_wait_create_jobs: allocate collective wait cs jobs * @scramble_vaddr: Routine to scramble the virtual address prior of mapping it * in the MMU. +* @ack_protection_bits_errors: ack and dump all security violations */ struct hl_asic_funcs {int (*early_init)(struct hl_device *hdev);
@@ -960,6 +961,7 @@ struct hl_asic_funcs { struct hl_ctx *ctx, struct hl_cs *cs, u32 wait_queue_id, u32 collective_engine_id);u64 (*scramble_vaddr)(struct hl_device *hdev,u64 virt_addr); +void (*ack_protection_bits_errors)(struct hl_device *hdev); };
drivers/misc/habanalabs/gaudi/gaudi.c +2 -1
@@ -8545,7 +8545,8 @@ static const struct hl_asic_funcs gaudi_funcs = { .get_device_time = gaudi_get_device_time, .collective_wait_init_cs = gaudi_collective_wait_init_cs, .collective_wait_create_jobs = gaudi_collective_wait_create_jobs, - .scramble_vaddr = hl_mmu_scramble_vaddr + .scramble_vaddr = hl_mmu_scramble_vaddr, + .ack_protection_bits_errors = gaudi_ack_protection_bits_errors };/**
drivers/misc/habanalabs/gaudi/gaudiP.h +1 -0
@@ -335,6 +335,7 @@ struct gaudi_device { };void gaudi_init_security (struct hl_device *hdev); +void gaudi_ack_protection_bits_errors (struct hl_device *hdev);void gaudi_add_device_attr (struct hl_device *hdev,struct attribute_group *dev_attr_grp);void gaudi_set_pll_profile (struct hl_device *hdev,enum hl_pll_frequency freq);
drivers/misc/habanalabs/gaudi/gaudi_security.c +5 -0
@@ -13052,3 +13052,8 @@ void gaudi_init_security(struct hl_device *hdev)gaudi_init_protection_bits (hdev); } + +void gaudi_ack_protection_bits_errors (struct hl_device *hdev) +{ + +}
drivers/misc/habanalabs/goya/goya.c +2 -1
@@ -5456,7 +5456,8 @@ static const struct hl_asic_funcs goya_funcs = { .get_device_time = goya_get_device_time, .collective_wait_init_cs = goya_collective_wait_init_cs, .collective_wait_create_jobs = goya_collective_wait_create_jobs, - .scramble_vaddr = hl_mmu_scramble_vaddr + .scramble_vaddr = hl_mmu_scramble_vaddr, + .ack_protection_bits_errors = goya_ack_protection_bits_errors };/*
drivers/misc/habanalabs/goya/goyaP.h +1 -0
@@ -173,6 +173,7 @@ void goya_init_mme_qmans(struct hl_device *hdev);void goya_init_tpc_qmans (struct hl_device *hdev);int goya_init_cpu_queues (struct hl_device *hdev);void goya_init_security (struct hl_device *hdev); +void goya_ack_protection_bits_errors (struct hl_device *hdev);int goya_late_init (struct hl_device *hdev);void goya_late_fini (struct hl_device *hdev);
drivers/misc/habanalabs/goya/goya_security.c +5 -0
@@ -3120,3 +3120,8 @@ void goya_init_security(struct hl_device *hdev)goya_init_protection_bits (hdev); } + +void goya_ack_protection_bits_errors (struct hl_device *hdev) +{ + +}
Signature · 1 line
2.25.1